Apple's AMP1 hits #1 on NVIDIA RoboLab leaderboard by writing Python to control robots
chris_j_paxton · x · 2026-11-12
Apple AIML released "On Agentic Manipulation Policies" (AMP1): a frontier model controls robots by writing Python code against harnesses for sensing (RGB-D, calibration, fused point cloud), perception (correctable scene model), and motion (end-effector waypoints, gripper commands), deciding what to observe and verifying outcomes between steps. Results: #1 on RoboLab-120 leaderboard (86%), best zero-shot 95.2% on LIBERO-PRO, 100% on robosuite uni/bimanual, 96.0% on BEHAVIOR-1K mobile manipulation, 84.1% on RoboDojo. Team includes Vladlen Koltun; paper and code are public.
More from Embodied
- Ex-Tesla Autopilot simulation leads exit stealth at $1.1B valuation with $160M raised — heyshrutimishra · 2026-11-12
- MIMIC and BMW train video-action model hitting up to 100% success on industrial tasks — pess_r · 2026-11-12
- Simular launches box, a dedicated computer built for running AI agents — _akhaliq · 2026-11-12
- Dex hand hits 99% on rubber-band task — hardware, not AI, is the bottleneck — chris_j_paxton · 2026-11-12
- Dyna co-founder Jason Ma keynotes on scaling real-world robot foundation models — chris_j_paxton · 2026-11-12
- Roboticist: RL is mandatory for robots too, behavior cloning was a detour — chris_j_paxton · 2026-11-12