Vision-Based Human Following and Obstacle Avoidance for an Autonomous Robot in Intersections

Abstract

This paper presents an autonomous transportation robot in intersections, which could help older and disabled people go through the pedestrian crossing safely. the robot is equipped with a camera, an inertial measurement unit, encoders, etc. in this study, a single camera mounted in the front of the robot can be used to detect the region of pedestrian crossing, the obstacles and pedestrians on the pedestrian crossing. after this, the robot can determine the strategy of the obstacle avoidance or human following by using the fuzzy controller. the overall system is tested and evaluated on a university campus.