CHORUS trains one VLA to coordinate multiple robots on manipulation tasks
chris_j_paxton · x · 2026-07-29
The repost highlights CHORUS, a system that trains a single VLA to coordinate multiple diverse robots using only local observations and identifying information.
The key claim is scalability: instead of relying on bespoke centralized control, the same model can support collaboration on manipulation tasks such as measuring with a tape, handing over a book, and lifting a laundry basket.
Related event: CHORUS: Single VLA Model Enables Decentralized Multi-Robot Collaboration(6 posts)→
More from Embodied
- GPT-6 tested on LIBERO robot task: turns on stove, fails to grasp moka pot — YuXiang_IRVL · 2026-09-23
- OpenRoboto Shift launches: decentralized egocentric video data network for robot brains — markjeffrey · 2026-09-23
- OpenRoboto launches decentralized rival to Figure's robot data network on Bittensor — markjeffrey · 2026-09-23
- Typesafe's decision model Jev drives a Go2 robot inside NVIDIA Isaac Sim via OM1 — paigeinsf · 2026-09-23
- Tesla pitches Optimus as the first general-purpose humanoid robot — XFreeze · 2026-09-23
- XPENG's IRON robot demos full-duplex speech with 9-mic array and lip reading — ChrisGPT · 2026-09-23