RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing

Kangning Yin1,2,3*, Zhe Cao1,2*, Wentao Dong1,2, Weishuai Zeng2,4, Tianyi Zhang1, Qiang Zhang5,
Jingbo Wang2, Jiangmiao Pang2, Ming Zhou2, Weinan Zhang1,2,3,
Shanghai Jiao Tong University1, Shanghai Artificial Intelligence Laboratory2,
Shanghai Innovation Institute3, Peking University4,
The Hong Kong University of Science and Technology (Guangzhou)5,
arXiv

Abstract

Achieving human-level competitive intelligence and physical agility in humanoid robots remains a major challenge, particularly in contact-rich and highly dynamic tasks such as boxing. While Multi-Agent Reinforcement Learning (MARL) offers a principled framework for strategic interaction, its direct application to humanoid control is hindered by high-dimensional contact dynamics and the absence of strong physical motion priors. We propose RoboStriker, a hierarchical three-stage framework that enables fully autonomous humanoid boxing by decoupling high-level strategic reasoning from low-level physical execution. The framework first learns a comprehensive reper- toire of boxing skills by training a single-agent motion tracker on human motion capture data. These skills are subsequently distilled into a structured latent manifold, regularized by projecting the Gaussian-parameterized distribution onto a unit hypersphere. This topological constraint effectively confines exploration to the subspace of physically plausible motions. In the final stage, we introduce Latent-Space Neural Fictitious Self- Play (LS-NFSP), where competing agents learn competitive tactics by interacting within the latent action space rather than the raw motor space, significantly stabilizing multi-agent training. Experimental results demonstrate that RoboStriker achieves superior competitive performance in simulation and exhibits sim-to-real transfer.


Video Demonstrations


Isaaclab


stage3 warmup with a stationary player

stage3 neural fictitious selfplay

stage3 neural fictitious selfplay

Mujoco sim2sim validation

Realworld deploy(More clips are coming soon...)

Approach Overview


BibTeX

@misc{yin2026robostrikerhierarchicaldecisionmakingautonomous,
      title={RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing}, 
      author={Kangning Yin and Zhe Cao and Wentao Dong and Weishuai Zeng and Tianyi Zhang and Qiang Zhang and Jingbo Wang and Jiangmiao Pang and Ming Zhou and Weinan Zhang},
      year={2026},
      eprint={2601.22517},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2601.22517}, 
}