Towards Dynamic Quadrupedal Gaits: A Symmetry-Guided RL Hierarchy Enables Free Gait Transitions at Varying Speeds

2025-10-12

AI Summary

To address the challenges of expert-dependent gait parameter tuning and autonomous gait transitions across multiple speeds in quadrupedal robots, this paper proposes a symmetry-guided hierarchical reinforcement learning framework. Methodologically, we design a model-free reward function leveraging temporal, morphological, and time-reversal symmetries—coupled with the speed–gait-period relationship—and integrate it with dynamic system modeling to enable end-to-end generation and smooth transitions among trotting, bounding, half-bounding, and galloping gaits, without predefined trajectories or foot-tip trajectory tracking. Our key contributions are: (i) the first incorporation of multiple physical symmetries into reward shaping to significantly reduce manual tuning effort; and (ii) empirical validation of robust, generalizable inter-gait switching across speeds in both simulation and on real Unitree Go2 hardware, markedly enhancing locomotion adaptability and agility in complex environments.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Quadrupedal robots exhibit a wide range of viable gaits, but generating specific footfall sequences often requires laborious expert tuning of numerous variables, such as touch-down and lift-off events and holonomic constraints for each leg. This paper presents a unified reinforcement learning framework for generating versatile quadrupedal gaits by leveraging the intrinsic symmetries and velocity-period relationship of dynamic legged systems. We propose a symmetry-guided reward function design that incorporates temporal, morphological, and time-reversal symmetries. By focusing on preserved symmetries and natural dynamics, our approach eliminates the need for predefined trajectories, enabling smooth transitions between diverse locomotion patterns such as trotting, bounding, half-bounding, and galloping. Implemented on the Unitree Go2 robot, our method demonstrates robust performance across a range of speeds in both simulations and hardware tests, significantly improving gait adaptability without extensive reward tuning or explicit foot placement control. This work provides insights into dynamic locomotion strategies and underscores the crucial role of symmetries in robotic gait design.

Problem

• Generating specific quadrupedal footfall sequences requires laborious expert tuning
• Eliminating predefined trajectories enables smooth transitions between diverse locomotion patterns
• Achieving robust gait adaptability across varying speeds without explicit foot control

Innovation

• Symmetry-guided reinforcement learning for gaits
• No predefined trajectories for smooth transitions
• Robust performance across speeds without foot control