Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zhikai, Lu, Haofei, Lian, Yunrui, Chen, Ziqing, Liu, Yun, Lin, Chenghuai, Xue, Han, Zeng, Zicheng, Qi, Zekun, Zheng, Shaolin, Luan, Qing, Wang, Jingbo, Xing, Junliang, Wang, He, Yi, Li
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914390565978112
author Zhang, Zhikai
Lu, Haofei
Lian, Yunrui
Chen, Ziqing
Liu, Yun
Lin, Chenghuai
Xue, Han
Zeng, Zicheng
Qi, Zekun
Zheng, Shaolin
Luan, Qing
Wang, Jingbo
Xing, Junliang
Wang, He
Yi, Li
author_facet Zhang, Zhikai
Lu, Haofei
Lian, Yunrui
Chen, Ziqing
Liu, Yun
Lin, Chenghuai
Xue, Han
Zeng, Zicheng
Qi, Zekun
Zheng, Shaolin
Luan, Qing
Wang, Jingbo
Xing, Junliang
Wang, He
Yi, Li
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2603_12686
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
Zhang, Zhikai
Lu, Haofei
Lian, Yunrui
Chen, Ziqing
Liu, Yun
Lin, Chenghuai
Xue, Han
Zeng, Zicheng
Qi, Zekun
Zheng, Shaolin
Luan, Qing
Wang, Jingbo
Xing, Junliang
Wang, He
Yi, Li
Robotics
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/
title Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
topic Robotics
url https://arxiv.org/abs/2603.12686