An Improved RRT* Algorithm for Robotic Arms via Multi-strategy Fusion
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
To solve low search efficiency, poor path smoothness, and redundant nodes in robotic arm path planning in complex environments, this paper proposes an improved RRT* algorithm via multi-strategy fusion. It uses dynamic target biasing to boost search directionality, specific region sampling to cut invalid nodes, maximum safety distance direct-connection to shorten path length and search time, dynamic polygon pruning to reduce node redundancy, and cubic B-spline curves to optimize smoothness. Experiments show that vs traditional RRT and RRT*, it reduces average path length by 13.6%, planning time by 62.2%, and achieves 99% success rate in simple environments; in complex environments, it stably finds feasible paths with better smoothness, fitting practical obstacle avoidance path planning, significantly improves the efficiency, accuracy, and stability of path search.
Fields of Study & Subjects
Robotic Path Planning Algorithms
Reinforcement Learning in Robotics
Robotic Mechanisms and Dynamics
Publication details
- Journal / source
- IEEE International Conference on Power, Electronics and Green Energy (ICPEGE)
- Pages
- 340–346
- Publication date
- 28 January 2026
- Language
- EN