Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

TL;DR

This paper introduces LATENT, a system that learns humanoid tennis skills from imperfect human motion data, enabling robots to perform dynamic tennis actions and sustain rallies with real players.

Contribution

LATENT leverages primitive motion fragments as priors to learn humanoid tennis skills, reducing data collection difficulty and enabling effective sim-to-real transfer.

Findings

Robust humanoid tennis policy learned from imperfect data

Successful real-world deployment on Unitree G1 robot

Ability to sustain multi-shot rallies with human players

Abstract

Human athletes demonstrate versatile and highly-dynamic tennis skills to successfully conduct competitive rallies with a high-speed tennis ball. However, reproducing such behaviors on humanoid robots is difficult, partially due to the lack of perfect humanoid action data or human kinematic motion data in tennis scenarios as reference. In this work, we propose LATENT, a system that Learns Athletic humanoid TEnnis skills from imperfect human motioN daTa. The imperfect human motion data consist only of motion fragments that capture the primitive skills used when playing tennis rather than precise and complete human-tennis motion sequences from real-world tennis matches, thereby significantly reducing the difficulty of data collection. Our key insight is that, despite being imperfect, such quasi-realistic data still provide priors about human primitive skills in tennis scenarios. With further correction and composition, we learn a humanoid policy that can consistently strike incoming balls under a wide range of conditions and return them to target locations, while preserving natural motion styles. We also propose a series of designs for robust sim-to-real transfer and deploy our policy on the Unitree G1 humanoid robot. Our method achieves surprising results in the real world and can stably sustain multi-shot rallies with human players. Project page: https://zzk273.github.io/LATENT/