To address the inverse kinematics challenge arising from the joint redundancy in mobile platform-arm coupled systems, the traditional pseudo-inverse matrix-based methods are sensitive to singularity. This paper proposes an improved algorithm that integrates reinforcement learning (RL) and differential evolution (DE) to solve the inverse kinematics problem for highly redundant mobile robotic arms. The optimization model in the DE algorithm is constructed based on the physical model of the mobile robotic arms, with the fitness function defined as the error between the target pose and the desired end-effector pose of the mobile robotic arms. To overcome the limitations of fixed evolutionary parameters in conventional DE algorithm and enhance both global search capability and convergence speed, a dynamic mutation multi-strategy mechanism that adaptively adjusts evolutionary directions at different stages to balance global exploration and local exploitation is proposed. Furthermore, the deep deterministic policy gradient (DDPG) algorithm is employed to optimize the evolutionary parameters, in which variation in population fitness and diversity serves as state inputs, and the improvement rate of the best individual’s fitness acts as the reward signal. Simulation results demonstrate that the proposed method eliminates the need for matrix inversion, effectively circumventing singularity issues and outperforming artificial bee colony, particle swarm optimization, and self-adaptive differential evolution algorithms in terms of inverse kinematics success rate and positioning accuracy. Additionally, it outperforms the self-adaptive differential evolution algorithm in trajectory smoothness and tracking precision, and exhibits lower average error in trajectory tracking.
CHENF, SELVAGGIOM, CALDWELLD G .Dexterous grasping by manipulability selection for mobile manipulator with visual guidance[J].IEEE Transactions on Industrial Informatics,2019,15(2):1202-1210.
[2]
LIM H, QIAOL J .A review and comparative study of differential evolution algorithms in solving inverse kinematics of mobile manipulator[J].Symmetry,2023,15(5):1080.
LIC M, RENK Z, GONGJ .Inverse kinematics solution of cleaning mobile manipulator based on improved genetic algorithm[J].Acta Energiae Solaris Sinica,2022,43(7):180-185.(in Chinese)
[5]
ZHAOG J, TAOB, JIANGD,et al .A closed-form inverse kinematic analytical method for seven-DOF space manipulator with aspheric wrist structure[J].Machines,2024,12(9):632.
[6]
COLANJ, DAVILAA, HASEGAWAY .Variable step sizes for iterative Jacobian-based inverse kinematics of robotic manipulators[J].IEEE Access,2024,12:87909-87922.
BAIY H, LUOM Z, PANGF L .An algorithm for solving robot inverse kinematics based on FOA optimized BP neural network[J].Applied Sciences,2021,11(15):7129.
[9]
AGGARWALL, AGGARWALK, URBANICR J .Use of artificial neural networks for the development of an inverse kinematic solution and visual identification of singularity zone(s)[J].Procedia CIRP,2014,17:812-817.
[10]
RAMR V, PATHAKP M, JUNCOS J .Inverse kinematics of mobile manipulator using bidirectional particle swarm optimization by manipulator decoupling[J].Mechanism and Machine Theory,2019,131:385-405.
[11]
NGUYEN-VANS, LIEUQ X, XUAN-MUNGN,et al..A new study on optimization of four-bar mechanisms based on a hybrid-combined differential evolution and jaya algorithm[J]. Symmetry,2022,14(2):381.
[12]
LIUY Y, XIJ L, BAIH F,et al .A general robot inverse kinematics solution method based on improved PSO algorithm[J].IEEE Access,2021,9:32341-32350.
[13]
KHALEELH Z .Inverse kinematics solution for redundant robot manipulator using combination of GA and NN[J].Al-Khwarizmi Engineering Journal,2018,14(1):136-144.
[14]
WONGC C, FENGH M, LAIY C,et al .Ant colony optimization and image model-based robot manipulator system for pick-and-place tasks[J]. Journal of Intelligent & Fuzzy Systems,2019,36(2): 1083-1098.
[15]
LOPEZ-FRANCOC, HERNANDEZ-BARRAGANJ, ALANISA Y,et al .A soft computing approach for inverse kinematics of robot manipulators[J]. Engineering Applications of Artificial Intelligence,2018,74:104-120.
[16]
LÓPEZ-FRANCOC, HERNÁNDEZ-BARRAGÁNJ, ALANISA Y,et al .Inverse kinematics of mobile manipulators based on differential evolution[J].International Journal of Advanced Robotic Systems,2018,15:1729881417752738.
[17]
HERNANDEZ-BARRAGANJ, LOPEZ-FRANCOC, ARANA-DANIELN,et al .Inverse kinematics for cooperative mobile manipulators based on self-adaptive differential evolution[J].PeerJ Computer Science,2021,7: e419.
[18]
ZHANGQ Q, WANGD Q, GAOL F .Research on the inverse kinematics of manipulator using an improved self-adaptive mutation differential evolution algorithm[J]. International Journal of Advanced Robotic Systems,2021,18(3):17298814211014413.
[19]
MINC, ZHANGM, ZHANGQ X,et al .A two-stage adaptive differential evolution algorithm with accompanying populations[J]. Mathematics,2025,13(3):440.
[20]
蔡自兴, 谢斌. 机器人学[M]. 3版.北京:清华大学出版社,2015:40-42.
[21]
CAIZ X, XIEB.Robotics[M]. 3rd ed.Beijing:Tsinghua University Press, 2015: 40-42.(in Chinese)
[22]
YANGQ Y, CHUS C, PANJ S,et al .Dynamic multi-strategy integrated differential evolution algorithm based on reinforcement learning for optimization problems[J]. Complex & Intelligent Systems,2024,10(2):1845-1877.
BAIJ H, LIJ J, WANGM J. An efficient artificial bee colony algorithm for analytical inverse kinematics of redundant manipulator[C]//7th International Conference on Intelligent Robotics and Control Engineering (IRCE). August 7-9,2024,Xi’an,China.IEEE,2024:117-123.
[25]
COLLINSMT J, SHENW M. Particle Swarm Optimization for high-DOF inverse kinematics[C]//3rd International Conference on Control,Automation and Robotics (ICCAR). April 24-26,2017,Nagoya,Japan.IEEE,2017:1-6.
[26]
LIM H, LUOX, QIAOL J. Inverse kinematics of robot manipulator based on BODE-CS algorithm[J]. Machines,2023,11(6): 648.
[27]
ZHANGJ Q, SANDERSONA C .JADE:adaptive differential evolution with optional external archive[J]. IEEE Transactions on Evolutionary Computation, 2009, 13(5): 945-958.
[28]
BRESTJ, GREINERS, BOSKOVICB,et al .Self-adapting control parameters in differential evolution:a comparative study on numerical benchmark problems[J]. IEEE Transactions on Evolutionary Computation, 2006, 10(6): 646-657.