Collaborative multi-target tracking using networked micro-robotic vehicles

Abstract

This paper presents a collaborative target tracking framework, in which distributed mechanisms are developed for tracking multiple mobile targets using a team of networked micro robotic vehicles. Applications of such a framework would include detection of multi-agent intrusion, network-assisted attack localization, and other collaborative search scenarios. The key idea of the developed framework is to design distributed algorithms that can be executed by tracking entities using a mobile ad hoc network. The paper comprises the following components. First, the software and hardware architectural detail of a Swarm Capable Autonomous Vehicle (SCAV) system that is used as the mobile platform in our target tracking application is presented. Second, the details of an indoor self-localization and Kalman filter based navigation system for the SCAV are presented. Third, a formal definition of the collaborative multi-target tracking problem and a heuristic based networked solution are developed. Finally, the performance of the proposed tracking framework is evaluated on a laboratory test-bed of a fleet of SCAV vehicles. A detailed system characterization in terms localization, navigation, and collaborative tracking performance is performed on the SCAV test-bed. In addition to valuable implementation insights about the localization, navigation, filtering, and ad hoc networking processes, a number of interesting conclusions about the overall tracking system are presented.