自动化学报2025，Vol.51Issue(7)：1585-1598,14.DOI:10.16383/j.aas.c240738
面向不同粗糙程度地面的四足机器人自适应控制方法
Adaptive Control Method for Quadruped Robot Facing Floors of Different Roughness
摘要
Abstract
Addressing the issue of high-speed stable motion for quadruped robots in complex environments,a hier-archical motion control framework integrating model and learning is proposed.First,a penalty mechanism based on single foot placement point deviation is introduced to effectively evaluate continuous sliding states.Second,a con-tinuous contact state description based on hyperbolic tangent function is constructed,significantly improving the phase switching impact problem in traditional discrete methods.Then,a LSTM-based ground characteristics real-time estimation network is designed to achieve adaptive adjustment of the centroid of mass position.Finally,a hier-archical control framework based on execution and decision layers is proposed to enhance the system's environ-mental adaptability.Experiments in the Isaac Gym simulation environment demonstrate that this control method can adapt to different friction coefficients and motion speeds.Particularly in an extremely low friction environment(μ=0.05),the adaptive control strategy adjusts the centroid of mass height by 0.0610 m,while maintaining a mo-tion speed of 1.4284 m/s and controlling the sliding distance of the foot end to 0.308±0.005 0 cm.This outcome serves to provide a comprehensive demonstration of the effectiveness and practical value of the proposed control method.关键词
四足机器人/强化学习/自适应控制策略/奖励函数优化/分层控制框架Key words
Quadruped robot/reinforcement learning/adaptive control strategy/reward function optimization/hierarchical control framework引用本文复制引用
张楠杰,陈玉全,季茂沁,孙运康,王冰..面向不同粗糙程度地面的四足机器人自适应控制方法[J].自动化学报,2025,51(7):1585-1598,14.基金项目
国家自然科学基金(51777058)资助Supported by National Natural Science Foundation of China(51777058) （51777058）
