SO-TA replaces standard attention with optimal-transport alignment across vision, force/torque, and proprioception to improve diffusion-policy performance on real-robot insertion and wiping tasks.
Making sense of vision and touch: Self-supervised learning of multimodal representations for contact-rich tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spacetime Optimal-Transport Attention for Visuo-Haptic Imitation Learning of Contact-Rich Manipulation
SO-TA replaces standard attention with optimal-transport alignment across vision, force/torque, and proprioception to improve diffusion-policy performance on real-robot insertion and wiping tasks.