论文部分内容阅读
从机器人运动控制的需要出发,在分析视觉坐标系和机器人坐标系的映射关系基础上,建立了机器人单目视觉定位的数学模型.提出了基于遗传算法的参数辩识方法.该算法直接利用建立的视觉定位数学模型和一组特征点实测结果,通过遗传算法得到包括摄像机参数在内的所有参数.比较了直接测量法、待定系数法、基于遗传算法3种计算方法在实际ROBOCUP全自主机器人平台的运用结果,实验证实提出的算法可以得到更好的实际效果.
Based on the need of robot motion control and based on the analysis of the mapping relationship between the visual coordinate system and the robot coordinate system, a mathematical model of robot monocular vision positioning is established and a parameter identification method based on genetic algorithm is proposed. , And all the parameters including the camera parameters are obtained by the genetic algorithm.Compared with the direct measurement method, the undetermined coefficient method and the genetic algorithm based on the three kinds of calculation methods in the actual ROBOCUP fully autonomous robotic platform The experimental results show that the proposed algorithm can get better practical results.