Path planning method and device, equipment and storage medium

The path planning method obtains the detour path and determines the target path, which solves the collision risk and return problems of the robot when blocked by obstacles, and improves driving stability.

CN118999568APending Publication Date: 2024-11-22HANGZHOU HIKROBOT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411099189.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The robot may face obstacles during driving, and there is a risk of collision during detour, so it cannot return to the original path.

Method used

Provide a path planning method, by obtaining multiple orbit paths, determining the target orbit path based on driving space information, and controlling the robot to drive according to the target path to bypass obstacles or wait on the current path, reducing the risk of collision and improving driving stability sex.

Benefits of technology

It effectively reduces the risk of collision between the robot and the obstacle, improves stability during driving, and ensures that the robot can safely bypass the obstacle and return to the original path.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118999568A_ABST
    Figure CN118999568A_ABST
Patent Text Reader

Abstract

The invention discloses a path planning method, device and equipment and a storage medium, relates to the technical field of intelligent control, and is at least used for supporting effective path planning when a robot is blocked by an obstacle, reducing the risk of collision between the robot and the obstacle and improving the stability of the robot in the running process. The method comprises the steps that under the condition that the current path of the robot is blocked by a front obstacle, multiple bypassing paths for bypassing the front obstacle are obtained; the starting position and the ending position of the bypassing path are located on the current path; determining a detour path planning result based on the driving space information corresponding to the plurality of detour paths; the driving space information is used for indicating the position relation of the robot relative to surrounding objects when the robot drives according to the detour path; the bypassing path planning result is used for indicating a target bypassing path allowing the robot to bypass a front obstacle or indicating that the target bypassing path does not exist; and controlling the robot to execute a driving strategy corresponding to the bypassing path planning result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to a path planning method, device, equipment and storage medium. Background Art

[0002] At present, robots can be used to automatically transport materials in warehouses and industrial factories. However, robots may encounter obstacles during driving and need to bypass them. In addition, there is a risk of collision with obstacles during the process of bypassing obstacles, and robots may not be able to bypass and return to the original path. Summary of the invention

[0003] The embodiments of the present application provide a path planning method, apparatus, device and storage medium for supporting effective path planning when a robot is blocked by an obstacle, reducing the risk of collision between the robot and the obstacle, and improving the stability of the robot during driving.

[0004] To achieve the above objectives, the present application provides the following technical solutions:

[0005] In a first aspect, a path planning method is provided, comprising: when a current path of a robot is blocked by an obstacle ahead, obtaining multiple detour paths that bypass the obstacle ahead; the starting position and the ending position of the detour path are on the current path; based on the driving space information corresponding to each of the multiple detour paths, determining the detour path planning result; the driving space information is used to indicate the position relationship of the robot relative to surrounding objects when driving along the detour path; the detour path planning result is used to indicate a target detour path that allows the robot to bypass the obstacle ahead, or to indicate that the target detour path does not exist; controlling the robot to execute a driving strategy corresponding to the detour path planning result; the driving strategy includes driving along the target detour path to bypass the obstacle ahead, or waiting on the current path.

[0006] In this technical solution, after obtaining multiple bypass paths for bypassing the obstacle ahead, it is possible to accurately determine whether there is a target bypass path that allows the robot to bypass the obstacle ahead based on the distances between the robot and the surrounding objects when traveling along each bypass path. Furthermore, the present application can control the robot to travel along the target bypass path to bypass the obstacle ahead when there is a target bypass path that allows the robot to bypass the obstacle ahead, thereby improving driving efficiency and reducing the risk of collision with obstacles. Alternatively, the present application can control the robot to wait on the current path when there is no target bypass path that allows the robot to bypass the obstacle ahead to avoid the problem of being unable to return to the current path when bypassing the obstacle ahead. Therefore, the present application can be used to support effective path planning when the robot is blocked by an obstacle, reduce the risk of collision between the robot and the obstacle, and improve the stability of the robot during driving.

[0007] In a possible embodiment, the driving space information includes at least one of the following: a first distance between the space occupied by the robot and the edge of the road involved in the detour path, and a second distance between the space occupied by the robot when it is parallel to the obstacle in front and the space occupied by the obstacle in front; a method for determining a detour path planning result based on the driving space information corresponding to each of the multiple detour paths specifically includes: when the first distances corresponding to each of the multiple detour paths are less than or equal to the first distance, determining that there is no target detour path; when there is at least one candidate detour path with a first distance greater than the first distance among the multiple detour paths, determining the target detour path based on the second distances corresponding to each of the candidate detour paths; when the second distance corresponding to the candidate detour path is less than or equal to the second distance, the probability that the candidate detour path is determined as the target detour path is positively correlated with the second distance corresponding to the candidate detour path; when the second distance corresponding to the candidate detour path is greater than the second distance, the probability that the candidate detour path is determined as the target detour path is negatively correlated with the second distance corresponding to the candidate detour path.

[0008] In a possible embodiment, the driving space information also includes at least one of the following: a third distance of the space occupied by the robot relative to the space occupied by other obstacles around the detour path, and a fourth distance of the space occupied by the robot relative to the space occupied by other robots passing by the detour path; a method for determining a detour path planning result based on the driving space information corresponding to each of a plurality of detour paths specifically includes: when the third distance corresponding to at least one candidate detour path is less than or equal to the first distance, determining that there is no target detour path; when there is at least one candidate detour path among the plurality of detour paths whose first distance is greater than the first distance and whose third distance is greater than the first distance, determining the target detour path based on the second distance and the fourth distance corresponding to each candidate detour path; the probability of a candidate detour path being determined as the target detour path is negatively correlated with the fourth distance corresponding to the candidate detour path.

[0009] In a possible embodiment, before obtaining multiple detour paths around the obstacle ahead, the method further includes: obtaining identification information of the road ahead on the current path; the identification information includes at least one of the following: the position of the obstacle ahead, the number of obstacles whose spacing relative to the obstacle ahead is less than or equal to a third distance, and the state of the path behind the obstacle ahead on the current path; the state of the path includes a passable state or a congested state; based on the identification information of the road ahead, determining whether a detour condition is met; the detour condition includes at least one of the following: the position of the obstacle ahead is spaced relative to the end point of the current path by a distance greater than a fourth distance, the number of obstacles is less than or equal to a preset number, and the state of the path is a passable state.

[0010] In a possible embodiment, a method for obtaining multiple bypass paths around a front obstacle specifically includes: determining the starting position and the ending position of the bypass path based on the length of the robot, and the length and position of the front obstacle; the starting position is the current position of the robot, or the distance between the starting position and the position of the front obstacle is equal to the weighted sum of the length of the robot and the length of the front obstacle; the distance between the ending position and the position of the front obstacle is equal to the weighted sum of the length of the robot and the length of the front obstacle; determining multiple bypass paths from the starting position to the end position via the side of the front obstacle; the bypass path includes a sub-path from the starting position to a first middle position, a sub-path from the first middle position to a second middle position, and a sub-path from the second middle position to the end position; the first middle position is between the starting position and the position of the front obstacle, and the second middle position is between the position of the front obstacle and the end position; the sub-paths included in different bypass paths have different first middle positions and / or different second middle positions.

[0011] In a possible embodiment, when the distance between the starting position and the position of the front obstacle is greater than the length of the robot, the sub-path from the starting position to the first intermediate position is a curved path; when the distance between the starting position and the position of the front obstacle is less than or equal to the length of the robot, the sub-path from the starting position to the first intermediate position is a straight path.

[0012] In a possible embodiment, when the driving strategy is to drive along a target detour path to bypass an obstacle ahead, a method for controlling a robot to execute a driving strategy corresponding to a detour path planning result specifically includes: when the target detour path conflicts with the driving paths of other robots, controlling the robot to wait for the other robots to leave the target detour path and then drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle ahead, and adjusting the target detour path to a prohibited entry state during the robot's waiting period to prohibit other robots whose driving paths do not conflict with the target detour path from entering the target detour path; when the target detour path does not conflict with the driving paths of other robots, controlling the robot to drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle ahead.

[0013] In a second aspect, a path planning device is provided, comprising: an acquisition unit, a processing unit and a control unit;

[0014] An acquisition unit, used for acquiring a plurality of detour paths around the obstacle ahead when the current path of the robot is blocked by the obstacle ahead; the starting position and the ending position of the detour path are on the current path;

[0015] A processing unit, configured to determine a detour path planning result based on driving space information corresponding to each of the plurality of detour paths; the driving space information is used to indicate a positional relationship of the robot relative to surrounding objects when the robot travels along the detour path; the detour path planning result is used to indicate a target detour path that allows the robot to bypass a front obstacle, or is used to indicate that there is no target detour path;

[0016] A control unit is used to control the robot to execute a driving strategy corresponding to the detour path planning result; the driving strategy includes driving along the target detour path to bypass the obstacle ahead, or waiting on the current path.

[0017] In a possible embodiment, the driving space information includes at least one of the following: a first distance between the space occupied by the robot and the edge of the road involved in the detour path, and a second distance between the space occupied by the robot when it is parallel to the obstacle in front and the space occupied by the obstacle in front; a processing unit is specifically used to: determine that there is no target detour path when the first distances corresponding to each of the multiple detour paths are less than or equal to the first distance; determine the target detour path based on the second distances corresponding to each candidate detour path when there is at least one candidate detour path with a first distance greater than the first distance among the multiple detour paths; when the second distance corresponding to the candidate detour path is less than or equal to the second distance, the probability that the candidate detour path is determined as the target detour path is positively correlated with the second distance corresponding to the candidate detour path; when the second distance corresponding to the candidate detour path is greater than the second distance, the probability that the candidate detour path is determined as the target detour path is negatively correlated with the second distance corresponding to the candidate detour path.

[0018] In a possible embodiment, the driving space information also includes at least one of the following: a third distance between the space occupied by the robot and the space occupied by other obstacles around the detour path, and a fourth distance between the space occupied by the robot and the space occupied by other robots passing by the detour path; a processing unit is specifically used to: determine that there is no target detour path when the third distances corresponding to at least one candidate detour path are both less than or equal to the first distance; determine the target detour path based on the second distance and the fourth distance corresponding to each candidate detour path when there is at least one candidate detour path among multiple detour paths whose first distance is greater than the first distance and whose third distance is greater than the first distance; the probability of a candidate detour path being determined as the target detour path is negatively correlated with the fourth distance corresponding to the candidate detour path.

[0019] In a possible embodiment, the acquisition unit is further used to acquire identification information of the road ahead on the current path; the identification information includes at least one of the following: the position of the obstacle ahead, the number of obstacles whose distance relative to the obstacle ahead is less than or equal to a third distance, and the state of the path behind the obstacle ahead on the current path; the state of the path includes a passable state or a congested state; the processing unit is further used to determine whether a detour condition is met based on the identification information of the road ahead; the detour condition includes at least one of the following: the position of the obstacle ahead is greater than a fourth distance relative to the end point of the current path, the number of obstacles is less than or equal to a preset number, and the state of the path is a passable state.

[0020] In a possible embodiment, the acquisition unit is specifically used to: determine the starting position and ending position of bypassing the front obstacle based on the length of the robot, and the length and position of the front obstacle; the starting position is the current position of the robot, or the distance between the starting position and the position of the front obstacle is equal to the weighted sum of the length of the robot and the length of the front obstacle; the distance between the ending position and the position of the front obstacle is equal to the weighted sum of the length of the robot and the length of the front obstacle; determine multiple bypass paths from the starting position through the side of the front obstacle to the end position; the bypass path includes a sub-path from the starting position to a first middle position, a sub-path from the first middle position to a second middle position, and a sub-path from the second middle position to the end position; the first middle position is between the starting position and the position of the front obstacle, and the second middle position is between the position of the front obstacle and the end position; the sub-paths included in different bypass paths have different first middle positions and / or different second middle positions.

[0021] In a possible embodiment, when the distance between the starting position and the position of the front obstacle is greater than the length of the robot, the sub-path from the starting position to the first intermediate position is a curved path; when the distance between the starting position and the position of the front obstacle is less than or equal to the length of the robot, the sub-path from the starting position to the first intermediate position is a straight path.

[0022] In a possible embodiment, the control unit is specifically used to: when a target detour path conflicts with the driving paths of other robots, control the robot to wait for the other robots to leave the target detour path and then drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle in front, and adjust the target detour path to a prohibited entry state during the robot waiting period to prohibit other robots whose driving paths do not conflict with the target detour path from entering the target detour path; when the target detour path does not conflict with the driving paths of other robots, control the robot to drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle in front.

[0023] In a third aspect, a server is provided, comprising: a processor and a memory. The processor is connected to the memory, the memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions stored in the memory, thereby implementing any one of the methods provided in the first aspect.

[0024] In a fourth aspect, a readable storage medium is provided, comprising computer-executable instructions. When the computer-executable instructions are executed on a server, the server executes any one of the methods provided in the first aspect.

[0025] In a fifth aspect, a computer program product is provided, comprising computer execution instructions, which, when executed on a server, cause the server to execute any one of the methods provided in the first aspect.

[0026] The technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of a flow chart of a path planning method provided in an embodiment of the present application;

[0029] Figure 3 A schematic diagram of a path scenario provided in an embodiment of the present application;

[0030] Figure 4 A schematic diagram of another path scenario provided in an embodiment of the present application;

[0031] Figure 5 A schematic diagram of another path scenario provided in an embodiment of the present application;

[0032] Figure 6 A schematic diagram of another path scenario provided in an embodiment of the present application;

[0033] Figure 7 A flowchart of another path planning method provided in an embodiment of the present application;

[0034] Figure 8 A schematic diagram of the structure of a path planning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0036] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0037] First, a brief introduction to the application scenarios involved in this application is given.

[0038] At present, when the robot detects an obstacle during its driving process and the blocking time reaches a set time, a detour path can be planned to bypass the obstacle.

[0039] However, if the path space, obstacle size, and robot size are not considered when planning the detour path, the robot may still be at risk of colliding with the obstacle while detouring it, and may not be able to detour back to the original path. Especially in narrow channel scenarios, the robot is easily restricted by space and cannot detour back to the original path, thus becoming a new obstacle and affecting the passage of other robots.

[0040] In addition, the robot's driving path is generally planned based on a topological map, but the topological map usually does not include information such as road width, making it difficult to effectively support the identification of whether it is possible to bypass the obstacle to the side, which can easily lead to problems such as taking a long detour or identifying that the obstacle cannot be bypassed.

[0041] Next, the implementation environment (implementation architecture) involved in this application is briefly introduced.

[0042] An embodiment of the present application provides a path planning method that can be applied to equipment of a robot system.

[0043] Optionally, a server for central scheduling may or may not be deployed in the robot system.

[0044] In the case where a server for central scheduling is deployed in the robot system, the robot system may include multiple robots and servers. In this case, the device that executes the path planning method provided in the embodiment of the present application may be a server. The server can establish a connection with each robot in the robot system to obtain the size information of each robot, as well as the position information, obstacle information, etc. measured by each robot. In addition, the server can also be used to manage the usage status of resources such as roads and charging piles. Furthermore, the server can plan the driving path of each robot based on the information measured by the robot and the usage status of the resources, and instruct the robot to travel along the planned path through interaction with the robot.

[0045] In the case where a central dispatching device is not deployed in the robot system, the robot system may include multiple robots. In this case, the device that executes the path planning method provided in the embodiment of the present application may be any one of the multiple robots. A connection can be established directly between different robots in the robot system. For example, connections can be established between different robots through communication protocols such as ZigBee or Bluetooth. In this case, robots can interact with each other through broadcasting and other means to share information such as position, size, and driving path, as well as negotiate the use of resources such as roads and charging piles.

[0046] For ease of understanding, the present application embodiment takes the server executing the path planning method as an example for explanation. It should be understood that when the robot executes the path planning method, except for the different information interaction process, its specific implementation logic can be understood by referring to the process of the server executing the path planning method.

[0047] Optionally, the server may be a single physical or logical server, or may be a server cluster. A server cluster may realize various functions of the server by two or more physical or logical servers sharing different responsibilities and cooperating with each other. Optionally, a server cluster may also be referred to as a computing device cluster. In some implementations, a server cluster may also be a distributed cluster. This application does not limit the form of the server.

[0048] The robot may be a device that has functions such as environmental perception, obstacle avoidance, and path planning, and can achieve autonomous movement. The embodiments of the present application do not impose any restrictions on the specific form of the robot. For example, the robot may be an intelligent sweeping robot, an intelligent car, a material handling robot, etc.

[0049] Optionally, the robot may be equipped with a sensor. The sensor may obtain information such as the robot's travel speed, travel direction, and distance to surrounding objects. Exemplarily, the sensor may include a visual sensor, a gyroscope sensor, a speed sensor, an acceleration sensor, and a distance sensor.

[0050] Among them, the visual sensor can be a monocular camera or a binocular camera, which is used to collect images of the robot's surrounding environment, etc.

[0051] The gyroscope sensor can be used to determine the motion posture of the robot. In some embodiments, the angular velocity of the robot around three axes (i.e., x, y, and z axes) can be determined by the gyroscope sensor. The gyroscope sensor can also be used for navigation, determining whether the robot is blocked, etc.

[0052] The speed sensor is used to measure the driving speed of the robot. In some embodiments, the robot measures the current driving speed through the speed sensor, and can be combined with the distance sensor to predict the environment of the robot at the next moment based on the environment of the robot at the current moment.

[0053] The acceleration sensor can detect the magnitude of the robot's acceleration in all directions (usually three axes). When the robot is stationary, it can detect the magnitude and direction of gravity.

[0054] The distance sensor is used to measure the distance between the robot and surrounding objects, etc. For example, the distance sensor can be an infrared distance sensor, a laser distance sensor, an ultrasonic distance sensor, etc.

[0055] In terms of hardware implementation, the above-mentioned server or robot can be implemented as follows: Figure 1 The electronic device shown is implemented. Figure 1 FIG. 1 is a schematic diagram of the structure of an electronic device 10 provided in an embodiment of the present application. The electronic device 10 can be used to implement the functions of the above-mentioned server or robot.

[0056] Figure 1 The electronic device 10 shown may include: a processor 101 , a memory 102 , a communication interface 103 and a bus 104 . The processor 101 , the memory 102 and the communication interface 103 may be connected via the bus 104 .

[0057] The processor 101 is the control center of the electronic device 10, and may be a general-purpose central processing unit (CPU) or other general-purpose processors, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0058] As an example, the processor 101 may include one or more CPUs, such as Figure 1 CPU 0 and CPU 1 are shown in .

[0059] The memory 102 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0060] In one possible implementation, the memory 102 may exist independently of the processor 101. The memory 102 may be connected to the processor 101 via a bus 104 and used to store data, instructions, or program codes. When the processor 101 calls and executes the instructions or program codes stored in the memory 102, the state detection method provided in the embodiment of the present application can be implemented.

[0061] In another possible implementation, the memory 102 may also be integrated with the processor 101 .

[0062] The communication interface 103 is used for connecting the electronic device 10 with other robots or central dispatching equipment through a communication network, which may be Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc. The communication interface 103 may include a receiving unit for receiving data and a sending unit for sending data.

[0063] The bus 104 may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 1 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0064] It should be pointed out that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device 10. Figure 1 In addition to the components shown, electronic device 10 may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0065] For ease of understanding, the path planning method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0066] like Figure 2 FIG. 2 is a flow chart of a path planning method provided by the present application. The method includes: S201-S203.

[0067] S201: When the current path of the robot is blocked by an obstacle ahead, obtain multiple detour paths that detour around the obstacle ahead.

[0068] The starting position and the ending position of each of the multiple detour paths are on the current path. In other words, the detour path can travel from the starting position on the current path, passing the side of the obstacle in front, to the ending position on the current path. Moreover, the starting positions of different detour paths in the multiple detour paths can be the same or different, and the ending positions can also be the same or different.

[0069] For example, Figure 3 , which is a schematic diagram of a path scenario provided by an embodiment of the present application. The detour path can start from the starting position on the current path of the robot, travel to the left side of the obstacle in front, and end at the end position on the current path of the robot.

[0070] The current path is the currently planned path for the robot to travel from the starting point to the end point via one or more roads. For example, when the robot is required to move materials from a storage location (i.e., the starting point) to a material processing location (i.e., the end point), the server can plan a path for the robot to travel from the material storage location to the material processing location via one or more roads. For another example, when the robot is required to travel from the current location (i.e., the starting point) to the location of the charging pile (i.e., the end point) for charging, the server can plan a path for the robot to travel from the current location to the location of the charging pile via one or more roads. It should be understood that the roads described in this application can be replaced by descriptions of channels, lanes, or other names without limitation.

[0071] Optionally, the obstacle ahead may be a robot that is not in operation and is parked on the road ahead, a robot that is temporarily stopped in operation, a material box, or a cone-shaped roadblock, etc.

[0072] In one possible implementation, while the robot is traveling along the current path, it can detect whether there is an obstacle within a specific distance ahead of the current path through a configured sensor. When an obstacle is detected within a specific distance ahead of the current path, the robot can determine that the current path is blocked by the obstacle ahead. For example, when the robot detects that there is an obstacle within a specific distance ahead of the current path, it can determine the duration of the obstacle ahead by setting a timer or the like. If it is determined that the duration of the obstacle ahead is greater than or equal to a preset duration threshold, the robot can determine that the current path is blocked by the obstacle ahead.

[0073] In this case, the robot can send the current position and the position of the obstacle ahead to the server. In this way, the server can determine the starting position and the ending position of the current path to bypass the obstacle ahead. Furthermore, the server can sample from the starting position to the ending position, with the current path as the center, along the driving direction of the current path and the directions on both sides of the current path, so as to plan multiple bypass paths for the robot to bypass the obstacle ahead. The specific implementation of this process can be understood by referring to the following S2011-S2012, which will not be described in detail here.

[0074] Alternatively, the robot can determine the starting position and ending position of the current path to bypass the obstacle in front based on the position of the obstacle in front. Then, the robot can sample from the starting position to the ending position, with the current path as the center, along the driving direction of the current path and the directions on both sides of the current path, to plan multiple bypass paths to bypass the obstacle in front.

[0075] S202: Determine a detour path planning result based on the driving space information corresponding to each of the plurality of detour paths.

[0076] The driving space information corresponding to the detour path is used to indicate the positional relationship of the robot relative to the surrounding objects when the robot is driving along the detour path. The distance between the robot and the surrounding objects when the robot is driving along the detour path can be understood as the distance between the edge of the sweeping area when the robot is driving along the detour path and the surrounding objects. The sweeping area when the robot is driving along the detour path is also the space occupied by the robot when it is driving along the detour path.

[0077] In one possible manner, the detour path planning result is used to indicate a target detour path that allows the robot to detour the obstacle ahead, or is used to indicate that there is no target detour path that allows the robot to detour the obstacle ahead.

[0078] In one possible implementation, after the server plans multiple detour paths for the robot to detour the obstacle ahead, the server can determine the sweeping area of ​​the robot when it travels along each detour path based on the device size of the robot. In addition, the server can determine the distance between the sweeping area of ​​the robot when it travels along each detour path and the surrounding objects, and obtain the driving space information corresponding to each of the multiple detour paths. Furthermore, based on the driving space information corresponding to each of the multiple detour paths, the server can determine whether the robot will collide with the surrounding objects when traveling along each detour path.

[0079] If the robot collides with surrounding objects when traveling along each of the multiple detour paths, the server can determine that there is no target detour path that allows the robot to bypass the obstacle ahead.

[0080] If the robot does not collide with surrounding objects when traveling along one or two or more detour paths, the server can determine that there is a target detour path that allows the robot to bypass the obstacle ahead. In addition, when there are two or more detour paths that do not collide with surrounding objects, the server can filter out the target detour path from the two or more detour paths. The specific implementation of this process can be understood with reference to the following S2021-S2022, or further understood in combination with S2023-S2024, which will not be elaborated here.

[0081] Alternatively, after the robot plans multiple bypass paths to bypass the obstacle ahead, it can determine the sweeping area of ​​the robot when traveling along each bypass path based on the device size of the robot. In addition, the robot can determine the distance between the sweeping area of ​​the robot when traveling along each bypass path and the surrounding objects, and obtain the driving space information corresponding to each of the multiple bypass paths. Furthermore, based on the driving space information corresponding to each of the multiple bypass paths, the robot can determine whether the robot will collide with the surrounding objects when traveling along each bypass path.

[0082] Optionally, the surrounding objects may be obstacles ahead, other obstacles around the detour path, other robots whose travel paths conflict with the detour path, etc. The robot may identify relevant information about the surrounding objects through configured sensors, or through interaction with a central dispatching device, or through interaction with other robots in the robot system.

[0083] For example, when the obstacle ahead and / or other obstacles around the detour path is a non-working robot, a material box, or a cone-shaped roadblock, etc., the server can identify the position, size, and other related information of the obstacle ahead and / or other obstacles around the detour path by obtaining the measurement results of the robot.

[0084] For another example, when the obstacle ahead and / or other obstacles around the detour path are robots in a working state, the server can obtain relevant information such as the device size, driving path, and position of each robot in the robot system by interacting with the robot. Alternatively, the robot can obtain relevant information such as the device size, driving path, and position of each robot in the robot system by interacting with each robot in the robot system. Then, the robot identifies the robot that is parked on the current path, and / or the robot that is parked on the detour path, and / or other robots whose driving paths conflict with the detour path.

[0085] S203: Control the robot to execute a driving strategy corresponding to the detour path planning result.

[0086] Among them, the driving strategy includes driving along the target detour path to bypass the obstacles ahead, or waiting on the current path.

[0087] If the detour path planning result indicates that there is a target detour path that allows the robot to bypass the obstacle ahead, it can be shown that the robot can bypass the obstacle ahead and improve driving efficiency. The server can then instruct the robot to drive along the target detour path and adjust the target detour path to a prohibited entry state to prohibit other robots from entering the target detour path and avoid conflicts between robots. In this way, the robot can drive along the target detour path to continue driving along the current path after bypassing the obstacle ahead.

[0088] Alternatively, the robot may send a message to the server requesting to use the target bypass path, or may broadcast a message requesting to use the target bypass path to other robots in the robot system, so as to prohibit other robots from entering the target bypass path, and avoid conflicts with other robots during driving along the target bypass path. Furthermore, the robot may drive along the target bypass path, so as to continue driving along the current path after bypassing the obstacle ahead.

[0089] If the detour path planning result indicates that there is no target detour path that allows the robot to detour the obstacle ahead, it can be indicated that the robot cannot detour the obstacle ahead. Then the server can instruct the robot to wait on the current path to avoid collisions and other problems when the robot detours the obstacle ahead.

[0090] In a possible embodiment, the driving space information of the aforementioned detour path may include at least one of the following: a first distance between the space occupied by the robot and the edge of the road involved in the detour path, and a second distance between the space occupied by the robot when it is parallel to the obstacle ahead and the space occupied by the obstacle ahead.

[0091] Among them, the first distance can be used to determine whether the space occupied by the robot when traveling along the detour path is completely within the road width range, so as to determine whether the current passable road width of the road ahead can support the robot to pass.

[0092] In one possible manner, the server may determine the first spacing based on the size of the robot and the size of the obstacle in front, as well as the road width of the road in front. The first spacing may be the smallest spacing among the dynamic spacings of the robot relative to the edge of the road during the robot's driving along the detour path. Among them, the size of the robot may include the length and width of the robot. The length of the robot may be the length of the side parallel to the advancing direction in the minimum circumscribed rectangle of the robot. The width of the robot may be the length of the side perpendicular to the advancing direction in the minimum circumscribed rectangle of the robot. The size of the obstacle in front may include the length and width of the obstacle in front. The length of the obstacle in front may be the length of the side parallel to the advancing direction of the robot in the minimum circumscribed rectangle of the obstacle in front. The width of the obstacle in front may be the length of the side perpendicular to the advancing direction of the robot in the minimum circumscribed rectangle of the obstacle in front.

[0093] For example, the robot can measure the road width of the road ahead through a configured sensor and send the measurement result to the server. In this way, the server can determine the first spacing based on the measurement result of the robot.

[0094] For another example, the server can determine the road width of the road in front of the robot based on the road width marked in the pre-configured topological map, and then determine the first spacing. Specifically, the robot in the robot system can travel based on the road in the topological map. The roads in the topological map generally do not have width. For example, the robot can travel in a manner such that the central axis of the device coincides with the road in the topological map. In order to facilitate the server to perform path planning, the width between each road and the edge of the road can be marked in the topological map. In this case, the server can determine the road width of the road in front of the robot based on the road width marked in the topological map.

[0095] For example, Figure 4 As shown, it is a scene diagram of another path provided by an embodiment of the present application. When the robot travels along the current path, the server can determine the left road width between the road corresponding to the current path of the robot and the left edge of the road, and the right road width between the road corresponding to the current path and the right edge of the road based on the annotations in the topological map, and then determine the first spacing. Figure 4 It shows that when the robot passes from the left side of the front obstacle, the first spacing is the lateral distance between the space occupied by the robot and the left edge of the road.

[0096] The second distance is the distance between the space occupied by the robot when it passes the obstacle in front and the space occupied by the obstacle in front. It can be used to determine whether there is a sufficient safety distance between the robot and the obstacle in front when they are parallel, so as to determine whether the robot will collide with the obstacle in front. Figure 4 When the robot passes through the left side of the front obstacle, the second spacing is the lateral distance between the space occupied by the robot and the space occupied by the front obstacle.

[0097] Based on this, in the above S202, that is, when determining the detour path planning result based on the driving space information corresponding to each of the multiple detour paths, the present application provides an optional implementation method, including: S2021-S2022.

[0098] S2021: When the first spacings corresponding to the plurality of detour paths are all less than or equal to the first distance, determine that there is no target detour path.

[0099] If the first spacings corresponding to the multiple detour paths are all less than or equal to the first distance, it can be indicated that the space occupied by the robot when driving along each detour path exceeds the road width range of the road ahead, and the current passable road width of the road ahead is difficult for the robot to pass through. Then the server can determine that there is no target detour path.

[0100] Optionally, the first distance can be flexibly set based on the needs of the actual deployment scenario of the robot. For example, the first distance can be 0 meters or 0.1 meters.

[0101] S2022: When there is at least one candidate detour path among the multiple detour paths whose first spacing is greater than the first distance, determine a target detour path based on a second spacing corresponding to each candidate detour path.

[0102] If there is at least one candidate detour path among the multiple detour paths whose first spacing is greater than the first distance, it can be indicated that the space occupied by the robot when driving along the at least one candidate detour path does not exceed the road width range of the road ahead. Furthermore, the server can determine the target detour path based on the second spacing corresponding to each candidate detour path.

[0103] When the second spacing corresponding to the candidate detour path is less than or equal to the second distance, the probability that the candidate detour path is determined as the target detour path is positively correlated with the second spacing corresponding to the candidate detour path. When the second spacing corresponding to the candidate detour path is greater than the second distance, the probability that the candidate detour path is determined as the target detour path is negatively correlated with the second spacing corresponding to the candidate detour path. The second distance may be a safety distance for avoiding a collision between the robot and a front obstacle when the robot is parallel. For example, the second distance may be 0.2 meters or 0.4 meters.

[0104] In other words, when the second spacing corresponding to a candidate detour path is less than or equal to the second distance, the focus can be on the impact of the size of the second spacing on the risk of the robot colliding with the obstacle ahead, without considering the impact of the actual path length of the candidate detour path on the robot's driving efficiency. Specifically, if the second spacing when the robot is parallel to the obstacle ahead along the candidate detour path is larger, the risk of the robot colliding with the obstacle ahead is smaller, and the probability of the candidate detour path being determined as the target detour path is greater. If the second spacing when the robot is parallel to the obstacle ahead along the candidate detour path is smaller, the risk of the robot colliding with the obstacle ahead is greater, and the probability of the candidate detour path being determined as the target detour path is smaller.

[0105] In the case where the second spacing corresponding to a candidate detour path is greater than the second distance, the impact of the size of the second spacing on the risk of the robot colliding with the obstacle ahead may no longer be considered, and the focus may be placed on the impact of the actual path length of the candidate detour path on the robot's driving efficiency. Specifically, if the second spacing when the robot follows the candidate detour path and is parallel to the obstacle ahead is larger, the path length actually traveled by the robot along the candidate detour path is larger, the driving efficiency is lower, and the probability that the candidate detour path is determined as the target detour path is smaller. If the second spacing when the robot follows the candidate detour path and is parallel to the obstacle ahead is smaller, the path length actually traveled by the robot along the candidate detour path is smaller, the driving efficiency is higher, and the probability that the candidate detour path is determined as the target detour path is larger.

[0106] In one possible manner, the server can flexibly determine the target detour path from at least one candidate detour path based on the second interval corresponding to each of the at least one candidate detour paths, according to the correlation between the probability of the aforementioned candidate detour path being determined as the target detour path and the second interval corresponding to the candidate detour path.

[0107] For example, the server may configure the corresponding path cost for at least one candidate detour path according to the first expression, and then select the candidate detour path with the smallest path cost from the at least one candidate detour path as the target detour path. The first expression is as follows:

[0108]

[0109] Wherein, C is the path cost corresponding to the candidate detour path. d is the second distance corresponding to the candidate detour path. ds is the second distance. a, r1, and r2 are coefficients greater than 0.

[0110] Further, the server may determine the second distance corresponding to the candidate detour path according to the second expression. The second expression is as follows:

[0111] d=D-(rbt__wid+obs_wid) / 2.

[0112] Where D is the distance between the center axis of the robot's minimum bounding rectangle along the forward direction and the center axis of the minimum bounding rectangle of the obstacle in front of it. rbt__wid is the width of the robot's minimum bounding rectangle, that is, the length of the side of the robot's minimum bounding rectangle perpendicular to the forward direction. obs_wid is the width of the minimum bounding rectangle of the obstacle in front of it, that is, the length of the side of the minimum bounding rectangle of the obstacle in front of it perpendicular to the forward direction.

[0113] For another example, the server may first determine the difference between the second spacing and the second distance corresponding to each candidate detour path, and then determine the candidate detour path with the smallest difference between the second spacing and the second distance as the target detour path.

[0114] In a possible embodiment, the driving space information of the aforementioned detour path may also include at least one of the following: a third distance between the space occupied by the robot and the space occupied by other obstacles around the detour path, and a fourth distance between the space occupied by the robot and the space occupied by other robots passing around the detour path.

[0115] The third spacing may be the smallest spacing among the dynamic spacings of the robot relative to the space occupied by other obstacles when the robot is traveling along the detour path. The third spacing may be used to determine whether the robot will collide with other obstacles around the detour path when traveling along the detour path.

[0116] Other robots passing by the detour path can be understood as other robots whose paths are in the vicinity of the detour path or have overlapping sections with the detour path. The fourth distance can be the distance between the space occupied by the robot and other robots in the forward direction of the current path. In order to avoid conflicts with other robots passing by the detour path, the robot needs to wait for other robots to leave the overlapping sections with the detour path before entering the detour path. In this case, the larger the fourth distance of the robot relative to other robots, the longer the waiting time and the lower the driving efficiency. The smaller the fourth distance of the robot relative to other robots, the shorter the waiting time and the higher the driving efficiency.

[0117] It should be understood that when a robot executes the above method, it can obtain the driving paths of other robots through interaction with a server that performs central scheduling, or it can also obtain the driving paths of other robots through interaction with other robots, which will not be elaborated herein.

[0118] Based on this, in the above S202, that is, when determining the detour path planning result based on the driving space information corresponding to each of the multiple detour paths, the present application provides another optional implementation method, including: S2023-S2024.

[0119] S2023: When the third distances corresponding to at least one candidate detour path are both less than or equal to the first distance, determine that there is no target detour path.

[0120] If the third distances corresponding to at least one of the candidate detour paths in S2022 are all less than or equal to the first distance, it can be indicated that the space occupied by the robot when traveling along each of the candidate detour paths will collide with other obstacles. Then the server can determine that there is no target detour path.

[0121] It should be understood that the execution order of S2023 can also be before S2021 without limitation.

[0122] S2024: When there is at least one candidate detour path among multiple detour paths whose first spacing is greater than the first distance and whose third spacing is greater than the first distance, determine the target detour path based on the second spacing and the fourth spacing corresponding to each candidate detour path.

[0123] If there is at least one candidate detour path among the multiple detour paths whose first spacing is greater than the first distance and whose third spacing is greater than the first distance, it can be indicated that the space occupied by the robot when driving along each candidate detour path does not exceed the road width range of the road ahead and will not collide with other obstacles. The server can determine the target detour path based on the second spacing and the fourth spacing corresponding to each candidate detour path.

[0124] In one possible manner, the server can flexibly determine the target detour path from at least one candidate detour path based on the second interval corresponding to each of the at least one candidate detour paths, according to the correlation between the probability of the aforementioned candidate detour path being determined as the target detour path and the second interval corresponding to the candidate detour path.

[0125] For example, the server may configure the corresponding path cost for at least one candidate detour path according to the third expression, and then select the candidate detour path with the smallest path cost from the at least one candidate detour path as the target detour path. The third expression is as follows:

[0126]

[0127] Wherein, C is the path cost corresponding to the candidate detour path. d is the second distance corresponding to the candidate detour path. L is the fourth distance corresponding to the candidate detour path. ds is the second distance. a, b, r1, and r2 are coefficients greater than 0.

[0128] For another example, the server may first determine the weighted sum between the second distance and the fourth distance of the candidate detour path, then determine the difference between the weighted sum and the second distance, and then determine the candidate detour path with the smallest difference between the weighted sum and the second distance as the target detour path.

[0129] Based on this, the present application can accurately determine whether the detour path is passable by determining whether the space occupied by the robot exceeds the road width limit, whether there is a collision between the space occupied by the robot and other obstacles or other robots, and whether the space occupied by the robot maintains a safe distance from obstacles ahead.

[0130] In one embodiment, when the current path of the robot is blocked by an obstacle ahead, before obtaining multiple detour paths around the obstacle ahead, the path planning method provided by the present application further includes: S301-S302.

[0131] S301: Obtain identification information of the road ahead on the current path.

[0132] It should be noted that, considering that detour path planning may take a long time and may occupy more computing resources of the robot, when the current path of the robot is blocked by an obstacle ahead, the server may first determine whether the detour condition is met.

[0133] For example, if the position of the obstacle ahead is near the end of the robot's current path, the robot does not need to go around the obstacle ahead. For another example, if there are a large number of obstacles whose spacing relative to the obstacle ahead is less than or equal to the third distance, the robot may be blocked by a new obstacle in a short time after going around the obstacle ahead, and may not be able to go around the new obstacle, so there is no need to go around the obstacle ahead. For another example, if the path behind the obstacle ahead on the current path is congested, the robot still cannot pass after going around the obstacle ahead, so there is no need to go around the obstacle ahead.

[0134] Based on this, when the current path of the robot is blocked by an obstacle ahead, the server can obtain the identification information of the road ahead on the current path of the robot to determine whether the detour condition is met. It should be understood that the way in which the server obtains the identification information of the road ahead on the current path of the robot can refer to the specific description of the server identifying the relevant information of the robot's surrounding objects in the aforementioned S202, which will not be repeated here.

[0135] The identification information includes at least one of the following: the position of the obstacle ahead, the number of obstacles whose spacing relative to the obstacle ahead is less than or equal to the third distance, and the status of the path behind the obstacle ahead on the current path. The status of the path includes a pass status or a congestion status.

[0136] The obstacle whose distance relative to the obstacle in front is less than or equal to the third distance, that is, the obstacle within the third distance behind the obstacle in front on the current path. The third distance can be flexibly set based on the needs of the actual deployment scenario of the robot. For example, the third distance can be 10 meters or 20 meters.

[0137] S302: Determine whether detour conditions are met based on the identification information of the road ahead.

[0138] Among them, the detour conditions include at least one of the following: the distance between the position of the obstacle in front and the end point of the current path is greater than a fourth distance, the number of obstacles is less than or equal to a preset number, and the state of the path is a passable state.

[0139] If the distance between the position of the obstacle ahead and the end point of the current path is greater than the fourth distance, and the number of obstacles is less than or equal to the preset number, and the path is in a passable state, the server can determine that the detour conditions are met and perform detour path planning.

[0140] If the distance between the position of the obstacle ahead and the end point of the current path is less than or equal to the fourth distance, and the number of obstacles is greater than the preset number, and the path is congested, the server can determine that the detour condition is not met and wait on the current path. Based on this, the application can judge the path conditions before and after the robot detours the obstacle, determine the feasibility of detouring the obstacle ahead, and improve the stability of the detour process.

[0141] In one embodiment, in the above S201, that is, when obtaining multiple detour paths around the obstacle ahead, the present application provides an optional implementation method, including: S2011-S2012.

[0142] S2011: Based on the length of the robot, and the length and position of the obstacle in front, determine the starting position and the ending position of bypassing the obstacle in front.

[0143] The starting position of the bypassing obstacle may be the current position of the robot. Alternatively, the distance between the starting position of the bypassing obstacle and the position of the obstacle is equal to the weighted sum of the length of the robot and the length of the obstacle. The distance between the ending position of the bypassing obstacle and the position of the obstacle is equal to the weighted sum of the length of the robot and the length of the obstacle.

[0144] The length of the robot may be the length of the side of the minimum circumscribed rectangle of the robot parallel to the driving direction of the robot. The length of the front obstacle may be the length of the side of the minimum circumscribed rectangle of the front obstacle parallel to the driving direction of the robot.

[0145] In one possible way, when the robot detects that it is blocked by an obstacle in front, the distance relative to the obstacle in front may be small. For example, the obstacle in front may be an obstacle such as a material box that suddenly falls in front of the robot. For another example, the obstacle in front may be another robot that suddenly drives into the road in front of the robot from another road. In this case, the robot can brake to avoid collision with the obstacle in front. In this way, the server can determine that the starting position of the robot to bypass the obstacle in front is the current position of the robot.

[0146] Alternatively, when the robot detects that it is blocked by an obstacle in front, the distance relative to the obstacle in front may be large. In this case, the server may determine the position before the obstacle in front and whose distance relative to the obstacle in front is equal to the weighted sum of the length of the robot and the length of the obstacle in front as the starting position for bypassing the obstacle in front, so as to make the path of the robot bypassing the obstacle in front smoother and avoid rollover, etc.

[0147] In addition, the server can determine the position behind the front obstacle and whose distance relative to the front obstacle is equal to the weighted sum of the length of the robot and the length of the front obstacle as the end position of circumventing the front obstacle, so as to make the path of the robot circumventing the front obstacle smoother and avoid rollover, etc.

[0148] For example, the server may determine the weighted sum between the length of the robot and the length of the obstacle ahead according to the fourth expression. The fourth expression is as follows:

[0149] dis=k*rbt_len+c*obs_len.

[0150] Where dis is the weighted sum of the length of the robot and the length of the obstacle in front. rbt_len is the length of the robot. obs_len is the length of the obstacle in front. k and c are weights greater than 0. For example, k and c can be 0.5.

[0151] Optionally, when the server determines the starting position and the ending position of bypassing the obstacle ahead based on the fourth expression, the value of k may be the same or different without limitation.

[0152] S2012: Determine multiple detour paths from the starting position through the side of the front obstacle to the end position.

[0153] The detour path includes a sub-path from the starting position to the first intermediate position, a sub-path from the first intermediate position to the second intermediate position, and a sub-path from the second intermediate position to the end position. The first intermediate position is between the starting position and the position of the obstacle ahead, and the second intermediate position is between the position of the obstacle ahead and the end position. Different detour paths include sub-paths with different first intermediate positions and / or different second intermediate positions.

[0154] In one possible implementation, the server can divide the road ahead of the robot into four layers in the driving direction, and divide the layers into four layers at a fixed distance in the width direction perpendicular to the driving direction to obtain multiple intermediate position points. Furthermore, the server can sample from the starting position of the bypassing obstacle to the ending position of the bypassing obstacle with the current path as the center, so as to plan multiple bypassing paths for bypassing the obstacle ahead.

[0155] For example, Figure 5 As shown, it is a scene schematic diagram of another path provided by an embodiment of the present application. The L1 section is a sub-path that travels from the starting position on the current path to the first intermediate position. The L2 section is a sub-path that travels from the first intermediate position to the second intermediate position. The L3 section is a sub-path that travels from the second intermediate position to the end position on the current path. The first intermediate position can be any intermediate position point among multiple intermediate position points in the width direction between the L1 section and the L2 section. The second intermediate position can be any intermediate position point among multiple intermediate position points in the width direction between the L2 section and the L3 section.

[0156] In one possible manner, when the distance between the starting position and the position of the obstacle ahead is greater than the length of the robot, the sub-path from the starting position to the first intermediate position is a curved path, so that the robot can smoothly bypass the obstacle. When the distance between the starting position and the position of the obstacle ahead is less than or equal to the length of the robot, in order to avoid problems such as rollover caused by taking a curved path with a large slope, the sub-path from the starting position to the first intermediate position can be a straight path.

[0157] For example, in combination Figure 5 ,like Figure 6 FIG. 1 is a schematic diagram of another path scenario provided by an embodiment of the present application. When the distance between the starting position and the position of the obstacle in front is less than or equal to the length of the robot, the robot can turn left from the starting position and drive straight to the first middle position, then turn right from the first middle position and drive straight to the second middle position, then turn right from the second middle position and drive along the curved path to the end position.

[0158] In one embodiment, in the above S203, when the driving strategy is to drive according to the target detour path to bypass the obstacle ahead, when controlling the robot to execute the driving strategy corresponding to the detour path planning result, the present application provides an optional implementation method, including: S2031-S2032.

[0159] S2031: When there is a conflict between the target detour path and the driving paths of other robots, the control robot waits for the other robots to leave the target detour path and then drives along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle in front, and adjusts the target detour path to a prohibited entry state during the robot's waiting period to prohibit other robots whose driving paths do not conflict with the target detour path from entering the target detour path.

[0160] Optionally, the target detour path conflicts with the driving paths of other robots, which may be that the driving paths of other robots are around the target detour path, or there is an overlapping section between the driving paths of other robots and the target detour path. Other robots may be passing around the target detour path, or passing through the overlapping section between their driving paths and the target detour path.

[0161] When the server determines that the robot drives along the target detour path to bypass the obstacle ahead, it can first determine whether the target detour path conflicts with the driving paths of other robots. If the target detour path conflicts with the driving paths of other robots, the server can instruct the robot to wait for other robots to leave the target detour path, and instruct the robot to drive along the target detour path after other robots leave the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle ahead, and avoids problems such as collisions between the robot and other robots. In addition, the server can adjust the use status of the target detour path to a prohibited entry status during the robot waiting period to prohibit other robots whose driving paths do not conflict with the target detour path from entering the target detour path. The robot waiting period is the period when the robot waits for other robots whose driving paths conflict with the target detour path to leave.

[0162] In one possible approach, when the target detour path conflicts with the driving paths of other robots, the server can also detect whether the other robots can normally leave the target detour path. For example, the server interacts with other robots to determine whether the power system and other components of the other robots can work normally. For another example, the server can determine whether the other robots are blocked by obstacles and cannot move.

[0163] If other robots can leave the target detour path normally, the server can instruct the robot to wait for other robots to leave the target detour path. If other robots cannot leave the target detour path normally, it can be indicated that the robot cannot drive along the target detour path even if it waits. The server can then replan the robot's detour path to avoid collisions between the robot and other robots.

[0164] S2032: When there is no conflict between the target detour path and the driving paths of other robots, control the robot to drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle in front.

[0165] If the target detour path does not conflict with the driving paths of other robots, the server can instruct the robot to drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle ahead, thereby improving the driving efficiency of the robot.

[0166] In one embodiment, Figure 7 FIG. 4 is a flow chart of another path planning method provided by the present application. The method includes: S401-S409.

[0167] S401: Determine that the robot is blocked by an obstacle in front.

[0168] S402: Determine whether detour conditions are met.

[0169] S403: Determine the starting position and the ending position of bypassing the obstacle ahead.

[0170] S404: Plan multiple detour paths.

[0171] S405: Determine whether there is a target detour path.

[0172] S406: Determine whether the target detour path conflicts with the driving paths of other robots.

[0173] S407: Determine whether other robots can normally drive away from the target detour path.

[0174] S408: Control the robot to wait for other robots to leave the target detour path and then drive along the target detour path, and adjust the target detour path to a prohibited entry state during the robot's waiting period.

[0175] S409: Control the robot to travel along the target detour path.

[0176] It should be understood that the implementation of S401-S409 may refer to the specific description of S201-S203 and S301-S302 mentioned above, which will not be repeated here.

[0177] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the method. It is understandable that in order to realize the above functions, the robot includes at least one of the hardware structure and software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0178] The embodiment of the present application can divide the robot into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0179] For example, Figure 8 A schematic diagram of the structure of a path planning device is shown. The path planning device 20 can be used to execute the method involved in the above embodiment. The path planning device 20 includes: an acquisition unit 501, a processing unit 502 and a control unit 503;

[0180] The acquisition unit 501 is used to acquire multiple detour paths around the obstacles ahead when the current path of the robot is blocked by the obstacles ahead; the starting position and the ending position of the detour paths are on the current path;

[0181] The processing unit 502 is used to determine a detour path planning result based on the driving space information corresponding to each of the plurality of detour paths; the driving space information is used to indicate the position relationship of the robot relative to the surrounding objects when the robot travels along the detour path; the detour path planning result is used to indicate a target detour path that allows the robot to bypass the obstacle ahead, or to indicate that there is no target detour path;

[0182] The control unit 503 is used to control the robot to execute a driving strategy corresponding to the detour path planning result; the driving strategy includes driving along the target detour path to bypass the obstacle ahead, or waiting on the current path.

[0183] In a possible embodiment, the driving space information includes at least one of the following: a first distance between the space occupied by the robot and the edge of the road involved in the detour path, and a second distance between the space occupied by the robot when it is parallel to the obstacle in front and the space occupied by the obstacle in front; the processing unit 502 is specifically used to: determine that there is no target detour path when the first distances corresponding to each of the multiple detour paths are less than or equal to the first distance; determine the target detour path based on the second distances corresponding to each of the candidate detour paths when there is at least one candidate detour path with a first distance greater than the first distance among the multiple detour paths; when the second distance corresponding to the candidate detour path is less than or equal to the second distance, the probability that the candidate detour path is determined to be the target detour path is positively correlated with the second distance corresponding to the candidate detour path; when the second distance corresponding to the candidate detour path is greater than the second distance, the probability that the candidate detour path is determined to be the target detour path is negatively correlated with the second distance corresponding to the candidate detour path.

[0184] In a possible embodiment, the driving space information also includes at least one of the following: a third distance of the space occupied by the robot relative to the space occupied by other obstacles around the detour path, and a fourth distance of the space occupied by the robot relative to the space occupied by other robots passing by the detour path; the processing unit 502 is specifically used to: determine that there is no target detour path when the third distances corresponding to at least one candidate detour path are both less than or equal to the first distance; determine the target detour path based on the second distance and the fourth distance corresponding to each candidate detour path when there is at least one candidate detour path among multiple detour paths whose first distance is greater than the first distance and whose third distance is greater than the first distance; the probability of a candidate detour path being determined as the target detour path is negatively correlated with the fourth distance corresponding to the candidate detour path.

[0185] In a possible embodiment, the acquisition unit 501 is also used to obtain identification information of the road ahead on the current path; the identification information includes at least one of the following: the position of the obstacle ahead, the number of obstacles whose distance relative to the obstacle ahead is less than or equal to a third distance, and the state of the path behind the obstacle ahead on the current path; the state of the path includes a passable state or a congested state; the processing unit 502 is also used to determine whether a detour condition is met based on the identification information of the road ahead; the detour condition includes at least one of the following: the position of the obstacle ahead is greater than a fourth distance relative to the end point of the current path, the number of obstacles is less than or equal to a preset number, and the state of the path is a passable state.

[0186] In a possible embodiment, the acquisition unit 501 is specifically used to: determine the starting position and the ending position of the detour around the front obstacle based on the length of the robot, and the length and position of the front obstacle; the starting position is the current position of the robot, or the distance between the starting position and the position of the front obstacle is equal to the weighted sum of the length of the robot and the length of the front obstacle; the distance between the ending position and the position of the front obstacle is equal to the weighted sum of the length of the robot and the length of the front obstacle; determine multiple detour paths from the starting position through the side of the front obstacle to the end position; the detour path includes a sub-path from the starting position to a first middle position, a sub-path from the first middle position to a second middle position, and a sub-path from the second middle position to the end position; the first middle position is between the starting position and the position of the front obstacle, and the second middle position is between the position of the front obstacle and the end position; the sub-paths included in different detour paths have different first middle positions and / or different second middle positions.

[0187] In a possible embodiment, when the distance between the starting position and the position of the front obstacle is greater than the length of the robot, the sub-path from the starting position to the first intermediate position is a curved path; when the distance between the starting position and the position of the front obstacle is less than or equal to the length of the robot, the sub-path from the starting position to the first intermediate position is a straight path.

[0188] In a possible embodiment, the control unit 503 is specifically used to: when a target detour path conflicts with the driving paths of other robots, control the robot to wait for the other robots to leave the target detour path and then drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle in front, and adjust the target detour path to a prohibited entry state during the robot waiting period to prohibit other robots whose driving paths do not conflict with the target detour path from entering the target detour path; when the target detour path does not conflict with the driving paths of other robots, control the robot to drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle in front.

[0189] For the detailed description of the above optional methods, please refer to the above method embodiments, which will not be repeated here. In addition, the explanation of any of the above path planning devices 20 and the description of the beneficial effects can refer to the above corresponding method embodiments, which will not be repeated here.

[0190] As an example, combining Figure 1 , the functions partially or completely implemented by the acquisition unit 501, the processing unit 502 and the control unit 503 in the path planning device 20 can be Figure 1 Processor 101 in the Figure 1The program code in the memory 102 is implemented.

[0191] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed on a server, the server executes any of the methods executed by the server provided above.

[0192] For the explanation of the relevant contents and description of the beneficial effects of any of the above-mentioned computer-readable storage media, reference may be made to the above-mentioned corresponding embodiments, which will not be repeated here.

[0193] The embodiment of the present application also provides a computer program product including instructions, which, when executed on a server, causes the server to perform any of the methods in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the server, the process or function according to the embodiment of the present application is generated in whole or in part.

[0194] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided in the embodiments of the present application, such as but not limited to the above-mentioned memories, computer-readable storage media, etc., are all non-transitory.

[0195] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the server, all or part of the processes or functions according to the embodiments of the present application are generated.

[0196] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0197] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A path planning method, characterized in that: include: When the current path of the robot is blocked by a front obstacle, obtaining multiple detour paths that detour the front obstacle; The starting position and the ending position of the detour path are on the current path; Determining a detour path planning result based on the driving space information corresponding to each of the plurality of detour paths; The driving space information is used to indicate the position relationship of the robot relative to surrounding objects when the robot drives along the detour path; The detour path planning result is used to indicate a target detour path that allows the robot to detour the front obstacle, or to indicate that the target detour path does not exist; The robot is controlled to execute a driving strategy corresponding to the detour path planning result; the driving strategy includes driving along the target detour path to bypass the obstacle ahead, or waiting on the current path.

2. The method according to claim 1, characterized in that The driving space information includes at least one of the following: a first distance between the space occupied by the robot and the edge of the road involved in the detour path, and a second distance between the space occupied by the robot when it is parallel to the front obstacle and the space occupied by the front obstacle; The step of determining the detour path planning result based on the driving space information corresponding to each of the plurality of detour paths includes: When the first spacings corresponding to the plurality of detour paths are all less than or equal to the first distance, determining that the target detour path does not exist; In the case that there is at least one candidate detour path among the multiple detour paths whose first spacing is greater than the first distance, the target detour path is determined based on the second spacing corresponding to each candidate detour path; when the second spacing corresponding to the candidate detour path is less than or equal to the second distance, the probability that the candidate detour path is determined as the target detour path is positively correlated with the second spacing corresponding to the candidate detour path; when the second spacing corresponding to the candidate detour path is greater than the second distance, the probability that the candidate detour path is determined as the target detour path is negatively correlated with the second spacing corresponding to the candidate detour path.

3. The method according to claim 2, characterized in that The driving space information further includes at least one of the following: a third distance between the space occupied by the robot and the space occupied by other obstacles around the detour path, and a fourth distance between the space occupied by the robot and the space occupied by other robots driving around the detour path; The step of determining the detour path planning result based on the driving space information corresponding to each of the plurality of detour paths further includes: When the third distances corresponding to the at least one candidate detour path are both less than or equal to the first distance, determining that the target detour path does not exist; When there is at least one candidate detour path among the multiple detour paths whose first spacing is greater than the first distance and whose third spacing is greater than the first distance, the target detour path is determined based on the second spacing and the fourth spacing corresponding to each candidate detour path; the probability of the candidate detour path being determined as the target detour path is negatively correlated with the fourth spacing corresponding to the candidate detour path.

4. The method according to claim 1, characterized in that: Before acquiring a plurality of detour paths for detouring the obstacle ahead, the method further includes: Acquire identification information of a road ahead on the current path; the identification information includes at least one of the following: the position of the obstacle ahead, the number of obstacles whose spacing relative to the obstacle ahead is less than or equal to a third distance, and the state of a path behind the obstacle ahead on the current path; the state of the path includes a traffic state or a congestion state; Based on the identification information of the road ahead, determine whether a detour condition is met; the detour condition includes at least one of the following: the distance between the position of the obstacle ahead and the end point of the current path is greater than a fourth distance, the number of obstacles is less than or equal to a preset number, and the state of the path is a passable state.

5. The method according to claim 1, characterized in that The obtaining of a plurality of detour paths for detour around the front obstacle comprises: Based on the length of the robot, and the length and position of the obstacle in front, determine the starting position and the ending position of bypassing the obstacle in front; the starting position is the current position of the robot, or the distance between the starting position and the position of the obstacle in front is equal to the weighted sum of the length of the robot and the length of the obstacle in front; the distance between the ending position and the position of the obstacle in front is equal to the weighted sum of the length of the robot and the length of the obstacle in front; Determine the multiple detour paths from the starting position through the side of the front obstacle to the end position; the detour paths include a sub-path from the starting position to a first intermediate position, a sub-path from the first intermediate position to a second intermediate position, and a sub-path from the second intermediate position to the end position; the first intermediate position is between the starting position and the position of the front obstacle, and the second intermediate position is between the position of the front obstacle and the end position; different detour paths include sub-paths with different first intermediate positions and / or different second intermediate positions.

6. The method according to claim 5, characterized in that When the distance between the starting position and the position of the front obstacle is greater than the length of the robot, the sub-path from the starting position to the first intermediate position is a curved path; when the distance between the starting position and the position of the front obstacle is less than or equal to the length of the robot, the sub-path from the starting position to the first intermediate position is a straight path.

7. The method according to claim 1, characterized in that In a case where the driving strategy is to drive along the target detour path to bypass the front obstacle, controlling the robot to execute the driving strategy corresponding to the detour path planning result includes: In the case where the target detour path conflicts with the driving paths of other robots, the robot is controlled to wait for the other robots to leave the target detour path and then drive along the target detour path, so that the robot continues to drive along the current path after bypassing the obstacle in front, and the target detour path is adjusted to a prohibited entry state during the waiting period of the robot, so as to prohibit other robots whose driving paths do not conflict with the target detour path from entering the target detour path; In the case where there is no conflict between the target detour path and the driving paths of other robots, the robot is controlled to drive along the target detour path, so that the robot continues to drive along the current path after bypassing the front obstacle.

8. A path planning device, characterized in that: include: an acquisition unit, a processing unit, and a control unit; The acquisition unit is used to acquire a plurality of detour paths that detour the obstacle in front when the current path of the robot is blocked by the obstacle in front; the starting position and the ending position of the detour path are on the current path; The processing unit is used to determine the detour path planning result based on the driving space information corresponding to each of the multiple detour paths; the driving space information is used to indicate the position relationship of the robot relative to the surrounding objects when traveling along the detour path; The detour path planning result is used to indicate a target detour path that allows the robot to detour the front obstacle, or to indicate that the target detour path does not exist; The control unit is used to control the robot to execute a driving strategy corresponding to the detour path planning result; the driving strategy includes driving along the target detour path to bypass the obstacle ahead, or waiting on the current path.

9. A server, characterized in that: include: processor; The processor is connected to a memory, the memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions stored in the memory, so that the server implements the method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: Used to store computer instructions, when the computer instructions are executed on a server, the server executes the method according to any one of claims 1 to 7.