Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2407.04056 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910527724191744 |
|---|---|
| author | Zhuang, Jiafan Han, Gaofei Xia, Zihao Wang, Boxi Li, Wenji Wang, Dongliang Hao, Zhifeng Cai, Ruichu Fan, Zhun |
| author_facet | Zhuang, Jiafan Han, Gaofei Xia, Zihao Wang, Boxi Li, Wenji Wang, Dongliang Hao, Zhifeng Cai, Ruichu Fan, Zhun |
| contents | In unseen and complex outdoor environments, collision avoidance navigation for unmanned aerial vehicle (UAV) swarms presents a challenging problem. It requires UAVs to navigate through various obstacles and complex backgrounds. Existing collision avoidance navigation methods based on deep reinforcement learning show promising performance but suffer from poor generalization abilities, resulting in performance degradation in unseen environments. To address this issue, we investigate the cause of weak generalization ability in DRL and propose a novel causal feature selection module. This module can be integrated into the policy network and effectively filters out non-causal factors in representations, thereby reducing the influence of spurious correlations between non-causal factors and action predictions. Experimental results demonstrate that our proposed method can achieve robust navigation performance and effective collision avoidance especially in scenarios with unseen backgrounds and obstacles, which significantly outperforms existing state-of-the-art algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04056 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robust Policy Learning for Multi-UAV Collision Avoidance with Causal Feature Selection Zhuang, Jiafan Han, Gaofei Xia, Zihao Wang, Boxi Li, Wenji Wang, Dongliang Hao, Zhifeng Cai, Ruichu Fan, Zhun Robotics In unseen and complex outdoor environments, collision avoidance navigation for unmanned aerial vehicle (UAV) swarms presents a challenging problem. It requires UAVs to navigate through various obstacles and complex backgrounds. Existing collision avoidance navigation methods based on deep reinforcement learning show promising performance but suffer from poor generalization abilities, resulting in performance degradation in unseen environments. To address this issue, we investigate the cause of weak generalization ability in DRL and propose a novel causal feature selection module. This module can be integrated into the policy network and effectively filters out non-causal factors in representations, thereby reducing the influence of spurious correlations between non-causal factors and action predictions. Experimental results demonstrate that our proposed method can achieve robust navigation performance and effective collision avoidance especially in scenarios with unseen backgrounds and obstacles, which significantly outperforms existing state-of-the-art algorithms. |
| title | Robust Policy Learning for Multi-UAV Collision Avoidance with Causal Feature Selection |
| topic | Robotics |
| url | https://arxiv.org/abs/2407.04056 |