Extreme-RGMT: Continual Learning of Highly Dynamic Skills for Robust Generalist Humanoid Control

• URL: http://arxiv.org/abs/2607.20110v1
• Date: Wed, 22 Jul 2026 13:10:22 GMT
• Title: Extreme-RGMT: Continual Learning of Highly Dynamic Skills for Robust Generalist Humanoid Control
• Abstract summary: We introduce Extreme-RGMT, a two-stage continual learning framework for robust generalist humanoid control.<n>Extreme-RGMT learns a generalist motion-tracking base policy from diverse multi-source motion data, then employs an asymmetric skill acquisition and capability consolidation mechanism.<n>Experiments show that Extreme-RGMT achieves state-of-the-art generalist whole-body motion-tracking performance.
• Score: 12.247654049983522
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans can progressively acquire highly dynamic motor skills while preserving reliable everyday motor abilities. In contrast, existing humanoid controllers face a trade-off between generalist and specialist capabilities: generalist motion tracking policies struggle to reliably execute rare highly dynamic motions, whereas specialist training can degrade previously acquired behaviors. We introduce Extreme-RGMT, a two-stage continual learning framework for robust generalist humanoid control. The method first learns a generalist motion-tracking base policy from diverse multi-source motion data, then employs an asymmetric skill acquisition and capability consolidation mechanism to constrain policy drift on mastered motions while emphasizing difficult dynamic segments. To address the scarcity of highly dynamic motions, their high failure rates, and the resulting shortage of informative samples, Extreme-RGMT combines difficulty-aware sampling with advantage-prioritized trajectory resampling to emphasize critical segments. Experiments show that Extreme-RGMT achieves state-of-the-art generalist whole-body motion-tracking performance, including substantially improved completion of challenging highly dynamic motions. The resulting controller directly executes diverse unseen highly dynamic motions under fixed references and online inertial motion-capture inputs, advancing generalist whole-body motion-tracking controllers toward highly dynamic motor capabilities at the human-expert level.

Related papers

• Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report [25.18747802029395]
  We present ABot-C0, a generalist motion-control system for quadruped robots.<n>We construct a data pyramid through conditional video-generation, annotated motion capture, and human design, producing 16,074 physically feasible motion clips.<n>We then go a step further toward robust all-terrain locomotion by adopting a three-stage privileged-to-perceptive framework.
  arXiv  Detail & Related papers  (2026-07-08T13:04:07Z)
• 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)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control [41.16304916968901]
  High-fidelity motion tracking serves as the litmus test for generalizable, human-level motor skills.<n>Current policies often hit a "generality barrier" as motion libraries scale in diversity.<n>We introduce OmniXtreme, a scalable framework that decouples general motor skill learning from sim-to-real physical skill refinement.
  arXiv  Detail & Related papers  (2026-02-27T09:28:06Z)
• OmniTrack: General Motion Tracking via Physics-Consistent Reference [54.256312586493415]
  We introduce OmniTrack, a general tracking framework that explicitly decouples physical feasibility from general motion tracking.<n>Experiments show that OmniTrack improves tracking accuracy and demonstrates strong generalization to unseen motions.<n>In real-world tests, OmniTrack achieves hour-long, consistent, and stable tracking, including complex acrobatic motions such as flips and cartwheels.
  arXiv  Detail & Related papers  (2026-02-27T09:12:15Z)
• A Kung Fu Athlete Bot That Can Do It All Day: Highly Dynamic, Balance-Challenging Motion Dataset and Autonomous Fall-Resilient Tracking [5.968082051565195]
  Martial arts are characterized by rapid center-of-mass shifts, complex coordination, and abrupt posture transitions.<n>KungFuAthlete is a high-dynamic martial arts motion dataset derived from professional athletes' daily training videos.<n>We propose a novel training paradigm that enables a single policy to jointly learn high-dynamic motion tracking and fall recovery.
  arXiv  Detail & Related papers  (2026-02-14T07:49:56Z)
• TeleGate: Whole-Body Humanoid Teleoperation via Gated Expert Selection with Motion Prior [27.930225667015872]
  This paper presents TeleGate, a unified whole-body teleoperation framework for humanoid robots.<n>Our key idea is to preserve the full capability of domain-specific expert policies by training a lightweight gating network.<n>To compensate for the absence of future reference trajectories in real-time teleoperation, we introduce a VAE-based motion prior module.
  arXiv  Detail & Related papers  (2026-02-10T10:14:06Z)
• CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation [70.5382178207975]
  hIsight Perturbation (CHIP) is a plug-and-play module that enables controllable end-effector stiffness.<n>CHIP is easy to implement and requires neither data augmentation nor additional reward tuning.<n>We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-16T18:56:04Z)
• KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control [30.738592041595933]
  We present VMS, a unified whole-body controller that enables humanoid robots to learn diverse and dynamic behaviors within a single policy.<n>Our framework integrates a hybrid tracking objective that balances local motion fidelity with global trajectory consistency.<n>We validate VMS specialization extensively in both simulation and real-world experiments, demonstrating accurate imitation of dynamic skills, stable performance over minute-long sequences, and strong generalization to unseen motions.
  arXiv  Detail & Related papers  (2025-09-20T11:31:14Z)
• GENMO: A GENeralist Model for Human MOtion [64.16188966024542]
  We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework.<n>Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals.<n>Our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control.
  arXiv  Detail & Related papers  (2025-05-02T17:59:55Z)
• Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots [121.42930679076574]
  We present a model-free reinforcement learning framework for training robust locomotion policies in simulation. domain randomization is used to encourage the policies to learn behaviors that are robust across variations in system dynamics. We demonstrate this on versatile walking behaviors such as tracking a target walking velocity, walking height, and turning yaw.
  arXiv  Detail & Related papers  (2021-03-26T07:14:01Z)

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.