论文部分内容阅读
采用智能优化方法进行仿人机器人实时步态控制系统设计,把仿人机器人的上楼梯过程近似为7连杆模型,并推导出1个周期内的运动学方程;使用2个模糊控制器分别对上楼梯过程中单双腿支撑周期内的关节轨迹输出进行离线学习训练,通过嵌入式视觉系统采集环境信息作为控制器的输入信息,并进行实时控制;同时为了解决模糊控制器离线训练过程耗时长、结果难收敛的缺点,使用微粒群优化算法对模糊控制器的规则进行优化.实验表明:该方法可以有效减少训练时间,并获得仿人机器人上楼梯过程中较好的稳定控制效果.
The intelligent optimization method is used to design the real-time gait control system of the humanoid robot. The up-stairs process of the humanoid robot is approximated as 7-link model, and the kinematics equation is deduced in 1 cycle. Two fuzzy controllers In the process of going up stairs, the trajectory output of joint trajectory in single-leg support period is trained offline. The environment information is collected by embedded vision system as the controller input information and real-time control. At the same time, in order to solve the problem that the offline training process of fuzzy controller takes long time , The result is difficult to converge, the particle swarm optimization algorithm is used to optimize the rules of the fuzzy controller.The experimental results show that this method can effectively reduce the training time and obtain the better stability control effect of the humanoid robot up the stairs.