NVIDIA's ScheduleGen generates collision-aware multi-arm robot training data via MILP scheduling
AjayMandlekar · x · 2026-10-31
NVIDIA and UT Austin researchers introduce ScheduleGen, a synthetic demonstration-generation pipeline for multi-arm imitation learning. It adapts object-relative contact skills, plans per-arm joint-space paths, and solves a MILP for collision/ordering/synchronization constraints, keeping only validated trajectories. Beyond bimanual setups it covers cluttered shared workspaces, long-horizon contact, four-arm systems, and a fixed-waist humanoid. Across 28 simulation variants it achieves 79.6% mean generation success and 65.5% learned-policy success, with 50–80% real-world success via sim-to-real and real-to-sim-to-real transfer.
Related event: NVIDIA Unveils ScheduleGen for Multi-Arm Robot Training Data(2 posts)→
More from Embodied
- Agility Robotics lost $138.1M in 2025 as Brett Adcock's doom prediction nears — Rewkang · 2026-10-31
- Promised the Year of Physical AI: Humanoid Robots Are Behind Schedule — Distinct-Question-16 · 2026-10-31
- PokeBot's RoboAPI brings the call-a-model pattern to robot arms, no task training needed — rohanpaul_ai · 2026-10-31
- Foundry Robotics raises $100M Series A to build factories that look like data centers — ishabytes · 2026-10-31
- NVIDIA's MotionBricks robotics motion-generation model trends on Hugging Face — nvidia · 2026-10-31
- Agility Robotics to raise $465M ahead of Nasdaq debut as AGLT on Nov 5, Foxconn leads with $201M — xmercury_one · 2026-10-31