Papers
Sign in to view your remaining parses.
Tag Filter
Humanoid Whole-Body Control
PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
Published:12/15/2025
Humanoid Whole-Body ControlHumanoid Robot LearningContrastive Learning FrameworkState Representation Learning MethodsData-Efficient Reinforcement Learning
The paper introduces the PvP framework, addressing sample inefficiency in humanoid robot control by leveraging the complementarity of proprioceptive and privileged states. It improves learning efficiency without manual data augmentation, significantly enhancing performance in vel
03
Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning
Published:11/14/2025
Humanoid Whole-Body ControlReinforcement Learning Training PipelineAction Generation in Dynamic EnvironmentsBadminton Motion ControlMultistage Reinforcement Learning
This paper presents a reinforcement learning training pipeline to develop a unified wholebody controller for humanoid badminton, enabling coordinated footwork and striking without reliance on motion priors or expert demonstrations. The training is validated in both simulated and
02
GMT: General Motion Tracking for Humanoid Whole-Body Control
Published:6/18/2025
Humanoid Whole-Body ControlGeneral Motion Tracking FrameworkAdaptive Sampling StrategyMotion Mixture-of-Experts ArchitectureDiverse Motion Tracking
The paper presents GMT, a motion tracking framework enabling humanoid robots to track diverse fullbody motions in realworld settings. It features an Adaptive Sampling strategy and a Motion MixtureofExperts architecture, demonstrating stateoftheart performance through exten
02
KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
Published:6/15/2025
Humanoid Whole-Body ControlHigh-Dynamic Motion ImitationPhysics-Based Dynamic TrackingBi-Level Optimization FrameworkRobot Skill Learning
This paper presents KungfuBot, a physicsbased humanoid control framework that learns highdynamic human behaviors like Kungfu and dance through multistep motion processing and adaptive tracking, achieving significantly lower tracking errors successfully implemented on a robot.
03
ExBody2: Advanced Expressive Humanoid Whole-Body Control
Published:12/18/2024
Humanoid Whole-Body ControlExpressive Dynamic Motion GenerationMotion Capture-Based Control StrategyKinematic Adaptation Optimization for RobotsWhole-Body Motion Tracking Algorithm
The paper presents ExBody2, an advanced control method enabling humanoid robots to perform expressive wholebody movements while maintaining stability. It employs a training approach based on human motion capture and simulations, addressing tradeoffs between versatility and spec
03