LOW-LEVEL SENSOR FUSION-BASED HUMAN TRACKING FOR MOBILE ROBOT

In this paper, a novel sensor-based human tracking method that enables a mobile robot to follow a human with high robustness and responsiveness is presented. The method is based on low-level sensor data fusion combining depth data from a stereo camera and an infrared 2D laser range finder (LRF) to detect target human in the near surrounding of the robot. After initial position of target human is located by sensor fusion-based human detection, a novel tracking algorithm that combines a laser data-based search window and Kalman filter is used to recursively predict and update estimations of target human position in robot’s coordinate system. The use of tracking window contributes to reduction of computational cost by defining region of interest (ROI) enabling so real-time performance. The performance of proposed system was tested in several indoor scenarios. Experimental results show that the proposed human detection algorithm is robust and human tracking algorithm is able to handle fast human movements and keep tracking of target human in various scenarios