轮式移动机器人的双强化学习自适应模糊控制  

Dual reinforcement learning adaptive fuzzy control of wheeled mobile robot

作　　者：叶锦华[1] 李迪[1] 叶峰[1] 

机构地区：[1]华南理工大学机械与汽车工程学院,广州510641

出　　处：《吉林大学学报（工学版）》2014年第3期742-749,共8页Journal of Jilin University:Engineering and Technology Edition

基　　金：'863'国家高技术研究发展计划项目(2011AA04A104;2012AA040909);广东省战略新兴产业核心技术攻关项目(2012A010702004)

摘　　要：针对包含执行器动力学模型的三阶不确定非完整轮式移动机器人系统,提出了一种基于反演设计和双强化学习自适应模糊系统的轨迹跟踪控制方法。该控制方法对运动学控制器采用分流控制技术,防止系统运行初期的速度跳变。对本体动力学和执行器动力学分别使用强化学习自适应模糊控制,优化补偿常规方法难以解决的系统未知参数和非参数不确定性,并利用鲁棒项来消除未知外部扰动和模糊控制逼近误差对系统的影响,提高了系统的控制性能。Lyapunov理论证明:控制系统是稳定且最终有界收敛的,仿真结果表明了该方法的有效性。A trajectory tracking method is proposed for three-order uncertain nonholonomic mobile robot with actuator dynamic model. This method is based on the backstepping technique and dual reinforcement learning adaptive fuzzy logic system. The shunting control technique is used to prevent the velocity jump at the beginning of system for the motion controller. The reinforcement learning adaptive fuzzy logic control is employed for both body dynamics and actuator dynamics, such that the unknown system uncertainties of parameters and non-parameters can be compensated optimally. Moreover, in order to enhance the control performance, the robust compensators are applied to eliminate the impact of unknown external disturbance and approximation error of fuzzy system. The stability and ultimately bounded convergence of the control system are proven by Lyapunov theory. The validity of this method is verified by the simulation results.

关 键 词：自动控制技术 轮式移动机器人 轨迹跟踪 自适应模糊控制 强化学习 分流模型 非完整系统 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]