Hybrid Cognition for Target Tracking in Cognitive Radar Networks

This work investigates online learning techniques for a cognitive radar network utilizing feedback from a central coordinator. The available spectrum is divided into channels, and each radar node must transmit in one channel per time step. The network attempts to optimize radar tracking accuracy by learning the optimal channel selection for spectrum sharing and radar performance. We define optimal selection for such a network in relation to the radar observation quality obtainable in a given channel. This is a difficult problem since the network must seek the optimal assignment from nodes to channels, rather than just seek the best overall channel. Since the presence of primary users appears as interference, the approach also improves spectrum sharing performance. In other words, maximizing radar performance also minimizes interference to primary users. Each node is able to learn the quality of several available channels through repeated sensing. We define hybrid cognition as the condition where both the independent radar nodes as well as the central coordinator are modeled as cognitive agents, with restrictions on the amount of information that can be exchanged between the radars and the coordinator. Importantly, each part of the network acts as an online learner, observing the environment to inform future actions. We show that in interference-limited spectrum, where the signal-to-interference-plus-noise ratio varies by channel and over time for a target with fixed radar cross section, a cognitive radar network is able to use information from the central coordinator in order to reduce the amount of time necessary to learn the optimal channel selection. We also show that even limited use of a central coordinator can eliminate collisions, which occur when two nodes select the same channel. We provide several reward functions which capture different aspects of the dynamic radar scenario and describe the online machine learning algorithms which are applicable to this structure. In addition, we study varying levels of feedback, where central coordinator update rates vary. We compare our algorithms against baselines and demonstrate dramatic improvements in convergence time over the prior art. A network using hybrid cognition is able to use a minimal amount of feedback to achieve much faster convergence times and therefore lower tracking error.

I. Introduction

This work seeks to improve the learning rate of a cognitive radar network (CRN) by introducing a central coordinator (CC) to provide limited feedback. Specifically in this work we address the role of a central coordinator within a cognitive radar network using an online learning strategy to achieve coordination as well as optimize radar tracking and spectrum sharing performance. Generally, radar networks achieve superior tracking performance than is possible for a single high-powered radar node [2]. This is due in part to the increased spatial diversity [3] and spectral agility [4]. Distributed nodes can cover a greater area to perform detection, and can exploit more spatial degrees of freedom to more accurately estimate target parameters. However, to obtain this superior performance, the individual radar nodes which comprise the radar network must coordinate with each other to efficiently use the available spectrum and avoid causing harmful interference inside or outside the network. At the root, this problem is caused by a fundamental need to both explore the available channels and simultaneously exploit the best channels (in terms of tracking performance).