Robot path planning method and quality evaluation method thereof

Abstract

The invention discloses a robot path planning method and a quality evaluation method thereof in the technical field of robot path planning, and aims to solve the technical problem that existing robot path planning cannot respond to environmental changes in time. The method comprises the steps that a cellular automaton is used for breeding according to a conversion rule, a robot chassis cellular set locally avoids a dynamically-changing obstacle cellular set and gradually arrives at a target point cellular set, efficient path planning in an environment with continuously-changing local conditions is achieved, real-time dynamic and locally-adaptive obstacle avoidance is achieved, and the obstacle avoidance efficiency is improved. According to the method, better robustness can be shown in an uncertain environment, a safer and more convenient path can be planned, obstacles can be avoided according to the shape and the physical property of the moving chassis, the moving chassis can reach a target point in a safe and more convenient mode, and meanwhile the requirement for performance is not too high; path evaluation is carried out through a corresponding quality evaluation method, the planned path quality can be reflected, and a basis is provided for later research and parameter adjustment.

Description

Technical Field

[0001] The invention relates to a robot path planning method and a quality evaluation method thereof, and belongs to the technical field of robot path planning. Background Art

[0002] With the development of mobile robot technology, the fully automatic operation of mobile robots will greatly reduce manpower input compared to traditional manual operation or manual driving.

[0003] Traditional algorithms such as A Star and Dijkstra were originally designed to solve path planning problems in static or relatively static environments. These algorithms work by calculating the shortest path from the start point to the end point, and they rely on a fixed graph structure in which obstacles are static or relatively static. These traditional algorithms may encounter challenges in environments where local conditions are constantly changing (such as dynamic obstacles, road congestion, etc.). They need to recalculate the path frequently, which may lead to a significant increase in computational costs, and in some cases may not be able to respond to environmental changes in a timely manner. Summary of the invention

[0004] The purpose of this application is to overcome the deficiencies in the prior art and to provide a robot path planning method and a quality evaluation method thereof that can more efficiently perform path planning in an environment where local conditions are constantly changing.

[0005] In order to achieve the above objectives, this application is implemented by adopting the following technical solutions:

[0006] In a first aspect, the present application provides a robot path planning method, comprising:

[0007] Setting a cellular automaton model, wherein the cellular automaton model includes a cellular space, a conversion rule, and a cellular set;

[0008] In the cellular space, a target point cellular set is set, and an initial robot chassis cellular set and an obstacle cellular set are set in the cellular space according to the projections of the actual robot chassis and the actual obstacles;

[0009] The obstacle cell set is iterated according to the change of the real obstacle, the neighborhood cell set of the robot chassis cell set is determined according to the distribution of the obstacle cell set, and the neighborhood cells are converted into robot chassis cells in the neighborhood cell set according to the conversion rule, and a synchronized planning path is output according to the converted robot chassis cell set until the robot chassis cell set reaches the target point cell set.

[0010] In some embodiments of the first aspect,

[0011] Acquire functional parameters of the actual robot chassis in advance, and obtain steering capability limit and movement speed limit according to the functional parameters;

[0012] The neighborhood cell set is obtained as follows:

[0013] In response to completing the initial setting of the robot chassis cell set, or in response to completing the conversion of the neighborhood cells into the robot chassis cells, candidate cells are determined from around the robot chassis cell set according to the steering capability limit and the movement speed limit, obstacle cells and cells blocked by the obstacle cells and thus unreachable are eliminated from the candidate cells, and the remaining candidate cells are used as neighborhood cells to obtain a neighborhood cell set.

[0014] In some embodiments of the first aspect,

[0015] The synchronously converting the neighborhood cells into robot chassis cells in the neighborhood cell set according to the conversion rule, and outputting a planned path according to the converted robot chassis cell set, including:

[0016] Obtain the current cellular space position of the robot chassis cellular set and the current chassis orientation;

[0017] According to the current cellular space position and the current chassis orientation, a conversion rule function is obtained, and the next cellular space position and chassis orientation of the robot chassis cell set are obtained according to the output of the conversion rule function. According to the next cellular space position and chassis orientation, the neighborhood cells are converted into robot chassis cells; wherein the conversion rule function is as follows:

[0018]

[0019] Where t is the count number of the transformation step, i and j are the current cellular space position coordinates of the robot chassis cell set, θ is the current chassis orientation of the robot chassis cell set, T(i,j,θ,t) is the output of the transformation rule function at the tth step, i′ and j′ are the cellular space position coordinates of the robot chassis cell set at the t+1th step, θ′ is the chassis orientation of the robot chassis cell set at the t+1th step, N V (i,j,θ) is the neighborhood cell set, i D and j D are the cell space position coordinates of the target point cell set, D(i,j,i D ,j D ) is the distance between the robot chassis cell set and the target point cell set, and R(i,j,θ,i′,j′,θ′) is the event that the robot chassis cell set moves from the coordinate (i,j,θ) to the coordinate (i',j',θ).

[0020] In some embodiments of the first aspect,

[0021] The synchronization converts the neighborhood cells into robot chassis cells in the neighborhood cell set according to the conversion rule, and outputs a synchronized planning path according to the converted robot chassis cell set, including:

[0022] Assigning weights to each neighborhood cell, wherein the weight of the neighborhood cell that is farther from the robot chassis cell set is greater than the weight of the neighborhood cell that is closer to the robot chassis cell set;

[0023] To assign weights to the direction of the target point cell set, the next cellular space position of the robot chassis cell set is determined according to the weight of the direction of the target point cell set and the weight of the neighborhood cells.

[0024] In some embodiments of the first aspect, the outputting a synchronized planned path according to the converted robot chassis cell set includes:

[0025] Fitting the robot chassis into a rectangle, obtaining the planned coordinates of the vertices of the robot chassis rectangle according to the converted robot chassis cell set, and obtaining the planned speed and planned turning radius of the robot chassis according to the planned coordinates;

[0026] The starting coordinates of the robot chassis rectangle are obtained according to the robot chassis cell set before the conversion, and the verification coordinates of the vertices of the robot chassis rectangle are obtained according to the planned speed, the planned turning radius and the starting coordinates; wherein the acquisition formula of the verification coordinates is as follows:

[0027]

[0028] Where I is the number of the rectangle vertex, I = A, B, C, D, A, B, C, D are the four vertices of the robot chassis rectangle, t is the count number of the conversion step, x I (t) and y I (t) are the verification coordinates of the tth step, x O and O are the centroid coordinates in the starting coordinates, v(τ) is the planned speed, θ′ is the planned turning radius, τ is any moment in the integral range, dτ is the time differential in the integral range, R(τ) is the turning radius of the tth step, x I and I They are the vertex coordinates in the starting coordinates respectively;

[0029] In response to an error between the verification coordinates and the planning coordinates being less than a threshold, the planning speed and the planning turning radius are output as the planning path.

[0030] In a second aspect, the present application also provides a method for evaluating the quality of a robot planning path, comprising:

[0031] Integrate the planned path provided by the robot path planning method according to any one of the embodiments of the first aspect into a complete path;

[0032] Discretizing the complete path into a number of points according to evaluation accuracy requirements;

[0033] Obtain the safety factor of each discrete point; wherein the safety factor of the discrete point is obtained as follows:

[0034]

[0035] In the formula, s J is the safety factor of the Jth discrete point, J is the counting number of the discrete point, v J is the velocity of the Jth discrete point, d J is the distance between the Jth discrete point and the nearest obstacle, δ is the adjustment parameter of acceleration, θ is the adjustment parameter of robot mass, γ is the adjustment parameter of speed, and a J is the acceleration of the Jth discrete point, m is the mass of the robot;

[0036] The average safety factor of the discrete points is obtained, the path efficiency coefficient of the complete path is obtained, and the path quality is obtained according to the path efficiency coefficient and the average safety factor of the complete path.

[0037] In some embodiments of the second aspect, the path efficiency coefficient of the complete path is obtained by the following formula:

[0038]

[0039] In the formula, Q is the path efficiency coefficient, A is the penalty adjustment parameter of length on quality, B is the sensitivity adjustment parameter of distance factor, and ρ is the adjustment parameter of path detour. is the average distance between the discrete point and the nearest obstacle;

[0040] The path quality is obtained as follows:

[0041]

[0042] Where Q' is the path quality, is the average safety factor, and n is the number of discrete points.

[0043] In a third aspect, the present application also provides a computer device, comprising a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the robot path planning method described in any embodiment of the first aspect are performed.

[0044] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the robot path planning method described in any embodiment of the first aspect.

[0045] In a fifth aspect, the present application also provides a computer program product, comprising a computer program / instructions, characterized in that when the computer program / instructions are executed by a processor, the steps of the robot path planning method described in any embodiment of the first aspect are implemented.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The robot path planning method provided in the present application utilizes cellular automata to reproduce according to conversion rules, and the robot chassis cell set locally avoids the dynamically changing obstacle cell set and gradually reaches the target point cell set, thereby realizing efficient path planning in an environment where local conditions are constantly changing; the robot chassis cell set set based on the projection of the actual robot chassis is used for path planning, which has good universality for different types of motion chassis; the robot chassis cell set is restricted to be converted and reproduced within the neighborhood cell set that has excluded the obstacle cell set, thereby realizing real-time dynamic and locally adaptive avoidance of obstacles, which may show better robustness in an environment where incomplete or inaccurate information is processed, and a safer and more convenient path is planned, which can avoid obstacles according to the shape and physical properties of the motion chassis, and reach the target point in a safe and convenient manner, while not requiring too much performance; the path is evaluated by the corresponding quality evaluation method, which can reflect the quality of the planned path, provide a basis for later research and parameter adjustment, and enable the robot path planning method to more efficiently generate paths for locally avoiding dynamically changing obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 is a flowchart of the steps of the robot path planning method provided in this embodiment;

[0050] Figure 2 Schematic diagram of the overall effect of the cellular space planning path in this embodiment;

[0051] Figure 3 is a flowchart of the steps of chassis parameters and environment status feedback in this embodiment;

[0052] Figure 4 It is a schematic block diagram of the principles of the computer device provided in this embodiment. DETAILED DESCRIPTION

[0054] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0055] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. 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, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0056] Embodiment 1:

[0057] Figure 1 This is a flow chart of a robot path planning method in the first embodiment of the present invention. This flow chart only shows the logical sequence of the method described in this embodiment. In other possible embodiments of the present invention, different Figure 1 The steps shown or described are accomplished in the order shown.

[0058] The robot path planning method provided in this embodiment can be applied to a terminal and can be executed by a robot path planning device, which can be implemented by software and / or hardware, and can be integrated in a terminal, such as any smart phone, tablet computer or computer device with communication function. Figure 1 The method of this implementation specifically includes the following steps:

[0059] Set up a cellular automaton model, which includes a cell space, a transition rule, and a cell set;

[0060] The cellular space is the activity range of the cell. In the cellular space, the target point cellular set is set. The initial robot chassis cellular set and obstacle cellular set are set in the cellular space according to the projection of the actual robot chassis and the actual obstacles.

[0061] The obstacle cell set is iterated according to the changes of the actual obstacles, the neighborhood cell set of the robot chassis cell set is determined according to the distribution of the obstacle cell set, and the neighborhood cells are converted into robot chassis cells in the neighborhood cell set according to the conversion rules. The synchronized planning path is output according to the converted robot chassis cell set until the robot chassis cell set reaches the target point cell set.

[0062] Depending on the complexity of the environment, the cellular space can choose different resolutions. Lower resolutions are more concise and have relatively higher calculation speeds, but they are less accurate and are not suitable for complex environments. Higher resolutions can accommodate more environmental information and include more details in the calculation, but they will also consume more computing resources. Therefore, it is necessary to choose the appropriate resolution based on the actual environment.

[0063] In this embodiment, the cellular space used is a two-dimensional plane. The three-dimensional path planning can be obtained by reasonable expansion based on the content of this embodiment.

[0064] In the cellular space, each square represents a cell. Each cell has different states. This embodiment uses a state function to represent the states of different cells, such as 0: idle cell, 1: obstacle cell, 2: starting point, 3: target point cell, 4: robot chassis cell.

[0065] As the reproduction rule of the robot chassis cell set in the cellular automaton model, the conversion rule is mainly obtained from the motion ability of the actual robot chassis and the environment / rule constraints. That is, the obstacle cell set that changes all the time is used to simulate the dynamically changing obstacles in reality in the cellular automaton model, and the conversion rule is used to simulate the environment (wind direction and sun direction) / rule constraints (such as not being able to turn left or move backward) in the cellular automaton model, and the motion ability and real influence of the actual robot chassis are imposed on the robot chassis cell set, thereby ensuring the accuracy and practicality of path generation.

[0066] In addition, it is worth noting that the planned path mentioned in this embodiment refers to the local path generated in the step of real-time path generation, rather than the complete path from the starting point to the target point; when the local path of each step is generated, the partial path is generated according to the cells that have been most recently converted to the robot chassis cell set. In the cellular automaton model, the number of grids occupied by the robot chassis cell set is strictly controlled according to the projection size of the actual robot chassis. When new neighboring cells are converted to robot chassis cells, the corresponding number of the oldest robot chassis cells are converted to other cells (free cells, neighboring cells, etc.) to ensure that in the planning of each step of the planned path, the number of grids occupied by the robot chassis cell set is always kept uniform, so that the motion simulation of the robot chassis is more accurate. Reference Figure 2 , Figure 2The six red cells represent the robot chassis cell set of the robot chassis projection. The two red cells represent the positions of the robot chassis cell set at the initial and target cell sets respectively. The blue represents the complete path, and the green represents the obstacle cell set. In order to fully consider the obstacle avoidance performance and whether the robot involved in the planned path can pass normally, the robot chassis is not represented by a single cell in the cellular space, but by a group of cells involved in the projection of the entire robot in the two-dimensional cellular space. Figure 2 , this group of cells maintains a fixed arrangement and combination order during operation, that is, it maintains the shape of the robot projection, and is constrained by the dynamic limitations of the motion chassis (such as turning radius, etc.).

[0067] The neighborhood cell set is adjusted and iterated in real time according to the obstacle cell set. The robot chassis cell set "moves" and iterates gradually in the direction of the target point cell set by continuously converting the neighborhood cells into robot chassis cells. The cells that have been converted into robot chassis cells can be integrated into a complete path cell set, or the path on a certain side of the robot chassis cell can be integrated into a complete path cell set. The complete path that the robot chassis cell set has experienced is obtained through the complete path cell set, that is, the complete path of all planned paths. The complete path can be used to evaluate the path generation quality, and the parameters of the cellular automaton model can be adjusted based on the evaluation.

[0068] It is not difficult for a person skilled in the art to see that the robot path planning method provided in this embodiment is different from the previous path planning method in that the previous path planning method can only be applied to static or relatively static environments to generate a complete path from the starting point to the target point and avoid obstacles; the robot path planning method provided in this embodiment does not adopt a one-time complete path generation method, but adopts a local planning path generated in a single unit time to command the robot's actions; the robot path planning method provided in this embodiment does not directly generate a complete path, but generates a planning path that can be fully executed in a single unit time toward the target point according to the local obstacle situation during each conversion iteration through the robot chassis cell set. This method only considers the target point direction and the obstacle situation in the neighborhood, and calculates the path planning of the robot in a single short time with extremely low calculation amount; therefore, the robot path planning method provided in this embodiment can realize motion planning in a dynamic obstacle environment with low resource occupancy, and the instructions output to the robot according to the planned path are the most suitable for the current local obstacle environment, and the robot can be commanded to accurately avoid dynamic obstacles and reach the target point in the whole process.

[0069] Embodiment 2:

[0070] This embodiment provides a robot path planning method. This embodiment is optimized on the basis of the first embodiment to improve the technical effect and refine the technical solution. For the contents not fully described in this embodiment, please refer to the first embodiment.

[0071] The function of the neighborhood cell set is to divide the candidate area of ​​the robot chassis cell, paving the way for the next transformation iteration of the robot chassis cell. In a further but non-limiting embodiment of the present application, the functional parameters of the actual robot chassis are obtained in advance, and the steering ability limit and the movement speed limit are obtained according to the functional parameters; the neighborhood cell set is obtained as follows:

[0072] In response to completing the initial setting of the robot chassis cell set, or in response to completing the conversion of the neighborhood cells into the robot chassis cells, candidate cells are determined from around the robot chassis cell set according to the steering capability limit and the movement speed limit, obstacle cells and cells blocked by the obstacle cells and thus unreachable are eliminated from the candidate cells, and the remaining candidate cells are used as neighborhood cells to obtain the neighborhood cell set.

[0073] Among them, completing the initial setting of the robot chassis cell set refers to the first step of directly converting the cells corresponding to the projection of the robot chassis into robot chassis cells at the beginning of the path generation task; and completing the conversion of neighborhood cells into robot chassis cells refers to each step of the conversion iteration based on the existing robot chassis cell set.

[0074] By obtaining the neighborhood cell set mentioned above, a candidate cell region is delineated around the robot chassis cell set.

[0075] As one embodiment, the neighborhood cells are converted into robot chassis cells in the neighborhood cell set according to the conversion rule, and the planning path is output according to the converted robot chassis cell set, including:

[0076] Get the current cell space position of the robot chassis cell set and the current chassis orientation;

[0077] According to the current cellular space position and the current chassis orientation, a conversion rule function is obtained, and the next cellular space position and chassis orientation of the robot chassis cell set are obtained according to the output of the conversion rule function. According to the next cellular space position and chassis orientation, the neighborhood cells are converted into robot chassis cells; wherein the conversion rule function is as follows:

[0078]

[0079] Where t is the count number of the transformation step, i and j are the current cellular space position coordinates of the robot chassis cell set, θ is the current chassis orientation of the robot chassis cell set, T(i,j,θ,t) is the output of the transformation rule function at the tth step, i′ and j′ are the cellular space position coordinates of the robot chassis cell set at the t+1th step, θ′ is the chassis orientation of the robot chassis cell set at the t+1th step, N V (i,j,θ) is the neighborhood cell set, i D and j D are the cell space position coordinates of the target point cell set, D(i,j,i D ,j D ) is the distance between the robot chassis cell set and the target point cell set, and R(i,j,θ,i′,j′,θ′) is the event that the robot chassis cell set moves from the coordinate (i,j,θ) to the coordinate (i',j',θ).

[0080] The planning path is generated according to the conversion rule function, and the output of each planning path is the beginning of the next planning path.

[0081] If the robot chassis is a non-omnidirectional motion chassis (such as an Ackerman chassis, etc.), special kinematic characteristic restrictions should be introduced into the conversion rules or steering ability restrictions and motion speed restrictions.

[0082] Different from the above conversion rules, this embodiment also provides another output method of the planned path: assigning weights to each neighborhood cell, wherein the weight of the neighborhood cell that is farther from the robot chassis cell set is greater than the weight of the neighborhood cell that is closer to the robot chassis cell set;

[0083] To assign weights to the direction of the target cell set, the next cellular spatial position of the robot chassis cell set is determined according to the weight of the direction of the target cell set and the weight of the neighborhood cells. That is, the neighborhood cells are converted into robot chassis cells in the next step, and a synchronized planning path is output according to the converted robot chassis cell set. This method helps to adjust the degree of movement of the robot chassis toward the target point.

[0084] Two planning path generation methods and their combination.

[0085] In the above, the iteration result of the robot chassis cell set is used as the planned path to control the movement of the robot; since the robot chassis is projected in the cell space in this embodiment, the path accuracy varies according to the cell resolution, and the lower path accuracy may cause errors between the planned path and the ideal state. Therefore, as one embodiment,

[0086] Output the synchronized planning path based on the converted robot chassis cell set, including:

[0087] Considering that the chassis of most robots are rectangular, in this embodiment, the robot chassis is fitted into a rectangle, and the planning coordinates of the vertices of the robot chassis rectangle are obtained according to the converted robot chassis cell set, and the planning speed and planning turning radius of the robot chassis are obtained according to the planning coordinates;

[0088] The starting coordinates of the robot chassis rectangle are obtained according to the robot chassis cell set before the conversion. The verification coordinates of the robot chassis rectangle vertices are obtained according to the planned speed, planned turning radius and the starting coordinates. The verification coordinates are obtained as follows:

[0089]

[0090] Where I is the number of the rectangle vertex, I = A, B, C, D, A, B, C, D are the four vertices of the robot chassis rectangle, t is the count number of the conversion step, x I (t) and y I (t) are the verification coordinates of the tth step, x O and O are the centroid coordinates in the starting coordinates, v(τ) is the planned speed, θ′ is the planned turning radius, τ is any moment in the integral range, dτ is the time differential in the integral range, R(τ) is the turning radius of the tth step, x I and I They are the vertex coordinates in the starting coordinates respectively;

[0091] In response to the error between the verification coordinates and the planned coordinate form being less than a threshold, the planned speed and the planned turning radius are output as the planned path.

[0092] The starting coordinates of the robot chassis rectangle are the starting coordinates within the single local path planning step. The planning coordinates are the cellular coordinates obtained according to the iterated robot chassis cell set. The planned speed and planned turning radius of the robot chassis obtained according to the planning coordinates are the control commands output to the robot. According to the acquisition formula of the verification coordinates, the planned speed and planned turning radius are reversely substituted into the cellular automaton model based on the starting coordinates to obtain the verification coordinates. When the error between the verification coordinates and the planning coordinates is very small or completely consistent, it means that the execution scheme of the planned speed and planned turning radius is effective and reasonable, and it also means that the resolution of the cellular space is reasonable; after the verification is completed, the planned speed and planned turning radius are input to the robot's control system for execution, otherwise the planned path is regenerated in the next step.

[0093] As one embodiment, the cellular automaton model uses Moore-type neighbors as the neighbor type.

[0094] refer to Figure 3As one of the embodiments, after the output of the planned path is completed in each step, the chassis parameters and the environment are fed back in the next step according to the verification situation, and then the conversion rules, steering ability limits and movement speed limits are adjusted.

[0095] In summary, the robot path planning method provided in this embodiment improves the technical effect and refines the technical solution compared to the first embodiment.

[0096] Embodiment three:

[0097] This embodiment provides a quality evaluation method for a robot planning path, which is mainly used to evaluate the quality of the path in Embodiment 1 or 2. The quality evaluation method for a robot planning path provided in this embodiment includes:

[0098] Integrate the planned paths provided by the robot path planning method in the first embodiment or any one of the above into a complete path;

[0099] Discretize the complete path into several points according to the evaluation accuracy requirements;

[0100] Obtain the safety factor of each discrete point; the formula for obtaining the safety factor of the discrete point is as follows:

[0101]

[0102] In the formula, s J is the safety factor of the Jth discrete point, J is the counting number of the discrete point, v J is the velocity of the Jth discrete point, d J is the distance between the Jth discrete point and the nearest obstacle, δ is the adjustment parameter of acceleration, θ is the adjustment parameter of robot mass, γ is the adjustment parameter of speed, and a J is the acceleration of the Jth discrete point, m is the mass of the robot, and a larger mass makes it more difficult to slow down or change direction when approaching an obstacle, increasing the risk of collision;

[0103] Get the average safety factor of discrete points, get the path efficiency coefficient of the complete path, and get the path quality based on the path efficiency coefficient and the average safety factor of the complete path.

[0104] It is worth noting that the more discrete points there are, the higher the accuracy and the smaller the calculated path quality error; the fewer discrete points there are, the lower the accuracy and the larger the calculated path quality error.

[0105] The above safety factor acquisition formula is a nonlinear response method, which makes the output (safety factor) decrease rapidly as the input variables (such as speed, acceleration, and the ratio of mass to obstacle distance) increase. At the same time, it has a fast response characteristic, which enables the model to sensitively capture small changes in risk.

[0106] In a further but non-limiting embodiment of the present application,

[0107] The path efficiency coefficient of the complete path is obtained as follows:

[0108]

[0109] Where Q is the path efficiency coefficient, which is used to evaluate feasibility and convenience, A is the penalty adjustment parameter for length to quality, B is the sensitivity adjustment parameter for distance factor, both A and B are positive adjustment parameters, ρ is the adjustment parameter for the detour, when the path length is close to the shortest path, ρ-1 approaches 0, making e -A(ρ-1) As it approaches 1, the penalty of length on quality becomes smaller. is the average distance between the discrete point and the nearest obstacle; the longer the path, the smaller this value is, and the greater the penalty for the total quality. When the path is too close to the obstacle, As it approaches 0, the penalty on total mass increases. This item quickly reduces the safety factor when the distance to the obstacle is very close, and is sensitive to the high risk at close distances.

[0110] Combining the evaluation functions of feasibility, safety, and convenience, the formula for obtaining path quality is as follows:

[0111]

[0112] Where Q' is the path quality, is the average safety factor, and n is the number of discrete points.

[0113] Q'∈(0,1), the closer Q' is to 1, the higher the path quality. It reflects the overall safety of the entire route.

[0114] The complete path of the robot chassis is evaluated by the quality evaluation method for the robot planning path provided in this embodiment, which helps to optimize the parameters of the quality evaluation method for the robot planning path.

[0115] Embodiment 4:

[0116] This embodiment provides a computer device, including a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the robot path planning method provided in Embodiment 1 or 2 are performed.

[0117] The computer device may be a server or an electronic terminal. As one embodiment, refer to Figure 4, the computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data obtained and generated in the robot path planning method. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the robot path planning method provided in embodiment one or two is implemented.

[0118] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] The computer device provided in this embodiment has the same technical effects as those in Embodiment 1 or 2, which will not be described in detail here.

[0120] Embodiment five:

[0121] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the robot path planning method provided in Embodiment 1 or Embodiment 2 are implemented.

[0122] The computer-readable storage medium provided in this embodiment has the same technical effects as those in Embodiment 1 or 2, and will not be described in detail here.

[0123] Embodiment six:

[0124] This embodiment provides a computer program product, on which a computer program is stored, and when the program is executed by a processor, the steps of the robot path planning method provided in Embodiment 1 or Embodiment 2 are implemented. The computer program product provided in this embodiment can be transmitted, distributed and downloaded in the form of a signal via the Internet.

[0125] The computer program product provided in this embodiment has the same technical effects as those in Embodiment 1 or 2, and will not be described in detail here.

[0126] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0127] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0130] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A robot path planning method, characterized in that: include, Setting a cellular automaton model, wherein the cellular automaton model includes a cellular space, a conversion rule, and a cellular set; In the cellular space, a target point cellular set is set, and an initial robot chassis cellular set and an obstacle cellular set are set in the cellular space according to the projections of the actual robot chassis and the actual obstacles; The obstacle cell set is iterated according to the change of the real obstacle, the neighborhood cell set of the robot chassis cell set is determined according to the distribution of the obstacle cell set, and the neighborhood cells are converted into robot chassis cells in the neighborhood cell set according to the conversion rule, and a synchronized planning path is output according to the converted robot chassis cell set until the robot chassis cell set reaches the target point cell set.

2. The robot path planning method according to claim 1, characterized in that: Acquire functional parameters of the actual robot chassis in advance, and obtain steering capability limit and movement speed limit according to the functional parameters; The neighborhood cell set is obtained as follows: In response to completing the initial setting of the robot chassis cell set, or in response to completing the conversion of the neighborhood cells into the robot chassis cells, candidate cells are determined from around the robot chassis cell set according to the steering capability limit and the movement speed limit, obstacle cells and cells blocked by the obstacle cells and thus unreachable are eliminated from the candidate cells, and the remaining candidate cells are used as neighborhood cells to obtain a neighborhood cell set.

3. The robot path planning method according to claim 2, characterized in that: The synchronously converting the neighborhood cells into robot chassis cells in the neighborhood cell set according to the conversion rule, and outputting a planned path according to the converted robot chassis cell set, including: Obtain the current cellular space position of the robot chassis cellular set and the current chassis orientation; According to the current cellular space position and the current chassis orientation, a conversion rule function is obtained, and the next cellular space position and chassis orientation of the robot chassis cell set are obtained according to the output of the conversion rule function. According to the next cellular space position and chassis orientation, the neighborhood cells are converted into robot chassis cells; wherein the conversion rule function is as follows: Where t is the count number of the conversion step, i and j are the current cellular space position coordinates of the robot chassis cell set, θ is the current chassis orientation of the robot chassis cell set, T(i,j,θ,t) is the output of the conversion rule function at the tth step, i' and j' are the cellular space position coordinates of the robot chassis cell set at the t+1th step, θ' is the chassis orientation of the robot chassis cell set at the t+1th step, N V (i,j,θ) is the neighborhood cell set, i D and j D are the cell space position coordinates of the target point cell set, D(i,j,i D ,j D ) is the distance between the robot chassis cell set and the target point cell set, and R(i,j,θ,i′,j′,θ′) is the event that the robot chassis cell set moves from the coordinate (i,j,θ) to the coordinate (i',j',θ).

4. The robot path planning method according to claim 2, characterized in that: The synchronization converts the neighborhood cells into robot chassis cells in the neighborhood cell set according to the conversion rule, and outputs a synchronized planning path according to the converted robot chassis cell set, including: Assigning weights to each neighborhood cell, wherein the weight of the neighborhood cell that is farther from the robot chassis cell set is greater than the weight of the neighborhood cell that is closer to the robot chassis cell set; To assign weights to the direction of the target point cell set, the next cellular space position of the robot chassis cell set is determined according to the weight of the direction of the target point cell set and the weight of the neighborhood cells.

5. The robot path planning method according to claim 1, characterized in that: The planning path synchronized with the output of the converted robot chassis cell set includes: Fitting the robot chassis into a rectangle, obtaining the planned coordinates of the vertices of the robot chassis rectangle according to the converted robot chassis cell set, and obtaining the planned speed and planned turning radius of the robot chassis according to the planned coordinates; The starting coordinates of the robot chassis rectangle are obtained according to the robot chassis cell set before the conversion, and the verification coordinates of the vertices of the robot chassis rectangle are obtained according to the planned speed, the planned turning radius and the starting coordinates; wherein the acquisition formula of the verification coordinates is as follows: Where I is the number of the rectangle vertex, I = A, B, C, D, A, B, C, D are the four vertices of the robot chassis rectangle, t is the count number of the conversion step, x I (t) and y I (t) are the verification coordinates of the tth step, x O and O are the centroid coordinates in the starting coordinates, v(τ) is the planned speed, θ′ is the planned turning radius, τ is any moment in the integral range, dτ is the time differential in the integral range, R(τ) is the turning radius of the tth step, x I and I They are the vertex coordinates in the starting coordinates respectively; In response to an error between the verification coordinates and the planning coordinates being less than a threshold, the planning speed and the planning turning radius are output as the planning path.

6. A method for evaluating the quality of a robot planning path, characterized in that: include, Integrate the planned path provided by the robot path planning method according to any one of claims 1 to 5 into a complete path; Discretizing the complete path into a number of points according to evaluation accuracy requirements; Obtain the safety factor of each discrete point; wherein the safety factor of the discrete point is obtained as follows: In the formula, s J is the safety factor of the Jth discrete point, J is the counting number of the discrete point, v J is the velocity of the Jth discrete point, d J is the distance between the Jth discrete point and the nearest obstacle, δ is the adjustment parameter of acceleration, θ is the adjustment parameter of robot mass, γ is the adjustment parameter of speed, and a J is the acceleration of the Jth discrete point, m is the mass of the robot; The average safety factor of the discrete points is obtained, the path efficiency coefficient of the complete path is obtained, and the path quality is obtained according to the path efficiency coefficient and the average safety factor of the complete path.

7. The quality evaluation method for robot planning path according to claim 6 is characterized in that: The formula for obtaining the path efficiency coefficient of the complete path is as follows: In the formula, Q is the path efficiency coefficient, A is the penalty adjustment parameter of length on quality, B is the sensitivity adjustment parameter of distance factor, and ρ is the adjustment parameter of path detour. is the average distance between the discrete point and the nearest obstacle; The path quality is obtained as follows: Where Q' is the path quality, is the average safety factor, and n is the number of discrete points.

8. A computer device, characterized in that: The method comprises a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the robot path planning method according to any one of claims 1 to 7 are executed.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the robot path planning method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the robot path planning method according to any one of claims 1 to 7 are implemented.

Images