Particle.news
Download on the App Store

LATENT Trains Unitree G1 Humanoid to Play Tennis From Imperfect Human Data

A correctable latent action space learned from short motion-capture fragments delivered reliable on-court returns in early trials.

Overview

  • In real-world tests, reported success ranged from a best-case 96.5% within 2.5 meters of a target to roughly 90% forehand and just under 80% backhand return rates, depending on source and metric.
  • Researchers collected about five hours of amateur motion-capture fragments for strokes and footwork to build priors for humanlike movement.
  • The team trained high-level policies via reinforcement learning in simulation with dynamics randomization and observation noise before transferring to the Unitree G1.
  • Across 10,000 evaluated trials, the system sustained multi-shot rallies with humans and outperformed prior methods in success rate, accuracy, and motion naturalness.
  • The preprint is posted on arXiv with open-source code available, and authors note current limits such as reliance on motion capture and simplified return tasks, with planned advances like active vision and multi-agent training.