Joint trajectory optimization method and device for collaborative robot

By using seven-time B-spline function and improved non-dominant sorting genetic algorithm in collaborative robots, the problem of slow local optimal solution and convergence speed in multi-objective trajectory optimization is solved, and the better trajectory planning effect is achieved, ensuring that The stability and efficiency of robot motion are achieved.

CN118990501AActive Publication Date: 2024-11-22INST OF AUTOMATION CHINESE ACAD OF SCI

Patent Information

Application Number
CN202411310981.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-11-22
Estimated Expiration
2044-09-19

AI Technical Summary

Technical Problem

In the multi-objective trajectory optimization of collaborative robots, non-dominant sorting genetic algorithms are prone to fall into local optimal solutions, with slow convergence speed and difficult to reasonably allocate weights. The diversity of solutions is insufficient, resulting in poor trajectory planning effects.

Method used

The spatial path points of the terminal mechanism of the robot arm are interpolated using the seven-time B-spline function, and the improved non-dominant sorting genetic algorithm is used to determine the control vertices of the joint trajectory. By dynamically adjusting the probability of crossing and mutation, avoiding premature convergence and optimizing multi-objective Function to obtain the Pareto optimal solution set.

Benefits of technology

The optimized robot joint trajectory has a short running time, low energy consumption, small motion impact, and excellent smoothness, ensuring the robot's motion stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118990501A_ABST
    Figure CN118990501A_ABST
Patent Text Reader

Abstract

The invention relates to a joint trajectory optimization method and device of a collaborative robot. The method comprises the steps that interpolation is conducted on space path points of a mechanical arm terminal mechanism of the collaborative robot through a seven-time B-spline curve function, so that B-spline track curves of all joints are obtained; taking the numerical value of the control vertex of the B-spline trajectory curve of each joint as an optimization variable, and determining a Pareto optimal solution set of the numerical value of the control vertex of the B-spline trajectory curve of each joint by using a non-dominated sorting genetic algorithm; and based on the Pareto optimal solution set, determining a planning scheme of the joint trajectory of the collaborative robot. By the adoption of the method and device, the problem that a non-dominated sorting genetic algorithm is caught in a local optimal solution too early in the solving process of the collaborative robot multi-target trajectory optimization model can be avoided, the optimized robot joint trajectory is short in operation time, low in energy consumption, small in movement impact and excellent in smoothness, and the optimal robot joint trajectory is obtained. Therefore, the motion stability of the robot can be ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of collaborative robot motion trajectory planning, and more specifically, to a collaborative robot joint trajectory optimization method and device. Background Art

[0002] Collaborative robots refer to robots that can work with humans on the production line. Compared with traditional industrial robots, collaborative robots have higher flexibility and safety, and can work with humans in the same workspace without the need for additional safety facilities. This feature gives collaborative robots a clear advantage in some scenarios that require flexible production and human-machine collaboration. Trajectory planning, as the core of robot grasping control, fundamentally determines the robot's operating performance. Excellent trajectory planning can improve the robot's work efficiency, reduce energy consumption, and reduce joint wear caused by vibration and impact on the basis of ensuring the completion of the task, thereby increasing the service life of the industrial robot. Summary of the invention

[0003] In order to solve the above problems, the present disclosure proposes a joint trajectory optimization method and device for a collaborative robot, a computing system and a computer-readable storage medium, which can solve the problems of slow convergence speed and easy falling into local optimal solutions of the non-dominated sorting genetic algorithm (NSGA-II) during target optimization.

[0004] According to one aspect of the present disclosure, a joint trajectory optimization method for a collaborative robot is provided, the joint trajectory optimization method for the collaborative robot comprising: interpolating the spatial path points of the robotic arm terminal mechanism of the collaborative robot using a seventh-order B-spline curve function to obtain the B-spline trajectory curve of each joint; using the numerical values ​​of the control vertices of the B-spline trajectory curve of each joint as optimization variables, and determining the Pareto optimal solution set of the numerical values ​​of the control vertices of the B-spline trajectory curve of each joint using a non-dominated sorting genetic algorithm; determining a planning scheme for the joint trajectory of the collaborative robot based on the Pareto optimal solution set, wherein the non-dominated sorting genetic algorithm comprises: determining an adjusted crossover probability based on an initial crossover probability, a predetermined gain factor, a standard deviation of the fitness of an offspring population, and an average fitness of the offspring population; determining an adjusted mutation probability based on an initial mutation probability, a predetermined gain factor, a standard deviation of the fitness of an offspring population, and an average fitness of the offspring population; performing crossover and mutation operations on the offspring population based on the adjusted crossover probability and mutation probability to generate a new offspring population.

[0005] Optionally, the non-dominated sorting genetic algorithm also includes: setting initialization-related parameters of the non-dominated sorting genetic algorithm, and generating an initial seed of the population to determine the initial population, wherein the initialization-related parameters include population size, mutation probability, crossover probability, maximum number of iterations, motion constraints of joint trajectories, and constraints on the motion characteristics of the robot arm itself; determining a dominant population in the initial population based on a fitness function that is an objective function of joint trajectory optimization of the collaborative robot; determining the crowding degree of each individual in the dominant population; and selecting individuals of a number equal to the population size from a set of dominant individuals based on the crowding degree of each individual as a descendant population.

[0006] Optionally, the non-dominated sorting genetic algorithm also includes: after generating a new offspring population, adding 1 to the number of iterations; merging the offspring population and the new offspring population to determine the crowding degree of each individual in the merged population; based on the crowding degree of each individual in the merged population, selecting individuals of the same number as the population size from the set of dominant individuals as a new population; determining the adjusted mutation probability and mutation probability for the new population and performing crossover and mutation operations on it to generate an offspring population of the new population, and adding 1 to the number of iterations; repeating the steps of merging populations, determining new populations, and generating an offspring population of the new population until the number of iterations reaches the maximum number of iterations to obtain the Pareto optimal solution set corresponding to the objective function.

[0007] Optionally, the crowding degree of each individual is determined based on the number of objective functions and the value of each individual on the objective function.

[0008] Optionally, the step of generating initial seeds of the population includes: generating initial seeds of the population using Logistic chaotic mapping.

[0009] Optionally, the objective function includes a function characterizing the time from the initial position to the final position of the robot arm terminal mechanism, a function characterizing the average acceleration of the joint, a function characterizing the energy consumed by the joint, and a function characterizing the joint pulsation.

[0010] Optionally, the motion constraints of the joint trajectory include the maximum values ​​of the control vertices of the B-spline velocity, acceleration, and jerk trajectory curves of the corresponding joints, and the motion characteristic constraints of the robot arm itself include the maximum values ​​of the joint torque, joint velocity, joint acceleration, joint jerk, and joint displacement.

[0011] According to another aspect of the present disclosure, a joint trajectory optimization device for a collaborative robot is provided, and the joint trajectory optimization device for the collaborative robot includes: an interpolation unit, configured to interpolate the spatial path points of the robot arm terminal mechanism of the collaborative robot using a seventh-order B-spline curve function to obtain a B-spline trajectory curve of each joint; a solution unit, configured to use the values ​​of the control vertices of the B-spline trajectory curve of each joint as optimization variables, and determine the Pareto optimal solution set of the values ​​of the control vertices of the B-spline trajectory curve of each joint using a non-dominated sorting genetic algorithm; a planning unit, configured to The method is configured to determine a planning scheme for the joint trajectory of a collaborative robot based on the Pareto optimal solution set, wherein the non-dominated sorting genetic algorithm comprises: determining an adjusted crossover probability based on an initial crossover probability, a predetermined gain factor, a standard deviation of the fitness of an offspring population, and an average fitness of an offspring population; determining an adjusted mutation probability based on an initial mutation probability, a predetermined gain factor, a standard deviation of the fitness of an offspring population, and an average fitness of an offspring population; and performing crossover and mutation operations on the offspring population based on the adjusted crossover probability and mutation probability to generate a new offspring population.

[0012] Optionally, the non-dominated sorting genetic algorithm also includes: setting initialization-related parameters of the non-dominated sorting genetic algorithm, and generating an initial seed of the population to determine the initial population, wherein the initialization-related parameters include population size, mutation probability, crossover probability, maximum number of iterations, motion constraints of joint trajectories, and constraints on the motion characteristics of the robot arm itself; determining a dominant population in the initial population based on a fitness function that is an objective function of joint trajectory optimization of the collaborative robot; determining the crowding degree of each individual in the dominant population; and selecting individuals of a number equal to the population size from a set of dominant individuals based on the crowding degree of each individual as a descendant population.

[0013] Optionally, the non-dominated sorting genetic algorithm also includes: after generating a new offspring population, adding 1 to the number of iterations; merging the offspring population and the new offspring population to determine the crowding degree of each individual in the merged population; based on the crowding degree of each individual in the merged population, selecting individuals of the same number as the population size from the set of dominant individuals as a new population; determining the adjusted mutation probability and mutation probability for the new population and performing crossover and mutation operations on it to generate an offspring population of the new population, and adding 1 to the number of iterations; repeating the steps of merging populations, determining new populations, and generating an offspring population of the new population until the number of iterations reaches the maximum number of iterations to obtain the Pareto optimal solution set corresponding to the objective function.

[0014] Optionally, the crowding degree of each individual is determined based on the number of objective functions and the value of each individual on the objective function.

[0015] Optionally, the step of generating initial seeds of the population includes: generating initial seeds of the population using Logistic chaotic mapping.

[0016] Optionally, the objective function includes a function characterizing the time from the initial position to the final position of the robot arm terminal mechanism, a function characterizing the average acceleration of the joint, a function characterizing the energy consumed by the joint, and a function characterizing the joint pulsation.

[0017] Optionally, the motion constraints of the joint trajectory include the maximum values ​​of the control vertices of the B-spline velocity, acceleration, and jerk trajectory curves of the corresponding joints, and the motion characteristic constraints of the robot arm itself include the maximum values ​​of the joint torque, joint velocity, joint acceleration, joint jerk, and joint displacement.

[0018] According to another aspect of the present disclosure, a computing system is provided that includes at least one computing device and at least one storage device storing instructions, wherein the instructions, when executed by the at least one computing device, prompt the at least one computing device to execute the joint trajectory optimization method of the collaborative robot as described above.

[0019] According to yet another aspect of the present disclosure, a computer-readable storage medium storing instructions is provided, wherein when the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the joint trajectory optimization method of the collaborative robot as described above.

[0020] By adopting the present disclosure, it is possible to avoid the problem of the non-dominated sorting genetic algorithm falling into the local optimal solution too early in the process of solving the collaborative robot multi-objective trajectory optimization model. The optimized robot joint trajectory has a shorter running time, lower energy consumption, smaller motion impact, and better smoothness, thereby ensuring the robot's motion stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or other objects and advantages of the present disclosure will become more apparent through the following description of embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 is a flow chart showing a joint trajectory optimization method of a collaborative robot according to an exemplary embodiment of the present disclosure;

[0023] Figure 2 is a diagram showing the joint trajectory planning process of the robot;

[0024] Figure 3 is a flow chart illustrating a non-dominated sorting genetic algorithm (NSGA-II) algorithm according to an exemplary embodiment of the present disclosure;

[0025] Figure 4is a block diagram showing a joint trajectory optimization device of a collaborative robot according to an exemplary embodiment of the present disclosure;

[0026] FIG. 5A to FIG. 5F is a graph diagram of the speed, acceleration and jerk of six joints according to an example of the present disclosure;

[0027] Figure 6 is a block diagram illustrating a computing system including at least one computing device and at least one storage device storing instructions according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Below, in conjunction with the accompanying drawings, a description of a specific embodiment is provided to help the reader obtain a comprehensive understanding of the method, device and / or system described herein. However, after understanding the disclosure of the present application, various changes, modifications and equivalents of the method, device and / or system described herein will be clear. For example, the order of operations described herein is only an example and is not limited to those orders set forth herein, but can be changed as will be clear after understanding the disclosure of the present application, except for operations that must occur in a specific order. In addition, for greater clarity and simplicity, the description of features known in the art may be omitted.

[0029] Generally, in the practical application of collaborative robots, it is necessary to first plan the spatial path of the end-effector of the robot arm from the specified starting point to the end point. At this time, the planned path is pure physical space information. After that, after trajectory planning, a specific plan is obtained to pass through several points (waypoints) between the above paths (for example, when, at what speed, and at what acceleration to pass a certain point). Collaborative robots are usually used in unstructured environments that require frequent task changes or work mode adjustments. In different working environments, the robot's motion trajectory needs to be optimized differently. For example, some tasks may focus more on fast completion (i.e., shortest time), while other tasks may focus more on energy saving (i.e., optimal energy), and some tasks may require smooth motion to reduce the impact on precision equipment (i.e., minimum impact). Therefore, single-objective trajectory optimization is difficult to meet the application requirements of complex situations, and more and more attention has been paid to multi-objective trajectory optimization, considering selecting the most suitable trajectory for each environment in different operating scenarios. The traditional method is to convert the multi-objective problem into a single-objective problem and then use the single-objective optimization method for optimization, but the problem with this method is that it is difficult to reasonably allocate weights, the diversity of solutions is insufficient, and it may fall into a local optimal solution.

[0030] Since the non-dominated sorting genetic algorithm (NSGA-II) has the advantages of parallelism, robustness, and strong adaptability, it is suitable for solving the multi-objective trajectory optimization task of collaborative robots. However, since the non-dominated sorting genetic algorithm is a population-based algorithm, its results are easily affected by the initial population. If the initial population is not good enough, it may fall into the local optimal solution. At the same time, the non-dominated sorting genetic algorithm has limited processing capabilities for non-convex and multi-peak problems, and may have problems such as low search efficiency and slow convergence. In summary, in the actual application of collaborative robots, in order to obtain a better trajectory planning solution, it is necessary to comprehensively consider factors such as work efficiency, energy consumption, and stability. However, traditional multi-objective optimization research is difficult to reasonably allocate weights, the diversity of solutions is insufficient, and it may fall into the local optimal solution. In addition, the use of traditional genetic algorithms for collaborative robot multi-objective trajectory optimization methods is prone to premature convergence problems.

[0031] The present invention adopts an intelligent multi-objective optimization algorithm to realize the multi-objective optimization of the joint trajectory of a collaborative robot, and specifically relates to a collaborative robot multi-objective trajectory optimization method based on an improved non-dominated sorting genetic algorithm. The method takes shortening the robot's working time, reducing energy consumption and reducing motion impact as the objective function, and uses the non-dominated sorting genetic algorithm to optimize the robot's joint trajectory, and finally obtains a trajectory planning scheme with better comprehensive performance. Taking various limiting factors into consideration, multi-objective trajectory optimization is performed, and by improving the algorithm, the premature convergence problem that is easily generated by the non-dominated sorting genetic algorithm is improved.

[0032] Figure 1 is a flow chart illustrating a joint trajectory optimization method of a collaborative robot according to an exemplary embodiment of the present disclosure. Figure 2 is a diagram showing the joint trajectory planning process of the robot. Figure 2 Before the robot performs a task, it is necessary to plan the trajectory of each joint according to the task requirements, set the path according to the task requirements to generate the waypoints of the joints, and each joint on the robot must pass through each path node in sequence to complete the task while satisfying the kinematic constraints.

[0033] like Figure 1 As shown, in step S101, a seventh-order B-spline curve function is used to interpolate the spatial path points of the robot arm terminal mechanism of the collaborative robot to obtain the B-spline trajectory curve of each joint.

[0034] In this example, assume that the joint position nodes that the robot must pass through to complete the task are:

[0035] m Θ=[ m θ 0 mθ 1 … m θ n ] T .

[0036] In the above formula, m θ i is the i-th position of the m-th joint of the robot, i=0,1,2,…,n; m=1,2,…,M, where M is the number of robot joints (for example, M=6); and n+1 is the number of joint path points.

[0037] The time nodes corresponding to the joint position nodes can be expressed as:

[0038] T=[t 0 t 1 … t n ].

[0039] Based on the canonical B-spline basis function, the spatial path points from the starting point to the end point of the planned robot terminal mechanism are interpolated using the seventh-order B-spline curve function. The expression of the seventh-order B-spline curve interpolation trajectory of the i-th segment of the m-th joint of the robot is:

[0040]

[0041] Where, m = 1, 2, ..., M (M is the number of robot joints); m p i (x) is the i-th segment of the 7th-order B-spline curve interpolation trajectory of the m-th joint of the robot; x is the node of the 7th-order B-spline curve, is the normalized time vector; B j,7 (x) is the 7th-order B-spline basis function; m a j is the jth B-spline curve control point of the nth joint of the robot; n+1 is the number of joint path points. Make the segmented connection points of the curve correspond to the nodes in the B-spline definition domain one by one, and the first and last points are consistent with the first and last data points. The B-spline interpolation curve consists of n+7 control vertices a j (i=0,1,…,n+7-1) and the node vector X=[x 0 ,x 1 ,…,x n+14 ]; the duplication degree of the nodes at both ends is 8, that is, x 0 =x 1 =…=x 7 =0,x n+7 =x n+7+1 =…=x n+14= 1, normalize the time node T, and get the exact value of the unknown node of the node sequence X of the joint's B-spline interpolation curve; this will provide a basis for the subsequent solution of the joint position, velocity and acceleration trajectory.

[0042] The values ​​of unknown nodes of the B-spline interpolation curve can be expressed as:

[0043]

[0044] In the above formula, Δt k =T i-k -t i-k-1 (k=0,1,…,n-1) is the chord length, T=t m -t 0 The total running time for the robot to complete the task.

[0045] The spline domain [x 7 ,x n+7 ] are substituted into the above formula one by one, and n+1 equations satisfying the interpolation condition are obtained:

[0046]

[0047] In the above formula, x i+7 ∈[x 7 ,x m+7 ], i = 0, 1, ..., m. Therefore, it is necessary to add 7-1 additional equations to solve them simultaneously. Generally, the tangent vector boundary condition is taken, for example, the 7th order B-spline curve is taken, and the start and stop speed v is specified. s 、v e , start-stop acceleration a s 、a e and start-stop pulsation s 、j e , the added 6 equations are as follows:

[0048]

[0049] In the above formula, p'(x), p"(x), and p"'(x) are the first-order derivative, second-order derivative, and third-order derivative of the B-spline curve, respectively, representing the velocity, acceleration, and jerk of each joint.

[0050] The derivatives of each order can be obtained according to the De Boer recursion formula:

[0051]

[0052] in:

[0053]

[0054] Thus, we get n+7 linear equations. By solving the equations, we can get the control vertex vectors of the B-spline trajectory curves of each joint. According to the normalized time node vector X, we can find the control vertex vectors of each joint at time t i The position p passed by i Then, the robot's joint position trajectory can be obtained by using the control point value, and the velocity, acceleration and jerk trajectory curves can be obtained by taking its derivative.

[0055] Since B-spline has the convex hull property, the joint trajectory kinematic constraints are converted into constraints of B-spline control vertices:

[0056]

[0057] In the above formula, m = 1, 2, ..., M, where M is the number of joints of the manipulator and n + 1 is the number of key points; m a j 1 , m a j 2 and m a j 3 are the jth control vertex of the B-spline velocity, acceleration and pulsation trajectory curve of the mth joint; v mmax 、a mmax 、j mmax are the position, velocity, acceleration and maximum jerk of the mth joint of the robot; k v , k a , k j is the magnification factor. Considering the strong convex hull property of the B-spline curve, the kinematic constraints should be appropriately magnified.

[0058] According to the optimization goals of shortest time, optimal energy and minimum impact, the robot optimization objective function is determined as:

[0059]

[0060] In the above formula, T is the time it takes for the manipulator to move from the initial position to the final position along a certain trajectory; Δt i is the robot operation time interval, t i is the running time of the robot to the i-th joint path point; a i 、j i They are joint acceleration and jerk (pulsation), respectively; q i represents the joint angle value of the joint at key point i; τ i Expressed as the control torque of the manipulator; F 1 is the movement time, which measures the movement efficiency of the manipulator; F 2is the average acceleration of the joint, which is an indicator to measure the energy consumption of the manipulator joint; F 3 is the joint pulsation, which measures the smoothness of the trajectory; F 4 Energy consumed by the joints.

[0061] In step S102, the numerical values ​​of the control vertices of the B-spline trajectory curves of each joint are used as optimization variables, and the Pareto optimal solution set of the numerical values ​​of the control vertices of the B-spline trajectory curves of each joint is determined by using a non-dominated sorting genetic algorithm. In the example, according to the robot's 7th-order B-spline curve interpolation trajectory, optimization objective function and kinematic constraints, the immune genetic multi-objective optimization algorithm of the non-dominated neighborhood is used to obtain the Pareto optimal solution set corresponding to the optimization. In step S103, based on the Pareto optimal solution set, the planning scheme of the joint trajectory of the collaborative robot is determined, wherein the non-dominated sorting genetic algorithm includes: determining the adjusted crossover probability based on the initial crossover probability, the predetermined gain factor, the standard deviation of the fitness of the offspring population and the average fitness of the offspring population; determining the adjusted mutation probability based on the initial mutation probability, the predetermined gain factor, the standard deviation of the fitness of the offspring population and the average fitness of the offspring population; performing crossover and mutation operations on the offspring population based on the adjusted crossover probability and mutation probability to generate a new offspring population.

[0062] In the example, the step of generating a descendant population includes: setting initialization-related parameters of a non-dominated sorting genetic algorithm, and generating an initial seed of the population to determine the initial population (for example, using a Logistic chaotic map to generate the initial seed of the population), wherein the initialization-related parameters include population size, mutation probability, crossover probability, maximum number of iterations, motion constraints of joint trajectories, and motion characteristic constraints of the robot itself; determining a dominant population in the initial population based on a fitness function that is an objective function of joint trajectory optimization of a collaborative robot; determining the crowding degree of each individual in the dominant population; and selecting individuals of the same number as the population size from a set of dominant individuals based on the crowding degree of each individual as a descendant population. For example, the crowding degree of each individual is determined based on the number of objective functions and the value of each individual on the objective function. For example, the objective function includes a function that characterizes the time from the initial posture to the terminal posture of the robot arm, a function that characterizes the average acceleration of the joint, a function that characterizes the energy consumed by the joint, and a function that characterizes the joint pulsation (for example, the objective function F as described above). 1 To F 4 ). For example, the motion constraints of the joint trajectory include the maximum values ​​of the control vertices of the B-spline velocity, acceleration, and jerk trajectory curves of the corresponding joints, and the motion characteristic constraints of the robot itself include the maximum values ​​of the joint torque, joint velocity, joint acceleration, joint jerk, and joint displacement.

[0063] For example,

[0064] Joint torque: |τ mi (t)|≤τ mmax , i=1,2,…,m;

[0065] Joint jerk: |j mi (t)|≤j mmax , i=1,2,…,m;

[0066] Joint acceleration: |a mi t)|≤a mmax , i=1,2,…,m;

[0067] Joint velocity: |v mi (t)|≤v mmax , i=1,2,…,m;

[0068] Joint displacement: |q mi (t)|≤q mmax , i=1,2,…,m.

[0069] Among them, q mmax is the maximum range of joint motion; v mmax is the maximum value of the joint angular velocity; a mmax is the maximum value of the joint angular acceleration; j mmax is the maximum value of the joint angular acceleration; τ mmax is the maximum moment acting on the joint.

[0070] For example, set the relevant parameters for initializing the non-dominated sorting genetic algorithm (including population size NIND, mutation probability Pm, crossover probability Pc, maximum number of iterations Gen, and upper and lower limits of the problem value in the problem domain, etc.); use Logistic chaotic mapping to generate the initial seed Spop of the population, that is, the initial spatial position of each individual in the population.

[0071] For example, the iterative formula of Logistic chaos mapping is:

[0072] x n+1 = r·x n ·(1-x n ).

[0073] Among them, x n is the value of the nth iteration, x n+1 is the value of the next iteration, r is the parameter of the chaotic map, and its value is usually between [3.57,4].

[0074] Initializing the population through one-dimensional Logistic chaotic mapping can give a certain degree of randomness to the individuals in the population, which helps to increase the diversity of the population and improve the global search ability of the algorithm.

[0075] Then, according to the Pareto optimal solution criterion, the dominant population in the initial population is determined by calculating the fitness function, and the crowding distance of each individual in the dominant population is further calculated. The crowding calculation method based on entropy can be expressed as:

[0076]

[0077] Among them, CrowdingDistance i is the crowding value of individual i, N is the number of objective functions, f i (j) is the value of individual i on the jth objective function. The crowding calculation method based on entropy can be used to measure the distribution density of individuals in the target space. By calculating the distribution entropy of individuals in the target space, the diversity of individuals can be evaluated, thereby helping the algorithm maintain the diversity of the population.

[0078] Next, based on the non-dominated set and crowding degree of the selected individuals, the individuals in the dominant set are selected first, and then the individuals with higher crowding degree are selected from these individuals, and the process is repeated until NIND individuals are selected. Then, according to the crossover probability and mutation probability in the algorithm, the initial population is subjected to crossover and mutation operations to generate a new offspring population. Among them, the crossover probability and mutation probability can be adjusted adaptively. When the fitness change trend of the population is large, the dynamically adjusted crossover probability will be reduced to slow down the evolution speed of the population, so as to better explore the search space and avoid converging to the local optimal solution too early. When the fitness change trend of the population is small, the crossover probability is dynamically adjusted to increase to speed up the evolution speed of the population, so as to better explore the search space and avoid falling into the local optimal solution.

[0079] Specifically, the calculation formula for dynamically adjusting the crossover probability is as follows:

[0080]

[0081] Among them, P c is the crossover probability after dynamic adjustment, P c0 is the initial crossover probability, k is the gain factor, σ f is the standard deviation of the population fitness, f avg is the average fitness of the population. The function of the gain factor k is to adjust the influence of the change of population fitness on the mutation probability and crossover probability.

[0082] The calculation formula for dynamically adjusting the mutation probability is as follows:

[0083]

[0084] Among them, P m is the dynamically adjusted mutation probability, P m0 is the initial mutation probability, k is the gain factor, σ f is the standard deviation of the population fitness, f avg is the average fitness of the population.

[0085] Subsequently, the size of the dominant population is determined for the new offspring population according to the Pareto optimal solution criterion, and the crowding distance of the individuals in the dominant population is calculated. If the size of the dominant population exceeds the expected value, the antibodies with a larger crowding distance are retained. Until the algorithm is judged to meet the end condition, the Pareto optimal solution set corresponding to the objective function is output, and the final trajectory planning scheme is selected from the Pareto optimal solution set.

[0086] In the example, after a new offspring population is generated, the number of iterations is increased by 1; the offspring population and the new offspring population are merged to determine the crowding degree of each individual in the merged population; based on the crowding degree of each individual in the merged population, individuals of the same number as the size of the population are selected from the set of dominant individuals as a new population; the adjusted mutation probability and mutation probability are determined for the new population and crossover and mutation operations are performed on it to generate an offspring population of the new population, and the number of iterations is increased by 1; the steps of merging populations, determining new populations, and generating offspring populations of the new population are repeated until the number of iterations reaches the maximum number of iterations to obtain the Pareto optimal solution set corresponding to the objective function (for details, please refer to Figure 3 description).

[0087] The joint trajectory optimization method of a collaborative robot according to an exemplary embodiment of the present disclosure comprehensively considers the kinematic constraints of each joint of the robot, and effectively improves the motion performance of the robot joints based on the proposed objective functions of shortest time, optimal energy and minimum impact. At the same time, in order to address the premature convergence problem that is prone to occur in the algorithm, the non-dominated sorting multi-objective genetic algorithm is improved to obtain a more reliable collaborative robot multi-objective trajectory planning solution set.

[0088] Figure 3It is a flowchart showing the non-dominated sorting genetic algorithm (NSGA-II) algorithm according to an exemplary embodiment of the present disclosure. In the example, firstly, a 7-order B-spline curve is used for interpolation planning; secondly, on the basis of considering the joint trajectory and the robot kinematic constraints, the robot's work efficiency, energy consumption and motion stability requirements are comprehensively considered, and three optimization objectives (shortest time, optimal energy and minimum impact) are proposed; finally, based on the meaning of the Pareto optimal set, the improved NSGA-II algorithm is finally obtained.

[0089] like Figure 3 As shown, in step S301, the initialization-related parameters of the non-dominated sorting genetic algorithm are set, and the initial seeds of the population are generated to determine the initial population (for example, the initial seeds of the population are generated using the Logistic chaotic map), wherein the initialization-related parameters include the population size, mutation probability, crossover probability, maximum number of iterations, motion constraints of joint trajectories, and motion characteristic constraints of the robot itself. In step S302, it is determined whether the first generation of offspring populations is generated. If it is determined in step S302 that the first generation of offspring population is not generated, then based on the fitness function as the objective function of the joint trajectory optimization of the collaborative robot, determine the dominant population in the initial population; determine the crowding degree of each individual in the dominant population; based on the crowding degree of each individual, select individuals of the same number as the population size from the dominant individual set as the offspring population; based on the initial crossover probability, the predetermined gain factor, the standard deviation of the fitness of the offspring population and the average fitness of the offspring population, determine the adjusted crossover probability; based on the initial mutation probability, the predetermined gain factor, the standard deviation of the fitness of the offspring population and the average fitness of the offspring population, determine the adjusted mutation probability; perform crossover and mutation operations on the offspring population based on the adjusted crossover probability and mutation probability to generate a new offspring population (steps S303, S304, S305 and S306). If it is determined in step S302 that the first generation of offspring population is generated, then in step S307, increase the number of iterations by one (i.e., gen=2). Next, in step S308, the parent population and the child population are merged (the parent population refers to the population individuals retained by the selection operation in the current iteration, which are the optimal solutions of the previous generation; the child population refers to the new individual set generated from the parent generation through crossover and mutation operations). The merging method includes, for example, directly putting the parent and child individuals together to form a mixed population, and then selecting according to non-dominated sorting and crowding distance to determine the next generation population.

[0090] Next, in step S309, it is determined whether a new parent population is generated. If it is determined in step S309 that a new parent population is not generated, then in steps S310, S311 and S312, the size of the dominant population is determined for the new offspring population according to the Pareto optimal solution criterion, and the crowding distance of the individuals in the dominant population is calculated. If the size of the dominant population exceeds the expected value, the antibodies with a larger crowding distance are retained. If it is determined in step S309 that a new parent population is generated, then in step S313, a new generation of parent individuals is selected according to the non-dominated sorting and crowding degree (for example, individuals with excellent performance in non-dominated sorting and crowding distance are selected as the parents of the new generation). In step S314, the selected parent individuals are subjected to the above-mentioned adaptive crossover and mutation operations to generate a new offspring population. Next, in step S315, it is determined whether the number of iterations reaches the maximum number of iterations. If it is determined in step S315 that the number of iterations does not reach the maximum number of iterations, the number of iterations is increased by one and the process returns to step S308. If it is determined in step S315 that the number of iterations has reached the maximum number of iterations, then in step S316 a Pareto optimal solution is output.

[0091] By adopting the non-dominated sorting genetic algorithm disclosed in the present invention, the problem of falling into the local optimal solution too early in the process of solving the collaborative robot multi-objective trajectory optimization model is avoided. The optimized robot joint trajectory has a shorter running time, lower energy consumption, smaller motion impact, and better smoothness, which provides a strong guarantee for the robot's motion stability.

[0092] Figure 4 is a block diagram illustrating a joint trajectory optimization apparatus of a collaborative robot according to an exemplary embodiment of the present disclosure.

[0093] like Figure 4As shown, according to an exemplary embodiment of the present disclosure, a joint trajectory optimization device 400 of a collaborative robot includes: an interpolation unit 401, configured to interpolate the spatial path points of the mechanical arm terminal mechanism of the collaborative robot using a seventh-order B-spline curve function to obtain a B-spline trajectory curve of each joint; a solution unit 402, configured to use the values ​​of the control vertices of the B-spline trajectory curve of each joint as optimization variables, and use a non-dominated sorting genetic algorithm to determine the Pareto optimal solution set of the values ​​of the control vertices of the B-spline trajectory curve of each joint; a planning unit 403, configured To determine a planning scheme for the joint trajectory of a collaborative robot based on the Pareto optimal solution set, wherein the non-dominated sorting genetic algorithm includes: determining an adjusted crossover probability based on an initial crossover probability, a predetermined gain factor, a standard deviation of the fitness of an offspring population, and an average fitness of the offspring population; determining an adjusted mutation probability based on an initial mutation probability, a predetermined gain factor, a standard deviation of the fitness of an offspring population, and an average fitness of the offspring population; performing crossover and mutation operations on the offspring population based on the adjusted crossover probability and mutation probability to generate a new offspring population.

[0094] In the example, initialization-related parameters of a non-dominated sorting genetic algorithm are set, and an initial seed of a population is generated to determine an initial population, wherein the initialization-related parameters include population size, mutation probability, crossover probability, maximum number of iterations, motion constraints of joint trajectories, and constraints on the motion characteristics of the robot itself; based on a fitness function that is an objective function of joint trajectory optimization of a collaborative robot, a dominant population in the initial population is determined; the crowding degree of each individual in the dominant population is determined; and based on the crowding degree of each individual, individuals of a number equal to the population size are selected from a set of dominant individuals as a descendant population.

[0095] In the example, after a new offspring population is generated, the number of iterations is increased by 1; the offspring population and the new offspring population are merged to determine the crowding degree of each individual in the merged population; based on the crowding degree of each individual in the merged population, individuals of the same number as the size of the population are selected from the set of dominant individuals as a new population; the adjusted mutation probability and mutation probability are determined for the new population and crossover and mutation operations are performed on it to generate an offspring population of the new population, and the number of iterations is increased by 1; the steps of merging populations, determining new populations, and generating offspring populations of the new population are repeated until the number of iterations reaches the maximum number of iterations to obtain the Pareto optimal solution set corresponding to the objective function.

[0096] In an example, the crowding degree of each individual is determined based on the number of objective functions and the value of each individual on the objective function.

[0097] In an example, the step of generating initial seeds of the population includes: generating initial seeds of the population using Logistic chaos mapping.

[0098] In an example, the objective function includes a function characterizing the time from the initial position to the final position of the robot arm terminal mechanism, a function characterizing the average acceleration of the joint, a function characterizing the energy consumed by the joint, and a function characterizing the joint pulsation.

[0099] In the example, the motion constraints of the joint trajectories include the maximum values ​​of the control vertices of the B-spline velocity, acceleration, and jerk trajectory curves of the corresponding joints, and the motion characteristic constraints of the robot itself include the maximum values ​​of the joint torque, joint velocity, joint acceleration, joint jerk, and joint displacement.

[0100] Combination of the above Figures 1 to 3 The specific operations shown are respectively Figure 4 The joint trajectory optimization device 400 of the collaborative robot is shown to be executed by the corresponding units, and the specific operation details will not be repeated here.

[0101] FIG. 5A to FIG. 5F Schematic diagram of the curves of velocity, acceleration and jerk of six joints according to an example of the present disclosure.

[0102] In the example, trajectory planning is performed for a Sawyer robot including seven joints and optimized according to an objective function; the kinematic constraints of each joint during trajectory planning of the Sawyer robot are shown in Table 1 below.

[0103] Table 1

[0104]

[0105] The data in Table 1 represent the constraints of velocity, acceleration, and jerk of each joint of the Sawyer robot.

[0106] The joint position nodes of the six joints of a given Sawyer robot are shown in Table 2 below.

[0107] Table 2

[0108]

[0109] The data in Table 2 represent the path points that the Sawyer robot must pass through from starting to stopping each joint movement when completing the task.

[0110] Under given constraints and joint path conditions, a simulation study was conducted using Matlab software using the method disclosed herein, and the initial parameters in the algorithm are shown in Table 3 below.

[0111] Table 3

[0112]

[0113] The data in Table 3 represent the initial relevant parameters of the non-dominated sorting genetic algorithm (NSGA-II).

[0114] like FIG. 5A to FIG. 5F As shown, the six joints reach the final position through the specified joint path nodes, the velocity and acceleration curves are continuous, and all kinematic constraints are within the constraint range. The trajectory planning scheme has high reliability.

[0115] Figure 6 is a block diagram illustrating a computing system including at least one computing device and at least one storage device storing instructions according to an exemplary embodiment of the present disclosure.

[0116] like Figure 6 As shown, the computing system 600 provided according to the exemplary embodiment of the present disclosure includes a computing device 601 and a storage device 602, in which computer executable instructions are stored. When the computer executable instructions are executed by the computing device 601, the joint trajectory optimization method of the collaborative robot described in any of the aforementioned embodiments is executed.

[0117] The computing device 601 is deployed in a server or client, and may also be deployed on a node device in a distributed network environment. In addition, the computing device 601 may be a PC computer, a tablet device, a personal digital assistant, a smart phone, a web application or other device capable of executing the above-mentioned instruction set. Here, the computing device is not necessarily a single computing device, but may also be any device or circuit capable of executing the above-mentioned instruction (or instruction set) individually or jointly. The computing device may also be a part of an integrated control system or a system manager, or may be configured as a portable electronic device interconnected with an interface locally or remotely (e.g., via wireless transmission). In the computing device, the processor includes a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. As an example and not limitation, the processor also includes an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0118] According to another aspect of the present disclosure, a computer-readable storage medium storing instructions is provided, and when the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the joint trajectory optimization method of the collaborative robot described in any of the aforementioned embodiments. Computer-readable storage media include magnetic media such as floppy disks and tapes, optical media (including compact disk (CD) ROM and DVD ROM), magneto-optical media such as floppy disks, hardware devices such as ROM, RAM, and flash memory designed to store and execute program commands. The instructions may include language codes executable by a computer using an interpreter and machine language codes generated by a compiler.

[0119] By adopting the present disclosure, it is possible to avoid the problem of the non-dominated sorting genetic algorithm falling into the local optimal solution too early in the process of solving the collaborative robot multi-objective trajectory optimization model. The optimized robot joint trajectory has a shorter running time, lower energy consumption, smaller motion impact, and better smoothness, thereby ensuring the robot's motion stability.

[0120] The processes, methods or algorithms disclosed herein may be transmitted to or implemented by a processing device, a controller or a computer, which may include any existing programmable electronic control unit or a dedicated electronic control unit. Similarly, the processes, methods or algorithms may be stored in a variety of forms as data and instructions that can be executed by a controller or a computer, including but not limited to information being permanently stored on a non-writable storage medium (such as a ROM device) and information being variably stored on a writable storage medium (such as a floppy disk, a tape, a CD, a RAM device, and other magnetic and optical media). The processes, methods or algorithms may also be implemented in a software executable object. Optionally, the processes, methods or algorithms may be implemented in whole or in part using suitable hardware components (such as an ASIC, an FPGA, a state machine, a controller or other hardware components or devices) or a combination of hardware components, software components and firmware components.

[0121] Although the present disclosure includes specific examples, it will be apparent to those of ordinary skill in the art that various changes in form and detail may be made in these examples without departing from the spirit and scope of the claims and their equivalents. The examples described herein will be considered to be descriptive only and not for limiting purposes. The description of the features or aspects in each example will be considered to be applicable to similar features or aspects in other examples. Suitable results may be obtained if the described techniques are performed in a different order, and / or if the components in the described systems, architectures, devices, or circuits are combined in different ways and / or replaced or supplemented with other components or their equivalents in the described systems, architectures, devices, or circuits. Therefore, the scope of the present disclosure is not limited by specific embodiments, but by the claims and their equivalents, and all variations within the scope of the claims and their equivalents will be interpreted as included in the present disclosure.

Claims

1. A joint trajectory optimization method for a collaborative robot, characterized in that: The joint trajectory optimization method of the collaborative robot comprises: The spatial path points of the robot arm terminal mechanism of the collaborative robot are interpolated using the seventh-order B-spline curve function to obtain the B-spline trajectory curve of each joint; Taking the values ​​of the control vertices of the B-spline trajectory curve of each joint as optimization variables, a non-dominated sorting genetic algorithm is used to determine the Pareto optimal solution set of the values ​​of the control vertices of the B-spline trajectory curve of each joint; Based on the Pareto optimal solution set, a planning scheme for the joint trajectory of the collaborative robot is determined. The non-dominated sorting genetic algorithm includes: determining an adjusted crossover probability based on an initial crossover probability, a predetermined gain factor, a standard deviation of the fitness of the offspring population and an average fitness of the offspring population; determining an adjusted mutation probability based on an initial mutation probability, a predetermined gain factor, a standard deviation of the fitness of the offspring population and an average fitness of the offspring population; and performing crossover and mutation operations on the offspring population based on the adjusted crossover probability and mutation probability to generate a new offspring population.

2. The joint trajectory optimization method of a collaborative robot according to claim 1, characterized in that: The non-dominated sorting genetic algorithm also includes: Setting initialization related parameters of the non-dominated sorting genetic algorithm and generating an initial seed of the population to determine the initial population, wherein the initialization related parameters include population size, mutation probability, crossover probability, maximum number of iterations, motion constraints of joint trajectories, and motion characteristic constraints of the robot itself; determining a dominant population in an initial population based on a fitness function that is an objective function of joint trajectory optimization of the collaborative robot; Determine the crowding degree of each individual in the dominant population; Based on the crowding degree of each individual, individuals of the same number as the population size are selected from the set of dominant individuals as the offspring population.

3. The joint trajectory optimization method of the collaborative robot according to claim 2, characterized in that: The non-dominated sorting genetic algorithm also includes: After generating a new offspring population, increase the number of iterations by 1; Merge the offspring population and the new offspring population, and determine the crowding degree of each individual in the merged population; Based on the crowding degree of each individual in the merged population, selecting individuals of the same number as the size of the population from the set of dominant individuals as a new population; Determine the adjusted mutation probability and mutation probability for the new population and perform crossover and mutation operations on it to generate a descendant population of the new population, and increase the number of iterations by 1; The steps of merging populations, determining a new population, and generating a descendant population of the new population are repeated until the number of iterations reaches the maximum number of iterations, so as to obtain a Pareto optimal solution set corresponding to the objective function.

4. The joint trajectory optimization method of a collaborative robot according to claim 2, characterized in that: The crowding degree of each individual is determined based on the number of objective functions and the value of each individual on the objective function.

5. The joint trajectory optimization method of a collaborative robot according to claim 2, characterized in that: The step of generating the initial seeds of the population includes: generating the initial seeds of the population using Logistic chaos mapping.

6. The joint trajectory optimization method of a collaborative robot according to claim 2, characterized in that: The objective function includes a function characterizing the time from the initial position to the final position of the robot arm terminal mechanism, a function characterizing the average acceleration of the joint, a function characterizing the energy consumed by the joint, and a function characterizing the joint pulsation.

7. The joint trajectory optimization method of a collaborative robot according to claim 2, characterized in that: The motion constraints of the joint trajectory include the maximum values ​​of the control vertices of the B-spline velocity, acceleration, and jerk trajectory curves of the corresponding joints. The motion characteristic constraints of the robot itself include the maximum values ​​of the joint torque, joint velocity, joint acceleration, joint jerk, and joint displacement.

8. A joint trajectory optimization device for a collaborative robot, characterized in that: The joint trajectory optimization device of the collaborative robot comprises: An interpolation unit is configured to interpolate the spatial path points of the robot arm terminal mechanism of the collaborative robot using a seventh-order B-spline curve function to obtain a B-spline trajectory curve of each joint; A solution unit is configured to use the values ​​of the control vertices of the B-spline trajectory curves of each joint as optimization variables and determine the Pareto optimal solution set of the values ​​of the control vertices of the B-spline trajectory curves of each joint by using a non-dominated sorting genetic algorithm; A planning unit is configured to determine a planning scheme for the joint trajectory of the collaborative robot based on the Pareto optimal solution set, The non-dominated sorting genetic algorithm includes: determining an adjusted crossover probability based on an initial crossover probability, a predetermined gain factor, a standard deviation of the fitness of the offspring population and an average fitness of the offspring population; determining an adjusted mutation probability based on an initial mutation probability, a predetermined gain factor, a standard deviation of the fitness of the offspring population and an average fitness of the offspring population; and performing crossover and mutation operations on the offspring population based on the adjusted crossover probability and mutation probability to generate a new offspring population.

9. A computing system comprising at least one computing device and at least one storage device storing instructions, characterized in that: When the instructions are executed by the at least one computing device, the at least one computing device is prompted to execute the joint trajectory optimization method of the collaborative robot according to any one of claims 1-7.

10. A computer-readable storage medium storing instructions, characterized in that: When the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the joint trajectory optimization method of the collaborative robot according to any one of claims 1-7.

Citation Information

Patent Citations

  • Non-dominated neighbor immune genetic multi-target optimizing method of joint track of electrohydraulic robot

    CN110216673A

  • Multi-machine cooperative trajectory optimization method based on quintic non-uniform rational B-spline

    CN113296407A

  • Logistics route optimization method and system based on adaptive NSGAII

    CN113919557A

  • Method and system for determining motion path of mechanical arm

    US20200101608A1

Cited By

  • Six-axis robot trajectory planning method in non-structural environment

    CN120197393A

  • Robot time optimal trajectory planning method based on dynamics constraint

    CN120773069A

  • Robot motion balance control method and system

    CN121254886A

  • Control method, device and equipment of bronchoscope auxiliary robot

    CN122056694A

  • A control method, device, and equipment for a bronchoscopy-assisted robot.

    CN122056694B