Generalizing kinematic skill learning to energy efficient dynamic motion planning using optimized Dynamic Movement Primitives

Abstract

In manufacturing, automating the generation of dynamic trajectories for diverse robots and loads in response to kinematic task requirements presents a significant challenge. Previous research has primarily addressed kinematic trajectory generation and dynamic motion planning as separate endeavors, with integrated solutions rarely explored. This paper presents a novel methodology that combines reinforcement learning (RL)-based kinematic skill learning, dynamic modeling and an enhanced version of Dynamic Movement Primitives (DMP). Utilizing a pre-established skill library, the RL-enabled method generates multiple kinematic trajectories that fulfill the specific task requirements. These trajectories are further refined by dynamic modeling, selecting paths that minimize energy consumption tailored to specific robot types and loads. The newly proposed Optimized Normalized Dynamic Motion Primitive (ON-DMP) enhances obstacle avoidance with minimal energy consumption, remaining effective in novel environments. Validated through both simulated and real-world experiments, this methodology shows robust results in improving task completion in dynamic real-world environments without the need of reprogramming.