Stanford's I3L boosts whole-body robot deployment success by 68.3 points
jiajunwu_cs · x · 2026-10-30
Stanford's Fei-Fei Li group, with Lambda and Northwestern, introduces I3L, a hardware-plus-learning system that closes the last-mile reliability gap for long-horizon whole-body mobile manipulation.
Key points:
- JoyLo+: a low-cost, open-source interface with policy-tracking leader arms and touch-triggered takeover, letting operators correct arms, torso, and mobile base in a coordinated way
- Iterative loop: targeted corrections near failures are aggregated with prior demos, the policy is retrained, and the improved policy is redeployed to surface new failure modes
- Results: evaluated across 3 robot embodiments and 8 simulated and real-world tasks (including 4 long-horizon mobile manipulation tasks); under a four-round HG-DAgger protocol, I3L improves autonomous success over base policies by an average of 68.3 percentage points
- Paper, code, models, and datasets are open-sourced
More from Embodied
- Hugging Face co-founder Thom Wolf: give this robot an Oscar — Thom_Wolf · 2026-10-30
- Musk on Tesla vs Waymo robotaxis: 'It was never a real contest' — AccBalanced · 2026-10-30
- LA adds 11,000 aerospace jobs in two years as physical AI and defense tech boom — builditwithjoe · 2026-10-30
- Pokebot launches RoboAPI: a public API for near-real-time robot action prediction — CyberRobooo · 2026-10-30
- AGIBOT unveils 'Worken' metric: robots × autonomous hours × output efficiency — xmercury_one · 2026-10-30
- SCRUB-1: Fine-tuned π0.5 Robot Arm Lifts Surgical Instrument Handoff From 0% to 79% — StewartalsopIII · 2026-10-30