Multi-objective trajectory planning for industrial robots based on machine learning

doi:10.16731/j.cnki.1671-3133.2024.02.005

Abstract

Abstract: In order to meet the diverse needs of robot work trajectories, a new multi-objective sparrow search algorithm with optimization objectives of time,energy and impact was proposed to find the optimal trajectory of robots.Firstly,the joint space trajectory was constructed by the 7-degree B-spline interpolation method,and the multi-objective synthetic optimal trajectory planning model was established.Secondly,the sparrow search algorithm was improved by constraint violation computing,non-dominated ranking and elitist retention to solve the multi-objective trajectory planning problem.Finally,the data in the random population was deleted by the bag-tree classification algorithm,and a five-layer BP neural network was built to replace and improve the numerical calculation part of the fitness value in the multi-objective sparrow search algorithm,thus improving the efficiency of the algorithm.Through the MATLAB simulation and experiment,the feasibility and validity of the algorithm were demonstrated.

Key words: industrial robot, trajectory planning, machine learning, sparrow search algorithm, multi-objective optimization

CLC Number:

TP242

ZHANG Xuecong, CHAO Yongsheng, LI Chunyan, ZHOU Jianglin. Multi-objective trajectory planning for industrial robots based on machine learning[J]. Modern Manufacturing Engineering, 2024, 521(2): 31-37.

References

[1] 米根锁,李明.布谷鸟搜索算法在空间机械臂轨迹规划中的应用研究[J].机械科学与技术,2018,37 (12):7-12.
[2] 赵毓,管公顺,郭继峰,等.基于多智能体强化学习的空间机械臂轨迹规划[J].航空学报,2021,42(1):259-269.
[3] 蔡自兴,谢斌.机器人学[M].3版.北京:清华大学出版社,2014.
[4] 赵俊宇,张平,李方,等.面向制造环境的工业机器人节能轨迹规划[J].机器人,2021,43(6):653-663.
[5] BUREERAT S,PHOLDEE N,RADPUKDEE T,et al.Self-adaptive MRPBIL-DE for 6D robot multiobjective trajectory planning[J].Expert Systems with Applications,2019,136(1):133-144.
[6] KUMAR S,TEJANI G G,PHOLDEE N,et al.Performance enhancement of meta-heuristics through random mutation and simulated annealing-based selection for concurrent topology and sizing optimization of truss structures[J].Soft Comput-ing,2022,26(12):5661-5683.
[7] WANSASUEB K,PANMANEE S,PANAGANT N,et al.Hybridised differential evolution and equilibrium optimiser with learning parameters for mechanical and aircraft wing design[J].Knowledge-Based Systems,2022,239:107955.
[8] LU S,ZHAO J,JIANG L,et al.Solving the time-jerk optimal trajectory planning problem of a robot using augmented lagrange constrained particle swarm optimization[J].Mathematical Problems in Engineering,2017,2017(6):1-10.
[9] ROUT A,BBVL D,BISWAL B B,et al.Optimal trajectory planning of industrial robot for improving positional accuracy[J].Industrial Robot,2019,48(1):71-83.
[10] 曾氢菲,刘雪梅,冯焱,等.双光束激光焊接机器人轨迹优化[J].中国激光,2021,48(18):198-208.
[11] 曾氢菲,刘雪梅,邱呈溶.Inverse kinematics and error analysis of cooperative welding robot with multiple manipulators[J].中国焊接(英文版),2020,29(2):8.
[12] 苏俊,熊瑞平,温记明,等.基于改进粒子群算法的六自由度工业机器人轨迹规划[J].制造技术与机床,2022(10):38-45.
[13] 何建成,李林升,林国湘.基于多目标粒子群算法工业机器人最优轨迹规划[J].制造业自动化,2021,43(2):57-62.
[14] 李林.六轴工业机器人的轨迹规划和声纹控制研究[D].重庆:重庆大学,2021.
[15] 徐可欣.六轴工业机器人轨迹规划算法研究[D].南京:南京航空航天大学,2020.
[16] 李昊天.基于能耗优化及时间优化综合评估的工业机器人轨迹规划研究[D].杭州:浙江大学,2020.
[17] 张溯.冗余双臂工业机器人轨迹规划研究[D].西安:西安理工大学,2019.
[18] 郝奇,许四祥,江天琦,等.基于ROS的机器人等离子切割板坯毛刺运动规划[J].重庆理工大学学报(自然科学),2018,32(9):61-66.
[19] 陈栋,李世其,王峻峰,等.并联机构的运动学多目标轨迹规划方法[J].机械工程学报,2019,55(15):163-173.
[20] XUE J,SHEN B.A novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science & Control Engineering, 2020,8(1):22-34.
[21] HORNIK K,STINCHCOMBE M,WHITE H.Multilayer feedforward networks are universal approximators[J].Neural Networks,1989,2(5):359-366.
[22] DEB K,PRATAP A,AGARWAL S,et al.A fast and elitist multiobjective genetic algorithm:NSGA-II[J].IEEE Transactions on Evolutionary Computation,2002,6(2):182-197.
[23] GUERRERO-PEA E,AFR A. Multi-objective evolutionary algorithm with prediction in the objective space[J].Information Sciences,2019,501:293-316.