Energy optimization method, device and medium for robotic arm based on improved grey wolf algorithm

Abstract

The present invention discloses a method, device, and medium for optimizing the energy of a robotic arm based on an improved gray wolf algorithm, relating to the field of robotic arm motion technology. The method comprises: obtaining information on the starting point, end point, and obstacles of the robotic arm; using a path planning method to determine a feasible path for the robotic arm based on the starting point, end point, and obstacle information of the robotic arm; constructing a robotic arm energy optimization model with the goal of minimizing the impact received during the robotic arm's motion and the maximum time allowed for the robotic arm to operate as a constraint; solving the robotic arm energy optimization model using an improved gray wolf algorithm to obtain a time distribution of the robotic arm's joint states; and optimizing the feasible path of the robotic arm based on the time distribution of the robotic arm's joint states to obtain the optimal joint trajectory of the robotic arm. The present invention can reduce the energy loss of the robotic arm during task execution and extend the service life of the robotic arm.

Description

Technical Field

[0001] The present invention belongs to the field of robotic arm motion technology and relates to the optimization of the joint space trajectory of a robotic arm, and in particular to a robotic arm energy optimization method, device and medium based on an improved grey wolf algorithm. Background Art

[0002] Existing algorithms for robot path planning primarily include the A* algorithm and the probabilistic sampling algorithm. The discrete points generated by these algorithms need to be continuousized using interpolation methods. Common interpolation methods include cubic terms, quintic terms, and B-spline curves. However, these methods suffer from insufficient energy optimization and low computational efficiency. This can lead to high costs and shortened robot lifespans in industrial production. Parameters in interpolation methods must be optimized to achieve optimal energy performance to ensure production quality and control costs. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device and medium for optimizing the energy of a robotic arm based on an improved grey wolf algorithm, so as to reduce the energy loss of the robotic arm during task execution and extend the service life of the robotic arm.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A robotic arm energy optimization method based on an improved grey wolf algorithm, comprising:

[0006] Get the starting point, end point and obstacle information of the robotic arm;

[0007] A path planning method is used to determine a feasible path of the robotic arm based on the starting point, end point and obstacle information of the robotic arm; the feasible path of the robotic arm includes a sequence of discrete points of joint states of all joints of the robotic arm;

[0008] With the goal of minimizing the impact on the robot during movement and the maximum operating time allowed for the robot as a constraint, an energy optimization model for the robot is constructed.

[0009] The improved grey wolf algorithm is used to solve the energy optimization model of the robotic arm to obtain the joint state time distribution of the robotic arm; the joint state time distribution of the robotic arm includes the time intervals between discrete points of the joint states of all joints of the robotic arm;

[0010] The feasible path of the robotic arm is optimized according to the time distribution of the joint states of the robotic arm to obtain the optimal joint trajectory of the robotic arm.

[0011] Optionally, the expression of the robotic arm energy optimization model is:

[0012]

[0013] Among them, f(X n ) is the impact received by the robot during its movement, θ i is the discrete point of the i-th joint state, θ i+1 is the i+1th joint state discrete point, X i is the time interval between the discrete points of the i-th joint state and the i+1-th joint state, T max is the maximum time allowed for the robot to run, and n is the total number of discrete points in the joint state.

[0014] Optionally, an improved grey wolf algorithm is used to solve the energy optimization model of the robotic arm to obtain the time distribution of the joint states of the robotic arm, specifically including:

[0015] Initialize the number of iterations, the number of wolves in the pack, and the position of each individual gray wolf in the pack;

[0016] Calculate the fitness values ​​of the gray wolf individuals, take the top three gray wolf individuals as the three alpha wolves, and take the position of the gray wolf individual with the best fitness value as the optimal solution;

[0017] Calculate the distance between the individual gray wolf and the three alpha wolves based on the distance calculation coefficient, and update the position of the individual gray wolf based on the position update coefficient;

[0018] Updating the distance calculation coefficient and the position update coefficient using a random number and a convergence factor;

[0019] Determine whether the maximum number of iterations has been reached;

[0020] If the maximum number of iterations has not been reached, return to the step of calculating the fitness values ​​of the gray wolf individuals, taking the gray wolf individuals with the top three fitness values ​​as the three alpha wolves, and taking the position of the gray wolf individual with the best fitness value as the optimal solution;

[0021] If the maximum number of iterations is reached, the optimal solution is used as the joint state time distribution of the robotic arm.

[0022] Optionally, the distance between the individual gray wolf and the three alpha wolves is calculated based on the distance calculation coefficient. The specific formula is:

[0023]

[0024] Among them, D α is the distance between the gray wolf and the first wolf, D β is the distance between the gray wolf and the second wolf, D γ is the distance between the gray wolf and the third wolf, C1, C2 and c3 are distance calculation coefficients, w α is the position of the first wolf, W β is the position of the second wolf, W γis the position of the third wolf, and w is the position of the individual gray wolf.

[0025] Optionally, the position of the individual gray wolf is updated according to the position update coefficient. The specific formula is:

[0026]

[0027] Among them, W t+1 is the updated position of the gray wolf individual, w1 is the best position near the first wolf, w2 is the best position near the second wolf, w3 is the best position near the third wolf, A1, A2 and A3 are all position update coefficients.

[0028] Optionally, a random number and a convergence factor are used to update the distance calculation coefficient and the position update coefficient. The specific formula is:

[0029] A=2a·r1-a;

[0030] C = 2·r2;

[0031] a=2e -t / T ;

[0032] Where A is the position update coefficient, C is the distance calculation coefficient, a is the convergence factor, r1 and r2 are both random numbers between 0 and 1, e is the base of the natural logarithm, t is the current number of iterations, and T is the maximum number of iterations.

[0033] Optionally, the path planning method is a fast search random tree algorithm.

[0034] A computer device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the mechanical arm energy optimization method based on the improved grey wolf algorithm.

[0035] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the robotic arm energy optimization method based on the improved grey wolf algorithm.

[0036] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0037] The present invention provides a method for optimizing the energy of a robotic arm based on an improved gray wolf algorithm. The method takes minimizing the impact on the robotic arm during movement as the goal and the maximum time allowed for the robotic arm to operate as the constraint. A robotic arm energy optimization model is constructed, and the improved gray wolf algorithm is used to solve the robotic arm energy optimization model to obtain the time distribution of the joint states of the robotic arm, so that the robotic arm can complete the movement within the specified time and with minimal energy loss, thereby extending the service life of the robotic arm. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 Flowchart of the robotic arm energy optimization method based on the improved grey wolf algorithm provided by the present invention;

[0040] Figure 2 A comparison chart of the optimization results of the Grey Wolf Algorithm and the Improved Grey Wolf Algorithm provided by the present invention;

[0041] Figure 3 This is a comparison chart of the trajectories of the six joints of the robotic arm provided by the present invention before and after optimization. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] A path is a route from a starting point to a destination, and trajectory planning involves determining the time between each step along that path. The challenge of trajectory planning for a robotic arm is to determine how to align time and path so that the robotic arm achieves optimal energy, time, and loss along a specified path. Currently, widely used optimization algorithms include linear programming, genetic algorithms, and particle swarm optimization. The goal of this invention is to calculate a robotic arm trajectory so that it completes its movement within a specified timeframe with minimal energy loss, thereby extending the robotic arm's service life.

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0045] like Figure 1 As shown, the robotic arm energy optimization method based on the improved gray wolf algorithm provided by the present invention includes:

[0046] Step 1: Get the starting point, end point, and obstacle information of the robotic arm.

[0047] Step 2: Using a path planning method, determine a feasible path for the robotic arm based on the starting point, end point, and obstacle information of the robotic arm. The feasible path of the robotic arm includes a sequence of discrete points of joint states for all joints of the robotic arm. The joint states specifically refer to the rotation angles of the joints, i.e., the joint angles.

[0048] Preferably, the path planning method is a Rapidly-exploring Random Tree (RRT) algorithm.

[0049] Step 3: With the goal of minimizing the impact on the robot during movement and the maximum time allowed for the robot to operate as a constraint, a robot energy optimization model is constructed.

[0050] The trajectory of the robot arm is planned using cubic polynomial interpolation between two discrete points. The angle function is:

[0051] θ(t)=a1t 3 +a2t 2 +a3t 1 +a4

[0052] Where θ(t) is the rotation angle of the robot arm joint, and a1, a2, a3, and a4 are all unknown coefficients of the angle function. The velocity function is derived as follows:

[0053] v(t)=3a1t 2 +2a2t 1 +a3

[0054] Given the initial and final positions and the initial and final velocities, the simultaneous equations are:

[0055]

[0056] Among them, θ i is the discrete point of the i-th joint state, i.e. the initial position, θ i+1 is the i+1th joint state discrete point, that is, the end position, X i is the time interval between the discrete points of the i-th joint state and the i+1-th joint state, that is, the time required from the starting point to the end point. The solution is:

[0057]

[0058] a3=0

[0059] a4=θ i

[0060] According to the robot arm impact calculation method, the cumulative square of the third derivative of the angle is used as the impact, and the objective function is designed as:

[0061]

[0062] Given that θ(t)=a1t 3 +a2t 2 +a3t 1 +a4, then after derivation:

[0063]

[0064] Known but:

[0065]

[0066] The impact f(X n )for:

[0067]

[0068] So the optimization problem is described as:

[0069]

[0070] Among them, T max is the maximum allowed time for the robot arm to operate, and n is the total number of discrete joint states. The optimization problem aims to minimize the impact of the robot arm during movement and find the time distribution of each trajectory within the maximum allowed time for the robot arm to operate, that is, the time interval between the discrete joint states of all joints of the robot arm.

[0071] Step 4: Use the improved grey wolf algorithm to solve the energy optimization model of the robotic arm to obtain the joint state time distribution of the robotic arm. The joint state time distribution of the robotic arm includes the time intervals between the discrete joint state points of all joints of the robotic arm.

[0072] The Gray Wolf Algorithm (GWA) mimics the survival of a wolf pack, which has a strict hierarchy. The alpha (optimal solution) is assigned to α, the second (suboptimal solution) to β, the third (suboptimal solution) to γ, and the rest to ω. ω follows the three alpha wolves as they forage, finding the three best solutions each time. It then searches around these three solutions, finding three better solutions to update the values ​​of α, β, and γ.

[0073] During hunting, the distance between individual wolves and their prey is defined as:

[0074] D=|C·W p (t)-W(t)|

[0075] The update formula for individual wolves is as follows:

[0076] W(t+1)=W p(t)-A·D

[0077] Where t is the current iteration number, C and A are coefficients that change according to random factors, C is called the distance calculation coefficient, and A is called the position update coefficient. The coefficient vector is defined as follows:

[0078] A=2a·r1-a

[0079] C=2·r2

[0080] Among them, W p is the position of the prey, W is the position of the wolf, a is the convergence factor, which is a factor that gradually converges from 2 to 0, and r1 and r2 are both random numbers between 0 and 1. The convergence equation of a is:

[0081] a=2e -t / T

[0082] Where T is the maximum number of iterations, t is the current number of iterations, and e is the base of the natural logarithm. This equation improves the linear function of the traditional gray wolf algorithm into a nonlinear convergence function, which is more consistent with the wolf pack hunting process. When the gray wolf identifies the prey's location, it follows the leader's α, β, and γ to surround the prey. The distance between the gray wolf and the leader is defined as follows:

[0083] D α =|C1·W α -W|

[0084] D β =|C2·W β -W|

[0085] D γ =|C3·W γ -W|

[0086] Among them, D α is the distance between the gray wolf and the first wolf, D β is the distance between the gray wolf and the second wolf, D γ is the distance between the gray wolf and the third wolf. C1, C2, and C3 are distance calculation coefficients. Subscripts 1, 2, and 3 correspond to the three alpha wolves, respectively. W α is the position of the first wolf, W β is the position of the second wolf, W γ is the position of the third wolf, and W is the position of the individual gray wolf.

[0087] Update the position of the gray wolf according to the following formula:

[0088] W1=W α -A1·(D α )

[0089] W2=W β-A2·(D β )

[0090] W3=W γ -A3·(D γ )

[0091]

[0092] Among them, W t+1 is the updated position of the gray wolf individual, W1 is the optimal position near the first wolf, W2 is the optimal position near the second wolf, and W3 is the optimal position near the third wolf. A1, A2, and A3 are all position update coefficients, and the subscripts 1, 2, and 3 correspond to the three alpha wolves, respectively.

[0093] The overall algorithm flow is as follows:

[0094] (1) Initialize the number of iterations, the number of wolves in the pack, and the position of each individual gray wolf in the pack; the position of each individual gray wolf in the pack is randomly distributed within a desirable range, which includes the time intervals X = X1, X2, ..., X between the discrete points of the joint states of all joints of the manipulator. n .

[0095] (2) According to the formula Calculate the fitness values ​​of the gray wolf individuals, take the top three gray wolf individuals as the three alpha wolves, and take the position of the gray wolf individual with the best fitness value as the optimal solution.

[0096] (3) Calculate the distance between the gray wolf and the three alpha wolves based on the distance calculation coefficient, and update the position of the gray wolf based on the position update coefficient. The updated position is

[0097] (4) Using random numbers and convergence factors, the distance calculation coefficient C=2·r2 and the position update coefficient A=2a·r1-a are updated.

[0098] (5) Determine whether the maximum number of iterations has been reached; if not, return to step (2); if the maximum number of iterations has been reached, use the optimal solution as the joint state time distribution of the robotic arm.

[0099] Step 5: Optimize the feasible path of the robotic arm according to the time distribution of the joint states of the robotic arm to obtain the optimal joint trajectory of the robotic arm.

[0100] A specific embodiment is provided below to further illustrate the above technical solution in detail.

[0101] The DH table method is used to model the robotic arm. The UR5 robotic arm is used as an example model. The DH parameters of the UR5 robotic arm are shown in Table 1.

[0102] Table 1 DH parameter table of UR5 robot arm

[0103] <![CDATA[a k (mm)]]> <![CDATA[α k (rad)]]> <![CDATA[d k (mm)]]> <![CDATA[θ k ]]> 1 0 π / 2 89.15 <![CDATA[θ 1 ]]> 2 -425 0 0 <![CDATA[θ 2 ]]> 3 -392.25 0 0 <![CDATA[θ 3 ]]> 4 0 π / 2 109.15 <![CDATA[θ 4 ]]> 5 0 -π / 2 94.65 <![CDATA[θ 5 ]]> 6 0 0 82.30 <![CDATA[θ 6 ]]>

[0104] Among them, a k is the connecting rod length, α k is the connecting rod torsion angle, d k is the connecting rod offset, θ k is the joint angle, and k is the joint number of the robotic arm.

[0105] Step 1: The path planning method of the robot arm uses the RRT algorithm. The working environment of the robot arm is a three-dimensional space of 5m×5m×5m. The starting point is (0°, 0°, 0°, 0°, 0°, 0°), and the target point is (180°, -30°, -60°, 180°, 90°, 90°). The angles in brackets refer to the rotation angles of each joint of the robot arm. The specific process of the RRT algorithm is as follows: Given the starting point x init , end point x goal and obstacle information, randomly sample a point x within the map range rand , search for x on the existing path tree rand The nearest node x nearest , from x nearest To x rand Extend the specified step size to get the new point x new , for x new and x nearest And the middle line for collision detection, if the collision detection is successful, x new Add to the path tree and add x nearest Set as its parent node. If the collision detection fails, discard point x new Repeat the above random sampling steps, x new Pass collision detection and reach x goal When nearby, from x goal Start searching for the parent node until x is found init The feasible path is obtained. The planning obtains a series of discrete points, and the energy loss can be minimized by interpolating between the discrete points by solving the robotic arm energy optimization model using the improved gray wolf algorithm.

[0106] The expression of the robotic arm energy optimization model is as follows:

[0107]

[0108] Step 2: The optimization algorithm parameters are set as follows: number of iterations N = 1000; number of wolf packs n = 20; T max = 50. The optimization result is the time consumed between each joint state, that is, the time interval between the discrete points of the joint state Xi , transform the constraint condition into a penalty function and add it to the fitness function calculation, that is, if Then f(X n ) is infinite. The Grey Wolf Algorithm and the Improved Grey Wolf Algorithm are used to solve the time distribution of the minimum impact of the manipulator to complete the task under the total task time limit. The results are as follows Figure 2 As shown, the trajectories of the six joints before and after optimization using the improved gray wolf algorithm are as follows Figure 3 shown.

[0109] from Figure 2 It can be seen from the figure that when the number of iterations is 180, the fitness value of the improved gray wolf algorithm tends to be stable. Figure 3 As can be seen from the figure, the optimized angle curves for each joint have become smoother, reducing sudden angle fluctuations. The optimization results are significant, reducing energy consumption and extending the lifespan of the robotic arm. The optimization method determined the trajectory that minimizes impact on the robotic arm within a specified timeframe. If the time is evenly distributed between each step within the specified timeframe, the impact is 1.3348. After optimization, the impact is reduced to 0.249, a reduction of 81.35%.

[0110] In summary, compared with the prior art, the present invention has the following advantages:

[0111] 1. The energy optimization method for a robotic arm based on the improved grey wolf algorithm provided by the present invention adjusts the time interval according to the discrete points of path planning, thereby reducing the energy loss of the robotic arm in performing tasks.

[0112] 2. The robotic arm energy optimization method based on the improved gray wolf algorithm provided by the present invention modifies the convergence factor equation, which is faster than the traditional linear convergence factor in capturing prey and improving the convergence speed of the optimization algorithm.

[0113] 3. The robotic arm energy optimization method based on the improved grey wolf algorithm provided by the present invention makes the robotic arm trajectory smoother and extends the service life of the robotic arm.

[0114] In one embodiment, a computer program product is further provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0115] In one embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0116] In one embodiment, a computer device is further provided, including a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented.

[0117] Furthermore, the computer device also includes an input / output interface (I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store pending transactions. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments are implemented.

[0118] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards.

[0119] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but are not limited to these.

[0120] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A robotic arm energy optimization method based on an improved grey wolf algorithm, characterized in that: include: Get the starting point, end point and obstacle information of the robotic arm; A path planning method is used to determine a feasible path for the robotic arm based on the starting point, end point and obstacle information of the robotic arm; The feasible path of the robotic arm includes a sequence of discrete points of joint states of all joints of the robotic arm; With the goal of minimizing the impact on the robot during movement and the maximum operating time allowed for the robot as a constraint, an energy optimization model for the robot is constructed. The expression is: Among them, f(X n ) is the impact received by the robot during its movement, θ i is the discrete point of the i-th joint state, θ i+1 is the i+1th joint state discrete point, X i is the time interval between the discrete points of the i-th joint state and the i+1-th joint state, T max is the maximum time allowed for the robot to run, and n is the total number of discrete points of joint states; The improved grey wolf algorithm is used to solve the energy optimization model of the robotic arm to obtain the time distribution of the joint states of the robotic arm, specifically including: Initialize the number of iterations, the number of wolves in the pack, and the position of each individual gray wolf in the pack; Calculate the fitness values ​​of the gray wolf individuals, take the top three gray wolf individuals as the three alpha wolves, and take the position of the gray wolf individual with the best fitness value as the optimal solution; Calculate the distance between the individual gray wolf and the three alpha wolves based on the distance calculation coefficient, and update the position of the individual gray wolf based on the position update coefficient; Updating the distance calculation coefficient and the position update coefficient using a random number and a convergence factor; Determine whether the maximum number of iterations has been reached; If the maximum number of iterations has not been reached, return to the step of calculating the fitness values ​​of the gray wolf individuals, taking the gray wolf individuals with the top three fitness values ​​as the three alpha wolves, and taking the position of the gray wolf individual with the best fitness value as the optimal solution; If the maximum number of iterations is reached, the optimal solution is used as the joint state time distribution of the robotic arm; the joint state time distribution of the robotic arm includes the time intervals between discrete points of the joint states of all joints of the robotic arm; The feasible path of the robotic arm is optimized according to the time distribution of the joint states of the robotic arm to obtain the optimal joint trajectory of the robotic arm.

2. The method for optimizing the energy of a robotic arm based on the improved grey wolf algorithm according to claim 1, characterized in that: The distance between the individual gray wolf and the three alpha wolves is calculated using the distance calculation coefficient. The specific formula is: D α =|C1·W α -W| D β =|C2·W β -W|; D γ =|C3·W γ -W| Among them, D α is the distance between the gray wolf and the first wolf, D β is the distance between the gray wolf and the second wolf, D γ is the distance between the gray wolf and the third wolf, C1, C2 and C3 are distance calculation coefficients, W α is the position of the first wolf, W β is the position of the second wolf, W γ is the position of the third wolf, and W is the position of the individual gray wolf.

3. The method for optimizing the energy of a robotic arm based on the improved grey wolf algorithm according to claim 2, characterized in that: Update the position of the individual gray wolf according to the position update coefficient. The specific formula is: W1=W α -A1·(D α ) <h2 style=";text-align:left;direction:ltr">W2=W<h2 style=";text-align:left;direction:ltr"> β <h2 style=";text-align:left;direction:ltr"> -A2·(D<h2 style=";text-align:left;direction:ltr"> β <h2 style=";text-align:left;direction:ltr"> ) <h2 style=";text-align:left;direction:ltr">W3=W<h2 style=";text-align:left;direction:ltr"> γ <h2 style=";text-align:left;direction:ltr"> -A3·(D<h2 style=";text-align:left;direction:ltr"> γ <h2 style=";text-align:left;direction:ltr"> ); Among them, W t+1 is the updated position of the gray wolf individual, W1 is the best position near the first wolf, W2 is the best position near the second wolf, W3 is the best position near the third wolf, A1, A2 and A3 are all position update coefficients.

4. The method for optimizing the energy of a robotic arm based on the improved grey wolf algorithm according to claim 3, characterized in that: The distance calculation coefficient and the position update coefficient are updated using a random number and a convergence factor. The specific formula is: A=2a·r1-a; C＝2·r2； a=2e -t / T ; Where A is the position update coefficient, C is the distance calculation coefficient, a is the convergence factor, r1 and r2 are both random numbers between 0 and 1, e is the base of the natural logarithm, t is the current number of iterations, and T is the maximum number of iterations.

5. The method for optimizing the energy of a robotic arm based on the improved grey wolf algorithm according to claim 1, characterized in that: The path planning method is a fast search random tree algorithm.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the robotic arm energy optimization method based on the improved grey wolf algorithm as described in any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the robot arm energy optimization method based on the improved grey wolf algorithm as described in any one of claims 1 to 5 is implemented.

Images