摘要
针对未知环境下机器人自主导航问题,以提升机器人视觉跟随精度与自主导航性能为目的,研究基于视觉双窗口的机器人视觉跟随式导航方法。机器人通过视觉双窗口摄像头采集跟随对象图像,采用两步标定算法获取视觉双窗口摄像头内外参数,将双窗口摄像头统一至相同世界坐标系内,实现视觉双窗口摄像机图像与现实场景内图像间的映射。对采集的图像序列进行特征立体匹配,将二维与三维扩展Kalman滤波器同时用于跟随对象位置预测,实现跟随目标的跟随定位。以基于行为的控制结构作为机器人导航控制结构的基础,根据跟随目标的跟随定位结果利用宏行为控制机器人运动。仿真结果显示,上述方法可控制机器人在复杂背景环境下准确跟随设定的对象,在存在障碍物的条件下,机器人可准确避开障碍物,并在之后回归到准确的跟随导航路线。
Aiming at the problem of robot autonomous navigation in unknown environment,in order to improve the robot visual following accuracy and autonomous navigation performance,a robot visual following navigation method based on visual double windows is was studied.The robot collecteds the following object image through the visual dual window camera,obtains obtained the internal and external parameters of the visual dual window camera by using the two-step calibration algorithm,unifies unified the dual window camera into the same world coordinate system,and realizes realized the mapping between the visual dual window camera image and the image in the real scene.On this basis,the feature stereo matching is was carried out for the collected image sequence,and the two-dimensional and three-dimensional extended Kalman filter wereare used to predict the position of the following object at the same time,so as to realize the following and positioning of the following target.The behavior based control structure wais used as the basis of the robot navigation control structure,and the macro behavior wais used to control the robot motion according to the following and positioning results of the following target.The simulation results show that this method can control the robot to accurately follow the set object in the complex background environment.;Under the condition of obstacles,the robot can accurately avoid the obstacles,and then return to the accurate follow navigation route.
作者
王连枝
朱朝旭
赵帅
李宝玺
WANG Lian-zhi;ZHU Zhao-xu;ZHAO Shuai;LI Bao-xi(Department of the Electrical Engineering,Kaifeng University,Kaifeng Henan 475000,China)
出处
《计算机仿真》
北大核心
2023年第2期466-470,共5页
Computer Simulation
关键词
视觉双窗口
机器人视觉
跟随式导航
摄像头标定
位置预测
宏行为
Visual double window
Robot vision
Follow navigation
Camera calibration
Location prediction
Macro behavior