CHI 2026 best paper uses EMS and embodied AI to guide physical tasks
MacrinePhD · x · 2026-07-22
Researchers built an embodied AI system that tracks body pose, vision, and location to guide people through physical tasks in real time using electrical muscle stimulation (EMS).
- Instead of a fixed script, the system infers the next action and coordinates muscles step by step.
- The demo includes actions such as flexing the biceps to reach, stimulating the fingers to grip, and activating the triceps to lower a bike rack.
- The poster says the work won Best Paper at CHI 2026 and presents it as an example of AI moving into physical assistance, not just text or video.
- Code and details are linked, along with a demo video.
Related event: CHI 2026 Best Paper: Embodied AI Guides Human Actions via EMS(3 posts)→
More from Embodied
- Mundo turns a few room photos into an explorable, simulatable 3D world — at 1.5 FPS — mark_k · 2026-10-27
- Zurich Physical AI Hackathon puts attendees in a room with $1.5M of humanoids — ___Mufasaa · 2026-10-27
- Apple responds after iPhone Duo inner displays crack along the hinge — mobileraj · 2026-10-27
- VLA models encode task concepts as curved multi-dimensional geometry, 19-author study finds — ninamiolane · 2026-10-27
- Munro Live Posts Full Cybercab Engineering Deep-Dive Video — yunta_tsai · 2026-10-27
- Tesla's Robotaxi Fleet Keeps Growing in Austin — yunta_tsai · 2026-10-27