HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control

TL;DR

HUSKY introduces a physics-aware, learning-based framework for humanoid skateboarding that integrates a lean-to-steer coupling, hybrid phase dynamics, and trajectory-guided phase transitions. By explicitly modeling the coupled humanoid–board system, leveraging Adversarial Motion Priors for pushing, and enforcing physics-guided steering, the method achieves stable, agile skateboarding both in simulation and on real hardware. The work demonstrates strong performance across pushing, steering, and phase transitions, with rigorous sim-to-real transfer via skateboard identification and domain randomization. This approach advances dynamic humanoid control on underactuated platforms and offers a practical path toward robust, real-world humanoid skateboarding. The framework generalizes to diverse boards and environments, highlighting its potential for complex human–object interactions in dynamic settings.

Abstract

While current humanoid whole-body control frameworks predominantly rely on the static environment assumptions, addressing tasks characterized by high dynamism and complex interactions presents a formidable challenge. In this paper, we address humanoid skateboarding, a highly challenging task requiring stable dynamic maneuvering on an underactuated wheeled platform. This integrated system is governed by non-holonomic constraints and tightly coupled human-object interactions. Successfully executing this task requires simultaneous mastery of hybrid contact dynamics and robust balance control on a mechanically coupled, dynamically unstable skateboard. To overcome the aforementioned challenges, we propose HUSKY, a learning-based framework that integrates humanoid-skateboard system modeling and physics-aware whole-body control. We first model the coupling relationship between board tilt and truck steering angles, enabling a principled analysis of system dynamics. Building upon this, HUSKY leverages Adversarial Motion Priors (AMP) to learn human-like pushing motions and employs a physics-guided, heading-oriented strategy for lean-to-steer behaviors. Moreover, a trajectory-guided mechanism ensures smooth and stable transitions between pushing and steering. Experimental results on the Unitree G1 humanoid platform demonstrate that our framework enables stable and agile maneuvering on skateboards in real-world scenarios. The project page is available on https://husky-humanoid.github.io/.

Figures (11)

• Figure 1: Skateboard Model. We analyze the skateboard kinematic structure and derive the coupling relationships among the board tilt, truck steering, and rake angles, which form the basis of the lean-to-steer behavior.
• Figure 2: Framework of HUSKY. (a) We first analyze and model the humanoid–skateboard system, deriving a physics-inspired lean-to-steer coupling mechanism. Due to the distinct contact dynamics and control objectives across skateboarding phases, we adopt a phase-wise learning strategy. (b) The learning-based whole-body control framework integrates an AMP-based pushing style for active forward propulsion, a steering strategy guided by physics-aware tilt references, and a trajectory-guided transition mechanism to enable stable switching between pushing and steering phases.
• Figure 3: Steering Trajectories Visualizations. (a) Omitting lean-to-steer coupling prevents effective steering. (b) Incorporating physics-guided tilt guidance substantially increases the reachable heading range and precision.
• Figure 4: Training Performance Comparison. Episode length (left) and steering contact reward (right). Without transition guidance, the policy fails to maintain correct foot–board contacts. In contrast, the policy discovers correct contact patterns early in training and establishes stable phase transitions.
• Figure 5: Transition trajectories analysis. Representative trajectories during phase transitions. The humanoid maintains smooth, coordinated whole-body motions, with seamless transitions between pushing and steering.