aiqbench analysis
This research demonstrates a hierarchical reinforcement learning framework enabling humanoid robots to execute complex badminton rallies using limited human motion data. By combining motion augmentation with an adversarial regularizer, the system achieves naturalistic whole-body coordination for dynamic strikes like jump returns on physical hardware. This work advances the practical application of AI in robotics by bridging the gap between sparse training data and high-speed athletic performance.
Humanoid Badminton: Learning Dynamic Racket Skills from Limited Human Motion Data
arXiv:2609.31840v1 Announce Type: new Abstract: High-speed racket sports provide a demanding testbed for humanoid robots, requiring time-critical decisions, precise striking, and dynamic whole-body coordination. In badminton, fast-changing shuttle trajectories require timely contact decisions, while successful returns demand precise racket pose and velocity within a brief contact window and across a broad three-dimensional striking workspace. Human motion data provide valuable priors for such athletic skills, but usable badminton references are limited and imperfect. Direct tracking provides insufficient executable variation for diverse shuttle conditions, while purely task-driven optimization may produce unnatural motion. To address these challenges, we present a three-stage hierarchical reinforcement learning framework for dynamic humanoid badminton. First, task-randomized motion augmentation expands sparse annotated hitting events into executable target-conditioned stroke variations, forming a continuous latent skill space. Second, a high-level planner outputs continuous latent skill codes to compose these skills online according to the observed shuttle state. Third, a context-conditioned adversarial regularizer encourages more natural planner-level skill usage while preserving return performance. When deployed on a real humanoid robot, our system achieves sustained multi-skill rallies with human players, including forehand, backhand, and highly dynamic jump returns. This is the first real-world humanoid racket-sport system to demonstrate multi-skill human--robot rallies including highly dynamic jump returns.
Abstract:High-speed racket sports provide a demanding testbed for humanoid robots, requiring time-critical decisions, precise striking, and dynamic whole-body coordination. In badminton, fast-changing shuttle trajectories require timely contact decisions, while successful returns demand precise racket pose and velocity within a brief contact window and across a broad three-dimensional striking workspace. Human motion data provide valuable priors for such athletic skills, but usable badminton references are limited and imperfect. Direct tracking provides insufficient executable variation for diverse shuttle conditions, while purely task-driven optimization may produce unnatural motion. To address these challenges, we present a three-stage hierarchical reinforcement learning framework for dynamic humanoid badminton. First, task-randomized motion augmentation expands sparse annotated hitting events into executable target-conditioned stroke variations, forming a continuous latent skill space. Second, a high-level planner outputs continuous latent skill codes to compose these skills online according to the observed shuttle state. Third, a context-conditioned adversarial regularizer encourages more natural planner-level skill usage while preserving return performance. When deployed on a real humanoid robot, our system achieves sustained multi-skill rallies with human players, including forehand, backhand, and highly dynamic jump returns. This is the first real-world humanoid racket-sport system to demonstrate multi-skill human--robot rallies including highly dynamic jump returns.
Robotics (cs.RO)
arXiv:2609.31840 [cs.RO]
(or arXiv:2609.31840v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.31840 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 291 words
Related coverage
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
Learning Human-Like Badminton Skills for Humanoid Robots
arXiv · Sep 16, 2026
Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots
arXiv · Aug 21, 2026
HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos
arXiv · Oct 12, 2026