Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy 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_ | 1866912438072377344 |
|---|---|
| author | Yang, Taegeun Hwang, Jiwoo Jeong, Jeil Yoon, Minsung Yoon, Sung-Eui |
| author_facet | Yang, Taegeun Hwang, Jiwoo Jeong, Jeil Yoon, Minsung Yoon, Sung-Eui |
| contents | We propose a hierarchical reinforcement learning (HRL) framework for efficient Navigation Among Movable Obstacles (NAMO) using a mobile manipulator. Our approach combines interaction-based obstacle property estimation with structured pushing strategies, facilitating the dynamic manipulation of unforeseen obstacles while adhering to a pre-planned global path. The high-level policy generates pushing commands that consider environmental constraints and path-tracking objectives, while the low-level policy precisely and stably executes these commands through coordinated whole-body movements. Comprehensive simulation-based experiments demonstrate improvements in performing NAMO tasks, including higher success rates, shortened traversed path length, and reduced goal-reaching times, compared to baselines. Additionally, ablation studies assess the efficacy of each component, while a qualitative analysis further validates the accuracy and reliability of the real-time obstacle property estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15380 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy Learning Yang, Taegeun Hwang, Jiwoo Jeong, Jeil Yoon, Minsung Yoon, Sung-Eui Robotics We propose a hierarchical reinforcement learning (HRL) framework for efficient Navigation Among Movable Obstacles (NAMO) using a mobile manipulator. Our approach combines interaction-based obstacle property estimation with structured pushing strategies, facilitating the dynamic manipulation of unforeseen obstacles while adhering to a pre-planned global path. The high-level policy generates pushing commands that consider environmental constraints and path-tracking objectives, while the low-level policy precisely and stably executes these commands through coordinated whole-body movements. Comprehensive simulation-based experiments demonstrate improvements in performing NAMO tasks, including higher success rates, shortened traversed path length, and reduced goal-reaching times, compared to baselines. Additionally, ablation studies assess the efficacy of each component, while a qualitative analysis further validates the accuracy and reliability of the real-time obstacle property estimation. |
| title | Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.15380 |