A novel framework for trajectory planning in robotic arm developed by integrating dynamical movement primitives with particle swarm optimization

Abstract

In human-robot collaboration, imitation learning and autonomous adaptation to new scenarios are pivotal concerns for robotic arms. To address these challenges, a novel framework (DMP-PSO) for trajectories planning in robotic arm is presented by integrating dynamical movement primitives (DMP) with particle swarm optimization (PSO) in this paper. Firstly, DMP is employed to learn and generalize motion trajectories. Secondly, the initial state and search region of PSO are enhanced based on the generalized trajectories to rapidly generate obstacle avoidance trajectories within the search region. Finally, the proposed DMP-PSO framework autonomously generates diverse trajectories for robotic arms encompassing obstacle avoidance paths through its ingenious design. The effectiveness of this framework is validated through various means. The numerical simulation results show that the trajectory planning based on DMP-PSO has good adaptability and strong consistency, and significantly improves the efficiency. Furthermore, virtual simulations along with physical experiments corroborate the exceptional robustness and practicality exhibited by the proposed framework.