Tracking Multiple Moving Objects for Mobile Robotics Navigation

Abstract

For mobile vehicle navigation in dynamic environments it is desirable that robots have a model of the dynamic aspects of the world. In this paper we present a method for detection and tracking of multiple moving objects using sensor information. The method uses particle filters to estimate objects states, and sample based joint probabilistic data association filters to perform the assignment of features detected from sensor data to filters. A perception mechanism, based on occupancy grids, is presented to distinguish between mobile features and static objects. Experimental results from a real-time implementation using a laser range sensor are presented demonstrating the feasibility and effectiveness of the presented methods.