GR-BC learns robot skills from failed attempts, hitting ~91% success rate
jiqizhixin · x · 2026-11-18
Researchers from Zhejiang University, TeleAI, and Gamma Robotics introduce GR-BC, which learns from demonstrations, robot rollouts, and human corrections. It builds a goal-reachability graph across attempts (multi-view + gripper consistency), uses shortest-path search to estimate remaining steps, and weights action chunks in behavior cloning so useful fragments of failed trajectories count. With X-VLA it reports 91% mean success across four real manipulation tasks.
More from Embodied
- Genesis AI CEO says robots are 6-10 months from the 99.99% success rate needed for mass deployment — davidpattersonx · 2026-11-18
- Lex Sokolin amazed by 'incredible' robot marketing clip — LexSokolin · 2026-11-18
- Neuracore launches Policy Playback: preview robot policy predictions mid-training — stepjamUK · 2026-11-18
- Physical AI panel at MXV Capital AGM features live progress update from Lambda Surgical — ditzikow · 2026-11-18
- Boston Dynamics touts Spot robodog as a helping hand and extra set of eyes — xmercury_one · 2026-11-18
- Rodney Brooks, Roomba creator, calls today's humanoids learning dexterity 'pure fantasy' — lukas_m_ziegler · 2026-11-18