Decentralized multi-humanoid transport: one policy, no comms, pinch-lift-move (decMHT)
tweetsatpreet · x · 2026-09-22
Oregon State's DRAIL lab (Bikram Pandit, Alan Fern) presents decMHT, a decentralized object-centric control abstraction letting teams of humanoid robots cooperatively pick up, transport, and hand off shared objects. Each humanoid is assigned a local attachment region on the object and learns gripperless bimanual pinching; one policy spans single-robot pickup, multi-robot transport, and robot-to-robot handover with no inter-robot communication. Notably, policies trained only on single-robot pickup already transfer nontrivially to cooperative settings. The lab also has related ICRA 2026 quadruped-arm and CoRL 2025 bipedal transport work, with hands as the next frontier.
More from Embodied
- Cybercab #67 joins Tesla's Austin robotaxi fleet — EricETesla · 2026-09-22
- Robot beats up human in a cage match in San Francisco — Charuru · 2026-09-22
- Stanford's three-tier controller gets GPT-6 Astra to 79.13% on RoboMME with just 3.63 calls per episode — DJiafei · 2026-09-22
- Saudi brand Ceer unveils Exobot, an AI-designed concept humanoid — aziz4ai · 2026-09-22
- Weekly AI Recap: Helix 2.5 Lifts Household Robot Success to 56%, World Models Meet Robot Control — TheTuringPost · 2026-09-22
- SemiAnalysis tears down A20 on TSMC N2, DRAM revealed in iPhone 18 Pro Max package — dylan522p · 2026-09-22