Heave-Ho project page: decentralized multi-humanoid collaboration with zero network messages
CyberRobooo · x · 2026-11-21
The Heave-Ho project page (USC + VinMotion) details a decentralized framework for long-horizon multi-humanoid collaboration: the leader speaks the next team skill, followers hear it onboard and sync via a shared schedule — zero network messages between robots. A multi-agent post-training framework adapts a humanoid foundation tracking model, plus a vision-language planner. Trained with 2 identical robots, it scales to 10 and generalizes to heterogeneous teams; HH-Bench covers 12 tasks.
More from Embodied
- Open-source humanoid Asimov starts wheeled variant on day 389 of development — freelerobot · 2026-11-21
- 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