When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911679523061760 |
|---|---|
| author | Alvarez, Maxime Watanabe, Ryo Crook, Paul Meymand, Afshin Zeinaddini Kurian, Suvin Ferreiro, Pablo Sano, Genki |
| author_facet | Alvarez, Maxime Watanabe, Ryo Crook, Paul Meymand, Afshin Zeinaddini Kurian, Suvin Ferreiro, Pablo Sano, Genki |
| contents | As end-to-end robotic policies are progressively deployed in the real world to solve real tasks, they face a gap between the training and inference conditions. Scaling the amount and diversity of the training data has shown some success in improving zero-shot generalization, yet robots still fail when faced with new, unseen test conditions. For instance, while robots with fixed frames of reference are common, those with moving frames pose a greater challenge for deployment. To address this specific instance of the issue, we present a study of strategies for encoding the robot's proprioceptive state to improve both in- and out-of-distribution performance at test time. Through a systematic study of joint representations, we find that a simple episode-wise relative frame provides the best trade-off between task performance and robustness, outperforming the baselines in extensive real-robot experiments conducted in a realistic test environment. The results suggest a practical path to leveraging data collected by robots with varying frames of reference and deployment to unseen test configurations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13067 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation Alvarez, Maxime Watanabe, Ryo Crook, Paul Meymand, Afshin Zeinaddini Kurian, Suvin Ferreiro, Pablo Sano, Genki Robotics Artificial Intelligence As end-to-end robotic policies are progressively deployed in the real world to solve real tasks, they face a gap between the training and inference conditions. Scaling the amount and diversity of the training data has shown some success in improving zero-shot generalization, yet robots still fail when faced with new, unseen test conditions. For instance, while robots with fixed frames of reference are common, those with moving frames pose a greater challenge for deployment. To address this specific instance of the issue, we present a study of strategies for encoding the robot's proprioceptive state to improve both in- and out-of-distribution performance at test time. Through a systematic study of joint representations, we find that a simple episode-wise relative frame provides the best trade-off between task performance and robustness, outperforming the baselines in extensive real-robot experiments conducted in a realistic test environment. The results suggest a practical path to leveraging data collected by robots with varying frames of reference and deployment to unseen test configurations. |
| title | When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.13067 |