摘要
针对移动机器人轨迹跟踪控制问题,建立了机器人运动学模型,设计了基于Lyapunov稳定理论的轨迹跟踪控制器,该控制器的性能取决于其参数的取值。采用人工神经网络来动态地调解参数的大小,使控制器获得最优的性能。粒子群优化算法具有收敛速度快,需要调节的参数少等优点,但优化过程中容易发生早熟收敛,使优化陷入局部极小值。通过引入模拟退火算法、交叉算子和变异算子,设计了一种改进的粒子群优化算法,对人工神经网络的参数进行优化计算。最后,仿真计算结果表明了该方法的有效性。
For the problem of tracking control of three wheel mobile robot, kinematic model of mobile robot and controller based on Lyapunov steady theory are formed. The performance of this controller is based on its parameters. ANN is used to adjust the parameters dynamically. PSO (particle swarm optimization) has the advantage of fast convergence speed and few parameters to adjust, but premature convergence often occurs during optimization. SA, intercross operator and aberrance operator are combined to improve PSO' s performance, a new IPSO (improved particle swarm optimization) is formed to optimize the controller' s parameters. At last, simulation results are provided to illustrate the flexibility and correctness of the controller.
出处
《计算机工程与设计》
CSCD
北大核心
2009年第18期4278-4280,4283,共4页
Computer Engineering and Design
基金
装甲兵工程学院战略投资基金项目(2005ZB02)
关键词
移动机器人
轨迹跟踪
控制规律
人工神经网络
改进的粒子群算法
mobile robot
tracking control
controller
artificial neural network
improved particle swarm optimization