Obstacle Avoidance Control for Mobile Robots based on Vision

Abstract

This paper treats the navigation problem of mobile robots to avoid obstacles according to vision information. In our method, first we detect obstacles which exist in front of a mobile robot by calculating the optical flow. Then, based on the area of detection we decide the optimal trajectory for a robot. Here, we may use the sensor data for supporting a vision system. In order to find the optimal trajectory, we compute the distance between a mobile robot and obstacle evaluating a function. Through experiments, we show how our proposed method can avoid obstacles.