URPlanner: A Universal Paradigm For Collision-Free Robotic Motion Planning Based on Deep Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908380284583936 |
|---|---|
| author | Ying, Fengkang Zhang, Hanwen Wang, Haozhe Huang, Huishi Ang Jr, Marcelo H. |
| author_facet | Ying, Fengkang Zhang, Hanwen Wang, Haozhe Huang, Huishi Ang Jr, Marcelo H. |
| contents | Collision-free motion planning for redundant robot manipulators in complex environments is yet to be explored. Although recent advancements at the intersection of deep reinforcement learning (DRL) and robotics have highlighted its potential to handle versatile robotic tasks, current DRL-based collision-free motion planners for manipulators are highly costly, hindering their deployment and application. This is due to an overreliance on the minimum distance between the manipulator and obstacles, inadequate exploration and decision-making by DRL, and inefficient data acquisition and utilization. In this article, we propose URPlanner, a universal paradigm for collision-free robotic motion planning based on DRL. URPlanner offers several advantages over existing approaches: it is platform-agnostic, cost-effective in both training and deployment, and applicable to arbitrary manipulators without solving inverse kinematics. To achieve this, we first develop a parameterized task space and a universal obstacle avoidance reward that is independent of minimum distance. Second, we introduce an augmented policy exploration and evaluation algorithm that can be applied to various DRL algorithms to enhance their performance. Third, we propose an expert data diffusion strategy for efficient policy learning, which can produce a large-scale trajectory dataset from only a few expert demonstrations. Finally, the superiority of the proposed methods is comprehensively verified through experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20175 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | URPlanner: A Universal Paradigm For Collision-Free Robotic Motion Planning Based on Deep Reinforcement Learning Ying, Fengkang Zhang, Hanwen Wang, Haozhe Huang, Huishi Ang Jr, Marcelo H. Robotics Collision-free motion planning for redundant robot manipulators in complex environments is yet to be explored. Although recent advancements at the intersection of deep reinforcement learning (DRL) and robotics have highlighted its potential to handle versatile robotic tasks, current DRL-based collision-free motion planners for manipulators are highly costly, hindering their deployment and application. This is due to an overreliance on the minimum distance between the manipulator and obstacles, inadequate exploration and decision-making by DRL, and inefficient data acquisition and utilization. In this article, we propose URPlanner, a universal paradigm for collision-free robotic motion planning based on DRL. URPlanner offers several advantages over existing approaches: it is platform-agnostic, cost-effective in both training and deployment, and applicable to arbitrary manipulators without solving inverse kinematics. To achieve this, we first develop a parameterized task space and a universal obstacle avoidance reward that is independent of minimum distance. Second, we introduce an augmented policy exploration and evaluation algorithm that can be applied to various DRL algorithms to enhance their performance. Third, we propose an expert data diffusion strategy for efficient policy learning, which can produce a large-scale trajectory dataset from only a few expert demonstrations. Finally, the superiority of the proposed methods is comprehensively verified through experiments. |
| title | URPlanner: A Universal Paradigm For Collision-Free Robotic Motion Planning Based on Deep Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.20175 |