Robot path planning method based on improved artificial potential field method

Abstract

This invention relates to a robot path planning method based on an improved artificial potential field method. The main steps include: defining a gravitational potential field function, a virtual potential field function, and a repulsive potential field function; calculating the gravitational, virtual, and repulsive forces acting on the robot based on these functions, and then calculating the resultant force on the robot; optimizing the robot's step size using a particle swarm optimization algorithm, and determining the robot's next position based on the optimal step size; if the obtained next position allows the robot to reach the target position, then the path planning ends; if the robot gets stuck in a local minimum, the virtual target position is updated, and the robot's next position is recalculated, thereby encouraging the robot to escape the local minimum. This invention effectively solves the problems of traditional artificial potential field methods easily getting stuck in local minima and the target position being unreachable, enabling the robot to reach the target position with the optimal path in complex environments with multiple obstacles.

Description

Technical Field

[0001] This invention relates to the field of robot path planning methods, and in particular to a robot path planning method based on an improved artificial potential field method. Background Technology

[0002] The research, development, manufacturing, and application of robots, such as industrial robots, service robots, and special-purpose robots, are important indicators of a country's technological innovation and manufacturing level. Robot path planning, a key technology in robotics, aims to search for the optimal path from the starting position to the target position for the robot based on certain performance indicators, such as distance, time, and energy.

[0003] The artificial potential field method, with its advantages of simple mathematical form, low computational cost, and smooth path planning, is widely used in obstacle avoidance path planning for robots. In obstacle avoidance path planning, the artificial potential field method abstracts the robot's working environment into a potential field. The target position exerts an attractive force on the robot, while obstacles exert a repulsive force. Under the combined action of these forces, the robot moves towards its target position. However, the traditional artificial potential field method has two insurmountable drawbacks: first, the robot is prone to getting stuck in local minima; second, when obstacles exist near the target position, the robot cannot continue to approach the target position after reaching the vicinity. These drawbacks limit the effectiveness of the traditional artificial potential field method in robot obstacle avoidance path planning. Summary of the Invention

[0004] Therefore, it is necessary to provide a robot path planning method based on an improved artificial potential field method to address the above-mentioned technical problems.

[0005] To achieve the above objectives, the present invention provides a robot path planning method based on an improved artificial potential field method, specifically comprising the following steps:

[0006] Step 1: Initialize the parameters of the artificial potential field method and determine the robot's initial position X0 and target position X0. g The total number of obstacles m and the position X of the j-th obstacle j j = 1, 2, ..., m;

[0007] Step 2: Define the gravitational potential field function U a Virtual potential function U v and repulsive potential field function U r ;

[0008] Step 3: Set the robot's virtual target position X v Let X be the robot's current position.

[0009] Step 4: Based on the gravitational potential field function Ua Virtual potential function U v and repulsive potential field function U r Calculate the gravitational force acting on the robot Virtual Gravity and repulsive force Then calculate the net force acting on the robot.

[0010] Step 5: Optimize the robot's step size x using the particle swarm optimization algorithm, and then determine the optimal step size x. * Determine the robot's next position X n ;

[0011] Step 6: Determine the next position X obtained. n Can the robot reach the target location X? g If so, the robot moves to the next position X. n If the path planning ends, proceed to step seven; otherwise, proceed to step seven.

[0012] Step 7: Determine if the robot is trapped in a local minimum. If so, the robot does not move and discards the obtained next position X. n Update the robot's virtual target position X v Return to step four; otherwise, move the robot to the next position X. n Return to step three.

[0013] Furthermore, the parameters of the artificial potential field method that need to be initialized in step one include: the gravitational coefficient K. a1 With K a2 Virtual gravitational coefficient K v Repulsion coefficient K r Gravitational threshold d a The distance d affected by obstacles r The offset distance d of the virtual target position v Target position determination parameter l, robot's minimum step size x min and maximum movement step size x max .

[0014] Furthermore, step two defines the gravitational potential field function U. a for:

[0015]

[0016] Among them, K a1 K a2 Let X be the gravitational coefficient, and X be the robot's current position. g d represents the target position of the robot. a This is the threshold of gravitational influence.

[0017] Furthermore, step two defines the virtual potential field function U. v for:

[0018]

[0019] Among them, K v Let X be the virtual gravity coefficient, and X be the robot's current position. v This is the virtual target location for the robot.

[0020] Furthermore, step two defines the repulsive potential field function U. r for:

[0021]

[0022] Among them, U r,j K represents the repulsive potential field generated by the j-th obstacle. r Let X be the repulsive force coefficient, and X be the robot's current position. g X is the target position of the robot. j Let d be the position of the j-th obstacle. r Distance is affected by obstacles.

[0023] Furthermore, step four involves calculating the gravitational force acting on the robot. Virtual Gravity Repulsive force and combined efforts The specific method is as follows:

[0024] Robot's target position X g Gravity on robots Equal to the gravitational potential field function U a The negative gradient of gravity amplitude The expression is:

[0025]

[0026] Among them, K a1 K a2 d is the gravitational coefficient. a The threshold of gravitational action; gravity The direction is from the robot's current position X to the robot's target position X. g ;

[0027] The robot's virtual target position X v Virtual gravity on robots Equal to the virtual potential field function U v Negative gradient, virtual gravity amplitude The expression is:

[0028]

[0029] Among them, K v For virtual gravity coefficients; virtual gravity The direction is from the robot's current position X to the robot's virtual target position X. v ;

[0030] The repulsive force of the j-th obstacle on the robot Equal to the repulsive potential field U generated by the j-th obstacle r,j The negative gradient, repulsive force amplitude The expression is:

[0031]

[0032] Among them, K r d is the repulsion coefficient. r The distance affected by obstacles; the repulsive force of the j-th obstacle on the robot. The direction is determined by the position X of the j-th obstacle. j Points to the robot's current position X;

[0033] The net force acting on the robot Gravity acting on the robot Virtual Gravity and repulsive force The summation yields the following expression:

[0034]

[0035] Furthermore, the specific steps of step five, which uses the particle swarm optimization algorithm to optimize the robot's movement step size x, are as follows:

[0036] Step 1: Initialize the parameters of the particle swarm optimization algorithm, define the fitness function, set the position and update rate of the first generation of particles, establish the first generation of particle swarm, and set the iteration number i = 0;

[0037] Step 2: Calculate the fitness of each particle in the initial particle swarm based on the fitness function, and select the individual best particle and the global best particle.

[0038] Step 3: Calculate the update rate of the next generation of particles based on the individual optimal particles and the global optimal particles;

[0039] Step 4: Calculate the position of the next generation of particles based on the position of the current generation of particles and the renewal rate of the next generation of particles;

[0040] Step 5: Let i = i + 1, calculate the fitness of each particle in the new generation of particle swarm according to the fitness function, and select the individual best particle and the global best particle.

[0041] Step 6: Determine if the iteration termination condition is met. If so, the position of the globally optimal particle is the robot's optimal movement step size x. * If the iteration terminates, return to step 3; otherwise, return to step 3.

[0042] Furthermore, step six determines the obtained next position X. n Make the robot reach the target position X g The condition is: X g -X n ≤l, where l is the target position determination parameter.

[0043] Furthermore, the condition for determining in step seven that the robot is trapped in a local minimum is: the distance between the robot's current position X and a previous position is less than or equal to the robot's minimum step size x. min A number of integer multiples thereof.

[0044] Furthermore, in step seven, when the robot gets stuck in a local minimum, a point on the perpendicular bisector of the line connecting the robot's current position and the target position is selected, and this point is used to update the virtual target position X. v Updated virtual target location X v Solve by solving the following equations simultaneously:

[0045]

[0046] Where, d v This represents the offset distance of the virtual target position.

[0047] The technical solution provided by this invention has the following beneficial effects:

[0048] This invention improves upon the gravitational and repulsive potential field functions of the traditional artificial potential field method. It introduces a virtual target position and defines a virtual potential field function, enabling the robot to move towards the target position under the combined influence of gravity, virtual gravity, and repulsion. When the robot becomes trapped in a local minimum, the virtual target position is updated, and the robot's next position is recalculated, thus motivating the robot to escape the local minimum. This invention overcomes the shortcomings of the traditional artificial potential field method, such as its susceptibility to local minima and the unreachability of the target position, enabling the robot to reach the target position with the optimal path in complex environments with multiple obstacles. Attached Figure Description

[0049] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0050] Figure 1 This is a flowchart of a robot path planning method based on an improved artificial potential field method in an embodiment of the present invention;

[0051] Figure 2 This is an example diagram illustrating the robot's motion tasks and working environment in an embodiment of the present invention;

[0052] Figure 3 This is an example of a robot getting stuck at a local minimum point under the traditional artificial potential field method.

[0053] Figure 4 This is a graph showing the change in the net force acting on a robot when it gets stuck in a local minimum position using the traditional artificial potential field method.

[0054] Figure 5 This is an example of a robot target position being unreachable under the traditional artificial potential field method.

[0055] Figure 6 This is a graph showing the change of the net force on the robot when the target position is unreachable under the traditional artificial potential field method.

[0056] Figure 7 This is a graph showing the global optimal particle fitness as a function of the number of iterations when optimizing the robot's step size in a certain embodiment of the present invention.

[0057] Figure 8 This is an example diagram of the robot path planning results in an embodiment of the present invention;

[0058] Figure 9 This is a graph showing the change in the net force acting on the robot in an embodiment of the present invention. Detailed Implementation

[0059] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0060] In this embodiment, the research object is a six-degree-of-freedom robotic arm. The present invention is used to plan an optimal path for the robotic arm from the starting position to the target position without collision.

[0061] In this embodiment, a robot path planning method based on an improved artificial potential field method is described, with the following specific steps: Figure 1 As shown, it includes:

[0062] Step 1: Initialize the parameters of the artificial potential field method and determine the robot's initial position X0 and target position X0. g The total number of obstacles m and the position X of the j-th obstacle j j = 1, 2, ..., m;

[0063] Step 2: Define the gravitational potential field function U a Virtual potential function U v and repulsive potential field function U r ;

[0064] Step 3: Set the robot's virtual target position X v Let X be the robot's current position.

[0065] Step 4: Based on the gravitational potential field function U a Virtual potential function U v and repulsive potential field function U r Calculate the gravitational force acting on the robot Virtual Gravity and repulsive force Then calculate the net force acting on the robot.

[0066] Step 5: Optimize the robot's step size x using the particle swarm optimization algorithm, and then determine the optimal step size x. * Determine the robot's next position X n ;

[0067] Step 6: Determine the next position X obtained. n Can the robot reach the target location X? g If so, the robot moves to the next position X. n If the path planning ends, proceed to step seven; otherwise, proceed to step seven.

[0068] Step 7: Determine if the robot is trapped in a local minimum. If so, the robot does not move and discards the obtained next position X. n Update the robot's virtual target position X v Return to step four; otherwise, move the robot to the next position X. n Return to step three.

[0069] In this embodiment, the robot's motion task and working environment are as follows: Figure 2 As shown, the robot's starting position is X0(0,0,0), and the robot's target position is X. g The number of obstacles is (100, 100, 100), the total number of obstacles is m = 6, and the positions of the obstacles are X1(20, 20, 20), X2(35, 28, 30), X3(47, 45, 47), X4(58, 50, 60), X5(70, 75, 75), X6(87, 80, 80); the obstacles are all spheres with radii R1 = 3, R2 = 3, R3 = 3.4, R4 = 3.5, R5 = 2.7, and R6 = 5.3.

[0070] Specifically, the parameters for initializing the artificial potential field method in step one include: the gravitational coefficient K. a1 With K a2 Virtual gravitational coefficient K v Repulsion coefficient K r Gravitational threshold da The distance d affected by obstacles r The offset distance d of the virtual target position v Target position determination parameter l, robot's minimum step size x min and maximum movement step size x max .

[0071] In this embodiment, the gravitational coefficient K a1 =35, K a2 =35, virtual gravitational coefficient K v =20, repulsion coefficient K r =20, gravitational threshold d a =315, the distance d affected by the obstacle r =10, the offset distance d of the virtual target v =5, target position determination parameter l = 0.25, robot's minimum step size x min =1, maximum movement step size x max =2.

[0072] It should be noted that the specific values ​​of the above parameters are only a preferred example of the present invention. In other embodiments, the specific values ​​can be adjusted according to the actual situation.

[0073] Specifically, step two defines the gravitational potential field function U. a for:

[0074]

[0075] Among them, K a1 K a2 Let X be the gravitational coefficient, and X be the robot's current position. g d represents the target position of the robot. a This is the threshold of gravitational influence.

[0076] Specifically, step two defines the virtual potential field function U. v for:

[0077]

[0078] Among them, K v Let X be the virtual gravity coefficient, and X be the robot's current position. v This is the virtual target location for the robot.

[0079] Specifically, step two defines the repulsive potential field function U. r for:

[0080]

[0081] Among them, U r,jK represents the repulsive potential field generated by the j-th obstacle. r Let X be the repulsive force coefficient, and X be the robot's current position. g X is the target position of the robot. j Let d be the position of the j-th obstacle. r Distance is affected by obstacles.

[0082] Specifically, step four calculates the gravitational force acting on the robot. Virtual Gravity Repulsive force and combined efforts The specific method is as follows:

[0083] Robot's target position X g Gravity on robots Equal to the gravitational potential field function U a The negative gradient of gravity amplitude The expression is:

[0084]

[0085] Among them, K a1 K a2 d is the gravitational coefficient. a The threshold of gravitational action; gravity The direction is from the robot's current position X to the robot's target position X. g ;

[0086] The robot's virtual target position X v Virtual gravity on robots Equal to the virtual potential field function U v Negative gradient, virtual gravity amplitude The expression is:

[0087]

[0088] Among them, K v For virtual gravity coefficients; virtual gravity The direction is from the robot's current position X to the robot's virtual target position X. v ;

[0089] The repulsive force of the j-th obstacle on the robot Equal to the repulsive potential field U generated by the j-th obstacle r,j The negative gradient, repulsive force amplitude The expression is:

[0090]

[0091] Among them, K r d is the repulsion coefficient. r The distance affected by obstacles; the repulsive force of the j-th obstacle on the robot. The direction is determined by the position X of the j-th obstacle. j Points to the robot's current position X;

[0092] The net force acting on the robot Gravity acting on the robot Virtual Gravity and repulsive force The summation yields the following expression:

[0093]

[0094] Specifically, step five, which uses the particle swarm optimization algorithm to optimize the robot's step size x, involves the following steps:

[0095] Step 1: Initialize the parameters of the particle swarm optimization algorithm, define the fitness function, set the position and update rate of the first generation of particles, establish the first generation of particle swarm, and set the iteration number i = 0;

[0096] Step 2: Calculate the fitness of each particle in the initial particle swarm based on the fitness function, and select the individual best particle and the global best particle.

[0097] Step 3: Calculate the update rate of the next generation of particles based on the individual optimal particles and the global optimal particles;

[0098] Step 4: Calculate the position of the next generation of particles based on the position of the current generation of particles and the renewal rate of the next generation of particles;

[0099] Step 5: Let i = i + 1, calculate the fitness of each particle in the new generation of particle swarm according to the fitness function, and select the individual best particle and the global best particle.

[0100] Step 6: Determine if the iteration termination condition is met. If so, the position of the globally optimal particle is the robot's optimal movement step size x. * If the iteration terminates, return to step 3; otherwise, return to step 3.

[0101] In this embodiment, the particle swarm size is set to 50, the maximum number of iterations is 25, the inertia weight is 0.8, the self-learning factor is 0.5, and the swarm learning factor is 0.5. The position of the initial particles is in the interval [x...]. min ,x max Randomly generated, the initial particle update rate is in the interval [0.1x]. min 0.1x max Randomly generated.

[0102] In other embodiments, the specific values ​​described above may also be adjusted according to actual circumstances.

[0103] Specifically, step six determines the obtained next position X. n Make the robot reach the target position X g The condition is: |X g -X n |≤l, where l is the target position determination parameter, and in this embodiment, l=0.25 is preferred.

[0104] Specifically, step seven determines that the robot is trapped in a local minimum: the distance between the robot's current position X and a previous position is less than or equal to the robot's minimum step size x. min A number of integer multiples thereof.

[0105] In this embodiment, the distance between the robot's current position X and the position 7 steps before the current position is less than or equal to the robot's minimum step size x. min If the value is 4 times that of the robot, the robot will get stuck in a local minimum.

[0106] Specifically, in step seven, when the robot gets stuck in a local minimum, a point on the perpendicular bisector of the line connecting the robot's current position and the target position is selected, and the virtual target position X is updated using this point's position. v Updated virtual target location X v Solve by solving the following equations simultaneously:

[0107]

[0108] Where, d v This represents the offset distance of the virtual target position.

[0109] Traditional artificial potential field methods are prone to causing robots to get stuck in local minima. Figure 2 The robot's motion task and working environment are shown, and the traditional artificial potential field method is used for robot path planning, such as... Figure 3 As shown, after moving 30 steps, the robot gets stuck in a local minimum near obstacle 1. It will move back and forth between the two points marked by the triangle in the diagram, preventing it from escaping the local minimum and continuing towards the target position. The change in the amplitude of the net force acting on the robot when it gets stuck in the local minimum is as follows: Figure 4 As shown, when the robot gets stuck in a local minimum, the magnitude of the net force acting on the robot will fluctuate between two values, but in opposite directions.

[0110] Another drawback of the traditional artificial potential field method is that when there are obstacles near the robot's target location, the robot cannot continue to approach the target location after reaching the vicinity. Figure 2In the robot's motion task and working environment shown, after the robot is stimulated to escape the local minimum point near obstacle 1 using the method of this invention, the traditional artificial potential field method is still used for robot path planning, such as... Figure 5 As shown, due to the presence of obstacle 6 near the robot's target location, after reaching the vicinity of the target location, the robot will move back and forth between the two points marked by the rhombus in the diagram, unable to continue approaching the target location; the change in the amplitude of the net force acting on the robot when the target location is unreachable is as follows. Figure 6 As shown.

[0111] The application results of the method of the present invention in this embodiment are as follows: Figure 7-9 As shown; Figure 7 The graph shows the change in the global optimal particle fitness with the number of iterations when optimizing the robot's step size in a certain step. The global optimal particle fitness gradually decreases and converges, indicating that the particle swarm optimization algorithm can obtain the optimal step size for the robot, enabling it to reach the target position faster. Figure 2 The robot's motion task and working environment are shown, and the method of this invention is used for robot path planning, such as... Figure 8 As shown, the robot did not get stuck in a local minimum near obstacle 1. Even if there is obstacle 6 near the robot's target position, the robot can still reach the target position. Figure 9 The changes in the amplitude of the net force acting on the robot during its movement are shown. In summary, this invention can effectively overcome the shortcomings of traditional artificial potential field methods, which are prone to getting stuck in local minima and making the target position unreachable, enabling the robot to reach the target position with the optimal path in complex environments with multiple obstacles.

[0112] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0113] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In the unit claims listing several devices, several of these devices may be embodied by the same hardware item. The use of the terms first, second, and third, etc., does not indicate any order and can be interpreted as identifiers.

[0114] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A robot path planning method based on an improved artificial potential field method, characterized in that, The specific steps are as follows: Step 1: Initialize the parameters of the artificial potential field method and determine the robot's initial position X0 and target position X0. g The total number of obstacles m and the position X of the j-th obstacle j j = 1, 2, ..., m; Step 2: Define the gravitational potential field function U a Virtual potential function U v and repulsive potential field function U r ; Step 3: Set the robot's virtual target position X v Let X be the robot's current position. Step 4: Based on the gravitational potential field function U a Virtual potential function U v and repulsive potential field function U r Calculate the gravitational force acting on the robot Virtual Gravity and repulsive force Then calculate the net force acting on the robot. Step 5: Optimize the robot's step size x using the particle swarm optimization algorithm, and then determine the optimal step size x. * Determine the robot's next position X n ; Step 6: Determine the next position X obtained. n Can the robot reach the target location X? g If so, the robot moves to the next position X. n If the path planning ends, proceed to step seven; otherwise, proceed to step seven. Step 7: Determine if the robot is trapped in a local minimum. If so, the robot does not move and discards the obtained next position X. n Update the robot's virtual target position X v Return to step four; otherwise, move the robot to the next position X. n Return to step three; Step four involves calculating the gravitational force acting on the robot. Virtual Gravity repulsion and combined efforts The specific method is as follows: Robot's target position X g Gravity on robots Equal to the gravitational potential field function U a The negative gradient of gravity amplitude The expression is: Among them, K a1 K a2 d is the gravitational coefficient. a The threshold of gravitational action; gravity The direction is from the robot's current position X to the robot's target position X. g ; The robot's virtual target position X v Virtual gravity on robots Equal to the virtual potential field function U v Negative gradient, virtual gravity amplitude The expression is: Among them, K v For virtual gravity coefficients; virtual gravity The direction is from the robot's current position X to the robot's virtual target position X. v ; The repulsive force of the j-th obstacle on the robot Equal to the repulsive potential field U generated by the j-th obstacle r,j The negative gradient, repulsive force amplitude The expression is: Among them, K r d is the repulsion coefficient. r The distance affected by obstacles; the repulsive force of the j-th obstacle on the robot. The direction is determined by the position X of the j-th obstacle. j Points to the robot's current position X; The net force acting on the robot Gravity acting on the robot Virtual Gravity and repulsive force The summation yields the following expression: The condition for determining in step seven that the robot is trapped in a local minimum is: the distance between the robot's current position X and a previous position is less than or equal to the robot's minimum step size x. min Several integer multiples of; In step seven, when the robot gets stuck in a local minimum, a point on the perpendicular bisector of the line connecting the robot's current position and the target position is selected, and the virtual target position X is updated using this point. v Updated virtual target location X v Solve by solving the following equations simultaneously: Where, d v This represents the offset distance of the virtual target position.

2. The robot path planning method based on the improved artificial potential field method according to claim 1, characterized in that, The parameters for initializing the artificial potential field method in step one include: the gravitational coefficient K. a1 With K a2 Virtual gravitational coefficient K v Repulsion coefficient K r Gravitational threshold d a The distance d affected by obstacles r The offset distance d of the virtual target position v Target position determination parameter l, robot's minimum step size x min and maximum movement step size x max .

3. The robot path planning method based on the improved artificial potential field method according to claim 1, characterized in that, Step two defines the gravitational potential field function U. a for: Among them, K a1 K a2 Let X be the gravitational coefficient, and X be the robot's current position. g The target position for the robot, d a This is the threshold of gravitational influence.

4. The robot path planning method based on the improved artificial potential field method according to claim 1, characterized in that, Step two defines the virtual potential field function U. v for: Among them, K v Let X be the virtual gravity coefficient, and X be the robot's current position. v This is the virtual target location for the robot.

5. The robot path planning method based on the improved artificial potential field method according to claim 1, characterized in that, Step two defines the repulsive potential field function U. r for: Among them, U r,j K represents the repulsive potential field generated by the j-th obstacle. r Let X be the repulsive force coefficient, and X be the robot's current position. g X is the target position of the robot. j Let d be the position of the j-th obstacle. r Distance is affected by obstacles.

6. The robot path planning method based on the improved artificial potential field method according to claim 1, characterized in that, The specific steps of step five, which uses the particle swarm optimization algorithm to optimize the robot's movement step size x, are as follows: Step 1: Initialize the parameters of the particle swarm optimization algorithm, define the fitness function, set the position and update rate of the first generation of particles, establish the first generation of particle swarm, and set the iteration number i = 0; Step 2: Calculate the fitness of each particle in the initial particle swarm based on the fitness function, and select the individual best particle and the global best particle. Step 3: Calculate the update rate of the next generation of particles based on the individual optimal particles and the global optimal particles; Step 4: Calculate the position of the next generation of particles based on the position of the current generation of particles and the renewal rate of the next generation of particles; Step 5: Let i = i + 1, calculate the fitness of each particle in the new generation of particle swarm according to the fitness function, and select the individual best particle and the global best particle. Step 6: Determine if the iteration termination condition is met. If so, the position of the globally optimal particle is the robot's optimal movement step size x. * If the iteration terminates, return to step 3; otherwise, return to step 3.

7. The robot path planning method based on the improved artificial potential field method according to claim 1, characterized in that, Step six determines the next position X. n Make the robot reach the target position X g The condition is: |X g -X n |≤l, where l is the target position determination parameter.

Images