RAX lets a real robot explore for 2 hours and turn learned skills into reusable code — no demos needed
du_yilun · x · 2026-10-28
A UC Berkeley team unveils RAX: a real robot explores on its own for 2 hours, then runs the skills it learned as code. No demonstrations, no teleoperation — exploration itself is converted into reusable robot skills.
DU Yilun highlighted that the system can stack LEGO blocks using RAX. The work points to a self-supervised, real-robot skill-acquisition path for embodied AI.
More from Embodied
- GPT-6.1 Terra beats Opus 5.5 at real robot control, 3.7x better than GPT-5.6 from 3 months ago — ycombinator · 2026-10-28
- Robots gearing up for a roboparty: researcher teases policy still in training — andrew_n_carr · 2026-10-28
- OpenTac tactile sensors demoed at CoRL 2026 among 17 robot demos — _krishna_murthy · 2026-10-28
- Hybrid LLM agent scores 83.2%, beats nine VLA policies on new SO-101 robot arm benchmark — Truman Hickok · 2026-10-28
- cixliv: robot fighting may be the first realized market where bots beat average humans — cixliv · 2026-10-28
- Can the Hiwonder MentorPi T1 run fully offline as a robot pet? Pi 5 questioned — oulu2006 · 2026-10-28