Abstract
Imitation learning for contact-rich manipulation requires high-quality expert data that is expensive to obtain. This makes learning a sample-efficient policy a key issue. To address this, we propose VISTA, a workspace-level equivariant visuotactile diffusion policy for data-efficient contact-rich imitation learning. VISTA projects visual and tactile observations into spherical tokens, injects tactile contact cues into visual spherical directions through permutation-equivariant spherical fusion, and rotates the fused harmonic representation using the end-effector orientation. The resulting representation conditions an equivariant diffusion policy to predict spatially consistent actions. Extensive experiments in both simulation and real-world robotic settings show that VISTA substantially improves data efficiency over strong visuotactile imitation learning baselines. Project website: https://vista-paper.github.io/
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wong, L. H. K., Ma, Y., Wei, X. S., Tan, Z., Song, Z., Xie, D., Chen, K., & Dou, Q. (2026). Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation. https://omanscience.com/en/articles/equivariant-visual-tactile-diffusion-policy-for-contact-rich-manipulation
MLA 9
Wong, Lik Hang Kenny, et al. "Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation." https://omanscience.com/en/articles/equivariant-visual-tactile-diffusion-policy-for-contact-rich-manipulation.
Chicago (author–date)
Wong, Lik Hang Kenny, Yiyao Ma, Xiu-Shen Wei, Zelong Tan, Zhuheng Song, Dongsheng Xie, Kai Chen, and Qi Dou. 2026. "Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation." https://omanscience.com/en/articles/equivariant-visual-tactile-diffusion-policy-for-contact-rich-manipulation.
Harvard
Wong, L. H. K., Ma, Y., Wei, X. S., Tan, Z., Song, Z., Xie, D., Chen, K. and Dou, Q. (2026) 'Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation', Available at: https://omanscience.com/en/articles/equivariant-visual-tactile-diffusion-policy-for-contact-rich-manipulation.
Vancouver
Wong LHK, Ma Y, Wei XS, Tan Z, Song Z, Xie D, et al. Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation. https://omanscience.com/en/articles/equivariant-visual-tactile-diffusion-policy-for-contact-rich-manipulation
IEEE
L. H. K. Wong, Y. Ma, X. S. Wei, Z. Tan, Z. Song, D. Xie, K. Chen, and Q. Dou, "Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation," https://omanscience.com/en/articles/equivariant-visual-tactile-diffusion-policy-for-contact-rich-manipulation.