Program

Abstract: We address the problem of decentralized state estimation in multi-agent networks. The spatially distributed agents acquire local measurements with information about a time-varying state described by some underlying state-space model. The agents aim at making inference about the time-varying state not only based on their measurements but also using information received from neighboring agents. This information can be local estimates of the state and/or measurements of these agents. We discuss ways of constructing the local estimates through such cooperation. We present strategies based on the concepts of diffusion and consensus.

Short Bio: Petar M. Djurić received the B.S. and M.S. degrees in electrical engineering from the University of Belgrade, respectively, and the Ph.D. degree in electrical engineering from the University of Rhode Island. He is a SUNY Distinguished Professor and currently a Chair of the Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY, USA. His research has been in the area of signal and information processing with primary interests in the theory of signal modeling, detection, and estimation; signal and information processing over networks; machine learning; Monte Carlo-based methods; RFID and the IoT. Prof. Djurić was a recipient of the IEEE Signal Processing Magazine Best Paper Award in 2007 and the EURASIP Technical Achievement Award in 2012. In 2008, he was the Chair of Excellence of Universidad Carlos III de Madrid-Banco de Santander. From 2008 to 2009, he was a Distinguished Lecturer of the IEEE Signal Processing Society. He has been on numerous committees of the IEEE Signal Processing Society and of many professional conferences and workshops. He is the Editor-in-Chief of the IEEE Transactions on Signal and Information Processing over Networks. Prof. Djurić is a Fellow of IEEE and EURASIP.

Abstract: The multi-target tracking (MTT) literature includes a dizzying alphabet soup of problem statements, solution methodologies, and performance metrics. This talk identifies some foundational elements of the MTT problem, with the goal of providing an accessible introduction while illustrating interesting aspects and challenges. We focus on the maximum a posteriori (MAP) criterion and the multiple-hypothesis tracking solution paradigm. We address some concerns that have been raised in the literature regarding MHT, and discuss recent advances that include graph-based methods to improve tractability in challenging disparate-sensor settings.

Bio: Dr. Coraluppi is a Chief Scientist at Systems & Technology Research (STR), a Boston-based research company focused on defense and intelligence problems. He received the BS degree in Electrical Engineering and Mathematics from Carnegie Mellon University in 1990, and MS and PhD degrees in Electrical Engineering from the University of Maryland in 1992 and 1997. He has led research in several US and NATO research settings (ALPHATECH, NATO Undersea Research Centre, Compunetix, and STR). His primary focus has been on multi-target tracking and multi-sensor data fusion for difficult surveillance challenges in various domains (air, ground, maritime, and undersea). He is Associate Editor-in-Chief for both the IEEE Transactions on Aerospace and Electronic Systems and the ISIF Journal of Advances in Information Fusion. He serves on the IEEE AESS Board of Governors and the ISIF Board of Directors. This year, he is Technical Co-Chair of ISIF/IEEE FUSION 2018 to be held in Cambridge UK.