RAX learns precision robot skills with zero teleoperation, cuts inference from 72 min to 18 s
du_yilun · x · 2026-10-17
Du Yilun's team reports RAX operating real robots with ZERO teleoperation or action demonstrations, learning precision insertion, air-fryer manipulation, stain wiping, hidden-object tracking, Bandu tower assembly, and long-horizon mobile whole-body control.
Key details:
- The agent builds an articulated 3D model of the air fryer and plans on it; for 0.1 mm-clearance insertion it uses contact and force feedback to measure surfaces when depth sensing struggles.
- On RB-Y1, previously learned chair/cup/basket/box skills combine into a six-stage task; when conditions change, the agent updates only the relevant code while retaining working skills.
- Once exploration produces an autonomous program, execution becomes far more efficient: air-fryer inference overhead drops from 72 minutes to 18 seconds—about 241× lower.
- Experience persists on the robot and seeds the next task.
More from Embodied
- Researcher builds generative machine vision pipeline reconstructing scenes from monocular video — RexDouglass · 2026-10-17
- Starkey Launches Omega AI+ Hearing Aid With Quad DNN Architecture and Sleep Tracking — BrandonSawalich · 2026-10-17
- RAX open-sources everything: zero demos, all experiment sessions included — du_yilun · 2026-10-17
- RAX separates the coding agent workspace from the robot stack for multi-embodiment — du_yilun · 2026-10-17
- RAX scales robot exploration, not demos: zero teleop, +37 points on benchmarks — du_yilun · 2026-10-17
- Ocean robotics firm Ulysses runs multi-region missions, hires more robot deployers — espricewright · 2026-10-17