Target Tracking Algorithms For Distributed Sensor Networks PDF Download

"The main research objective of this thesis is to address distributed target tracking for mobile sensor networks. Based on real-life limitations, we are particularly interested in mobile sensors with Limited Sensing Range (LSR). There are three possible multi-target tracking scenarios for n mobile sensors tracking m targets: i) many sensors tracking few targets n ” m (e.g. tracking high-valued targets), ii) a few sensors track many targets n “ m (e.g. the sensor coverage problem and situational awareness in a crowded airport terminal), and iii) swarms of sensors tracking swarms of targets n,m ” 1 (e.g. selflocalization of autonomous vehicles in intellegent transportation systems). First, we show that all three problems can be posed as coupled distributed estimation and control problems for mobile sensor networks. To tackle this estimation and control problem, we propose a unified theoretical framework in which every mobile agent (or sensor) has a two-fold objective: a) maintaining a safe distance (or minimum separation) from neighboring mobile agents during target tracking and b) enhancing the quality of sensed information collectively by the team of sensors to improve the performance of distributed estimation. In many real-life applications, the quality of sensed data is a function of the proximity to the target. We propose an information-theoretic measure for quality of sensed data by each sensor called the information value as the trace of the Fisher Information Matrix (FIM). This metric of quality of sensed data plays a key role in all of our proposed distributed tracking and control algorithms. We show that objective a) of any mobile agent is fundamentally a "collision-avoidance" (or "separation") objective that is a byproduct of flocking behavior for multi-agent systems [48], while objective b) for LSR-type sensors requires solving an additional control problem to enhance the collective information value of the team of agents. We refer to the latter problem as the information-driven control problem. For distributed tracking on mobile networks, we apply Information Filter and Kalman-Consensus Filter (KCF) as effective algorithms for distributed multi-target tracking on networks. The other problem of interest is the formal stability analysis of the coupled distributed estimation and flocking-based mobility-control and self-deployment algorithms for problems i) and ii). We prove that the error dynamics of the KCF and the structural dynamics of the flock of sensors from a cascade nonlinear system and provide a Lyapunov-based stability analysis of case i). We present additional theoretical results on analysis of information-driven control and tracking algoritjms for problems i) and ii) together with successful experimental results. In addition, we identify the key questions regarding problem iii) that remains the subject of ongoing and future research."