基于大脑情感学习的四轮驱动机器人速度补偿控制

由于4轮驱动机器人的轮间耦合特性及系统非线性的存在，即使单个驱动电机的控制精度达到最优，机器人整体的运动控制效果也未必理想.针对这一问题，提出一种基于大脑情感学习的机器人速度补偿控制方法.基于大脑情感学习计算模型，设计了融合机器人整体速度跟踪误差及其积分、微分信息的补偿控制器，通过计算模型内部各节点权值的在线学习，及时地调整控制器的参数，实现对4个轮子速度的自适应补偿.仿真实验表明，该方法有效减小了非线性干扰对系统的影响，具有较高的稳态控制精度和较快的响应速度，大大提高了机器人整体的速度和轨迹跟踪精度.

Velocity compensation control for a four-wheel drive robot based on brain emotional learning

Since there are system nonlinearity and couple relationships in four wheels, even each motor has the optimal parameters, and the whole robot may not be precisely controlled. A velocity compensation controller based on brain emotional learning was applied to the motion control of a four-wheel drive omni-directional mobile robot (FDOMR) in this paper, which contains differential and integral information of robot speed tracking errors. By means of the parameters adjusted through online learning of weight of every node inside the computing model, adaptive compensation of four wheels’ speed was achieved. The simulation results show that the influence produced by non-linear disturbance is effectively decreased; as a result, the system has higher steady-state control precision and faster response speed, greatly increasing the whole velocity and trajectory control precision of the robot.