| title | PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration |
|---|---|
| authors | Chen-Yu Lin, Jing-Wen Chen, Hsueh-En Chang, Hung-An Chen, Sheng-Hsun Chang, Chi-Pin Huang, Fu-En Yang, Min-Hung Chen, Yi-Ting Chen, Yu-Chiang Frank Wang, Shao-Hua Sun |
| date | 2026-08-21 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2608.21031 |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We present PhysCaP, a Physics-Informed Code-as-Policy agent for active perception in robotic manipulation. While vision-language-action policies excel at imitating demonstrations, they rely on passive observation and fail to infer latent physical properties critical for manipulation. PhysCaP augments code-as-policy frameworks with a physics-informed exploration layer that enables explicit information-seeking through interaction. It introduces training-free physical property extraction modules that estimate object mass and stiffness from robot proprioception without additional sensors. To balance exploration costs and the efficiency of information obtained, PhysCaP employs a dual-agent design: a Planner that decides when to explore and when to stop, and a Prioritizer that filters implausible interactions and ranks the remainder using a heuristic priority score, enabling efficient, targeted exploration. We evaluate PhysCaP on real-world tabletop manipulation tasks (searching for hidden objects, detecting empty cans, and finding ripe avocados) and a simulated task in LIBERO. The results show that existing passive and naive interactive baselines either fail when physical properties are hidden or over-explore, whereas PhysCaP achieves comparable performance with fewer interactions and reduced execution time. Ablation studies further validate the effectiveness of the proposed physical property extraction modules. Project page: https://physcap.github.io |
cite
@misc{lin2026physcap,
title={PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration},
author={Chen-Yu Lin and Jing-Wen Chen and Hsueh-En Chang and Hung-An Chen and Sheng-Hsun Chang and Chi-Pin Huang and Fu-En Yang and Min-Hung Chen and Yi-Ting Chen and Yu-Chiang Frank Wang and Shao-Hua Sun},
year={2026},
eprint={2608.21031},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.21031}
}