arXiv：cs.LG· Ammar Issa, Anubhav Singh, Anton Tsaritsin, Sergey Kolyubin·· 4 小时前AI 评分31
基于分层强化学习的四足机器人节能步态自适应
Energy-Efficient Gait Adaptation via Hierarchical Reinforcement Learning for Quadrupedal Locomotion Across Diverse Terrains
AI 导读
研究提出一种分层强化学习（HRL）框架，将高频关节运动执行策略与低频步态自适应策略分离，后者显式最小化运输成本（CoT）。三阶段 Isaac 训练流程实现零样本 sim-to-real 迁移，学习到的层级策略呈现随速度自动切换步态：低速踱步、高速小跑。在 Unitree AlienGo 四足机器人上完成零样本部署。
正文
Abstract:While energy efficiency is a critical objective for legged-robot locomotion control, achieving low energy consumption while maintaining robust performance across different velocity ranges and terrain conditions remains a key challenge. This is particularly true for end-to-end RL policies, where gait generation, motion execution, and energy optimization are tightly coupled, leading to high sensitivity to reward design. In this work, we propose a hierarchical reinforcement learning (HRL) framework that separates a high-frequency policy for stable and robust joint-level motion execution from low-frequency gait adaptation that explicitly minimizes the cost of transport (CoT). The three-stage Isaac-based training procedure enables zero-shot sim-to-real transfer with improved tracking accuracy, robustness, and energy efficiency. The learned hierarchy exhibits automatic speed-dependent gait adaptation, transitioning from pacing at low speeds to trotting at higher speeds. We validate the proposed approach in simulation against representative single-policy and hierarchical locomotion baselines, demonstrating reduced CoT over a broad range of commanded velocities, while maintaining robust locomotion across flat, uneven rough, and inclined terrains. We further demonstrate its practical feasibility through zero-shot deployment on a physical Unitree AlienGo quadruped.
| Comments: | 9 pages. Submitted to IEEE ICRA 2027. Ammar Issa, Anubhav Singh, and Anton Tsaritsin contributed equally |
| Subjects: | Robotics (cs.RO); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.10297 [cs.RO] |
| (or arXiv:2610.10297v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10297 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Anubhav Singh [view email]
[v1]
Wed, 7 Oct 2026 15:53:35 UTC (4,402 KB)
来源：arXiv：cs.LG · arxiv.org