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
通过物理互动评估和后训练机器人政策是昂贵的,难以扩展的,激励行动条件的世界模型作为互动模拟器。然而,视觉上可信的预测可以歪曲接触动态,为政策评估和学习提供不可靠的反馈。我们引入了PhysCanvas,一个国家一致的视觉触摸世界模型,用于接触丰富的机器人操纵。PhysCanvas统一了多视角RGB、触摸图像、标记移位、任务状态和统一视觉空间内的行动。
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