ELLIPSE: Evidential Learning for Robust Waypoints and Uncertainties
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910041574998016 |
|---|---|
| author | Dong, Zihao Chung, Chanyoung Kim, Dong-Ki Maulimov, Mukhtar Meng, Xiangyun Khambhaita, Harmish Agha-mohammadi, Ali-akbar Shaban, Amirreza |
| author_facet | Dong, Zihao Chung, Chanyoung Kim, Dong-Ki Maulimov, Mukhtar Meng, Xiangyun Khambhaita, Harmish Agha-mohammadi, Ali-akbar Shaban, Amirreza |
| contents | Robust waypoint prediction is crucial for mobile robots operating in open-world, safety-critical settings. While Imitation Learning (IL) methods have demonstrated great success in practice, they are susceptible to distribution shifts: the policy can become dangerously overconfident in unfamiliar states. In this paper, we present \textit{ELLIPSE}, a method building on multivariate deep evidential regression to output waypoints and multivariate Student-t predictive distributions in a single forward pass. To reduce covariate-shift-induced overconfidence under viewpoint and pose perturbations near expert trajectories, we introduce a lightweight domain augmentation procedure that synthesizes plausible viewpoint/pose variations without collecting additional demonstrations. To improve uncertainty reliability under environment/domain shift (e.g., unseen staircases), we apply a post-hoc isotonic recalibration on probability integral transform (PIT) values so that prediction sets remain plausible during deployment. We ground the discussion and experiments in staircase waypoint prediction, where obtaining robust waypoint and uncertainty is pivotal. Extensive real world evaluations show that \textit{ELLIPSE} improves both task success rate and uncertainty coverage compared to baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04585 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ELLIPSE: Evidential Learning for Robust Waypoints and Uncertainties Dong, Zihao Chung, Chanyoung Kim, Dong-Ki Maulimov, Mukhtar Meng, Xiangyun Khambhaita, Harmish Agha-mohammadi, Ali-akbar Shaban, Amirreza Robotics Robust waypoint prediction is crucial for mobile robots operating in open-world, safety-critical settings. While Imitation Learning (IL) methods have demonstrated great success in practice, they are susceptible to distribution shifts: the policy can become dangerously overconfident in unfamiliar states. In this paper, we present \textit{ELLIPSE}, a method building on multivariate deep evidential regression to output waypoints and multivariate Student-t predictive distributions in a single forward pass. To reduce covariate-shift-induced overconfidence under viewpoint and pose perturbations near expert trajectories, we introduce a lightweight domain augmentation procedure that synthesizes plausible viewpoint/pose variations without collecting additional demonstrations. To improve uncertainty reliability under environment/domain shift (e.g., unseen staircases), we apply a post-hoc isotonic recalibration on probability integral transform (PIT) values so that prediction sets remain plausible during deployment. We ground the discussion and experiments in staircase waypoint prediction, where obtaining robust waypoint and uncertainty is pivotal. Extensive real world evaluations show that \textit{ELLIPSE} improves both task success rate and uncertainty coverage compared to baselines. |
| title | ELLIPSE: Evidential Learning for Robust Waypoints and Uncertainties |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.04585 |