Human following robot based on control of particle distribution with integrated range sensors

Abstract

In this study, a human-following robot based on a laser range scanner and a Kinect sensor is developed for tracking and identifying target human. Most of tracking systems with laser range scanners have the problems of occlusions and the harmful effects of noise. Generally, human tracking systems utilize particle filter to solve those problems. However, if there are several people in the measurement range of laser scanners, particles are sometimes distributed to only a certain human. With a particle filter based on control of particle distribution and with integrated sensors between LRF and Kinect, this study aims to identify the target human and achieve human-following behavior by the robot Tracking experiments of several people and human-following experiments were performed, and some results are provided in the paper.