Today for AI
HOT RADAR
agentHEAT 11.6°

AI CURATED HOT STORY · 11/7/2026

Apple Unveils HALO Humanoid Robot System With 91% Success Rate in Unmapped Environments

1 reports archived1 independent sourcesupdated 11/7/2026, 17:40:17
Synthesis & Latest Updates
1 Sources Cross-Validated

Apple's research team published an arXiv paper detailing HALO, a humanoid robot autonomy stack that layers a VLM task orchestrator, a DiT motion generator, and a reinforcement-learning tracker, deployed on a Unitree G1 with an onboard Mac mini for inference. Across 360 single-task trials in six previously unmapped real environments, HALO averaged a 91% success rate, though long-horizon composite tasks fell to 70% and the hardest combination to 50%. The team also open-sourced the data generation, training, and deployment code.

LATEST/Apple's research team published an arXiv paper detailing HALO, a humanoid robot autonomy stack that layers a VLM task orchestrator, a DiT motion generator, and a reinforcement-learning tracker, deployed on a Unitree G1 with an onboard Mac mini for inference. Across 360 single-task trials in six previously unmapped real environments, HALO averaged a 91% success rate, though long-horizon composite tasks fell to 70% and the hardest combination to 50%. The team also open-sourced the data generation, training, and deployment code.

Hourly heat curve

3 fully observed hours
Now
11.6
Peak
11.918:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·84 pts

    Apple Unveils HALO Humanoid Robot System With 91% Success Rate in Unmapped Environments

    • HALO uses a three-tier stack: a VLM orchestrator, a DiT motion generator, and a 50Hz reinforcement-learning tracking policy.
    • It hit 91% average success over 360 single-task trials in six unmapped real environments, but long-horizon composite tasks averaged only 70%, with the hardest at 50%.
    • Training data was synthesized in about 48 hours on 250 H100 GPUs, the motion generator trained on 64 B200s, and the full pipeline code is open-sourced.