Learning Human-Like Badminton Skills for Humanoid Robots
- URL: http://arxiv.org/abs/2602.08370v1
- Date: Mon, 09 Feb 2026 08:09:52 GMT
- Title: Learning Human-Like Badminton Skills for Humanoid Robots
- Authors: Yeke Chen, Shihao Dong, Xiaoyu Ji, Jingkai Sun, Zeren Luo, Liu Zhao, Jiahui Zhang, Wanyue Li, Ji Ma, Bowen Xu, Yimin Han, Yudong Zhao, Peng Lu,
- Abstract summary: 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.
- Score: 25.27775061243493
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Realizing versatile and human-like performance in high-demand sports like badminton remains a formidable challenge for humanoid robotics. Unlike standard locomotion or static manipulation, this task demands a seamless integration of explosive whole-body coordination and precise, timing-critical interception. While recent advances have achieved lifelike motion mimicry, bridging the gap between kinematic imitation and functional, physics-aware striking without compromising stylistic naturalness is non-trivial. To address this, we propose Imitation-to-Interaction, a progressive reinforcement learning framework designed to evolve a robot from a "mimic" to a capable "striker." 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. Crucially, to overcome the sparsity of expert demonstrations, we introduce a manifold expansion strategy that generalizes discrete strike points into a dense interaction volume. We validate our framework through the mastery of diverse skills, including lifts and drop shots, in simulation. Furthermore, we demonstrate the first zero-shot sim-to-real transfer of anthropomorphic badminton skills to a humanoid robot, successfully replicating the kinetic elegance and functional precision of human athletes in the physical world.
Related papers
- 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) - FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions [147.04372611893032]
We present FRoM-W1, an open-source framework designed to achieve general humanoid whole-body motion control using natural language.<n>We extensively evaluate FRoM-W1 on Unitree H1 and G1 robots.<n>Results demonstrate superior performance on the HumanML3D-X benchmark for human whole-body motion generation.
arXiv Detail & Related papers (2026-01-19T07:59:32Z) - Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis [51.95817740348585]
Human-X is a novel framework designed to enable immersive and physically plausible human interactions across diverse entities.<n>Our method jointly predicts actions and reactions in real-time using an auto-regressive reaction diffusion planner.<n>Our framework is validated in real-world applications, including virtual reality interface for human-robot interaction.
arXiv Detail & Related papers (2025-08-04T06:35:48Z) - KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills [58.73043119128804]
This paper presents a physics-based humanoid control framework, aiming to master highly-dynamic human behaviors such as Kungfu and dancing.<n>For motion processing, we design a pipeline to extract, filter out, correct, and retarget motions, while ensuring compliance with physical constraints.<n>For motion imitation, we formulate a bi-level optimization problem to dynamically adjust the tracking accuracy tolerance.<n>In experiments, we train whole-body control policies to imitate a set of highly-dynamic motions.
arXiv Detail & Related papers (2025-06-15T13:58:53Z) - StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion [31.30409161905949]
StyleLoco is a novel framework for learning humanoid locomotion.<n>It combines the agility of reinforcement learning with the natural fluidity of human-like movements.<n>We demonstrate that StyleLoco enables humanoid robots to perform diverse locomotion tasks.
arXiv Detail & Related papers (2025-03-19T10:27:44Z) - Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning [54.26816599309778]
We propose a novel whole-body locomotion algorithm based on dynamic balance and Reinforcement Learning (RL)<n> Specifically, we introduce a dynamic balance mechanism by leveraging an extended measure of Zero-Moment Point (ZMP)-driven rewards and task-driven rewards in a whole-body actor-critic framework.<n> Experiments conducted on a full-sized Unitree H1-2 robot verify the ability of our method to maintain balance on extremely narrow terrains.
arXiv Detail & Related papers (2025-02-24T14:53:45Z) - Redefining Robot Generalization Through Interactive Intelligence [0.0]
We argue that robot foundation models must evolve to an interactive multi-agent perspective in order to handle the complexities of real-time human-robot co-adaptation.<n>By moving beyond single-agent designs, our position emphasizes how foundation models in robotics can achieve a more robust, personalized, and anticipatory level of performance.
arXiv Detail & Related papers (2025-02-09T17:13:27Z) - Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration [9.42179962375058]
We propose a transferable framework that reduces the data bottleneck by using a unified digital human model as a common prototype.<n>The model learns behavior primitives from human demonstrations through adversarial imitation, and complex robot structures are decomposed into functional components.<n>Our framework is validated on five humanoid robots with diverse configurations.
arXiv Detail & Related papers (2024-12-19T18:41:45Z) - ExBody2: Advanced Expressive Humanoid Whole-Body Control [16.69009772546575]
We propose a method for producing whole-body tracking controllers that are trained on both human motion capture and simulated data.<n>We use a teacher policy to produce intermediate data that better conforms to the robot's kinematics.<n>We observed significant improvement of tracking performance after fine-tuning on a small amount of data.
arXiv Detail & Related papers (2024-12-17T18:59:51Z) - I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement Learning [8.97654258232601]
We develop a framework to control humanoid robots through bounded residual reinforcement learning (I-CTRL)<n>I-CTRL excels in motion imitation with simple and unique rewards that generalize across five robots.<n>Our framework introduces an automatic priority scheduler to manage large-scale motion datasets.
arXiv Detail & Related papers (2024-05-14T16:12:27Z) - Learning Human-to-Robot Handovers from Point Clouds [63.18127198174958]
We propose the first framework to learn control policies for vision-based human-to-robot handovers.
We show significant performance gains over baselines on a simulation benchmark, sim-to-sim transfer and sim-to-real transfer.
arXiv Detail & Related papers (2023-03-30T17:58:36Z)
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.