eGAIT: Multi-Skilled Policy for Energy-Efficient Gait Transitions
- 3 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 1575-1586
Abstract
Achieving adaptive, multi-skilled, and energy-efficient locomotion is vital for advancing the operation of autonomous quadrupedal systems. This study presents eGAIT, a unified multi-skilled policy enabling energy-efficient and stable gait transitions across nine non-monotonic, velocity-optimized gaits, in response to dynamic velocity commands. The framework leverages a hybrid control architecture that integrates model-based and learning-based methods to address the entire locomotion pipeline. An MPC-based gait generator produces velocity-optimized trajectories, which are imitated through Proximal Policy Optimization (PPO), driven by a Adversarial Motion Prior (AMP) style reward to train distinct policies for specific velocity ranges. These policies are unified through a Hierarchical Reinforcement Learning (HRL) framework featuring a novel modified Deep Q-Network (eDQN) for real-time velocity-to-policy mapping. Training efficiency is enhanced by an auxiliary selector layer that guides velocity-policy mapping, while a sparsely activated stability reward mechanism ensures smooth gait transitions by incorporating geometric and rotational stability. Extensively validated in simulation and on a Unitree Go1 robot, eGAIT achieves a 100% success rate in velocity-to-policy mapping, a 35% improvement in energy efficiency, a 31% improvement in both velocity tracking and stability compared to the next best state-of-the-art method. This work advances autonomous quadrupedal locomotion, enabling longer, more efficient, and stable operations in dynamic environments. Supplementary materials and visualizations related to the paper can be found at: https://github.com/RPL-CS-UCL/egait/.Keywords
Funding Information
- United Kingdom Research and Innovation (UKRI) Future Leaders Fellowship (MR/V025333/1)
This publication has 33 references indexed in Scilit:
- LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images2025
- Non-linear Model Predictive Control for Multi-task GPS-free Autonomous Navigation in Vineyards2024
- Robot skill learning system of multi-space fusion based on dynamic movement primitives and adaptive neural network controlNeurocomputing, 2024
- Optimization of energy consumption in industrial robots, a reviewCognitive Robotics, 2023
- GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model2022
- Reinforced model predictive control (RL-MPC) for building energy managementApplied Energy, 2022
- Review on model predictive control: an engineering perspectiveThe International Journal of Advanced Manufacturing Technology, 2021
- Imitation Learning from MPC for Quadrupedal Multi-Gait Control2021
- Reinforcement learning for control: Performance, stability, and deep approximatorsAnnual Reviews in Control, 2018
- Hierarchical Reinforcement Learning2012