Development of Image Processing based Human Tracking and Control Algorithm for a Service Robot

Abstract

This paper presents an human detection algorithm and an obstacle avoidance algorithm for a service robot that provides a service tracking. The mobile robot will have the ability to follow a human and avoid dynamically moving obstacles in an unstructured outdoor environment. To detect a human by an Image processing, we defined features of the human body in xml file and employed a support vector data description method. In order to avoid moving obstacles while tracking a person, we defined an ultrasonic obstacle sensor, each obstacle using the relative distance between the robot and an obstacle. For smoothly by passing obstacles without collision, a dynamic obstacle avoidance algorithm for the service robot is implemented, which directly employed a real-time position vector between the robot and the shortest path around the obstacle.