Legged robots must exhibit robust and agile locomotion across diverse, unstructured terrains, a challenge exacerbated under blind locomotion settings where terrain information is unavailable. This work introduces a hierarchical reinforcement learning framework that leverages terrain-specialized policies and curriculum learning to enhance agility and tracking performance in complex environments. We validated our method on simulation, where our approach outperforms a generalist policy by up to 16% in success rate and achieves lower tracking errors as the velocity target increases, particularly on low-friction and discontinuous terrains, demonstrating superior adaptability and robustness across mixed-terrain scenarios.
@article{arxiv.2509.20635,
title = {Learning Terrain-Specialized Policies for Adaptive Locomotion in Challenging Environments},
author = {Matheus P. Angarola and Francisco Affonso and Marcelo Becker},
journal= {arXiv preprint arXiv:2509.20635},
year = {2025}
}
Comments
Accepted to the 22nd International Conference on Advanced Robotics (ICAR 2025). 7 pages