USC's Heave-Ho coordinates 10 humanoids with zero network messages
CMHungSteven · x · 2026-11-21
USC researchers unveiled Heave-Ho, a decentralized framework for long-horizon multi-humanoid collaborative loco-manipulation, demoed with a G1 robot 'working at U-Haul'.
- A multi-agent post-training framework adapts a humanoid foundation tracking model to physically coupled interactions, enabling coordinated decentralized control from local observations alone
- A vision-language planner plus a speech-based leader-follower mechanism (leader speaks commands in English/Mandarin) synchronizes execution with zero network messages
- Trained with only 2 identical humanoids, it scales to 10-robot teams and generalizes to heterogeneous teams without retraining
- Introduces HH-Bench with 12 tasks for teams of 2-10 humanoids; consistently outperforms baselines
Paper and code are open-sourced.
More from Embodied
- USC's Heave-Ho trains Unitree G1 humanoids to collaborate, scales 2 to 10 robots — CyberRobooo · 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