基于小生境粒子群优化的挖掘机器人自抗扰视觉伺服控制

为提高挖掘机器人的自主挖掘能力,设计一种基于图像的自抗扰视觉伺服控制器,对挖掘机器人的动臂、斗杆、铲斗组成的3节机械臂末端位置和姿态在x-z平面进行控制,实现自主挖掘目标任务。针对自抗扰控制器需要整定的参数较多,参数间相互影响,整定困难的特点,引入粒子群算法对控制器参数进行优化。由于原始粒子群算法存在后期易陷入局部最优的缺欠,采用小生境粒子群算法对自抗扰控制器参数进行整定优化。对粒子群及小生境粒子群算法的优化性能进行比较研究的基础上,设计了适合挖掘机器人的自抗扰视觉伺服控制器,采用小生境粒子群算法得到自抗扰控制器整定参数。搭建xPCTarget主机—目标机环境进行试验及仿真,表明小生境粒子群优化的自抗扰视觉伺服控制器控制精度高、鲁棒性强。

Auto Disturbances Refection Visual Servoing Control for Excavator Robot Based on Niching Particle Swarm Optimization

To improve the ability of autonomous mining of excavator robot,design a kind of active disturbance rejection visual servoing controller based on image,to control the position and direction of the end,composed of boom,bucket rod and bucket,of excavator robot,in x-z plane,realize the goal and task for autonomous mining.For the features that many parameters are needed to be tuned for auto disturbance rejection controller,mutual influence between the parameters and the difficulty for parameters tuning,introduce particle swarm optimization algorithm to optimize the parameters of the controller.Because of the shortcoming that original particle swarm algorithm get into the local optimum later,use niche particle swarm optimization algorithm to tune parameters of active disturbance rejection controller(ADRC).On the basis of comparative studies of optimal performance for particle swarm and niche particle swarm optimization algorithm,design the active disturbance rejection visual servoing controller suitable for excavator robot,use niche particle swarm algorithm to get the setting parameter of ADRC.Build xPC Target host-target environment to do experiment and simulation,shows that the active disturbance rejection visual servoing controller optimized by niche particle swarm there is higher control accuracy and strong robustness.