# PhysCanvas: A Visuo-Tactile World Model for Robot Policy Evaluation and Learning

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/a47zp6w4oyfqhwsfupadtrpv6
- Original: https://arxiv.org/abs/2610.28613

## Summary

PhysCanvas is a state-consistent visuo-tactile world model for contact-rich robot manipulation that unifies multi-view RGB, tactile images, marker displacement, task state, and actions within a single vision space, sharing a video VAE and a pretrained generative backbone.