Episode Details
Back to EpisodesLATENT: Teaching a Humanoid to Play Tennis from Imperfect Data
Published 4 months, 2 weeks ago
Description
Introduces a three-stage pipeline that extracts a latent action space from noisy, low-quality human motion capture, then trains a high-level RL policy in simulation to compose and execute dynamic whole-body tennis skills. Achieves volleys at human-level performance on a humanoid robot.