A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion
Not on the map. Why?
Abstract (arXiv)
Locomotion is a fundamental skill for humanoid robots. However, most existing works make locomotion a single, tedious, unextendable, and unconstrained movement. This limits the kinematic capabilities of humanoid robots. In contrast, humans possess versatile athletic abilities-running, jumping, hopping, and finely adjusting gait parameters such as frequency and foot height. In this paper, we investigate solutions to bring such versatility into humanoid locomotion and thereby propose HugWBC: a unified and general humanoid whole-body controller for versatile locomotion. By designing a general command space in the aspect of tasks and behaviors, along with advanced techniques like symmetrical loss and intervention training for learning a whole-body humanoid controlling policy in simulation, HugWBC enables real-world humanoid robots to produce various natural gaits, including walking, jumping, standing, and hopping, with customizable parameters such as frequency, foot swing height, further combined with different body height, waist rotation, and body pitch. Beyond locomotion, HugWBC also supports real-time interventions from external upper-body controllers like teleoperation, enabling loco-manipulation with precision under any locomotive behavior. Extensive experiments validate the high tracking accuracy and robustness of HugWBC with/without upper-body intervention for all commands, and we further provide an in-depth analysis of how the various commands affect humanoid movement and offer insights into the relationships between these commands. To our knowledge, HugWBC is the first humanoid whole-body controller that supports such versatile locomotion behaviors with high robustness and flexibility.
Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 38 of its 56 references that are in the map. First posted on arXiv 5 Feb 2025.
Builds on
38 of 56 references.
References · 38
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
- 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
- 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
- 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
- 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 202
- 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 167
- 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
- 2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 137
- 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
- 2022Rapid Locomotion via Reinforcement Learningcited by 130
- 2023Extreme Parkour with Legged Robotscited by 120
26 more
- 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
- 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 113
- 2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 112
- 2024HOVER: Versatile Neural Whole-Body Controller for Humanoid Robotscited by 76
- 2024ExBody2: Advanced Expressive Humanoid Whole-Body Controlcited by 75
- 2020Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Compositioncited by 71
- 2024Humanoid Parkour Learningcited by 66
- 2024Visual Whole-Body Control for Legged Loco-Manipulationcited by 58
- 2018Learning Symmetric and Low-energy Locomotioncited by 53
- 2024WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contactscited by 49
- 2024Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Controlcited by 41
- 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 38
- 2024Learning Humanoid Locomotion with Perceptive Internal Modelcited by 38
- 2023DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learningcited by 37
- 2023DTC: Deep Tracking Controlcited by 37
- 2021A Unified MPC Framework for Whole-Body Dynamic Locomotion and Manipulationcited by 33
- 2019Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Controlcited by 29
- 2022Perceptive Locomotion through Nonlinear Model Predictive Controlcited by 27
- 2024Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policiescited by 26
- 2019Footstep Planning for Autonomous Walking Over Rough Terraincited by 8
- 2020Efficient Multi-Contact Pattern Generation with Sequential Convex Approximations of the Centroidal Dynamicscited by 6
- 2022BiConMP: A Nonlinear Model Predictive Control Framework for Whole Body Motion Planningcited by 6
- 2017Combining Trajectory Optimization, Supervised Machine Learning, and Model Structure for Mitigating the Curse of Dimensionality in the Control of Bipedal Robotscited by 4
- 2016A Convex Model of Momentum Dynamics for Multi-Contact Motion Generationcited by 3
- 2020Solving Footstep Planning as a Feasibility Problem using L1-norm Minimization (Extended Version)cited by 2
- 2021Bipedal Walking on Constrained Footholds: Momentum Regulation via Vertical COM Controlcited by 1
Built on by
Citing papers per year: 2025: 7; 2026: 3.
10 papers.
- 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusioncited by 128
- 2025OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interactioncited by 57
- 2025PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction Systemcited by 17
- 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructionscited by 10
- 2025Towards Adaptable Humanoid Control via Adaptive Motion Trackingcited by 6
- 2025From Generated Human Videos to Physically Plausible Robot Trajectoriescited by 5
- 2026CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperationcited by 4
- 2025A Scalable Whole-body Motion Transfer via Implicit Kinodynamic Motion Retargetingcited by 2
- 2025PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representationscited by 2
- 2026Scaling Behavior Foundation Model for Humanoid Robotscited by 2
- 2026Scaling Behavior Foundation Model for Humanoid Robots16 Jul 2026
- 2026CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation13 Feb 2026
- 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions19 Jan 2026
- 2025PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations15 Dec 2025
- 2025From Generated Human Videos to Physically Plausible Robot Trajectories4 Dec 2025
- 2025Towards Adaptable Humanoid Control via Adaptive Motion Tracking16 Oct 2025
- 2025PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System13 Oct 2025
- 2025OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction30 Sep 2025
- 2025A Scalable Whole-body Motion Transfer via Implicit Kinodynamic Motion Retargeting18 Sep 2025
- 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion11 Aug 2025