自主认知机制及在机器人中的应用

来源期刊:中南大学学报(自然科学版)2011年第z1期

论文作者:蔡建羡 李立新 高琴

文章页码:486 - 492

关键词:条件反射;学习自动机;自主认知;运动控制

Key words:conditioned reflex; learning automaton; autonomous cognitive; motion control

摘    要:在学习自动机理论的框架中,基于条件反射理论,建立一种具有自主认知机制的自主认知自动机。该自动机是一个五元组,包括内部集合、取向核、认知核、自主认知单元和操作熵。从理论上证明自主认知机制的收敛性。采用设计的自主认知自动机作为机器人的数学抽象和形式化工具,描述机器人的自学习行为,应用于自平衡机器人的运动控制。自主认知自动机的状态集合用于描述机器人的倾角和倾角速度,操作行为集合用于描述施加到机器人左右轮电机上的控制信号。随着学习的进行,机器人逐渐掌握运动平衡技能。

Abstract: Based on the conditioned reflex theory a self-cognitive automaton which has autonomous cognitive mechanism is constructed under the learning automaton frame. The bionic self-learning automaton has a 5-tupe structure and mainly contains inner sets, oriented core, cognitive core, autonomous cognitive unit and operant entropy. Theoretical proof is made for the convergence of autonomous cognitive mechanism. And the designed self-cognitive automaton which is used as the mathematical abstraction and formal tool of robot is used to describe the self-learning behavior of robot and is applied to the motion control of self-balanced robot. The state sets of self-cognitive automaton are described by tilt angle and tilt angle rate of robot, and the operant sets are described by control signals of left motor and right motor. Robot gradually learned the motion balanced skill with the learning proceeding.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号