首页>
外国专利>
PARTICLE SWARM OPTIMIZATION AND REINFORCEMENT LEARNING ALGORITHM-BASED DYNAMIC WALKING CONTROL SYSTEM FOR BIOMIMETIC BIPED ROBOT
PARTICLE SWARM OPTIMIZATION AND REINFORCEMENT LEARNING ALGORITHM-BASED DYNAMIC WALKING CONTROL SYSTEM FOR BIOMIMETIC BIPED ROBOT
展开▼
机译:基于仿生双足机器人的粒子群优化与强化学习算法的动态行走控制系统
展开▼
页面导航
摘要
著录项
相似文献
摘要
The invention relates to the technical field of biomimetic humanoid robot walking control. Provided is a particle swarm optimization and reinforcement learning algorithm-based dynamic walking control system for a biomimetic biped robot. The dynamic walking control system comprises: a motion mode control center; a central mode control center; an action stage control center; a postural reflex control center; and a joint unit. A modulation signal output terminal of the motion mode control center is connected to a modulation signal input terminal of the joint unit. A stimulus signal output terminal of the motion mode control center is connected to a stimulus signal input terminal of the central mode control center. An excitation signal output terminal of the central mode control center is respectively connected to an excitation signal input terminal of the action stage control center and an excitation signal input terminal of the joint unit. An action signal output terminal of the action stage control center is connected to an action signal input terminal of the postural reflex control center. The control system has a high stability, high efficiency and high adaptivity.
展开▼