Research on trajectory learning and modification method based on improved dynamic movement primitives

Abstract

Traditional robot trajectory planning and programming methods often struggle to adapt to changing working requirements, leading to repeated programming in manufacturing processes. To address these challenges, a trajectory learning and modification method based on improved Dynamic Movement Primitives (DMPs), called FDC-DMP, is proposed. The method introduces an improved force-controlled dynamic coupling term (FDCT) that uses virtual force as coupling force. This enhancement enables precise and flexible shape modifications within the target trajectory range. The paper also dissects the core dynamic systems of DMP to achieve the reproduction and generalization of both robot position and pose trajectories. The practical feasibility of the proposed method in manufacturing is demonstrated through two case studies on trajectory planning for bus body polishing.