Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data

Key points

• Workhorse learns such manipulation from robot-free human demonstrations.1
• A reinforcement-learning whole-body tracker follows them on the robot.1
• During box sorting, we show recoveries after a person pushes the robot or takes the box away.1
• With both policies retrained from the same demonstrations, a simulated second humanoid completes box sorting in 83% of episodes without pushes.1

Sources (1)

• [1]Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 09:06 PM

  Humanoid robots still struggle to plan contact-rich whole-body manipulation from egocentric RGB and proprioception.

  Workhorse learns such manipulation from robot-free human demonstrations.

Extractive summary: sentences quoted from the sources.