Mechanical arm path planning method and system based on environmental parameter self-adaptive adjustment

Abstract

The invention relates to the technical field of path planning, in particular to a mechanical arm path planning method and system based on environment parameter self-adaptive adjustment, and the method comprises the steps: taking the tail end position of a mechanical arm as a starting node, taking the position of a target object as a target node to construct a random tree, and setting a search radius to dynamically obtain obstacle data; the step length is dynamically adjusted according to obstacle data, an adaptive sampling strategy is introduced, and an initial path is generated by selecting an optimal father node and reconnecting peripheral nodes; smoothing the initial path, adjusting an offset point, optimizing a target node search area and constraining a path direction included angle to obtain a final path; and the path node coordinates are converted into mechanical arm physical coordinate system coordinates, and a mechanical arm is driven to execute an obstacle avoidance grabbing task. According to the method, the path planning efficiency is remarkably improved, the planning time is shortened, the path quality is optimized, and the safety and stability in a complex environment are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a robotic arm path planning method and system based on adaptive adjustment of environmental parameters. Background Art

[0002] In key technical fields such as robotic arm motion control, autonomous driving, and logistics transportation, path planning, as the core technology to ensure the efficient operation of the system, directly determines the operation efficiency and reliability of each system. Currently, traditional path planning algorithms are still widely used in path planning scenarios. Taking the A* algorithm as an example, it can effectively search for the global optimal path in a simple static environment. However, when faced with complex obstacle distributions or dynamic environments, this algorithm needs to traverse a large number of nodes, resulting in an exponential increase in the computational complexity and making it difficult to meet the requirements of real-time path planning. The Dijkstra algorithm also faces efficiency bottlenecks. Its high time complexity causes a significant increase in the planning time when dealing with large-scale map data and cannot adapt to application scenarios with extremely high real-time requirements.

[0003] In view of the drawbacks of traditional algorithms, the existing improved Informed RRT* algorithm is based on the RRT algorithm and introduces an elliptical sampling strategy to optimize the search range, which improves the search efficiency to a certain extent. However, this algorithm still has obvious technical defects: First, it has insufficient adaptability to dynamic environments and cannot quickly respond to environmental changes and re-plan the path; Second, it lacks an effective path safety guarantee mechanism and is difficult to avoid potential collision risks; Third, it has poor robustness in the end region and is prone to path oscillations or the situation where it cannot accurately converge to the target point. These problems limit the application and development of existing path planning algorithms in complex dynamic scenarios. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a robotic arm path planning method and system based on adaptive adjustment of environmental parameters. The method includes the following steps:

[0005] S1: Taking the current position of the end of the robotic arm as the starting node, the position of the target object to be grasped as the target node, and starting from the starting node, construct a random tree containing path nodes between the starting node and the target node. In the random tree, set a search radius centered on each current node and dynamically obtain obstacle data within this range;

[0006] S2: According to the obstacle data, dynamically adjust the step size of the end of the robotic arm. At the same time, introduce an adaptive sampling strategy. When selecting the parent node of the new node, preferentially select the nearby node with the smallest total cost and no collision, and reconnect the surrounding nodes to generate an initial path;

[0007] S3: Smooth the initial path, reduce the turning points in the initial path, dynamically adjust the path offset points, and preferentially select the offset points that are close to the target node and collision-free. By optimizing the search area of the target node and constraining the angle between the path direction and the target node direction, the final path is obtained;

[0008] S4: Based on the final path, generate path node coordinates, convert the path node coordinates into path coordinates in the physical coordinate system of the robotic arm, and drive the robotic arm to perform an obstacle avoidance grasping task based on the path coordinates in the physical coordinate system of the robotic arm.

[0009] In an embodiment of the present invention, in S2, the method for generating the initial path is as follows:

[0010] S21: Calculate the straight-line path length between the starting node and the target node, calculate the target sampling probability according to the straight-line path length and the current path length, and generate sampling points according to the target sampling probability;

[0011] S22: Find the first node closest to the sampling point in the random tree , from the first node extend a step length towards the sampling point to generate a second node ;

[0012] S23: Traverse whether there are obstacles in the path between the first node and the second node :

[0013] If so, return to S21 for resampling;

[0014] If not, enter step S24;

[0015] S24: Traverse the step length area that is an integer multiple of the second node to obtain a set of neighbor nodes , for each node in the set of neighbor nodes , calculate the total cost from each node to the second node :

[0016] , where, represents the path length between the node and the starting node, represents the second node and the node ;

[0017] S25: Select the node with the minimum total cost and no path collision as the parent node of the second node and add the second node to the random tree, and update the path cost of the second node to be: wherein represents the path length between node and the starting node, represents the path length between the second node and node ;

[0018] S26: Traverse all nodes within a radius r around the second node , calculate the candidate cost through each node the second node . If and there is no path collision, update the parent node of node to be , and update the node cost of the node to be ;

[0019]

[0020] S27: Repeat steps S21 - S26 to obtain an initial path

[0020] In an embodiment of the present invention, in S21, the method for calculating the target sampling probability based on the straight - line path length and the current path length and generating a sampling point according to the target sampling probability is as follows:

[0021] Set a global variable to represent the current optimal path length, and its initial value is set to . Define a path length calculation function to obtain the total length by accumulating the segment - by - segment Euclidean distance of the path:

[0022] wherein represents the path node coordinates, N represents the number of nodes, represents the Euclidean distance;

[0023] When sampling a target point according to the initial target sampling probability to generate a new candidate path , calculate the length of the new candidate path through the path length calculation function. If is less than , then use to update value, and synchronously update the target sampling probability :

[0024] , wherein, represents the straight-line distance between the starting node and the target node ;

[0025] Generate a random number between 0 and 1 , if , then use the target node as the sampling point; otherwise, perform random sampling within the elliptical sampling region to obtain a sampling point; during each iterative calculation, if it is found that the current path length is less than the updated after the previous iteration, use the current shortest path to update the parameters of the elliptical sampling region .

[0026] In an embodiment of the present invention, the candidate cost :

[0027] , wherein, represents the path length from node to the starting node, represents the second node and node ;

[0028] In an embodiment of the present invention, the obstacle data includes obstacle type, obstacle information, and obstacle quantity, and the acquisition method is as follows:

[0029] When the obstacle is a circular obstacle, the obstacle information further includes the center point coordinates and radius of the circular obstacle. Within the search radius, if the distance from the current node to the center point of the circular obstacle satisfies the condition, the obstacle quantity is incremented by 1; wherein, represents the search radius, represents the radius of the circular obstacle;

[0030] When the obstacle is a polygonal obstacle, the obstacle information includes the coordinates of each vertex on the surface of the polygonal obstacle. Within the search radius, if the distance from the current node to any vertex of the polygonal obstacle satisfies the condition, the obstacle quantity is incremented by 1; wherein, Indicates the search radius.

[0031] In an embodiment of the present invention, the obstacle data further includes obstacle density , and its calculation method is:

[0032] , wherein, represents the total number of obstacles.

[0033] In an embodiment of the present invention, according to the obstacle data, the method for dynamically adjusting the step size of the end of the robotic arm is as follows:

[0034] According to the obstacle density , dynamically adjust the step size of the end of the robotic arm , and its calculation formula is:

[0035] , wherein, represents the minimum step size in the obstacle-dense area, represents the maximum step size in the obstacle-sparse area.

[0036] In an embodiment of the present invention, in S3, the method for obtaining the final path is as follows:

[0037] Taking the nodes of the initial path as interpolation points, setting the smoothing factor of the curve to control the curve bending degree, interpolating the line segments between adjacent nodes to generate a continuous curve, replacing the original discrete node path, and generating a smoothed initial path;

[0038] Taking each node in the smoothed initial path as the center, generating a candidate offset point set using polar coordinate parameterization :

[0039] Setting the initial offset and the offset angle interval , that is, generating 1 direction every to generate the number of directions K and the corresponding angle set ;

[0040] For each direction , the offset point coordinates are: , forming a candidate offset point set ;

[0041] For the candidate offset point set , preferentially screening the offset point with the shortest distance to the target node : , represents the offset point and the target node the Euclidean distance between;

[0042] Meanwhile, the offset point satisfies the constraint conditions, including the spatial occupancy legality constraint condition and the line segment collision detection constraint condition, where the spatial occupancy legality constraint condition is: the offset point satisfies the unobstructed occupancy condition: , where represents the spatial occupancy area of the i-th obstacle, represents the set of total spatial occupancy areas of m obstacles;

[0043] The line segment collision detection constraint condition is: Define the penultimate node of the path as , ensure that the node and the node the connecting line segment between has no intersection with the obstacle set: , m represents the total number of obstacles;

[0044] If the current offset point does not satisfy the constraint conditions, the offset amount increases in a set geometric sequence to generate a new set of offset points, and adaptively increases the search area radius for determining the target node ;

[0045] When any node enters the search area of the target node, and at the same time satisfies that the angle between the path direction from the previous node of the node to the node and the direction from the node to the target node is less than the preset angle threshold, the final path is obtained.

[0046] In an embodiment of the present invention, the method for adaptively increasing the search area radius for determining the target node is as follows:

[0047] , where, represents the initial target node area radius, max_iter represents the maximum number of iterations, represents the current number of iterations.

[0048] In an embodiment of the present invention, the calculation method of the angle is as follows:

[0049] , where, represents the path direction vector from the previous node of the current node to the current node, represents the direction vector from the current node to the target node.

[0050] Based on the same inventive concept, the present invention also provides a robotic arm path planning system with adaptive adjustment based on environmental parameters. The robotic arm path planning system with adaptive adjustment based on environmental parameters includes the following modules:

[0051] An initialization module, which is used to take the current position of the end of the robotic arm as the starting node, the position where the target object to be grasped is located as the target node, and construct a random tree containing the path nodes between the starting node and the target node starting from the starting node. In the random tree, a search radius is set centered on each current node, and obstacle data within this range is dynamically obtained;

[0052] A path generation module, which is used to dynamically adjust the step size of the end of the robotic arm according to the obstacle data, and at the same time introduce an adaptive sampling strategy. When selecting the parent node of a new node, it preferentially selects the nearby node with the minimum total cost and no collision, and reconnects the surrounding nodes to generate an initial path;

[0053] A path optimization module, which is used to smooth the initial path, reduce the turning points in the initial path, dynamically adjust the path offset points, preferentially select the offset points that are close to the target node and have no collision, and obtain the final path by optimizing the search area of the target node and constraining the angle between the path direction and the target node direction;

[0054] A task execution module, which is used to generate path node coordinates based on the final path, convert the path node coordinates into path coordinates in the physical coordinate system of the robotic arm, and drive the robotic arm to perform an obstacle avoidance grasping task based on the path coordinates in the physical coordinate system of the robotic arm.

[0055] The present invention also provides a computer storage medium. The computer storage medium stores a computer software product. The computer software product includes several instructions for causing a computer device to execute the robotic arm path planning method with adaptive adjustment based on environmental parameters.

[0056] The above technical solutions of the present invention have the following advantages compared with the prior art:

[0057] The present invention uses a dynamic step adjustment mechanism to flexibly change the step size according to the density of obstacles, ensure safety through detailed exploration in dense areas, and expand in large steps to improve efficiency in sparse areas; introduce an adaptive sampling strategy to dynamically adjust the sampling probability of the target point according to the current optimal path length, guide the search tree to grow quickly toward the target, and accelerate convergence; optimize the node connection and reconnection mechanism, select the parent node with the smallest total cost and no collision and reconnect the surrounding nodes to reduce the path cost; smooth and offset the preliminary path to reduce turning points, give priority to offset points near the end point and no collision, and improve the path quality; dynamically expand the radius of the end point area and combine the direction alignment constraint to improve the success rate of the end point connection. The overall solution significantly improves the efficiency of path planning, shortens the planning time, optimizes the path quality, and enhances the safety and stability in complex environments. It has the advantages of high efficiency, accuracy, safety, and strong portability, providing strong support for industrial production automation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein:

[0059] Figure 1 A schematic flow chart of a robot arm path planning method based on adaptive adjustment of environmental parameters is provided in an embodiment of the present invention;

[0060] Figure 2 A schematic diagram of the structure of a robot arm path planning system based on adaptive adjustment of environmental parameters is provided in an embodiment of the present invention;

[0061] Description of the accompanying drawings in the specification: 100, initialization module; 200, path generation module; 300, path optimization module; 400, task execution module. DETAILED DESCRIPTION

[0062] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0063] Embodiment 1:

[0064] like Figure 1 As shown, the present invention provides a robot arm path planning method based on adaptive adjustment of environmental parameters, based on an improved RRT* algorithm, to improve the efficiency of path planning, reduce planning time, optimize path quality, enhance the safety and stability of path planning in a complex obstacle environment, and meet the requirements of efficient and accurate path planning in different scenarios. Specifically, the method includes the following steps:

[0065] S1: Taking the current position of the end effector of the robotic arm as the starting node, the position where the target object to be grasped is located as the target node, starting from the starting node, constructing a random tree containing the path nodes between the starting node and the target node. In the random tree, with each current node as the center, set a search radius, and dynamically obtain the obstacle data within this range;

[0066] S2: According to the obstacle data, dynamically adjust the step size of the end of the robotic arm. At the same time, introduce an adaptive sampling strategy. When selecting the parent node of the new node, preferentially select the nearby node with the minimum total cost and no collision, and reconnect the surrounding nodes to generate an initial path;

[0067] S3: Smooth the initial path to reduce the turning points in the initial path, dynamically adjust the path offset point, preferentially select the offset point that is close to the target node and has no collision. By optimizing the search area of the target node and constraining the angle between the path direction and the target node direction, obtain the final path;

[0068] S4: Based on the final path, generate the path node coordinates, convert the path node coordinates into the path coordinates in the physical coordinate system of the robotic arm, and based on the path coordinates in the physical coordinate system of the robotic arm, drive the robotic arm to perform the obstacle avoidance grasping task.

[0069] Further, in S1, take the current pose of the end effector of the robotic arm as the starting node , define the spatial coordinates of the target object to be grasped as , when the random tree is initialized, it only contains a single root node , and is independently initialized as the target state of path planning and is not included in the initial node set. Taking as the root node, construct a random tree containing the path nodes between the starting node and the target node. In the tree structure, with each current node as the center, set a search radius , and dynamically obtain the obstacle data within this range, where the obstacle data includes obstacle type, obstacle information, obstacle quantity, and obstacle density. The acquisition method is as follows:

[0070] When the obstacle is a circular obstacle, the obstacle information also includes the center point coordinates and radius of the circular obstacle. Within the search radius , if the distance from the current node to the center point of the circular obstacle satisfies the condition of , the quantity of the obstacle is incremented by 1; where represents the radius of the circular obstacle;

[0071] When the obstacle is a polygonal obstacle, the obstacle information includes the coordinates of each vertex on the surface of the polygonal obstacle, and within the search radius, the distance from the current node to any vertex of the polygonal obstacle Meet When the condition of is satisfied, the number of obstacles is incremented by 1.

[0072] Specifically, according to the total number of obstacles obtained by statistics , calculate the obstacle density , and its formula is as follows:

[0073] .

[0074] Furthermore, in this embodiment, in S2, to improve the efficiency and reliability of path generation in a complex environment, a method for generating an initial path by guiding the search direction through dynamic sampling probability, combining an adaptive step size and a global reconnection mechanism is as follows:

[0075] S21: Calculate the straight-line path length between the starting node and the target node, calculate the target sampling probability according to the straight-line path length and the current path length, and generate a sampling point according to the target sampling probability, including:

[0076] Set the global variable Indicates the current optimal path length, and its initial value is set to , define the path length calculation function , and obtain the total length by accumulating the Euclidean distance of path segments:

[0077] , Among them, Indicates the path node coordinates, N indicates the number of nodes, Indicates the Euclidean distance;

[0078] When sampling the target point according to the initial target sampling probability To generate a new candidate path , calculate the length of the new candidate path through the path length calculation function , if Is less than , then use To update Value, and synchronously update the target sampling probability :

[0079] ;

[0080] Generate a random number between 0 and 1 , if , then use the target node as the sampling point; otherwise, perform random sampling within the elliptical sampling area to obtain a sampling point; during each iterative calculation, if it is found that the current path length is less than that after the previous iterative update , use the current shortest path to update the parameters of the elliptical sampling area as follows:

[0081] During the first iteration, the elliptical sampling area uses the initial path length as the major axis 2a, and the focal length 2c is determined by the Euclidean distance between the starting and ending points:

[0082]

[0083]

[0084] At this time, the elliptical sampling area is defined as: , where X is the sampling point;

[0085] If it is found during each iteration that the current path length is less than that after the previous iterative update , then update the parameters of the elliptical sampling area according to the following rules:

[0086]

[0087] At this time, the elliptical sampling area shrinks to:

[0088] , where k represents the number of iterations.

[0089] S22: Find the first node in the random tree that is closest to the sampling point , and expand a step length from the first node to the sampling point to generate a second node

[0090] . This step length is dynamically adjusted according to the obstacle density. When the obstacles are dense, the step length is reduced for fine exploration, and when they are sparse, the step length is increased for accelerated expansion; Specifically, according to the obstacle density , dynamically adjust the step length

[0091] of the end of the robotic arm , and its calculation formula is: represents the minimum step length in the dense obstacle area,

[0092] represents the maximum step length in the sparse obstacle area;S23: Traverse the first node and the second node to check if there are obstacles on the path between them:

[0093] If yes, return to S21 for resampling;

[0094] If no, proceed to step S24;

[0095] S24: Centered at the second node , obtain a set of neighbor nodes within an area of an integer multiple of the step size (such as a circular area with a radius of ). For each node in the set of neighbor nodes , calculate the total cost of each node to the second node : :

[0096] , where represents the path length between node and the starting node, represents the path length between the second node and node ;

[0097] S25: From the set of neighbor nodes , select the node with the minimum total cost and a collision-free path as the parent node of the second node . Add the second node to the random tree, and update the path cost of the second node to:

[0098] , where represents the path length between node and the starting node, represents the path length between the second node and node ;

[0099] S26: Traverse all nodes within a radius r around the second node , calculate the candidate cost of passing through each node to the second node . If and the path is collision-free, update the parent node of node to , and synchronously update the node The node cost of ; Among them, the candidate cost is calculated as follows:

[0100] , Among them, represents the path length between node and the starting node, represents the second node and node ;

[0101] S27: Repeat steps S21~S26 until the termination condition is met (such as finding a feasible node within the neighborhood of the target node or reaching the maximum number of iterations), and finally generate an initial path including node coordinates and path costs.

[0102] Furthermore, in this embodiment, in S3, the method to obtain the final path is as follows:

[0103] Using the node set of the initial path as interpolation control points, sample the cubic spline interpolation algorithm with the belt tension parameter for path smoothing:

[0104] For adjacent nodes and , construct a parametric spline curve , , satisfying: , ;

[0105] The tangent vector is controlled by the tension parameter : ,

[0106] , where , degenerates to a natural spline when enhances the tangent continuity when

[0107] Generate a smooth curve point set through equidistant sampling, replace the original discrete node path, reduce the number of path turning points from n - 1 to a theoretically continuously differentiable smooth curve, and generate a smoothed initial path;

[0108] Using each node in the smoothed initial path as the center, generate a candidate offset point set using polar coordinate parameterization:

[0109] Set the initial offset Unit, offset angle interval = 45°), that is, generate 1 direction every 45°, and the number of generated directions K = 8, and the corresponding angle set .

[0110] For each direction , the offset point coordinates are: , forming a set of candidate offset points ;

[0111] Adopt a goal - oriented heuristic search strategy and perform the following operations on the set of candidate offset points :

[0112] Give priority to screening the offset point with the shortest distance to the target node : , represents the Euclidean distance between the offset point and the target node ;

[0113] At the same time, the offset point satisfies the constraint conditions, including the legal occupancy constraint condition of space and the line segment collision detection constraint condition. Among them, the legal occupancy constraint condition of space is: the offset point satisfies the unobstructed occupancy condition: , where represents the space occupancy area of the i - th obstacle, represents the set of total space occupancy areas of m obstacles;

[0114] The line segment collision detection constraint condition is: define the penultimate node of the path as , and ensure that the connection line segment between the node and the node has no intersection with the obstacle set: , m represents the total number of obstacles.

[0115] If the current offset point does not satisfy the constraint conditions, the offset amount increases according to a geometric sequence , generating a new set of offset points, is the number of increments, represents the initial offset amount, represents the offset amount after the k - th increment;

[0116] At the same time, adaptively increase the search area radius for determining entry into the target node:

[0117] , where, represents the initial target node area radius, and max_iter represents the maximum number of iterations. represents the current number of iterations; this formula ensures that the search domain shrinks exponentially as the iteration progresses and focuses on the target point at the end.

[0118] When any node enters the search area of the target node the path direction vector of the current node is defined the target direction vector is the previous node of the current node, and calculate the path direction from the previous node of this node to this node and the angle between the direction from this node to the target node :

[0119] where represents the path direction vector from the previous node of the current node to this node, represents the direction vector from the current node to the target node;

[0120] Set a preset angle threshold In this embodiment when then confirm that the current path is the final path; when insert an intermediate node at the end of the path is the step coefficient, and adjust the search area of the target node to an elliptical search area:

[0121] where the major axis and the minor axis is the scaling coefficient to guide the path to converge towards the target node.

[0122] Through the above smoothing processing, offset adjustment and direction constraint, a final path that is collision-free, smooth and precisely aligned with the target is generated, meeting the engineering application requirements of the robotic arm for obstacle avoidance and grasping.

[0123] Embodiment 2:

[0124] As Figure 2 shown, based on the same inventive concept as Embodiment 1, the present invention also provides a robotic arm path planning system based on adaptive adjustment of environmental parameters, specifically including the following modules: an initialization module 100, a path generation module 200, a path optimization module 300, and a task execution module 400;

[0125] Among them, the initialization module 100 is used to take the current position of the end of the robotic arm as the starting node, the position where the target object to be grasped is located as the target node, and construct a random tree including the path nodes between the starting node and the target node starting from the starting node. In the random tree, a search radius is set centered on each current node, and obstacle data within this range is dynamically obtained;

[0126] The path generation module 200 is used to dynamically adjust the step size of the end of the robotic arm according to the obstacle data. At the same time, an adaptive sampling strategy is introduced. When selecting the parent node of a new node, the nearby node with the smallest total cost and no collision is preferentially selected, and the surrounding nodes are reconnected to generate an initial path;

[0127] The path optimization module 300 is used to smooth the initial path, reduce the turning points in the initial path, dynamically adjust the path offset point, preferentially select the offset point that is close to the target node and has no collision, and obtain the final path by optimizing the search area of the target node and constraining the angle between the path direction and the target node direction;

[0128] The task execution module 400 is used to generate path node coordinates based on the final path, convert the path node coordinates into path coordinates in the physical coordinate system of the robotic arm, and drive the robotic arm to perform an obstacle avoidance grasping task based on the path coordinates in the physical coordinate system of the robotic arm.

[0129] A robotic arm path planning system based on adaptive adjustment of environmental parameters proposed in this embodiment is used to implement the aforementioned robotic arm path planning method based on adaptive adjustment of environmental parameters. Therefore, the specific implementation manners in the robotic arm path planning system based on adaptive adjustment of environmental parameters can be seen in the embodiment part of the aforementioned robotic arm path planning method based on adaptive adjustment of environmental parameters. For example, the initialization module 100, the path generation module 200, the path optimization module 300, and the task execution module 400 are respectively used to correspondingly implement steps S1, S2, S3, and S4 in the robotic arm path planning method based on adaptive adjustment of environmental parameters in Embodiment 1. Therefore, its specific implementation manners can refer to the descriptions of the corresponding respective embodiment parts. To avoid redundancy, they will not be elaborated here.

[0130] Embodiment 3:

[0131] The present invention also provides a computer storage medium, which stores a computer software product. The computer software product includes several instructions for causing a computer device to execute the robotic arm path planning method based on adaptive adjustment of environmental parameters described in Embodiment 1.

[0132] Those skilled in the art will understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on 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.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the processes and / or Figure 1 blocks.

[0134] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the processes and / or Figure 1 blocks.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the processes and / or Figure 1 blocks.

[0136] Obviously, the above embodiments are only examples given for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or variations can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or variations derived therefrom are still within the protection scope of the present invention.

Claims

1. A robotic arm path planning method based on adaptive adjustment of environmental parameters, characterized in that, It includes the following steps: S1: Taking the current position of the end of the robotic arm as the starting node, the position where the target object to be grasped is located as the target node, starting from the starting node, constructing a random tree containing the path nodes between the starting node and the target node. In the random tree, with each current node as the center, set a search radius, and dynamically obtain the obstacle data within this range; S2: According to the obstacle data, dynamically adjust the step size of the end of the robotic arm. At the same time, introduce an adaptive sampling strategy. When selecting the parent node of the new node, preferentially select the nearby node with the minimum total cost and no collision, and reconnect the surrounding nodes to generate an initial path; S3: Smooth the initial path to reduce the turning points in the initial path, dynamically adjust the path offset point, preferentially select the offset point that is close to the target node and has no collision. By optimizing the search area of the target node and constraining the angle between the path direction and the target node direction, obtain the final path; S4: Based on the final path, generate the path node coordinates, convert the path node coordinates into the path coordinates in the physical coordinate system of the robotic arm, and based on the path coordinates in the physical coordinate system of the robotic arm, drive the robotic arm to perform the obstacle avoidance grasping task.

2. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 1, wherein In S2, the method for generating the initial path is as follows: S21: Calculate the straight-line path length between the starting node and the target node, calculate the target sampling probability according to the straight-line path length and the current path length, and generate a sampling point according to the target sampling probability; S22: Find the first node closest to the sampling point in the random tree , starting from the first node , extend a step length towards the sampling point to generate a second node ; S23: Traverse the first node and the second node to check if there are obstacles on the path between them: If so, return to S21 for resampling; If not, enter step S24; S24: Traverse the second node in the step length area that is an integer multiple of , and obtain the neighbor node set . For each node in the neighbor node set , calculate the total cost from each node to the second node ， Among them, represents the path length between the node and the starting node, represents the second node and the node between the path lengths; S25: Select the total cost with the minimum value and a collision-free path as the parent node of the second node , and add the second node to the random tree, and update the path cost of the second node to be: ， Among them, represents the path length between the node and the starting node, represents the second node and the node the path length between; S26: traverse the second node All nodes within the radius r , calculation through each node The second node Candidate cost ,like And the path has no collision, update the node The parent node is , and update the node The node cost is ; S27: Repeat steps S21 - S26 to obtain the initial path.

3. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 2, wherein, In S21, the method for calculating the target sampling probability according to the straight-line path length and the current path length and generating a sampling point according to the target sampling probability is as follows: Set global variables Indicates the current optimal path length, and its initial value is set to , define the path length calculation function , obtain the total length by accumulating the Euclidean distances of path segments: ， Among them, represents the path node coordinates, N represents the number of nodes, represents the Euclidean distance; When sampling target points according to the initial target sampling probability to generate a new candidate path calculate the length of the new candidate path through the path length calculation function If is less than then use to update and synchronously update the value of the target sampling probability as follows: ​ ， Among them, represents the straight-line distance between the starting node and the target node; Generate a random number between 0 and 1 , if , then use the target node as the sampling point; otherwise, perform random sampling within the elliptical sampling region to obtain a sampling point; in each iterative calculation, if it is found that the current path length is less than the updated after the previous iteration, use the current shortest path to update the parameters of the elliptical sampling region .

4. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 2, wherein The candidate cost is calculated as follows: ， Among them, represents the path length between the node and the starting node, represents the second node and the node between the path lengths.

5. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 1, wherein The obstacle data includes the obstacle type, obstacle information, and the number of obstacles. The method for obtaining it is as follows: When the obstacle is a circular obstacle, the obstacle information further includes the center point coordinates and radius of the circular obstacle. Within the search radius, if the distance from the current node to the center point of the circular obstacle satisfies the condition, the number of obstacles is incremented by 1; where represents the search radius, represents the radius of the circular obstacle; When the obstacle is a polygonal obstacle, the obstacle information includes the coordinates of each vertex on the surface of the polygonal obstacle, and within the search radius, the distance from the current node to any vertex of the polygonal obstacle Meet When the condition of is satisfied, the number of obstacles is incremented by 1; where Represents the search radius 6. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 5, wherein The obstacle data further includes obstacle density , and the calculation method thereof is as follows: ， Among them, represents the total number of obstacles.

7. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 6, wherein The method for dynamically adjusting the step size of the end of the robotic arm according to the obstacle data is as follows: According to the obstacle density , dynamically adjust the step size of the end of the robotic arm , and its calculation formula is: ， Among them, represents the minimum step size in the area with dense obstacles, represents the maximum step size in the area with sparse obstacles.

8. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 1, wherein, In S3, the method for obtaining the final path is as follows: Taking the nodes of the initial path as interpolation points, set the smoothing factor of the curve to control the degree of curve bending, interpolate the line segments between adjacent nodes to generate a continuous curve, replace the original discrete node path, and generate the smoothed initial path; For each node in the smoothed initial path as the center, a candidate offset point set is generated using polar coordinate parameterization : Set the initial offset and the offset angle interval , that is, every generate 1 direction, generate the number of directions K, and the corresponding angle set ; For each direction , the offset point coordinates are: , forming a candidate offset point set ; For the set of candidate offset points , preferentially screen the offset point with the shortest distance to the target node : , denotes the Euclidean distance between the offset point and the target node ; Meanwhile, the offset point satisfies the constraint conditions, including the spatial occupancy legality constraint condition and the line segment collision detection constraint condition, where the spatial occupancy legality constraint condition is: the offset point satisfies the unobstructed occupancy condition: , where represents the spatial occupancy area of the i-th obstacle; represents the set of the total spatial occupancy areas of m obstacles; The line segment collision detection constraint is: Define the penultimate node of the path as , to ensure that the and the between the connection line segment has no intersection with the obstacle set: , where m represents the total number of obstacles; If the current offset point does not meet the constraint condition, the offset increases in an increasing geometric progression as set, a new set of offset points is generated, and the search area radius for determining entry into the target node is adaptively increased ; When any node enters the search area of the target node, and at the same time satisfies that the angle between the path direction from the previous node of the node to the node and the direction from the node to the target node is less than the preset angle threshold, the final path is obtained.

9. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 8, wherein The method for adaptively increasing and determining the search area radius of the target node is as follows: ， Among them, represents the radius of the initial target node area, and max_iter represents the maximum number of iterations, represents the current number of iterations.

10. The robotic arm path planning method based on adaptive adjustment according to environmental parameters as claimed in claim 8, wherein, The included angle is calculated as follows: ， Among them, represents the path direction vector from the previous node of the current node to the current node, represents the direction vector from the current node to the target node.

11. A robotic arm path planning system based on adaptive adjustment of environmental parameters, characterized in that, The robotic arm path planning system based on adaptive adjustment according to environmental parameters includes the following modules: Initialization module, which is used to take the current position of the end of the robotic arm as the starting node, the position where the target object to be grasped is located as the target node, starting from the starting node, constructing a random tree containing the path nodes between the starting node and the target node. In the random tree, with each current node as the center, set a search radius, and dynamically obtain the obstacle data within this range; Path generation module, which is used to dynamically adjust the step size of the end of the robotic arm according to the obstacle data. At the same time, introduce an adaptive sampling strategy. When selecting the parent node of the new node, preferentially select the nearby node with the minimum total cost and no collision, and reconnect the surrounding nodes to generate an initial path; The path optimization module is used to smooth the initial path, reduce the turning points in the initial path, dynamically adjust the path offset points, preferentially select the offset points that are close to the target node and have no collision, and obtain the final path by optimizing the search area of the target node and constraining the angle between the path direction and the target node direction; The task execution module is used to generate path node coordinates based on the final path, convert the path node coordinates into path coordinates in the physical coordinate system of the robotic arm, and drive the robotic arm to perform an obstacle avoidance grasping task based on the path coordinates in the physical coordinate system of the robotic arm.

12. A computer storage medium, characterized in that, The computer storage medium stores a computer software product, and the computer software product includes a number of instructions for causing a computer device to execute the robotic arm path planning method based on adaptive adjustment of environmental parameters according to any one of claims 1 to 10.

Images