Policy Contrastive Decoding for Robotic Foundation Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918465383694336 |
|---|---|
| author | Wu, Shihan Luo, Xu Zhang, Ji Xie, Junlin Song, Jingkuan Shen, Heng Tao Gao, Lianli |
| author_facet | Wu, Shihan Luo, Xu Zhang, Ji Xie, Junlin Song, Jingkuan Shen, Heng Tao Gao, Lianli |
| contents | Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are prone to learning spurious correlations from pre-training trajectories, adversely affecting their generalization capabilities beyond the training data. To tackle this, we propose a novel Policy Contrastive Decoding (PCD) approach, which redirects the robot policy's focus toward object-relevant visual clues by contrasting action probability distributions derived from original and object-masked visual inputs. As a training-free method, our PCD can be used as a plugin to improve different types of robot policies without needing to finetune or access model weights. We conduct extensive experiments on top of three open-source robot policies, including the autoregressive policy OpenVLA and the diffusion-based policies Octo and $π_0$. The obtained results in both simulation and real-world environments prove PCD's flexibility and effectiveness, e.g., PCD enhances the state-of-the-art policy $π_0$ by 8.9% in the simulation environment and by 108% in the real-world environment. Code and demos are publicly available at: https://koorye.github.io/PCD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_13255 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Policy Contrastive Decoding for Robotic Foundation Models Wu, Shihan Luo, Xu Zhang, Ji Xie, Junlin Song, Jingkuan Shen, Heng Tao Gao, Lianli Robotics Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are prone to learning spurious correlations from pre-training trajectories, adversely affecting their generalization capabilities beyond the training data. To tackle this, we propose a novel Policy Contrastive Decoding (PCD) approach, which redirects the robot policy's focus toward object-relevant visual clues by contrasting action probability distributions derived from original and object-masked visual inputs. As a training-free method, our PCD can be used as a plugin to improve different types of robot policies without needing to finetune or access model weights. We conduct extensive experiments on top of three open-source robot policies, including the autoregressive policy OpenVLA and the diffusion-based policies Octo and $π_0$. The obtained results in both simulation and real-world environments prove PCD's flexibility and effectiveness, e.g., PCD enhances the state-of-the-art policy $π_0$ by 8.9% in the simulation environment and by 108% in the real-world environment. Code and demos are publicly available at: https://koorye.github.io/PCD. |
| title | Policy Contrastive Decoding for Robotic Foundation Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.13255 |