WO2022095453A1 - 一种识别障碍物的方法、装置、介质和电子设备 - Google Patents

一种识别障碍物的方法、装置、介质和电子设备 Download PDF

Info

Publication number
WO2022095453A1
WO2022095453A1 PCT/CN2021/100714 CN2021100714W WO2022095453A1 WO 2022095453 A1 WO2022095453 A1 WO 2022095453A1 CN 2021100714 W CN2021100714 W CN 2021100714W WO 2022095453 A1 WO2022095453 A1 WO 2022095453A1
Authority
WO
WIPO (PCT)
Prior art keywords
obstacle
type
current
feature information
identification feature
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
Application number
PCT/CN2021/100714
Other languages
English (en)
French (fr)
Inventor
侯峥韬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Roborock Innovation Technology Co Ltd
Original Assignee
Beijing Roborock Innovation Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Roborock Innovation Technology Co Ltd filed Critical Beijing Roborock Innovation Technology Co Ltd
Priority to US18/252,035 priority Critical patent/US12564303B2/en
Priority to EP21888156.3A priority patent/EP4242911A4/en
Publication of WO2022095453A1 publication Critical patent/WO2022095453A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/24—Floor-sweeping machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4061—Steering means; Means for avoiding obstacles; Details related to the place where the driver is accommodated
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L23/00—Cleaning footwear
    • A47L23/20—Devices or implements for drying footwear, also with heating arrangements
    • A47L23/205—Devices or implements for drying footwear, also with heating arrangements with heating arrangements
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L9/00—Details or accessories of suction cleaners, e.g. mechanical means for controlling the suction or for effecting pulsating action; Storing devices specially adapted to suction cleaners or parts thereof; Carrying-vehicles specially adapted for suction cleaners
    • A47L9/28—Installation of the electric equipment, e.g. adaptation or attachment to the suction cleaner; Controlling suction cleaners by electric means
    • A47L9/2805—Parameters or conditions being sensed
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L9/00—Details or accessories of suction cleaners, e.g. mechanical means for controlling the suction or for effecting pulsating action; Storing devices specially adapted to suction cleaners or parts thereof; Carrying-vehicles specially adapted for suction cleaners
    • A47L9/28—Installation of the electric equipment, e.g. adaptation or attachment to the suction cleaner; Controlling suction cleaners by electric means
    • A47L9/2836—Installation of the electric equipment, e.g. adaptation or attachment to the suction cleaner; Controlling suction cleaners by electric means characterised by the parts which are controlled
    • A47L9/2852—Elements for displacement of the vacuum cleaner or the accessories therefor, e.g. wheels, casters or nozzles
    • 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
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/243—Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals
    • 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
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/246—Arrangements for determining position or orientation using environment maps, e.g. simultaneous localisation and mapping [SLAM]
    • 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
    • G05D1/60—Intended control result
    • G05D1/644—Optimisation of travel parameters, e.g. of energy consumption, journey time or distance
    • G05D1/6445—Optimisation of travel parameters, e.g. of energy consumption, journey time or distance for optimising payload operation, e.g. camera or spray coverage
    • 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
    • G05D1/60—Intended control result
    • G05D1/656—Interaction with payloads or external entities
    • G05D1/689—Pointing payloads towards fixed or moving targets
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
    • A47L2201/04—Automatic control of the travelling movement; Automatic obstacle detection
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2105/00—Specific applications of the controlled vehicles
    • G05D2105/10—Specific applications of the controlled vehicles for cleaning, vacuuming or polishing
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2107/00—Specific environments of the controlled vehicles
    • G05D2107/40—Indoor domestic environment
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2109/00—Types of controlled vehicles
    • G05D2109/10—Land vehicles
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2111/00—Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
    • G05D2111/10—Optical signals

Definitions

  • the present disclosure relates to the field of robotics, and in particular, to a method, apparatus, medium and electronic device for identifying obstacles.
  • the walking robot sends the ground conditions back to the computer through sensors or cameras, and the computer makes judgments based on the road conditions, and then stably walks back and forth, left and right.
  • a sweeping robot also known as automatic cleaning machine, smart vacuum cleaner, robot vacuum cleaner, etc., is a smart home device that can automatically clean the ground. It can automatically complete the floor cleaning work in the room with artificial intelligence.
  • the purpose of the present disclosure is to provide a method, device, medium and electronic device for identifying obstacles, which can solve at least one of the above-mentioned technical problems.
  • the specific plans are as follows:
  • the present disclosure provides a method for identifying obstacles, including:
  • the target type of the obstacle is determined.
  • the identification feature information includes at least an obstacle type; when the current identification feature information does not meet the identification condition, detouring to more than one position around the obstacle includes: obtaining the The current position of the obstacle; query the environment map based on the current position, and obtain the obstacle type marked corresponding to the current position; when the marked obstacle type does not match the current obstacle type, detour to the obstacle more than one location around the object.
  • the identification feature information further includes a confidence value of the obstacle type; when the current identification feature information does not meet the identification condition, detour to more than one position around the obstacle , including: when the confidence value of the current obstacle type is less than a preset confidence threshold, detouring to more than one position around the obstacle.
  • determining the target type of the obstacle according to all identification feature information of the obstacle includes: classifying and counting all obstacle types of the obstacle, and obtaining each obstacle type The statistical value of ; determine the obstacle type corresponding to the maximum statistical value as the target type.
  • determining the target type of the obstacle according to all identification feature information of the obstacle includes: screening all confidence values of the obstacle, and obtaining the confidence value greater than or equal to the first obstacle type with the preset reliability threshold; classify and count all the first obstacle types, and obtain the statistical value of each first obstacle type; determine that the first obstacle type corresponding to the maximum statistical value is all the first obstacle types. Describe the target type.
  • the method further includes: when the marked obstacle type does not match the current obstacle type, determining the marked obstacle type for misidentified information.
  • the method further includes: when detouring the obstacle, collecting actual area information of the obstacle; after the determining that the marked obstacle type is misidentified information, further comprising: : transmit the target type and the actual area information to the environment map.
  • the present disclosure provides a device for identifying obstacles, including:
  • an obtaining unit used for obtaining the current identification feature information of the obstacle in the process of identifying an obstacle
  • a detour unit used for detouring to more than one position around the obstacle when the current identification feature information does not meet the identification conditions, and correspondingly acquiring the identification feature information of the obstacle at each position;
  • a determining unit configured to determine the target type of the obstacle according to all identification feature information of the obstacle.
  • the identification feature information includes at least the type of the obstacle; in the detour unit, it includes: a subunit for obtaining a current position, for obtaining the current position of the obstacle; a subunit for querying Query the environment map based on the current position, and obtain the obstacle type marked corresponding to the current position; the first detour subunit is used for detouring to when the marked obstacle type does not match the current obstacle type more than one location around the obstacle.
  • the identification feature information further includes a confidence value of the obstacle type;
  • the detour unit includes: a second detour sub-unit for when the current obstacle type is When the confidence value is less than the preset confidence threshold, detour to more than one position around the obstacle.
  • the determining unit includes: a first statistical subunit, configured to classify and count all obstacle types of the obstacle, and obtain a statistical value of each obstacle type; a first determining target type subunit The unit is used to determine that the obstacle type corresponding to the maximum statistical value is the target type.
  • the determining unit includes: a screening subunit, configured to screen all confidence values of the obstacles, and obtain a first obstacle whose confidence value is greater than or equal to a preset confidence threshold type; a second statistical subunit, used to classify and count all the first obstacle types, and obtain the statistical value of each first obstacle type; a second target type determination subunit, used to determine the first obstacle corresponding to the maximum statistical value.
  • An obstacle type is the target type.
  • the device further includes: a marking unit, configured to determine that the marked obstacle type is misidentification information when the marked obstacle type does not match the current obstacle type.
  • the device further comprises: a collecting area information unit, used for collecting actual area information of the obstacle when detouring the obstacle; a transmitting unit, used for determining the mark when After the obstacle type is misidentified information, the target type and the actual area information are transmitted to the environment map.
  • the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the identification of an obstacle according to any one of the first aspect method of things.
  • the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are When executed by the one or more processors, the one or more processors are caused to implement the method for identifying an obstacle according to any one of the first aspect.
  • the present disclosure provides a method, apparatus, medium and electronic device for identifying obstacles.
  • the present disclosure identifies an obstacle, and when the identification feature information does not meet the identification conditions, the obstacle is bypassed, the identification feature information of multiple positions of the current obstacle is continued to be collected, and the target type of the obstacle is determined based on all the identification feature information.
  • the false recognition rate is reduced, the recognition reliability is improved, and the occurrence of misjudgment or missed judgment is avoided.
  • FIG. 1 shows a flowchart of a method for identifying an obstacle according to an embodiment of the present disclosure
  • FIG. 2 shows a schematic diagram of bypassing a current obstacle according to a method for identifying an obstacle according to an embodiment of the present disclosure
  • FIG. 3 shows a unit block diagram of an apparatus for identifying obstacles according to an embodiment of the present disclosure
  • FIG. 4 shows a schematic diagram of a connection structure of an electronic device according to an embodiment of the present disclosure.
  • the term “including” and variations thereof are open-ended inclusions, ie, "including but not limited to”.
  • the term “based on” is “based at least in part on.”
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; the term “some embodiments” means “at least some embodiments”. Relevant definitions of other terms will be given in the description below.
  • the first embodiment provided in the present disclosure is an embodiment of a method for identifying an obstacle.
  • Walking robots (such as sweeping robots) have limitations in their ability to recognize obstacles through cameras. Some obstacles (such as pet feces) often lead to misrecognition or missed recognition due to their changing shapes. If the sweeping robot misidentifies pet feces, it often misses a large area; if the sweeping robot misses recognizing pet feces, it may smear the feces on a clean area. In view of the above problems, embodiments of the present disclosure provide a method for identifying obstacles.
  • step S101 in the process of identifying an obstacle, the current identification feature information of the obstacle is acquired.
  • the walking robot in the embodiment of the present disclosure uses a camera to collect image information.
  • a walking robot such as a sweeping robot
  • the preset recognition range for example, the distance from the current obstacle is greater than or equal to 30 cm
  • the current obstacle information is collected through the camera, And obtain the obstacle type by analyzing the current obstacle information.
  • the identification feature information is a detection result generated by the walking robot through current obstacle information.
  • the identification feature information includes an obstacle type and a confidence value of the obstacle type.
  • the obstacle type is the recognition result of the current obstacle, which is used to distinguish different obstacles.
  • the obstacle type includes the name of the obstacle.
  • the confidence value is a judgment on the reliability of obtaining the obstacle type, which is usually expressed as a percentage. For example, when the current obstacle is a pot of cactus, after collecting the information of the pot of cactus, the walking robot obtains that the type of the obstacle is the type of cactus, and the confidence value is 90%; however, due to the influence of the shooting angle and shooting environment, it is possible to obtain the The obstacle type is lotus root type, and the confidence value is 60%.
  • the embodiment of the present disclosure provides the walking robot with the reliability information after judging the current obstacle type by identifying the feature information, and prompts the walking robot to further confirm the unreliable obstacle during the walking process, so as to avoid misidentification and missed identification.
  • Step S102 when the current identification feature information does not meet the identification conditions, detour to more than one position around the obstacle, and acquire the identification feature information of the obstacle at each position accordingly.
  • the embodiment of the present disclosure provides that when the current identification feature information does not meet the identification conditions, the walking robot is controlled to obtain the identification of the current obstacle from multiple angles and multiple positions around the current obstacle. feature information to improve the reliability of the final recognition result.
  • the embodiments of the present disclosure provide two judgment methods:
  • detouring to more than one position around the obstacle includes the following steps:
  • Step S102-11 obtaining the current position of the obstacle.
  • the current position may be any position where the current obstacle is, or may be multiple positions.
  • Step S102-12 query an environment map based on the current position, and obtain the obstacle type marked corresponding to the current position.
  • the environment map is a digital map displayed on the terminal.
  • Each obstacle in the current environment digitally marks the digital area occupied by the obstacle and the types of obstacles in the digital area in the environment map.
  • the location in the environment map has a mapping relationship with the measured location in the actual environment, and a location in the actual environment has a corresponding location in the environment map.
  • the actual area occupied by walls and furnishings in a room is also marked in the environment map with the digital area occupied by walls and furnishings;
  • the digital area occupied by the makeshift objects is also marked on the map.
  • the current position of the current obstacle has a corresponding position in the environment map. If the corresponding position falls in a digital area, the digital area is the area marked in the environment map after the last walking robot identified the obstacle, then The marked obstacle type can be obtained through this numerical field.
  • Step S102-13 when the marked obstacle type does not match the current obstacle type, detour to more than one position around the obstacle.
  • the marked obstacle type does not match the current obstacle type, indicating that there are two possibilities, one is that the last recognition result may be wrong, that is, it may be misidentified; the other is that the current position corresponds to the first digital area.
  • the marked obstacle type is not the same obstacle type as the current obstacle type, that is, the obstacle at the current position may have changed from the last identified obstacle, and it is not the same obstacle. It shows that the current recognition result is different from the result marked in the environment map after the previous recognition, and there is a possibility of misrecognition.
  • detouring to more than one position around the obstacle includes the following steps:
  • Step S102-21 when the confidence value of the current obstacle type is less than a preset confidence threshold, detour to more than one position around the obstacle.
  • the confidence value of the current obstacle type is less than the preset confidence threshold, indicating that the current recognition is doubtful.
  • the embodiments of the present disclosure provide to control the walking robot to go around the current obstacle, obtain multiple identification feature information of the current obstacle at multiple positions and angles, and determine the target type of the current obstacle through the multiple identification feature information.
  • Step S103 Determine the target type of the obstacle according to all identification feature information of the obstacle.
  • the obtained obstacle types may be different, thus affecting the confirmation of the target type of the current obstacle. Therefore, in the embodiment of the present disclosure, all identification feature information of the current obstacle is comprehensively analyzed, so as to obtain the target type of the current obstacle.
  • Step S103-11 classify and count all obstacle types of the obstacle, and obtain a statistical value of each obstacle type.
  • obstacle types include cactus type and lotus root type, a statistic of 18 for an obstacle type of cactus type, and a statistic value of 2 for an obstacle type of lotus root type.
  • Step S103-12 Determine the obstacle type corresponding to the maximum statistical value as the target type.
  • the cactus type is determined as the target type of the current obstacle.
  • determining the target type of the obstacle according to all the identification feature information of the obstacle includes the following steps:
  • Step S103-21 Screen all confidence values of the obstacles to obtain a first obstacle type whose confidence value is greater than or equal to a preset confidence threshold.
  • the obstacle type with low reliability is excluded by the confidence value being greater than or equal to the preset confidence threshold value, and the first obstacle type with high reliability is obtained.
  • Step S103-22 classify and count all the first obstacle types, and obtain the statistical value of each first obstacle type.
  • obstacle types include cactus type and lotus root type, a statistic of 18 for an obstacle type of cactus type, and a statistic value of 2 for an obstacle type of lotus root type.
  • Step S103-23 determining that the first obstacle type corresponding to the maximum statistical value is the target type.
  • the cactus type is determined as the target type of the current obstacle.
  • Step S104 when the marked obstacle type does not match the current obstacle type, it is determined that the marked obstacle type is misidentification information.
  • the following steps are also included:
  • Step S105 transmitting the target type and the actual area information to the environment map.
  • the embodiment of the present disclosure identifies an obstacle, and when the identification feature information does not meet the identification conditions, bypasses the obstacle, continues to collect identification feature information of multiple positions of the current obstacle, and determines the target of the obstacle based on all the identification feature information type.
  • the false recognition rate is reduced, the recognition reliability is improved, and the occurrence of misjudgment or missed judgment is avoided.
  • the present disclosure also provides a second embodiment, that is, an apparatus for identifying obstacles. Since the second embodiment is basically similar to the first embodiment, the description is relatively simple, and for related parts, please refer to the corresponding description of the first embodiment.
  • the apparatus embodiments described below are merely illustrative.
  • FIG. 3 shows an embodiment of an apparatus for identifying obstacles provided by the present disclosure.
  • the present disclosure provides a device for identifying obstacles, including:
  • an obtaining unit 301 configured to obtain current identification feature information of an obstacle in the process of identifying an obstacle
  • a detour unit 302 configured to detour to more than one position around the obstacle when the current identification feature information does not meet the identification condition, and correspondingly obtain the identification feature information of the obstacle at each position;
  • the determining unit 303 is configured to determine the target type of the obstacle according to all identification feature information of the obstacle.
  • the identification feature information at least includes obstacle types
  • the detour unit 302 includes:
  • a query subunit configured to query an environment map based on the current position, and obtain the obstacle type marked corresponding to the current position
  • the first detouring subunit is used for detouring to more than one position around the obstacle when the marked obstacle type does not match the current obstacle type.
  • the identification feature information further includes a confidence value of the obstacle type
  • the detour unit 302 includes:
  • a second detour subunit configured to detour to more than one position around the obstacle when the confidence value of the current obstacle type is less than a preset confidence threshold.
  • the determining unit 303 it includes:
  • a first statistical subunit used to classify and count all obstacle types of the obstacle, and obtain the statistical value of each obstacle type
  • the first target type determination subunit is used to determine the obstacle type corresponding to the maximum statistical value as the target type.
  • the determining unit 303 it includes:
  • a screening subunit configured to screen all confidence values of the obstacles, and obtain a first obstacle type whose confidence value is greater than or equal to a preset confidence threshold
  • the second statistical subunit is used to classify and count all the first obstacle types, and obtain the statistical value of each first obstacle type
  • the second determining target type subunit is configured to determine that the first obstacle type corresponding to the maximum statistical value is the target type.
  • the device further includes:
  • a marking unit configured to determine that the marked obstacle type is misidentification information when the marked obstacle type does not match the current obstacle type.
  • the device further includes:
  • a collecting area information unit used for collecting the actual area information of the obstacle when detouring the obstacle
  • a transmitting unit configured to transmit the target type and the actual area information to the environment map after it is determined that the marked obstacle type is misidentified information.
  • the embodiment of the present disclosure identifies an obstacle, and when the identification feature information does not meet the identification conditions, bypasses the obstacle, continues to collect identification feature information of multiple positions of the current obstacle, and determines the target of the obstacle based on all the identification feature information type.
  • the false recognition rate is reduced, the recognition reliability is improved, and the occurrence of misjudgment or missed judgment is avoided.
  • Embodiments of the present disclosure provide a third embodiment, that is, an electronic device, which is used for a method for identifying obstacles, the electronic device includes: at least one processor; and is connected in communication with the at least one processor memory; where,
  • the memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of identifying an obstacle as described in the first embodiment .
  • Embodiments of the present disclosure provide a fourth embodiment, that is, a computer storage medium for identifying obstacles, where the computer storage medium stores computer-executable instructions, and the computer-executable instructions can perform the identification as described in the first embodiment. obstacle method.
  • Terminal devices in the embodiments of the present disclosure may include, but are not limited to, such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (eg, mobile terminals such as in-vehicle navigation terminals), etc., and stationary terminals such as digital TVs, desktop computers, and the like.
  • the electronic device shown in FIG. 4 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • the electronic device may include a processing device (eg, a central processing unit, a graphics processor, etc.) 401 that may be loaded into a random access memory according to a program stored in a read only memory (ROM) 402 or from a storage device 408
  • the program in the (RAM) 403 executes various appropriate operations and processes.
  • various programs and data required for the operation of the electronic device are also stored.
  • the processing device 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404.
  • An input/output (I/O) interface 405 is also connected to bus 404 .
  • I/O interface 405 input devices 406 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 407 of a computer, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. Communication means 409 may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While FIG. 4 shows an electronic device having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication device 409, or from the storage device 408, or from the ROM 402.
  • the processing apparatus 401 When the computer program is executed by the processing apparatus 401, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • clients and servers can communicate using any currently known or future developed network protocols such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communication eg, a communication network
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.
  • Computer program code for performing operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and This includes conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner. Among them, the name of the unit does not constitute a limitation of the unit itself under certain circumstances.
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLDs Complex Programmable Logical Devices
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Multimedia (AREA)
  • Automation & Control Theory (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mechanical Engineering (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种识别障碍物的方法、装置、介质和电子设备。该方法对障碍物进行识别，当识别特征信息不满足识别条件时，则绕行该障碍物，继续采集当前障碍物多位置的识别特征信息，并基于所有识别特征信息确定障碍物的目标类型。从而降低了误识别率，提高了识别的可靠性，避免了误判或漏判的发生。

Description

一种识别障碍物的方法、装置、介质和电子设备
相关申请的交叉引用
本申请要求于2020年11月6日递交的中国专利申请第202011228693.1号的优先权，在此全文引用上述中国专利申请公开的内容以作为本申请的一部分。
技术领域
本公开涉及机器人领域，具体而言，涉及一种识别障碍物的方法、装置、介质和电子设备。
背景技术
行走机器人是通过传感器或摄像头把地面的状况送回电脑，电脑则根据路面情况作出判断，进而稳定地前后左右行走。例如，扫地机器人，又称自动打扫机、智能吸尘器、机器人吸尘器等，是一种能够对地面进行自动清扫的智能家居设备，能够凭借人工智能，自动在房间内完成地板消扫工作。
当前，行走机器人通过摄像头对障碍物的识别能力尚有很大的局限性，有些障碍物(比如宠物粪便)，由于形状多变，常常导致误识别或者漏识别的情况。如果扫地机器人出现误识别宠物粪便时，常会出现大面积漏扫；如果扫地机器人出现漏识别宠物粪便时，则可能将粪便涂抹至干净区域，用户体验极差。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
本公开的目的在于提供一种识别障碍物的方法、装置、介质和电子设备，能够解决上述提到的至少一个技术问题。具体方案如下：
根据本公开的具体实施方式，第一方面，本公开提供一种识别障碍物的方法，包括：
在对一障碍物进行识别的过程中，获取所述障碍物的当前识别特征信息；
当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，相应的在各位置获取所述障碍物的识别特征信息；
根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型。
在一些实施方式中，所述识别特征信息至少包括障碍物类型；所述当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，包括：获取所述障碍物的当前位置；基于所述当前位置查询环境地图，获取所述当前位置对应标记的障碍物类型；当所述标记的障碍物类型与当前障碍物类型不匹配时，绕行至所述障碍物周围一个以 上的位置。
在一些实施方式中，所述识别特征信息还包括所述障碍物类型的置信度值；所述当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，包括：当所述当前障碍物类型的置信度值小于预设置信度阈值时，绕行至所述障碍物周围一个以上的位置。
在一些实施方式中，所述根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型，包括：对所述障碍物的所有障碍物类型进行分类统计，获取每个障碍物类型的统计值；确定最大统计值对应的障碍物类型为所述目标类型。
在一些实施方式中，所述根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型，包括：对所述障碍物的所有置信度值进行筛选，获取所述置信度值大于或等于预设置信度阈值的第一障碍物类型；对所有第一障碍物类型进行分类统计，获取每个第一障碍物类型的统计值；确定最大统计值对应的第一障碍物类型为所述目标类型。
在一些实施方式中，在所述确定所述障碍物的目标类型后，还包括：当所述标记的障碍物类型与所述当前障碍物类型不匹配时，则确定所述标记的障碍物类型为误识别信息。
在一些实施方式中，所述方法还包括：当绕行所述障碍物时，采集所述障碍物的实际区域信息；在所述确定所述标记的障碍物类型为误识别信息后，还包括：将所述目标类型和所述实际区域信息传送到所述环境地图。
根据本公开的具体实施方式，第二方面，本公开提供一种识别障碍物的装置，包括：
获取单元，用于在对一障碍物进行识别的过程中，获取所述障碍物的当前识别特征信息；
绕行单元，用于当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，相应的在各位置获取所述障碍物的识别特征信息；
确定单元，用于根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型。
在一些实施方式中，所述识别特征信息至少包括障碍物类型；在所述绕行单元中，包括：获取当前位置子单元，用于获取所述障碍物的当前位置；查询子单元，用于基于所述当前位置查询环境地图，获取所述当前位置对应标记的障碍物类型；第一绕行子单元，用于当所述标记的障碍物类型与当前障碍物类型不匹配时，绕行至所述障碍物周围一个以上的位置。
在一些实施方式中，所述识别特征信息还包括所述障碍物类型的置信度值；在所述绕行单元中，包括：第二绕行子单元，用于当所述当前障碍物类型的置信度值小于预设置信度阈值时，绕行至所述障碍物周围一个以上的位置。
在一些实施方式中，所述确定单元包括：第一统计子单元，用于对所述障碍物的所有障碍物类型进行分类统计，获取每个障碍物类型的统计值；第一确定目标类型子单元，用于确定最大统计值对应的障碍物类型为所述目标类型。
在一些实施方式中，所述确定单元包括：筛选子单元，用于对所述障碍物的所有置信 度值进行筛选，获取所述置信度值大于或等于预设置信度阈值的第一障碍物类型；第二统计子单元，用于对所有第一障碍物类型进行分类统计，获取每个第一障碍物类型的统计值；第二确定目标类型子单元，用于确定最大统计值对应的第一障碍物类型为所述目标类型。
在一些实施方式中，所述装置还包括：标记单元，用于当所述标记的障碍物类型与所述当前障碍物类型不匹配时，则确定所述标记的障碍物类型为误识别信息。
在一些实施方式中，所述装置还包括：采集区域信息单元，用于当绕行所述障碍物时，采集所述障碍物的实际区域信息；传送单元，用于在所述确定所述标记的障碍物类型为误识别信息后，将所述目标类型和所述实际区域信息传送到所述环境地图。
根据本公开的具体实施方式，第三方面，本公开提供一种计算机可读存储介质，其上存储有计算机程序，所述程序被处理器执行时实现如第一方面任一项所述识别障碍物的方法。
根据本公开的具体实施方式，第四方面，本公开提供一种电子设备，包括：一个或多个处理器；存储装置，用于存储一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如第一方面任一项所述识别障碍物的方法。
本公开实施例的上述方案与现有技术相比，至少具有以下有益效果：
本公开提供了一种识别障碍物的方法、装置、介质和电子设备。本公开对障碍物进行识别，当识别特征信息不满足识别条件时，则绕行该障碍物，继续采集当前障碍物多位置的识别特征信息，并基于所有识别特征信息确定障碍物的目标类型。从而降低了误识别率，提高了识别的可靠性，避免了误判或漏判的发生。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，元件和元素不一定按照比例绘制。在附图中：
图1示出了根据本公开实施例的识别障碍物的方法的流程图；
图2示出了根据本公开实施例的识别障碍物的方法的绕行当前障碍物示意图；
图3示出了根据本公开实施例的识别障碍物的装置的单元框图；
图4示出了根据本公开的实施例的电子设备连接结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面结合附图详细说明本公开的可选实施例。
对本公开提供的第一实施例，即一种识别障碍物的方法的实施例。
行走机器人(比如扫地机器人)通过摄像头对障碍物的识别能力存在局限性，有些障碍物(比如宠物粪便)，由于形状多变，常常导致误识别或者漏识别的情况。如果扫地机器人出现误识别宠物粪便时，常会出现大面积漏扫；如果扫地机器人出现漏识别宠物粪便时，则可能将粪便涂抹至干净区域。针对上述问题，本公开实施例提供了一种识别障碍物的方法。
下面结合图1和图2对本公开实施例进行详细说明。
如图1所示，步骤S101，在对一障碍物进行识别的过程中，获取所述障碍物的当前识别特征信息。
本公开实施例的行走机器人采用摄像头采集图像信息。行走机器人(比如扫地机器人)在工作过程中，当检测到预设识别范围(比如，距离当前障碍物在大于或等于30厘米的范围)内存在障碍物时，则通过摄像头采集当前障碍物信息，并通过分析当前障碍物信息获取障碍物类型。
所述识别特征信息是行走机器人通过对当前障碍物信息生成的检测结果。所述识别特征信息包括障碍物类型和所述障碍物类型的置信度值。障碍物类型是对当前障碍物识别结果，用于区别不同的障碍物，障碍物类型包括障碍物的名称。置信度值是对获得障碍物类型的可靠性的判断，常采用百分比表示。例如，当前障碍物为一盆仙人掌时，行走机器人采集该盆仙人掌信息后，获得障碍物类型为仙人掌类型，且置信度值为90％；但是，由于拍摄角度及拍摄环境的影响，可能获得的障碍物类型为莲藕类型，且置信度值为60％，在此情况下可能造成误识别以及误操作。本公开实施例通过识别特征信息为行走机器人提供 了对当前障碍物类型判断后的可靠性信息，促使行走机器人在行走过程中对不可靠障碍物进行进一步的确认，避免误识别和漏识别。
步骤S102，当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，相应的在各位置获取所述障碍物的识别特征信息。
为了避免单一识别特征信息对识别结果的干扰，本公开实施例提供了当所述当前识别特征信息不满足识别条件时，控制行走机器人围绕当前障碍物从多角度、多位置获取当前障碍物的识别特征信息，以提高最终识别结果的可靠性。
对于判断当前识别特征信息是否满足识别条件，本公开实施例提供了两种判断方法：
判断方法一
所述当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，包括以下步骤：
步骤S102-11，获取所述障碍物的当前位置。
当前位置可以是当前障碍物所处的任意一个位置，也可以是所处的多个位置。
步骤S102-12，基于所述当前位置查询环境地图，获取所述当前位置对应标记的障碍物类型。
环境地图是显示在终端的数字地图，当前环境中的每一个障碍物在环境地图中都以数字化的方式标记着障碍物所占据的数字区域，以及该数字区域中的障碍物类型。环境地图中的位置与实际环境中测量的位置具有映射关系，实际环境中的一个位置，在环境地图中存在对应的位置。例如，一个房间中的墙和陈设物所占据的实际区域，在环境地图中也标记着墙和陈设物所占据的数字区域；临时摆放物(如花盆)所占据的实际区域，在环境地图中也标记着临时摆放物所占据的数字区域。
当前障碍物所处的当前位置在环境地图中存在一对应位置，如果该对应位置落在了一个数字区域中，该数字区域就是上一次行走机器人识别障碍物后在环境地图中标记的区域，则通过该数字区域能够获取标记的障碍物类型。
步骤S102-13，当所述标记的障碍物类型与当前障碍物类型不匹配时，绕行至所述障碍物周围一个以上的位置。
标记的障碍物类型与当前障碍物类型不匹配，说明存在两种可能性，一种是上一次识别结果可能是错误的，也就是可能误识别；另一种是当前位置对应第一数字区域中标记的障碍物类型与当前障碍物类型不是同一种障碍物类型，也就是在当前位置的障碍物与上一次识别时的障碍物可能已经发生了变化，不是同一种障碍物。表明通过当前的识别结果与上一次识别后在环境地图中标记的结果不同，存在误识别的可能性。
判断方法二
所述当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，包括以下步骤：
步骤S102-21，当所述当前障碍物类型的置信度值小于预设置信度阈值时，绕行至所 述障碍物周围一个以上的位置。
当前障碍物类型的置信度值小于预设置信度阈值，表明当前识别存疑。
为了确定当前障碍物的障碍物类型，提高获取当前障碍物的目标类型的可靠性。本公开实施例提供了控制行走机器人绕行所述当前障碍物，并在多个位置和角度获取当前障碍物多个识别特征信息，并通过多个识别特征信息确定当前障碍物的目标类型。
步骤S103，根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型。
由于环境因素的影响，对每个位置每个角度的障碍物信息分别识别后，获取的障碍物类型可能不同，从而影响对当前障碍物的目标类型的确认。因此，本公开实施例对当前障碍物的所有识别特征信息进行综合分析，从而获取所述当前障碍物的目标类型。
具体地，包括以下步骤：
步骤S103-11，对所述障碍物的所有障碍物类型进行分类统计，获取每个障碍物类型的统计值。
本公开实施例对所有障碍物类型进行分类统计，获取每个障碍物类型的统计值。例如，障碍物类型包括仙人掌类型和莲藕类型，障碍物类型为仙人掌类型的统计值为18，以及障碍物类型为莲藕类型的统计值为2。
步骤S103-12，确定最大统计值对应的障碍物类型为所述目标类型。
例如，继续上述的例子，由于障碍物类型为仙人掌类型的统计值为18，也就是最大统计值，因而确定仙人掌类型为当前障碍物的目标类型。
进一步的，为了排除无效数据的干扰，所述根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型，包括以下步骤：
步骤S103-21，对所述障碍物的所有置信度值进行筛选，获取所述置信度值大于或等于预设置信度阈值的第一障碍物类型。
通过置信度值大于或等于预设置信度阈值排除了可靠性低的障碍物类型，获取可靠性高的第一障碍物类型。
步骤S103-22，对所有第一障碍物类型进行分类统计，获取每个第一障碍物类型的统计值。
本公开实施例对所有可靠性高的第一障碍物类型进行分类统计，获取每个障碍物类型的统计值。例如，障碍物类型包括仙人掌类型和莲藕类型，障碍物类型为仙人掌类型的统计值为18，以及障碍物类型为莲藕类型的统计值为2。
步骤S103-23，确定最大统计值对应的第一障碍物类型为所述目标类型。
例如，继续上述的例子，由于障碍物类型为仙人掌类型的统计值为18，也就是最大统计值，因而确定仙人掌类型为当前障碍物的目标类型。
可选的，在所述确定所述障碍物的目标类型后，还包括以下步骤：
步骤S104，当所述标记的障碍物类型与所述当前障碍物类型不匹配时，则确定所述标记的障碍物类型为误识别信息。
为了使实际信息与环境地图中的数字信息保持一致，当绕行所述障碍物时，采集所述障碍物的实际区域信息。
可选的，在所述确定所述标记的障碍物类型为误识别信息后，还包括以下步骤：
步骤S105，将所述目标类型和所述实际区域信息传送到所述环境地图。
以便在所述环境地图中绘制对应所述实际区域信息的数字区域，并在该数字区域内标记障碍物的障碍物类型。
本公开实施例对障碍物进行识别，当识别特征信息不满足识别条件时，则绕行该障碍物，继续采集当前障碍物多位置的识别特征信息，并基于所有识别特征信息确定障碍物的目标类型。从而降低了误识别率，提高了识别的可靠性，避免了误判或漏判的发生。
与本公开提供的第一实施例相对应，本公开还提供了第二实施例，即一种识别障碍物的装置。由于第二实施例基本相似于第一实施例，所以描述得比较简单，相关的部分请参见第一实施例的对应说明即可。下述描述的装置实施例仅仅是示意性的。
图3示出了本公开提供的一种识别障碍物的装置的实施例。
如图3所示，本公开提供一种识别障碍物的装置，包括：
获取单元301，用于在对一障碍物进行识别的过程中，获取所述障碍物的当前识别特征信息；
绕行单元302，用于当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，相应的在各位置获取所述障碍物的识别特征信息；
确定单元303，用于根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型。
可选的，所述识别特征信息至少包括障碍物类型；
在所述绕行单元302中，包括：
获取当前位置子单元，用于获取所述障碍物的当前位置；
查询子单元，用于基于所述当前位置查询环境地图，获取所述当前位置对应标记的障碍物类型；
第一绕行子单元，用于当所述标记的障碍物类型与当前障碍物类型不匹配时，绕行至所述障碍物周围一个以上的位置。
可选的，所述识别特征信息还包括所述障碍物类型的置信度值；
在所述绕行单元302中，包括：
第二绕行子单元，用于当所述当前障碍物类型的置信度值小于预设置信度阈值时，绕行至所述障碍物周围一个以上的位置。
可选的，在所述确定单元303中，包括：
第一统计子单元，用于对所述障碍物的所有障碍物类型进行分类统计，获取每个障碍物类型的统计值；
第一确定目标类型子单元，用于确定最大统计值对应的障碍物类型为所述目标类型。
可选的，在所述确定单元303中，包括：
筛选子单元，用于对所述障碍物的所有置信度值进行筛选，获取所述置信度值大于或等于预设置信度阈值的第一障碍物类型；
第二统计子单元，用于对所有第一障碍物类型进行分类统计，获取每个第一障碍物类型的统计值；
第二确定目标类型子单元，用于确定最大统计值对应的第一障碍物类型为所述目标类型。
可选的，所述装置，还包括：
标记单元，用于当所述标记的障碍物类型与所述当前障碍物类型不匹配时，则确定所述标记的障碍物类型为误识别信息。
可选的，所述装置还包括：
采集区域信息单元，用于当绕行所述障碍物时，采集所述障碍物的实际区域信息；
传送单元，用于在所述确定所述标记的障碍物类型为误识别信息后，将所述目标类型和所述实际区域信息传送到所述环境地图。
本公开实施例对障碍物进行识别，当识别特征信息不满足识别条件时，则绕行该障碍物，继续采集当前障碍物多位置的识别特征信息，并基于所有识别特征信息确定障碍物的目标类型。从而降低了误识别率，提高了识别的可靠性，避免了误判或漏判的发生。
本公开实施例提供了第三实施例，即一种电子设备，该设备用于识别障碍物的方法，所述电子设备，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如第一实施例所述识别障碍物的方法。
本公开实施例提供了第四实施例，即一种识别障碍物的计算机存储介质，所述计算机存储介质存储有计算机可执行指令，该计算机可执行指令可执行如第一实施例中所述识别障碍物的方法。
下面参考图4，其示出了适于用来实现本公开实施例的电子设备的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图4示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图4所示，电子设备可以包括处理装置(例如中央处理器、图形处理器等)401，其可以根据存储在只读存储器(ROM)402中的程序或者从存储装置408加载到随机访问存储器(RAM)403中的程序而执行各种适当的动作和处理。在RAM 403中，还存储有电子设备操作所需的各种程序和数据。处理装置401、ROM 402以及RAM 403通过总线404彼此相连。输入/输出(I/O)接口405也连接至总线404。
通常，以下装置可以连接至I/O接口405：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置406；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置407；包括例如磁带、硬盘等的存储装置408；以及通信装置409。通信装置409可以允许电子设备与其他设备进行无线或有线通信以交换数据。虽然图4示出了具有各种装置的电子设备，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置409从网络上被下载和安装，或者从存储装置408被安装，或者从ROM 402被安装。在该计算机程序被处理装置401执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程 序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (16)

  1. 一种识别障碍物的方法，其特征在于，包括：
    在对一障碍物进行识别的过程中，获取所述障碍物的当前识别特征信息；
    当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，相应的在各位置获取所述障碍物的识别特征信息；
    根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型。
  2. 根据权利要求1所述的方法，其特征在于，
    所述识别特征信息至少包括障碍物类型；
    所述当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，包括：
    获取所述障碍物的当前位置；
    基于所述当前位置查询环境地图，获取所述当前位置对应标记的障碍物类型；
    当所述标记的障碍物类型与当前障碍物类型不匹配时，绕行至所述障碍物周围一个以上的位置。
  3. 根据权利要求1所述的方法，其特征在于，
    所述识别特征信息还包括所述障碍物类型的置信度值；
    所述当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，包括：
    当所述当前障碍物类型的置信度值小于预设置信度阈值时，绕行至所述障碍物周围一个以上的位置。
  4. 根据权利要求2所述的方法，其特征在于，所述根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型，包括：
    对所述障碍物的所有障碍物类型进行分类统计，获取每个障碍物类型的统计值；
    确定最大统计值对应的障碍物类型为所述目标类型。
  5. 根据权利要求3所述的方法，其特征在于，所述根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型，包括：
    对所述障碍物的所有置信度值进行筛选，获取所述置信度值大于或等于预设置信度阈值的第一障碍物类型；
    对所有第一障碍物类型进行分类统计，获取每个第一障碍物类型的统计值；
    确定最大统计值对应的第一障碍物类型为所述目标类型。
  6. 根据权利要求2所述的方法，其特征在于，在所述确定所述障碍物的目标类型后，还包括：
    当所述标记的障碍物类型与所述当前障碍物类型不匹配时，则确定所述标记的障碍物类型为误识别信息。
  7. 根据权利要求6所述的方法，其特征在于，
    所述方法还包括：
    当绕行所述障碍物时，采集所述障碍物的实际区域信息；
    在所述确定所述标记的障碍物类型为误识别信息后，还包括：
    将所述目标类型和所述实际区域信息传送到所述环境地图。
  8. 一种识别障碍物的装置，其特征在于，包括：
    获取单元，用于在对一障碍物进行识别的过程中，获取所述障碍物的当前识别特征信息；
    绕行单元，用于当所述当前识别特征信息不满足识别条件时，绕行至所述障碍物周围一个以上的位置，相应的在各位置获取所述障碍物的识别特征信息；
    确定单元，用于根据所述障碍物的所有识别特征信息，确定所述障碍物的目标类型。
  9. 根据权利要求8所述的装置，其特征在于，
    所述识别特征信息至少包括障碍物类型；
    在所述绕行单元中，包括：
    获取当前位置子单元，用于获取所述障碍物的当前位置；
    查询子单元，用于基于所述当前位置查询环境地图，获取所述当前位置对应标记的障碍物类型；
    第一绕行子单元，用于当所述标记的障碍物类型与当前障碍物类型不匹配时，绕行至所述障碍物周围一个以上的位置。
  10. 根据权利要求8所述的装置，其特征在于，
    所述识别特征信息还包括所述障碍物类型的置信度值；
    在所述绕行单元中，包括：
    第二绕行子单元，用于当所述当前障碍物类型的置信度值小于预设置信度阈值时，绕行至所述障碍物周围一个以上的位置。
  11. 根据权利要求9所述的装置，其特征在于，在所述确定单元中，包括：
    第一统计子单元，用于对所述障碍物的所有障碍物类型进行分类统计，获取每个障碍物类型的统计值；
    第一确定目标类型子单元，用于确定最大统计值对应的障碍物类型为所述目标类型。
  12. 根据权利要求10所述的装置，其特征在于，在所述确定单元中，包括：
    筛选子单元，用于对所述障碍物的所有置信度值进行筛选，获取所述置信度值大于或等于预设置信度阈值的第一障碍物类型；
    第二统计子单元，用于对所有第一障碍物类型进行分类统计，获取每个第一障碍物类型的统计值；
    第二确定目标类型子单元，用于确定最大统计值对应的第一障碍物类型为所述目标类型。
  13. 根据权利要求9所述的装置，其特征在于，所述装置，还包括：
    标记单元，用于当所述标记的障碍物类型与所述当前障碍物类型不匹配时，则确定所述标记的障碍物类型为误识别信息。
  14. 根据权利要求13所述的装置，其特征在于，所述装置还包括：
    采集区域信息单元，用于当绕行所述障碍物时，采集所述障碍物的实际区域信息；
    传送单元，用于在所述确定所述标记的障碍物类型为误识别信息后，将所述目标类型和所述实际区域信息传送到所述环境地图。
  15. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述程序被处理器执行时实现如权利要求1至7中任一项所述的方法。
  16. 一种电子设备，其特征在于，包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如权利要求1至7中任一项所述的方法。
PCT/CN2021/100714 2020-11-06 2021-06-17 一种识别障碍物的方法、装置、介质和电子设备 Ceased WO2022095453A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US18/252,035 US12564303B2 (en) 2020-11-06 2021-06-17 Obstacle recognition method and apparatus, medium and electronic device
EP21888156.3A EP4242911A4 (en) 2020-11-06 2021-06-17 OBSTACLE RECOGNITION METHOD AND APPARATUS, SUPPORT AND ELECTRONIC DEVICE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011228693.1A CN112380942B (zh) 2020-11-06 2020-11-06 一种识别障碍物的方法、装置、介质和电子设备
CN202011228693.1 2020-11-06

Publications (1)

Publication Number Publication Date
WO2022095453A1 true WO2022095453A1 (zh) 2022-05-12

Family

ID=74579754

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/100714 Ceased WO2022095453A1 (zh) 2020-11-06 2021-06-17 一种识别障碍物的方法、装置、介质和电子设备

Country Status (4)

Country Link
US (1) US12564303B2 (zh)
EP (1) EP4242911A4 (zh)
CN (2) CN118898739A (zh)
WO (1) WO2022095453A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115471708A (zh) * 2022-09-27 2022-12-13 禾多科技（北京）有限公司 车道线类型信息生成方法、装置、设备和计算机可读介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118898739A (zh) * 2020-11-06 2024-11-05 北京石头创新科技有限公司 一种识别障碍物的方法、装置、介质和电子设备
CN112836681B (zh) * 2021-03-03 2024-01-26 上海高仙自动化科技发展有限公司 一种障碍物标记方法、装置及可读非暂时性存储介质
CN116416519B (zh) * 2021-12-22 2025-12-12 广东栗子科技有限公司 区域的智能划分方法及装置
CN120190833B (zh) * 2025-05-26 2025-08-01 卧安科技(深圳)有限公司 具身机器人避障回看控制方法、装置及具身机器人系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108445878A (zh) * 2018-02-28 2018-08-24 北京奇虎科技有限公司 一种用于扫地机器人的障碍物处理方法和扫地机器人
CN109645892A (zh) * 2018-12-12 2019-04-19 深圳乐动机器人有限公司 一种障碍物的识别方法及清洁机器人
CN110315538A (zh) * 2019-06-27 2019-10-11 深圳乐动机器人有限公司 一种在电子地图上显示障碍物的方法、装置及机器人
CN111481105A (zh) * 2020-04-20 2020-08-04 北京石头世纪科技股份有限公司 一种自行走机器人避障方法、装置、机器人和存储介质
CN112380942A (zh) * 2020-11-06 2021-02-19 北京石头世纪科技股份有限公司 一种识别障碍物的方法、装置、介质和电子设备

Family Cites Families (136)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5646843A (en) * 1990-02-05 1997-07-08 Caterpillar Inc. Apparatus and method for surface based vehicle control system
US5633995A (en) * 1991-06-19 1997-05-27 Martin Marietta Corporation Camera system and methods for extracting 3D model of viewed object
JPH06139498A (ja) * 1992-10-30 1994-05-20 Mitsubishi Electric Corp 障害物回避装置
US5592215A (en) * 1993-02-03 1997-01-07 Rohm Co., Ltd. Stereoscopic picture system and stereoscopic display panel therefor
JP3369368B2 (ja) * 1995-10-11 2003-01-20 富士通株式会社 画像処理装置
JP3945279B2 (ja) * 2002-03-15 2007-07-18 ソニー株式会社 障害物認識装置、障害物認識方法、及び障害物認識プログラム並びに移動型ロボット装置
US7015831B2 (en) * 2002-12-17 2006-03-21 Evolution Robotics, Inc. Systems and methods for incrementally updating a pose of a mobile device calculated by visual simultaneous localization and mapping techniques
US6816109B1 (en) * 2003-08-04 2004-11-09 Northrop Grumman Corporation Method for automatic association of moving target indications from entities traveling along known route
JP3994950B2 (ja) * 2003-09-19 2007-10-24 ソニー株式会社 環境認識装置及び方法、経路計画装置及び方法、並びにロボット装置
US7689321B2 (en) * 2004-02-13 2010-03-30 Evolution Robotics, Inc. Robust sensor fusion for mapping and localization in a simultaneous localization and mapping (SLAM) system
US7623734B2 (en) * 2004-09-30 2009-11-24 Microsoft Corporation Method and system for automatically inscribing noisy objects in scanned image data within a minimum area rectangle
KR100703692B1 (ko) * 2004-11-03 2007-04-05 삼성전자주식회사 공간상에 존재하는 오브젝트들을 구별하기 위한 시스템,장치 및 방법
US20100222925A1 (en) * 2004-12-03 2010-09-02 Takashi Anezaki Robot control apparatus
JP4341564B2 (ja) * 2005-02-25 2009-10-07 株式会社豊田中央研究所 対象物判定装置
JP2006239844A (ja) * 2005-03-04 2006-09-14 Sony Corp 障害物回避装置、障害物回避方法及び障害物回避プログラム並びに移動型ロボット装置
CN101297267B (zh) * 2005-09-02 2012-01-11 Neato机器人技术公司 多功能机器人设备
EP1790541A2 (en) * 2005-11-23 2007-05-30 MobilEye Technologies, Ltd. Systems and methods for detecting obstructions in a camera field of view
US7912633B1 (en) * 2005-12-01 2011-03-22 Adept Mobilerobots Llc Mobile autonomous updating of GIS maps
US7634336B2 (en) * 2005-12-08 2009-12-15 Electronics And Telecommunications Research Institute Localization system and method of mobile robot based on camera and landmarks
KR100791381B1 (ko) * 2006-06-01 2008-01-07 삼성전자주식회사 이동 로봇의 원격 조종을 위한 충돌방지 시스템, 장치 및방법
JP4871160B2 (ja) * 2007-02-16 2012-02-08 株式会社東芝 ロボットおよびその制御方法
JP4975503B2 (ja) * 2007-04-06 2012-07-11 本田技研工業株式会社 脚式移動ロボット
JP4328813B2 (ja) * 2007-04-06 2009-09-09 本田技研工業株式会社 移動装置、ならびにその制御方法および制御プログラム
US20090048727A1 (en) * 2007-08-17 2009-02-19 Samsung Electronics Co., Ltd. Robot cleaner and control method and medium of the same
US8825387B2 (en) * 2008-07-25 2014-09-02 Navteq B.V. Positioning open area maps
US8706298B2 (en) * 2010-03-17 2014-04-22 Raytheon Company Temporal tracking robot control system
KR20120070291A (ko) * 2010-12-21 2012-06-29 삼성전자주식회사 보행 로봇 및 그의 동시 위치 인식 및 지도 작성 방법
US8655588B2 (en) * 2011-05-26 2014-02-18 Crown Equipment Limited Method and apparatus for providing accurate localization for an industrial vehicle
US8799201B2 (en) * 2011-07-25 2014-08-05 Toyota Motor Engineering & Manufacturing North America, Inc. Method and system for tracking objects
US8442321B1 (en) * 2011-09-14 2013-05-14 Google Inc. Object recognition in images
SG11201400958XA (en) * 2012-01-25 2014-04-28 Adept Technology Inc Autonomous mobile robot for handling job assignments in a physical environment inhabited by stationary and non-stationary obstacles
KR101984214B1 (ko) * 2012-02-09 2019-05-30 삼성전자주식회사 로봇 청소기의 청소 작업을 제어하기 위한 장치 및 방법
KR102083188B1 (ko) * 2013-07-29 2020-03-02 삼성전자주식회사 청소 로봇 및 그 제어 방법
EP3082542B1 (en) * 2013-12-19 2018-11-28 Aktiebolaget Electrolux Sensing climb of obstacle of a robotic cleaning device
JP6599603B2 (ja) * 2014-04-18 2019-10-30 東芝ライフスタイル株式会社 自律走行体
CN111568297B (zh) * 2014-07-01 2023-02-03 三星电子株式会社 清洁机器人及其控制方法
US9697439B2 (en) * 2014-10-02 2017-07-04 Xerox Corporation Efficient object detection with patch-level window processing
JP6537251B2 (ja) * 2014-11-14 2019-07-03 シャープ株式会社 自律走行装置
KR20160058594A (ko) * 2014-11-17 2016-05-25 삼성전자주식회사 로봇 청소기, 단말장치 및 그 제어 방법
US10274958B2 (en) * 2015-01-22 2019-04-30 Bae Systems Information And Electronic Systems Integration Inc. Method for vision-aided navigation for unmanned vehicles
KR102023966B1 (ko) * 2015-02-10 2019-09-23 에브리봇 주식회사 로봇 청소기 및 그의 제어 방법
KR102328252B1 (ko) * 2015-02-13 2021-11-19 삼성전자주식회사 청소 로봇 및 그 제어방법
KR102314637B1 (ko) * 2015-03-23 2021-10-18 엘지전자 주식회사 로봇 청소기 및 이를 구비하는 로봇 청소 시스템
US9953540B2 (en) * 2015-06-16 2018-04-24 Here Global B.V. Air space maps
EP3276374B1 (en) * 2015-06-29 2024-10-09 Yuneec Technology Co., Limited Aircraft and obstacle avoidance method and system thereof
KR101772084B1 (ko) * 2015-07-29 2017-08-28 엘지전자 주식회사 이동 로봇 및 그 제어방법
US20170090456A1 (en) * 2015-09-25 2017-03-30 Multimedia Image Solution Limited Autonomous cleaning robot
JP7007078B2 (ja) * 2015-10-08 2022-01-24 東芝ライフスタイル株式会社 電気掃除機
DE102015119501A1 (de) * 2015-11-11 2017-05-11 RobArt GmbH Unterteilung von Karten für die Roboternavigation
US10242455B2 (en) * 2015-12-18 2019-03-26 Iris Automation, Inc. Systems and methods for generating a 3D world model using velocity data of a vehicle
CN108885436B (zh) * 2016-01-15 2021-12-14 美国iRobot公司 自主监视机器人系统
US10452071B1 (en) * 2016-02-29 2019-10-22 AI Incorporated Obstacle recognition method for autonomous robots
US10788836B2 (en) * 2016-02-29 2020-09-29 AI Incorporated Obstacle recognition method for autonomous robots
US11726487B1 (en) * 2016-06-06 2023-08-15 AI Incorporated Method for robotic devices to identify doorways using machine learning
US10713961B2 (en) * 2016-06-10 2020-07-14 ETAK Systems, LLC Managing dynamic obstructions in air traffic control systems for unmanned aerial vehicles
US10272828B2 (en) * 2016-08-16 2019-04-30 Irobot Corporation Light indicator system for an autonomous mobile robot
AU2017316090B2 (en) * 2016-08-25 2020-10-29 Lg Electronics Inc. Mobile robot and control method therefor
CN106406343B (zh) * 2016-09-23 2020-07-10 北京小米移动软件有限公司 无人飞行器的控制方法、装置和系统
CN107976688A (zh) * 2016-10-25 2018-05-01 菜鸟智能物流控股有限公司 一种障碍物的检测方法及相关装置
KR102662949B1 (ko) * 2016-11-24 2024-05-02 엘지전자 주식회사 인공지능 이동 로봇 및 그 제어방법
CN110554711B (zh) * 2016-12-16 2022-03-18 广州极飞科技股份有限公司 无人机作业的方法、装置、无人机及存储介质
KR20180075176A (ko) * 2016-12-26 2018-07-04 엘지전자 주식회사 이동 로봇 및 그 제어방법
KR102688528B1 (ko) * 2017-01-25 2024-07-26 엘지전자 주식회사 이동 로봇 및 그 제어방법
KR102624560B1 (ko) * 2017-01-31 2024-01-15 엘지전자 주식회사 청소기
WO2018158927A1 (ja) * 2017-03-02 2018-09-07 エスゼット ディージェイアイ テクノロジー カンパニー リミテッド ３次元形状推定方法、飛行体、モバイルプラットフォーム、プログラム及び記録媒体
KR102017148B1 (ko) * 2017-03-03 2019-09-02 엘지전자 주식회사 장애물을 학습하는 인공지능 이동 로봇 및 그 제어방법
KR101984101B1 (ko) * 2017-03-06 2019-05-30 엘지전자 주식회사 청소기 및 그 제어방법
US20180299899A1 (en) * 2017-04-13 2018-10-18 Neato Robotics, Inc. Localized collection of ambient data
WO2018214078A1 (zh) * 2017-05-24 2018-11-29 深圳市大疆创新科技有限公司 拍摄控制方法及装置
US20180348783A1 (en) * 2017-05-31 2018-12-06 Neato Robotics, Inc. Asynchronous image classification
KR20180134230A (ko) * 2017-06-08 2018-12-18 삼성전자주식회사 청소 로봇 및 그 제어 방법
US11301734B2 (en) * 2017-07-12 2022-04-12 Lenovo (Singapore) Pte. Ltd. Object association determination
KR101984516B1 (ko) * 2017-07-21 2019-05-31 엘지전자 주식회사 청소기 및 그 제어방법
US11348269B1 (en) * 2017-07-27 2022-05-31 AI Incorporated Method and apparatus for combining data to construct a floor plan
KR102206201B1 (ko) * 2017-08-02 2021-01-22 삼성전자주식회사 청소 로봇 및 그 제어방법
CN111033425A (zh) * 2017-09-04 2020-04-17 日本电产株式会社 移动体、位置推断装置以及计算机程序
CN109901567B (zh) * 2017-12-08 2020-06-23 百度在线网络技术（北京）有限公司 用于输出障碍物信息的方法和装置
US10638906B2 (en) * 2017-12-15 2020-05-05 Neato Robotics, Inc. Conversion of cleaning robot camera images to floorplan for user interaction
KR20190081316A (ko) * 2017-12-29 2019-07-09 삼성전자주식회사 청소용 이동장치 및 그 제어방법
US10878294B2 (en) * 2018-01-05 2020-12-29 Irobot Corporation Mobile cleaning robot artificial intelligence for situational awareness
CN108247647B (zh) * 2018-01-24 2021-06-22 速感科技（北京）有限公司 一种清洁机器人
JP7149502B2 (ja) * 2018-03-29 2022-10-07 パナソニックＩｐマネジメント株式会社 自律移動掃除機、自律移動掃除機による掃除方法、及び自律移動掃除機用プログラム
US10929664B2 (en) * 2018-03-30 2021-02-23 Iunu, Inc. Visual observer of unmanned aerial vehicle for monitoring horticultural grow operations
EP3777630B1 (en) * 2018-04-09 2026-03-11 LG Electronics Inc. Robot cleaner
KR102100474B1 (ko) * 2018-04-30 2020-04-13 엘지전자 주식회사 인공지능 청소기 및 그 제어방법
KR102070283B1 (ko) * 2018-05-16 2020-01-28 엘지전자 주식회사 청소기 및 그 제어방법
KR102015498B1 (ko) * 2018-06-27 2019-10-23 엘지전자 주식회사 복수의 자율주행 청소기 및 그 제어방법
US11074811B2 (en) * 2018-08-21 2021-07-27 Here Global B.V. Method and apparatus for using drones for road and traffic monitoring
US10775174B2 (en) * 2018-08-30 2020-09-15 Mapbox, Inc. Map feature extraction system for computer map visualizations
KR102629036B1 (ko) * 2018-08-30 2024-01-25 삼성전자주식회사 로봇 및 그의 제어 방법
US11464375B2 (en) * 2018-09-04 2022-10-11 Irobot Corporation Navigation of autonomous mobile robots
CN109163707B (zh) * 2018-09-06 2019-11-26 百度在线网络技术（北京）有限公司 障碍物感知方法、系统、计算机设备、计算机存储介质
WO2020060267A1 (en) * 2018-09-20 2020-03-26 Samsung Electronics Co., Ltd. Cleaning robot and method for performing task thereof
KR102577785B1 (ko) * 2018-09-20 2023-09-13 삼성전자주식회사 청소 로봇 및 그의 태스크 수행 방법
CN110968083B (zh) * 2018-09-30 2023-02-10 科沃斯机器人股份有限公司 栅格地图的构建方法、避障的方法、设备及介质
US20200135035A1 (en) * 2018-10-26 2020-04-30 Foresight Ai Inc. Intelligent on-demand capturing of a physical environment using airborne agents
CN109255341B (zh) * 2018-10-30 2021-08-10 百度在线网络技术（北京）有限公司 障碍物感知错误数据的提取方法、装置、设备及介质
CN109240314B (zh) * 2018-11-09 2020-01-24 百度在线网络技术（北京）有限公司 用于采集数据的方法和装置
TWI671489B (zh) 2018-11-12 2019-09-11 台灣愛司帝科技股份有限公司 發光二極體顯示器
CN111399492A (zh) * 2018-12-28 2020-07-10 深圳市优必选科技有限公司 一种机器人及其障碍物感知方法和装置
KR102255273B1 (ko) * 2019-01-04 2021-05-24 삼성전자주식회사 청소 공간의 지도 데이터를 생성하는 장치 및 방법
KR102234642B1 (ko) * 2019-01-17 2021-04-01 엘지전자 주식회사 이동 로봇 및 이동 로봇의 제어방법
CN109857112A (zh) * 2019-02-21 2019-06-07 广东智吉科技有限公司 机器人避障方法及装置
CN114942638A (zh) * 2019-04-02 2022-08-26 北京石头创新科技有限公司 机器人工作区域地图构建方法、装置
ES3062005T3 (en) * 2019-04-03 2026-04-08 Shenzhen Yinwang Intelligent Technology Co Ltd Localization method and localization device
CA3220289A1 (en) * 2019-04-05 2020-10-08 Equipmentshare.Com Inc. System and method for autonomous operation of a machine
KR102297496B1 (ko) * 2019-07-11 2021-09-02 엘지전자 주식회사 인공지능을 이용한 이동 로봇 및 이동 로봇의 제어방법
KR102281346B1 (ko) * 2019-07-25 2021-07-23 엘지전자 주식회사 로봇 청소기 및 그 제어방법
KR102251550B1 (ko) * 2019-07-31 2021-05-12 엘지전자 주식회사 이동 로봇 및 그 제어방법
US11249482B2 (en) * 2019-08-09 2022-02-15 Irobot Corporation Mapping for autonomous mobile robots
CN110622085A (zh) * 2019-08-14 2019-12-27 珊口（深圳）智能科技有限公司 移动机器人及其控制方法和控制系统
KR102826475B1 (ko) * 2019-08-28 2025-06-30 엘지전자 주식회사 인공 지능 모니터링 장치 및 그의 동작 방법
CN110522359B (zh) * 2019-09-03 2021-09-03 深圳飞科机器人有限公司 清洁机器人以及清洁机器人的控制方法
KR20210028426A (ko) * 2019-09-04 2021-03-12 엘지전자 주식회사 로봇 청소기 및 그 제어방법
US11327483B2 (en) * 2019-09-30 2022-05-10 Irobot Corporation Image capture devices for autonomous mobile robots and related systems and methods
KR102778546B1 (ko) * 2019-10-01 2025-03-07 엘지전자 주식회사 로봇 청소기 및 청소 경로를 결정하기 위한 방법
WO2021096144A1 (en) * 2019-11-12 2021-05-20 Samsung Electronics Co., Ltd. Mistakenly ingested object identifying robot cleaner and controlling method thereof
KR20210084129A (ko) * 2019-12-27 2021-07-07 삼성전자주식회사 로봇 청소기 및 그 제어 방법
CN111012254B (zh) * 2019-12-30 2024-10-18 南京智慧建筑研究院有限公司 智能扫地机器人
US11694333B1 (en) * 2020-02-05 2023-07-04 State Farm Mutual Automobile Insurance Company Performing semantic segmentation of 3D data using deep learning
US20210244249A1 (en) * 2020-02-10 2021-08-12 Matician, Inc. Configuration of a cleaning head for an autonomous vacuum
KR102320678B1 (ko) * 2020-02-28 2021-11-02 엘지전자 주식회사 이동 로봇 및 그 제어방법
CN111538329B (zh) * 2020-04-09 2023-02-28 北京石头创新科技有限公司 一种图像查看方法、终端及清洁机
CN121209520A (zh) * 2020-04-14 2025-12-26 北京石头创新科技有限公司 一种机器人避障方法、装置和存储介质
US11180162B1 (en) * 2020-05-07 2021-11-23 Argo AI, LLC Systems and methods for controlling vehicles using an amodal cuboid based algorithm
US11690490B2 (en) * 2020-07-08 2023-07-04 Pixart Imaging Inc. Auto clean machine and auto clean machine control method
KR20220029824A (ko) * 2020-08-28 2022-03-10 삼성전자주식회사 청소 로봇 및 그 제어 방법
KR20220056643A (ko) * 2020-10-28 2022-05-06 삼성전자주식회사 로봇 청소기 및 그의 주행 방법
DE102020129026A1 (de) * 2020-11-04 2022-05-05 Vorwerk & Co. Interholding Gesellschaft mit beschränkter Haftung Sich selbsttätig fortbewegendes Reinigungsgerät
US11960282B2 (en) * 2021-01-05 2024-04-16 Abb Schweiz Ag Systems and methods for servicing a data center using autonomous vehicle
CN116021506A (zh) * 2021-10-26 2023-04-28 美智纵横科技有限责任公司 机器人控制方法、装置和存储介质
US12336675B2 (en) * 2022-04-11 2025-06-24 Vorwerk & Co. Interholding Gmb Obstacle avoidance using fused depth and intensity from nnt training
EP4464219A4 (en) * 2022-06-15 2025-08-27 Samsung Electronics Co Ltd ROBOT CLEANER AND ITS CONTROL METHOD
US20240119630A1 (en) * 2022-10-05 2024-04-11 Avidbots Corp System and method of obstacle and cliff detection for a semi-autonomous cleaning device
CN119562782A (zh) * 2023-01-03 2025-03-04 深圳市闪至科技有限公司 扫地机器人的控制方法、装置、扫地机器人、系统及存储介质
US20250072693A1 (en) * 2023-08-30 2025-03-06 Sharkninja Operating Llc Robotic Cleaner With Extendable Cleaning Surface

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108445878A (zh) * 2018-02-28 2018-08-24 北京奇虎科技有限公司 一种用于扫地机器人的障碍物处理方法和扫地机器人
CN109645892A (zh) * 2018-12-12 2019-04-19 深圳乐动机器人有限公司 一种障碍物的识别方法及清洁机器人
CN110315538A (zh) * 2019-06-27 2019-10-11 深圳乐动机器人有限公司 一种在电子地图上显示障碍物的方法、装置及机器人
CN111481105A (zh) * 2020-04-20 2020-08-04 北京石头世纪科技股份有限公司 一种自行走机器人避障方法、装置、机器人和存储介质
CN112380942A (zh) * 2020-11-06 2021-02-19 北京石头世纪科技股份有限公司 一种识别障碍物的方法、装置、介质和电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4242911A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115471708A (zh) * 2022-09-27 2022-12-13 禾多科技（北京）有限公司 车道线类型信息生成方法、装置、设备和计算机可读介质
CN115471708B (zh) * 2022-09-27 2023-09-12 禾多科技（北京）有限公司 车道线类型信息生成方法、装置、设备和计算机可读介质

Also Published As

Publication number Publication date
CN112380942A (zh) 2021-02-19
CN118898739A (zh) 2024-11-05
US20240008705A1 (en) 2024-01-11
EP4242911A1 (en) 2023-09-13
EP4242911A4 (en) 2024-08-21
CN112380942B (zh) 2024-08-06
US12564303B2 (en) 2026-03-03

Similar Documents

Publication Publication Date Title
WO2022095453A1 (zh) 一种识别障碍物的方法、装置、介质和电子设备
CN114359548B (zh) 一种圆查找方法、装置、电子设备及存储介质
CN110216661B (zh) 跌落区域识别的方法及装置
CN109961074A (zh) 一种查找物品的方法、机器人及计算机可读存储介质
CN110443275B (zh) 去除噪声的方法、设备及存储介质
WO2022095488A1 (zh) 一种检测未知障碍物的方法、装置、介质和电子设备
JP2022542413A (ja) 投影方法および投影システム
CN110335313A (zh) 音频采集设备定位方法及装置、说话人识别方法及系统
CN113378768A (zh) 垃圾桶状态识别方法、装置、设备以及存储介质
CN110443191A (zh) 用于识别物品的方法和装置
CN114964204A (zh) 地图构建方法、地图使用方法、装置、设备和存储介质
CN110119456A (zh) 检索图像的方法及装置
CN113177980A (zh) 用于自动驾驶的目标对象速度确定方法、装置及电子设备
CN112288804B (zh) 一种目标定位的方法及装置
CN113741446B (zh) 一种机器人自主探索的方法、终端设备及存储介质
CN109889977B (zh) 一种基于高斯回归的蓝牙定位方法、装置、设备和系统
CN109978083A (zh) 机器人监测物品环境状态的方法、装置及设备
CN116098522A (zh) 一种地毯区域检测方法、装置及清洁机器人
US20220004774A1 (en) Information processing device, information processing method, and information processing system
CN118863728A (zh) 区域通行状态的确定方法、路径规划方法及装置
CN116206183A (zh) 车道线识别错误的反馈方法、装置、设备及存储介质
CN115453567A (zh) 一种障碍物检测方法、装置、设备、介质及车辆
CN116828398A (zh) 一种跟踪行为识别方法、装置、电子设备和存储介质
CN114659450A (zh) 机器人跟随方法、装置、机器人及存储介质
CN115905588A (zh) 三维测量数据的处理方法和装置、电子设备及存储介质

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: 21888156

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18252035

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021888156

Country of ref document: EP

Effective date: 20230606

WWG Wipo information: grant in national office

Ref document number: 18252035

Country of ref document: US