RoboStriker: Latent-Space Strategic Games for Autonomous Humanoid Boxing

• URL: http://arxiv.org/abs/2608.16195v1
• Date: Mon, 17 Aug 2026 07:19:09 GMT
• Title: RoboStriker: Latent-Space Strategic Games for Autonomous Humanoid Boxing
• Abstract summary: RoboStriker is a novel two-player latent-space zero-sum Markov game.<n>It first distills the tracking expertise of predefined boxing motions into a topologically bounded latent manifold.<n>RoboStriker substantially reduces the catastrophic balance failures observed in raw action-space methods.<n>It achieves superior tactical performance in both competitive win rates and striking efficiency.
• Score: 42.646050136986155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Achieving human-level competitive intelligence and physical agility in humanoid robots remains a profound challenge, particularly in contact-rich and highly dynamic tasks such as boxing. While Multi-Agent Reinforcement Learning offers a principled framework for strategic interaction, its direct application to unstructured raw motor spaces inevitably leads to joint-level physical collapse, preventing the emergence of any viable combat tactics. To resolve this fundamental conflict between strategic exploration and physical feasibility, we formulate the humanoid combat task as a novel two-player latent-space zero-sum Markov game. Under standard regularity and approximate best-response assumptions, we show that the latent formulation induces an equivalent game over the decoder-reachable action manifold, providing an approximate-Nash interpretation of the resulting self-play dynamics. To instantiate this theoretical formulation, we propose RoboStriker, a hierarchical framework that decouples high-level reasoning from low-level execution. It first distills the tracking expertise of predefined boxing motions into a topologically bounded latent manifold. This structured latent foundation subsequently drives multi-agent co-evolution via Latent-Space Neural Fictitious Self-Play. Extensive experimental results demonstrate that gaming within this structured latent space substantially outperforms direct exploration. By constraining strategic exploration through a pretrained motion decoder, RoboStriker substantially reduces the catastrophic balance failures observed in raw action-space methods and achieves superior tactical performance in both competitive win rates and striking efficiency. Finally, we successfully deploy and validate our learned combat policies on real-world humanoid robots. Our code and video and supplementary materials are available at RoboStriker.

Related papers

• RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting [52.18271301977709]
  We propose RPG, a hybrid expert policy framework, for smooth and stable humanoid multi-skills transition.<n>Our approach incorporates motion transition randomization and temporal randomization to train a unified policy that generates agile fighting actions.<n>We design a control pipeline that integrates walking/running locomotion with fighting skills, allowing humanlike long-time combat of arbitrary duration.
  arXiv  Detail & Related papers  (2026-04-23T07:14:35Z)
• SMASH: Mastering Scalable Whole-Body Skills for Humanoid Ping-Pong with Egocentric Vision [53.709632118234936]
  Methodname is a modular system for agile humanoid table tennis.<n>It unifies scalable whole-body skill learning with onboard egocentric perception.<n>We demonstrate the first humanoid table-tennis system capable of consecutive strikes using onboard sensing alone.
  arXiv  Detail & Related papers  (2026-04-01T17:11:52Z)
• Diff-Muscle: Efficient Learning for Musculoskeletal Robotic Table Tennis [21.901628569185515]
  We propose Diff-Muscle, a musculoskeletal robot control algorithm that reformulates policy learning from the redundant muscle-activation space into a significantly lower-dimensional joint space.<n>Specifically, we propose a hierarchical reinforcement learning framework that integrates a Kinematics-based Muscle Actuation Controller (K-MAC) with high-level trajectory planning.<n> Experimental results demonstrate that Diff-Muscle significantly outperforms state-of-the-art baselines in success rates while maintaining minimal muscle activation.
  arXiv  Detail & Related papers  (2026-03-09T17:00:28Z)
• Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching [77.28042137892943]
  We present Perceptive Humanoid Parkour (PHP), a modular framework that enables humanoid robots to autonomously perform long-horizon, vision-based parkour.<n>We train motion-tracking reinforcement learning expert policies for these composed motions, and distill them into a single depth-based, multi-skill student policy.<n>We validate our framework with extensive real-world experiments on a Unitree G1 humanoid robot.
  arXiv  Detail & Related papers  (2026-02-17T18:59:11Z)
• Learning Human-Like Badminton Skills for Humanoid Robots [25.27775061243493]
  We propose a progressive reinforcement learning framework designed to evolve a robot from a "mimic" to a capable "striker"<n>Our approach establishes a robust motor prior from human data, distills it into a compact, model-based state representation, and stabilizes dynamics via adversarial priors.<n>We validate our framework through the mastery of diverse skills, including lifts and drop shots, in simulation.
  arXiv  Detail & Related papers  (2026-02-09T08:09:52Z)
• Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework [50.6604971348824]
  Soccer presents a significant challenge for humanoid robots, demanding tightly integrated perception-action capabilities.<n>We propose Perception-Action integrated Decision-making (PAiD), a progressive architecture that decomposes soccer skill acquisition into three stages.<n> Experiments on the Unitree G1 demonstrate high-fidelity human-like kicking with robust performance under diverse conditions.
  arXiv  Detail & Related papers  (2026-02-05T05:05:03Z)
• RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing [43.240817529539356]
  RoboStriker is a hierarchical three-stage framework that enables fully autonomous humanoid boxing.<n>The framework first learns a comprehensive repertoire of boxing skills by training a single-agent motion tracker on human motion capture data.<n>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.
  arXiv  Detail & Related papers  (2026-01-30T03:51:58Z)
• Robot Crash Course: Learning Soft and Stylized Falling [7.959692704349906]
  We aim to reduce physical damage to the robot while providing users with control over a robot's end pose.<n>Our work demonstrates that even bipedal robots can perform controlled, soft falls.
  arXiv  Detail & Related papers  (2025-11-13T18:55:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.