HapticVLA achieves tactile-aware robotic manipulation at 86.7% success rate without requiring any physical tactile sensors at inference time.
March 17, 2026
Original Paper
HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing
arXiv · 2603.15257
The Takeaway
It uses a teacher-student distillation framework where tactile knowledge is learned offline and distilled into a vision-only model. This democratizes high-dexterity manipulation by removing the cost and hardware complexity of tactile sensors for deployment.
From the abstract
Tactile sensing is a crucial capability for Vision-Language-Action (VLA) architectures, as it enables dexterous and safe manipulation in contact-rich tasks. However, reliance on dedicated tactile hardware increases cost and reduces reproducibility across robotic platforms. We argue that tactile-aware manipulation can be learned offline and deployed without direct haptic feedback at inference. To this end, we present HapticVLA, which proceeds in two tightly coupled stages: Safety-Aware Reward-Wei