WO2019200564A1 - Method for evaluating localization system of autonomous driving vehicles - Google Patents
Method for evaluating localization system of autonomous driving vehicles Download PDFInfo
- Publication number
- WO2019200564A1 WO2019200564A1 PCT/CN2018/083558 CN2018083558W WO2019200564A1 WO 2019200564 A1 WO2019200564 A1 WO 2019200564A1 CN 2018083558 W CN2018083558 W CN 2018083558W WO 2019200564 A1 WO2019200564 A1 WO 2019200564A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- localization
- curve
- adv
- path
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C25/00—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
Definitions
- Embodiments of the present disclosure relate generally to operating autonomous vehicles. More particularly, embodiments of the disclosure relate to localization processes of autonomous driving.
- Vehicles operating in an autonomous mode can relieve occupants, especially the driver, from some driving-related responsibilities.
- the vehicle can navigate to various locations using onboard sensors, allowing the vehicle to travel with minimal human interaction or in some cases without any passengers.
- Motion planning and control are critical operations in autonomous driving.
- the precision of planning a path to control an autonomous driving vehicle (ADV) relies on the prevision of the localization processes that determine the locations of the ADV along the path. Thus, it is important to determine the quality and any system delay of the localization system of the ADV.
- ADV autonomous driving vehicle
- Embodiments of the present disclosure provide a computer-implemented method for determining a system delay of localization of autonomous driving vehicles, a non-transitory machine-readable medium and data processing system.
- the computer-implemented method for determining a system delay of localization of autonomous driving vehicles includes: receiving first localization data of a first localization performed by a first localization system of an autonomous driving vehicle (ADV) driving along a path; receiving second localization data of a second localization performed by a second localization system of the ADV along the path, wherein the first localization and the second localization are performed concurrently on the ADV; generating a first localization curve based on the first localization data representing locations of the ADV along the path tracked by the first localization system; generating a second localization curve based on the second localization data representing the locations of the ADV along the path tracked by the second localization system; and determining a system delay of the second localization system by comparing the second localization curve against the first localization curve as a localization reference, wherein the system delay of the second localization system is utilized to compensate planning of a path to drive the ADV subsequently.
- ADV autonomous driving vehicle
- the non-transitory machine-readable medium has instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations include: receiving first localization data of a first localization performed by a first localization system of an autonomous driving vehicle (ADV) driving along a path; receiving second localization data of a second localization performed by a second localization system of the ADV along the path, wherein the first localization and the second localization are performed concurrently on the ADV; generating a first localization curve based on the first localization data representing locations of the ADV along the path tracked by the first localization system; generating a second localization curve based on the second localization data representing the locations of the ADV along the path tracked by the second localization system; and determining a system delay of the second localization system by comparing the second localization curve against the first localization curve as a localization reference, wherein the system delay of the second localization system is utilized to compensate planning of a path to drive the ADV subsequently.
- ADV autonomous driving vehicle
- the data processing system includes a processor; and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations.
- the operations include: receiving first localization data of a first localization performed by a first localization system of an autonomous driving vehicle (ADV) driving along a path, receiving second localization data of a second localization performed by a second localization system of the ADV along the path, wherein the first localization and the second localization are performed concurrently on the ADV, generating a first localization curve based on the first localization data representing locations of the ADV along the path tracked by the first localization system, generating a second localization curve based on the second localization data representing the locations of the ADV along the path tracked by the second localization system, and determining a system delay of the second localization system by comparing the second localization curve against the first localization curve as a localization reference, wherein the system delay of the second localization system is utilized to compensate planning of a path to drive the ADV
- ADV autonomous driving
- Figure 1 is a block diagram illustrating a networked system according to one embodiment.
- Figure 2 is a block diagram illustrating an example of an autonomous vehicle according to one embodiment.
- Figures 3A-3B are block diagrams illustrating an example of a perception and planning system used with an autonomous vehicle according to one embodiment.
- Figure 4 is a block diagram illustrating an example of a localization evaluation system according to one embodiment.
- Figures 5A and 5B are diagrams illustrating examples of localization curves for localization evaluation according to one embodiment.
- Figure 6 is a flow diagram illustrating a process of evaluating localization according to one embodiment.
- Figure 7 is a block diagram illustrating a data processing system according to one embodiment.
- an ADV in order to evaluate a localization system of an ADV, an ADV is equipped with two localization systems: 1) a known localization system with a set of known sensors and 2) a target localization system that will be eventually deployed in the ADV for normal driving.
- the known localization system refers to a localization system with known performance and precision, which is usually implemented using higher precision devices and/or sensors.
- the target localization system is specifically designed for the ADV or a particular type of ADVs, which typically may have unknown quality and behaviors and may be implemented using lower performance or precision devices.
- the ADV equipped with two localization systems then drives through a predetermined path, while both localization systems are configured to concurrently determine and track the locations of the ADV along the path. The locations determined by both localization systems are recorded and stored in a persistent storage device.
- an evaluation process is performed on the captured localization data to determine the quality and/or system delay of the target localization system, for example, by comparing the localization data of the known (or reference) localization system and the localization data of the target (or unknown) localization system.
- a localization curve is generated for each of the localization systems, where the localization curve represents the locations along the path the ADV has driven and captured by a localization system.
- the localization curve of the known localization system is utilized as a reference localization curve because it was produced by a known localization system.
- the localization curve of the target localization system represents a target localization curve that is to be evaluated.
- One of the localization curves is shifted back and forth in time and a similarity score representing the similarity in shape between the reference localization curve and the target localization curve is calculated.
- the similarity score reaches maximum, the corresponding shifted time represents the system delay of the target localization system, while the similarity score represents the quality of the target localization system.
- an ADV is equipped with two localization systems, one is known (e.g., reference) and one is unknown (e.g., target) and the ADV is configured to drive through a predetermined path.
- a first localization system e.g., reference localization system
- a first localization curve is generated as a result representing the locations of the ADV along the path tracked by the first localization system.
- a second localization system performs a second localization using a second set of sensors to track the locations of the ADV along the path.
- a second localization curve is generated as a result representing the locations of the ADV along the path tracked by the second localization system.
- a system delay of the second localization system is determined by comparing the second localization curve against the first localization curve as a localization reference. The system delay of the second localization system can then be utilized to compensate path planning of the ADV subsequently.
- a similarity score is calculated to represent the similarity in shape between two localization curves.
- a similarity score is calculated for that particular shifted time.
- Such a process is repeatedly performed for a number of shifted time intervals and a similarity score is calculated for each of the shifted time intervals.
- the similarity scores of all shifted time intervals are examined to identify the highest similarity score that indicates the two localization curves are most similar to each other at the corresponding shifted time interval.
- the shifted time interval with the highest similarity score can be designated as the system delay for the second localization system, while the similarity score itself can be used to represent the quality of the localization system.
- a correlation coefficient between the two localization curves is calculated to represent the similarity between the two localization curves, which is also used to represent the quality of the second localization system.
- FIG. 1 is a block diagram illustrating an autonomous vehicle network configuration according to one embodiment of the disclosure.
- network configuration 100 includes autonomous vehicle 101 that may be communicatively coupled to one or more servers 103-104 over a network 102. Although there is one autonomous vehicle shown, multiple autonomous vehicles can be coupled to each other and/or coupled to servers 103-104 over network 102.
- Network 102 may be any type of networks such as a local area network (LAN) , a wide area network (WAN) such as the Internet, a cellular network, a satellite network, or a combination thereof, wired or wireless.
- Server (s) 103-104 may be any kind of servers or a cluster of servers, such as Web or cloud servers, application servers, backend servers, or a combination thereof.
- Servers 103-104 may be data analytics servers, content servers, traffic information servers, map and point of interest (MPOI) severs, or location servers, etc.
- MPOI map and point of interest
- An autonomous vehicle refers to a vehicle that can be configured to in an autonomous mode in which the vehicle navigates through an environment with little or no input from a driver.
- Such an autonomous vehicle can include a sensor system having one or more sensors that are configured to detect information about the environment in which the vehicle operates. The vehicle and its associated controller (s) use the detected information to navigate through the environment.
- Autonomous vehicle 101 can operate in a manual mode, a full autonomous mode, or a partial autonomous mode.
- autonomous vehicle 101 includes, but is not limited to, perception and planning system 110, vehicle control system 111, wireless communication system 112, user interface system 113, infotainment system 114, and sensor system 115.
- Autonomous vehicle 101 may further include certain common components included in ordinary vehicles, such as, an engine, wheels, steering wheel, transmission, etc., which may be controlled by vehicle control system 111 and/or perception and planning system 110 using a variety of communication signals and/or commands, such as, for example, acceleration signals or commands, deceleration signals or commands, steering signals or commands, braking signals or commands, etc.
- Components 110-115 may be communicatively coupled to each other via an interconnect, a bus, a network, or a combination thereof.
- components 110-115 may be communicatively coupled to each other via a controller area network (CAN) bus.
- CAN controller area network
- a CAN bus is a vehicle bus standard designed to allow microcontrollers and devices to communicate with each other in applications without a host computer. It is a message-based protocol, designed originally for multiplex electrical wiring within automobiles, but is also used in many other contexts.
- sensor system 115 includes, but it is not limited to, one or more cameras 211, global positioning system (GPS) unit 212, inertial measurement unit (IMU) 213, radar unit 214, and a light detection and range (LIDAR) unit 215.
- GPS system 212 may include a transceiver operable to provide information regarding the position of the autonomous vehicle.
- IMU unit 213 may sense position and orientation changes of the autonomous vehicle based on inertial acceleration.
- Radar unit 214 may represent a system that utilizes radio signals to sense objects within the local environment of the autonomous vehicle. In some embodiments, in addition to sensing objects, radar unit 214 may additionally sense the speed and/or heading of the objects.
- LIDAR unit 215 may sense objects in the environment in which the autonomous vehicle is located using lasers.
- LIDAR unit 215 could include one or more laser sources, a laser scanner, and one or more detectors, among other system components.
- Cameras 211 may include one or more devices to capture images of the environment surrounding the autonomous vehicle. Cameras 211 may be still cameras and/or video cameras. A camera may be mechanically movable, for example, by mounting the camera on a rotating and/or tilting a platform.
- Sensor system 115 may further include other sensors, such as, a sonar sensor, an infrared sensor, a steering sensor, a throttle sensor, a braking sensor, and an audio sensor (e.g., microphone) .
- An audio sensor may be configured to capture sound from the environment surrounding the autonomous vehicle.
- a steering sensor may be configured to sense the steering angle of a steering wheel, wheels of the vehicle, or a combination thereof.
- a throttle sensor and a braking sensor sense the throttle position and braking position of the vehicle, respectively. In some situations, a throttle sensor and a braking sensor may be integrated as an integrated throttle/braking sensor.
- vehicle control system 111 includes, but is not limited to, steering unit 201, throttle unit 202 (also referred to as an acceleration unit) , and braking unit 203.
- Steering unit 201 is to adjust the direction or heading of the vehicle.
- Throttle unit 202 is to control the speed of the motor or engine that in turn control the speed and acceleration of the vehicle.
- Braking unit 203 is to decelerate the vehicle by providing friction to slow the wheels or tires of the vehicle. Note that the components as shown in Figure 2 may be implemented in hardware, software, or a combination thereof.
- wireless communication system 112 is to allow communication between autonomous vehicle 101 and external systems, such as devices, sensors, other vehicles, etc.
- wireless communication system 112 can wirelessly communicate with one or more devices directly or via a communication network, such as servers 103-104 over network 102.
- Wireless communication system 112 can use any cellular communication network or a wireless local area network (WLAN) , e.g., using WiFi to communicate with another component or system.
- Wireless communication system 112 could communicate directly with a device (e.g., a mobile device of a passenger, a display device, a speaker within vehicle 101) , for example, using an infrared link, Bluetooth, etc.
- User interface system 113 may be part of peripheral devices implemented within vehicle 101 including, for example, a keyword, a touch screen display device, a microphone, and a speaker, etc.
- Perception and planning system 110 includes the necessary hardware (e.g., processor (s) , memory, storage) and software (e.g., operating system, planning and routing programs) to receive information from sensor system 115, control system 111, wireless communication system 112, and/or user interface system 113, process the received information, plan a route or path from a starting point to a destination point, and then drive vehicle 101 based on the planning and control information.
- Perception and planning system 110 may be integrated with vehicle control system 111.
- Perception and planning system 110 obtains the trip related data.
- perception and planning system 110 may obtain location and route information from an MPOI server, which may be a part of servers 103-104.
- the location server provides location services and the MPOI server provides map services and the POIs of certain locations.
- such location and MPOI information may be cached locally in a persistent storage device of perception and planning system 110.
- perception and planning system 110 may also obtain real-time traffic information from a traffic information system or server (TIS) .
- TIS traffic information system
- servers 103-104 may be operated by a third party entity. Alternatively, the functionalities of servers 103-104 may be integrated with perception and planning system 110.
- MPOI information MPOI information
- location information e.g., obstacles, objects, nearby vehicles
- perception and planning system 110 can plan an optimal route and drive vehicle 101, for example, via control system 111, according to the planned route to reach the specified destination safely and efficiently.
- Server 103 may be a data analytics system to perform data analytics services for a variety of clients.
- data analytics system 103 includes data collector 121 and machine learning engine 122.
- Data collector 121 collects driving statistics 123 from a variety of vehicles, either autonomous vehicles or regular vehicles driven by human drivers.
- Driving statistics 123 include information indicating the driving commands (e.g., throttle, brake, steering commands) issued and responses of the vehicles (e.g., speeds, accelerations, decelerations, directions) captured by sensors of the vehicles at different points in time.
- Driving statistics 123 may further include information describing the driving environments at different points in time, such as, for example, routes (including starting and destination locations) , MPOIs, road conditions, weather conditions, etc.
- machine learning engine 122 Based on driving statistics 123, machine learning engine 122 generates or trains a set of rules, algorithms, and/or predictive models 124 for a variety of purposes.
- algorithms 124 include one or more algorithms to evaluate a localization system to determine the performance or quality of the localization system and the system delay of the localization system. Such algorithms may be utilized by localization evaluation system 125 based on the localization data collected from ADVs, for example, by determining the system delay and the similarity score of the localization system in view of a localization system reference.
- FIGS 3A and 3B are block diagrams illustrating an example of a perception and planning system used with an autonomous vehicle according to one embodiment.
- System 300 may be implemented as a part of autonomous vehicle 101 of Figure 1 including, but is not limited to, perception and planning system 110, control system 111, and sensor system 115.
- perception and planning system 110 includes, but is not limited to, localization module 301, perception module 302, prediction module 303, decision module 304, planning module 305, control module 306, routing module 307, and localization evaluation system 308.
- modules 301-308 may be implemented in software, hardware, or a combination thereof. For example, these modules may be installed in persistent storage device 352, loaded into memory 351, and executed by one or more processors (not shown) . Note that some or all of these modules may be communicatively coupled to or integrated with some or all modules of vehicle control system 111 of Figure 2. Some of modules 301-308 may be integrated together as an integrated module.
- Localization module 301 determines a current location of autonomous vehicle 300 (e.g., leveraging GPS unit 212) and manages any data related to a trip or route of a user.
- Localization module 301 (also referred to as a map and route module) manages any data related to a trip or route of a user.
- a user may log in and specify a starting location and a destination of a trip, for example, via a user interface.
- Localization module 301 communicates with other components of autonomous vehicle 300, such as map and route information 311, to obtain the trip related data.
- localization module 301 may obtain location and route information from a location server and a map and POI (MPOI) server.
- MPOI map and POI
- a location server provides location services and an MPOI server provides map services and the POIs of certain locations, which may be cached as part of map and route information 311. While autonomous vehicle 300 is moving along the route, localization module 301 may also obtain real-time traffic information from a traffic information system or server.
- a perception of the surrounding environment is determined by perception module 302.
- the perception information may represent what an ordinary driver would perceive surrounding a vehicle in which the driver is driving.
- the perception can include the lane configuration (e.g., straight or curve lanes) , traffic light signals, a relative position of another vehicle, a pedestrian, a building, crosswalk, or other traffic related signs (e.g., stop signs, yield signs) , etc., for example, in a form of an object.
- Perception module 302 may include a computer vision system or functionalities of a computer vision system to process and analyze images captured by one or more cameras in order to identify objects and/or features in the environment of autonomous vehicle.
- the objects can include traffic signals, road way boundaries, other vehicles, pedestrians, and/or obstacles, etc.
- the computer vision system may use an object recognition algorithm, video tracking, and other computer vision techniques.
- the computer vision system can map an environment, track objects, and estimate the speed of objects, etc.
- Perception module 302 can also detect objects based on other sensors data provided by other sensors such as a radar and/or LIDAR.
- prediction module 303 predicts what the object will behave under the circumstances. The prediction is performed based on the perception data perceiving the driving environment at the point in time in view of a set of map/rout information 311 and traffic rules 312. For example, if the object is a vehicle at an opposing direction and the current driving environment includes an intersection, prediction module 303 will predict whether the vehicle will likely move straight forward or make a turn. If the perception data indicates that the intersection has no traffic light, prediction module 303 may predict that the vehicle may have to fully stop prior to enter the intersection. If the perception data indicates that the vehicle is currently at a left-turn only lane or a right-turn only lane, prediction module 303 may predict that the vehicle will more likely make a left turn or right turn respectively.
- decision module 304 makes a decision regarding how to handle the object. For example, for a particular object (e.g., another vehicle in a crossing route) as well as its metadata describing the object (e.g., a speed, direction, turning angle) , decision module 304 decides how to encounter the object (e.g., overtake, yield, stop, pass) . Decision module 304 may make such decisions according to a set of rules such as traffic rules or driving rules 312, which may be stored in persistent storage device 352.
- rules such as traffic rules or driving rules 312, which may be stored in persistent storage device 352.
- Routing module 307 is configured to provide one or more routes or paths from a starting point to a destination point. For a given trip from a start location to a destination location, for example, received from a user, routing module 307 obtains route and map information 311 and determines all possible routes or paths from the starting location to reach the destination location. Routing module 307 may generate a reference line in a form of a topographic map for each of the routes it determines from the starting location to reach the destination location. A reference line refers to an ideal route or path without any interference from others such as other vehicles, obstacles, or traffic condition. That is, if there is no other vehicle, pedestrians, or obstacles on the road, an ADV should exactly or closely follows the reference line.
- the topographic maps are then provided to decision module 304 and/or planning module 305.
- Decision module 304 and/or planning module 305 examine all of the possible routes to select and modify one of the most optimal route in view of other data provided by other modules such as traffic conditions from localization module 301, driving environment perceived by perception module 302, and traffic condition predicted by prediction module 303.
- the actual path or route for controlling the ADV may be close to or different from the reference line provided by routing module 307 dependent upon the specific driving environment at the point in time.
- planning module 305 plans a path or route for the autonomous vehicle, as well as driving parameters (e.g., distance, speed, and/or turning angle) , using a reference line provided by routing module 307 as a basis. That is, for a given object, decision module 304 decides what to do with the object, while planning module 305 determines how to do it. For example, for a given object, decision module 304 may decide to pass the object, while planning module 305 may determine whether to pass on the left side or right side of the object. Planning and control data is generated by planning module 305 including information describing how vehicle 300 would move in a next moving cycle (e.g., next route/path segment) . For example, the planning and control data may instruct vehicle 300 to move 10 meters at a speed of 30 mile per hour (mph) , then change to a right lane at the speed of 25 mph.
- driving parameters e.g., distance, speed, and/or turning angle
- control module 306 controls and drives the autonomous vehicle, by sending proper commands or signals to vehicle control system 111, according to a route or path defined by the planning and control data.
- the planning and control data include sufficient information to drive the vehicle from a first point to a second point of a route or path using appropriate vehicle settings or driving parameters (e.g., throttle, braking, steering commands) at different points in time along the path or route.
- the planning phase is performed in a number of planning cycles, also referred to as driving cycles, such as, for example, in every time interval of 100 milliseconds (ms) .
- driving cycles such as, for example, in every time interval of 100 milliseconds (ms) .
- one or more control commands will be issued based on the planning and control data. That is, for every 100 ms, planning module 305 plans a next route segment or path segment, for example, including a target position and the time required for the ADV to reach the target position. Alternatively, planning module 305 may further specify the specific speed, direction, and/or steering angle, etc. In one embodiment, planning module 305 plans a route segment or path segment for the next predetermined period of time such as 5 seconds.
- planning module 305 plans a target position for the current cycle (e.g., next 5 seconds) based on a target position planned in a previous cycle.
- Control module 306 then generates one or more control commands (e.g., throttle, brake, steering control commands) based on the planning and control data of the current cycle.
- control commands e.g., throttle, brake, steering control commands
- Decision module 304 and planning module 305 may be integrated as an integrated module.
- Decision module 304/planning module 305 may include a navigation system or functionalities of a navigation system to determine a driving path for the autonomous vehicle.
- the navigation system may determine a series of speeds and directional headings to affect movement of the autonomous vehicle along a path that substantially avoids perceived obstacles while generally advancing the autonomous vehicle along a roadway-based path leading to an ultimate destination.
- the destination may be set according to user inputs via user interface system 113.
- the navigation system may update the driving path dynamically while the autonomous vehicle is in operation.
- the navigation system can incorporate data from a GPS system and one or more maps so as to determine the driving path for the autonomous vehicle.
- ADV 300 can be utilized to evaluate the performance of a localization system to be deployed on ADV 300.
- localization module 301 in order to evaluate the performance of the localization system, in this example, localization module 301 as a target localization system, another localization system, i.e., a known localization system referred to herein as a reference localization system, is also utilized on ADV 300.
- ADV 300 equipped with a target localization system and a reference localization system, is configured to drive through a predetermined path or route, while both localization systems concurrently track and capture the localization data such as locations of ADV 300 along the path and generate the respective localization data.
- the reference localization data generated by the reference localization system is stored in persistent storage device 352 as a part of reference localization data 313.
- the target localization data generated by the target localization system is stored as a part of target localization data 314.
- Localization evaluation module 308 is configured to analyze the localization data 313-314 to determine the performance and the system delay of the target localization system, for example, by comparing reference localization data 313 with target localization data 314.
- the collected localization data 313-314 can be analyzed offline, for example, by localization evaluation system 125 of server 103.
- FIG 4 is a block diagram illustrating a localization evaluation system according to one embodiment.
- localization module 301 includes a reference localization module 401 and a target localization module 402.
- Reference localization module 401 is considered as a trusted or known localization module that produces known localization quality with known or no system delay.
- Target localization module 402 is a localization module that will be or has been deployed in the ADVs for normal operations.
- Reference localization module 401 is utilized only for the purpose of evaluating the performance of target localization module 402.
- reference localization module 401 is associated with a set of known sensors, referred to herein as reference sensor system 115A, while target localization module 402 is associated with a set of target sensors, referred to herein as target sensor system 115B.
- Target sensor system 115B will be deployed on the ADVs during normal operations or mass production of ADVs.
- the ADV is configured to drive according to a predetermined path or route, during which both localization modules 401-402 concurrently perform localization using sensor systems 115A-115B and generate localization data 313-314 respectively.
- Reference localization data 313 includes information recording the locations of the ADV along the path captured by reference localization module 401 via sensor system 115A.
- Target localization data 314 includes information recording the locations of the ADV along the path captured by target localization module 402.
- Reference localization data 313 and target localization data 314 are then analyzed by localization evaluation module or system 410.
- the localization evaluation module 410 may be implemented as a part of localization evaluation system 125 of Figure 1 or localization evaluation module 308 of Figure 3A.
- localization evaluation module 410 examines reference localization data 313 to generate a reference localization curve (also referred to as a localization graph) .
- the localization evaluation module 410 examines target localization data 314 to generate a target localization curve.
- a localization curve includes a number of points and each point represents a particular location of the ADV at a particular point in time.
- the localization evaluation module 410 compares the reference localization curve and the target localization curve to determine the similarity between two localization curves and the system delay of the target localization module 402.
- the localization evaluation module 410 shifts in time one of the localization curves against the other.
- the localization evaluation module 410 compares the shifted curves to determine the similarity in shape between two curves within a predetermined time window.
- the above process is iteratively performed to shift one localization curve back and forth in time with respect to the other localization curve, and the similarity between two curves within the time window is determine for the corresponding shifted time interval.
- the corresponding shifted time interval is considered as the system delay of the target localization module 402.
- the level or similarity score of the highest similarity is utilized to represent the quality of localization module 402, i.e., how similar or close localization module 402 has performed in view of the reference localization module 401 as a known localization standard.
- reference localization curve 501 is generated based on reference localization data 313 and target localization curve 502 is generated based on target localization data 314.
- one of the localization curves 501-502 is shifted in time back and forth for a number of time intervals. For each shifted time interval, a similarity score between the reference localization curve 501 and target localization curve 502 is calculated within a predetermined time window.
- reference localization curve 501 is shifted back and forth while target localization curve 502 remains steady for a number of time intervals (e.g., -0.3 seconds (s) , -0.2s, -0.1s, 0, 0.1s, 0.2s, 0.3s) .
- a predetermined time interval has been selected as 0.1s, but it can be other time interval values.
- Curve 501A has been shifted backwardly by 0.2s; curve 501B has been shifted backwardly by 0.1 s; curve 501C has been shifted forwardly by 0.1s; and curve 501D has been shifted forwardly by 0.2s.
- a similarity score is calculated to represent the similarity between reference localization curve 501 and target localization curve 502.
- a similarity score is calculated for each of the localization curves 501 and 501A-501D within the time window.
- a higher similarity score indicates that reference localization curve 501 and target localization curve 502 within the same time window are more similar.
- a shifted time interval corresponding to the highest similarity scores is designated as the system delay of the target localization system. The highest similarity score can be used to measure the quality of the target localization system.
- a correlation coefficient is calculated between each of the reference localization curves 501 and 501A-501D and target localization curve 502 to represent the level of similarity between the two localization curves.
- a correlation coefficient is a numerical measure of some type of correlation, meaning a statistical relationship between two variables.
- the variables may be two columns of a given data set of observations, often called a sample, or two components of a multivariate random variable with a known distribution.
- correlation coefficients present certain problems, including the propensity of some types to be distorted by outliers and the possibility of incorrectly being used to infer a causal relationship between the variables.
- FIG. 6 is a flow diagram illustrating an example of a process of evaluating a localization system of an autonomous driving vehicle according to one embodiment.
- Process 600 can be performed by processing logic which may include software, hardware, or a combination thereof.
- processing logic may be performed by localization evaluation system 125 or localization evaluation module 308.
- processing logic receives first localization data of a first localization performed by a first localization system of an ADV driving along a path.
- processing logic receives second localization data of a second localization performed by a second localization system of the ADV along the path. The first localization and the second localization are performed concurrently on the ADV.
- processing logic In operation 603, processing logic generates a first localization curve based on the first localization data representing locations of the ADV along the path tracked by the first localization system. In operation 604, processing logic generates a second localization curve based on the second localization data representing the locations of the ADV along the path tracked by the second localization system. In operation 605, processing logic determines a system delay of the second localization system by comparing the second localization curve against the first localization curve as a localization reference. The system delay of the second localization system is utilized to compensate planning of a path to drive the ADV subsequently.
- components as shown and described above may be implemented in software, hardware, or a combination thereof.
- such components can be implemented as software installed and stored in a persistent storage device, which can be loaded and executed in a memory by a processor (not shown) to carry out the processes or operations described throughout this application.
- such components can be implemented as executable code programmed or embedded into dedicated hardware such as an integrated circuit (e.g., an application specific IC or ASIC) , a digital signal processor (DSP) , or a field programmable gate array (FPGA) , which can be accessed via a corresponding driver and/or operating system from an application.
- an integrated circuit e.g., an application specific IC or ASIC
- DSP digital signal processor
- FPGA field programmable gate array
- such components can be implemented as specific hardware logic in a processor or processor core as part of an instruction set accessible by a software component via one or more specific instructions.
- FIG. 7 is a block diagram illustrating an example of a data processing system which may be used with one embodiment of the disclosure.
- system 1500 may represent any of data processing systems described above performing any of the processes or methods described above, such as, for example, perception and planning system 110 or any of servers 103-104 of Figure 1.
- System 1500 can include many different components. These components can be implemented as integrated circuits (ICs) , portions thereof, discrete electronic devices, or other modules adapted to a circuit board such as a motherboard or add-in card of the computer system, or as components otherwise incorporated within a chassis of the computer system.
- ICs integrated circuits
- System 1500 is intended to show a high level view of many components of the computer system. However, it is to be understood that additional components may be present in certain implementations and furthermore, different arrangement of the components shown may occur in other implementations.
- System 1500 may represent a desktop, a laptop, a tablet, a server, a mobile phone, a media player, a personal digital assistant (PDA) , a Smartwatch, a personal communicator, a gaming device, a network router or hub, a wireless access point (AP) or repeater, a set-top box, or a combination thereof.
- PDA personal digital assistant
- AP wireless access point
- system 1500 shall also be taken to include any collection of machines or systems that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.
- system 1500 includes processor 1501, memory 1503, and devices 1505-1508 connected via a bus or an interconnect 1510.
- Processor 1501 may represent a single processor or multiple processors with a single processor core or multiple processor cores included therein.
- Processor 1501 may represent one or more general-purpose processors such as a microprocessor, a central processing unit (CPU) , or the like. More particularly, processor 1501 may be a complex instruction set computing (CISC) microprocessor, reduced instruction set computing (RISC) microprocessor, very long instruction word (VLIW) microprocessor, or processor implementing other instruction sets, or processors implementing a combination of instruction sets.
- CISC complex instruction set computing
- RISC reduced instruction set computing
- VLIW very long instruction word
- Processor 1501 may also be one or more special-purpose processors such as an application specific integrated circuit (ASIC) , a cellular or baseband processor, a field programmable gate array (FPGA) , a digital signal processor (DSP) , a network processor, a graphics processor, a communications processor, a cryptographic processor, a co-processor, an embedded processor, or any other type of logic capable of processing instructions.
- ASIC application specific integrated circuit
- FPGA field programmable gate array
- DSP digital signal processor
- network processor a graphics processor
- communications processor a cryptographic processor
- co-processor a co-processor
- embedded processor or any other type of logic capable of processing instructions.
- Processor 1501 which may be a low power multi-core processor socket such as an ultra-low voltage processor, may act as a main processing unit and central hub for communication with the various components of the system. Such processor can be implemented as a system on chip (SoC) . Processor 1501 is configured to execute instructions for performing the operations and steps discussed herein.
- System 1500 may further include a graphics interface that communicates with optional graphics subsystem 1504, which may include a display controller, a graphics processor, and/or a display device.
- Processor 1501 may communicate with memory 1503, which in one embodiment can be implemented via multiple memory devices to provide for a given amount of system memory.
- Memory 1503 may include one or more volatile storage (or memory) devices such as random access memory (RAM) , dynamic RAM (DRAM) , synchronous DRAM (SDRAM) , static RAM (SRAM) , or other types of storage devices.
- RAM random access memory
- DRAM dynamic RAM
- SDRAM synchronous DRAM
- SRAM static RAM
- Memory 1503 may store information including sequences of instructions that are executed by processor 1501, or any other device.
- executable code and/or data of a variety of operating systems, device drivers, firmware (e.g., input output basic system or BIOS) , and/or applications can be loaded in memory 1503 and executed by processor 1501.
- An operating system can be any kind of operating systems, such as, for example, Robot Operating System (ROS) , operating system from Mac from Apple, from LINUX, UNIX, or other real-time or embedded operating systems.
- System 1500 may further include IO devices such as devices 1505-1508, including network interface device (s) 1505, optional input device (s) 1506, and other optional IO device (s) 1507.
- Network interface device 1505 may include a wireless transceiver and/or a network interface card (NIC) .
- the wireless transceiver may be a WiFi transceiver, an infrared transceiver, a Bluetooth transceiver, a WiMax transceiver, a wireless cellular telephony transceiver, a satellite transceiver (e.g., a global positioning system (GPS) transceiver) , or other radio frequency (RF) transceivers, or a combination thereof.
- the NIC may be an Ethernet card.
- Input device (s) 1506 may include a mouse, a touch pad, a touch sensitive screen (which may be integrated with display device 1504) , a pointer device such as a stylus, and/or a keyboard (e.g., physical keyboard or a virtual keyboard displayed as part of a touch sensitive screen) .
- input device 1506 may include a touch screen controller coupled to a touch screen.
- the touch screen and touch screen controller can, for example, detect contact and movement or break thereof using any of a plurality of touch sensitivity technologies, including but not limited to capacitive, resistive, infrared, and surface acoustic wave technologies, as well as other proximity sensor arrays or other elements for determining one or more points of contact with the touch screen.
- IO devices 1507 may include an audio device.
- An audio device may include a speaker and/or a microphone to facilitate voice-enabled functions, such as voice recognition, voice replication, digital recording, and/or telephony functions.
- Other IO devices 1507 may further include universal serial bus (USB) port (s) , parallel port (s) , serial port (s) , a printer, a network interface, a bus bridge (e.g., a PCI-PCI bridge) , sensor (s) (e.g., a motion sensor such as an accelerometer, gyroscope, a magnetometer, a light sensor, compass, a proximity sensor, etc. ) , or a combination thereof.
- USB universal serial bus
- s parallel port
- serial port s
- printer e.g., a printer
- network interface e.g., a PCI-PCI bridge
- sensor e.g., a motion sensor such as an accelerometer, gyro
- Devices 1507 may further include an imaging processing subsystem (e.g., a camera) , which may include an optical sensor, such as a charged coupled device (CCD) or a complementary metal-oxide semiconductor (CMOS) optical sensor, utilized to facilitate camera functions, such as recording photographs and video clips.
- an imaging processing subsystem e.g., a camera
- an optical sensor such as a charged coupled device (CCD) or a complementary metal-oxide semiconductor (CMOS) optical sensor, utilized to facilitate camera functions, such as recording photographs and video clips.
- CCD charged coupled device
- CMOS complementary metal-oxide semiconductor
- Certain sensors may be coupled to interconnect 1510 via a sensor hub (not shown) , while other devices such as a keyboard or thermal sensor may be controlled by an embedded controller (not shown) , dependent upon the specific configuration or design of system 1500.
- a mass storage may also couple to processor 1501.
- this mass storage may be implemented via a solid state device (SSD) .
- the mass storage may primarily be implemented using a hard disk drive (HDD) with a smaller amount of SSD storage to act as a SSD cache to enable non-volatile storage of context state and other such information during power down events so that a fast power up can occur on re-initiation of system activities.
- a flash device may be coupled to processor 1501, e.g., via a serial peripheral interface (SPI) . This flash device may provide for non-volatile storage of system software, including BIOS as well as other firmware of the system.
- Storage device 1508 may include computer-accessible storage medium 1509 (also known as a machine-readable storage medium or a computer-readable medium) on which is stored one or more sets of instructions or software (e.g., module, unit, and/or logic 1528) embodying any one or more of the methodologies or functions described herein.
- Processing module/unit/logic 1528 may represent any of the components described above, such as, for example, planning module 305, control module 306, localization evaluation module 308, or localization evaluation system 125.
- Processing module/unit/logic 1528 may also reside, completely or at least partially, within memory 1503 and/or within processor 1501 during execution thereof by data processing system 1500, memory 1503 and processor 1501 also constituting machine-accessible storage media.
- Processing module/unit/logic 1528 may further be transmitted or received over a network via network interface device 1505.
- Computer-readable storage medium 1509 may also be used to store the some software functionalities described above persistently. While computer-readable storage medium 1509 is shown in an exemplary embodiment to be a single medium, the term ācomputer-readable storage mediumā should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more sets of instructions. The terms ācomputer-readable storage mediumā shall also be taken to include any medium that is capable of storing or encoding a set of instructions for execution by the machine and that cause the machine to perform any one or more of the methodologies of the present disclosure. The term ācomputer-readable storage mediumā shall accordingly be taken to include, but not be limited to, solid-state memories, and optical and magnetic media, or any other non-transitory machine-readable medium.
- Processing module/unit/logic 1528, components and other features described herein can be implemented as discrete hardware components or integrated in the functionality of hardware components such as ASICS, FPGAs, DSPs or similar devices.
- processing module/unit/logic 1528 can be implemented as firmware or functional circuitry within hardware devices.
- processing module/unit/logic 1528 can be implemented in any combination hardware devices and software components.
- system 1500 is illustrated with various components of a data processing system, it is not intended to represent any particular architecture or manner of interconnecting the components; as such details are not germane to embodiments of the present disclosure. It will also be appreciated that network computers, handheld computers, mobile phones, servers, and/or other data processing systems which have fewer components or perhaps more components may also be used with embodiments of the disclosure.
- Embodiments of the disclosure also relate to an apparatus for performing the operations herein.
- a computer program is stored in a non-transitory computer readable medium.
- a machine-readable medium includes any mechanism for storing information in a form readable by a machine (e.g., a computer) .
- a machine-readable (e.g., computer-readable) medium includes a machine (e.g., a computer) readable storage medium (e.g., read only memory ( āROMā ) , random access memory ( āRAMā ) , magnetic disk storage media, optical storage media, flash memory devices) .
- processing logic that comprises hardware (e.g. circuitry, dedicated logic, etc. ) , software (e.g., embodied on a non-transitory computer readable medium) , or a combination of both.
- processing logic comprises hardware (e.g. circuitry, dedicated logic, etc. ) , software (e.g., embodied on a non-transitory computer readable medium) , or a combination of both.
- Embodiments of the present disclosure are not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of embodiments of the disclosure as described herein.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Manufacturing & Machinery (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
A first localization system (401) performs a first localization using a first set of sensors (115A) to track locations of the ADV (300) along the path from a starting point to a destination point. A first localization curve (501) is generated as a result representing the locations of the ADV (300) along the path tracked by the first localization system (401). Currently, a second localization system (402) performs a second localization using a second set of sensors (115B) to track the locations of the ADV (300) along the path. A second localization curve (502) is generated as a result representing the locations of the ADV (300) along the path tracked by the second localization system (402). A system delay of the second localization system (402) is determined by comparing the second localization curve (502) against the first localization curve (501) as a localization reference. The system delay of the second localization system (402) can then be utilized to compensate path planning of the ADV (300) subsequently.
Description
EmbodimentsĀ ofĀ theĀ presentĀ disclosureĀ relateĀ generallyĀ toĀ operatingĀ autonomousĀ vehicles.Ā MoreĀ particularly,Ā embodimentsĀ ofĀ theĀ disclosureĀ relateĀ toĀ localizationĀ processesĀ ofĀ autonomousĀ driving.
VehiclesĀ operatingĀ inĀ anĀ autonomousĀ modeĀ (e.g.,Ā driverless)Ā canĀ relieveĀ occupants,Ā especiallyĀ theĀ driver,Ā fromĀ someĀ driving-relatedĀ responsibilities.Ā WhenĀ operatingĀ inĀ anĀ autonomousĀ mode,Ā theĀ vehicleĀ canĀ navigateĀ toĀ variousĀ locationsĀ usingĀ onboardĀ sensors,Ā allowingĀ theĀ vehicleĀ toĀ travelĀ withĀ minimalĀ humanĀ interactionĀ orĀ inĀ someĀ casesĀ withoutĀ anyĀ passengers.
MotionĀ planningĀ andĀ controlĀ areĀ criticalĀ operationsĀ inĀ autonomousĀ driving.Ā TheĀ precisionĀ ofĀ planningĀ aĀ pathĀ toĀ controlĀ anĀ autonomousĀ drivingĀ vehicleĀ (ADV)Ā reliesĀ onĀ theĀ previsionĀ ofĀ theĀ localizationĀ processesĀ thatĀ determineĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ path.Ā Thus,Ā itĀ isĀ importantĀ toĀ determineĀ theĀ qualityĀ andĀ anyĀ systemĀ delayĀ ofĀ theĀ localizationĀ systemĀ ofĀ theĀ ADV.Ā However,Ā thereĀ hasĀ beenĀ aĀ lackĀ ofĀ efficientĀ wayĀ toĀ evaluateĀ aĀ localizationĀ systemĀ ofĀ anĀ ADV.
SUMMARY
EmbodimentsĀ ofĀ theĀ presentĀ disclosureĀ provideĀ aĀ computer-implementedĀ methodĀ forĀ determiningĀ aĀ systemĀ delayĀ ofĀ localizationĀ ofĀ autonomousĀ drivingĀ vehicles,Ā aĀ non-transitoryĀ machine-readableĀ mediumĀ andĀ dataĀ processingĀ system.
InĀ anĀ aspectĀ ofĀ theĀ disclosure,Ā theĀ computer-implementedĀ methodĀ forĀ determiningĀ aĀ systemĀ delayĀ ofĀ localizationĀ ofĀ autonomousĀ drivingĀ vehiclesĀ includes:Ā receivingĀ firstĀ localizationĀ dataĀ ofĀ aĀ firstĀ localizationĀ performedĀ byĀ aĀ firstĀ localizationĀ systemĀ ofĀ anĀ autonomousĀ drivingĀ vehicleĀ (ADV)Ā drivingĀ alongĀ aĀ path;Ā receivingĀ secondĀ localizationĀ dataĀ ofĀ aĀ secondĀ localizationĀ performedĀ byĀ aĀ secondĀ localizationĀ systemĀ ofĀ theĀ ADVĀ alongĀ theĀ path,Ā whereinĀ theĀ firstĀ localizationĀ andĀ theĀ secondĀ localizationĀ areĀ performedĀ concurrentlyĀ onĀ theĀ ADV;Ā generatingĀ aĀ firstĀ localizationĀ curveĀ basedĀ onĀ theĀ firstĀ localizationĀ dataĀ representingĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system;Ā generatingĀ aĀ secondĀ localizationĀ curveĀ basedĀ onĀ theĀ secondĀ localizationĀ dataĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system;Ā andĀ determiningĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference,Ā whereinĀ theĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ utilizedĀ toĀ compensateĀ planningĀ ofĀ aĀ pathĀ toĀ driveĀ theĀ ADVĀ subsequently.
InĀ anotherĀ aspectĀ ofĀ theĀ disclosure,Ā theĀ non-transitoryĀ machine-readableĀ mediumĀ hasĀ instructionsĀ storedĀ therein,Ā whichĀ whenĀ executedĀ byĀ aĀ processor,Ā causeĀ theĀ processorĀ toĀ performĀ operations,Ā theĀ operationsĀ include:Ā receivingĀ firstĀ localizationĀ dataĀ ofĀ aĀ firstĀ localizationĀ performedĀ byĀ aĀ firstĀ localizationĀ systemĀ ofĀ anĀ autonomousĀ drivingĀ vehicleĀ (ADV)Ā drivingĀ alongĀ aĀ path;Ā receivingĀ secondĀ localizationĀ dataĀ ofĀ aĀ secondĀ localizationĀ performedĀ byĀ aĀ secondĀ localizationĀ systemĀ ofĀ theĀ ADVĀ alongĀ theĀ path,Ā whereinĀ theĀ firstĀ localizationĀ andĀ theĀ secondĀ localizationĀ areĀ performedĀ concurrentlyĀ onĀ theĀ ADV;Ā generatingĀ aĀ firstĀ localizationĀ curveĀ basedĀ onĀ theĀ firstĀ localizationĀ dataĀ representingĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system;Ā generatingĀ aĀ secondĀ localizationĀ curveĀ basedĀ onĀ theĀ secondĀ localizationĀ dataĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system;Ā andĀ determiningĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference,Ā whereinĀ theĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ utilizedĀ toĀ compensateĀ planningĀ ofĀ aĀ pathĀ toĀ driveĀ theĀ ADVĀ subsequently.
InĀ aĀ furtherĀ aspectĀ ofĀ theĀ disclosure,Ā theĀ dataĀ processingĀ systemĀ includesĀ aĀ processor;Ā andĀ aĀ memoryĀ coupledĀ toĀ theĀ processorĀ toĀ storeĀ instructions,Ā whichĀ whenĀ executedĀ byĀ theĀ processor,Ā causeĀ theĀ processorĀ toĀ performĀ operations.Ā TheĀ operationsĀ include:Ā receivingĀ firstĀ localizationĀ dataĀ ofĀ aĀ firstĀ localizationĀ performedĀ byĀ aĀ firstĀ localizationĀ systemĀ ofĀ anĀ autonomousĀ drivingĀ vehicleĀ (ADV)Ā drivingĀ alongĀ aĀ path,Ā receivingĀ secondĀ localizationĀ dataĀ ofĀ aĀ secondĀ localizationĀ performedĀ byĀ aĀ secondĀ localizationĀ systemĀ ofĀ theĀ ADVĀ alongĀ theĀ path,Ā whereinĀ theĀ firstĀ localizationĀ andĀ theĀ secondĀ localizationĀ areĀ performedĀ concurrentlyĀ onĀ theĀ ADV,Ā generatingĀ aĀ firstĀ localizationĀ curveĀ basedĀ onĀ theĀ firstĀ localizationĀ dataĀ representingĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system,Ā generatingĀ aĀ secondĀ localizationĀ curveĀ basedĀ onĀ theĀ secondĀ localizationĀ dataĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system,Ā andĀ determiningĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference,Ā whereinĀ theĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ utilizedĀ toĀ compensateĀ planningĀ ofĀ aĀ pathĀ toĀ driveĀ theĀ ADVĀ subsequently.
EmbodimentsĀ ofĀ theĀ disclosureĀ areĀ illustratedĀ byĀ wayĀ ofĀ exampleĀ andĀ notĀ limitationĀ inĀ theĀ figuresĀ ofĀ theĀ accompanyingĀ drawingsĀ inĀ whichĀ likeĀ referencesĀ indicateĀ similarĀ elements.
FigureĀ 1Ā isĀ aĀ blockĀ diagramĀ illustratingĀ aĀ networkedĀ systemĀ accordingĀ toĀ oneĀ embodiment.
FigureĀ 2Ā isĀ aĀ blockĀ diagramĀ illustratingĀ anĀ exampleĀ ofĀ anĀ autonomousĀ vehicleĀ accordingĀ toĀ oneĀ embodiment.
FiguresĀ 3A-3BĀ areĀ blockĀ diagramsĀ illustratingĀ anĀ exampleĀ ofĀ aĀ perceptionĀ andĀ planningĀ systemĀ usedĀ withĀ anĀ autonomousĀ vehicleĀ accordingĀ toĀ oneĀ embodiment.
FigureĀ 4Ā isĀ aĀ blockĀ diagramĀ illustratingĀ anĀ exampleĀ ofĀ aĀ localizationĀ evaluationĀ systemĀ accordingĀ toĀ oneĀ embodiment.
FiguresĀ 5AĀ andĀ 5BĀ areĀ diagramsĀ illustratingĀ examplesĀ ofĀ localizationĀ curvesĀ forĀ localizationĀ evaluationĀ accordingĀ toĀ oneĀ embodiment.
FigureĀ 6Ā isĀ aĀ flowĀ diagramĀ illustratingĀ aĀ processĀ ofĀ evaluatingĀ localizationĀ accordingĀ toĀ oneĀ embodiment.
FigureĀ 7Ā isĀ aĀ blockĀ diagramĀ illustratingĀ aĀ dataĀ processingĀ systemĀ accordingĀ toĀ oneĀ embodiment.
VariousĀ embodimentsĀ andĀ aspectsĀ ofĀ theĀ disclosuresĀ willĀ beĀ describedĀ withĀ referenceĀ toĀ detailsĀ discussedĀ below,Ā andĀ theĀ accompanyingĀ drawingsĀ willĀ illustrateĀ theĀ variousĀ embodiments.Ā TheĀ followingĀ descriptionĀ andĀ drawingsĀ areĀ illustrativeĀ ofĀ theĀ disclosureĀ andĀ areĀ notĀ toĀ beĀ construedĀ asĀ limitingĀ theĀ disclosure.Ā NumerousĀ specificĀ detailsĀ areĀ describedĀ toĀ provideĀ aĀ thoroughĀ understandingĀ ofĀ variousĀ embodimentsĀ ofĀ theĀ presentĀ disclosure.Ā However,Ā inĀ certainĀ instances,Ā well-knownĀ orĀ conventionalĀ detailsĀ areĀ notĀ describedĀ inĀ orderĀ toĀ provideĀ aĀ conciseĀ discussionĀ ofĀ embodimentsĀ ofĀ theĀ presentĀ disclosures.
ReferenceĀ inĀ theĀ specificationĀ toĀ āoneĀ embodimentāĀ orĀ āanĀ embodimentāĀ meansĀ thatĀ aĀ particularĀ feature,Ā structure,Ā orĀ characteristicĀ describedĀ inĀ conjunctionĀ withĀ theĀ embodimentĀ canĀ beĀ includedĀ inĀ atĀ leastĀ oneĀ embodimentĀ ofĀ theĀ disclosure.Ā TheĀ appearancesĀ ofĀ theĀ phraseĀ āinĀ oneĀ embodimentāĀ inĀ variousĀ placesĀ inĀ theĀ specificationĀ doĀ notĀ necessarilyĀ allĀ referĀ toĀ theĀ sameĀ embodiment.
AccordingĀ toĀ someĀ embodiments,Ā inĀ orderĀ toĀ evaluateĀ aĀ localizationĀ systemĀ ofĀ anĀ ADV,Ā anĀ ADVĀ isĀ equippedĀ withĀ twoĀ localizationĀ systems:Ā 1)Ā aĀ knownĀ localizationĀ systemĀ withĀ aĀ setĀ ofĀ knownĀ sensorsĀ andĀ 2)Ā aĀ targetĀ localizationĀ systemĀ thatĀ willĀ beĀ eventuallyĀ deployedĀ inĀ theĀ ADVĀ forĀ normalĀ driving.Ā TheĀ knownĀ localizationĀ systemĀ refersĀ toĀ aĀ localizationĀ systemĀ withĀ knownĀ performanceĀ andĀ precision,Ā whichĀ isĀ usuallyĀ implementedĀ usingĀ higherĀ precisionĀ devicesĀ and/orĀ sensors.Ā TheĀ targetĀ localizationĀ systemĀ isĀ specificallyĀ designedĀ forĀ theĀ ADVĀ orĀ aĀ particularĀ typeĀ ofĀ ADVs,Ā whichĀ typicallyĀ mayĀ haveĀ unknownĀ qualityĀ andĀ behaviorsĀ andĀ mayĀ beĀ implementedĀ usingĀ lowerĀ performanceĀ orĀ precisionĀ devices.Ā TheĀ ADVĀ equippedĀ withĀ twoĀ localizationĀ systemsĀ thenĀ drivesĀ throughĀ aĀ predeterminedĀ path,Ā whileĀ bothĀ localizationĀ systemsĀ areĀ configuredĀ toĀ concurrentlyĀ determineĀ andĀ trackĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ path.Ā TheĀ locationsĀ determinedĀ byĀ bothĀ localizationĀ systemsĀ areĀ recordedĀ andĀ storedĀ inĀ aĀ persistentĀ storageĀ device.
SubsequentlyĀ offlineĀ orĀ online,Ā anĀ evaluationĀ processĀ isĀ performedĀ onĀ theĀ capturedĀ localizationĀ dataĀ toĀ determineĀ theĀ qualityĀ and/orĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ system,Ā forĀ example,Ā byĀ comparingĀ theĀ localizationĀ dataĀ ofĀ theĀ knownĀ (orĀ reference)Ā localizationĀ systemĀ andĀ theĀ localizationĀ dataĀ ofĀ theĀ targetĀ (orĀ unknown)Ā localizationĀ system.Ā InĀ oneĀ embodiment,Ā aĀ localizationĀ curveĀ isĀ generatedĀ forĀ eachĀ ofĀ theĀ localizationĀ systems,Ā whereĀ theĀ localizationĀ curveĀ representsĀ theĀ locationsĀ alongĀ theĀ pathĀ theĀ ADVĀ hasĀ drivenĀ andĀ capturedĀ byĀ aĀ localizationĀ system.Ā TheĀ localizationĀ curveĀ ofĀ theĀ knownĀ localizationĀ systemĀ isĀ utilizedĀ asĀ aĀ referenceĀ localizationĀ curveĀ becauseĀ itĀ wasĀ producedĀ byĀ aĀ knownĀ localizationĀ system.Ā TheĀ localizationĀ curveĀ ofĀ theĀ targetĀ localizationĀ systemĀ representsĀ aĀ targetĀ localizationĀ curveĀ thatĀ isĀ toĀ beĀ evaluated.Ā OneĀ ofĀ theĀ localizationĀ curvesĀ isĀ shiftedĀ backĀ andĀ forthĀ inĀ timeĀ andĀ aĀ similarityĀ scoreĀ representingĀ theĀ similarityĀ inĀ shapeĀ betweenĀ theĀ referenceĀ localizationĀ curveĀ andĀ theĀ targetĀ localizationĀ curveĀ isĀ calculated.Ā WhenĀ theĀ similarityĀ scoreĀ reachesĀ maximum,Ā theĀ correspondingĀ shiftedĀ timeĀ representsĀ theĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ system,Ā whileĀ theĀ similarityĀ scoreĀ representsĀ theĀ qualityĀ ofĀ theĀ targetĀ localizationĀ system.
AccordingĀ toĀ oneĀ embodiment,Ā anĀ ADVĀ isĀ equippedĀ withĀ twoĀ localizationĀ systems,Ā oneĀ isĀ knownĀ (e.g.,Ā reference)Ā andĀ oneĀ isĀ unknownĀ (e.g.,Ā target)Ā andĀ theĀ ADVĀ isĀ configuredĀ toĀ driveĀ throughĀ aĀ predeterminedĀ path.Ā AĀ firstĀ localizationĀ systemĀ (e.g.,Ā referenceĀ localizationĀ system)Ā performsĀ aĀ firstĀ localizationĀ usingĀ aĀ firstĀ setĀ ofĀ sensorsĀ toĀ trackĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ fromĀ aĀ startingĀ pointĀ toĀ aĀ destinationĀ point.Ā AĀ firstĀ localizationĀ curveĀ isĀ generatedĀ asĀ aĀ resultĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system.Ā Concurrently,Ā aĀ secondĀ localizationĀ systemĀ performsĀ aĀ secondĀ localizationĀ usingĀ aĀ secondĀ setĀ ofĀ sensorsĀ toĀ trackĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ path.Ā AĀ secondĀ localizationĀ curveĀ isĀ generatedĀ asĀ aĀ resultĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system.Ā AĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ determinedĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference.Ā TheĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ canĀ thenĀ beĀ utilizedĀ toĀ compensateĀ pathĀ planningĀ ofĀ theĀ ADVĀ subsequently.
InĀ oneĀ embodiment,Ā inĀ comparingĀ twoĀ localizationĀ curves,Ā aĀ similarityĀ scoreĀ isĀ calculatedĀ toĀ representĀ theĀ similarityĀ inĀ shapeĀ betweenĀ twoĀ localizationĀ curves.Ā WhenĀ oneĀ ofĀ theĀ localizationĀ curvesĀ isĀ shiftedĀ inĀ timeĀ forĀ aĀ predeterminedĀ timeĀ interval,Ā aĀ similarityĀ scoreĀ isĀ calculatedĀ forĀ thatĀ particularĀ shiftedĀ time.Ā SuchĀ aĀ processĀ isĀ repeatedlyĀ performedĀ forĀ aĀ numberĀ ofĀ shiftedĀ timeĀ intervalsĀ andĀ aĀ similarityĀ scoreĀ isĀ calculatedĀ forĀ eachĀ ofĀ theĀ shiftedĀ timeĀ intervals.Ā TheĀ similarityĀ scoresĀ ofĀ allĀ shiftedĀ timeĀ intervalsĀ areĀ examinedĀ toĀ identifyĀ theĀ highestĀ similarityĀ scoreĀ thatĀ indicatesĀ theĀ twoĀ localizationĀ curvesĀ areĀ mostĀ similarĀ toĀ eachĀ otherĀ atĀ theĀ correspondingĀ shiftedĀ timeĀ interval.Ā TheĀ shiftedĀ timeĀ intervalĀ withĀ theĀ highestĀ similarityĀ scoreĀ canĀ beĀ designatedĀ asĀ theĀ systemĀ delayĀ forĀ theĀ secondĀ localizationĀ system,Ā whileĀ theĀ similarityĀ scoreĀ itselfĀ canĀ beĀ usedĀ toĀ representĀ theĀ qualityĀ ofĀ theĀ localizationĀ system.Ā WhenĀ theĀ targetĀ localizationĀ systemĀ performsĀ withĀ theĀ qualityĀ closeĀ orĀ similarĀ toĀ theĀ referenceĀ localizationĀ system,Ā itsĀ performanceĀ isĀ consideredĀ goodĀ orĀ satisfactory.Ā InĀ oneĀ embodiment,Ā aĀ correlationĀ coefficientĀ betweenĀ theĀ twoĀ localizationĀ curvesĀ isĀ calculatedĀ toĀ representĀ theĀ similarityĀ betweenĀ theĀ twoĀ localizationĀ curves,Ā whichĀ isĀ alsoĀ usedĀ toĀ representĀ theĀ qualityĀ ofĀ theĀ secondĀ localizationĀ system.
FigureĀ 1Ā isĀ aĀ blockĀ diagramĀ illustratingĀ anĀ autonomousĀ vehicleĀ networkĀ configurationĀ accordingĀ toĀ oneĀ embodimentĀ ofĀ theĀ disclosure.Ā ReferringĀ toĀ FigureĀ 1,Ā networkĀ configuration Ā 100Ā includesĀ autonomousĀ vehicleĀ 101Ā thatĀ mayĀ beĀ communicativelyĀ coupledĀ toĀ oneĀ orĀ moreĀ serversĀ 103-104Ā overĀ aĀ network Ā 102.Ā AlthoughĀ thereĀ isĀ oneĀ autonomousĀ vehicleĀ shown,Ā multipleĀ autonomousĀ vehiclesĀ canĀ beĀ coupledĀ toĀ eachĀ otherĀ and/orĀ coupledĀ toĀ serversĀ 103-104Ā overĀ network Ā 102.Ā NetworkĀ 102Ā mayĀ beĀ anyĀ typeĀ ofĀ networksĀ suchĀ asĀ aĀ localĀ areaĀ networkĀ (LAN)Ā ,Ā aĀ wideĀ areaĀ networkĀ (WAN)Ā suchĀ asĀ theĀ Internet,Ā aĀ cellularĀ network,Ā aĀ satelliteĀ network,Ā orĀ aĀ combinationĀ thereof,Ā wiredĀ orĀ wireless.Ā ServerĀ (s)Ā 103-104Ā mayĀ beĀ anyĀ kindĀ ofĀ serversĀ orĀ aĀ clusterĀ ofĀ servers,Ā suchĀ asĀ WebĀ orĀ cloudĀ servers,Ā applicationĀ servers,Ā backendĀ servers,Ā orĀ aĀ combinationĀ thereof.Ā ServersĀ 103-104Ā mayĀ beĀ dataĀ analyticsĀ servers,Ā contentĀ servers,Ā trafficĀ informationĀ servers,Ā mapĀ andĀ pointĀ ofĀ interestĀ (MPOI)Ā severs,Ā orĀ locationĀ servers,Ā etc.
AnĀ autonomousĀ vehicleĀ refersĀ toĀ aĀ vehicleĀ thatĀ canĀ beĀ configuredĀ toĀ inĀ anĀ autonomousĀ modeĀ inĀ whichĀ theĀ vehicleĀ navigatesĀ throughĀ anĀ environmentĀ withĀ littleĀ orĀ noĀ inputĀ fromĀ aĀ driver.Ā SuchĀ anĀ autonomousĀ vehicleĀ canĀ includeĀ aĀ sensorĀ systemĀ havingĀ oneĀ orĀ moreĀ sensorsĀ thatĀ areĀ configuredĀ toĀ detectĀ informationĀ aboutĀ theĀ environmentĀ inĀ whichĀ theĀ vehicleĀ operates.Ā TheĀ vehicleĀ andĀ itsĀ associatedĀ controllerĀ (s)Ā useĀ theĀ detectedĀ informationĀ toĀ navigateĀ throughĀ theĀ environment.Ā AutonomousĀ vehicleĀ 101Ā canĀ operateĀ inĀ aĀ manualĀ mode,Ā aĀ fullĀ autonomousĀ mode,Ā orĀ aĀ partialĀ autonomousĀ mode.
InĀ oneĀ embodiment,Ā autonomousĀ vehicleĀ 101Ā includes,Ā butĀ isĀ notĀ limitedĀ to,Ā perceptionĀ andĀ planningĀ system Ā 110,Ā vehicleĀ controlĀ system Ā 111,Ā wirelessĀ communicationĀ system Ā 112,Ā userĀ interfaceĀ system Ā 113,Ā infotainmentĀ systemĀ 114,Ā andĀ sensorĀ system Ā 115.Ā AutonomousĀ vehicleĀ 101Ā mayĀ furtherĀ includeĀ certainĀ commonĀ componentsĀ includedĀ inĀ ordinaryĀ vehicles,Ā suchĀ as,Ā anĀ engine,Ā wheels,Ā steeringĀ wheel,Ā transmission,Ā etc.,Ā whichĀ mayĀ beĀ controlledĀ byĀ vehicleĀ controlĀ system Ā 111Ā and/orĀ perceptionĀ andĀ planningĀ system Ā 110Ā usingĀ aĀ varietyĀ ofĀ communicationĀ signalsĀ and/orĀ commands,Ā suchĀ as,Ā forĀ example,Ā accelerationĀ signalsĀ orĀ commands,Ā decelerationĀ signalsĀ orĀ commands,Ā steeringĀ signalsĀ orĀ commands,Ā brakingĀ signalsĀ orĀ commands,Ā etc.
ComponentsĀ 110-115Ā mayĀ beĀ communicativelyĀ coupledĀ toĀ eachĀ otherĀ viaĀ anĀ interconnect,Ā aĀ bus,Ā aĀ network,Ā orĀ aĀ combinationĀ thereof.Ā ForĀ example,Ā componentsĀ 110-115Ā mayĀ beĀ communicativelyĀ coupledĀ toĀ eachĀ otherĀ viaĀ aĀ controllerĀ areaĀ networkĀ (CAN)Ā bus.Ā AĀ CANĀ busĀ isĀ aĀ vehicleĀ busĀ standardĀ designedĀ toĀ allowĀ microcontrollersĀ andĀ devicesĀ toĀ communicateĀ withĀ eachĀ otherĀ inĀ applicationsĀ withoutĀ aĀ hostĀ computer.Ā ItĀ isĀ aĀ message-basedĀ protocol,Ā designedĀ originallyĀ forĀ multiplexĀ electricalĀ wiringĀ withinĀ automobiles,Ā butĀ isĀ alsoĀ usedĀ inĀ manyĀ otherĀ contexts.
ReferringĀ nowĀ toĀ FigureĀ 2,Ā inĀ oneĀ embodiment,Ā sensorĀ system Ā 115Ā includes,Ā butĀ itĀ isĀ notĀ limitedĀ to,Ā oneĀ orĀ moreĀ cameras Ā 211,Ā globalĀ positioningĀ systemĀ (GPS)Ā unit Ā 212,Ā inertialĀ measurementĀ unitĀ (IMU)Ā 213,Ā radarĀ unit Ā 214,Ā andĀ aĀ lightĀ detectionĀ andĀ rangeĀ (LIDAR)Ā unit Ā 215.Ā GPSĀ system Ā 212Ā mayĀ includeĀ aĀ transceiverĀ operableĀ toĀ provideĀ informationĀ regardingĀ theĀ positionĀ ofĀ theĀ autonomousĀ vehicle.Ā IMUĀ unit Ā 213Ā mayĀ senseĀ positionĀ andĀ orientationĀ changesĀ ofĀ theĀ autonomousĀ vehicleĀ basedĀ onĀ inertialĀ acceleration.Ā RadarĀ unit Ā 214Ā mayĀ representĀ aĀ systemĀ thatĀ utilizesĀ radioĀ signalsĀ toĀ senseĀ objectsĀ withinĀ theĀ localĀ environmentĀ ofĀ theĀ autonomousĀ vehicle.Ā InĀ someĀ embodiments,Ā inĀ additionĀ toĀ sensingĀ objects,Ā radarĀ unit Ā 214Ā mayĀ additionallyĀ senseĀ theĀ speedĀ and/orĀ headingĀ ofĀ theĀ objects.Ā LIDARĀ unit Ā 215Ā mayĀ senseĀ objectsĀ inĀ theĀ environmentĀ inĀ whichĀ theĀ autonomousĀ vehicleĀ isĀ locatedĀ usingĀ lasers.Ā LIDARĀ unit Ā 215Ā couldĀ includeĀ oneĀ orĀ moreĀ laserĀ sources,Ā aĀ laserĀ scanner,Ā andĀ oneĀ orĀ moreĀ detectors,Ā amongĀ otherĀ systemĀ components.Ā Cameras Ā 211Ā mayĀ includeĀ oneĀ orĀ moreĀ devicesĀ toĀ captureĀ imagesĀ ofĀ theĀ environmentĀ surroundingĀ theĀ autonomousĀ vehicle.Ā Cameras Ā 211Ā mayĀ beĀ stillĀ camerasĀ and/orĀ videoĀ cameras.Ā AĀ cameraĀ mayĀ beĀ mechanicallyĀ movable,Ā forĀ example,Ā byĀ mountingĀ theĀ cameraĀ onĀ aĀ rotatingĀ and/orĀ tiltingĀ aĀ platform.
InĀ oneĀ embodiment,Ā vehicleĀ controlĀ system Ā 111Ā includes,Ā butĀ isĀ notĀ limitedĀ to,Ā steeringĀ unit Ā 201,Ā throttleĀ unitĀ 202Ā (alsoĀ referredĀ toĀ asĀ anĀ accelerationĀ unit)Ā ,Ā andĀ brakingĀ unit Ā 203.Ā SteeringĀ unit Ā 201Ā isĀ toĀ adjustĀ theĀ directionĀ orĀ headingĀ ofĀ theĀ vehicle.Ā ThrottleĀ unit Ā 202Ā isĀ toĀ controlĀ theĀ speedĀ ofĀ theĀ motorĀ orĀ engineĀ thatĀ inĀ turnĀ controlĀ theĀ speedĀ andĀ accelerationĀ ofĀ theĀ vehicle.Ā BrakingĀ unit Ā 203Ā isĀ toĀ decelerateĀ theĀ vehicleĀ byĀ providingĀ frictionĀ toĀ slowĀ theĀ wheelsĀ orĀ tiresĀ ofĀ theĀ vehicle.Ā NoteĀ thatĀ theĀ componentsĀ asĀ shownĀ inĀ FigureĀ 2Ā mayĀ beĀ implementedĀ inĀ hardware,Ā software,Ā orĀ aĀ combinationĀ thereof.
ReferringĀ backĀ toĀ FigureĀ 1,Ā wirelessĀ communicationĀ system Ā 112Ā isĀ toĀ allowĀ communicationĀ betweenĀ autonomousĀ vehicleĀ 101Ā andĀ externalĀ systems,Ā suchĀ asĀ devices,Ā sensors,Ā otherĀ vehicles,Ā etc.Ā ForĀ example,Ā wirelessĀ communicationĀ system Ā 112Ā canĀ wirelesslyĀ communicateĀ withĀ oneĀ orĀ moreĀ devicesĀ directlyĀ orĀ viaĀ aĀ communicationĀ network,Ā suchĀ asĀ serversĀ 103-104Ā overĀ network Ā 102.Ā WirelessĀ communicationĀ system Ā 112Ā canĀ useĀ anyĀ cellularĀ communicationĀ networkĀ orĀ aĀ wirelessĀ localĀ areaĀ networkĀ (WLAN)Ā ,Ā e.g.,Ā usingĀ WiFiĀ toĀ communicateĀ withĀ anotherĀ componentĀ orĀ system.Ā WirelessĀ communicationĀ system Ā 112Ā couldĀ communicateĀ directlyĀ withĀ aĀ deviceĀ (e.g.,Ā aĀ mobileĀ deviceĀ ofĀ aĀ passenger,Ā aĀ displayĀ device,Ā aĀ speakerĀ withinĀ vehicleĀ 101)Ā ,Ā forĀ example,Ā usingĀ anĀ infraredĀ link,Ā Bluetooth,Ā etc.Ā UserĀ interfaceĀ system Ā 113Ā mayĀ beĀ partĀ ofĀ peripheralĀ devicesĀ implementedĀ withinĀ vehicleĀ 101Ā including,Ā forĀ example,Ā aĀ keyword,Ā aĀ touchĀ screenĀ displayĀ device,Ā aĀ microphone,Ā andĀ aĀ speaker,Ā etc.
SomeĀ orĀ allĀ ofĀ theĀ functionsĀ ofĀ autonomousĀ vehicleĀ 101Ā mayĀ beĀ controlledĀ orĀ managedĀ byĀ perceptionĀ andĀ planningĀ system Ā 110,Ā especiallyĀ whenĀ operatingĀ inĀ anĀ autonomousĀ drivingĀ mode.Ā PerceptionĀ andĀ planningĀ system Ā 110Ā includesĀ theĀ necessaryĀ hardwareĀ (e.g.,Ā processorĀ (s)Ā ,Ā memory,Ā storage)Ā andĀ softwareĀ (e.g.,Ā operatingĀ system,Ā planningĀ andĀ routingĀ programs)Ā toĀ receiveĀ informationĀ fromĀ sensorĀ system Ā 115,Ā controlĀ system Ā 111,Ā wirelessĀ communicationĀ system Ā 112,Ā and/orĀ userĀ interfaceĀ system Ā 113,Ā processĀ theĀ receivedĀ information,Ā planĀ aĀ routeĀ orĀ pathĀ fromĀ aĀ startingĀ pointĀ toĀ aĀ destinationĀ point,Ā andĀ thenĀ driveĀ vehicleĀ 101Ā basedĀ onĀ theĀ planningĀ andĀ controlĀ information.Ā Alternatively,Ā perceptionĀ andĀ planningĀ system Ā 110Ā mayĀ beĀ integratedĀ withĀ vehicleĀ controlĀ system Ā 111.
ForĀ example,Ā aĀ userĀ asĀ aĀ passengerĀ mayĀ specifyĀ aĀ startingĀ locationĀ andĀ aĀ destinationĀ ofĀ aĀ trip,Ā forĀ example,Ā viaĀ aĀ userĀ interface.Ā PerceptionĀ andĀ planningĀ system Ā 110Ā obtainsĀ theĀ tripĀ relatedĀ data.Ā ForĀ example,Ā perceptionĀ andĀ planningĀ system Ā 110Ā mayĀ obtainĀ locationĀ andĀ routeĀ informationĀ fromĀ anĀ MPOIĀ server,Ā whichĀ mayĀ beĀ aĀ partĀ ofĀ serversĀ 103-104.Ā TheĀ locationĀ serverĀ providesĀ locationĀ servicesĀ andĀ theĀ MPOIĀ serverĀ providesĀ mapĀ servicesĀ andĀ theĀ POIsĀ ofĀ certainĀ locations.Ā Alternatively,Ā suchĀ locationĀ andĀ MPOIĀ informationĀ mayĀ beĀ cachedĀ locallyĀ inĀ aĀ persistentĀ storageĀ deviceĀ ofĀ perceptionĀ andĀ planningĀ system Ā 110.
WhileĀ autonomousĀ vehicleĀ 101Ā isĀ movingĀ alongĀ theĀ route,Ā perceptionĀ andĀ planningĀ system Ā 110Ā mayĀ alsoĀ obtainĀ real-timeĀ trafficĀ informationĀ fromĀ aĀ trafficĀ informationĀ systemĀ orĀ serverĀ (TIS)Ā .Ā NoteĀ thatĀ serversĀ 103-104Ā mayĀ beĀ operatedĀ byĀ aĀ thirdĀ partyĀ entity.Ā Alternatively,Ā theĀ functionalitiesĀ ofĀ serversĀ 103-104Ā mayĀ beĀ integratedĀ withĀ perceptionĀ andĀ planningĀ system Ā 110.Ā BasedĀ onĀ theĀ real-timeĀ trafficĀ information,Ā MPOIĀ information,Ā andĀ locationĀ information,Ā asĀ wellĀ asĀ real-timeĀ localĀ environmentĀ dataĀ detectedĀ orĀ sensedĀ byĀ sensorĀ systemĀ 115Ā (e.g.,Ā obstacles,Ā objects,Ā nearbyĀ vehicles)Ā ,Ā perceptionĀ andĀ planningĀ system Ā 110Ā canĀ planĀ anĀ optimalĀ routeĀ andĀ driveĀ vehicleĀ 101,Ā forĀ example,Ā viaĀ controlĀ system Ā 111,Ā accordingĀ toĀ theĀ plannedĀ routeĀ toĀ reachĀ theĀ specifiedĀ destinationĀ safelyĀ andĀ efficiently.
BasedĀ onĀ drivingĀ statistics Ā 123,Ā machineĀ learningĀ engine Ā 122Ā generatesĀ orĀ trainsĀ aĀ setĀ ofĀ rules,Ā algorithms,Ā and/orĀ predictiveĀ models Ā 124Ā forĀ aĀ varietyĀ ofĀ purposes.Ā InĀ oneĀ embodiment,Ā algorithms Ā 124Ā includeĀ oneĀ orĀ moreĀ algorithmsĀ toĀ evaluateĀ aĀ localizationĀ systemĀ toĀ determineĀ theĀ performanceĀ orĀ qualityĀ ofĀ theĀ localizationĀ systemĀ andĀ theĀ systemĀ delayĀ ofĀ theĀ localizationĀ system.Ā SuchĀ algorithmsĀ mayĀ beĀ utilizedĀ byĀ localizationĀ evaluationĀ system Ā 125Ā basedĀ onĀ theĀ localizationĀ dataĀ collectedĀ fromĀ ADVs,Ā forĀ example,Ā byĀ determiningĀ theĀ systemĀ delayĀ andĀ theĀ similarityĀ scoreĀ ofĀ theĀ localizationĀ systemĀ inĀ viewĀ ofĀ aĀ localizationĀ systemĀ reference.
FiguresĀ 3AĀ andĀ 3BĀ areĀ blockĀ diagramsĀ illustratingĀ anĀ exampleĀ ofĀ aĀ perceptionĀ andĀ planningĀ systemĀ usedĀ withĀ anĀ autonomousĀ vehicleĀ accordingĀ toĀ oneĀ embodiment.Ā System Ā 300Ā mayĀ beĀ implementedĀ asĀ aĀ partĀ ofĀ autonomousĀ vehicleĀ 101Ā ofĀ FigureĀ 1Ā including,Ā butĀ isĀ notĀ limitedĀ to,Ā perceptionĀ andĀ planningĀ system Ā 110,Ā controlĀ system Ā 111,Ā andĀ sensorĀ system Ā 115.Ā ReferringĀ toĀ FiguresĀ 3A-3B,Ā perceptionĀ andĀ planningĀ system Ā 110Ā includes,Ā butĀ isĀ notĀ limitedĀ to,Ā localizationĀ module Ā 301,Ā perceptionĀ module Ā 302,Ā predictionĀ module Ā 303,Ā decisionĀ module Ā 304,Ā planningĀ module Ā 305,Ā controlĀ module Ā 306,Ā routingĀ module Ā 307,Ā andĀ localizationĀ evaluationĀ system Ā 308.
SomeĀ orĀ allĀ ofĀ modulesĀ 301-308Ā mayĀ beĀ implementedĀ inĀ software,Ā hardware,Ā orĀ aĀ combinationĀ thereof.Ā ForĀ example,Ā theseĀ modulesĀ mayĀ beĀ installedĀ inĀ persistentĀ storageĀ device Ā 352,Ā loadedĀ intoĀ memory Ā 351,Ā andĀ executedĀ byĀ oneĀ orĀ moreĀ processorsĀ (notĀ shown)Ā .Ā NoteĀ thatĀ someĀ orĀ allĀ ofĀ theseĀ modulesĀ mayĀ beĀ communicativelyĀ coupledĀ toĀ orĀ integratedĀ withĀ someĀ orĀ allĀ modulesĀ ofĀ vehicleĀ controlĀ system Ā 111Ā ofĀ FigureĀ 2.Ā SomeĀ ofĀ modulesĀ 301-308Ā mayĀ beĀ integratedĀ togetherĀ asĀ anĀ integratedĀ module.
BasedĀ onĀ theĀ sensorĀ dataĀ providedĀ byĀ sensorĀ system Ā 115Ā andĀ localizationĀ informationĀ obtainedĀ byĀ localizationĀ module Ā 301,Ā aĀ perceptionĀ ofĀ theĀ surroundingĀ environmentĀ isĀ determinedĀ byĀ perceptionĀ module Ā 302.Ā TheĀ perceptionĀ informationĀ mayĀ representĀ whatĀ anĀ ordinaryĀ driverĀ wouldĀ perceiveĀ surroundingĀ aĀ vehicleĀ inĀ whichĀ theĀ driverĀ isĀ driving.Ā TheĀ perceptionĀ canĀ includeĀ theĀ laneĀ configurationĀ (e.g.,Ā straightĀ orĀ curveĀ lanes)Ā ,Ā trafficĀ lightĀ signals,Ā aĀ relativeĀ positionĀ ofĀ anotherĀ vehicle,Ā aĀ pedestrian,Ā aĀ building,Ā crosswalk,Ā orĀ otherĀ trafficĀ relatedĀ signsĀ (e.g.,Ā stopĀ signs,Ā yieldĀ signs)Ā ,Ā etc.,Ā forĀ example,Ā inĀ aĀ formĀ ofĀ anĀ object.
ForĀ eachĀ ofĀ theĀ objects,Ā predictionĀ module Ā 303Ā predictsĀ whatĀ theĀ objectĀ willĀ behaveĀ underĀ theĀ circumstances.Ā TheĀ predictionĀ isĀ performedĀ basedĀ onĀ theĀ perceptionĀ dataĀ perceivingĀ theĀ drivingĀ environmentĀ atĀ theĀ pointĀ inĀ timeĀ inĀ viewĀ ofĀ aĀ setĀ ofĀ map/routĀ information Ā 311Ā andĀ trafficĀ rulesĀ 312.Ā ForĀ example,Ā ifĀ theĀ objectĀ isĀ aĀ vehicleĀ atĀ anĀ opposingĀ directionĀ andĀ theĀ currentĀ drivingĀ environmentĀ includesĀ anĀ intersection,Ā predictionĀ module Ā 303Ā willĀ predictĀ whetherĀ theĀ vehicleĀ willĀ likelyĀ moveĀ straightĀ forwardĀ orĀ makeĀ aĀ turn.Ā IfĀ theĀ perceptionĀ dataĀ indicatesĀ thatĀ theĀ intersectionĀ hasĀ noĀ trafficĀ light,Ā predictionĀ module Ā 303Ā mayĀ predictĀ thatĀ theĀ vehicleĀ mayĀ haveĀ toĀ fullyĀ stopĀ priorĀ toĀ enterĀ theĀ intersection.Ā IfĀ theĀ perceptionĀ dataĀ indicatesĀ thatĀ theĀ vehicleĀ isĀ currentlyĀ atĀ aĀ left-turnĀ onlyĀ laneĀ orĀ aĀ right-turnĀ onlyĀ lane,Ā predictionĀ module Ā 303Ā mayĀ predictĀ thatĀ theĀ vehicleĀ willĀ moreĀ likelyĀ makeĀ aĀ leftĀ turnĀ orĀ rightĀ turnĀ respectively.
ForĀ eachĀ ofĀ theĀ objects,Ā decisionĀ module Ā 304Ā makesĀ aĀ decisionĀ regardingĀ howĀ toĀ handleĀ theĀ object.Ā ForĀ example,Ā forĀ aĀ particularĀ objectĀ (e.g.,Ā anotherĀ vehicleĀ inĀ aĀ crossingĀ route)Ā asĀ wellĀ asĀ itsĀ metadataĀ describingĀ theĀ objectĀ (e.g.,Ā aĀ speed,Ā direction,Ā turningĀ angle)Ā ,Ā decisionĀ module Ā 304Ā decidesĀ howĀ toĀ encounterĀ theĀ objectĀ (e.g.,Ā overtake,Ā yield,Ā stop,Ā pass)Ā .Ā DecisionĀ module Ā 304Ā mayĀ makeĀ suchĀ decisionsĀ accordingĀ toĀ aĀ setĀ ofĀ rulesĀ suchĀ asĀ trafficĀ rulesĀ orĀ drivingĀ rules Ā 312,Ā whichĀ mayĀ beĀ storedĀ inĀ persistentĀ storageĀ device Ā 352.
BasedĀ onĀ aĀ decisionĀ forĀ eachĀ ofĀ theĀ objectsĀ perceived,Ā planningĀ module Ā 305Ā plansĀ aĀ pathĀ orĀ routeĀ forĀ theĀ autonomousĀ vehicle,Ā asĀ wellĀ asĀ drivingĀ parametersĀ (e.g.,Ā distance,Ā speed,Ā and/orĀ turningĀ angle)Ā ,Ā usingĀ aĀ referenceĀ lineĀ providedĀ byĀ routingĀ module Ā 307Ā asĀ aĀ basis.Ā ThatĀ is,Ā forĀ aĀ givenĀ object,Ā decisionĀ module Ā 304Ā decidesĀ whatĀ toĀ doĀ withĀ theĀ object,Ā whileĀ planningĀ module Ā 305Ā determinesĀ howĀ toĀ doĀ it.Ā ForĀ example,Ā forĀ aĀ givenĀ object,Ā decisionĀ module Ā 304Ā mayĀ decideĀ toĀ passĀ theĀ object,Ā whileĀ planningĀ module Ā 305Ā mayĀ determineĀ whetherĀ toĀ passĀ onĀ theĀ leftĀ sideĀ orĀ rightĀ sideĀ ofĀ theĀ object.Ā PlanningĀ andĀ controlĀ dataĀ isĀ generatedĀ byĀ planningĀ module Ā 305Ā includingĀ informationĀ describingĀ howĀ vehicle Ā 300Ā wouldĀ moveĀ inĀ aĀ nextĀ movingĀ cycleĀ (e.g.,Ā nextĀ route/pathĀ segment)Ā .Ā ForĀ example,Ā theĀ planningĀ andĀ controlĀ dataĀ mayĀ instructĀ vehicle Ā 300Ā toĀ moveĀ 10Ā metersĀ atĀ aĀ speedĀ ofĀ 30Ā mileĀ perĀ hourĀ (mph)Ā ,Ā thenĀ changeĀ toĀ aĀ rightĀ laneĀ atĀ theĀ speedĀ ofĀ 25Ā mph.
BasedĀ onĀ theĀ planningĀ andĀ controlĀ data,Ā controlĀ module Ā 306Ā controlsĀ andĀ drivesĀ theĀ autonomousĀ vehicle,Ā byĀ sendingĀ properĀ commandsĀ orĀ signalsĀ toĀ vehicleĀ controlĀ system Ā 111,Ā accordingĀ toĀ aĀ routeĀ orĀ pathĀ definedĀ byĀ theĀ planningĀ andĀ controlĀ data.Ā TheĀ planningĀ andĀ controlĀ dataĀ includeĀ sufficientĀ informationĀ toĀ driveĀ theĀ vehicleĀ fromĀ aĀ firstĀ pointĀ toĀ aĀ secondĀ pointĀ ofĀ aĀ routeĀ orĀ pathĀ usingĀ appropriateĀ vehicleĀ settingsĀ orĀ drivingĀ parametersĀ (e.g.,Ā throttle,Ā braking,Ā steeringĀ commands)Ā atĀ differentĀ pointsĀ inĀ timeĀ alongĀ theĀ pathĀ orĀ route.
InĀ oneĀ embodiment,Ā theĀ planningĀ phaseĀ isĀ performedĀ inĀ aĀ numberĀ ofĀ planningĀ cycles,Ā alsoĀ referredĀ toĀ asĀ drivingĀ cycles,Ā suchĀ as,Ā forĀ example,Ā inĀ everyĀ timeĀ intervalĀ ofĀ 100Ā millisecondsĀ (ms)Ā .Ā ForĀ eachĀ ofĀ theĀ planningĀ cyclesĀ orĀ drivingĀ cycles,Ā oneĀ orĀ moreĀ controlĀ commandsĀ willĀ beĀ issuedĀ basedĀ onĀ theĀ planningĀ andĀ controlĀ data.Ā ThatĀ is,Ā forĀ everyĀ 100Ā ms,Ā planningĀ module Ā 305Ā plansĀ aĀ nextĀ routeĀ segmentĀ orĀ pathĀ segment,Ā forĀ example,Ā includingĀ aĀ targetĀ positionĀ andĀ theĀ timeĀ requiredĀ forĀ theĀ ADVĀ toĀ reachĀ theĀ targetĀ position.Ā Alternatively,Ā planningĀ module Ā 305Ā mayĀ furtherĀ specifyĀ theĀ specificĀ speed,Ā direction,Ā and/orĀ steeringĀ angle,Ā etc.Ā InĀ oneĀ embodiment,Ā planningĀ module Ā 305Ā plansĀ aĀ routeĀ segmentĀ orĀ pathĀ segmentĀ forĀ theĀ nextĀ predeterminedĀ periodĀ ofĀ timeĀ suchĀ asĀ 5Ā seconds.Ā ForĀ eachĀ planningĀ cycle,Ā planningĀ module Ā 305Ā plansĀ aĀ targetĀ positionĀ forĀ theĀ currentĀ cycleĀ (e.g.,Ā nextĀ 5Ā seconds)Ā basedĀ onĀ aĀ targetĀ positionĀ plannedĀ inĀ aĀ previousĀ cycle.Ā ControlĀ module Ā 306Ā thenĀ generatesĀ oneĀ orĀ moreĀ controlĀ commandsĀ (e.g.,Ā throttle,Ā brake,Ā steeringĀ controlĀ commands)Ā basedĀ onĀ theĀ planningĀ andĀ controlĀ dataĀ ofĀ theĀ currentĀ cycle.
NoteĀ thatĀ decisionĀ module Ā 304Ā andĀ planningĀ module Ā 305Ā mayĀ beĀ integratedĀ asĀ anĀ integratedĀ module.Ā DecisionĀ module Ā 304/planningĀ module Ā 305Ā mayĀ includeĀ aĀ navigationĀ systemĀ orĀ functionalitiesĀ ofĀ aĀ navigationĀ systemĀ toĀ determineĀ aĀ drivingĀ pathĀ forĀ theĀ autonomousĀ vehicle.Ā ForĀ example,Ā theĀ navigationĀ systemĀ mayĀ determineĀ aĀ seriesĀ ofĀ speedsĀ andĀ directionalĀ headingsĀ toĀ affectĀ movementĀ ofĀ theĀ autonomousĀ vehicleĀ alongĀ aĀ pathĀ thatĀ substantiallyĀ avoidsĀ perceivedĀ obstaclesĀ whileĀ generallyĀ advancingĀ theĀ autonomousĀ vehicleĀ alongĀ aĀ roadway-basedĀ pathĀ leadingĀ toĀ anĀ ultimateĀ destination.Ā TheĀ destinationĀ mayĀ beĀ setĀ accordingĀ toĀ userĀ inputsĀ viaĀ userĀ interfaceĀ system Ā 113.Ā TheĀ navigationĀ systemĀ mayĀ updateĀ theĀ drivingĀ pathĀ dynamicallyĀ whileĀ theĀ autonomousĀ vehicleĀ isĀ inĀ operation.Ā TheĀ navigationĀ systemĀ canĀ incorporateĀ dataĀ fromĀ aĀ GPSĀ systemĀ andĀ oneĀ orĀ moreĀ mapsĀ soĀ asĀ toĀ determineĀ theĀ drivingĀ pathĀ forĀ theĀ autonomousĀ vehicle.
TheĀ referenceĀ localizationĀ dataĀ generatedĀ byĀ theĀ referenceĀ localizationĀ systemĀ isĀ storedĀ inĀ persistentĀ storageĀ device Ā 352Ā asĀ aĀ partĀ ofĀ referenceĀ localizationĀ data Ā 313.Ā TheĀ targetĀ localizationĀ dataĀ generatedĀ byĀ theĀ targetĀ localizationĀ systemĀ isĀ storedĀ asĀ aĀ partĀ ofĀ targetĀ localizationĀ data Ā 314.Ā LocalizationĀ evaluationĀ module Ā 308Ā isĀ configuredĀ toĀ analyzeĀ theĀ localizationĀ dataĀ 313-314Ā toĀ determineĀ theĀ performanceĀ andĀ theĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ system,Ā forĀ example,Ā byĀ comparingĀ referenceĀ localizationĀ data Ā 313Ā withĀ targetĀ localizationĀ data Ā 314.Ā Alternatively,Ā theĀ collectedĀ localizationĀ dataĀ 313-314Ā canĀ beĀ analyzedĀ offline,Ā forĀ example,Ā byĀ localizationĀ evaluationĀ system Ā 125Ā ofĀ server Ā 103.
FigureĀ 4Ā isĀ aĀ blockĀ diagramĀ illustratingĀ aĀ localizationĀ evaluationĀ systemĀ accordingĀ toĀ oneĀ embodiment.Ā ReferringĀ toĀ FigureĀ 4,Ā inĀ thisĀ example,Ā localizationĀ module Ā 301Ā includesĀ aĀ referenceĀ localizationĀ module Ā 401Ā andĀ aĀ targetĀ localizationĀ module Ā 402.Ā ReferenceĀ localizationĀ module Ā 401Ā isĀ consideredĀ asĀ aĀ trustedĀ orĀ knownĀ localizationĀ moduleĀ thatĀ producesĀ knownĀ localizationĀ qualityĀ withĀ knownĀ orĀ noĀ systemĀ delay.Ā TargetĀ localizationĀ module Ā 402Ā isĀ aĀ localizationĀ moduleĀ thatĀ willĀ beĀ orĀ hasĀ beenĀ deployedĀ inĀ theĀ ADVsĀ forĀ normalĀ operations.Ā ReferenceĀ localizationĀ module Ā 401Ā isĀ utilizedĀ onlyĀ forĀ theĀ purposeĀ ofĀ evaluatingĀ theĀ performanceĀ ofĀ targetĀ localizationĀ module Ā 402.Ā InĀ addition,Ā referenceĀ localizationĀ module Ā 401Ā isĀ associatedĀ withĀ aĀ setĀ ofĀ knownĀ sensors,Ā referredĀ toĀ hereinĀ asĀ referenceĀ sensorĀ system Ā 115A,Ā whileĀ targetĀ localizationĀ module Ā 402Ā isĀ associatedĀ withĀ aĀ setĀ ofĀ targetĀ sensors,Ā referredĀ toĀ hereinĀ asĀ targetĀ sensorĀ system Ā 115B.Ā TargetĀ sensorĀ system Ā 115BĀ willĀ beĀ deployedĀ onĀ theĀ ADVsĀ duringĀ normalĀ operationsĀ orĀ massĀ productionĀ ofĀ ADVs.
InĀ oneĀ embodiment,Ā theĀ ADVĀ isĀ configuredĀ toĀ driveĀ accordingĀ toĀ aĀ predeterminedĀ pathĀ orĀ route,Ā duringĀ whichĀ bothĀ localizationĀ modulesĀ 401-402Ā concurrentlyĀ performĀ localizationĀ usingĀ sensorĀ systems Ā 115A-115BĀ andĀ generateĀ localizationĀ dataĀ 313-314Ā respectively.Ā ReferenceĀ localizationĀ data Ā 313Ā includesĀ informationĀ recordingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ capturedĀ byĀ referenceĀ localizationĀ module Ā 401Ā viaĀ sensorĀ system Ā 115A.Ā TargetĀ localizationĀ data Ā 314Ā includesĀ informationĀ recordingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ capturedĀ byĀ targetĀ localizationĀ module Ā 402.Ā ReferenceĀ localizationĀ data Ā 313Ā andĀ targetĀ localizationĀ data Ā 314Ā areĀ thenĀ analyzedĀ byĀ localizationĀ evaluationĀ moduleĀ orĀ system Ā 410.Ā TheĀ localizationĀ evaluationĀ module Ā 410Ā mayĀ beĀ implementedĀ asĀ aĀ partĀ ofĀ localizationĀ evaluationĀ system Ā 125Ā ofĀ FigureĀ 1Ā orĀ localizationĀ evaluationĀ module Ā 308Ā ofĀ FigureĀ 3A.
AccordingĀ toĀ oneĀ embodiment,Ā localizationĀ evaluationĀ module Ā 410Ā examinesĀ referenceĀ localizationĀ data Ā 313Ā toĀ generateĀ aĀ referenceĀ localizationĀ curveĀ (alsoĀ referredĀ toĀ asĀ aĀ localizationĀ graph)Ā .Ā TheĀ localizationĀ evaluationĀ module Ā 410Ā examinesĀ targetĀ localizationĀ data Ā 314Ā toĀ generateĀ aĀ targetĀ localizationĀ curve.Ā AĀ localizationĀ curveĀ includesĀ aĀ numberĀ ofĀ pointsĀ andĀ eachĀ pointĀ representsĀ aĀ particularĀ locationĀ ofĀ theĀ ADVĀ atĀ aĀ particularĀ pointĀ inĀ time.Ā TheĀ localizationĀ evaluationĀ module Ā 410Ā comparesĀ theĀ referenceĀ localizationĀ curveĀ andĀ theĀ targetĀ localizationĀ curveĀ toĀ determineĀ theĀ similarityĀ betweenĀ twoĀ localizationĀ curvesĀ andĀ theĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ module Ā 402.
InĀ oneĀ embodiment,Ā theĀ localizationĀ evaluationĀ module Ā 410Ā shiftsĀ inĀ timeĀ oneĀ ofĀ theĀ localizationĀ curvesĀ againstĀ theĀ other.Ā TheĀ localizationĀ evaluationĀ module Ā 410Ā thenĀ comparesĀ theĀ shiftedĀ curvesĀ toĀ determineĀ theĀ similarityĀ inĀ shapeĀ betweenĀ twoĀ curvesĀ withinĀ aĀ predeterminedĀ timeĀ window.Ā TheĀ aboveĀ processĀ isĀ iterativelyĀ performedĀ toĀ shiftĀ oneĀ localizationĀ curveĀ backĀ andĀ forthĀ inĀ timeĀ withĀ respectĀ toĀ theĀ otherĀ localizationĀ curve,Ā andĀ theĀ similarityĀ betweenĀ twoĀ curvesĀ withinĀ theĀ timeĀ windowĀ isĀ determineĀ forĀ theĀ correspondingĀ shiftedĀ timeĀ interval.Ā WhenĀ theĀ shapesĀ ofĀ theĀ referenceĀ localizationĀ curveĀ isĀ mostĀ similarĀ toĀ theĀ targetĀ localizationĀ curveĀ orĀ viaĀ versa,Ā theĀ correspondingĀ shiftedĀ timeĀ intervalĀ isĀ consideredĀ asĀ theĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ module Ā 402.Ā TheĀ levelĀ orĀ similarityĀ scoreĀ ofĀ theĀ highestĀ similarityĀ isĀ utilizedĀ toĀ representĀ theĀ qualityĀ ofĀ localizationĀ module Ā 402,Ā i.e.,Ā howĀ similarĀ orĀ closeĀ localizationĀ module Ā 402Ā hasĀ performedĀ inĀ viewĀ ofĀ theĀ referenceĀ localizationĀ module Ā 401Ā asĀ aĀ knownĀ localizationĀ standard.
ReferringĀ nowĀ toĀ FigureĀ 5A,Ā inĀ thisĀ example,Ā referenceĀ localizationĀ curve Ā 501Ā isĀ generatedĀ basedĀ onĀ referenceĀ localizationĀ data Ā 313Ā andĀ targetĀ localizationĀ curve Ā 502Ā isĀ generatedĀ basedĀ onĀ targetĀ localizationĀ data Ā 314.Ā InĀ oneĀ embodiment,Ā toĀ determineĀ aĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ system,Ā oneĀ ofĀ theĀ localizationĀ curvesĀ 501-502Ā isĀ shiftedĀ inĀ timeĀ backĀ andĀ forthĀ forĀ aĀ numberĀ ofĀ timeĀ intervals.Ā ForĀ eachĀ shiftedĀ timeĀ interval,Ā aĀ similarityĀ scoreĀ betweenĀ theĀ referenceĀ localizationĀ curve Ā 501Ā andĀ targetĀ localizationĀ curve Ā 502Ā isĀ calculatedĀ withinĀ aĀ predeterminedĀ timeĀ window.
ForĀ example,Ā asĀ shownĀ inĀ FigureĀ 5B,Ā referenceĀ localizationĀ curve Ā 501Ā isĀ shiftedĀ backĀ andĀ forthĀ whileĀ targetĀ localizationĀ curve Ā 502Ā remainsĀ steadyĀ forĀ aĀ numberĀ ofĀ timeĀ intervalsĀ (e.g.,Ā -0.3Ā secondsĀ (s)Ā ,Ā -0.2s,Ā -0.1s,Ā 0,Ā 0.1s,Ā 0.2s,Ā 0.3s)Ā .Ā InĀ thisĀ example,Ā aĀ predeterminedĀ timeĀ intervalĀ hasĀ beenĀ selectedĀ asĀ 0.1s,Ā butĀ itĀ canĀ beĀ otherĀ timeĀ intervalĀ values.Ā Curve Ā 501AĀ hasĀ beenĀ shiftedĀ backwardlyĀ byĀ 0.2s;Ā curve Ā 501BĀ hasĀ beenĀ shiftedĀ backwardlyĀ byĀ 0.1Ā s;Ā curve Ā 501CĀ hasĀ beenĀ shiftedĀ forwardlyĀ byĀ 0.1s;Ā andĀ curve Ā 501DĀ hasĀ beenĀ shiftedĀ forwardlyĀ byĀ 0.2s.Ā ForĀ eachĀ shiftedĀ timeĀ interval,Ā aĀ similarityĀ scoreĀ isĀ calculatedĀ toĀ representĀ theĀ similarityĀ betweenĀ referenceĀ localizationĀ curve Ā 501Ā andĀ targetĀ localizationĀ curve Ā 502.Ā Thus,Ā aĀ similarityĀ scoreĀ isĀ calculatedĀ forĀ eachĀ ofĀ theĀ localizationĀ curvesĀ 501Ā andĀ 501A-501DĀ withinĀ theĀ timeĀ window.Ā AĀ higherĀ similarityĀ scoreĀ indicatesĀ thatĀ referenceĀ localizationĀ curve Ā 501Ā andĀ targetĀ localizationĀ curve Ā 502Ā withinĀ theĀ sameĀ timeĀ windowĀ areĀ moreĀ similar.Ā InĀ oneĀ embodiment,Ā afterĀ allĀ ofĀ theĀ similarityĀ scoresĀ haveĀ beenĀ calculatedĀ forĀ allĀ shiftedĀ timeĀ intervals,Ā amongstĀ theĀ similarityĀ scoresĀ ofĀ differentĀ shiftedĀ timeĀ intervalsĀ (e.g.,Ā similarityĀ scoresĀ forĀ curves Ā 501Ā andĀ 501A-501D)Ā ,Ā aĀ shiftedĀ timeĀ intervalĀ correspondingĀ toĀ theĀ highestĀ similarityĀ scoresĀ isĀ designatedĀ asĀ theĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ system.Ā TheĀ highestĀ similarityĀ scoreĀ canĀ beĀ usedĀ toĀ measureĀ theĀ qualityĀ ofĀ theĀ targetĀ localizationĀ system.
InĀ oneĀ embodiment,Ā aĀ correlationĀ coefficientĀ isĀ calculatedĀ betweenĀ eachĀ ofĀ theĀ referenceĀ localizationĀ curvesĀ 501Ā andĀ 501A-501DĀ andĀ targetĀ localizationĀ curve Ā 502Ā toĀ representĀ theĀ levelĀ ofĀ similarityĀ betweenĀ theĀ twoĀ localizationĀ curves.Ā TheĀ shiftedĀ timeĀ intervalĀ correspondingĀ toĀ theĀ highestĀ correlationĀ coefficientĀ amongstĀ allĀ representsĀ theĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ system,Ā whileĀ theĀ highestĀ correlationĀ coefficientĀ representsĀ theĀ qualityĀ ofĀ theĀ targetĀ localizationĀ system.Ā ForĀ example,Ā ifĀ theĀ highestĀ correlationĀ coefficientĀ isĀ achievedĀ atĀ tĀ =Ā -0.3sĀ withĀ theĀ correlationĀ coefficientĀ ofĀ 0.96,Ā theĀ qualityĀ scoreĀ ofĀ theĀ targetĀ localizationĀ curve Ā 502Ā isĀ 0.96Ā andĀ theĀ systemĀ delayĀ ofĀ theĀ targetĀ localizationĀ systemĀ isĀ 0.3s.
AĀ correlationĀ coefficientĀ isĀ aĀ numericalĀ measureĀ ofĀ someĀ typeĀ ofĀ correlation,Ā meaningĀ aĀ statisticalĀ relationshipĀ betweenĀ twoĀ variables.Ā TheĀ variablesĀ mayĀ beĀ twoĀ columnsĀ ofĀ aĀ givenĀ dataĀ setĀ ofĀ observations,Ā oftenĀ calledĀ aĀ sample,Ā orĀ twoĀ componentsĀ ofĀ aĀ multivariateĀ randomĀ variableĀ withĀ aĀ knownĀ distribution.Ā SeveralĀ typesĀ ofĀ correlationĀ coefficientĀ exist,Ā eachĀ withĀ theirĀ ownĀ definitionĀ andĀ ownĀ rangeĀ ofĀ usabilityĀ andĀ characteristics.Ā TheyĀ allĀ assumeĀ valuesĀ inĀ theĀ rangeĀ fromĀ -1Ā toĀ +1,Ā whereĀ +1Ā indicatesĀ theĀ strongestĀ possibleĀ agreementĀ andĀ -1Ā theĀ strongestĀ possibleĀ disagreement.Ā AsĀ toolsĀ ofĀ analysis,Ā correlationĀ coefficientsĀ presentĀ certainĀ problems,Ā includingĀ theĀ propensityĀ ofĀ someĀ typesĀ toĀ beĀ distortedĀ byĀ outliersĀ andĀ theĀ possibilityĀ ofĀ incorrectlyĀ beingĀ usedĀ toĀ inferĀ aĀ causalĀ relationshipĀ betweenĀ theĀ variables.
FigureĀ 6Ā isĀ aĀ flowĀ diagramĀ illustratingĀ anĀ exampleĀ ofĀ aĀ processĀ ofĀ evaluatingĀ aĀ localizationĀ systemĀ ofĀ anĀ autonomousĀ drivingĀ vehicleĀ accordingĀ toĀ oneĀ embodiment.Ā Process Ā 600Ā canĀ beĀ performedĀ byĀ processingĀ logicĀ whichĀ mayĀ includeĀ software,Ā hardware,Ā orĀ aĀ combinationĀ thereof.Ā ForĀ example,Ā process Ā 600Ā mayĀ beĀ performedĀ byĀ localizationĀ evaluationĀ system Ā 125Ā orĀ localizationĀ evaluationĀ module Ā 308.Ā ReferringĀ toĀ FigureĀ 6,Ā inĀ operation Ā 601,Ā processingĀ logicĀ receivesĀ firstĀ localizationĀ dataĀ ofĀ aĀ firstĀ localizationĀ performedĀ byĀ aĀ firstĀ localizationĀ systemĀ ofĀ anĀ ADVĀ drivingĀ alongĀ aĀ path.Ā InĀ operation Ā 602,Ā processingĀ logicĀ receivesĀ secondĀ localizationĀ dataĀ ofĀ aĀ secondĀ localizationĀ performedĀ byĀ aĀ secondĀ localizationĀ systemĀ ofĀ theĀ ADVĀ alongĀ theĀ path.Ā TheĀ firstĀ localizationĀ andĀ theĀ secondĀ localizationĀ areĀ performedĀ concurrentlyĀ onĀ theĀ ADV.
InĀ operation Ā 603,Ā processingĀ logicĀ generatesĀ aĀ firstĀ localizationĀ curveĀ basedĀ onĀ theĀ firstĀ localizationĀ dataĀ representingĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system.Ā InĀ operation Ā 604,Ā processingĀ logicĀ generatesĀ aĀ secondĀ localizationĀ curveĀ basedĀ onĀ theĀ secondĀ localizationĀ dataĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system.Ā InĀ operation Ā 605,Ā processingĀ logicĀ determinesĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference.Ā TheĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ utilizedĀ toĀ compensateĀ planningĀ ofĀ aĀ pathĀ toĀ driveĀ theĀ ADVĀ subsequently.
NoteĀ thatĀ someĀ orĀ allĀ ofĀ theĀ componentsĀ asĀ shownĀ andĀ describedĀ aboveĀ mayĀ beĀ implementedĀ inĀ software,Ā hardware,Ā orĀ aĀ combinationĀ thereof.Ā ForĀ example,Ā suchĀ componentsĀ canĀ beĀ implementedĀ asĀ softwareĀ installedĀ andĀ storedĀ inĀ aĀ persistentĀ storageĀ device,Ā whichĀ canĀ beĀ loadedĀ andĀ executedĀ inĀ aĀ memoryĀ byĀ aĀ processorĀ (notĀ shown)Ā toĀ carryĀ outĀ theĀ processesĀ orĀ operationsĀ describedĀ throughoutĀ thisĀ application.Ā Alternatively,Ā suchĀ componentsĀ canĀ beĀ implementedĀ asĀ executableĀ codeĀ programmedĀ orĀ embeddedĀ intoĀ dedicatedĀ hardwareĀ suchĀ asĀ anĀ integratedĀ circuitĀ (e.g.,Ā anĀ applicationĀ specificĀ ICĀ orĀ ASIC)Ā ,Ā aĀ digitalĀ signalĀ processorĀ (DSP)Ā ,Ā orĀ aĀ fieldĀ programmableĀ gateĀ arrayĀ (FPGA)Ā ,Ā whichĀ canĀ beĀ accessedĀ viaĀ aĀ correspondingĀ driverĀ and/orĀ operatingĀ systemĀ fromĀ anĀ application.Ā Furthermore,Ā suchĀ componentsĀ canĀ beĀ implementedĀ asĀ specificĀ hardwareĀ logicĀ inĀ aĀ processorĀ orĀ processorĀ coreĀ asĀ partĀ ofĀ anĀ instructionĀ setĀ accessibleĀ byĀ aĀ softwareĀ componentĀ viaĀ oneĀ orĀ moreĀ specificĀ instructions.
FigureĀ 7Ā isĀ aĀ blockĀ diagramĀ illustratingĀ anĀ exampleĀ ofĀ aĀ dataĀ processingĀ systemĀ whichĀ mayĀ beĀ usedĀ withĀ oneĀ embodimentĀ ofĀ theĀ disclosure.Ā ForĀ example,Ā system Ā 1500Ā mayĀ representĀ anyĀ ofĀ dataĀ processingĀ systemsĀ describedĀ aboveĀ performingĀ anyĀ ofĀ theĀ processesĀ orĀ methodsĀ describedĀ above,Ā suchĀ as,Ā forĀ example,Ā perceptionĀ andĀ planningĀ system Ā 110Ā orĀ anyĀ ofĀ serversĀ 103-104Ā ofĀ FigureĀ 1.Ā System Ā 1500Ā canĀ includeĀ manyĀ differentĀ components.Ā TheseĀ componentsĀ canĀ beĀ implementedĀ asĀ integratedĀ circuitsĀ (ICs)Ā ,Ā portionsĀ thereof,Ā discreteĀ electronicĀ devices,Ā orĀ otherĀ modulesĀ adaptedĀ toĀ aĀ circuitĀ boardĀ suchĀ asĀ aĀ motherboardĀ orĀ add-inĀ cardĀ ofĀ theĀ computerĀ system,Ā orĀ asĀ componentsĀ otherwiseĀ incorporatedĀ withinĀ aĀ chassisĀ ofĀ theĀ computerĀ system.
NoteĀ alsoĀ thatĀ system Ā 1500Ā isĀ intendedĀ toĀ showĀ aĀ highĀ levelĀ viewĀ ofĀ manyĀ componentsĀ ofĀ theĀ computerĀ system.Ā However,Ā itĀ isĀ toĀ beĀ understoodĀ thatĀ additionalĀ componentsĀ mayĀ beĀ presentĀ inĀ certainĀ implementationsĀ andĀ furthermore,Ā differentĀ arrangementĀ ofĀ theĀ componentsĀ shownĀ mayĀ occurĀ inĀ otherĀ implementations.Ā System Ā 1500Ā mayĀ representĀ aĀ desktop,Ā aĀ laptop,Ā aĀ tablet,Ā aĀ server,Ā aĀ mobileĀ phone,Ā aĀ mediaĀ player,Ā aĀ personalĀ digitalĀ assistantĀ (PDA)Ā ,Ā aĀ Smartwatch,Ā aĀ personalĀ communicator,Ā aĀ gamingĀ device,Ā aĀ networkĀ routerĀ orĀ hub,Ā aĀ wirelessĀ accessĀ pointĀ (AP)Ā orĀ repeater,Ā aĀ set-topĀ box,Ā orĀ aĀ combinationĀ thereof.Ā Further,Ā whileĀ onlyĀ aĀ singleĀ machineĀ orĀ systemĀ isĀ illustrated,Ā theĀ termĀ āmachineāĀ orĀ āsystemāĀ shallĀ alsoĀ beĀ takenĀ toĀ includeĀ anyĀ collectionĀ ofĀ machinesĀ orĀ systemsĀ thatĀ individuallyĀ orĀ jointlyĀ executeĀ aĀ setĀ (orĀ multipleĀ sets)Ā ofĀ instructionsĀ toĀ performĀ anyĀ oneĀ orĀ moreĀ ofĀ theĀ methodologiesĀ discussedĀ herein.
InĀ oneĀ embodiment,Ā system Ā 1500Ā includesĀ processor Ā 1501,Ā memory Ā 1503,Ā andĀ devicesĀ 1505-1508Ā connectedĀ viaĀ aĀ busĀ orĀ anĀ interconnect Ā 1510.Ā Processor Ā 1501Ā mayĀ representĀ aĀ singleĀ processorĀ orĀ multipleĀ processorsĀ withĀ aĀ singleĀ processorĀ coreĀ orĀ multipleĀ processorĀ coresĀ includedĀ therein.Ā Processor Ā 1501Ā mayĀ representĀ oneĀ orĀ moreĀ general-purposeĀ processorsĀ suchĀ asĀ aĀ microprocessor,Ā aĀ centralĀ processingĀ unitĀ (CPU)Ā ,Ā orĀ theĀ like.Ā MoreĀ particularly,Ā processor Ā 1501Ā mayĀ beĀ aĀ complexĀ instructionĀ setĀ computingĀ (CISC)Ā microprocessor,Ā reducedĀ instructionĀ setĀ computingĀ (RISC)Ā microprocessor,Ā veryĀ longĀ instructionĀ wordĀ (VLIW)Ā microprocessor,Ā orĀ processorĀ implementingĀ otherĀ instructionĀ sets,Ā orĀ processorsĀ implementingĀ aĀ combinationĀ ofĀ instructionĀ sets.Ā Processor Ā 1501Ā mayĀ alsoĀ beĀ oneĀ orĀ moreĀ special-purposeĀ processorsĀ suchĀ asĀ anĀ applicationĀ specificĀ integratedĀ circuitĀ (ASIC)Ā ,Ā aĀ cellularĀ orĀ basebandĀ processor,Ā aĀ fieldĀ programmableĀ gateĀ arrayĀ (FPGA)Ā ,Ā aĀ digitalĀ signalĀ processorĀ (DSP)Ā ,Ā aĀ networkĀ processor,Ā aĀ graphicsĀ processor,Ā aĀ communicationsĀ processor,Ā aĀ cryptographicĀ processor,Ā aĀ co-processor,Ā anĀ embeddedĀ processor,Ā orĀ anyĀ otherĀ typeĀ ofĀ logicĀ capableĀ ofĀ processingĀ instructions.
ProcessorĀ 1501Ā mayĀ communicateĀ withĀ memoryĀ 1503,Ā whichĀ inĀ oneĀ embodimentĀ canĀ beĀ implementedĀ viaĀ multipleĀ memoryĀ devicesĀ toĀ provideĀ forĀ aĀ givenĀ amountĀ ofĀ systemĀ memory.Ā MemoryĀ 1503Ā mayĀ includeĀ oneĀ orĀ moreĀ volatileĀ storageĀ (orĀ memory)Ā devicesĀ suchĀ asĀ randomĀ accessĀ memoryĀ (RAM)Ā ,Ā dynamicĀ RAMĀ (DRAM)Ā ,Ā synchronousĀ DRAMĀ (SDRAM)Ā ,Ā staticĀ RAMĀ (SRAM)Ā ,Ā orĀ otherĀ typesĀ ofĀ storageĀ devices.Ā MemoryĀ 1503Ā mayĀ storeĀ informationĀ includingĀ sequencesĀ ofĀ instructionsĀ thatĀ areĀ executedĀ byĀ processorĀ 1501,Ā orĀ anyĀ otherĀ device.Ā ForĀ example,Ā executableĀ codeĀ and/orĀ dataĀ ofĀ aĀ varietyĀ ofĀ operatingĀ systems,Ā deviceĀ drivers,Ā firmwareĀ (e.g.,Ā inputĀ outputĀ basicĀ systemĀ orĀ BIOS)Ā ,Ā and/orĀ applicationsĀ canĀ beĀ loadedĀ inĀ memoryĀ 1503Ā andĀ executedĀ byĀ processorĀ 1501.Ā AnĀ operatingĀ systemĀ canĀ beĀ anyĀ kindĀ ofĀ operatingĀ systems,Ā suchĀ as,Ā forĀ example,Ā RobotĀ OperatingĀ SystemĀ (ROS)Ā ,Ā
operatingĀ systemĀ from
Mac
fromĀ Apple,Ā
from
LINUX,Ā UNIX,Ā orĀ otherĀ real-timeĀ orĀ embeddedĀ operatingĀ systems.
InputĀ deviceĀ (s)Ā 1506Ā mayĀ includeĀ aĀ mouse,Ā aĀ touchĀ pad,Ā aĀ touchĀ sensitiveĀ screenĀ (whichĀ mayĀ beĀ integratedĀ withĀ displayĀ deviceĀ 1504)Ā ,Ā aĀ pointerĀ deviceĀ suchĀ asĀ aĀ stylus,Ā and/orĀ aĀ keyboardĀ (e.g.,Ā physicalĀ keyboardĀ orĀ aĀ virtualĀ keyboardĀ displayedĀ asĀ partĀ ofĀ aĀ touchĀ sensitiveĀ screen)Ā .Ā Ā ForĀ example,Ā inputĀ deviceĀ 1506Ā mayĀ includeĀ aĀ touchĀ screenĀ controllerĀ coupledĀ toĀ aĀ touchĀ screen.Ā TheĀ touchĀ screenĀ andĀ touchĀ screenĀ controllerĀ can,Ā forĀ example,Ā detectĀ contactĀ andĀ movementĀ orĀ breakĀ thereofĀ usingĀ anyĀ ofĀ aĀ pluralityĀ ofĀ touchĀ sensitivityĀ technologies,Ā includingĀ butĀ notĀ limitedĀ toĀ capacitive,Ā resistive,Ā infrared,Ā andĀ surfaceĀ acousticĀ waveĀ technologies,Ā asĀ wellĀ asĀ otherĀ proximityĀ sensorĀ arraysĀ orĀ otherĀ elementsĀ forĀ determiningĀ oneĀ orĀ moreĀ pointsĀ ofĀ contactĀ withĀ theĀ touchĀ screen.
IOĀ devicesĀ 1507Ā mayĀ includeĀ anĀ audioĀ device.Ā AnĀ audioĀ deviceĀ mayĀ includeĀ aĀ speakerĀ and/orĀ aĀ microphoneĀ toĀ facilitateĀ voice-enabledĀ functions,Ā suchĀ asĀ voiceĀ recognition,Ā voiceĀ replication,Ā digitalĀ recording,Ā and/orĀ telephonyĀ functions.Ā OtherĀ IOĀ devicesĀ 1507Ā mayĀ furtherĀ includeĀ universalĀ serialĀ busĀ (USB)Ā portĀ (s)Ā ,Ā parallelĀ portĀ (s)Ā ,Ā serialĀ portĀ (s)Ā ,Ā aĀ printer,Ā aĀ networkĀ interface,Ā aĀ busĀ bridgeĀ (e.g.,Ā aĀ PCI-PCIĀ bridge)Ā ,Ā sensorĀ (s)Ā (e.g.,Ā aĀ motionĀ sensorĀ suchĀ asĀ anĀ accelerometer,Ā gyroscope,Ā aĀ magnetometer,Ā aĀ lightĀ sensor,Ā compass,Ā aĀ proximityĀ sensor,Ā etc.Ā )Ā ,Ā orĀ aĀ combinationĀ thereof.Ā DevicesĀ 1507Ā mayĀ furtherĀ includeĀ anĀ imagingĀ processingĀ subsystemĀ (e.g.,Ā aĀ camera)Ā ,Ā whichĀ mayĀ includeĀ anĀ opticalĀ sensor,Ā suchĀ asĀ aĀ chargedĀ coupledĀ deviceĀ (CCD)Ā orĀ aĀ complementaryĀ metal-oxideĀ semiconductorĀ (CMOS)Ā opticalĀ sensor,Ā utilizedĀ toĀ facilitateĀ cameraĀ functions,Ā suchĀ asĀ recordingĀ photographsĀ andĀ videoĀ clips.Ā CertainĀ sensorsĀ mayĀ beĀ coupledĀ toĀ interconnect Ā 1510Ā viaĀ aĀ sensorĀ hubĀ (notĀ shown)Ā ,Ā whileĀ otherĀ devicesĀ suchĀ asĀ aĀ keyboardĀ orĀ thermalĀ sensorĀ mayĀ beĀ controlledĀ byĀ anĀ embeddedĀ controllerĀ (notĀ shown)Ā ,Ā dependentĀ uponĀ theĀ specificĀ configurationĀ orĀ designĀ ofĀ system Ā 1500.
ToĀ provideĀ forĀ persistentĀ storageĀ ofĀ informationĀ suchĀ asĀ data,Ā applications,Ā oneĀ orĀ moreĀ operatingĀ systemsĀ andĀ soĀ forth,Ā aĀ massĀ storageĀ (notĀ shown)Ā mayĀ alsoĀ coupleĀ toĀ processor Ā 1501.Ā InĀ variousĀ embodiments,Ā toĀ enableĀ aĀ thinnerĀ andĀ lighterĀ systemĀ designĀ asĀ wellĀ asĀ toĀ improveĀ systemĀ responsiveness,Ā thisĀ massĀ storageĀ mayĀ beĀ implementedĀ viaĀ aĀ solidĀ stateĀ deviceĀ (SSD)Ā .Ā HoweverĀ inĀ otherĀ embodiments,Ā theĀ massĀ storageĀ mayĀ primarilyĀ beĀ implementedĀ usingĀ aĀ hardĀ diskĀ driveĀ (HDD)Ā withĀ aĀ smallerĀ amountĀ ofĀ SSDĀ storageĀ toĀ actĀ asĀ aĀ SSDĀ cacheĀ toĀ enableĀ non-volatileĀ storageĀ ofĀ contextĀ stateĀ andĀ otherĀ suchĀ informationĀ duringĀ powerĀ downĀ eventsĀ soĀ thatĀ aĀ fastĀ powerĀ upĀ canĀ occurĀ onĀ re-initiationĀ ofĀ systemĀ activities.Ā AlsoĀ aĀ flashĀ deviceĀ mayĀ beĀ coupledĀ toĀ processor Ā 1501,Ā e.g.,Ā viaĀ aĀ serialĀ peripheralĀ interfaceĀ (SPI)Ā .Ā ThisĀ flashĀ deviceĀ mayĀ provideĀ forĀ non-volatileĀ storageĀ ofĀ systemĀ software,Ā includingĀ BIOSĀ asĀ wellĀ asĀ otherĀ firmwareĀ ofĀ theĀ system.
Computer-readableĀ storageĀ medium Ā 1509Ā mayĀ alsoĀ beĀ usedĀ toĀ storeĀ theĀ someĀ softwareĀ functionalitiesĀ describedĀ aboveĀ persistently.Ā WhileĀ computer-readableĀ storageĀ medium Ā 1509Ā isĀ shownĀ inĀ anĀ exemplaryĀ embodimentĀ toĀ beĀ aĀ singleĀ medium,Ā theĀ termĀ ācomputer-readableĀ storageĀ mediumāĀ shouldĀ beĀ takenĀ toĀ includeĀ aĀ singleĀ mediumĀ orĀ multipleĀ mediaĀ (e.g.,Ā aĀ centralizedĀ orĀ distributedĀ database,Ā and/orĀ associatedĀ cachesĀ andĀ servers)Ā thatĀ storeĀ theĀ oneĀ orĀ moreĀ setsĀ ofĀ instructions.Ā TheĀ termsĀ ācomputer-readableĀ storageĀ mediumāĀ shallĀ alsoĀ beĀ takenĀ toĀ includeĀ anyĀ mediumĀ thatĀ isĀ capableĀ ofĀ storingĀ orĀ encodingĀ aĀ setĀ ofĀ instructionsĀ forĀ executionĀ byĀ theĀ machineĀ andĀ thatĀ causeĀ theĀ machineĀ toĀ performĀ anyĀ oneĀ orĀ moreĀ ofĀ theĀ methodologiesĀ ofĀ theĀ presentĀ disclosure.Ā TheĀ termĀ ācomputer-readableĀ storageĀ mediumāĀ shallĀ accordinglyĀ beĀ takenĀ toĀ include,Ā butĀ notĀ beĀ limitedĀ to,Ā solid-stateĀ memories,Ā andĀ opticalĀ andĀ magneticĀ media,Ā orĀ anyĀ otherĀ non-transitoryĀ machine-readableĀ medium.
ProcessingĀ module/unit/logic Ā 1528,Ā componentsĀ andĀ otherĀ featuresĀ describedĀ hereinĀ canĀ beĀ implementedĀ asĀ discreteĀ hardwareĀ componentsĀ orĀ integratedĀ inĀ theĀ functionalityĀ ofĀ hardwareĀ componentsĀ suchĀ asĀ ASICS,Ā FPGAs,Ā DSPsĀ orĀ similarĀ devices.Ā InĀ addition,Ā processingĀ module/unit/logic Ā 1528Ā canĀ beĀ implementedĀ asĀ firmwareĀ orĀ functionalĀ circuitryĀ withinĀ hardwareĀ devices.Ā Further,Ā processingĀ module/unit/logic Ā 1528Ā canĀ beĀ implementedĀ inĀ anyĀ combinationĀ hardwareĀ devicesĀ andĀ softwareĀ components.
NoteĀ thatĀ whileĀ system Ā 1500Ā isĀ illustratedĀ withĀ variousĀ componentsĀ ofĀ aĀ dataĀ processingĀ system,Ā itĀ isĀ notĀ intendedĀ toĀ representĀ anyĀ particularĀ architectureĀ orĀ mannerĀ ofĀ interconnectingĀ theĀ components;Ā asĀ suchĀ detailsĀ areĀ notĀ germaneĀ toĀ embodimentsĀ ofĀ theĀ presentĀ disclosure.Ā ItĀ willĀ alsoĀ beĀ appreciatedĀ thatĀ networkĀ computers,Ā handheldĀ computers,Ā mobileĀ phones,Ā servers,Ā and/orĀ otherĀ dataĀ processingĀ systemsĀ whichĀ haveĀ fewerĀ componentsĀ orĀ perhapsĀ moreĀ componentsĀ mayĀ alsoĀ beĀ usedĀ withĀ embodimentsĀ ofĀ theĀ disclosure.
SomeĀ portionsĀ ofĀ theĀ precedingĀ detailedĀ descriptionsĀ haveĀ beenĀ presentedĀ inĀ termsĀ ofĀ algorithmsĀ andĀ symbolicĀ representationsĀ ofĀ operationsĀ onĀ dataĀ bitsĀ withinĀ aĀ computerĀ memory.Ā TheseĀ algorithmicĀ descriptionsĀ andĀ representationsĀ areĀ theĀ waysĀ usedĀ byĀ thoseĀ skilledĀ inĀ theĀ dataĀ processingĀ artsĀ toĀ mostĀ effectivelyĀ conveyĀ theĀ substanceĀ ofĀ theirĀ workĀ toĀ othersĀ skilledĀ inĀ theĀ art.Ā AnĀ algorithmĀ isĀ here,Ā andĀ generally,Ā conceivedĀ toĀ beĀ aĀ self-consistentĀ sequenceĀ ofĀ operationsĀ leadingĀ toĀ aĀ desiredĀ result.Ā TheĀ operationsĀ areĀ thoseĀ requiringĀ physicalĀ manipulationsĀ ofĀ physicalĀ quantities.
ItĀ shouldĀ beĀ borneĀ inĀ mind,Ā however,Ā thatĀ allĀ ofĀ theseĀ andĀ similarĀ termsĀ areĀ toĀ beĀ associatedĀ withĀ theĀ appropriateĀ physicalĀ quantitiesĀ andĀ areĀ merelyĀ convenientĀ labelsĀ appliedĀ toĀ theseĀ quantities.Ā UnlessĀ specificallyĀ statedĀ otherwiseĀ asĀ apparentĀ fromĀ theĀ aboveĀ discussion,Ā itĀ isĀ appreciatedĀ thatĀ throughoutĀ theĀ description,Ā discussionsĀ utilizingĀ termsĀ suchĀ asĀ thoseĀ setĀ forthĀ inĀ theĀ claimsĀ below,Ā referĀ toĀ theĀ actionĀ andĀ processesĀ ofĀ aĀ computerĀ system,Ā orĀ similarĀ electronicĀ computingĀ device,Ā thatĀ manipulatesĀ andĀ transformsĀ dataĀ representedĀ asĀ physicalĀ (electronic)Ā quantitiesĀ withinĀ theĀ computerĀ system'sĀ registersĀ andĀ memoriesĀ intoĀ otherĀ dataĀ similarlyĀ representedĀ asĀ physicalĀ quantitiesĀ withinĀ theĀ computerĀ systemĀ memoriesĀ orĀ registersĀ orĀ otherĀ suchĀ informationĀ storage,Ā transmissionĀ orĀ displayĀ devices.
EmbodimentsĀ ofĀ theĀ disclosureĀ alsoĀ relateĀ toĀ anĀ apparatusĀ forĀ performingĀ theĀ operationsĀ herein.Ā SuchĀ aĀ computerĀ programĀ isĀ storedĀ inĀ aĀ non-transitoryĀ computerĀ readableĀ medium.Ā AĀ machine-readableĀ mediumĀ includesĀ anyĀ mechanismĀ forĀ storingĀ informationĀ inĀ aĀ formĀ readableĀ byĀ aĀ machineĀ (e.g.,Ā aĀ computer)Ā .Ā ForĀ example,Ā aĀ machine-readableĀ (e.g.,Ā computer-readable)Ā mediumĀ includesĀ aĀ machineĀ (e.g.,Ā aĀ computer)Ā readableĀ storageĀ mediumĀ (e.g.,Ā readĀ onlyĀ memoryĀ (Ā āROMāĀ )Ā ,Ā randomĀ accessĀ memoryĀ (Ā āRAMāĀ )Ā ,Ā magneticĀ diskĀ storageĀ media,Ā opticalĀ storageĀ media,Ā flashĀ memoryĀ devices)Ā .
TheĀ processesĀ orĀ methodsĀ depictedĀ inĀ theĀ precedingĀ figuresĀ mayĀ beĀ performedĀ byĀ processingĀ logicĀ thatĀ comprisesĀ hardwareĀ (e.g.Ā circuitry,Ā dedicatedĀ logic,Ā etc.Ā )Ā ,Ā softwareĀ (e.g.,Ā embodiedĀ onĀ aĀ non-transitoryĀ computerĀ readableĀ medium)Ā ,Ā orĀ aĀ combinationĀ ofĀ both.Ā AlthoughĀ theĀ processesĀ orĀ methodsĀ areĀ describedĀ aboveĀ inĀ termsĀ ofĀ someĀ sequentialĀ operations,Ā itĀ shouldĀ beĀ appreciatedĀ thatĀ someĀ ofĀ theĀ operationsĀ describedĀ mayĀ beĀ performedĀ inĀ aĀ differentĀ order.Ā Moreover,Ā someĀ operationsĀ mayĀ beĀ performedĀ inĀ parallelĀ ratherĀ thanĀ sequentially.
EmbodimentsĀ ofĀ theĀ presentĀ disclosureĀ areĀ notĀ describedĀ withĀ referenceĀ toĀ anyĀ particularĀ programmingĀ language.Ā ItĀ willĀ beĀ appreciatedĀ thatĀ aĀ varietyĀ ofĀ programmingĀ languagesĀ mayĀ beĀ usedĀ toĀ implementĀ theĀ teachingsĀ ofĀ embodimentsĀ ofĀ theĀ disclosureĀ asĀ describedĀ herein.
InĀ theĀ foregoingĀ specification,Ā embodimentsĀ ofĀ theĀ disclosureĀ haveĀ beenĀ describedĀ withĀ referenceĀ toĀ specificĀ exemplaryĀ embodimentsĀ thereof.Ā ItĀ willĀ beĀ evidentĀ thatĀ variousĀ modificationsĀ mayĀ beĀ madeĀ theretoĀ withoutĀ departingĀ fromĀ theĀ broaderĀ spiritĀ andĀ scopeĀ ofĀ theĀ disclosureĀ asĀ setĀ forthĀ inĀ theĀ followingĀ claims.Ā TheĀ specificationĀ andĀ drawingsĀ are,Ā accordingly,Ā toĀ beĀ regardedĀ inĀ anĀ illustrativeĀ senseĀ ratherĀ thanĀ aĀ restrictiveĀ sense.
Claims (21)
- AĀ computer-implementedĀ methodĀ forĀ determiningĀ aĀ systemĀ delayĀ ofĀ localizationĀ ofĀ autonomousĀ drivingĀ vehicles,Ā theĀ methodĀ comprising:receivingĀ firstĀ localizationĀ dataĀ ofĀ aĀ firstĀ localizationĀ performedĀ byĀ aĀ firstĀ localizationĀ systemĀ ofĀ anĀ autonomousĀ drivingĀ vehicleĀ (ADV)Ā drivingĀ alongĀ aĀ path;receivingĀ secondĀ localizationĀ dataĀ ofĀ aĀ secondĀ localizationĀ performedĀ byĀ aĀ secondĀ localizationĀ systemĀ ofĀ theĀ ADVĀ alongĀ theĀ path,Ā whereinĀ theĀ firstĀ localizationĀ andĀ theĀ secondĀ localizationĀ areĀ performedĀ concurrentlyĀ onĀ theĀ ADV;generatingĀ aĀ firstĀ localizationĀ curveĀ basedĀ onĀ theĀ firstĀ localizationĀ dataĀ representingĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system;generatingĀ aĀ secondĀ localizationĀ curveĀ basedĀ onĀ theĀ secondĀ localizationĀ dataĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system;Ā anddeterminingĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference,Ā whereinĀ theĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ utilizedĀ toĀ compensateĀ planningĀ ofĀ aĀ pathĀ toĀ driveĀ theĀ ADVĀ subsequently.
- TheĀ methodĀ ofĀ claimĀ 1,Ā furtherĀ comprisingĀ determiningĀ aĀ performanceĀ ofĀ theĀ secondĀ localizationĀ systemĀ basedĀ onĀ theĀ comparisonĀ ofĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ methodĀ ofĀ claimĀ 2,Ā whereinĀ theĀ performanceĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ determinedĀ basedĀ onĀ aĀ similarityĀ ofĀ shapesĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ methodĀ ofĀ claimĀ 1,Ā whereinĀ determiningĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ comprises:forĀ eachĀ ofĀ aĀ predeterminedĀ numberĀ ofĀ timeĀ intervals,shiftingĀ theĀ secondĀ localizationĀ curveĀ inĀ timeĀ byĀ theĀ timeĀ interval,Ā andcalculatingĀ aĀ similarityĀ scoreĀ representingĀ aĀ similarityĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curveĀ withinĀ aĀ timeĀ window;Ā anddesignatingĀ aĀ timeĀ intervalĀ ofĀ whichĀ theĀ correspondingĀ similarityĀ scoreĀ isĀ highestĀ amongstĀ theĀ predeterminedĀ numberĀ ofĀ timeĀ intervalsĀ asĀ theĀ systemĀ delayĀ forĀ theĀ secondĀ localizationĀ system.
- TheĀ methodĀ ofĀ claimĀ 4,Ā whereinĀ theĀ highestĀ similarityĀ scoreĀ isĀ usedĀ toĀ representĀ aĀ performanceĀ ofĀ theĀ secondĀ localizationĀ system.
- TheĀ methodĀ ofĀ claimĀ 4,Ā whereinĀ calculatingĀ aĀ similarityĀ scoreĀ representingĀ aĀ similarityĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curveĀ comprisesĀ calculatingĀ aĀ correlationĀ coefficientĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ methodĀ ofĀ claimĀ 1,Ā whereinĀ theĀ firstĀ localizationĀ isĀ performedĀ usingĀ aĀ firstĀ setĀ ofĀ sensorsĀ associatedĀ withĀ knownĀ qualityĀ andĀ precision,Ā andĀ whereinĀ theĀ secondĀ localizationĀ isĀ performedĀ usingĀ aĀ secondĀ setĀ ofĀ sensorsĀ toĀ beĀ deployedĀ inĀ theĀ ADVĀ duringĀ normalĀ operations.
- AĀ non-transitoryĀ machine-readableĀ mediumĀ havingĀ instructionsĀ storedĀ therein,Ā whichĀ whenĀ executedĀ byĀ aĀ processor,Ā causeĀ theĀ processorĀ toĀ performĀ operations,Ā theĀ operationsĀ comprising:receivingĀ firstĀ localizationĀ dataĀ ofĀ aĀ firstĀ localizationĀ performedĀ byĀ aĀ firstĀ localizationĀ systemĀ ofĀ anĀ autonomousĀ drivingĀ vehicleĀ (ADV)Ā drivingĀ alongĀ aĀ path;receivingĀ secondĀ localizationĀ dataĀ ofĀ aĀ secondĀ localizationĀ performedĀ byĀ aĀ secondĀ localizationĀ systemĀ ofĀ theĀ ADVĀ alongĀ theĀ path,Ā whereinĀ theĀ firstĀ localizationĀ andĀ theĀ secondĀ localizationĀ areĀ performedĀ concurrentlyĀ onĀ theĀ ADV;generatingĀ aĀ firstĀ localizationĀ curveĀ basedĀ onĀ theĀ firstĀ localizationĀ dataĀ representingĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system;generatingĀ aĀ secondĀ localizationĀ curveĀ basedĀ onĀ theĀ secondĀ localizationĀ dataĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system;Ā anddeterminingĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference,Ā whereinĀ theĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ utilizedĀ toĀ compensateĀ planningĀ ofĀ aĀ pathĀ toĀ driveĀ theĀ ADVĀ subsequently.
- TheĀ machine-readableĀ mediumĀ ofĀ claimĀ 8,Ā whereinĀ theĀ operationsĀ furtherĀ compriseĀ determiningĀ aĀ performanceĀ ofĀ theĀ secondĀ localizationĀ systemĀ basedĀ onĀ theĀ comparisonĀ ofĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ machine-readableĀ mediumĀ ofĀ claimĀ 9,Ā whereinĀ theĀ performanceĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ determinedĀ basedĀ onĀ aĀ similarityĀ ofĀ shapesĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ machine-readableĀ mediumĀ ofĀ claimĀ 8,Ā whereinĀ determiningĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ comprises:forĀ eachĀ ofĀ aĀ predeterminedĀ numberĀ ofĀ timeĀ intervals,shiftingĀ theĀ secondĀ localizationĀ curveĀ inĀ timeĀ byĀ theĀ timeĀ interval,Ā andcalculatingĀ aĀ similarityĀ scoreĀ representingĀ aĀ similarityĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curveĀ withinĀ aĀ timeĀ window;Ā anddesignatingĀ aĀ timeĀ intervalĀ ofĀ whichĀ theĀ correspondingĀ similarityĀ scoreĀ isĀ highestĀ amongstĀ theĀ predeterminedĀ numberĀ ofĀ timeĀ intervalsĀ asĀ theĀ systemĀ delayĀ forĀ theĀ secondĀ localizationĀ system.
- TheĀ machine-readableĀ mediumĀ ofĀ claimĀ 11,Ā whereinĀ theĀ highestĀ similarityĀ scoreĀ isĀ usedĀ toĀ representĀ aĀ performanceĀ ofĀ theĀ secondĀ localizationĀ system.
- TheĀ machine-readableĀ mediumĀ ofĀ claimĀ 11,Ā whereinĀ calculatingĀ aĀ similarityĀ scoreĀ representingĀ aĀ similarityĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curveĀ comprisesĀ calculatingĀ aĀ correlationĀ coefficientĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ machine-readableĀ mediumĀ ofĀ claimĀ 8,Ā whereinĀ theĀ firstĀ localizationĀ isĀ performedĀ usingĀ aĀ firstĀ setĀ ofĀ sensorsĀ associatedĀ withĀ knownĀ qualityĀ andĀ precision,Ā andĀ whereinĀ theĀ secondĀ localizationĀ isĀ performedĀ usingĀ aĀ secondĀ setĀ ofĀ sensorsĀ toĀ beĀ deployedĀ inĀ theĀ ADVĀ duringĀ normalĀ operations.
- AĀ dataĀ processingĀ system,Ā comprising:aĀ processor;Ā andaĀ memoryĀ coupledĀ toĀ theĀ processorĀ toĀ storeĀ instructions,Ā whichĀ whenĀ executedĀ byĀ theĀ processor,Ā causeĀ theĀ processorĀ toĀ performĀ operations,Ā theĀ operationsĀ includingreceivingĀ firstĀ localizationĀ dataĀ ofĀ aĀ firstĀ localizationĀ performedĀ byĀ aĀ firstĀ localizationĀ systemĀ ofĀ anĀ autonomousĀ drivingĀ vehicleĀ (ADV)Ā drivingĀ alongĀ aĀ path,receivingĀ secondĀ localizationĀ dataĀ ofĀ aĀ secondĀ localizationĀ performedĀ byĀ aĀ secondĀ localizationĀ systemĀ ofĀ theĀ ADVĀ alongĀ theĀ path,Ā whereinĀ theĀ firstĀ localizationĀ andĀ theĀ secondĀ localizationĀ areĀ performedĀ concurrentlyĀ onĀ theĀ ADV,generatingĀ aĀ firstĀ localizationĀ curveĀ basedĀ onĀ theĀ firstĀ localizationĀ dataĀ representingĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ firstĀ localizationĀ system,generatingĀ aĀ secondĀ localizationĀ curveĀ basedĀ onĀ theĀ secondĀ localizationĀ dataĀ representingĀ theĀ locationsĀ ofĀ theĀ ADVĀ alongĀ theĀ pathĀ trackedĀ byĀ theĀ secondĀ localizationĀ system,Ā anddeterminingĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ byĀ comparingĀ theĀ secondĀ localizationĀ curveĀ againstĀ theĀ firstĀ localizationĀ curveĀ asĀ aĀ localizationĀ reference,Ā whereinĀ theĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ utilizedĀ toĀ compensateĀ planningĀ ofĀ aĀ pathĀ toĀ driveĀ theĀ ADVĀ subsequently.
- TheĀ systemĀ ofĀ claimĀ 15,Ā whereinĀ theĀ operationsĀ furtherĀ compriseĀ determiningĀ aĀ performanceĀ ofĀ theĀ secondĀ localizationĀ systemĀ basedĀ onĀ theĀ comparisonĀ ofĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ systemĀ ofĀ claimĀ 16,Ā whereinĀ theĀ performanceĀ ofĀ theĀ secondĀ localizationĀ systemĀ isĀ determinedĀ basedĀ onĀ aĀ similarityĀ ofĀ shapesĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ systemĀ ofĀ claimĀ 15,Ā whereinĀ determiningĀ aĀ systemĀ delayĀ ofĀ theĀ secondĀ localizationĀ systemĀ comprises:forĀ eachĀ ofĀ aĀ predeterminedĀ numberĀ ofĀ timeĀ intervals,shiftingĀ theĀ secondĀ localizationĀ curveĀ inĀ timeĀ byĀ theĀ timeĀ interval,Ā andcalculatingĀ aĀ similarityĀ scoreĀ representingĀ aĀ similarityĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curveĀ withinĀ aĀ timeĀ window;Ā anddesignatingĀ aĀ timeĀ intervalĀ ofĀ whichĀ theĀ correspondingĀ similarityĀ scoreĀ isĀ highestĀ amongstĀ theĀ predeterminedĀ numberĀ ofĀ timeĀ intervalsĀ asĀ theĀ systemĀ delayĀ forĀ theĀ secondĀ localizationĀ system.
- TheĀ systemĀ ofĀ claimĀ 18,Ā whereinĀ theĀ highestĀ similarityĀ scoreĀ isĀ usedĀ toĀ representĀ aĀ performanceĀ ofĀ theĀ secondĀ localizationĀ system.
- TheĀ systemĀ ofĀ claimĀ 18,Ā whereinĀ calculatingĀ aĀ similarityĀ scoreĀ representingĀ aĀ similarityĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curveĀ comprisesĀ calculatingĀ aĀ correlationĀ coefficientĀ betweenĀ theĀ firstĀ localizationĀ curveĀ andĀ theĀ secondĀ localizationĀ curve.
- TheĀ systemĀ ofĀ claimĀ 15,Ā whereinĀ theĀ firstĀ localizationĀ isĀ performedĀ usingĀ aĀ firstĀ setĀ ofĀ sensorsĀ associatedĀ withĀ knownĀ qualityĀ andĀ precision,Ā andĀ whereinĀ theĀ secondĀ localizationĀ isĀ performedĀ usingĀ aĀ secondĀ setĀ ofĀ sensorsĀ toĀ beĀ deployedĀ inĀ theĀ ADVĀ duringĀ normalĀ operations.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US16/066,300 US11036225B2 (en) | 2018-04-18 | 2018-04-18 | Method for evaluating localization system of autonomous driving vehicles |
| EP18915040.2A EP3669247A4 (en) | 2018-04-18 | 2018-04-18 | Method for evaluating localization system of autonomous driving vehicles |
| CN201880053208.6A CN111033423B (en) | 2018-04-18 | 2018-04-18 | Methods for evaluating positioning systems for autonomous vehicles |
| PCT/CN2018/083558 WO2019200564A1 (en) | 2018-04-18 | 2018-04-18 | Method for evaluating localization system of autonomous driving vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/083558 WO2019200564A1 (en) | 2018-04-18 | 2018-04-18 | Method for evaluating localization system of autonomous driving vehicles |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019200564A1 true WO2019200564A1 (en) | 2019-10-24 |
Family
ID=68240535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/083558 Ceased WO2019200564A1 (en) | 2018-04-18 | 2018-04-18 | Method for evaluating localization system of autonomous driving vehicles |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US11036225B2 (en) |
| EP (1) | EP3669247A4 (en) |
| CN (1) | CN111033423B (en) |
| WO (1) | WO2019200564A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116125965A (en) * | 2021-11-15 | 2023-05-16 | åØęAdęéč“£ä»»å ¬åø | System and method for a vehicle |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11199847B2 (en) * | 2018-09-26 | 2021-12-14 | Baidu Usa Llc | Curvature corrected path sampling system for autonomous driving vehicles |
| CN111412929A (en) * | 2020-04-26 | 2020-07-14 | äøé£ę±½č½¦éå¢ęéå ¬åø | A method for evaluating the performance of combined inertial navigation based on high-precision maps |
| US12164306B1 (en) * | 2021-11-19 | 2024-12-10 | Zoox, Inc. | Adaptable origin for location offsets |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5317515A (en) * | 1991-01-23 | 1994-05-31 | Sumitomo Electric Industries, Ltd. | Vehicle heading correction apparatus |
| DE102011119762A1 (en) * | 2011-11-30 | 2012-06-06 | Daimler Ag | Positioning system for motor vehicle, has processing unit that determines localized position of vehicle using vehicle movement data measured based on specific location data stored in digital card |
| CN103064417A (en) * | 2012-12-21 | 2013-04-24 | äøęµ·äŗ¤éå¤§å¦ | Global localization guiding system and method based on multiple sensors |
| US20140095067A1 (en) | 2011-08-24 | 2014-04-03 | Denso Corporation | Travel trace storage apparatus |
| US20140297092A1 (en) * | 2013-03-26 | 2014-10-02 | Toyota Motor Engineering & Manufacturing North America, Inc. | Intensity map-based localization with adaptive thresholding |
| US20160097862A1 (en) | 2014-10-06 | 2016-04-07 | Hyundai Mobis Co., Ltd. | System and method for complex navigation using dead reckoning and gps |
| US20160282936A1 (en) | 2015-03-26 | 2016-09-29 | Honeywell International Inc. | Methods and apparatus for providing a snapshot truthing system for a tracker |
| KR20170119188A (en) | 2016-04-18 | 2017-10-26 | ģ¬ėØė²ģøģ°Øģøėģµķ©źø°ģ ģ°źµ¬ģ | Localization method for autonomous vehicle |
| WO2018063426A1 (en) * | 2016-09-27 | 2018-04-05 | Baidu Usa Llc | A vehicle position point forwarding method for autonomous vehicles |
Family Cites Families (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6278907B1 (en) * | 1999-11-24 | 2001-08-21 | Xerox Corporation | Apparatus and method of distributing object handling |
| EP2570772A1 (en) * | 2011-09-16 | 2013-03-20 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method for localisation and mapping of pedestrians or robots using wireless access points |
| US20140297090A1 (en) * | 2011-11-11 | 2014-10-02 | Hitachi, Ltd. | Autonomous Mobile Method and Autonomous Mobile Device |
| JP5846000B2 (en) * | 2012-03-28 | 2016-01-20 | ęē°ę©ę¢°ę Ŗå¼ä¼ē¤¾ | Yarn traveling information acquisition device |
| EP2835616A1 (en) * | 2013-08-09 | 2015-02-11 | Ams Ag | Position sensor device to determine a position of a moving device |
| DE102014203723A1 (en) * | 2014-02-28 | 2015-09-03 | Robert Bosch Gmbh | Method for operating mobile platforms |
| FR3028084B1 (en) * | 2014-11-03 | 2020-12-25 | Sagem Defense Securite | METHOD AND DEVICE FOR GUIDING AN AIRCRAFT |
| CN104614704B (en) * | 2015-01-29 | 2019-05-24 | ē¾åŗ¦åØēŗæē½ē»ęęÆļ¼åäŗ¬ļ¼ęéå ¬åø | A kind of method and apparatus of determining mobile terminal locations |
| WO2016193897A1 (en) * | 2015-05-29 | 2016-12-08 | Verity Studios Ag | Methods and systems for scheduling the transmission of localization signals and operating self-localizing apparatus |
| CN105355210B (en) * | 2015-10-30 | 2020-06-23 | ē¾åŗ¦åØēŗæē½ē»ęęÆļ¼åäŗ¬ļ¼ęéå ¬åø | Preprocessing method and device for far-field speech recognition |
| US9671500B1 (en) * | 2015-12-22 | 2017-06-06 | GM Global Technology Operations LLC | Systems and methods for locating a vehicle |
| US20170285176A1 (en) * | 2016-03-31 | 2017-10-05 | GM Global Technology Operations LLC | Systems and methods for locating a vehicle |
| CN105891810B (en) * | 2016-05-25 | 2018-08-14 | äøå½ē§å¦é¢å£°å¦ē ē©¶ę | A kind of quick self-adapted joint delay time estimation method |
| US10331138B2 (en) * | 2016-07-05 | 2019-06-25 | Baidu Usa Llc | Standard scene-based planning control methods for operating autonomous vehicles |
| US10248124B2 (en) * | 2016-07-21 | 2019-04-02 | Mobileye Vision Technologies, Inc. | Localizing vehicle navigation using lane measurements |
| US10838426B2 (en) * | 2016-07-21 | 2020-11-17 | Mobileye Vision Technologies Ltd. | Distributing a crowdsourced sparse map for autonomous vehicle navigation |
| CN107666638B (en) * | 2016-07-29 | 2019-02-05 | č ¾č®Æē§ęļ¼ę·±å³ļ¼ęéå ¬åø | A kind of method and terminal device for estimating tape-delayed |
| US10435015B2 (en) * | 2016-09-28 | 2019-10-08 | Baidu Usa Llc | System delay corrected control method for autonomous vehicles |
| CN107144819B (en) * | 2017-04-10 | 2019-11-26 | ęč§ę空ē§ęę é”ęéå ¬åø | A kind of sound localization method, device and electronic equipment |
| US10551509B2 (en) * | 2017-06-30 | 2020-02-04 | GM Global Technology Operations LLC | Methods and systems for vehicle localization |
| US10983199B2 (en) * | 2017-08-11 | 2021-04-20 | Zoox, Inc. | Vehicle sensor calibration and localization |
| US10332395B1 (en) * | 2017-12-21 | 2019-06-25 | Denso International America, Inc. | System and method for translating roadside device position data according to differential position data |
| US10503760B2 (en) * | 2018-03-29 | 2019-12-10 | Aurora Innovation, Inc. | Use of relative atlas in an autonomous vehicle |
-
2018
- 2018-04-18 EP EP18915040.2A patent/EP3669247A4/en not_active Withdrawn
- 2018-04-18 US US16/066,300 patent/US11036225B2/en active Active
- 2018-04-18 WO PCT/CN2018/083558 patent/WO2019200564A1/en not_active Ceased
- 2018-04-18 CN CN201880053208.6A patent/CN111033423B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5317515A (en) * | 1991-01-23 | 1994-05-31 | Sumitomo Electric Industries, Ltd. | Vehicle heading correction apparatus |
| US20140095067A1 (en) | 2011-08-24 | 2014-04-03 | Denso Corporation | Travel trace storage apparatus |
| DE102011119762A1 (en) * | 2011-11-30 | 2012-06-06 | Daimler Ag | Positioning system for motor vehicle, has processing unit that determines localized position of vehicle using vehicle movement data measured based on specific location data stored in digital card |
| CN103064417A (en) * | 2012-12-21 | 2013-04-24 | äøęµ·äŗ¤éå¤§å¦ | Global localization guiding system and method based on multiple sensors |
| US20140297092A1 (en) * | 2013-03-26 | 2014-10-02 | Toyota Motor Engineering & Manufacturing North America, Inc. | Intensity map-based localization with adaptive thresholding |
| US20160097862A1 (en) | 2014-10-06 | 2016-04-07 | Hyundai Mobis Co., Ltd. | System and method for complex navigation using dead reckoning and gps |
| US20160282936A1 (en) | 2015-03-26 | 2016-09-29 | Honeywell International Inc. | Methods and apparatus for providing a snapshot truthing system for a tracker |
| KR20170119188A (en) | 2016-04-18 | 2017-10-26 | ģ¬ėØė²ģøģ°Øģøėģµķ©źø°ģ ģ°źµ¬ģ | Localization method for autonomous vehicle |
| WO2018063426A1 (en) * | 2016-09-27 | 2018-04-05 | Baidu Usa Llc | A vehicle position point forwarding method for autonomous vehicles |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3669247A4 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116125965A (en) * | 2021-11-15 | 2023-05-16 | åØęAdęéč“£ä»»å ¬åø | System and method for a vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111033423B (en) | 2023-11-21 |
| EP3669247A4 (en) | 2021-04-21 |
| US11036225B2 (en) | 2021-06-15 |
| EP3669247A1 (en) | 2020-06-24 |
| CN111033423A (en) | 2020-04-17 |
| US20200125091A1 (en) | 2020-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11305765B2 (en) | Method for predicting movement of moving objects relative to an autonomous driving vehicle | |
| US10807599B2 (en) | Driving scenario based lane guidelines for path planning of autonomous driving vehicles | |
| US10990101B2 (en) | Method for drifting correction for planning a path for autonomous driving vehicles | |
| US11199846B2 (en) | Learning-based dynamic modeling methods for autonomous driving vehicles | |
| US20200004265A1 (en) | Autonomous driving vehicles with redundant ultrasonic radar | |
| US11260880B2 (en) | Map-less and localization-less lane following method for autonomous driving of autonomous driving vehicles on highway | |
| EP3659884B1 (en) | Predetermined calibration table-based method for operating an autonomous driving vehicle | |
| WO2020062033A1 (en) | Control dominated three-point turn planning for autonomous driving vehicles | |
| WO2020062030A1 (en) | A spiral path based three-point turn planning for autonomous driving vehicles | |
| WO2020132956A1 (en) | Torque feedback based vehicle longitudinal automatic calibration system for autonomous driving vehicles | |
| US11136023B2 (en) | Method for determining exiting intersection of moving objects for autonomous driving vehicles | |
| WO2020010489A1 (en) | A speed control command auto-calibration system for autonomous vehicles | |
| EP3659886B1 (en) | Method to determine vehicle load of autonomous driving vehicle using predetermined load calibration tables | |
| US11036225B2 (en) | Method for evaluating localization system of autonomous driving vehicles | |
| US10788839B2 (en) | Planning-control collaboration design for low cost autonomous driving technology | |
| US11247700B2 (en) | Enumeration-based three-point turn planning for autonomous driving vehicles | |
| WO2020191712A1 (en) | A map-less and camera-based lane markings sampling method for level-3 autonomous driving vehicles | |
| WO2020132954A1 (en) | Optimal planner switch method for three point turn of autonomous driving vehicles | |
| WO2020132945A1 (en) | Method and system for generating reference lines for autonomous driving vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18915040 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2018915040 Country of ref document: EP Effective date: 20200318 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |