A hierarchical reinforcement learning framework lets a quadruped robot automatically switch between trotting, bounding, galloping, and fall recovery based on distance to the goal, with switch distances tuned by CMA-ES.
Adaptive Energy Regularization for Autonomous Gait Transition and Energy-Efficient Quadruped Locomotion
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In reinforcement learning for legged robot locomotion, crafting effective reward strategies is crucial. Pre-defined gait patterns and complex reward systems are widely used to stabilize policy training. Drawing from the natural locomotion behaviors of humans and animals, which adapt their gaits to minimize energy consumption, we propose a simplified, energy-centric reward strategy to foster the development of energy-efficient locomotion across various speeds in quadruped robots. By implementing an adaptive energy reward function and adjusting the weights based on velocity, we demonstrate that our approach enables ANYmal-C and Unitree Go1 robots to autonomously select appropriate gaits, such as four-beat walking at lower speeds and trotting at higher speeds, resulting in improved energy efficiency and stable velocity tracking compared to previous methods using complex reward designs and prior gait knowledge. The effectiveness of our policy is validated through simulations in the IsaacGym simulation environment and on real robots, demonstrating its potential to facilitate stable and adaptive locomotion.
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Discovery of skill switching criteria for learning agile quadruped locomotion
A hierarchical reinforcement learning framework lets a quadruped robot automatically switch between trotting, bounding, galloping, and fall recovery based on distance to the goal, with switch distances tuned by CMA-ES.