WO2024051507A1 - 多机器人路径规划方法、装置及计算设备 - Google Patents

多机器人路径规划方法、装置及计算设备 Download PDF

Info

Publication number
WO2024051507A1
WO2024051507A1 PCT/CN2023/115133 CN2023115133W WO2024051507A1 WO 2024051507 A1 WO2024051507 A1 WO 2024051507A1 CN 2023115133 W CN2023115133 W CN 2023115133W WO 2024051507 A1 WO2024051507 A1 WO 2024051507A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
conflict
robots
target
information
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/CN2023/115133
Other languages
English (en)
French (fr)
Inventor
李晶
谭文哲
魏锡光
赵成业
李洪波
韩昊
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 Geekplus Technology Co Ltd
Original Assignee
Beijing Geekplus 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 Geekplus Technology Co Ltd filed Critical Beijing Geekplus Technology Co Ltd
Priority to KR1020257007289A priority Critical patent/KR20250049325A/ko
Priority to EP23862203.9A priority patent/EP4586035A4/en
Priority to JP2025512712A priority patent/JP2025527811A/ja
Priority to US18/996,318 priority patent/US20250390115A1/en
Publication of WO2024051507A1 publication Critical patent/WO2024051507A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • G05D1/02—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
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • 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
    • G05D1/69—Coordinated control of the position or course of two or more vehicles
    • G05D1/693—Coordinated control of the position or course of two or more vehicles for avoiding collisions between vehicles
    • 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
    • G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
    • 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
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • 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
    • G05D1/617—Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards
    • 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
    • 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
    • G05D1/69—Coordinated control of the position or course of two or more vehicles
    • G05D1/698—Control allocation
    • G05D1/6987—Control allocation by centralised control off-board any of the vehicles
    • 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
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2105/00—Specific applications of the controlled vehicles
    • G05D2105/20—Specific applications of the controlled vehicles for transportation
    • G05D2105/28—Specific applications of the controlled vehicles for transportation of freight
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2107/00—Specific environments of the controlled vehicles
    • G05D2107/70—Industrial sites, e.g. warehouses or factories
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2109/00—Types of controlled vehicles
    • G05D2109/10—Land vehicles
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the present disclosure relates to the field of warehousing technology, and in particular to a multi-robot path planning method, device and computing device.
  • AGVs Automated Guided Vehicles
  • autonomous mobile robots are taking on more and more handling and picking tasks in warehouses.
  • reasonable planning of the path of autonomous mobile robots has become a key research direction in the field of warehousing technology.
  • Embodiments of the present disclosure provide a multi-robot path planning method, device and computing device.
  • a multi-robot path planning method including: first, obtaining the driving information of multiple robots; then, predicting the conflict information of each robot based on the driving information of each robot, Among them, the conflict information includes the conflict types in which robots collide with other robots; secondly, according to the conflict information of each robot, the conflict information of the robots whose conflict type is the first conflict type is statistically calculated. According to the statistical results, the robots that meet the first conflict type will be counted. The robot corresponding to the re-planning condition is determined as the target robot, where the first conflict type is any conflict type among multiple conflict types; finally, the path of the target robot is re-planned according to the first conflict type.
  • a multi-robot path planning device including: an acquisition module configured to obtain the to-be-driving information of multiple robots; and a prediction module configured to obtain the to-be-driving information of each robot. , predict the conflict information of each robot, where the conflict information includes the conflict type in which the robot collides with other robots; the determination module is configured to determine the conflict information of the robot whose conflict type is the first conflict type based on the conflict information of each robot.
  • the robot determines the robot that meets the re-planning conditions corresponding to the first conflict type as the target robot, where the first conflict type is any conflict type among multiple conflict types; the re-planning module is configured to The first conflict type involves re-planning the path of the target robot.
  • a computing device including: a memory and a processor; the memory is used to store computer-executable instructions, and when the processor executes the computer-executable instructions, the multi-robot in the first aspect is implemented Steps of the path planning method.
  • a computer-readable storage medium which stores computer-executable instructions.
  • the steps of the multi-robot path planning method in the first aspect are implemented. .
  • Figure 1 is a schematic diagram of a multi-robot path planning system provided by some embodiments of the present disclosure
  • Figure 2 is a schematic diagram of a multi-robot path planning method provided by some embodiments of the present disclosure
  • Figure 3A is a schematic diagram of an opposing conflict provided by some embodiments of the present disclosure.
  • Figure 3B is a schematic diagram of a following conflict provided by some embodiments of the present disclosure.
  • Figure 3C is a schematic diagram of a cross-collision provided by some embodiments of the present disclosure.
  • Figure 3D is a schematic diagram of a stay conflict provided by some embodiments of the present disclosure.
  • Figure 4 is a flow chart for opposing conflicts in a multi-robot path planning method provided by some embodiments of the present disclosure
  • Figure 5 is a flow chart for intersection and following conflicts in a multi-robot path planning method provided by some embodiments of the present disclosure
  • Figure 6 is a schematic diagram of another multi-robot path planning method provided by some embodiments of the present disclosure.
  • Figure 7A is a schematic diagram of yet another multi-robot path planning method provided by some embodiments of the present disclosure.
  • Figure 7B is a schematic diagram of a robot's driving information provided by some embodiments of the present disclosure.
  • Figure 8 is a schematic diagram of a multi-robot path planning device provided by some embodiments of the present disclosure.
  • Figure 9 is a schematic diagram of a computing device provided by some embodiments of the present disclosure.
  • first, second, etc. may be used to describe various information in one or more embodiments of the present disclosure, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other.
  • the first may also be referred to as the second, and similarly, the second may also be referred to as the first.
  • Autonomous Mobile Robot (Automated Guided Vehicle, AGV): Its distinctive feature is driverless driving.
  • the AGV is equipped with an automatic guidance system, which ensures that the system can automatically drive along a predetermined route without manual piloting, and transport goods. Or materials are automatically transported from the starting point to the destination.
  • Path re-planning It consists of path planning and trajectory planning. The sequence points or curves connecting the starting position and the end position are called paths. The strategy that constitutes the path is called path planning. Path re-planning is usually performed when the existing path cannot be traveled. time, re-plan the path.
  • Robot conflict refers to the situation where the path edges or path points overlap with other robots when the robot is driving.
  • Opposing conflict refers to two robots passing the same point or crossing the same edge in a 180-degree direction.
  • Cross conflict refers to two robots passing through the same point in a 90-degree direction.
  • AGVs are increasingly taking on handling and picking tasks in the warehouse.
  • the warehouse is generally divided into path points and path edges. composed of grid map.
  • the path planning problem of multi-robots (such as AGV) is an important factor affecting warehouse efficiency and is very challenging in both theoretical research fields and practical applications.
  • a centralized method and a distributed method can be used to plan the robot's driving path.
  • centralized methods can search conflict-free paths for multiple robots from the spatiotemporal dimension through path planning algorithms.
  • the path points of each robot in the warehouse can be stored in a reservation table.
  • the path points can be expressed as (x, y, t).
  • the path points are used to indicate arrival at the coordinate position (x, y) at time t.
  • This path planning algorithm requires that two robots cannot occupy the same node or pass the same edge at the same time step, otherwise it will be regarded as a path conflict.
  • the algorithm is highly complex and the search space grows exponentially with the number of robots. It is difficult to meet the huge computational overhead and real-time response requirements of path planning for hundreds or thousands of robots.
  • distributed methods can plan paths for a single robot.
  • the distributed method is used to plan the path based on the principle of avoiding congestion and deadlock. For example, when searching for a path for a single robot, you can use a reservation table or a full map to analyze the robot's congestion situation, and add additional heuristic costs to guide the search and avoid some potential conflicts.
  • a reservation table or a full map to analyze the robot's congestion situation, and add additional heuristic costs to guide the search and avoid some potential conflicts.
  • many unpredictable path conflicts will occur during the driving process of the robot, resulting in the robot being unable to drive normally. with work.
  • the present disclosure provides a multi-robot path planning method.
  • the possible conflicts of each robot are predicted based on the driving information of each robot, and then the robots that may conflict are screened.
  • the robot that meets the re-planning conditions corresponding to the first conflict type is selected as the target robot, and the path of the target robot is re-planned according to the first conflict type. Therefore, the multi-robot path planning method provided by the embodiments of the present disclosure can reasonably avoid conflicts by re-planning the path of the target robot before a conflict may occur, and the target robot undergoing path re-planning meets the re-planning conditions, and the re-planning higher efficiency.
  • Figure 1 is a schematic diagram of a multi-robot path planning system provided by some embodiments of the present disclosure. As shown in Figure 1, the system includes a path planning end 101 and a robot end 102.
  • the path planning end 101 may include: a memory 1011 and a processor 1012.
  • the memory 1011 stores program codes of pre-written path planning rules
  • the processor 1012 performs path planning on the robot in the robot end 102 by executing the program codes of the path planning rules.
  • the robot side 102 may include at least one robot(s), such as robot 1021, robot 1022, and robot 1023.
  • the path planning terminal 101 can obtain the driving information of multiple robots (such as the robot 1021, the robot 1022 and the robot 1023) from the robot terminal 102, and then predict the conflict information of each robot based on the driving information of each robot; For the conflict information of the robot, statistics are made on the conflict information of the robots whose conflict type is the first conflict type. According to the statistical results, the robot that meets the re-planning conditions corresponding to the first conflict type is determined as the target robot; finally, according to the first conflict type , re-plan the path of the target robot.
  • the driving information of multiple robots such as the robot 1021, the robot 1022 and the robot 1023
  • the conflict information of the robot statistics are made on the conflict information of the robots whose conflict type is the first conflict type. According to the statistical results, the robot that meets the re-planning conditions corresponding to the first conflict type is determined as the target robot; finally, according to the first conflict type , re-plan the path of the target robot.
  • Figure 2 is a schematic diagram of a multi-robot path planning method provided by some embodiments of the present disclosure.
  • the multi-robot path planning method can be executed by the path planning end 101 in the above embodiment. As shown in Figure 2, the method includes the following steps:
  • Step 202 Obtain the driving information of multiple robots.
  • each robot among the multiple robots can be any robot in a warehousing scenario, such as a transport robot used to transport boxes or shelves.
  • the to-be-driving information refers to information related to pre-planned driving.
  • the to-be-driving information may include at least one of the robot's current position, end position, to-be-driving path, and end-point operation duration.
  • obtaining the driving information of multiple robots is used to later analyze and judge the driving information of these multiple robots, so as to predict conflicts between any one of the robots and other robots.
  • the embodiments of the present disclosure obtain the driving information of multiple robots, so that subsequent analysis can be performed based on the driving information of the multiple robots to predict the conflict information between each robot and other robots, thereby realizing the prediction of the conflict information of multiple robots. .
  • obtaining the to-be-driving information of multiple robots may include: obtaining the to-be-driving information of the multiple robots at the current detection time according to a preset detection cycle.
  • the preset detection period refers to a preset time period for conflict detection. For example, you can set the detection period to a shorter time interval, such as 3 seconds.
  • the current detection time refers to obtaining the robot's waiting information starting from the current detection time.
  • the waiting information of robot A at the 6th second includes at least: the waiting information of the robot A from the 6th second to the 8th second; the waiting information of the robot B at the 6th second at least includes: the waiting information of the robot B from the 6th second to the 8th second. Waiting to drive information at the 10th second.
  • the preset detection cycle interval is usually short, such as 3 seconds.
  • a conflict detection is triggered every short fixed period to obtain the driving information of multiple robots at the current detection time, which can be done in a relatively short time. Do multiple dashes Conflict detection further increases the frequency of analysis of the to-be-driving information of multiple robots, and improves the timeliness of subsequent conflict detection of multiple robots and determination of re-planned robots.
  • Embodiments of the present disclosure obtain the driving information of multiple robots at the current detection time according to a preset detection cycle, so that the driving information of multiple robots at the current detection time can be acquired according to a fixed detection cycle, thereby achieving time-based Detect conflicts periodically to improve the standardization of conflict detection.
  • Step 204 Predict the conflict information of each robot based on the driving information of each robot, where the conflict information includes conflict types between robots and other robots.
  • the conflict information may also include information such as the time when the robot collided with other robots, the location of the conflict, and the identity of the conflicting robot.
  • the robot's identification may include the name of the robot.
  • the conflict prediction when predicting the conflicts of each robot based on the information to be driven by each robot, can be performed on all the paths to be traveled by each robot from the current position to the end position.
  • the to-be-driving information of each robot can be compared, conflicts can be predicted from the starting path point of each robot to the ending path point, and the conflict information of the robots with conflicts at each path point can be recorded.
  • predicting the conflict information of each robot based on the driving information of each robot includes: determining the target driving data of each robot within the preset conflict detection range based on the driving information of each robot; if based on the first According to the target driving data of the robot and the second robot, if the first robot and the second robot pass through the same path point within the preset period, it is determined that there is a conflict between the first robot and the second robot; according to the goals of the first robot and the second robot The driving data identifies the conflict type between the first robot and the second robot; and generates conflict information about the first robot based on the conflict type.
  • the first robot and the second robot may be any two different robots among the plurality of robots.
  • the same path point passed by the first robot and the second robot within the preset period can be any path point within the preset conflict detection range.
  • the same path point that the first robot and the second robot pass through within a preset period of time can be called a first path point, where the first path point can be any of multiple path points within the preset conflict detection range.
  • a waypoint It should be noted that the following embodiments can be schematically explained by taking the same path point as the first path point as an example.
  • the preset conflict detection range may be used to indicate the size of the conflict detection window.
  • the preset conflict detection range can be a fixed-length range size starting from the current position of the robot.
  • the preset conflict detection range can be measured in the number of cells and represented by the window size (such as WindowSize).
  • the window size of the preset conflict detection range can be 10 grids (10 cells).
  • the target driving data is used to indicate driving data that the information to be driven is within a preset conflict detection range.
  • the target driving data may include the path to be traveled by the robot within the preset conflict detection range, way points, path edges, and the time to reach each way point.
  • the preset period refers to a preset time interval.
  • the preset time period can be 5 seconds, 10 seconds, etc.
  • the conflict type is used to indicate the type of conflict that occurs between robots.
  • the conflict type may include an opposing conflict, a following conflict, a crossing conflict, a staying conflict, etc.
  • the first robot and the second robot pass through the same path point, including: the first robot and the second robot drive from the same direction and pass the same path point (such as the first path point); or, the first robot The first robot and the second robot travel in opposite directions and pass the same way point; or the first robot and the second robot travel in directions 90 degrees to each other and pass the same way point.
  • FIG. 3A is a schematic diagram of an opposite conflict provided by some embodiments of the present disclosure.
  • the opposing conflict type means that two robots are traveling in directions 180 degrees from each other, passing the same way point, or passing the same path edge. As shown in Figure 3A, the path to be traveled by robot A is 2 ⁇ 3 ⁇ 4, and the path to be traveled by robot B is 4 ⁇ 3 ⁇ 2. Robot A and robot B move towards each other, and both pass through path point 2 and path Point 3 and path point 4, then there is a conflict between robot A and robot B.
  • Figure 3B is a schematic diagram of a following conflict provided by some embodiments of the present disclosure.
  • the following conflict type means two robots traveling in the same direction and passing the same waypoint. As shown in Figure 3B, the path to be traveled by robot A is 2 ⁇ 3 ⁇ 4, and the path to be traveled by robot B is 2 ⁇ 3 ⁇ 4. Robot A and robot B travel in the same direction, and both pass through path point 2 and path Point 3 and path point 4, then there is a following conflict between robot A and robot B.
  • Figure 3C is a schematic diagram of a cross-collision provided by some embodiments of the present disclosure.
  • the intersection conflict type means two robots traveling 90 degrees from each other and passing the same waypoint. As shown in Figure 3C, the path to be traveled by robot A is 2 ⁇ 3 ⁇ 4, and the path to be traveled by robot B is 1 ⁇ 3 ⁇ 5. Robot A and robot B travel in directions 90 degrees to each other, and both have passed the path. Point 3, then there is a cross conflict between robot A and robot B at path point 3.
  • Figure 3D is a schematic diagram disclosing a stay conflict provided by some embodiments.
  • the dwell conflict type means that a waypoint in a robot's path is the end point of another robot's path. As shown in Figure 3B, the path to be traveled by robot A is 2 ⁇ 3 ⁇ 4, and the path to be traveled by robot B is 5 ⁇ 3. If path point 3 is the end point of robot B, and robot A passes through path point 3, then Robot A and robot B have a stay conflict at waypoint 3.
  • the solution of the embodiment of the present disclosure can flexibly adjust the size of the detection window and re-plan the number of robots by presetting the conflict detection range, thereby improving the accuracy of robot conflict detection.
  • the method may further include: determining the target positions of the first robot and the second robot based on the target driving data of the first robot and the second robot. parameter.
  • generating the conflict information of the first robot according to the conflict type includes: generating conflict information of the first robot according to the conflict type when the target position parameter meets the preset position constraint conditions.
  • the target location parameters refer to parameters of locations related to preset location constraints.
  • the target position parameter may include the time when the robot reaches the first way point, and/or, the current position of the robot.
  • the preset location constraint conditions refer to preset conditions that constrain a certain location recognition conflict.
  • the preset position constraint conditions may include whether a robot that reaches the conflicting path point (such as the first path point) in advance takes the first path point as the end point.
  • the preset position constraints may include whether the distance between the first robot and the second robot is small enough, etc.
  • different conflict types can correspond to different preset position constraints.
  • preset position constraints By setting the preset position constraints, mispredictions of robot conflict information can be reduced. For example, both robot A and robot B will pass through the same path point 5. If robot A's current position is path point 5 and it needs to move further, robot B will need two connected path edges to reach path point 5; If the preset distance threshold is set to 1, then the distance between robot A and robot B is greater than the preset distance threshold. Therefore, it can be determined that the preset position constraints between robot A and robot B are not satisfied. B has no conflict at waypoint 5.
  • the target position parameters may include: the time to arrive at the same path point (such as the first path point); the preset position constraints include: the first robot arrives at the same path point (such as the first path point) late For the second robot, and/or, the time difference between the first robot and the second robot arriving at the same path point (eg, the first path point) is less than the preset time threshold.
  • that same waypoint is the conflicting waypoint. For example, if both robot A and robot B pass through the first path point, then the first path point is the conflicting path point.
  • the preset time threshold refers to the minimum time interval set in advance to ensure that the two robots will not conflict at the first path point. That is to say, when the time difference between the first robot and the second robot reaching the first way point is less than the preset time threshold, a conflict may occur between the first robot and the second robot.
  • the preset time threshold can be set to 10 seconds. If the time for robot A and robot B to arrive at the first way point is 20 seconds and 15 seconds respectively, then the time difference between robot A and robot B for arriving at the first way point is 5 seconds; because the time difference of 5 seconds is less than the preset time interval of 10 seconds , then robot A and robot B may conflict at the first way point.
  • robot A and robot B pass the first path point, and the first path point is the end point of robot A, not the end point of robot B
  • robot A arrives later than robot B then it is determined that robot A arrives later than robot B. There is no stay conflict with robot B.
  • robot A arrives earlier than robot B it is determined that robot A and robot B have a stay conflict. That is, when the first robot reaches the first waypoint later than the second robot, there may be a conflict between the first robot and the second robot.
  • the sooner or later the time at which the path conflict point is reached can be used to determine at least one of stay conflict, crossing conflict, oncoming conflict, and following conflict; the difference in the time at which the path conflict point is reached can also be used to determine on-going conflict, crossing conflict, oncoming conflict, and following conflict. At least one of conflict and following conflict.
  • the embodiments of the present disclosure do not limit this.
  • the embodiment of the present disclosure considers the constraints in the time dimension by taking the sooner or later time of the robot's arrival at the path point and whether the difference is less than the preset time threshold as preset constraints, making the final determined conflict information more accurate.
  • identifying the conflict type of the first robot and the second robot based on the target driving data of the first robot and the second robot includes: identifying the first robot based on the target driving data of the first robot and the second robot. If the robot and the second robot pass through the same path edge, the driving directions of the first robot and the second robot are identified based on the target driving data of the first robot and the second robot; if the driving directions of the first robot and the second robot are the same, then The conflict type between the first robot and the second robot is determined to be a following conflict; if the traveling directions of the first robot and the second robot are different, the conflict type between the first robot and the second robot is determined to be an opposing conflict. If it is determined based on the target driving data of the first robot and the second robot that the first robot and the second robot do not pass through the same path edge, the conflict type between the first robot and the second robot is determined to be a cross conflict.
  • the conflict type of the first robot and the second robot may be determined based on the target driving data. First, it can be identified whether the first robot and the second robot pass through the same path edge; if the first robot and the second robot pass through the same path edge, it can be further determined whether the traveling directions of the first robot and the second robot are the same. If they are the same, Then it can be determined that there is a following conflict between the first robot and the second robot; if they are not the same, it can be determined that there is an opposing conflict between the first robot and the second robot. If the first robot and the second robot do not pass through the same path edge, it is determined that the first robot and the second robot are in cross conflict.
  • the same path edge refers to any path edge among multiple path edges in the path to be traveled.
  • the same path edge passed by the first robot and the second robot is the first path edge.
  • the same path edge (such as the first path edge) may include the first path point.
  • the driving direction is determined based on the path to be traveled in the target driving data.
  • conflicting robots can be stored in a conflict set (such as conflictSet).
  • robots with different conflict types can be stored in different conflict sets; or, robots with different conflict types can also be put into one conflict set.
  • the path edge passed by robot A can be expressed as (N, N1); if the current path point of another robot B is N, also will pass through (N, N1), and the current position distance between robot A and robot B is 1 grid, which is less than the preset distance threshold of 2 grids; in this case, if robot B is behind robot A, then robot A and robot B exist Following the conflict, robot B can be stored in the conflict set.
  • the path edge of robot A to be traveled is (N, N1). If the current path point of another robot B is N1, the path edge to be traveled is (N, N1).
  • Robot B can be stored in the conflict set.
  • the embodiment of the present disclosure determines the type of conflict between the first robot and the second robot by identifying the path points, path edges, and driving directions of the first robot and the second robot, thereby improving the subsequent generation of conflict information for the first robot.
  • the accuracy further improves the accuracy of determining the target robot.
  • identifying the conflict type of the first robot and the second robot based on the target driving data of the first robot and the second robot includes: identifying the second robot based on the target driving data of the first robot and the second robot. If the robot takes the first way point as the end point, and the first robot does not take the first way point as the end point, it is determined that the conflict type between the first robot and the second robot is a stay conflict.
  • the end point of the robot may refer to the end point of the path on which the robot is to travel.
  • the first robot and the second robot pass through the same path point (such as the first path point) and there is a path conflict
  • the first robot and the second robot are identified according to the target driving data of the first robot and the second robot. Whether the second robot takes the first way point as the end point; if the second robot takes the first way point as the end point, and the first robot does not take the first way point as the end point, it is determined that the first robot has a stay conflict and the second robot is the end point. A clash of robots.
  • the second robot when it is determined that the second robot takes the first way point as the end point and the first robot does not take the first way point as the end point, it can be further determined whether the first robot reaches the first way point later than the second robot; if If the first robot reaches the first way point later than the second robot, it is determined that the first robot and the second robot have a stay conflict at the first way point.
  • both the first robot and the second robot take the first way point as the end point, it is determined that there is no stay conflict between the first robot and the second robot.
  • robot B has a stay conflict, and robot B can be stored in the conflict set.
  • Embodiments of the present disclosure identify the end points of the first robot and the second robot to determine whether there is a stay conflict between the first robot and the second robot, thereby improving the accuracy of subsequent generation of conflict information for the first robot and further improving Determine the accuracy of the target robot.
  • the method further includes: recording the information to be driven by the multiple robots into a preset information table.
  • predicting the conflict information of each robot based on the waiting information of each robot includes: traversing the preset information table, and predicting the conflict information of each robot based on the waiting information of each robot in the preset information table. .
  • the preset information table refers to a table preset for recording robot driving information.
  • the acquired driving information of multiple robots can be recorded in the preset information table.
  • the preset information table can be directly traversed. According to the traversed information of each robot, To predict the conflict information of each robot based on the driving information.
  • the driving information of each robot can be directly read, and the conflict information of each robot can be predicted.
  • the embodiments of the present disclosure predict the conflict information of the robots based on the traversed waiting information of each robot, and the obtained prediction results are more comprehensive and accurate, further ensuring the comprehensiveness of the driving information of each robot.
  • Step 206 According to the conflict information of each robot, statistics are made on the conflict information of the robots whose conflict type is the first conflict type. According to the statistical results, the robots that meet the re-planning conditions corresponding to the first conflict type are determined as the target robots.
  • the first conflict type is any one of the plurality of conflict types.
  • the first conflict type may be any one of an opposing conflict, a following conflict, a crossing conflict, and a staying conflict.
  • the statistical results refer to the statistical results of the conflict information of the conflicting robots.
  • statistics may include the number of conflicts in which each robot collided.
  • the statistical information of robot A may include: robot A has had 3 opposing conflicts, 6 cross-conflicts, etc.
  • the statistical information of robot B can include: robot B has 4 cross conflicts, 2 stay conflicts, etc.
  • the re-planning conditions refer to the conditions that determine the need to re-plan the robot's path. Different conflict types may have different re-planning conditions.
  • robots that meet the replanning conditions can be stored in a replanning set (such as rePlanSet).
  • a replanning set such as rePlanSet
  • the conflict information of the robots whose conflict type is the first conflict type is statistically calculated based on the conflict information of each robot. According to the statistical results, the robots that meet the first conflict type will be counted.
  • the robot with the re-planning condition corresponding to the type is determined as the target robot, including: for at least one third robot that has a conflict with each other, according to the conflict information of each third robot, counting the number of robots with each third robot that has a conflict with each other, we get The number of mutual conflicts of each third robot; the third robot with the largest number of mutual conflicts among at least one third robot is determined as the target robot.
  • the number of opposing conflicts refers to the number of opposing conflicts that occur to any robot (such as the third robot).
  • the number of opposing conflicts for robot A is 3, and the number of opposing conflicts for robot B is 5.
  • the number of conflicts corresponding to the same conflict type between any two robots can be one or multiple. For example, if the number of robots that collide with robot A includes 1 for robot B, 2 for robot C, and 1 for robot D, then the number of opposing conflicts for robot A is 4.
  • a robot that encounters a conflict may be called a third robot.
  • the number of the third robots may be multiple.
  • the number of conflicts that may occur with each third robot may be different.
  • the third robot with the largest number of mutual conflicts can be determined as the target robot.
  • the method includes: for at least one third robot in the conflict set, according to the conflict information of each third robot, counting the number of robots that have mutual conflicts with each third robot, and obtaining the number of mutual conflicts of each third robot. After determining the third robot with the largest number of opposing conflicts among at least one third robot as the target robot, the method also includes: deleting the target robot from the conflict set, and storing the target robot in the replanning set until it is in the conflict set. There is no third robot that collides with each other.
  • performing path re-planning on the target robot according to the first conflict type includes: performing path re-planning on each target robot in the re-planning set according to the opposing conflict.
  • a conflict set refers to a set used to record robots with various conflicts.
  • a conflict set can store robots with opposite conflicts or robots with cross conflicts.
  • the number of robots that conflict with the robot is counted based on the robot's conflict information.
  • counting the number of robots it may be that the robot has one or more than one conflict with a certain robot.
  • the target robot can be stored in a preset replanning set rePlanSet.
  • the initial value of the replanning set can be empty.
  • the target robot can be moved from the conflict set conflictSet to the replanning set rePlanSet, that is, the target robot is moved from the conflict set conflictSet Delete it from , and add it to rePlanSet.
  • the target robot after completing the movement of the first target robot, you can continue to determine whether there are still third-party robots that conflict with each other among the remaining third-party robots in the updated conflict set conflictSet (the target robot has been deleted). If the robot exists, the third robot with the largest number of opposing conflicts is determined as the second target robot, and the second target robot is deleted from the conflict set conflictSet and moved to the replanning set rePlanSet. The cycle repeats until there is no third robot that conflicts with each other in the conflict set conflictSet.
  • the conflicting third robot or conflictSet is empty.
  • the number of mutual conflicts between each robot can be calculated by the following formula (1):
  • c represents the conflict type
  • opposition represents the opposite conflict
  • i represents the number of robots
  • n represents the size of the conflict set conflictSet
  • j represents the path point of the unfinished path.
  • c represents the conflict type
  • opposition represents the opposite conflict
  • i represents the number of robots
  • n represents the size of the conflict set conflictSet
  • j represents the path point of the unfinished path.
  • c represents the conflict type
  • opposition represents the opposite conflict
  • i represents the number of robots
  • n represents the size of the conflict set conflictSet
  • j represents the path point of the unfinished path.
  • robots in conflict with robot A include robots B and C; robots in conflict with robot B include robot A; robots in conflict with robot C include robots A and D.
  • Figure 4 is a flow chart for opposing conflicts in a multi-robot path planning method provided by some embodiments of the present disclosure. As shown in Figure 4, the method includes the following steps:
  • Step 402 Determine the number of mutual conflicts of each third robot in the conflictSet.
  • Step 404 Determine the third robot with the largest number of opposing conflicts as the target robot.
  • Step 406 Determine whether conflictSet is empty, or whether the number of opposing conflicts of each third robot is 0.
  • conflictSet is empty or the number of opposing conflicts of each third robot is 0, then the process ends; if conflictSet is not empty, or the number of opposing conflicts of each third robot is not 0, then jump to step 408.
  • Step 408 Delete the target robot from conflictSet and put it into rePlanSet.
  • the embodiment of the present disclosure reduces the number of robots in the conflict set by deleting the target robot from the conflict set and storing it in the re-planning set, so as to facilitate subsequent statistics of the number of opposing conflicts of the remaining robots in the conflict set, and to facilitate subsequent direct re-planning. Extract robots from the planning set for re-planning to speed up the re-planning of conflicting robots.
  • the robot with the re-planning conditions corresponding to the type is determined as the target robot, including: for the fourth robot that has a stay conflict, based on the conflict information of the fourth robot, the end-point operation time of the robot that has a stay-conflict with the fourth robot is counted; if the end-point operation time is If the preset duration threshold is exceeded, the fourth robot is determined as the target robot.
  • the fourth robot may be any robot among multiple robots that has a stay conflict.
  • the end-point operation duration refers to the duration of operation after the robot that conflicts with the fourth robot reaches the end point of the path to be traveled.
  • the container robot may pick up and place the container after reaching the end point, including lifting and lowering the fork, and picking up/replacing the container.
  • the time it takes for the forks to lift and lower, and pick up/replace the bin is the end-point operation time of the bin robot.
  • the preset duration threshold refers to a preset threshold for the duration of the endpoint job.
  • the preset duration threshold can be 1 minute.
  • robot A can be determined as the target robot.
  • robot A when there are multiple robots that conflict with robot A at a certain path point, you can first determine the robot with the longest end-point operation time among the multiple robots, and determine whether the end-point operation time corresponding to this robot exceeds the predetermined time. Set a duration threshold. If it exceeds, robot A is determined to be the target robot.
  • the fourth robot will be regarded as the target robot, that is, the fourth robot will be deleted from the conflictSet and placed in the conflictSet. Enter rePlanSet.
  • the The robot with the re-planning condition corresponding to the first conflict type is determined as the target robot, including: for at least one fifth robot that has a cross conflict and/or a following conflict, according to the conflict information of each fifth robot, statistics of occurrences with each fifth robot
  • the number of robots with cross conflicts and following conflicts is calculated to obtain the sum of the number of cross conflicts and following conflicts of each fifth robot; among at least one fifth robot, the fifth robot with the largest sum of the number of cross conflicts and following conflicts is determined as the target robot. .
  • the sum of the number of cross conflicts and following conflicts refers to the sum of the number of conflicts in which any robot (such as the fifth robot) has cross conflicts and the number of conflicts in which following conflicts occur. For example, if the number of cross conflicts that robot A has is 3 and the number of following conflicts is 2, then the sum of the number of cross conflicts and following conflicts that robot A has is 5; if the number of cross conflicts that robot B has is 1 and the number of following conflicts is 2, then The sum of the number of cross conflicts and following conflicts for robot B is 3.
  • the number of conflicts corresponding to any two robots having cross conflicts and/or following conflicts may be one or multiple.
  • the number of robots that have cross conflicts and/or following conflicts with robot A can be 1 for robot B, 2 for robot C, and 1 for robot D. That is, the sum of the number of cross conflicts and following conflicts for robot A is 4.
  • a robot that has cross conflicts and following conflicts can be called a fifth robot, and the number of fifth robots can be multiple.
  • the sum of the number of cross conflicts and following conflicts that occur for each fifth robot may be different.
  • the fifth robot with the largest number of cross conflicts and following conflicts may be determined as the target robot.
  • for at least one fifth robot that has cross conflicts and/or following conflicts count the number of robots that have cross conflicts and follow conflicts with each fifth robot based on the conflict information of each fifth robot, and obtain each fifth robot.
  • the sum of the number of cross conflicts and following conflicts of five robots includes: for at least one fifth robot in the conflict set, counting the number of robots that have cross conflicts and following conflicts with each fifth robot based on the conflict information of each fifth robot, Obtain the sum of the number of cross conflicts and following conflicts for each fifth robot.
  • the method further includes: deleting the target robot from the conflict set, and adding the target robot to the target robot.
  • the robot is stored in the re-planning set until there is no fifth robot in the conflict set whose number is greater than the preset number threshold, or the number of robots in the re-planning set exceeds the preset number.
  • the fifth robot with the largest number of cross conflicts and following conflicts is determined as the target robot, and then the target robot is moved from the conflictSet to the rePlanSet. That is, the target robot is removed from the conflict set conflictSet and added to the replanning set rePlanSet.
  • the first target robot after completing the movement of the first target robot, continue to determine whether the sum of the number of crossing and following conflicts among the remaining fifth robots in the updated conflictSet (the target robot has been deleted) is greater than the preset quantity threshold. If a robot exists, move the robot from the conflict set conflictSet to the replanning set rePlanSet. The cycle repeats until the sum of the number of cross conflicts and following conflicts in the conflict set conflictSet is less than the preset number threshold, or the number of robots in the replanning set rePlanSet exceeds the preset number.
  • the preset quantity threshold refers to a preset threshold value of the sum of the number of cross conflicts and following conflicts. For example, if the preset quantity threshold is 4, then when the sum of the number of cross conflicts and following conflicts of robot A is 5, since the sum is greater than the preset conflict number threshold of 4, there is no need to determine the target robot in the conflict set conflictSet.
  • c represents the conflict type
  • follow represents following conflict
  • cross represents cross conflict
  • i represents the number of robots
  • n represents the conflictSet size
  • j represents the number of path points of the unfinished path.
  • c represents the conflict type
  • follow represents following conflict
  • cross represents cross conflict
  • i represents the number of robots
  • n represents the conflictSet size
  • j represents the number of path points of the unfinished path.
  • c represents the conflict type
  • follow represents following conflict
  • cross represents cross conflict
  • i represents the number of robots
  • n represents the conflictSet size
  • j represents the number of path points of the unfinished path.
  • replanning when the number of robots in the rePlanSet exceeds the preset number may include: replanning The number of target robots in the set rePlanSet exceeds the preset number, or the number of target robots in the replanning set rePlanSet exceeds the upper limit of the percentage.
  • a target robot threshold can be preset for the replanning set rePlanSet. For example, if the target robot threshold is 10, then when the number of target robots in the replanning set rePlanSet reaches 10, there is no need to store the target robot in the replanning set rePlanSet. In planning collection. Alternatively, you can also preset a percentage threshold for the re-planning set. For example, the percentage threshold is 10%. If the number of robots in the conflict set conflictSet is 80, then when the number of robots in the re-planning set rePlanSet reaches 8, you can There is no need to move the target robot determined in the conflict set to the replanning set rePlanSet.
  • performing path re-planning on the target robot according to the first conflict type includes: performing path re-planning on each target robot in the re-planning set according to crossing conflicts and following conflicts.
  • crossing and following conflicts can be resolved by the robot arriving later by slowing down or parking to avoid.
  • the robot can be The robot that arrives later is used as the target robot for path re-planning; when the sum of the number of cross conflicts and following conflicts is not greater than the preset quantity threshold, the impact can be resolved by slowing down or parking to avoid the conflict.
  • cross conflicts and follow conflicts occur more frequently than stay conflicts and opposite conflicts. If all replanning is performed, the calculation amount of replanning will be large and the effect will be poor. Therefore, you can choose cross conflicts and follow conflicts.
  • the number of conflicts and the robots (that is, some robots) that are greater than the preset number threshold are re-planned.
  • the paths of all robots with cross conflicts and/or following conflicts can be re-planned.
  • the target robot can be deleted from the conflict set and the target robot's identification or name and the corresponding to-be-driving information are stored in the re-planning set.
  • the path of each target robot in the re-planning set is subsequently re-planned based on cross conflicts and following conflicts.
  • Figure 5 is a flow chart for intersection and following conflicts in a multi-robot path planning method provided by some embodiments of the present disclosure. As shown in Figure 5, the method includes the following steps:
  • Step 502 Determine the sum of the number of cross conflicts and following conflicts of each fifth robot in the conflictSet.
  • Step 504 Determine the fifth robot with the largest number of cross conflicts and following conflicts as the target robot.
  • Step 506 Determine whether there are fifth robots in the conflict set whose number sum is greater than the preset number threshold, or whether the number of robots in the replanning set exceeds the preset number.
  • step 508 continues.
  • Step 508 Delete the target robot from conflictSet and put it into rePlanSet.
  • Step 208 Re-plan the path of the target robot according to the first conflict type.
  • different conflict types may correspond to different path re-planning methods.
  • re-planning the path of the target robot according to the first conflict type includes: determining the basic traffic cost corresponding to the first conflict type; determining the probability of at least one conflicting robot colliding with the target robot at the target path point. Prediction is made; among them, the target path point is a path point within the preset range of the target robot's current position; according to the basic traffic cost and the probability of conflict, the traffic cost generated by each conflicting robot for the target robot at the target path point is determined; based on each Traffic cost, path re-planning for the target robot.
  • determining the different basic traffic costs corresponding to each conflict type may include: using the current position of the target robot as a basis, determining multiple paths with a total penalty value, and then determining from the multiple paths a total penalty value less than
  • the path with the preset basic traffic cost threshold is used as the replanned path; or, it can also be based on the path point corresponding to the current position of the robot, explore the surrounding nodes, obtain the path information of other robots in the surrounding nodes, and then determine the conflict Type, according to the different basic traffic costs corresponding to different conflict types, choose the one that satisfies the current path point to the next path point.
  • the path point with the preset basic traffic cost threshold is used as the next path point; then the next path point is used as the benchmark to move until the end point is reached.
  • the base traffic cost is used to indicate a base traffic cost corresponding to the resulting conflict corresponding to the conflict type.
  • different base traffic costs can be configured for heading conflicts, crossing conflicts, following conflicts, and staying conflicts.
  • following conflicts may slow down the walking speed of the robot behind, but usually do not cause deadlocks, etc. Therefore, the basic traffic cost corresponding to following conflicts can be set lower.
  • cross conflicts generally occur at intersections. The robot needs to slow down, stop to avoid, accelerate, etc., which will affect the walking speed. Therefore, the basic traffic cost corresponding to the cross conflict can be higher than that of the following conflict.
  • opposing conflicts may cause deadlocks. For example, in some relatively narrow lane areas, if a conflict occurs, one party may need to turn around and re-plan the path. Therefore, the cost of opposing conflicts will be relatively large, that is, opposing conflicts may cause a deadlock.
  • the basic traffic cost corresponding to a conflict can be higher than that of a cross-conflict; for another example, for a stay conflict, when other robots reach the end point, they generally have to continue working on the spot, such as lifting or lowering shelves, forking boxes, pallets, etc. , which may cause the blocked robot to wait for a long time. Therefore, the basic traffic cost corresponding to the stay conflict can be set higher. Therefore, the basic traffic costs of each conflict type from light to heavy can be: following conflict, crossing conflict, opposing conflict and staying conflict.
  • the target path point refers to a path point within a preset range of the current position of the target robot, and may be a surrounding path point corresponding to the current position of the target robot.
  • the traffic cost incurred by each robot for the target robot at the target path point is determined based on the basic traffic cost and the probability of conflict. For example, when the current robot is currently at the current path point L, there are surrounding path points M and N; when exploring the surrounding path point M as the target path point, the conflict type corresponding to the conflicting robot A is opposite, and the corresponding conflict probability is P1 , the basic traffic cost is t1; the conflict type corresponding to conflict robot B is crossover, the corresponding conflict probability is P2, and the basic traffic cost is t2; the conflict type corresponding to conflict robot C is follow, the corresponding conflict probability is P3, and the basic traffic cost is t3.
  • the traffic cost generated by conflicting robot A is t1*P1
  • the traffic cost generated by conflicting robot B is t2*P2
  • the traffic cost generated by conflicting robot C is t3*P3
  • the total traffic cost of the target way point (way point M) is t1*P1+t2*P2+t3*P3; or, when exploring the surrounding way point N as the target way point, calculate the total traffic cost of the target way point N, and calculate the total traffic cost corresponding to each surrounding way point , select the target way point that meets the preset traffic cost threshold as the next way point.
  • way point M and way point N For example, after determining the traffic costs of way point M and way point N, you can continue to use way point M and way point N as the current way points to continue exploring the surrounding way points until you reach the target robot that needs to be replanned. The end point of the route to be traveled.
  • selection can also be made based on the length of the determined path, so that the re-planned path meets the preset path length threshold. With a shorter path length, it can be Quickly complete mobile handling tasks, saving robot movement resources and occupied path resources.
  • the embodiment of the present disclosure explores the total traffic cost of the target route point, selects the target route point that meets the preset traffic cost threshold from multiple target route points, and repeats the cycle, so that the route points in the replanned route are all If it meets the preset traffic cost threshold, the path of the target robot is re-planned, and the re-planned path also fully ensures the safety of the target robot's movement.
  • Figure 6 is a schematic diagram of another multi-robot path planning method provided by some embodiments of the present disclosure. As shown in Figure 6, the method includes the following steps:
  • Step 602 Trigger conflict detection according to the preset detection period, and obtain the driving information of multiple robots.
  • Step 604 Add the to-be-driving information of multiple robots into the preset information table.
  • Step 606 Determine the conflict information of each robot within the preset conflict detection range.
  • Step 610 Put the target robot that meets the conflicting re-planning conditions into rePanSet.
  • Step 612 Put the target robot that meets the replanning conditions of the stay conflict into rePanSet.
  • Step 614 Put the target robot that meets the re-planning conditions of intersection and following conflicts into rePanSet.
  • Step 616 Re-plan the path of the target robot in rePanSet.
  • step 610 does not limit the execution order of step 610, step 612 and step 614.
  • FIG. 7A is a schematic diagram of another multi-robot path planning method provided by some embodiments of the present disclosure.
  • FIG. 7B is a schematic diagram of robot waiting information provided by some embodiments of the present disclosure.
  • the following is an example of the multi-robot path planning method with reference to Figures 7A and 7B. As shown in Figure 7A, the method includes the following steps:
  • Step 702 According to the detection period of 3 seconds, obtain the waiting information of robot A ⁇ 4 ⁇ 5 ⁇ 6 ⁇ 3 ⁇ ; the waiting information of robot B ⁇ 6 ⁇ 5 ⁇ 2 ⁇ ; and the waiting information of robot C ⁇ 3 ⁇ 6 ⁇ 9 ⁇ .
  • Step 704 Determine the target driving data of robot A ⁇ 4 ⁇ 5 ⁇ 6 ⁇ 3 ⁇ ; the target driving data of robot B ⁇ 6 ⁇ 5 ⁇ 2 ⁇ ; and the target driving data of robot C within the 6 cells of the preset conflict detection range. Data ⁇ 3 ⁇ 6 ⁇ .
  • Step 706 Determine that the conflicts existing in robot A include: one opposing conflict with robot B and one stay conflict with robot C; the conflicts existing in robot B include: one opposing conflict with robot A.
  • Step 708 For the opposing conflict, determine robot B as the target robot for path re-planning; for the stay conflict, determine robot A as the robot for path re-planning.
  • Step 710 The basic traffic cost corresponding to the opposing conflict is 5, and the basic traffic cost corresponding to the following conflict is 2. Then the path re-planning for robot A is: ⁇ 4 ⁇ 1 ⁇ 2 ⁇ 3 ⁇ ; the path re-planning for robot B is: : ⁇ 6 ⁇ 9 ⁇ 8 ⁇ 5 ⁇ 2 ⁇ .
  • Path re-planning that is, re-planning the target robot before a conflict may occur, can reasonably avoid conflicts, and the target robot undergoing path re-planning meets the re-planning conditions, and the re-planning efficiency is higher.
  • FIG. 8 is a schematic diagram of a multi-robot path planning device provided by some embodiments of the present disclosure.
  • the multi-robot path planning device 800 includes: an acquisition module 802, a prediction module 804, a determination module 806 and a re-planning module 808 . in:
  • the acquisition module 802 is configured to acquire the driving information of multiple robots.
  • the prediction module 804 is configured to predict the conflict information of each robot based on the to-be-driving information of each robot; wherein the conflict information includes conflict types in which the robot collides with other robots.
  • the determination module 806 is configured to collect statistics on the conflict information of robots whose conflict information is the first conflict type based on the conflict information of each robot, and determine the robot that meets the re-planning conditions corresponding to the first conflict type as the target based on the statistical results.
  • the re-planning module 808 is configured to re-plan the path of the target robot according to the first conflict type.
  • the prediction module 804 is configured to: determine the target driving data of each robot within the preset conflict detection range based on the to-be-driving information of each robot; if based on the target driving data of the first robot and the second robot, If it is recognized that the first robot and the second robot pass the first path point within a preset period, it is determined that the first robot and the second robot conflict; where the first robot and the second robot are any two robots; according to the first robot and the target driving data of the second robot to identify the conflict type between the first robot and the second robot; and generate conflict information for the first robot based on the conflict type.
  • the multi-robot path planning device 800 further includes a target position parameter determination module.
  • the target position parameter determination module is configured to: determine the first robot and the second robot according to the target driving data of the first robot and the second robot.
  • the target position parameter; the prediction module 804 is configured to: generate conflict information of the first robot according to the conflict type when the target position parameter meets the preset position constraint conditions.
  • the target position parameters include the time to reach the way point;
  • the preset position constraints include: the first robot reaches the first way point later than the second robot, and/or the first robot is different from the second robot. The time difference to reach the first waypoint is less than the preset time threshold.
  • the prediction module 804 is configured to: if it is recognized that the first robot and the second robot pass through the same path edge according to the target driving data of the first robot and the second robot, then according to the first robot and the second robot
  • the target driving data of the first robot and the second robot are used to identify the driving directions of the first robot and the second robot; where the path edges include path points; if they pass through the same path edge; if the first robot and the second robot are traveling in the same direction, determine whether the first robot and the second robot are traveling in the same direction.
  • the conflict type of the robot is a following conflict; if the first robot and the second robot are traveling in different directions, it is determined that the conflict type of the first robot and the second robot is an opposing conflict; if based on the target driving data of the first robot and the second robot , if it is recognized that the traveling directions of the first robot and the second robot do not pass through the same path edge, then the conflict type between the first robot and the second robot is determined to be a cross conflict.
  • the prediction module 804 is configured to: if based on the target driving data of the first robot and the second robot, identify that the second robot takes the first way point as the end point; and the first robot does not take the first way point as the end point. end point, it is determined that the conflict type between the first robot and the second robot is a stay conflict.
  • the first conflict type includes an opposing conflict
  • the determination module 806 is configured to: for at least one third robot that has an opposing conflict, count the occurrence of an opposing conflict with each third robot according to the conflict information of each third robot. The number of robots, the number of mutual conflicts of each third robot is obtained; among at least one third robot, the third robot with the largest number of mutual conflicts is determined as the target robot.
  • the determination module 806 is configured to, for at least one third robot in the conflict set, count the number of robots that conflict with each third robot according to the conflict information of each third robot, and obtain each third robot. The number of opposing conflicts, where the conflict set is used to record the conflicting robots.
  • the multi-robot path planning device 800 also includes a first execution module, which is configured to: delete the target robot from the conflict set, and store the target robot in the re-planning set until there is no third conflicting object in the conflict set. Three robots; the re-planning module 808 is configured to perform path re-planning for each target robot in the re-planning set based on the mutual conflict.
  • the first conflict type includes a stay conflict
  • the determination module 806 is configured to: for the fourth robot that has a stay conflict, count the end points of the robots that have a stay conflict with the fourth robot based on the conflict information of the fourth robot. Operation duration; if the end-point operation duration exceeds the preset duration threshold, the fourth robot is determined as the target robot.
  • the first conflict type includes a cross conflict and a following conflict
  • the determining module 806 is configured to: for at least one fifth robot in which a cross conflict and/or a following conflict occurs, count according to the conflict information of each fifth robot. The number of robots that have cross conflicts and following conflicts with each fifth robot is obtained, and the sum of the number of cross conflicts and following conflicts of each fifth robot is obtained; among at least one fifth robot, the sum of the number of cross conflicts and following conflicts is the largest fifth robot. The robot is determined to be the target robot.
  • the determination module 806 is configured to: for at least one fifth robot in the conflict set, according to the conflict information of each fifth robot, count the number of robots that have cross conflicts and follow-up conflicts with each fifth robot, and obtain The sum of the number of cross conflicts and following conflicts of each fifth robot; where the conflict set is used to record the robots with conflicts.
  • the multi-robot path planning device 800 also includes a second execution module. The second execution module is configured to: delete the target robot from the conflict set, and store the target robot in the re-planning set until the sum of the number of targets in the conflict set is greater than the preset number.
  • the number of fifth robots exceeds the threshold, or the number of robots in the re-planning set exceeds the preset number; the re-planning module 808 is configured to perform path re-planning for each target robot in the re-planning set based on cross conflicts and following conflicts.
  • the re-planning module 808 is configured to determine the basic traffic cost corresponding to the first conflict type; predict the probability of at least one conflicting robot colliding with the target robot at the target way point; wherein the target way point is Path points within the preset range of the current position of the target robot; based on the basic traffic cost and the probability of conflict, determine the traffic costs incurred by each conflicting robot for the target robot at the target path point; based on each traffic cost, re-route the target robot planning.
  • the multi-robot path planning device 800 also includes a recording module configured to record the to-be-driving information of multiple robots into a preset information table; the prediction module 804 is configured to traverse the preset information table. , predict the conflict information of each robot based on the driving information of each robot in the preset information table.
  • each component in the device embodiment should be understood as the functional modules that must be established to implement each step of the program flow or each step of the method.
  • Each functional module is not an actual functional division or separation limit.
  • the device claim defined by such a set of functional modules should be understood as a functional module structure that mainly implements the solution through the computer program described in the specification, and should not be understood as a physical device that mainly implements the solution through hardware.
  • FIG. 9 is a schematic diagram of a computing device provided by some embodiments of the present disclosure.
  • computing device 900 includes memory 910 and processor 920 .
  • the processor 920 and the memory 910 are connected through a bus 930, and the database 950 is used to save data.
  • computing device 900 also includes an access device 940 that enables computing device 900 to communicate via one or more networks 960 .
  • networks 960 include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or networks such as the Internet A combination of communication networks.
  • PSTN Public Switched Telephone Network
  • LAN Local Area Network
  • WAN Wide Area Network
  • PAN Personal Area Network
  • Internet A combination of communication networks.
  • Access device 940 may include any type of network interface, wired or wireless, for example, one or more of a Network Interface Card (NIC), such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless Interface, World Interoperability for Microwave Access (Wi-MAX, World Interoperability for Microwave Access) interface, Ethernet interface, Universal Serial Bus (USB, Universal Serial Bus) interface, cellular network interface, Bluetooth interface, Near Field Communication (NFC, Near Field Communication) interface, etc.
  • NIC Network Interface Card
  • computing device 900 may also be connected to each other, such as by a bus.
  • computing device structural block diagram shown in FIG. 9 is for illustrative purposes only and does not limit the scope of the present disclosure. Those skilled in the art can add or replace other components as needed.
  • computing device 900 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (eg, tablet computer, personal digital assistant, laptop computer, notebook computer, netbook, etc.), a mobile phone (e.g., smartphones), wearable computing devices (e.g., smart watches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs.
  • a mobile computer or mobile computing device eg., tablet computer, personal digital assistant, laptop computer, notebook computer, netbook, etc.
  • a mobile phone e.g., smartphones
  • wearable computing devices e.g., smart watches, smart glasses, etc.
  • stationary computing devices such as desktop computers or PCs.
  • Computing device 900 may also be a mobile or stationary server.
  • the processor 920 is configured to execute computer-executable instructions of the multi-robot path planning method.
  • some embodiments of the present disclosure also provide a computer-readable storage medium storing computer instructions, which when executed by a processor are used for a multi-robot path planning method.
  • the multi-robot path planning device, computing device and computer-readable storage medium provided by the embodiments of the present application are all used to execute the corresponding multi-robot path planning method provided above. Therefore, the beneficial effects it can achieve can be referred to the above. The beneficial effects of the corresponding methods provided will not be described again here.
  • the computer instructions include computer program code, which may be in the form of source code or object code. Code form, executable file or some intermediate form, etc.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Manipulator (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

本公开提供一种多机器人路径规划方法、装置及计算设备，该多机器人路径规划方法包括：获取多个机器人的待行驶信息；根据各机器人的待行驶信息，预测各机器人的冲突信息；其中，冲突信息包括机器人与其他机器人发生冲突的冲突类型；根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人；其中，第一冲突类型为多个冲突类型中的任一冲突类型；根据第一冲突类型，对目标机器人进行路径重规划。

Description

多机器人路径规划方法、装置及计算设备
本申请要求于2022年09月07日提交的申请号为202211091138.8的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及仓储技术领域，特别涉及一种多机器人路径规划方法、装置及计算设备。
背景技术
随着物流仓库的智能化与自动化程度越来越高，自动导向车(Automated Guided Vehicle，AGV)，也可以称为自主移动机器人，在仓库中承担起越来越多的搬运和拣选任务。为提高自主移动机器人搬运和拣选的效率，对自主移动机器人的路径进行合理的规划，成为了仓储技术领域研究的重点方向。
发明内容
本公开实施例提供了一种多机器人路径规划方法、装置及计算设备。
根据本公开实施例的第一方面，提供了一种多机器人路径规划方法，包括：首先，获取多个机器人的待行驶信息；然后，根据各机器人的待行驶信息，预测各机器人的冲突信息，其中，冲突信息包括机器人与其他机器人发生冲突的冲突类型；其次，根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人，其中，第一冲突类型为多个冲突类型中的任一冲突类型；最后，根据第一冲突类型，对目标机器人进行路径重规划。
根据本公开实施例的第二方面，提供了一种多机器人路径规划装置，包括：获取模块，被配置为获取多个机器人的待行驶信息；预测模块，被配置为根据各机器人的待行驶信息，预测各机器人的冲突信息，其中，冲突信息包括机器人与其他机器人发生冲突的冲突类型；确定模块，被配置为根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人，其中，第一冲突类型为多个冲突类型中的任一冲突类型；重规划模块，被配置为根据第一冲突类型，对目标机器人进行路径重规划。
根据本公开实施例的第三方面，提供了一种计算设备，包括：存储器和处理器；存储器用于存储计算机可执行指令，处理器执行所述计算机可执行指令时实现第一方面中多机器人路径规划方法的步骤。
根据本公开实施例的第四方面，提供了一种计算机可读存储介质，其存储有计算机可执行指令，该计算机可执行指令被处理器执行时实现第一方面中多机器人路径规划方法的步骤。
附图说明
图1是本公开一些实施例提供的一种多机器人路径规划系统的示意图；
图2是本公开一些实施例提供的一种多机器人路径规划方法的示意图；
图3A是本公开一些实施例提供的一种相向冲突的示意图；
图3B是本公开一些实施例提供的一种跟随冲突的示意图；
图3C是本公开一些实施例提供的一种交叉冲突的示意图；
图3D是本公开一些实施例提供的一种停留冲突的示意图；
图4是本公开一些实施例提供的一种多机器人路径规划方法中针对相向冲突的流程图；
图5是本公开一些实施例提供的一种多机器人路径规划方法中针对交叉和跟随冲突的流程图；
图6是本公开一些实施例提供的另一种多机器人路径规划方法的示意图；
图7A是本公开一些实施例提供的又一种多机器人路径规划方法的示意图；
图7B是本公开一些实施例提供的一种机器人待行驶信息示意图；
图8是本本公开一些实施例提供的一种多机器人路径规划装置的示意图；
图9是本本公开一些实施例提供的一种计算设备的示意图。
具体实施方式
在下面的描述中阐述了很多具体细节以便于充分理解本公开。但是本公开能够以很多不同于在此描述的其它方式来实施，本领域技术人员可以在不违背本公开内涵的情况下做类似推广，因此本公开不受下面公开的具体实施的限制。
在本公开一个或多个实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本公开一个或多个实施例。在本公开一个或多个实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本公开一个或多个实施例中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本公开一个或多个实施例中可能采用术语第一、第二等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本公开一个或多个实施例范围的情况下，第一也可以被称为第二，类似地，第二也可以被称为第一。
首先，对本公开下述实施例涉及的名词术语进行解释。
自主移动机器人(Automated Guided Vehicle，AGV)：其显著的特点是无人驾驶，AGV上装备有自动导向系统，可以保障系统在不需要人工引航的情况下就能够沿预定的路线自动行驶，将货物或物料自动从起始点运送到目的地。
路径重规划：由路径规划和轨迹规划组成，连接起点位置和终点位置的序列点或曲线称之为路径，构成路径的策略称之为路径规划，路径重规划通常是在现有路径无法进行行驶时，重新进行路径规划。
机器人冲突：指在机器人行驶过程中与其他机器人出现路径边重合或路径点重合的情况。
相向冲突：指两个机器人以180度方向经过同一个点或跨过同一条边。
交叉冲突：指两个机器人以90度方向经过同一个点。
停留冲突：指机器人路径某点是其他机器人的终点。
跟随冲突：指两个机器人以相同方向经过同一个点或跨过同一条边。
随着物流仓库的智能化、自动化程度越来越高，AGV越来越多地承担起仓库中的搬运和拣选任务，为方便调度和控制AGV，一般会把仓库划分为由路径点和路径边构成的网格地图。多机器人(如AGV)路径规划问题是影响仓库效率的重要因素，在理论研究领域与实践应用领域都非常具有挑战性。
示例性地，可以使用集中式方法与分布式方法对机器人的行驶路径进行规划。
在一些示例中，集中式方法可以通过路径规划算法从时空维度搜索多机器人的无冲突路径。例如，可以在一张预约表中存储仓库中各机器人路径点，路径点可以表示为(x,y,t)，该路径点用于指示在时间t到达坐标位置(x,y)。该路径规划算法要求两机器人不能在相同时间步占据同一节点或经过同一条边，否则视为路径冲突。但是该算法复杂度高、搜索空间随着机器人的增多呈指数增长，很难满足成百上千台机器人路径规划的庞大计算开销与实时响应需求。
在一些示例中，分布式方法可以为单台机器人规划路径。在路径规划过程中，分布式方法以避免出现拥堵和死锁为原则进行路径规划。例如，在为单台机器人搜索路径时，可以借助预约表或全地图，分析机器人的拥堵情况，额外添加启发式代价引导搜索，避免一部分潜在冲突。但由于在物流仓储环境中动态事件频发，比如会车时停车避让、制动减速、启动加速等，使得机器人在行驶过程中会产生很多无法预料的路径冲突，导致机器人无法正常行驶 与工作。
为了解决上述问题，本公开提供一种多机器人路径规划方法，通过在机器人可能发生冲突之前，根据各机器人的待行驶信息预测出各机器人可能发生的冲突，然后对可能发生冲突的机器人进行筛选，将筛选出符合第一冲突类型对应重规划条件的机器人确定为目标机器人，并根据第一冲突类型对目标机器人进行路径重规划。因此，本公开实施例提供的多机器人路径规划方法在可能发生冲突前，通过对目标机器人的路径进行重规划，能够合理规避冲突发生，并且进行路径重规划的目标机器人符合重规划条件，重规划的效率更高。
图1为本公开一些实施例提供的一种多机器人路径规划系统的示意图，如图1所示，该系统包括路径规划端101和机器人端102。
在一些示例中，路径规划端101可以包括：存储器1011和处理器1012。其中，存储器1011存储有预先编写好的路径规划规则的程序代码，处理器1012通过执行路径规划规则的程序代码来对机器人端102中的机器人进行路径规划。
在一些示例中，机器人端102可以包括至少一个机器人(一个或多个)，如机器人1021、机器人1022和机器人1023。
例如，路径规划端101可以从机器人端102获取多个机器人(如机器人1021、机器人1022和机器人1023)的待行驶信息，然后，根据各机器人的待行驶信息，预测各机器人的冲突信息；根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人；最后，根据第一冲突类型，对目标机器人进行路径重规划。
下面结合附图，对本公开实施例提供的多机器人路径规划方法进行详述。
图2为本公开一些实施例提供的一种多机器人路径规划方法的示意图，在一些示例中，该多机器人路径规划方法可以通过上述实施例中的路径规划端101执行。如图2所示，该方法包括以下步骤：
步骤202：获取多个机器人的待行驶信息。
例如，多个机器人中的各机器人可以为仓储场景下的任一机器人，如用于搬运货箱或者货架的搬运机器人。
在一些示例中，待行驶信息是指预先规划好的行驶相关的信息，例如，待行驶信息可以包括机器人的当前位置、终点位置、待行驶路径和终点作业时长中的至少一项。
需要说明的是，获取多个机器人的待行驶信息，是用于后期对该些多个机器人的待行驶信息进行分析判断，以便于预测其中任一机器人与其他机器人发生的冲突。
本公开实施例通过获取多个机器人的待行驶信息，使得后续可以基于该多个机器人的待行驶信息进行分析，来预测各机器人与其他机器人的冲突信息，实现了对多个机器人冲突信息的预测。
在一些实施例中，获取多个机器人的待行驶信息可以包括：按照预设的检测周期，获取多个机器人在当前检测时刻的待行驶信息。
在一些示例中，预设的检测周期是指预先设置的进行冲突检测的时间周期。例如，可以将检测周期设置为一个较短的时间间隔，如3秒。当前检测时刻是指获取在当前检测时刻开始起，机器人的待行驶信息。
例如，若机器人A的待行驶路径的总行驶时长为8秒，机器人B的待行驶路径总行驶时长为10秒，预设的检测周期为3秒，则分别获取机器人A和机器人B在第3秒、第6秒和第9秒的待行驶信息。其中，机器人A在第6秒的待行驶信息至少包括：机器人A在第6秒至第8秒的待行驶信息；机器人B在第6秒的待行驶信息至少包括：机器人B在第6秒至第10秒的待行驶信息。
需要说明的是，预设的检测周期间隔通常较短，比如3秒，在每隔较短固定周期触发一次冲突检测，获取多个机器人在当前检测时刻的待行驶信息，可以在较短时间内进行多次冲 突检测，进一步增加对多个机器人的待行驶信息的分析频次，提高了后续对多个机器人冲突检测并确定重规划机器人的及时性。
本公开实施例通过按照预设的检测周期，获取多个机器人在当前检测时刻的待行驶信息，使得可以按照固定的检测周期对多个机器人在当前检测时刻的待行驶信息进行获取，实现按照时间周期对冲突进行检测，提高对冲突进行检测的规范性。
步骤204：根据各机器人的待行驶信息，预测各机器人的冲突信息，其中，冲突信息包括机器人与其他机器人发生冲突的冲突类型。
示例性地，冲突信息还可以包括机器人与其他机器人发生冲突的时间、发生冲突的位置以及发生冲突的机器人的标识等信息。其中，机器人的标识可以包括机器人的名称。
在一些实施例中，在根据各机器人的待行驶信息，预测各机器人存在的冲突时，可以对各机器人从当前位置到终点位置的全部待行驶路径进行冲突预测。在一些示例中，可以将各机器人的待行驶信息进行比对，依次从各机器人的开始路径点到终点路径点进行冲突预测，并记录每一路径点存在冲突的机器人的冲突信息。
在一些实施例中，根据各机器人的待行驶信息，预测各机器人的冲突信息，包括：根据各机器人的待行驶信息，确定各机器人在预设冲突检测范围内的目标行驶数据；若根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人在预设时段内经过同一路径点，则确定第一机器人和第二机器人存在冲突；根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人的冲突类型；根据冲突类型，生成第一机器人的冲突信息。
例如，第一机器人和第二机器人可以为多个机器人中的任意两个不同的机器人。第一机器人和第二机器人在预设时段内经过的同一路径点可以为预设冲突检测范围内的任一路径点。例如，可以将第一机器人和第二机器人在预设时段内经过的同一路径点称为第一路径点，其中，第一路径点可以为预设冲突检测范围内的多个路径点中的任一路径点。需要说明的是，以下实施例可以以同一路径点为第一路径点为例进行示意性说明。
在一些示例中，预设冲突检测范围可以用于指示冲突检测窗口的大小。例如，预设冲突检测范围可以是机器人从当前位置开始的一段固定长度的范围大小。例如，预设冲突检测范围可以用单元格数量来衡量，并采用窗口大小(如WindowSize)表示。如预设冲突检测范围的窗口大小可以为10格(10个单元格)。
在一些示例中，目标行驶数据用于指示待行驶信息在预设冲突检测范围内的行驶数据。例如，目标行驶数据可以包括机器人在预设冲突检测范围内的待行驶路径、路径点、路径边以及到达各路径点的时间等。
在一些示例中，预设时段是指预先设置的时间间隔。比如，预设时段可以是5秒、10秒等。
在一些示例中，冲突类型用于指示机器人之间发生的冲突的类型，例如，冲突类型可以包括相向冲突、跟随冲突、交叉冲突与停留冲突等。
示例性地，第一机器人和第二机器人经过同一路径点，包括：第一机器人和第二机器人从同一个方向驶来，并经过同一路径点(如第一路径点)；或者，第一机器人和第二机器人以相向方向行驶，并经过同一路径点；又或者，第一机器人和第二机器人以互为90度的方向行驶，并经过同一路径点。
图3A为本公开一些实施例提供的一种相向冲突的示意图。
在一些示例中，相向冲突类型表示两个机器人以互为180度的方向行驶，并经过同一个路径点，或经过同一条路径边。如图3A所示，机器人A的待行驶路径是2→3→4，机器人B的待行驶路径是4→3→2，机器人A和机器人B相向而行，且都经过了路径点2、路径点3和路径点4，则机器人A与机器人B之间存在相向冲突。
图3B为本公开一些实施例提供的一种跟随冲突的示意图。
在一些示例中，跟随冲突类型表示两个机器人以相同方向行驶，并经过同一个路径点。如图3B所示，机器人A的待行驶路径是2→3→4，机器人B的待行驶路径是2→3→4，机器人A和机器人B同向行驶，且都经过了路径点2、路径点3和路径点4，则机器人A与机器人B之间存在跟随冲突。
图3C为本公开一些实施例提供的一种交叉冲突的示意图。
在一些示例中，交叉冲突类型表示两个机器人以互为90度方向行驶，并经过同一个路径点。如图3C所示，机器人A的待行驶路径是2→3→4、机器人B的待行驶路径是1→3→5，机器人A和机器人B以互为90度方向行驶，且都经过了路径点3，则机器人A与机器人B在路径点3处存在交叉冲突。
图3D为公开一些实施例提供的一种停留冲突的示意图。
在一些示例中，停留冲突类型表示机器人行驶路径中的某个路径点为其他机器人行驶路径的终点。如图3B所示，机器人A的待行驶路径是2→3→4、机器人B的待行驶路径是5→3，若路径点3为机器人B的终点，且机器人A经过了路径点3，则机器人A与机器人B在路径点3处存在停留冲突。
需要说明的是，预测各机器人之间存在的冲突，还可以按照每一路径点进行预测，预测在任一路径点可能发生的冲突，如冲突类型，然后统计各路径点发生的冲突类型，再统计各机器人发生的冲突类型。
本公开实施例的方案可以通过预设冲突检测范围灵活调节检测窗口的大小以及重规划机器人的数量，提高了对机器人冲突检测的准确率。
在一些实施例中，在根据冲突类型，生成第一机器人的冲突信息之前，该方法还可以包括：根据第一机器人和第二机器人的目标行驶数据，确定第一机器人和第二机器人的目标位置参数。
在一些实施例中，根据冲突类型，生成第一机器人的冲突信息包括：在目标位置参数符合预设位置约束条件的情况下，根据冲突类型，生成第一机器人的冲突信息。
在一些示例中，目标位置参数是指与预设位置约束条件相关的位置的参数。例如，目标位置参数可以包括机器人到达第一路径点的时间，和/或，机器人的当前位置。
在一些示例中，预设位置约束条件是指预先设置的对某位置识别冲突具有约束的条件。例如，对于停留冲突，预设位置约束条件可以包括预先到达冲突路径点(如第一路径点)的机器人是否将第一路径点作为终点。对于相向冲突，预设位置约束条件可以包括第一机器人与第二机器人之间的距离是否足够小等。
在一些示例中，不同的冲突类型可以对应不同的预设位置约束条件，通过设置预设位置约束条件，可以减少机器人冲突信息的误预测。例如，机器人A与机器人B均会经过同一个路径点5，若机器人A的当前位置是路径点5，且还需要接着移动，机器人B还需要两条连接的路径边才可以到达路径点5；若将预设距离阈值设置为1，则机器人A和机器人B之间的距离大于预设距离阈值，因此，可以确定机器人A与机器人B之间不满足预设位置约束条件，则机器人A与机器人B在路径点5处不存在冲突。
在一些实施例中，目标位置参数可以包括：到达同一路径点(如第一路径点)的时间；预设位置约束条件包括：第一机器人到达同一路径点(如第一路径点)的时间晚于第二机器人，和/或，第一机器人与第二机器人到达同一路径点(如第一路径点)的时间差小于预设时间阈值。
在一些示例中，该同一路径点是发生冲突的路径点。比如，机器人A与机器人B均经过第一路径点，则第一路径点为发生冲突的路径点。
示例性地，预设时间阈值是指预先设置保证两个机器人在第一路径点不会发生冲突的最小时间间隔。也就是说，当第一机器人和第二机器人达到第一路径点的时间差小于预设时间阈值时，第一机器人和第二机器人之间可能会发生冲突。
例如，预设时间阈值可以设置为10秒。若机器人A与机器人B到达第一路径点的时间分别为20秒、15秒，则机器人A与机器人B的到达第一路径点的时间差为5秒；由于时间差5秒小于预设时间间隔10秒，则机器人A与机器人B可能会在第一路径点发生冲突。
示例性地，在确定机器人A与机器人B都经过第一路径点，且第一路径点是机器人A的终点，而不是机器人B的终点时，若机器人A晚于机器人B到达，则确定机器人A与机器人B不存在停留冲突，若机器人A早于机器人B到达，则确定机器人A与机器人B存在停留冲突。也就是说，在第一机器人到达第一路径点的时间晚于第二机器人，第一机器人和第二机器人之间可能存在冲突。
在一些示例中，到达路径冲突点的时间早晚可以判断停留冲突、交叉冲突、相向冲突和跟随冲突中的至少一项；到达路径冲突点的时间的差值也可以判断停留冲突、交叉冲突、相向冲突和跟随冲突中的至少一项。本公开实施例对此不作限定。
本公开实施例通过将机器人到达路径点的时间的早晚与差值是否小于预设时间阈值作为预设约束条件，考虑了在时间维度的约束条件，使得最终确定出来的冲突信息更加的准确。
在一些实施例中，根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人的冲突类型，包括：若根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人经过同一路径边，则根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人的行驶方向；若第一机器人和第二机器人的行驶方向相同，则确定第一机器人与第二机器人的冲突类型为跟随冲突；若第一机器人和第二机器人的行驶方向不相同，则确定第一机器人与第二机器人的冲突类型为相向冲突。若根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人不经过同一路径边，则确定第一机器人与第二机器人的冲突类型为交叉冲突。
在一些示例中，在确定第一机器人和第二机器人存在冲突后，可以根据目标行驶数据确定第一机器人和第二机器人的冲突类型。首先，可以识别第一机器人和第二机器人是否经过同一路径边；若第一机器人和第二机器人经过同一路径边，则可以进一步判断第一机器人和第二机器人的行驶方向是否相同，若相同，则可以确定第一机器人和第二机器人之间是跟随冲突；若不相同，则可以确定第一机器人和第二机器人之间是相向冲突。若第一机器人和第二机器人不经过同一路径边，则确定第一机器人和第二机器人为交叉冲突。
在一些示例中，同一路径边是指待行驶路径中的多个路径边中的任一条路径边，例如，第一机器人和第二机器人经过的同一路径边为第一路径边。其中，该同一路径边(如第一路径边)可以包括第一路径点。行驶方向是依据目标行驶数据中待行驶路径确定的。
示例性地，可以将发生冲突的机器人存放在冲突集合(如conflictSet)中。例如，可以将不同的冲突类型的机器人存放在不同的冲突集合中；或者，也可以是将不同冲突类型的机器人均放入一个冲突集合。
在一些示例中，若机器人A的当前路径点为N1，上一路径点为N，则机器人A经过的路径边可以表示为(N，N1)；若另一机器人B当前路径点为N，也会经过(N，N1)，且机器人A与机器人B的当前位置距离为1格，小于预设距离阈值2格；这种情况下，若机器人B处于机器人A后方，则机器人A与机器人B存在跟随冲突，可以将机器人B存放至冲突集合。
在另一些示例中，若机器人A的当前路径点为N，下一路径点为N1，则机器人A的待行驶路径边(N，N1)，若另一机器人B当前路径点为N1，待行驶路径边(N1，N)，即机器人A与机器人B以180度方向经过同一条路径边(N，N1)，则机器人A与机器人B之间存在相向冲突，可以将机器人B存放至冲突集合。
在另一些示例中，若机器人A当前路径点为N1，下一路径点为N，机器人B的当前路径点为M，下一路径点为N，则机器人A和机器人B之间存在交叉冲突，可以将机器人B存放至冲突集合。
本公开实施例通过对第一机器人和第二机器人在路径点、路径边、行驶方向上的识别，来确定第一机器人和第二机器人存在的冲突类型，提高了后续生成第一机器人的冲突信息的准确性，进一步提高了确定目标机器人的准确率。
在一些实施例中，根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人的冲突类型，包括：若根据第一机器人和第二机器人的目标行驶数据，识别第二机器人以第一路径点作为终点，且第一机器人不以第一路径点作为终点，则确定第一机器人与第二机器人的冲突类型为停留冲突。
例如，机器人的终点可以是指机器人的待行驶路径中的路径终点。
在一些示例中，在第一机器人和第二机器人经过同一路径点(如第一路径点)存在路径冲突的情况下，根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人是否以第一路径点作为终点；若第二机器人以第一路径点作为终点，且第一机器人不以第一路径点作为终点，则确定第一机器人存在停留冲突，第二机器人为第一机器人的冲突机器人。
示例性地，在确定第二机器人以第一路径点为终点，第一机器人不以第一路径点为终点时，还可以进一步确定第一机器人是否晚于第二机器人到达第一路径点；若第一机器人晚于第二机器人到达第一路径点，则确定第一机器人和第二机器人在第一路径点存在停留冲突。
在一些示例中，若第一机器人和第二机器人均以第一路径点作为终点，则确定第一机器人和第二机器人不存在停留冲突。
示例性地，若机器人A与机器人B经过同一路径点N，且机器人A先于机器人B到达，存并以路径点N作为路径终点，则机器人B存在停留冲突，可以将机器人B存放至冲突集合。
本公开实施例通过对第一机器人和第二机器人的终点进行识别，确定第一机器人和第二机器人之间是否存在停留冲突，提高了后续生成第一机器人的冲突信息的准确性，进一步提高了确定目标机器人的准确率。
在一些实施例中，在获取到多个机器人的待行驶数据后，该方法还包括：将多个机器人的待行驶信息记入预设信息表。
在一些实施例中，根据各机器人的待行驶信息，预测各机器人的冲突信息，包括：遍历预设信息表，根据预设信息表中每个机器人的待行驶信息，预测每个机器人的冲突信息。
在一些示例中，预设信息表是指预先设置的用于记录机器人行驶信息的表。例如，可以将获取到的多个机器人的待行驶信息记入预设信息表。
例如，在获取到多个机器人的待行驶信息后，将其计入预设信息表，后续在预测每个机器人的冲突信息时，可直接遍历预设信息表，根据遍历到的每个机器人的待行驶信息，来预测每个机器人的冲突信息。或者，也可以在获取到多个机器人的待行驶信息后，直接读取每个机器人的待行驶信息，并对每个机器人的冲突信息进行预测。
本公开实施例根据遍历得到的每个机器人的待行驶信息，对机器人的冲突信息进行预测，得到的预测结果更加的全面、准确，进一步保证了对每个机器人的待行驶信息的全面性。
步骤206：根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人。
例如，第一冲突类型为多个冲突类型中的任一冲突类型。例如，第一冲突类型可以为相向冲突、跟随冲突、交叉冲突以及停留冲突中的任意一种。
在一些示例中，统计结果是指对发生冲突的机器人的冲突信息进行统计得到的结果。例如，统计信息可以包括各机器人发生冲突的冲突数量。如，机器人A的统计信息中可以包括：机器人A发生的相向冲突有3次、交叉冲突有6次等。机器人B的统计信息中可以包括：机器人B发生的交叉冲突有4次，停留冲突有2次等。
在一些示例中，重规划条件是指判断需要对机器人进行路径重规划的条件，不同的冲突类型所对应的重规划条件可能不同。
示例性地，可以将符合重规划条件的机器人(即目标机器人)存放至重规划集合(如rePlanSet)中。
在一些实施例中，在第一冲突类型为相向冲突的情况下，根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人，包括：针对发生相向冲突的至少一个第三机器人，根据各第三机器人的冲突信息，统计与各第三机器人发生相向冲突的机器人的数目，得到各第三机器人的相向冲突数；将至少一个第三机器人中，相向冲突数最大的第三机器人确定为目标机器人。
在一些示例中，相向冲突数是指任一机器人(如第三机器人)发生相向冲突的数量。例如，机器人A发生相向冲突数为3、机器人B发生相向冲突数为5。
在一些示例中，任意两个机器人发生同一冲突类型对应的冲突数可以是一个，也可以是多个。例如，若与机器人A发生相向冲突的机器人的数目包括机器人B为1、机器人C为2、机器人D为1，则得到机器人A的相向冲突数为4。
例如，可以将发生相向冲突的机器人称为第三机器人，第三机器人的数量可以为多个，该多个第三机器人中，各第三机器人发生的相向冲突数可能不同。可以将多个第三机器人中，发生相向冲突数最多的第三机器人确定为目标机器人。
在一些实施例中，针对发生相向冲突的至少一个第三机器人，根据至少一个第三机器人的冲突信息，统计与各第三机器人发生相向冲突的机器人数目，得到各第三机器人的相向冲突数，包括：针对冲突集合中的至少一个第三机器人，根据各第三机器人的冲突信息，统计与各第三机器人发生相向冲突的机器人数目，得到各第三机器人的相向冲突数。在将至少一个第三机器人中，相向冲突数最大的第三机器人确定为目标机器人后，该方法还包括：从冲突集合中删除目标机器人，并将目标机器人存入重规划集合，直至冲突集合中不存在发生相向冲突的第三机器人。
在一些实施例中，根据第一冲突类型，对目标机器人进行路径重规划，包括：根据相向冲突，对重规划集合中的各目标机器人进行路径重规划。
例如，冲突集合是指用于记录存在各种冲突的机器人的集合，比如，冲突集合可以存放有存在相向冲突的机器人，也可以存放有存在交叉冲突的机器人等。
在一些示例中，针对冲突集合中的任一机器人，根据机器人的冲突信息，统计与该机器人发生相向冲突的机器人的数目。其中，统计机器人的数目时，可以是该机器人与某一机器人发生一次或大于一次相向冲突数。
示例性地，可以将目标机器人存放至预设重规划集合rePlanSet中，例如，重规划集合初始值可以为空。
示例性地，在冲突集合(conflictSet)中，将相向冲突数最大的第三机器人确定为目标机器人之后，可以将目标机器人从冲突集合conflictSet移动至重规划集合rePlanSet中，即将目标机器人从冲突集合conflictSet中删除，并添加至重规划集合rePlanSet。
在一些示例中，在完成第一个目标机器人的移动后，可以继续判断更新后的冲突集合conflictSet(已删除目标机器人)中的剩余的其他第三机器人中，是否还存在发生相向冲突的第三机器人，若存在，则将相向冲突数最大的第三机器人确定为第二个目标机器人，将第二个目标机器人从冲突集合conflictSet删除，并移动至重规划集合rePlanSet中。循环往复，直至冲突集合conflictSet中不存在发生相向冲突的第三机器人。
例如，将冲突集合rePlanSet中相向冲突数最多的第三机器人移动至重规划集合rePlanSet后，重新计算冲突集合rePlanSet中各第三机器人的相向冲突数，并将相向冲突数最多的第三机器人移动至重规划集合rePlanSet，反复循环，直至在冲突集合conflictSet中不存在发生相 向冲突的第三机器人或者冲突集合conflictSet为空。
例如，各机器人的相向冲突数可以通过下述式(1)进行计算：
其中，c表示冲突类型，opposite表示相向冲突，i表示第几个机器人，n表示冲突集合conflictSet的大小，j表示未完成路径第几个路径点。表示第i个机器人c类冲突的数量，表示第i个机器人第j个路径点c类冲突的数量。
例如，机器人A的相向冲突机器人包括机器人B和机器人C；机器人B的相向冲突机器人包括机器人A；机器人C的相向冲突机器人包括机器人A和机器人D。在第1轮筛选中，冲突集合conflictSet＝{A,B,C}，重规划集合rePlanSet＝{空}；若机器人A、机器人B和机器人C冲突数分别为2、1、2；可以将机器人A作为目标机器人，并从conflictSet中删去机器人A，并将机器人A放入rePlanSet；在第2轮筛选中，conflictSet＝{B,C}，rePlanSet＝{A}，由于A已经确定为目标机器人，因而不再贡献冲突，所以B、C冲突数分别更新为0、1，这种情况下，可以将机器人C确定为目标机器人。
图4为本公开一些实施例提供的一种多机器人路径规划方法中针对相向冲突的流程图，如图4所示，该方法包括以下步骤：
步骤402：确定conflictSet中各第三机器人的相向冲突数。
步骤404：将相向冲突数最大的第三机器人确定为目标机器人。
步骤406：确定conflictSet是否为空，或各第三机器人的相向冲突数是否为0。
若conflictSet为空或各第三机器人的相向冲突数为0，则结束；若conflictSet不为空，或者各第三机器人的相向冲突数不为0，则跳转至步骤408。
步骤408：将目标机器人从conflictSet中删去，并放入rePlanSet。
返回至步骤402。
本公开实施例通过将目标机器人从冲突集合中进行删除，并存入重规划集合，减少冲突集合中机器人的数目，以便于后续统计冲突集合中其余机器人的相向冲突数，并且方便后续直接在重规划集合中提取机器人进行重规划，加快对存在冲突的机器人的重规划速度。
在一些实施例中，在第一冲突类型为停留冲突的情况下，根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人，包括：针对发生停留冲突的第四机器人，根据第四机器人的冲突信息，统计与第四机器人发生停留冲突的机器人终点作业时长；若终点作业时长超过预设时长阈值，则将第四机器人确定为目标机器人。
例如，第四机器人可以为多个机器人中发生停留冲突的任一个机器人。
在一些示例中，终点作业时长是指与第四机器人发生停留冲突的机器人到达待行驶路径的终点后进行作业的时长。例如，当与第四机器人发生停留冲突的机器人为料箱机器人时，该料箱机器人到达终点后可能会进行取放料箱的工作，包括货叉升降、叉取/放回料箱，则货叉升降、叉取/放回料箱所用的时长即为料箱机器人的终点作业时长。
在一些示例中，预设时长阈值是指预先设置的终点作业的时长的阈值。比如，预设时长阈值可以为1分钟，当机器人A的冲突机器人B在终点的作业时长为2分钟，超过预设时长阈值(1分钟)，则可以将机器人A确定为目标机器人。
在一些示例中，在某一路径点与机器人A发生停留冲突的机器人有多个时，可以先确定多个机器人中在终点作业时长最长的机器人，判断该机器人对应的终点作业时长是否超过预设时长阈值，若超过，则确定机器人A为目标机器人。
示例性地，在第四机器人前方路径有停留冲突，且对应冲突机器人在终点作业时长，超过预设时长阈值，则将第四机器人作为目标机器人，即将第四机器人从conflictSet中删去，并放入rePlanSet。
在一些实施例中，在第一冲突类型包括交叉冲突和跟随冲突的情况下，根据各机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人，包括：针对发生交叉冲突和/或跟随冲突的至少一个第五机器人，根据各第五机器人的冲突信息，统计与各第五机器人发生交叉冲突和跟随冲突的机器人的数目，得到各第五机器人的交叉冲突与跟随冲突的数量和；将至少一个第五机器人中，交叉冲突与跟随冲突的数量和最大的第五机器人确定为目标机器人。
在一些示例中，交叉冲突与跟随冲突的数量和是指任一机器人(如第五机器人)发生交叉冲突的冲突数和发生跟随冲突的冲突数之和。例如，若机器人A发生交叉冲突数为3，跟随冲突数为2，则机器人A发生交叉冲突与跟随冲突的数量和为5；若机器人B发生交叉冲突数为1，跟随冲突数为2，则机器人B发生交叉冲突与跟随冲突的数量和为3。
在一些示例中，任意两个机器人发生交叉冲突和/或跟随冲突对应的冲突数可以是一个，也可以是多个。例如，与机器人A发生交叉冲突和/或跟随冲突的机器人的数目可以是机器人B为1、机器人C为2、机器人D为1，即机器人A的交叉冲突与跟随冲突的数量和为4。
例如，可以将发生交叉冲突和跟随冲突的机器人称为第五机器人，第五机器人的数量可以为多个，这个第五机器人中，各第五机器人发生交叉冲突和跟随冲突的数量和可能不同。可以将多个第五机器人中，相向发生交叉冲突和跟随冲突的数量和最多的第五机器人确定为目标机器人。
在一些实施例中，针对发生交叉冲突和/或跟随冲突的至少一个第五机器人，根据各第五机器人的冲突信息，统计与各第五机器人发生交叉冲突和跟随冲突的机器人数目，得到各第五机器人的交叉冲突与跟随冲突的数量和，包括：针对冲突集合中的至少一个第五机器人，根据各第五机器人的冲突信息，统计与各第五机器人发生交叉冲突和跟随冲突的机器人数目，得到各第五机器人的交叉冲突与跟随冲突的数量和。
在一些实施例中，在将至少一个第五机器人中，交叉冲突与跟随冲突的数量和最大的第五机器人确定为目标机器人之后，该方法还包括：从冲突集合中删除目标机器人，并将目标机器人存入重规划集合，直至冲突集合中不存在数量和大于预设数量阈值的第五机器人，或者，重规划集合中的机器人数目超过预设数目。
示例性地，在冲突集合(conflictSet)中，将交叉冲突与跟随冲突的数量和最大的第五机器人确定为目标机器人，然后将目标机器人从conflictSet移动至rePlanSet中。即将目标机器人从冲突集合conflictSet中删除，并添加至重规划集合rePlanSet。
在一些示例中，在完成第一个目标机器人的移动后，继续判断更新后的conflictSet(已删除目标机器人)中剩余的第五机器人中，是否存在交叉与跟随冲突的数量和大于预设数量阈值的机器人，若存在，则将该机器人从冲突集合conflictSet中移动至重规划集合rePlanSet中。循环往复，直至冲突集合conflictSet中交叉冲突与跟随冲突的数量和小于预设数量阈值，或者，重规划集合rePlanSet中的机器人的数目超过预设数目。
在一些示例中，预设数量阈值是指预先设置的交叉冲突与跟随冲突的数量和的阈值。例如，预设数量阈值为4，则机器人A发生交叉冲突与跟随冲突的数量和为5时，由于数量和大于预设冲突数阈值4，则可以无需在冲突集合conflictSet中确定目标机器人。
例如，各机器人的交叉冲突与跟随冲突的数量和可以通过下述式(2)进行计算：
其中，c表示冲突类型，follow表示跟随冲突，cross表示交叉冲突，i表示第几个机器人，n表示conflictSet大小，j表示未完成路径第几个路径点。表示第i个机器人c类冲突的数量，表示第i个机器人第j个路径点c类冲突的数量。
在一些示例中，重规划集合rePlanSet中的机器人的数目超过预设数目可以包括：重规划 集合rePlanSet中目标机器人数量超过预设数目，或者，重规划集合rePlanSet中目标机器人数量超过百分比上限。
例如，可以为重规划集合rePlanSet预先设置一个目标机器人阈值，比如，目标机器人阈值为10个，则在重规划集合rePlanSet中的目标机器人的数目达到10个时，可以无需再将目标机器人存入重规划集合中。或者，也可以为重规划集合预先设置一个百分比阈值，比如，百分比阈值是10％，若冲突集合conflictSet中机器人的数目为80，则在重规划集合rePlanSet中的机器人的数目达到8个时，可以无需再将冲突集合conflictSet中所确定的目标机器人移动至重规划集合rePlanSet。
在一些实施例中，根据第一冲突类型，对目标机器人进行路径重规划，包括：根据交叉冲突和跟随冲突，对重规划集合中的各目标机器人进行路径重规划。
在一些示例中，交叉和跟随冲突可以通过后到达的机器人通过减速或者停车避让来解决冲突，在交叉冲突与跟随冲突的数量和大于预设数量阈值时可能导致拥堵，这种情况下，可以将后到达的机器人作为目标机器人进行路径重规划；在交叉冲突与跟随冲突的数量和不大于预设数量阈值时，所造成的影响可以通过减速或者停车避让等方式解决冲突。例如，交叉冲突与跟随冲突相比于停留冲突与相向冲突出现的频次更多，若全部进行重规划，会导致重规划的计算量较大，且效果较差，因此，可以选择交叉冲突与跟随冲突的数量和大于预设数量阈值的机器人(即部分机器人)进行路径重规划，或者，也可以对存在交叉冲突和/或跟随冲突的全部进行路径重规划，或者，也可根据实际情况自行选择。
需要说明的是，将目标机器人从冲突集合中删除，并将目标机器人存入重规划集合中，可以将目标机器人从冲突集合中删除，将目标机器人的标识或名称及对应的待行驶信息存入重规划集合中，后续基于交叉冲突和跟随冲突，对重规划集合中的各目标机器人进行路径重规划。
图5为本公开一些实施例提供的一种多机器人路径规划方法中针对交叉和跟随冲突的流程图，如图5所示，该方法包括以下步骤：
步骤502：确定conflictSet中各第五机器人的交叉冲突与跟随冲突的数量和。
步骤504：将交叉冲突与跟随冲突数量最大的第五机器人确定为目标机器人。
步骤506：确定冲突集合中是否存在数量和大于预设数量阈值的第五机器人，或重规划集合中的机器人的数目是否超过预设数目。
若冲突集合中是否不存在数量和大于预设数量阈值的第五机器人，或者重规划集合中的机器人的数目超过预设数目，则结束；若冲突集合中是否还存在数量和大于预设数量阈值的第五机器人，或者重规划集合中的机器人的数目未超过预设数目，则继续执行步骤508。
步骤508：将目标机器人从conflictSet中删去，并放入rePlanSet。
返回至步骤502。
步骤208：根据第一冲突类型，对目标机器人进行路径重规划。
在一些示例中，不同的冲突类型可以对应着不同路径重规划的方式。
在一些实施例中，根据第一冲突类型，对目标机器人进行路径重规划，包括：确定第一冲突类型对应的基础交通代价；对至少一个冲突机器人在目标路径点处与目标机器人发生冲突的概率进行预测；其中，目标路径点为目标机器人当前位置预设范围内的路径点；根据基础交通代价以及发生冲突的概率，分别确定各冲突机器人在目标路径点为目标机器人产生的交通代价；基于各交通代价，对目标机器人进行路径重规划。
在一些示例中，确定各冲突类型对应的不同的基础交通代价可以包括：以目标机器人的当前位置为基准，确定多条附带惩罚总值的路径，然后从多条路径中确定出惩罚总值小于预设基础交通代价阈值的路径，作为重规划出的路径；或者，也可以是以该机器人当前位置对应的路径点为基准，探索周围节点，获取周围节点中其他机器人的路径信息，进而确定冲突类型，根据不同冲突类型对应的基础交通代价不同，选择满足当前路径点至下一路径点符合 预设基础交通代价阈值的路径点作为下一路径点；进而将该下一路径点为基准，进行移动，直至到达终点。
在一些示例中，基础交通代价用于指示与冲突类型相对应的所造成的冲突对应的基础交通代价。例如，可以对相向冲突、交叉冲突、跟随冲突和停留冲突配置不同的基础交通代价。
例如，跟随冲突可能会减慢后边机器人的行走速度，但是通常不会造成死锁等，因此，可以将跟随冲突对应的基础交通代价设置较低。又例如，交叉冲突一般发生在十字路口，机器人需要减速、停车避让、加速等，会影响行走速度，因此，交叉冲突对应的基础交通代价可以高于跟随冲突。又例如，相向冲突可能会造成死锁，如，在一些比较狭窄的巷道区域时，如果发生相向冲突，则可能需要一方调头并重新规划路径，因此，相向冲突造成的代价会比较大，即相向冲突对应的基础交通代价可以高于交叉冲突；又例如，对于停留冲突而言，由于其他机器人在到达终点时，一般要接着原地作业，比如顶升或放下货架、叉取货箱、托盘等，可能造成被阻塞机器人长时间等待，因此，可以将停留冲突对应的基础交通代价设置较高。因此，各冲突类型的基础交通代价由轻到重可以分别为：跟随冲突、交叉冲突、相向冲突和停留冲突。
在一些示例中，目标路径点是指目标机器人当前位置预设范围内的路径点，可以是目标机器人当前位置对应路径点的周围路径点。
在一些示例中，根据基础交通代价以及发生冲突的概率，分别确定各机器人在目标路径点为目标机器人产生的交通代价。比如，当前机器人目前处于当前路径点L处时，存在周围路径点M和N；将周围路径点M作为目标路径点进行探索时，冲突机器人A对应的冲突类型为相向，对应的冲突概率是P1，基础交通代价为t1；冲突机器人B对应的冲突类型为交叉，对应的冲突概率是P2，基础交通代价为t2；冲突机器人C对应的冲突类型为跟随，对应的冲突概率是P3，基础交通代价为t3。则冲突机器人A产生的交通代价为t1*P1，冲突机器人B产生的交通代价为t2*P2，冲突机器人C产生的交通代价为t3*P3，故目标路径点(路径点M)的总交通代价为t1*P1+t2*P2+t3*P3；或者，将周围路径点N作为目标路径点进行探索时，计算得到目标路径点N的总交通代价，从各周围路径点对应的各总交通代价，选择符合预设交通代价阈值的目标路径点作为下一路径点。
例如，在确定了路径点M和路径点N的交通代价后，可以继续将路径点M和路径点N作为当前路径点继续对周围路径点进行探索，直至到达所需要进行重规划的目标机器人的待行驶路径终点。
在一些示例中，在基于交通代价对路径进行重规划的基础上，还可以根据确定出来的路径的长度进行选择，使得重规划的路径满足预设路径长度阈值，在较短路径长度下，可以快速的完成移动搬运任务，节省机器人移动资源以及占用路径资源。
本公开实施例通过对目标路径点的总交通代价进行探索，从多个目标路径点中选择符合预设交通代价阈值的目标路径点，循环往复，使得重规划出来的路径中的路径点都是符合预设交通代价阈值的，实现了对目标机器人的路径重规划，并且重规划后的路径也充分保证了目标机器人移动的安全性。
图6为本公开一些实施例提供的另一种多机器人路径规划方法的示意图，如图6所示，该方法包括以下步骤：
步骤602：按照预设的检测周期触发冲突检测，获取多个机器人的待行驶信息。
步骤604：将多个机器人的待行驶信息计入预设信息表。
步骤606：确定各机器人在预设冲突检测范围内的冲突信息。
步骤608：将冲突数量大于0的机器人放入conflictSet，并令rePanSet＝空集。
步骤610：将满足相向冲突的重规划条件的目标机器人放入rePanSet。
步骤612：将满足停留冲突的重规划条件的目标机器人放入rePanSet。
步骤614：将满足交叉和跟随冲突的重规划条件的目标机器人放入rePanSet。
步骤616：对rePanSet中的目标机器人做路径重规划。
需要说明的是，本公开实施例对步骤610、步骤612和步骤614的执行顺序不作限定。
图7A为本公开一些实施例提供的又一种多机器人路径规划方法的示意图，图7B是本公开一些实施例提供的一种机器人待行驶信息示意图。下面结合图7A和图7B，对多机器人路径规划方法进行举例说明。如图7A所示，该方法包括以下步骤：
步骤702：按照3秒为检测周期，获取机器人A的待行驶信息{4→5→6→3}；机器人B的待行驶信息{6→5→2}；机器人C的待行驶信息{3→6→9}。
例如，机器人A、B、C的待行驶信息如图7B所示。
步骤704：确定在预设冲突检测范围的6格内，机器人A的目标行驶数据{4→5→6→3}；机器人B的目标行驶数据{6→5→2}；机器人C的目标行驶数据{3→6}。
步骤706：确定机器人A存在的冲突包括：与机器人B存在相向冲突1次、与机器人C存在停留冲突1次；机器人B存在的冲突包括：与机器人A存在相向冲突1次。
步骤708：针对相向冲突，确定机器人B为进行路径重规划的目标机器人；针对停留冲突，确定机器人A为进行路径重规划的机器人。
步骤710：相向冲突对应的基础交通代价为5，跟随冲突对应的基础交通代价为2，则为机器人A进行路径重规划得到：{4→1→2→3}；机器人B进行路径重规划得到：{6→9→8→5→2}。
本公开实施例在机器人可能发生冲突之前，先预测出可能发生的冲突，然后对可能发生冲突的机器人进行筛选，筛选出冲突信息的统计结果符合第一冲突对应重规划条件的目标机器人，对其进行路径重规划，即在可能发生冲突前，对目标机器人进行重规划，能够合理规避冲突发生，并且进行路径重规划的目标机器人符合重规划条件，重规划的效率更高。
图8为本公开一些实施例提供的一种多机器人路径规划装置的示意图，如图8所示，多机器人路径规划装置800包括：获取模块802、预测模块804、确定模块806和重规划模块808。其中：
获取模块802，被配置为获取多个机器人的待行驶信息。
预测模块804，被配置为根据各机器人的待行驶信息，预测各机器人的冲突信息；其中，冲突信息包括机器人与其他机器人发生冲突的冲突类型。
确定模块806，被配置为根据各机器人的冲突信息，对冲突信息为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合第一冲突类型对应的重规划条件的机器人确定为目标机器人；其中，第一冲突类型为多个冲突类型中的任一冲突类型。
重规划模块808，被配置为根据第一冲突类型，对目标机器人进行路径重规划。
在一些实施例中，预测模块804被配置为：根据各机器人的待行驶信息，确定各机器人在预设冲突检测范围内的目标行驶数据；若根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人在预设时段内经过第一路径点，则确定第一机器人和第二机器人存在冲突；其中，第一机器人和第二机器人为任两个机器人；根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人的冲突类型；根据冲突类型，生成第一机器人的冲突信息。
在一些实施例中，多机器人路径规划装置800还包括目标位置参数确定模块，目标位置参数确定模块被配置为：根据第一机器人和第二机器人的目标行驶数据，确定第一机器人和第二机器人的目标位置参数；预测模块804被配置为：在目标位置参数符合预设位置约束条件的情况下，根据冲突类型，生成第一机器人的冲突信息。
在一些实施例中，目标位置参数包括到达路径点的时间；预设位置约束条件包括：第一机器人到达第一路径点的时间晚于第二机器人，和/或，第一机器人与第二机器人到达第一路径点的时间差小于预设时间阈值。
在一些实施例中，预测模块804，被配置为：若根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人经过同一路径边，则根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人行驶方向；其中，路径边包括路径点；若经过同一路径边；若第一机器人和第二机器人行驶方向相同，则确定第一机器人与第二机器人的冲突类型为跟随冲突；若第一机器人和第二机器人行驶方向不相同，则确定第一机器人与第二机器人的冲突类型为相向冲突；若根据第一机器人和第二机器人的目标行驶数据，识别第一机器人和第二机器人行驶方向不经过同一路径边，则确定第一机器人与第二机器人的冲突类型为交叉冲突。
在一些实施例中，预测模块804被配置为：若根据第一机器人和第二机器人的目标行驶数据，识别第二机器人以第一路径点作为终点；且第一机器人不以第一路径点作为终点，则确定第一机器人与第二机器人的冲突类型为停留冲突。
在一些实施例中，第一冲突类型包括相向冲突；确定模块806被配置为：针对发生相向冲突的至少一个第三机器人，根据各第三机器人的冲突信息，统计与各第三机器人发生相向冲突的机器人数目，得到各第三机器人的相向冲突数；将至少一个第三机器人中，相向冲突数最大的第三机器人确定为目标机器人。
在一些实施例中，确定模块806被配置为针对冲突集合中的至少一个第三机器人，根据各第三机器人的冲突信息，统计与各第三机器人发生相向冲突的机器人数目，得到各第三机器人的相向冲突数，其中，冲突集合用于记录存在冲突的机器人。多机器人路径规划装置800还包括第一执行模块，第一执行模块被配置为：从冲突集合中删除目标机器人，并将目标机器人存入重规划集合，直至冲突集合中不存在发生相向冲突的第三机器人；重规划模块808被配置为根据相向冲突，对重规划集合中的各目标机器人进行路径重规划。
在一些实施例中，第一冲突类型包括停留冲突；确定模块806被配置为：针对发生停留冲突的第四机器人，根据第四机器人的冲突信息，统计与第四机器人发生停留冲突的机器人的终点作业时长；若终点作业时长超过预设时长阈值，则将第四机器人确定为目标机器人。
在一些实施例中，第一冲突类型包括交叉冲突和跟随冲突；确定模块806被配置为：针对发生交叉冲突和/或跟随冲突的至少一个第五机器人，根据各第五机器人的冲突信息，统计与各第五机器人发生交叉冲突和跟随冲突的机器人数目，得到各第五机器人的交叉冲突与跟随冲突的数量和；将至少一个第五机器人中，交叉冲突与跟随冲突的数量和最大的第五机器人确定为目标机器人。
在一些实施例中，确定模块806被配置为：针对冲突集合中的至少一个第五机器人，根据各第五机器人的冲突信息，统计与各第五机器人发生交叉冲突和跟随冲突的机器人数目，得到各第五机器人的交叉冲突与跟随冲突的数量和；其中，冲突集合用于记录存在冲突的机器人。多机器人路径规划装置800还包括第二执行模块，第二执行模块被配置为：从冲突集合中删除目标机器人，并将目标机器人存入重规划集合，直至冲突集合中不存在数量和大于预设数量阈值的第五机器人，或者，重规划集合中的机器人数目超过预设数目；重规划模块808被配置为根据交叉冲突和跟随冲突，对重规划集合中的各目标机器人进行路径重规划。
在一些实施例中，重规划模块808被配置为确定第一冲突类型对应的基础交通代价；对至少一个冲突机器人在目标路径点处与目标机器人发生冲突的概率进行预测；其中，目标路径点为目标机器人当前位置预设范围内的路径点；根据基础交通代价以及发生冲突的概率，分别确定各冲突机器人在目标路径点为目标机器人产生的交通代价；基于各交通代价，对目标机器人进行路径重规划。
在一些实施例中，多机器人路径规划装置800还包括记入模块，记入模块被配置为将多个机器人的待行驶信息记入预设信息表；预测模块804被配置为遍历预设信息表，根据预设信息表中每个机器人的待行驶信息，预测每个机器人的冲突信息。
需要说明的是，上述实施例提供的一种多机器人路径规划装置的技术方案与上述的多机器人路径规划方法的技术方案属于同一构思，多机器人路径规划装置的技术方案未详细描述的细节内容，均可以参见上述多机器人路径规划方法的技术方案的描述。此外，装置实施例中的各组成部分应当理解为实现该程序流程各步骤或该方法各步骤所必须建立的功能模块，各个功能模块并非实际的功能分割或者分离限定。由这样一组功能模块限定的装置权利要求应当理解为主要通过说明书记载的计算机程序实现该解决方案的功能模块构架，而不应当理解为主要通过硬件方式实现该解决方案的实体装置。
图9为本公开一些实施例提供的一种计算设备的示意图。如图9所示，计算设备900包括：存储器910和处理器920。处理器920与存储器910通过总线930相连接，数据库950用于保存数据。
在一些示例中，计算设备900还包括接入设备940，接入设备940使得计算设备900能够经由一个或多个网络960通信。这些网络的示例包括公用交换电话网(PSTN，Public Switched Telephone Network)、局域网(LAN，Local Area Network)、广域网(WAN，Wide Area Network)、个域网(PAN，Personal Area Network)或诸如因特网的通信网络的组合。接入设备940可以包括有线或无线的任何类型的网络接口，例如，网络接口卡(NIC，Network Interface Controller)中的一个或多个，诸如IEEE802.11无线局域网(WLAN，Wireless Local Area Networks)无线接口、全球微波互联接入(Wi-MAX，World Interoperability for Microwave Access)接口、以太网接口、通用串行总线(USB，Universal Serial Bus)接口、蜂窝网络接口、蓝牙接口、近场通信(NFC，Near Field Communication)接口，等等。
在一些示例中，计算设备900的上述部件以及图9中未示出的其他部件也可以彼此相连接，例如通过总线。例如，图9所示的计算设备结构框图仅仅是出于示例的目的，而不是对本公开范围的限制。本领域技术人员可以根据需要，增添或替换其他部件。
在一些示例中，计算设备900可以是任何类型的静止或移动计算设备，包括移动计算机或移动计算设备(例如，平板计算机、个人数字助理、膝上型计算机、笔记本计算机、上网本等)、移动电话(例如，智能手机)、可佩戴的计算设备(例如，智能手表、智能眼镜等)或其他类型的移动设备，或者诸如台式计算机或PC的静止计算设备。计算设备900还可以是移动式或静止式的服务器。
其中，处理器920用于执行所述多机器人路径规划方法的计算机可执行指令。
需要说明的是，上述实施例提供的计算设备900的技术方案与上述的多机器人路径规划方法的技术方案属于同一构思，计算设备的技术方案未详细描述的细节内容，均可以参见上述多机器人路径规划方法的技术方案的描述。
在一些实施例中，本公开一些实施例还提供一种计算机可读存储介质，其存储有计算机指令，该指令被处理器执行时以用于多机器人路径规划方法。
需要说明的是，上述本实施例提供的计算机可读存储介质的技术方案与上述的多机器人路径规划方法的技术方案属于同一构思，存储介质的技术方案未详细描述的细节内容，均可以参见上述多机器人路径规划方法的技术方案的描述。
本申请实施例提供的多机器人路径规划装置、计算设备及计算机可读存储介质均用于执行上文所提供的对应的多机器人路径规划方法，因此，其所能达到的有益效果可参考上文所提供的对应的方法中的有益效果，此处不再赘述。
上述对本公开特定实施例进行了描述。其他实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
所述计算机指令包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代 码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。
需要说明的是，对于前述的各方法实施例，为了简便描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本公开并不受所描述的动作顺序的限制，因为依据本公开，某些步骤可以采用其它顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定都是本公开所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其它实施例的相关描述。
以上公开的本公开实施例只是用于帮助阐述本公开。可选实施例并没有详尽叙述所有的细节，也不限制该公开仅为所述的具体实施方式。显然，根据本公开的内容，可作很多的修改和变化。本公开选取并具体描述这些实施例，是为了更好地解释本公开的原理和实际应用，从而使所属技术领域技术人员能很好地理解和利用本公开。本公开仅受权利要求书及其全部范围和等效物的限制。

Claims (16)

  1. 一种多机器人路径规划方法，包括：
    获取多个机器人的待行驶信息；
    根据各所述机器人的待行驶信息，预测各所述机器人的冲突信息；其中，所述冲突信息包括所述机器人与其他机器人发生冲突的冲突类型；
    根据各所述机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合所述第一冲突类型对应的重规划条件的机器人确定为目标机器人，其中，所述第一冲突类型为多个所述冲突类型中的任一冲突类型；
    根据所述第一冲突类型，对所述目标机器人进行路径重规划。
  2. 根据权利要求1所述的方法，其中，所述根据各所述机器人的待行驶信息，预测各所述机器人的冲突信息，包括：
    根据各所述机器人的待行驶信息，确定各所述机器人在预设冲突检测范围内的目标行驶数据；
    若根据第一机器人和第二机器人的目标行驶数据，识别所述第一机器人和所述第二机器人在预设时段内经过同一路径点，则确定所述第一机器人和所述第二机器人存在冲突；其中，所述第一机器人和所述第二机器人为所述多个机器人中的任意两个机器人；
    根据所述第一机器人和所述第二机器人的目标行驶数据，识别所述第一机器人和所述第二机器人的冲突类型；
    根据所述冲突类型，生成所述第一机器人的冲突信息。
  3. 根据权利要求2所述的方法，其中，在所述根据所述冲突类型，生成所述第一机器人的冲突信息之前，所述方法还包括：
    根据所述第一机器人和所述第二机器人的目标行驶数据，确定所述第一机器人和所述第二机器人的目标位置参数；
    所述根据所述冲突类型，生成所述第一机器人的冲突信息，包括：
    在所述目标位置参数符合预设位置约束条件的情况下，根据所述冲突类型，生成所述第一机器人的冲突信息。
  4. 根据权利要求3所述的方法，其中，所述目标位置参数包括：到达所述路径点的时间；
    所述预设位置约束条件包括：所述第一机器人到达所述路径点的时间晚于所述第二机器人，和/或，所述第一机器人与所述第二机器人到达所述路径点的时间差小于预设时间阈值。
  5. 根据权利要求2所述的方法，其中，所述根据所述第一机器人和所述第二机器人的目标行驶数据，识别所述第一机器人和所述第二机器人的冲突类型，包括：
    若根据所述第一机器人和所述第二机器人的目标行驶数据，识别所述第一机器人和所述第二机器人经过同一路径边，则根据所述第一机器人和所述第二机器人的目标行驶数据，识别所述第一机器人和所述第二机器人的行驶方向；其中，所述路径边包括所述路径点；
    若所述第一机器人和所述第二机器人的行驶方向相同，则确定所述第一机器人与所述第二机器人的冲突类型为跟随冲突；
    若所述第一机器人和所述第二机器人的行驶方向不相同，则确定所述第一机器人与所述第二机器人的冲突类型为相向冲突；
    若根据所述第一机器人和所述第二机器人的目标行驶数据，识别所述第一机器人和所述第二机器人不经过同一路径边，则确定所述第一机器人与所述第二机器人的冲突类型为交叉冲突。
  6. 根据权利要求2所述的方法，其中，所述根据所述第一机器人和所述第二机器人的目标行驶数据，识别所述第一机器人和所述第二机器人的冲突类型，包括：
    若根据所述第一机器人和所述第二机器人的目标行驶数据，识别所述第二机器人以所述路径点作为终点，且所述第一机器人不以所述路径点作为终点，则确定所述第一机器人与所述第二机器人的冲突类型为停留冲突。
  7. 根据权利要求1-6中任一项所述的方法，其中，所述第一冲突类型包括相向冲突；
    所述根据各所述机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合所述第一冲突类型对应的重规划条件的机器人确定为目标机器人，包括：
    针对发生相向冲突的至少一个第三机器人，根据各所述第三机器人的冲突信息，统计与各所述第三机器人发生相向冲突的机器人的数目，得到各所述第三机器人的相向冲突数；
    将至少一个所述第三机器人中，相向冲突数最大的所述第三机器人确定为所述目标机器人。
  8. 根据权利要求7所述的方法，其中，所述针对发生相向冲突的至少一个第三机器人，根据各所述第三机器人的冲突信息，统计与各所述第三机器人发生相向冲突的机器人的数目，得到各所述第三机器人的相向冲突数，包括：
    针对冲突集合中的至少一个所述第三机器人，根据各所述第三机器人的冲突信息，统计与各所述第三机器人发生相向冲突的机器人数目，得到各所述第三机器人的相向冲突数；其中，所述冲突集合用于记录存在冲突的机器人；
    在所述将至少一个所述第三机器人中，相向冲突数最大的所述第三机器人确定为所述目标机器人之后，所述方法还包括：
    从所述冲突集合中删除所述目标机器人，并将所述目标机器人存入重规划集合，直至所述冲突集合中不存在发生相向冲突的所述第三机器人；
    所述根据所述第一冲突类型，对所述目标机器人进行路径重规划，包括：
    根据所述相向冲突，对所述重规划集合中的各目标机器人进行路径重规划。
  9. 根据权利要求1-6中任一项所述的方法，其中，所述第一冲突类型包括停留冲突；
    所述根据各所述机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合所述第一冲突类型对应的重规划条件的机器人确定为目标机器人，包括：
    针对发生停留冲突的第四机器人，根据所述第四机器人的冲突信息，统计与所述第四机器人发生停留冲突的机器人的终点作业时长；
    若所述终点作业时长超过预设时长阈值，则将所述第四机器人确定为所述目标机器人。
  10. 根据权利要求1-6中任一项所述的方法，其中，所述第一冲突类型包括交叉冲突和跟随冲突；
    所述根据各所述机器人的冲突信息，对冲突类型为第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合所述第一冲突类型对应的重规划条件的机器人确定为目标机器人，包括：
    针对发生交叉冲突和/或跟随冲突的至少一个第五机器人，根据各所述第五机器人的冲突信息，统计与各所述第五机器人发生交叉冲突和跟随冲突的机器人数目，得到各所述第五机器人的交叉冲突与跟随冲突的数量和；
    将所述至少一个第五机器人中，交叉冲突与跟随冲突的数量和最大的所述第五机器人确定为所述目标机器人。
  11. 根据权利要求10所述的方法，其中，所述针对发生交叉冲突和/或跟随冲突的至少一个第五机器人，根据各所述第五机器人的冲突信息，统计与各所述第五机器人发生交叉冲突和跟随冲突的机器人数目，得到各所述第五机器人的交叉冲突与跟随冲突的数量和，包括：
    针对冲突集合中的至少一个所述第五机器人，根据各所述第五机器人的冲突信息，统计与各所述第五机器人发生交叉冲突和跟随冲突的机器人数目，得到各所述第五机器人的交叉冲突与跟随冲突数量和；其中，所述冲突集合用于记录存在冲突的机器人；
    在所述将所述至少一个第五机器人中，交叉冲突与跟随冲突的数量和最大的所述第五机器人确定为所述目标机器人之后，所述方法还包括：
    从所述冲突集合中删除所述目标机器人，并将所述目标机器人存入重规划集合，直至所述冲突集合中不存在数量和大于预设数量阈值的所述第五机器人，或者，所述重规划集合中的机器人的数目超过预设数目；
    所述根据所述第一冲突类型，对所述目标机器人进行路径重规划，包括：
    根据所述交叉冲突和跟随冲突，对所述重规划集合中的各目标机器人进行路径重规划。
  12. 根据权利要求1所述的方法，其中，所述根据所述第一冲突类型，对所述目标机器人进行路径重规划，包括：
    确定所述第一冲突类型对应的基础交通代价；
    对至少一个冲突机器人在目标路径点处与所述目标机器人发生冲突的概率进行预测；其中，所述目标路径点为所述目标机器人当前位置预设范围内的路径点；
    根据所述基础交通代价以及所述发生冲突的概率，分别确定各所述冲突机器人在所述目标路径点对所述目标机器人产生的交通代价；
    基于各所述交通代价，对所述目标机器人进行路径重规划。
  13. 根据权利要求1所述的方法，其中，在所述获取多个机器人的待行驶信息之后，所述方法还包括：
    将所述多个机器人的待行驶信息记入预设信息表；
    所述根据各所述机器人的待行驶信息，预测各所述机器人的冲突信息，包括：
    遍历所述预设信息表，根据所述预设信息表中各所述机器人的待行驶信息，预测各所述机器人的冲突信息。
  14. 一种多机器人路径规划装置，包括：
    获取模块，被配置为获取多个机器人的待行驶信息；
    预测模块，被配置为根据各所述机器人的待行驶信息，预测各所述机器人的冲突信息；其中，所述冲突信息包括所述机器人与其他机器人发生冲突的冲突类型；
    确定模块，被配置为根据各所述机器人的冲突信息，对第一冲突类型的机器人的冲突信息进行统计，根据统计结果，将符合所述第一冲突类型对应的重规划条件的机器人确定为目标机器人；其中，所述第一冲突类型为多个冲突类型中的任一冲突类型；
    重规划模块，被配置为根据所述第一冲突类型，对所述目标机器人进行路径重规划。
  15. 一种计算设备，包括：
    存储器和处理器；
    所述存储器用于存储计算机可执行指令，所述处理器用于执行所述计算机可执行指令实现权利要求1至13任意一项所述多机器人路径规划方法的步骤。
  16. 一种计算机可读存储介质，其存储有计算机指令，其中，所述计算机指令被处理器执行时实现权利要求1至13任意一项所述多机器人路径规划方法的步骤。
PCT/CN2023/115133 2022-09-07 2023-08-28 多机器人路径规划方法、装置及计算设备 Ceased WO2024051507A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020257007289A KR20250049325A (ko) 2022-09-07 2023-08-28 멀티 로봇 경로 계획 방법, 장치 및 컴퓨팅 디바이스
EP23862203.9A EP4586035A4 (en) 2022-09-07 2023-08-28 METHOD AND APPARATUS FOR MULTI-ROBOT TRAIL PLANNING, AND COMPUTER DEVICE
JP2025512712A JP2025527811A (ja) 2022-09-07 2023-08-28 マルチロボット経路計画方法、装置およびコンピューティングデバイス
US18/996,318 US20250390115A1 (en) 2022-09-07 2023-08-28 Multi-robot path planning method and apparatus, and computing device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211091138.8 2022-09-07
CN202211091138.8A CN116184996B (zh) 2022-09-07 2022-09-07 多机器人路径规划方法及装置

Publications (1)

Publication Number Publication Date
WO2024051507A1 true WO2024051507A1 (zh) 2024-03-14

Family

ID=86442938

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/115133 Ceased WO2024051507A1 (zh) 2022-09-07 2023-08-28 多机器人路径规划方法、装置及计算设备

Country Status (6)

Country Link
US (1) US20250390115A1 (zh)
EP (1) EP4586035A4 (zh)
JP (1) JP2025527811A (zh)
KR (1) KR20250049325A (zh)
CN (1) CN116184996B (zh)
WO (1) WO2024051507A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119356401A (zh) * 2024-12-25 2025-01-24 江苏中科重德智能科技有限公司 基于协商的多机器人冲突解决方法、设备及存储介质
TWI897748B (zh) * 2024-12-05 2025-09-11 中華汽車工業股份有限公司 應用於複數移動載具的路徑規劃系統及方法
CN120878114A (zh) * 2025-07-17 2025-10-31 北京国药新创科技发展有限公司 基于医疗物流机器人调度的多机协同冲突消解方法及系统
WO2025232310A1 (zh) * 2024-12-03 2025-11-13 杭州海康机器人股份有限公司 一种仓储机器人避让方式确定方法、装置及电子设备
CN121207180A (zh) * 2025-10-30 2025-12-26 浙江华睿科技股份有限公司 一种路径规划方法和相关装置
CN121498734A (zh) * 2025-12-02 2026-02-10 北京华胜信安电子科技发展有限公司 一种单通道岔道的多agv路径规划方法及设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116184996B (zh) * 2022-09-07 2026-04-28 北京极智嘉科技股份有限公司 多机器人路径规划方法及装置
CN117406740A (zh) * 2023-11-10 2024-01-16 北京有竹居网络技术有限公司 多机器人路径规划方法、装置、设备和介质
US20250370480A1 (en) * 2024-05-31 2025-12-04 Industrial Technology Research Institute Multi-mobile vehicle control system and method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110071750A1 (en) * 2009-09-21 2011-03-24 The Mitre Corporation Airport Surface Conflict Detection
CN108268016A (zh) * 2018-01-19 2018-07-10 广东美的智能机器人有限公司 多移动机器人的冲突管理方法及系统
CN113870602A (zh) * 2021-09-28 2021-12-31 湖南大学 一种多agv泊车调度的方法和系统
CN114527751A (zh) * 2022-01-21 2022-05-24 北京极智嘉科技股份有限公司 机器人路径规划方法、装置及电子设备
CN114661047A (zh) * 2022-03-16 2022-06-24 南京师范大学 一种基于时间窗的多agv实时调度的路径优化方法
CN116184996A (zh) * 2022-09-07 2023-05-30 北京极智嘉科技股份有限公司 多机器人路径规划方法及装置

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4251545B2 (ja) * 2003-07-11 2009-04-08 独立行政法人科学技術振興機構 移動ロボット用経路計画システム
JP4348276B2 (ja) * 2004-11-02 2009-10-21 本田技研工業株式会社 ロボット制御装置
JP4621073B2 (ja) * 2005-05-23 2011-01-26 本田技研工業株式会社 ロボット制御装置
JP6706835B2 (ja) * 2016-01-29 2020-06-10 パナソニックＩｐマネジメント株式会社 移動ロボット制御システム及び移動ロボットを制御するサーバ装置
JP6959056B2 (ja) * 2017-07-20 2021-11-02 株式会社Ihi 移動ロボットの制御装置と制御方法
DE102017120218A1 (de) * 2017-09-01 2019-03-07 RobArt GmbH Bewegungsplanung für autonome mobile roboter
CN111474926B (zh) * 2020-03-24 2023-09-01 浙江中烟工业有限责任公司 一种基于多agv时间窗路径优化算法的废烟回收方法
CN111596658A (zh) * 2020-05-11 2020-08-28 东莞理工学院 一种多agv无碰撞运行的路径规划方法及调度系统
CN111638717B (zh) * 2020-06-06 2023-11-07 浙江科钛机器人股份有限公司 一种分布式自主机器人交通协调机制的设计方法
US12124261B2 (en) * 2020-11-20 2024-10-22 Rapyuta Robotics Co., Ltd. Systems and methods for optimizing route plans in an operating environment
CN114840001B (zh) * 2022-06-01 2025-12-19 浙江大学 一种封闭环境下的多车协同轨迹规划方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110071750A1 (en) * 2009-09-21 2011-03-24 The Mitre Corporation Airport Surface Conflict Detection
CN108268016A (zh) * 2018-01-19 2018-07-10 广东美的智能机器人有限公司 多移动机器人的冲突管理方法及系统
CN113870602A (zh) * 2021-09-28 2021-12-31 湖南大学 一种多agv泊车调度的方法和系统
CN114527751A (zh) * 2022-01-21 2022-05-24 北京极智嘉科技股份有限公司 机器人路径规划方法、装置及电子设备
CN114661047A (zh) * 2022-03-16 2022-06-24 南京师范大学 一种基于时间窗的多agv实时调度的路径优化方法
CN116184996A (zh) * 2022-09-07 2023-05-30 北京极智嘉科技股份有限公司 多机器人路径规划方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4586035A4 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025232310A1 (zh) * 2024-12-03 2025-11-13 杭州海康机器人股份有限公司 一种仓储机器人避让方式确定方法、装置及电子设备
TWI897748B (zh) * 2024-12-05 2025-09-11 中華汽車工業股份有限公司 應用於複數移動載具的路徑規劃系統及方法
CN119356401A (zh) * 2024-12-25 2025-01-24 江苏中科重德智能科技有限公司 基于协商的多机器人冲突解决方法、设备及存储介质
CN120878114A (zh) * 2025-07-17 2025-10-31 北京国药新创科技发展有限公司 基于医疗物流机器人调度的多机协同冲突消解方法及系统
CN121207180A (zh) * 2025-10-30 2025-12-26 浙江华睿科技股份有限公司 一种路径规划方法和相关装置
CN121498734A (zh) * 2025-12-02 2026-02-10 北京华胜信安电子科技发展有限公司 一种单通道岔道的多agv路径规划方法及设备

Also Published As

Publication number Publication date
EP4586035A4 (en) 2025-11-26
JP2025527811A (ja) 2025-08-22
US20250390115A1 (en) 2025-12-25
CN116184996A (zh) 2023-05-30
CN116184996B (zh) 2026-04-28
EP4586035A1 (en) 2025-07-16
KR20250049325A (ko) 2025-04-11

Similar Documents

Publication Publication Date Title
EP4586035A1 (en) Multi-robot path planning method and apparatus, and computing device
US12124261B2 (en) Systems and methods for optimizing route plans in an operating environment
EP4141599B1 (en) Multi-robot route planning
CN111596658A (zh) 一种多agv无碰撞运行的路径规划方法及调度系统
CN111708364B (zh) 一种基于a*算法改进的agv路径规划方法
CN115345450A (zh) 容器搬运任务的分配方法及装置
CN108764579A (zh) 一种基于拥塞控制的仓储多机器人任务调度方法
CN113534787A (zh) Agv调度方法、装置、电子设备及可读存储介质
Shi et al. Task allocation and path planning of many robots with motion uncertainty in a warehouse environment
CN120373785A (zh) 一种机器人配送任务优先级调度方法
Schmidt et al. Research on decentralized control strategies for automated vehicle-based in-house transport systems: A survey
WO2025162067A1 (zh) 路径规划方法和路径规划装置
CN116339257A (zh) Agv多车调度系统以及相关调度方法
CN121165656A (zh) 多agv调度方法
Verma et al. Traffic management of multi-AGV systems by improved dynamic resource reservation
Petković et al. Human intention recognition for human aware planning in integrated warehouse systems
CN118760160A (zh) 基于冲突搜索的多机器人路径规划方法
CN117636641A (zh) 一种用于车辆搬运机器人的车辆间协同搬运方法及装置
US20220274590A1 (en) Transport planning system, transport planning method and program
CN119437269B (zh) 一种多智能体高效协同路径规划方法
Fu et al. Space-time map based path planning scheme in large-scale intelligent warehouse system
Bi et al. Dynamic Weighted and Heat-map Integrated Scalable Information Path-planning Algorithm.
CN118915718B (zh) 动子路径规划方法、装置、计算机设备及可读存储介质
Xiang et al. Research on scheduling algorithm of multi-agvs system
Zhuang et al. A collision-free path planning approach for multiple robots under warehouse scenarios

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 18996318

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 2025512712

Country of ref document: JP

ENP Entry into the national phase

Ref document number: 20257007289

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 1020257007289

Country of ref document: KR

WWE Wipo information: entry into national phase

Ref document number: 2023862203

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

WWP Wipo information: published in national office

Ref document number: 1020257007289

Country of ref document: KR

ENP Entry into the national phase

Ref document number: 2023862203

Country of ref document: EP

Effective date: 20250407

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23862203

Country of ref document: EP

Kind code of ref document: A1

WWP Wipo information: published in national office

Ref document number: 2023862203

Country of ref document: EP