A Review of Motion Planning Algorithms for Robotic Arm Systems

Abstract

Motion planning plays a vital role in the field of robotics. This paper discusses the latest advancements made in the research and development of various algorithms and approaches in motion planning in the past five years, with a strong focus on robotic arm systems. Most of the recent motion planning algorithms are based on random sampling algorithms. More effective algorithms such as optimization-based, Probabilistic Movement Primitives (ProMPs)-based and physics-based methods are feasible research directions to explore to improve the effectiveness. The evaluation benchmarking of the algorithm is a worthy research direction. The model-based methods can improve the efficiency of the task, but it has less ability to deal with accidents. In contrast, the modelfreed methods can solve this problem, but it takes a long time to compute. This paper also provides an insight into robotic manipulation of rigid and non-rigid (deformable) objects is explored. Based on the study, some challenges and future research trends are summarized, and some algorithms and approaches are suggested for the most efficient use of the robotic arms.

Benchmarking of Robot Arm Motion Planning in Cluttered Environments

“…Motion planning is essential for industrial robots to ensure precise movements and avoid obstacles [1]. However, challenges persist, including limited generalizability across robotic arm systems and insufficient examination of cluttered environments [2]- [4].…”