NVIDIA Unveils ScheduleGen for Multi-Arm Robot Training Data

NVIDIA and UT Austin researchers introduced ScheduleGen, a synthetic data-generation pipeline that uses MILP-based scheduling to create collaborative demonstration data for multi-arm imitation learning, addressing data scarcity in confined shared workspaces.

2026-10-31 ~ 2026-10-31 · 2 related posts

• NVIDIA's ScheduleGen generates collision-aware multi-arm robot training data via MILP scheduling — AjayMandlekar · 2026-10-31
• ScheduleGen: automated synthetic data generation for multi-arm robot manipulation — AjayMandlekar · 2026-10-31