A method and device for global path planning of a robot

Abstract

The purpose of this application is to provide a method and device for global path planning of a robot. This application obtains the full state of the robot, performs polygon modeling based on the full state to obtain a polygon model; performs collision screening on the polygon model to obtain a path map of the robot; determines the shortest path between nodes in the path map by means of graph search, and determines the global path planning of the robot according to the obtained shortest path. Thus, it can achieve the motion planning of a robot with an arbitrary polygon shape and improve the passability of the robot.

Description

Technical Field

[0001] This application relates to the field of computers, and in particular to a method and device for global path planning of a robot. Background Art

[0002] With the development of artificial intelligence technology, robots with functions such as automatic route planning, such as floor sweepers, drones, and driverless cars, have been widely popularized. Before moving, a robot usually first plans a global path and then moves according to the global path. In current mobile robot algorithms, a circular model is usually used for modeling to achieve path planning and motion planning. However, in actual robot design, the robot chassis is not completely designed as a circle, and it can also be rectangular, etc. Therefore, only circular modeling will seriously affect the passability of the robot. Summary of the Invention

[0003] An object of this application is to provide a method and device for global path planning of a robot, which solves the problem that the model modeling in the prior art is single and cannot perform polygon modeling, resulting in serious impacts.

[0004] According to one aspect of this application, a method for global path planning of a robot is provided. The method includes:

[0005] Obtain the full state of the robot, perform polygon modeling according to the full state to obtain a polygon model;

[0006] Perform collision screening on the polygon model to obtain a path map of the robot;

[0007] Determine the shortest path between nodes in the path map by means of graph search, and determine the global path planning of the robot according to the obtained shortest path.

[0008] Optionally, performing polygon modeling according to the full state to obtain a polygon model includes:

[0009] Determine state transitions according to the full state, and discretize the robot angle according to the state transitions to obtain a state transition graph;

[0010] Perform polygon modeling according to the state transition graph to obtain a polygon model.

[0011] Optionally, discretizing the robot angle according to the state transitions to obtain a state transition graph includes:

[0012] Determine the next state that can be moved to according to the current state of the robot, and determine the operable trajectory of the robot according to all movable states;

[0013] Select a target running trajectory from the available running trajectories, and discretize the angles of the robot in the full state of the target running trajectory to obtain a state transition diagram.

[0014] Optionally, perform polygon modeling according to the state transition diagram to obtain a polygon model, including:

[0015] Connect each state transition in series according to the state transition diagram, and obtain a polygon model based on the series connection result.

[0016] Optionally, perform collision screening on the polygon model, including:

[0017] Discretize the robot chassis into an assembly composed of multiple grids, and discretize the polygon model into sampling points;

[0018] Judge whether there is at least one sampling point in each grid. If so, the robot collides, and filter the sampling points that have collided.

[0019] Optionally, judge whether there is at least one sampling point in each grid, including:

[0020] Judge whether there is at least one sampling point in the grid in the advancing direction of each robot according to the full state of the robot.

[0021] Optionally, obtain the full state of the robot, including:

[0022] If the robot chassis is circular, obtain the first coordinate value and the second coordinate value of the robot;

[0023] If the robot chassis is irregular, obtain the first coordinate value, the second coordinate value and the angle value of the robot.

[0024] According to another aspect of the present application, there is also provided a device for global path planning of a robot. The device includes:

[0025] A modeling device, configured to obtain the full state of the robot, and perform polygon modeling according to the full state to obtain a polygon model;

[0026] A screening device, configured to perform collision screening on the polygon model to obtain a path map of the robot;

[0027] A determining device, configured to determine the shortest path between nodes in the path map by means of graph search, and determine the global path planning of the robot according to the obtained shortest path.

[0028] According to yet another aspect of the present application, there is also provided a device for global path planning of a robot. The device includes:

[0029] One or more processors; and

[0030] A memory storing computer-readable instructions, which when executed cause the processor to perform the operations of the method as described above.

[0031] According to another aspect of the present application, there is also provided a computer-readable medium having computer-readable instructions stored thereon, and the computer-readable instructions can be executed by a processor to implement the method as described above.

[0032] Compared with the prior art, the present application obtains the full state of the robot, performs polygon modeling based on the full state to obtain a polygon model, performs collision screening on the polygon model to obtain a path map of the robot, determines the shortest path between nodes in the path map by means of graph search, and determines the global path planning of the robot according to the obtained shortest path. Thus, it can achieve the motion planning of robots with arbitrary polygon shapes and improve the passability of the robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Other features, objects, and advantages of the present application will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings:

[0034] Figure 1 A schematic flowchart showing a method for global path planning of a robot provided according to one aspect of the present application;

[0035] Figure 2 A schematic diagram showing the state transition of the robot in an embodiment of the present application;

[0036] Figure 3 A state transition diagram of the robot in an embodiment of the present application;

[0037] Figure 4 A schematic diagram showing the discretization of the robot chassis in an embodiment of the present application;

[0038] Figure 5 A schematic structural diagram of a device for global path planning of a robot provided according to another aspect of the present application.

[0039] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The present application will be described in further detail below with reference to the drawings.

[0041] In a typical configuration of the present application, the terminal, the device of the service network, and the trusted party each include one or more processors (e.g., a Central Processing Unit (CPU)), an input / output interface, a network interface, and a memory.

[0042] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0043] Computer-readable media includes permanent and non-permanent, removable and non-removable media and can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0044] Figure 1A schematic flowchart of a method for global path planning of a robot provided according to an aspect of the present application is shown. The method includes: steps S11 to S13. Among them, in step S11, the full state of the robot is obtained, and polygon modeling is performed according to the full state to obtain a polygon model; in step S12, collision screening is performed on the polygon model to obtain a path map of the robot; in step S13, the shortest path between nodes in the path map is determined by a graph search method, and the global path planning of the robot is determined according to the obtained shortest path. Thus, motion planning of a robot with an arbitrary polygon shape can be achieved, and the passability of the robot can be improved.

[0045] Specifically, in step S11, the full state of the robot is obtained, and polygon modeling is performed according to the full state to obtain a polygon model. Here, the full state of the robot is used to describe the movement of the robot. According to the full state, information such as the position and angle of the robot can be obtained, and thus polygon modeling can be performed for the situation when the robot moves. This polygon modeling is used to represent the shape of the robot chassis. For example, if it is circular, a circular model is built; if it is rectangular, a rectangular model is built. Furthermore, for any-shaped chassis, a model of any polygon shape can be obtained.

[0046] Specifically, in step S12, collision screening is performed on the polygon model to obtain a path map of the robot. Here, after obtaining the corresponding polygon model according to the specific full state, collision screening is performed on the polygon model to determine whether the robot collides at some sampling points, and a path map including the movement path and collision points when the robot moves is obtained.

[0047] Specifically, in step S13, the shortest path between nodes in the path map is determined by a graph search method, and the global path planning of the robot is determined according to the obtained shortest path. Here, the obtained path map is searched using the graph search method, so as to search for the shortest path between nodes in the path map. Furthermore, the optimal shortest path can be obtained, and the optimal shortest path is used as the global path planning of the robot. According to the shape of the robot's own chassis, the corresponding global path planning is obtained, improving the accuracy and the passability of the robot.

[0048] In some embodiments of the present application, in step S11, state transition is determined according to the full state, the angle of the robot is discretized according to the state transition to obtain a state transition graph; polygon modeling is performed according to the state transition graph to obtain a polygon model. Here, the full state of the robot can be converted into the state transition situation of the robot, and then the angle when the robot moves is discretized using the state transition to obtain the corresponding state transition graph, and the polygon model is obtained based on the state transition graph.

[0049] Specifically, determine the next state that the robot can move to based on the current state of the robot, and determine the operable trajectories of the robot based on all the movable states; select a target operating trajectory from the operable trajectories, and discretize the angles of the robot in all states in the target operating trajectory to obtain a state transition graph. Here, when determining the state transition of the robot, the next state that the robot can move to is determined based on the current state of the robot, and all operable trajectories are determined according to each feasible up and down state, and then a target operating trajectory is selected from these operable trajectories; for example, as Figure 2 shown, the possible situations for the robot to transfer from the current state to the next state may include: moving forward one grid, moving forward eight grids, moving backward one grid, turning left by a certain angle, turning right by a certain angle, moving forward and turning left, moving forward and turning right, etc. Thus, the operable trajectories can be determined, and a trajectory can be selected from these operable trajectories. The selection method can use the heuristic search method (A*) to select from all operable trajectories.

[0050] Next, connect each state transition in series according to the state transition graph, and obtain a polygon model according to the series connection result. Here, after obtaining the discretized state transition graph, connect these state transitions in series. For example, when the robot is at the initial position A, and then the first sampling is performed to obtain the position B, sampling can be performed in the same state as the method for obtaining the state transition graph on the basis of B to obtain the position C of the robot. After connecting the state transitions in series, the state transitions can be represented in the form of a state transition graph (graph), as Figure 3 shown, and then a polygon model can be obtained by using the state transition graph.

[0051] In some embodiments of the present application, in step S12, the robot chassis is discretized into a combination composed of multiple grids, and the polygon model is discretized into sampling points; it is judged whether there is at least one sampling point in each grid. If so, the robot collides, and the sampling points that collide are filtered. Here, as Figure 4 shown, the robot chassis is abstracted, and an inflated grid map is established for collision detection. Specifically, if it is a circular chassis, the chassis can be directly abstracted into a dot, and then the collision detection of the grid map of the collision is performed. If it is other special-shaped chassis, such as a rectangular chassis, based on the above step S11, the special-shaped chassis is re-modeled, the robot is discretized into a combination composed of N grids, sampling points are discretized from the obtained polygon model, so as to judge whether each grid is occupied by sampling points. If so, the robot collides, and the sampling points that collide are filtered to improve the passability of the robot.

[0052] Specifically, based on the full state of the robot, it is determined whether there is at least one sampling point in the grid in the advancing direction of each robot. Here, to improve the sampling efficiency, when performing collision screening, the advancing direction of the robot is obtained according to the full state of the robot, so as to only judge whether the grid in the advancing direction is occupied by sampling points, and then judge whether the robot collides at the sampling point.

[0053] In some embodiments of the present application, in step S11, if the robot chassis is circular, the first coordinate value and the second coordinate value of the robot are obtained; if the robot chassis is irregular, the first coordinate value, the second coordinate value, and the angle value of the robot are obtained. Here, when obtaining the full state of the robot, it can be determined according to the shape of the robot chassis. For example, when the robot chassis is circular, only the first coordinate value and the second coordinate value of the robot need to be obtained, that is, (x, y) is obtained, which are the abscissa and ordinate of the robot when moving; when the robot chassis is an irregular chassis, such as a rectangle or a pentagram, in addition to the first coordinate value and the second coordinate value of the robot when moving, the moving angle value can also be obtained, that is, (x, y, yaw) of the robot is obtained. Thus, when modeling, a model of a robot with an arbitrary polygon shape can be obtained, and then the obtained polygon model can be used for the motion planning of the robot, improving the passability of the robot.

[0054] In addition, an embodiment of the present application also provides a computer-readable medium, on which computer-readable instructions are stored, and the computer-readable instructions can be executed by a processor to implement the foregoing method for global path planning of a robot.

[0055] Corresponding to the method described above, the present application also provides a terminal, which includes modules or units capable of executing the method steps described in the above Figure 1 or Figure 2 or Figure 3 or Figure 4 or each of the embodiments. These modules or units can be implemented in a hardware, software, or a combination of hardware and software manner, and the present application does not limit this. For example, in an embodiment of the present application, a device for global path planning of a robot is also provided, and the device includes:

[0056] One or more processors; and

[0057] A memory storing computer-readable instructions, and the computer-readable instructions, when executed, cause the processor to perform the operations of the method as described above.

[0058] For example, when the computer-readable instructions are executed, they cause the one or more processors to:

[0059] Obtain the full state of the robot, perform polygon modeling according to the full state, and obtain a polygon model;

[0060] Perform collision screening on the polygon model to obtain a path map of the robot;

[0061] Determine the shortest path between nodes in the path map by means of graph search, and determine the global path planning of the robot according to the obtained shortest path.

[0062] Figure 5 The structural schematic diagram of a device for global path planning of a robot provided by another aspect of the present application is shown. The device includes: a modeling device 11, a screening device 12, and a determining device 13. Among them, the modeling device 11 is used to obtain the full state of the robot, perform polygon modeling according to the full state to obtain a polygon model; the screening device 12 is used to perform collision screening on the polygon model to obtain a path map of the robot; the determining device 13 is used to determine the shortest path between nodes in the path map by means of graph search, and determine the global path planning of the robot according to the obtained shortest path.

[0063] It should be noted that the contents executed by the modeling device 11, the screening device 12, and the determining device 13 are respectively the same as or correspondingly the same as the contents in the above steps S11, S12, and S13. For the sake of brevity, they will not be repeated here.

[0064] Obviously, those skilled in the art can make various changes and modifications 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 equivalent technologies, the present application also intends to include these changes and modifications.

[0065] It should be noted that the present application can be implemented in a software and / or a combination of software and hardware. For example, it can be implemented by using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program (including related data structures) of the present application can be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive, or a floppy disk and the like. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with the processor to execute each step or function.

[0066] In addition, a part of the present application can be applied as a computer program product, for example, computer program instructions, which, when executed by a computer, can call or provide the methods and / or technical solutions according to the present application through the operations of the computer. The program instructions for calling the methods of the present application may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in the working memory of a computer device running according to the program instructions. Herein, an embodiment according to the present application includes a device, the device includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run based on the methods and / or technical solutions according to the foregoing multiple embodiments of the present application.

[0067] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present application, the present application can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be construed as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the apparatus claims can also be implemented by one unit or device through software or hardware. First, second, etc. are used to denote names and do not denote any particular order.

Claims

1. A method for global path planning of a robot, characterized in that The method includes: Obtaining the full state of the robot, performing polygon modeling based on the full state to obtain a polygon model, where the polygon modeling is used to represent the shape of the robot chassis; Performing collision screening on the polygon model to obtain a path map of the robot; Determining the shortest path between nodes in the path map by means of graph search, and determining the global path planning of the robot according to the obtained shortest path; Among them, performing polygon modeling based on the full state to obtain a polygon model includes: Determining the next state that can be moved to according to the current state of the robot, and determining the operable trajectory of the robot according to all movable states; Selecting a target operable trajectory from the operable trajectories, discretizing the angles in the full state of the robot in the target operable trajectory to obtain a state transition graph; Performing polygon modeling according to the state transition graph to obtain a polygon model.

2. The method according to claim 1, wherein Performing polygon modeling according to the state transition graph to obtain a polygon model includes: Connecting each state transition in series according to the state transition graph, and obtaining a polygon model according to the series connection result.

3. The method according to claim 1, wherein Performing collision screening on the polygon model includes: Discretizing the robot chassis into a combination composed of multiple grids, and discretizing the polygon model into sampling points; Judging whether there is at least one sampling point in each grid. If so, the robot collides, and the sampling points that collide are filtered.

4. The method according to claim 3, characterized in that, Judging whether there is at least one sampling point in each grid includes: Judging whether there is at least one sampling point in the grid in the advancing direction of each robot according to the full state of the robot.

5. The method according to claim 3, wherein Obtaining the full state of the robot includes: If the robot chassis is circular, obtaining the first coordinate value and the second coordinate value of the robot; If the robot chassis is of a special shape, obtaining the first coordinate value, the second coordinate value and the angle value of the robot.

6. A device for global path planning of a robot, characterized in that, The device includes: A modeling device for obtaining the full state of the robot, performing polygon modeling based on the full state to obtain a polygon model, where the polygon modeling is used to represent the shape of the robot chassis; A screening device for performing collision screening on the polygon model to obtain a path map of the robot; A determining device for determining the shortest path between nodes in the path map by means of graph search, and determining the global path planning of the robot according to the obtained shortest path; Among them, the modeling device is used for: Determining the next state that can be moved to according to the current state of the robot, and determining the operable trajectory of the robot according to all movable states; Selecting a target operable trajectory from the operable trajectories, discretizing the angles in the full state of the robot in the target operable trajectory to obtain a state transition graph; Performing polygon modeling according to the state transition graph to obtain a polygon model.

7. A device for global path planning of a robot, characterized in that, The device includes: One or more processors; and A memory storing computer-readable instructions, which when executed cause the processor to perform the operations of the method according to any one of claims 1 to 5.

8. A computer-readable medium having computer-readable instructions stored thereon, the computer-readable instructions being executable by a processor to implement the method according to any one of claims 1 to 5.

Images