Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.03005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916540988784640 |
|---|---|
| author | Cai, Xiaoyi Queeney, James Xu, Tong Datar, Aniket Pan, Chenhui Miller, Max Flather, Ashton Osteen, Philip R. Roy, Nicholas Xiao, Xuesu How, Jonathan P. |
| author_facet | Cai, Xiaoyi Queeney, James Xu, Tong Datar, Aniket Pan, Chenhui Miller, Max Flather, Ashton Osteen, Philip R. Roy, Nicholas Xiao, Xuesu How, Jonathan P. |
| contents | Self-supervised learning is a powerful approach for developing traversability models for off-road navigation, but these models often struggle with inputs unseen during training. Existing methods utilize techniques like evidential deep learning to quantify model uncertainty, helping to identify and avoid out-of-distribution terrain. However, always avoiding out-of-distribution terrain can be overly conservative, e.g., when novel terrain can be effectively analyzed using a physics-based model. To overcome this challenge, we introduce Physics-Informed Evidential Traversability (PIETRA), a self-supervised learning framework that integrates physics priors directly into the mathematical formulation of evidential neural networks and introduces physics knowledge implicitly through an uncertainty-aware, physics-informed training loss. Our evidential network seamlessly transitions between learned and physics-based predictions for out-of-distribution inputs. Additionally, the physics-informed loss regularizes the learned model, ensuring better alignment with the physics model. Extensive simulations and hardware experiments demonstrate that PIETRA improves both learning accuracy and navigation performance in environments with significant distribution shifts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_03005 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain Cai, Xiaoyi Queeney, James Xu, Tong Datar, Aniket Pan, Chenhui Miller, Max Flather, Ashton Osteen, Philip R. Roy, Nicholas Xiao, Xuesu How, Jonathan P. Robotics Machine Learning Systems and Control Self-supervised learning is a powerful approach for developing traversability models for off-road navigation, but these models often struggle with inputs unseen during training. Existing methods utilize techniques like evidential deep learning to quantify model uncertainty, helping to identify and avoid out-of-distribution terrain. However, always avoiding out-of-distribution terrain can be overly conservative, e.g., when novel terrain can be effectively analyzed using a physics-based model. To overcome this challenge, we introduce Physics-Informed Evidential Traversability (PIETRA), a self-supervised learning framework that integrates physics priors directly into the mathematical formulation of evidential neural networks and introduces physics knowledge implicitly through an uncertainty-aware, physics-informed training loss. Our evidential network seamlessly transitions between learned and physics-based predictions for out-of-distribution inputs. Additionally, the physics-informed loss regularizes the learned model, ensuring better alignment with the physics model. Extensive simulations and hardware experiments demonstrate that PIETRA improves both learning accuracy and navigation performance in environments with significant distribution shifts. |
| title | PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain |
| topic | Robotics Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2409.03005 |