Zebin Xing, Yuhang Zheng, Yupeng Zheng, Yichen Zhang, Zichen Li, Shangqing Zhou, Yujie Zang, Yuchen Liu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28613 · open-access PDF
물리적 상호 작용을 통해 로봇 정책을 평가하고 훈련하는 것은 비용이 많이 들고 규모가 어렵고, 액션 조건이있는 세계 모델을 상호 작용 시뮬레이터로 동기 부여합니다. 그러나 시각적으로 합리적인 예측은 접촉 역학을 잘못 표현하여 정책 평가 및 학습을위한 신뢰할 수없는 피드백을 제공 할 수 있습니다. PhysCanvas는 통합 시각 공간 내의 다중 뷰 RGB, 터치 이미지, 마커 이동, 작업 상태 및 행동을 통합합니다.
Machine translation (Meta M2M100); the English original follows.
Evaluating and post-training robot policies through physical interaction is costly and difficult to scale, motivating action-conditioned world models as interactive simulators. However, visually plausible predictions can misrepresent contact dynamics, providing unreliable feedback for policy evaluation and learning. We introduce PhysCanvas, a state-consistent visuo-tactile world model for contact-rich robot manipulation. PhysCanvas unifies multi-view RGB, tactile images, marker displacement, task state, and actions within a unified vision space. All modalities share a video VAE and pretrained
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28613, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange