Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914234725564416 |
|---|---|
| author | Bai, Junjie Chao, Yu-Wei Chen, Qizhi Gu, Jinwei Kim, Moo Jin Li, Zhaoshuo Li, Xuan Lin, Tsung-Yi Liu, Ming-Yu Ma, Nic Mo, Kaichun Qu, Delin Sun, Shangkun Xia, Hongchi Wei, Fangyin Zeng, Xiaohui |
| author_facet | Bai, Junjie Chao, Yu-Wei Chen, Qizhi Gu, Jinwei Kim, Moo Jin Li, Zhaoshuo Li, Xuan Lin, Tsung-Yi Liu, Ming-Yu Ma, Nic Mo, Kaichun Qu, Delin Sun, Shangkun Xia, Hongchi Wei, Fangyin Zeng, Xiaohui |
| contents | The 2025 BEHAVIOR Challenge is designed to rigorously track progress toward solving long-horizon tasks by physical agents in simulated environments. BEHAVIOR-1K focuses on everyday household tasks that people most want robots to assist with and these tasks introduce long-horizon mobile manipulation challenges in realistic settings, bridging the gap between current research and real-world, human-centric applications. This report presents our solution to the 2025 BEHAVIOR Challenge in a very close 2nd place and substantially outperforms the rest of the submissions. Building on $π_{0.5}$, we focus on systematically building our solution by studying the effects of training techniques and data. Through careful ablation studies, we reveal the scaling benefits in both the pre-training and post-training phases, leading to a validation Q-score of 0.345, significantly surpassing previous state-of-the-art performance. We summarize our practical lessons and design recommendations that we hope will provide actionable insights for the broader embodied AI community when adapting powerful foundation models to complex embodied scenarios. Project page: https://github.com/mli0603/openpi-comet |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10071 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge Bai, Junjie Chao, Yu-Wei Chen, Qizhi Gu, Jinwei Kim, Moo Jin Li, Zhaoshuo Li, Xuan Lin, Tsung-Yi Liu, Ming-Yu Ma, Nic Mo, Kaichun Qu, Delin Sun, Shangkun Xia, Hongchi Wei, Fangyin Zeng, Xiaohui Robotics The 2025 BEHAVIOR Challenge is designed to rigorously track progress toward solving long-horizon tasks by physical agents in simulated environments. BEHAVIOR-1K focuses on everyday household tasks that people most want robots to assist with and these tasks introduce long-horizon mobile manipulation challenges in realistic settings, bridging the gap between current research and real-world, human-centric applications. This report presents our solution to the 2025 BEHAVIOR Challenge in a very close 2nd place and substantially outperforms the rest of the submissions. Building on $π_{0.5}$, we focus on systematically building our solution by studying the effects of training techniques and data. Through careful ablation studies, we reveal the scaling benefits in both the pre-training and post-training phases, leading to a validation Q-score of 0.345, significantly surpassing previous state-of-the-art performance. We summarize our practical lessons and design recommendations that we hope will provide actionable insights for the broader embodied AI community when adapting powerful foundation models to complex embodied scenarios. Project page: https://github.com/mli0603/openpi-comet |
| title | Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge |
| topic | Robotics |
| url | https://arxiv.org/abs/2512.10071 |