Outdoor pedestrian tracking by multiple mobile robots based on SLAM and GPS fusion

Abstract

This paper presents laser-based pedestrian tracking system in outdoor environments using multiple mobile robots. Each robot detects pedestrians using its own laser scan image by an occupancy-grid-based method and tracks the detected pedestrians via Kalman filtering. When the robots are in close proximity to each other, they exchange pedestrian tracking information through intercommunication, and tracking data are combined using the Covariance Intersection (CI) method. In this cooperative tracking method, the robots constantly identify their own postures with a high degree of accuracy in a common coordinate frame. We apply EKF-SLAM and GPS fusion for robot localization. The experimental results for tracking two pedestrians with two robots validate the proposed method.