AINav: Large Language Model-Based Adaptive Interactive Navigation
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_ | 1866917176078761984 |
|---|---|
| author | Zhou, Kangjie Mu, Yao Song, Haoyang Zeng, Yi Wu, Pengying Gao, Han Liu, Chang |
| author_facet | Zhou, Kangjie Mu, Yao Song, Haoyang Zeng, Yi Wu, Pengying Gao, Han Liu, Chang |
| contents | Robotic navigation in complex environments remains a critical research challenge. Traditional navigation methods focus on optimal trajectory generation within fixed free workspace, therefore struggling in environments lacking viable paths to the goal, such as disaster zones or cluttered warehouses. To address this problem, we propose AINav, an adaptive interactive navigation approach that proactively interacts with environments to create feasible paths to achieve originally unreachable goals. Specifically, we present a primitive skill tree for task planning with large language models (LLMs), facilitating effective reasoning to determine interaction objects and sequences. To ensure robust subtask execution, we adopt reinforcement learning to pre-train a comprehensive skill library containing versatile locomotion and interaction behaviors for motion planning. Furthermore, we introduce an adaptive replanning approach featuring two LLM-based modules: an advisor serving as a flexible replanning trigger and an arborist for autonomous plan adjustment. Integrated with the tree structure, the replanning mechanism allows for convenient node addition and pruning, enabling rapid plan adaptation in a priori unknown environments. Comprehensive simulations and experiments have demonstrated AINav's effectiveness and adaptivity in diverse scenarios. The supplementary video is available at: https://youtu.be/CjXm5KFx9AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22942 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AINav: Large Language Model-Based Adaptive Interactive Navigation Zhou, Kangjie Mu, Yao Song, Haoyang Zeng, Yi Wu, Pengying Gao, Han Liu, Chang Robotics Artificial Intelligence Robotic navigation in complex environments remains a critical research challenge. Traditional navigation methods focus on optimal trajectory generation within fixed free workspace, therefore struggling in environments lacking viable paths to the goal, such as disaster zones or cluttered warehouses. To address this problem, we propose AINav, an adaptive interactive navigation approach that proactively interacts with environments to create feasible paths to achieve originally unreachable goals. Specifically, we present a primitive skill tree for task planning with large language models (LLMs), facilitating effective reasoning to determine interaction objects and sequences. To ensure robust subtask execution, we adopt reinforcement learning to pre-train a comprehensive skill library containing versatile locomotion and interaction behaviors for motion planning. Furthermore, we introduce an adaptive replanning approach featuring two LLM-based modules: an advisor serving as a flexible replanning trigger and an arborist for autonomous plan adjustment. Integrated with the tree structure, the replanning mechanism allows for convenient node addition and pruning, enabling rapid plan adaptation in a priori unknown environments. Comprehensive simulations and experiments have demonstrated AINav's effectiveness and adaptivity in diverse scenarios. The supplementary video is available at: https://youtu.be/CjXm5KFx9AI. |
| title | AINav: Large Language Model-Based Adaptive Interactive Navigation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2503.22942 |