多传感器信息融合的服务机器人导航方法

在机器人中,计算机视觉与传感器开始交融.本文设计了以人脸识别为视觉导引的主体,传感器为辅的服务机器人系统,提出了一种基于视觉的图像处理算法,采用将形态学处理与自适应阈值分割相结合直接除掉阴影,使用多传感器与视觉融合的方法来解决视觉误判的问题.在小车避障中运用单目测距的原理,跳过了传统相机的标定问题,并将该算法与迷宫机器人路径规划中的左手法则相结合运用在设计的服务机器人中.

Navigation Method of Service Robot Based on Multi-sensor Information Fusion

In the robot,there are fusion of the computer vision and the field of sensor.In the paper,a service robot system is designed that mainly is based on visual guidance using face recognition algorithm and the sensor.An image processing algorithm based on computer vi-sion is proposed,which combines the morphological processing with adaptive threshold segmentation to directly remove the shadow.The multi-sensor and visual fusion approach are used to solve the problem of visual misjudgment.The principle of monocular distance meas-urement is used to avoid the traditional camera's calibration problem.The algorithm is combined with the left-hand rule in the path design of labyrinth robot.