Mechanical arm intelligent motion planning method based on A*and genetic hybrid optimization algorithm

Abstract

A mechanical arm intelligent motion planning method based on an A * and genetic hybrid optimization algorithm comprises the steps that a mechanical arm kinematics model is established, a limited environment model is established, mechanical arm tail end obstacle avoidance trajectory planning is carried out based on the A * algorithm, inverse kinematics solution is carried out on a mechanical arm, a joint angle in a motion trajectory is obtained, collision detection is carried out, and if collision occurs, the mechanical arm is subjected to robot motion planning. The joint angle of the motion trail of the mechanical arm is optimized through a genetic algorithm, then trapezoidal speed interpolation is conducted, and the optimal motion trail of the mechanical arm is obtained; if no collision exists, trapezoidal speed interpolation is directly carried out, and the optimal motion trail of the mechanical arm is obtained; the system, the equipment and the medium are used for realizing the mechanical arm intelligent motion planning method based on the A * and genetic hybrid optimization algorithm. The problem that in the prior art, the collision possibility of an obstacle and a mechanical arm connecting rod is not considered is solved; and the planning efficiency and the path safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robot arm motion planning algorithms, and in particular to a robot arm intelligent motion planning method based on an A* and genetic hybrid optimization algorithm. Background Art

[0002] For a seven-degree-of-freedom robotic arm, there can generally be multiple trajectories from the starting position to the target position. How to autonomously plan an optimal collision-free path from these trajectories through constraints is the difficulty of intelligent motion planning of the robotic arm.

[0003] Obstacle avoidance trajectory planning can be divided into two categories. The first category is local planning algorithm, also known as obstacle space method. Classic methods include artificial potential field method. The key of this method is to determine the functional expression of gravitational field and repulsive field. The second category is search-type trajectory planning algorithm. The core of search-type trajectory planning algorithm is to build a model of environmental space. The main idea is to divide the task space into grids, regard grids without obstacles as searchable path sets, and grids with obstacles as unreachable positions. As long as the divided grid is large enough, the final path can be obtained, such as commonly used search algorithms: A* algorithm, Dijkstra algorithm, D* algorithm, etc.

[0004] For a robot in three-dimensional space, the search-based trajectory planning algorithm can only ensure that the end of the robot follows the planned trajectory, but does not consider the possibility of collision between obstacles and the robot's connecting rod. Therefore, when planning the motion of the end of the robot, it is necessary to optimize the robot's joint configuration and avoid obstacles to obtain a safe robot motion trajectory. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the purpose of the present invention is to propose a method for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm. Through the situation where the robotic arm connecting rod may collide with an obstacle, on the basis of the search-type trajectory planning A* algorithm, a genetic algorithm is used to take the minimum distance between the robotic arm connecting rod and the obstacle as the fitness, and the joint angles with a smaller distance are eliminated. The optimized joint angles are subjected to trapezoidal velocity interpolation processing to plan a new collision-free path. The present invention improves the planning efficiency and the safety of the path.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0007] A method for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm, the method comprising:

[0008] S1, establish the kinematic model of the robot arm;

[0009] S2, establishing a constrained environment model, wherein the constrained environment model includes N obstacles;

[0010] S3, using the robot kinematics model, in the constrained environment model, the robot end obstacle avoidance trajectory planning is performed based on the A* algorithm to obtain the robot arm motion trajectory;

[0011] S4, according to the motion trajectory of the robot arm, solving the inverse kinematics of the robot arm to obtain the joint angles in the motion trajectory of the robot arm;

[0012] S5, in the constrained environment model, collision detection is performed on the joint angles in the motion trajectory of the robot arm. If any link collides with an obstacle during the motion of the robot arm, S6 is executed. If none of the links collide with an obstacle during the motion of the robot arm, S7 is executed.

[0013] S6, using genetic algorithm to optimize the joint angles in the robot arm motion trajectory;

[0014] S7, perform gradient velocity interpolation on the joint angles to obtain the optimal motion trajectory of the robotic arm.

[0015] The kinematic model of the robot arm is expressed as:

[0016] 0 T i = 0 T1 1 T2… i-1 T i =f(Θ),

[0017]

[0018] in, 0 T i represents the pose matrix of the end of the robot relative to the base, i represents the number of joint angles of the robot, Θ represents the joint angle of the robot, n = [nx, ny, nz] T 、o=[ox,oy,oz] T 、a=[ax,ay,az] T Respectively represent the unit vectors of the x, y, and z axes of the terminal coordinate system in the base coordinate system {x0, y0, z0}, p = [px, py, pz] T The position vector of the origin of the end coordinate system relative to the base coordinate system.

[0019] The establishing of the restricted environment model comprises:

[0020] S2-1, set the initial position of the end of the robot arm to

[0021] S2-2, set the desired position of the end of the robot arm to pd = [px py pz] T ;

[0022] S2-3, randomly generate N obstacles between the initial position and the desired position to obtain a constrained environment model.

[0023] The N obstacles are N spherical envelope obstacles with a radius of R.

[0024] The robot arm kinematic model is used to perform obstacle avoidance trajectory planning at the end of the robot arm based on the A* algorithm in the constrained environment model to obtain the robot arm motion trajectory, including:

[0025] S3-1, select the evaluation function of the A* algorithm, the evaluation function is expressed as:

[0026] f(x)=g(x)+h(x),

[0027] Where f(x) represents the evaluation function, g(x) represents the actual cost of the minimum cost path from the starting node to the node x, and h(x) represents the estimated cost of the path from the x node to the target point.

[0028] S3-2, based on the robot kinematics model, defines the evaluation function, which is expressed as:

[0029]

[0030] Among them, p i represents the position of the i-th motion node, p des represents the position of the target point, 3 represents the three-dimensional space of the robot movement, g(p i ) indicates that from the previous node g(p i-l ) is added to this node;

[0031] S3-3, using the evaluation function to plan the obstacle avoidance trajectory of the end of the robot arm to obtain the movement trajectory of the robot arm.

[0032] The joint angle in the motion trajectory of the robot arm is expressed as:

[0033]

[0034] in, Represents the terminal pose, represents the joints in the robot's motion trajectory, J represents the Jacobian matrix of the robot, and J + represents the Moore-Penrose generalized inverse of J, J + =J T (JJ T ) -1 , (IJ+ J) is the null space projection matrix, Represents an arbitrary joint angular velocity vector.

[0035] The method of optimizing the joint angles in the motion trajectory of the robot arm by using a genetic algorithm comprises:

[0036] S6-1, initializing the genetic algorithm, setting the number of evolutions, the maximum number of evolutions and the number of variables, and randomly generating the number of individuals in the initial population, where the individuals are joint angles;

[0037] S6-2, selection operation, calculating the fitness of the population individuals, sorting the fitness of the population individuals, saving several population individuals with higher fitness, and deleting the others, wherein the fitness is the distance between the robot arm connecting rod and the obstacle, that is, the safety angle obtained by the genetic algorithm;

[0038] S6-3, crossover and mutation operation, setting the chromosome crossover probability, gene mutation probability and iterative evolution times, and performing crossover and mutation on the individuals in the population;

[0039] S6-4, termination condition judgment, when the number of iterative evolutions is equal to the maximum number of evolutions, the iteration is stopped, otherwise the joint angle corresponding to the individual of the last iteration is taken out and the process goes to S6-2.

[0040] A robot arm intelligent motion planning system based on A* and genetic hybrid optimization algorithm, comprising:

[0041] Kinematic model building module, to build the kinematic model of the robot arm;

[0042] A constrained environment model building module is used to build a constrained environment model, wherein the constrained environment model includes N obstacles;

[0043] The trajectory planning module uses the robot kinematics model to perform obstacle avoidance trajectory planning at the end of the robot based on the A* algorithm in the constrained environment model to obtain the robot motion trajectory;

[0044] The inverse kinematics solving module solves the inverse kinematics of the robot arm according to the robot arm motion trajectory to obtain the joint angles in the robot arm motion trajectory;

[0045] The collision detection module performs collision detection on the joint angles in the robot's motion trajectory in the constrained environment model. If any link collides with an obstacle during the robot's motion, the operation in the joint angle optimization module is executed. If none of the links collide with an obstacle during the robot's motion, the operation in the gradient velocity interpolation module is executed.

[0046] The joint angle optimization module uses genetic algorithms to optimize the joint angles in the robot's motion trajectory;

[0047] The gradient velocity interpolation module performs gradient velocity interpolation on the joint angles to obtain the optimal motion trajectory of the robotic arm.

[0048] An electronic device, comprising:

[0049] at least one processor;

[0050] and, a memory communicatively coupled to the at least one processor;

[0051] In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned methods for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm.

[0052] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements any of the above-mentioned methods for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] 1. Based on the classic search-type trajectory planning A* algorithm, the present invention performs obstacle avoidance trajectory planning for the end of the robot arm, obtains the corresponding joint angle through the inverse kinematics of the robot arm, and aims at the situation that the connecting rod may collide with the obstacle when the end of the robot arm performs trajectory tracking motion. The joint angle that affects the wrist joint of the robot arm is re-planned and designed based on the genetic algorithm. The genetic algorithm is an optimization algorithm of natural selection and genetic mechanism, which is often used to solve complex optimization problems. It searches for the optimal solution in the solution space by simulating the selection, crossover and mutation operations in the biological evolution process. It has good global search ability, is not easy to fall into the local optimum, and can obtain the optimal joint angle within the range of joint angles that the robot arm can reach.

[0055] 2. The present invention uses a spherical envelope, which expands the scope of the obstacle domain. It not only simplifies the modeling method of the obstacle domain, making it simpler and more convenient in calculation, but also can effectively improve the planning efficiency, making the entire robotic arm more conservative and safer on the obstacle avoidance path.

[0056] In summary, the present invention performs obstacle avoidance trajectory planning for the end of the robotic arm based on the search-type trajectory planning A* algorithm. When the end of the robotic arm performs trajectory tracking motion, the connecting rod may collide with an obstacle. The genetic algorithm uses the minimum distance between the robotic arm connecting rod and the obstacle as the fitness, eliminates the joint angles with a smaller distance, and performs trapezoidal velocity interpolation processing on the optimized joint angles, thereby planning a new collision-free path. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of the obstacle avoidance planning method used in the present invention.

[0058] Figure 2 Schematic diagram of the DH coordinate system of the robot arm of the present invention.

[0059] Figure 3 It is a schematic diagram of the robot arm of the present invention in a confined space.

[0060] Figure 4 This is a robot trajectory planning diagram generated based on the A* algorithm in the confined space of the present invention.

[0061] Figure 5 This is a three-dimensional diagram of the obstacle avoidance of the robotic arm before and after the joint angle optimization of the present invention.

[0062] Figure 6 This is a curve diagram of angle change after the joint angle is optimized according to the present invention.

[0063] Figure 7 This is a speed change curve diagram after the joint angle is optimized in the present invention. DETAILED DESCRIPTION

[0064] The technical solution of the present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0065] The robotic arm of this embodiment takes my country's "Tianhe" as the research object. The robotic arm is a seven-degree-of-freedom robotic arm, and its structure meets the Pieper criterion, that is, the three adjacent joint axes of the robotic arm intersect at one point, the front three axes intersect at the shoulder joint, and the rear three axes intersect at the wrist point. The rotation of the rear three axes will not affect the wrist position. The movement of the first four joints determines the wrist position and plays a major role in the position of the end of the robotic arm. The three joints of the wrist mainly determine the end posture. Based on this, the direction of the end of the robotic arm is adjusted to avoid collision with obstacles.

[0066] When simulating space obstacles, it is necessary to consider that the shapes of obstacles vary greatly, and it is difficult to establish geometric rules for collision for each special contour shape. Since obstacles always present irregular edges, even if they are complex, they can always be considered to be composed of basic shapes. Therefore, when obstacles in three-dimensional space can be modeled, a simplified model is adopted. The present invention uses a spherical envelope. This method expands the scope of the obstacle domain, not only simplifies the modeling method of the obstacle domain, but also makes it simpler and more convenient in calculation, and can effectively improve the planning efficiency, so that the entire robot arm is more conservative and safe on the obstacle avoidance path.

[0067] After planning a collision-free motion trajectory for the end of the robot arm based on the classic search-type trajectory planning A* algorithm, the joint angle information is obtained through the inverse kinematics of the robot arm, and the genetic algorithm is used to optimize the joint angles q5 and q6 that have a greater impact on the posture but a smaller impact on the position. When the robot arm collides with an obstacle on the original path, the path point where the collision occurs is recorded, and the joint angles q5 and q6 corresponding to the middle point of the path point are redesigned. The minimum distance between the robot arm link and the obstacle is used as the fitness, and the joint angles with a smaller distance are eliminated. The optimized joint configuration and the angle of the collision-free configuration are subjected to trapezoidal velocity interpolation processing, and then a new path is planned.

[0068] The following is a specific implementation scheme of this embodiment.

[0069] A robot arm intelligent motion planning method based on A* and genetic hybrid optimization algorithm, such as Figure 1 As shown, the method includes:

[0070] S1, establish the kinematic model of the robot arm, such as Figure 2 As shown, it is expressed as:

[0071] 0 T7= 0 T1 1 T2… 6 T7=f(Θ),

[0072]

[0073] in, 0 T7 represents the pose matrix of the end of the robot relative to the base, Θ = [θ1θ2θ3θ4θ5θ6θ7] represents the 7 joint angles of the robot, and n = [nx, ny, nz] T 、o=[ox,oy,oz] T 、a=[ax,ay,az] T Respectively represent the unit vectors of the x, y, and z axes of the terminal coordinate system in the base coordinate system {x0, y0, z0}, p = [px, py, pz] T The position vector of the origin of the end coordinate system relative to the base coordinate system.

[0074] DH parameters are shown in Table 1:

[0075] Table 1 DH parameters of the robot arm

[0076] Connecting rod Variable θi(°) αi(°) <![CDATA[a i (m)]]> <![CDATA[d i (m)]]> 1 90 90 0 1.7 2 90 90 0 1.8 3 0 0 10 5 4 0 0 10 0 5 -90 90 0 0 6 -90 90 0 1.8 7 180 90 0 1.7

[0077] S2, establish the constrained environment model and set relevant parameters, such as Figure 3 As shown, the restricted environment model includes N obstacles, which are expressed as:

[0078] S2-1, set the initial position of the end of the robot arm to

[0079] S2-2, set the desired position of the end of the robot arm to pd = [px py pz] T ;

[0080] S2-3, in order to simulate obstacles in space, a spherical envelope is used to simplify the obstacles, and N spherical envelope obstacles with a radius of R are randomly generated between the initial position and the expected position to obtain a restricted environment model.

[0081] S3, using the robot kinematics model, in the constrained environment model, the robot end obstacle avoidance trajectory planning is performed based on the A* algorithm to obtain the robot motion trajectory, specifically:

[0082] S3-1, the core part of the A* algorithm theory, lies in the selection and design of the evaluation function. The evaluation function is introduced when selecting the next inspection node of the current node. The evaluation function is expressed as:

[0083] f0=g(x)+h(0),

[0084] Where f(x) represents the evaluation function, g(x) represents the actual cost of the minimum cost path from the starting node to the node x, and h(x) represents the estimated cost of the path from the x node to the target point.

[0085] S3-2, based on the robot kinematics model, defines the evaluation function, which is expressed as:

[0086]

[0087] Among them, p i represents the position of the i-th motion node, p des represents the position of the target point, 3 represents the three-dimensional space of the robot movement, g(p i ) indicates that from the previous node g(p i-l ) is added to this node;

[0088] S3-3, use the evaluation function to plan the obstacle avoidance trajectory of the end of the robot arm to obtain the robot arm motion trajectory, such as Figure 4 shown.

[0089] S4, according to the motion trajectory of the robot arm, a series of continuous path point position records obtained in S3 are stored, and the inverse kinematics of the robot arm is solved to obtain the joint angles in the motion trajectory of the robot arm, which can be expressed as:

[0090]

[0091] in, Represents the terminal pose, represents the joints in the robot's motion trajectory, J represents the Jacobian matrix of the robot, and J + denotes the Moore-Penrose generalized inverse of J, J + =J T (JJ T ) -1 , (IJ + J) is the null space projection matrix, Represents an arbitrary joint angular velocity vector.

[0092] S5, design of collision detection algorithm between robot link and obstacle. In the structure of the robot, except for the bottom base of the robot, the rest of the link set is {L1, L2, L3, L4, L5, L6, L7}, assuming that the spatial obstacle is {M1, M2, M3, ... M n ,}, according to the characteristics of the robot arm task, collision detection is performed. If any link collides with an obstacle during the movement of the robot arm, "collision" is output, and S6 is executed. If all links do not collide with obstacles during the movement of the robot arm, "no collision" is output, and S7 is executed;

[0093] S6, using genetic algorithm to optimize the joint angles in the robot arm motion trajectory, specifically:

[0094] S6-1, initialization of the genetic algorithm, setting the number of evolutions g = 0, the maximum number of evolutions G = 500, randomly generating an initial population, the number of individuals in the population is N = 50, the individuals in the population are joint angles, the number of variables is 2, which are joint angles q5 and q6 respectively;

[0095] S6-2, fitness sorting and selection operation, calculate the fitness of the population individuals, sort the fitness of the population individuals, save the 50 population individuals with higher fitness, and delete the rest. The fitness is the distance between the robot arm connecting rod and the obstacle, that is, the safety angle obtained by the genetic algorithm. The fitness function is expressed as:

[0096] f(q5,q6)=min{D1,D2,D3,D4,D5,D6,D7},

[0097] Among them, D i is the distance between the i-th robot arm link and the obstacle;

[0098] S6-3, crossover mutation operation, set the chromosome crossover probability to p c =0.8, the probability of gene mutation is p m = 0.1, crossover mutation is performed on the individuals in the population, the individuals in the population increase from N = 50 to N = 100, and the iterator g = g + 1;

[0099] S6-4, termination condition judgment, when the iterative evolution times g = G, stop running, otherwise take out the joint angle corresponding to the individual of the last iteration and go to S6-2.

[0100] S7, performs gradient velocity interpolation on the joint angle to ensure the smooth operation of the robot arm and obtain the optimal motion trajectory of the robot arm. The configuration of the robot arm before and after joint optimization is as follows Figure 5 shown.

[0101] Finally, the movement of the robot arm is observed on the simulation platform, its collision with obstacles is observed, and the changes in its joint angle and velocity are recorded. S =[03.623.5], target position p d =

[13135] T For example, the robot arm joint angle and its speed change as follows Figure 6 and Figure 7 shown.

[0102] A robot arm intelligent motion planning system based on A* and genetic hybrid optimization algorithm, comprising:

[0103] Kinematic model building module, to build the kinematic model of the robot arm;

[0104] A constrained environment model building module is used to build a constrained environment model, wherein the constrained environment model includes N obstacles;

[0105] The trajectory planning module uses the robot kinematics model to perform obstacle avoidance trajectory planning at the end of the robot based on the A* algorithm in the constrained environment model to obtain the robot motion trajectory;

[0106] The inverse kinematics solving module solves the inverse kinematics of the robot arm according to the robot arm motion trajectory to obtain the joint angles in the robot arm motion trajectory;

[0107] The collision detection module performs collision detection on the joint angles in the robot's motion trajectory in the constrained environment model. If any link collides with an obstacle during the robot's motion, the operation in the joint angle optimization module is executed. If none of the links collide with an obstacle during the robot's motion, the operation in the gradient velocity interpolation module is executed.

[0108] The joint angle optimization module uses genetic algorithms to optimize the joint angles in the robot's motion trajectory;

[0109] The gradient velocity interpolation module performs gradient velocity interpolation on the joint angles to obtain the optimal motion trajectory of the robotic arm.

[0110] An electronic device, comprising:

[0111] at least one processor;

[0112] and, a memory communicatively coupled to the at least one processor;

[0113] In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned methods for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm.

[0114] A computer-readable storage medium stores a computer program, characterized in that when the computer program is executed by a processor, it implements any of the above-mentioned methods for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm.

[0115] In summary, the present invention performs obstacle avoidance trajectory planning for the end of the robotic arm based on the search-type trajectory planning A* algorithm. When the end of the robotic arm performs trajectory tracking motion, the connecting rod may collide with an obstacle. The genetic algorithm uses the minimum distance between the robotic arm connecting rod and the obstacle as the fitness, eliminates the joint angles with a smaller distance, and performs trapezoidal velocity interpolation processing on the optimized joint angles, thereby planning a new collision-free path.

[0116] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A method for intelligent motion planning of a robotic arm based on A* and genetic hybrid optimization algorithm, characterized in that: The method comprises: S1, establish the kinematic model of the robot arm; S2, establishing a constrained environment model, wherein the constrained environment model includes N obstacles; S3, using the robot kinematics model, in the constrained environment model, the robot end obstacle avoidance trajectory planning is performed based on the A* algorithm to obtain the robot arm motion trajectory; S4, according to the motion trajectory of the robot arm, solving the inverse kinematics of the robot arm to obtain the joint angles in the motion trajectory of the robot arm; S5, in the constrained environment model, collision detection is performed on the joint angles in the motion trajectory of the robot arm. If any link collides with an obstacle during the motion of the robot arm, S6 is executed. If none of the links collide with an obstacle during the motion of the robot arm, S7 is executed. S6, using genetic algorithm to optimize the joint angles in the robot arm motion trajectory; S7, perform gradient velocity interpolation on the joint angles to obtain the optimal motion trajectory of the robotic arm.

2. According to claim 1, a method for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm is characterized in that: The kinematic model of the robot arm is expressed as: 0 T i = 0 T1 1 T2… i-1 T i =f(Θ), in, 0 T i represents the pose matrix of the end of the robot relative to the base, i represents the number of joint angles of the robot, Θ represents the joint angle of the robot, n = [n x ,n y ,n z ] T 、o=[o x ,o y ,o z ] T 、a=[a x ,a y ,a z ] T Respectively represent the unit vectors of the x, y, and z axes of the terminal coordinate system in the base coordinate system {x0, y0, z0}, p = [p x ,p y ,p z ] T The position vector of the origin of the end coordinate system relative to the base coordinate system.

3. The method for intelligent motion planning of a robotic arm based on A* and genetic hybrid optimization algorithm according to claim 2, characterized in that: The establishing of the restricted environment model comprises: S2-1, set the initial position of the end of the robot arm to S2-2, set the desired position of the end of the robot arm to p d =[p x p y p z ] T ; S2-3, randomly generate N obstacles between the initial position and the desired position to obtain a constrained environment model.

4. The method for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm according to claim 3, characterized in that: The N obstacles are N spherical envelope obstacles with a radius of R.

5. The method for intelligent motion planning of a robotic arm based on A* and genetic hybrid optimization algorithm according to claim 4, characterized in that: The robot arm kinematic model is used to perform obstacle avoidance trajectory planning at the end of the robot arm based on the A* algorithm in the constrained environment model to obtain the robot arm motion trajectory, including: S3-1, select the evaluation function of the A* algorithm, the evaluation function is expressed as: f(x)=g(x)+h(x), Where f(x) represents the evaluation function, g(x) represents the actual cost of the minimum cost path from the starting node to the node x, and h(x) represents the estimated cost of the path from the x node to the target point. S3-2, based on the robot kinematics model, defines the evaluation function, which is expressed as: Among them, p i represents the position of the i-th motion node, p des represents the position of the target point, 3 represents the three-dimensional space of the robot movement, g(p i ) indicates that from the previous node g(p i-l ) is added to this node; S3-3, using the evaluation function to plan the obstacle avoidance trajectory of the end of the robot arm to obtain the movement trajectory of the robot arm.

6. The method for intelligent motion planning of a robotic arm based on A* and genetic hybrid optimization algorithm according to claim 5, characterized in that: The joint angle in the motion trajectory of the robot arm is expressed as: in, Represents the terminal pose, represents the joints in the robot's motion trajectory, J represents the Jacobian matrix of the robot, and J + represents the Moore-Penrose generalized inverse of J, J + =J T (JJ T ) -1 , (IJ + J) is the null space projection matrix, Represents an arbitrary joint angular velocity vector.

7. The method for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm according to claim 6, characterized in that: The method of optimizing the joint angles in the motion trajectory of the robot arm by using a genetic algorithm comprises: S6-1, initializing the genetic algorithm, setting the number of evolutions, the maximum number of evolutions and the number of variables, and randomly generating the number of individuals in the initial population, where the individuals are joint angles; S6-2, selection operation, calculating the fitness of the population individuals, sorting the fitness of the population individuals, saving several population individuals with higher fitness, and deleting the others, wherein the fitness is the distance between the robot arm connecting rod and the obstacle, that is, the safety angle obtained by the genetic algorithm; S6-3, crossover and mutation operation, setting the chromosome crossover probability, gene mutation probability and iterative evolution times, and performing crossover and mutation on the individuals in the population; S6-4, termination condition judgment, when the number of iterative evolutions is equal to the maximum number of evolutions, the iteration is stopped, otherwise the joint angle corresponding to the individual of the last iteration is taken out and the process goes to S6-2.

8. A robot arm intelligent motion planning system based on A* and genetic hybrid optimization algorithm, characterized in that: include: Kinematic model building module, to build the kinematic model of the robot arm; A constrained environment model building module is used to build a constrained environment model, wherein the constrained environment model includes N obstacles; The trajectory planning module uses the robot kinematics model to perform obstacle avoidance trajectory planning at the end of the robot based on the A* algorithm in the constrained environment model to obtain the robot motion trajectory; The inverse kinematics solving module solves the inverse kinematics of the robot arm according to the robot arm motion trajectory to obtain the joint angles in the robot arm motion trajectory; The collision detection module performs collision detection on the joint angles in the robot's motion trajectory in the constrained environment model. If any link collides with an obstacle during the robot's motion, the operation in the joint angle optimization module is executed. If none of the links collide with an obstacle during the robot's motion, the operation in the gradient velocity interpolation module is executed. The joint angle optimization module uses genetic algorithms to optimize the joint angles in the robot's motion trajectory; The gradient velocity interpolation module performs gradient velocity interpolation on the joint angles to obtain the optimal motion trajectory of the robotic arm.

9. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a robotic arm intelligent motion planning method based on an A* and genetic hybrid optimization algorithm as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a method for intelligent motion planning of a robotic arm based on an A* and genetic hybrid optimization algorithm as described in any one of claims 1 to 7 is implemented.

Images