Reflex teaches a Unitree G1 humanoid to catch boxes thrown by humans
DJiafei · x · 2026-10-09
The Reflex framework enables a Unitree G1 humanoid to catch human-thrown boxes using only onboard RGB-D sensing, with about one second to perceive, predict and move the whole body. The team argues catching is harder than fighting for humanoids, requiring whole-body control, real-time object dynamics reaction, and egocentric visual grounding. Training details, results and open-source code follow in the thread.
Related event: Reflex Lets Unitree G1 Catch Tossed Boxes in About a Second(8 posts)→
More from Embodied
- Princeton's Intro to Robotics planning & control module: videos, notes, code all free — Majumdar_Ani · 2026-10-09
- Robotics IPOs in Hong Kong: 'still better than Solana memecoins' — LexSokolin · 2026-10-09
- China's AI-powered AR glasses: a real-world copilot guiding repairs and assembly — alexmacgregor__ · 2026-10-09
- 10+ robot teams compete to fold paper planes, testing tactile sensing and bimanual control — micoolcho · 2026-10-09
- Sabi raises $50M to build the world's most wearable BCI cap, backed by ex-OpenAI CPO Kevin Weil — LexSokolin · 2026-10-09
- Earth Rover Challenge wraps at IROS 2026: 12 teams, 4 tracks, 3 days of sidewalk robot navigation — micoolcho · 2026-10-09