USC's Heave-Ho trains Unitree G1 humanoids to collaborate, scales 2 to 10 robots
CyberRobooo · x · 2026-11-21
USC's Heave-Ho project teaches multiple Unitree G1 humanoids to collaborate on physical tasks. A fine-tuned Qwen3-VL-2B plans actions while robots coordinate via spoken leader commands through onboard mics — no network needed. Trained with just 2 robots, it scales to teams of 10 without retraining: 94.41% average success across 12 simulated tasks, 92/100 real-world trials. Paper, code, and HH-Bench are public.
More from Embodied
- Open-source humanoid Asimov starts wheeled variant on day 389 of development — freelerobot · 2026-11-21
- Wanting a full self-driving Tesla RV: futuristic Cybertruck-style camper concept — PaulYacoubian · 2026-11-21
- PhysLDM reconstructs deformable trajectories at 2.48mm precision with 78x token compression — jiqizhixin · 2026-11-21
- Open-source autonomous driving book's Chapter 4 compares Pure Pursuit, Stanley, rear-wheel feedback — 4310sy · 2026-11-21
- SAFI teaches VLA robots to stop safely mid-task, cutting takeover success to 1.3% — DM2-ND · 2026-11-21
- Berkeley open-sources Specialist: 3D-printed gripper for robot data, runs on real arms — SongShuran · 2026-11-21