Apple's HALO: humanoid motion trained fully in simulation hits 91% success in real world
kevin_zakka · x · 2026-11-06
Apple released HALO (Perceptive Humanoid Motion from Simulation), trained entirely on synthetic data from 1,000 procedurally generated homes. It deploys zero-shot in 6 unseen real environments with a 91% success rate across 360 physical trials, fully onboard. The stack has three tiers: a VLM orchestrator (0.5 Hz) turning spoken requests into subtasks; a generator (3 Hz) using a frozen Qwen3.5-2B encoder with a DiT decoder and flow matching to plan 5s whole-body motion; and a 50 Hz tracker outputting targets for 29 joints. Tasks include sitting, crouching, box pushing, and following people. Paper, code, and project page are live.
More from Embodied
- University of Michigan's 26-lecture robotics math course (ROB 501) is free on YouTube — techNmak · 2026-11-06
- Musk: Tesla to wind down Cybertruck production mid-next year to boost Cybercab output — elonmusk · 2026-11-06
- Xinhua hires two UBTECH UWORLD U1 humanoid robots as news anchors — CyberRobooo · 2026-11-06
- SLA scales spatial-language-action models via continual pre-training with frozen 3D alignment — HKUSTGZ · 2026-11-06
- KAIST's DreamFree distills video diffusion representations for real-time robot control — kaist-ai · 2026-11-06
- Wayve details 'Learned Safety' approach to validate end-to-end AVs at scale — Jamie_Shotton · 2026-11-06