Raising Body Ownership in End-to-End Visuomotor Policy Learning via Robot-Centric Pooling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929580567166976 |
|---|---|
| author | Zhuang, Zheyu Kyrki, Ville Kragic, Danica |
| author_facet | Zhuang, Zheyu Kyrki, Ville Kragic, Danica |
| contents | We present Robot-centric Pooling (RcP), a novel pooling method designed to enhance end-to-end visuomotor policies by enabling differentiation between the robots and similar entities or their surroundings. Given an image-proprioception pair, RcP guides the aggregation of image features by highlighting image regions correlating with the robot's proprioceptive states, thereby extracting robot-centric image representations for policy learning. Leveraging contrastive learning techniques, RcP integrates seamlessly with existing visuomotor policy learning frameworks and is trained jointly with the policy using the same dataset, requiring no extra data collection involving self-distractors. We evaluate the proposed method with reaching tasks in both simulated and real-world settings. The results demonstrate that RcP significantly enhances the policies' robustness against various unseen distractors, including self-distractors, positioned at different locations. Additionally, the inherent robot-centric characteristic of RcP enables the learnt policy to be far more resilient to aggressive pixel shifts compared to the baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04331 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Raising Body Ownership in End-to-End Visuomotor Policy Learning via Robot-Centric Pooling Zhuang, Zheyu Kyrki, Ville Kragic, Danica Robotics We present Robot-centric Pooling (RcP), a novel pooling method designed to enhance end-to-end visuomotor policies by enabling differentiation between the robots and similar entities or their surroundings. Given an image-proprioception pair, RcP guides the aggregation of image features by highlighting image regions correlating with the robot's proprioceptive states, thereby extracting robot-centric image representations for policy learning. Leveraging contrastive learning techniques, RcP integrates seamlessly with existing visuomotor policy learning frameworks and is trained jointly with the policy using the same dataset, requiring no extra data collection involving self-distractors. We evaluate the proposed method with reaching tasks in both simulated and real-world settings. The results demonstrate that RcP significantly enhances the policies' robustness against various unseen distractors, including self-distractors, positioned at different locations. Additionally, the inherent robot-centric characteristic of RcP enables the learnt policy to be far more resilient to aggressive pixel shifts compared to the baselines. |
| title | Raising Body Ownership in End-to-End Visuomotor Policy Learning via Robot-Centric Pooling |
| topic | Robotics |
| url | https://arxiv.org/abs/2411.04331 |