Related papers: SkillX: Unified Multi-Skill Policy Learning for Humanoid Soccer

SkillX: Unified Multi-Skill Policy Learning for Humanoid Soccer

URL: http://arxiv.org/abs/2609.06718v2
Date: Fri, 11 Sep 2026 03:17:00 GMT
Title: SkillX: Unified Multi-Skill Policy Learning for Humanoid Soccer
Abstract summary: We present SkillX, a unified reinforcement learning framework that learns and composes multiple atomic soccer skills.<n>SkillX integrates three core designs: skill-specific adversarial motion priors, skill-specific critics, and an object-aware temporal encoder.<n> Experiments in simulation and on a real Noetix E1 humanoid demonstrate robust multi-skill execution, long-horizon skill composition, and successful sim-to-real deployment.
Score: 10.644145550941778
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Humanoid soccer is a challenging testbed for dynamic whole-body control, requiring robots to coordinate balance, locomotion, object interaction, and skill switching over long horizons. Existing humanoid sports methods often rely on task-specific multi-stage pipelines, making it difficult to jointly learn and compose multiple object-interactive skills within a single deployable policy. To address this, we present SkillX, a unified reinforcement learning framework that learns and composes multiple atomic soccer skills through a single command-conditioned policy. SkillX integrates three core designs: skill-specific adversarial motion priors, skill-specific critics, and an object-aware temporal encoder, enabling the robot to execute atomic skills and transition among them such as dribbling, trapping, and shooting. Experiments in simulation and on a real Noetix E1 humanoid demonstrate robust multi-skill execution, long-horizon skill composition, and successful sim-to-real deployment.

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)
Switch: Learning Agile Skills Switching for Humanoid Robots [62.14433450799811]
We introduce a hierarchical multi-skill system, Switch, enabling seamless skill transitions at any moment.<n>Our approach comprises three key components: (1) a Skill Graph that establishes potential cross-skill transitions based on kinematic similarity within multi-skill motion data, (2) a whole-body tracking policy trained on this skill graph through deep reinforcement learning, and (3) an online skill scheduler to drive the tracking policy for robust skill execution and smooth transitions.
arXiv Detail & Related papers (2026-04-16T10:11:28Z)
Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots [1.282675419968047]
We propose Tree Learning, a multi-skill continual learning framework for humanoid robots.<n>The framework adopts a root-branch hierarchical parameter inheritance mechanism, providing motion priors for branch skills.<n>A task-level reward shaping strategy is also proposed to accelerate skill convergence.
arXiv Detail & Related papers (2026-04-14T15:57:27Z)
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 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)
HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos [74.43500240121476]
We present HumanX, a full-stack framework that compiles human video into generalizable, real-world interaction skills for humanoids.<n>HumanX achieves over 8 times higher generalization success than prior methods.
arXiv Detail & Related papers (2026-02-02T18:53:01Z)
Learning Semantic Atomic Skills for Multi-Task Robotic Manipulation [34.73582639920571]
AtomSkill is a novel multi-task imitation learning framework.<n>It learns and leverages a structured Atomic Skill Space for composable robot manipulation.<n>It consistently outperforms state-of-the-art methods across diverse manipulation tasks.
arXiv Detail & Related papers (2025-12-20T13:46:08Z)
SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending [79.83865372778273]
We introduce SkillBlender, a novel hierarchical reinforcement learning framework for versatile humanoid loco-manipulation.<n>SkillBlender first pretrains goal-conditioned task-agnostic primitive skills, and then dynamically blends these skills to accomplish complex loco-manipulation tasks.<n>We also introduce SkillBench, a parallel, cross-embodiment, and diverse simulated benchmark containing three embodiments, four primitive skills, and eight challenging loco-manipulation tasks.
arXiv Detail & Related papers (2025-06-11T03:24:26Z)

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