Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.17231 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916930340782080 |
|---|---|
| author | Ghani, Saad Abdul Wang, Zizhao Stone, Peter Xiao, Xuesu |
| author_facet | Ghani, Saad Abdul Wang, Zizhao Stone, Peter Xiao, Xuesu |
| contents | This paper introduces Dynamic Learning from Learned Hallucination (Dyna-LfLH), a self-supervised method for training motion planners to navigate environments with dense and dynamic obstacles. Classical planners struggle with dense, unpredictable obstacles due to limited computation, while learning-based planners face challenges in acquiring high-quality demonstrations for imitation learning or dealing with exploration inefficiencies in reinforcement learning. Building on Learning from Hallucination (LfH), which synthesizes training data from past successful navigation experiences in simpler environments, Dyna-LfLH incorporates dynamic obstacles by generating them through a learned latent distribution. This enables efficient and safe motion planner training. We evaluate Dyna-LfLH on a ground robot in both simulated and real environments, achieving up to a 25% improvement in success rate compared to baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17231 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination Ghani, Saad Abdul Wang, Zizhao Stone, Peter Xiao, Xuesu Robotics Machine Learning This paper introduces Dynamic Learning from Learned Hallucination (Dyna-LfLH), a self-supervised method for training motion planners to navigate environments with dense and dynamic obstacles. Classical planners struggle with dense, unpredictable obstacles due to limited computation, while learning-based planners face challenges in acquiring high-quality demonstrations for imitation learning or dealing with exploration inefficiencies in reinforcement learning. Building on Learning from Hallucination (LfH), which synthesizes training data from past successful navigation experiences in simpler environments, Dyna-LfLH incorporates dynamic obstacles by generating them through a learned latent distribution. This enables efficient and safe motion planner training. We evaluate Dyna-LfLH on a ground robot in both simulated and real environments, achieving up to a 25% improvement in success rate compared to baselines. |
| title | Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2403.17231 |