Decentralized Multi-target Tracking with Multiple Quadrotors using a PHD Filter

We consider a scenario in which a group of quadrotors is tasked at tracking multiple stationary targets in an unknown, bounded environment. The quadrotors search for targets along a spatial grid overlaid on the environment while performing a random walk on this grid modeled by a discrete-time discrete-state (DTDS) Markov chain. The quadrotors can transmit their estimates of the target locations to other quadrotors that occupy their current location on the grid; thus, their communication network is time-varying and not necessarily connected. We model the search procedure as a renewal-reward process on the underlying DTDS Markov chain. To accommodate changes in the set of targets observed by each quadrotor as it explores the environment, along with uncertainties in the quadrotors' measurements of the targets, we formulate the tracking problem in terms of Random Finite Sets (RFS). The quadrotors use RFS-based Probability Hypothesis Density (PHD) filters to estimate the number of targets and their locations. We present a theoretical estimation framework, based on the Gaussian Mixture formulation of the PHD filter, and preliminary simulation results toward extending existing approaches for RFS-based multi-target tracking to a decentralized multi-robot strategy for multi-target tracking. We validate this approach with simulations of multi-target tracking scenarios with different densities of robots and targets, and we evaluate the average time required for the robots in each scenario to reach agreement on a common set of targets.

[1]  Vijay Kumar,et al.  Cooperative multi-target localization with noisy sensors , 2013, 2013 IEEE International Conference on Robotics and Automation.

[2]  Pratap Tokekar,et al.  Algorithm for searching and tracking an unknown and varying number of mobile targets using a limited FoV sensor , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Esko Valkeila,et al.  An Introduction to the Theory of Point Processes, Volume II: General Theory and Structure, 2nd Edition by Daryl J. Daley, David Vere‐Jones , 2008 .

[4]  David L. Hall,et al.  Random Set Theory for Target Tracking and Identification , 2001 .

[5]  Spring Berman,et al.  Multi-Robot Target Search using Probabilistic Consensus on Discrete Markov Chains , 2020, 2020 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[6]  Kazuya Yoshida,et al.  Collaborative mapping of an earthquake‐damaged building via ground and aerial robots , 2012, J. Field Robotics.

[7]  Tiago Pimentel,et al.  Mapping planetary caves with an autonomous, heterogeneous robot team , 2013, 2013 IEEE Aerospace Conference.

[8]  Wolfram Burgard,et al.  Tracking multiple moving objects with a mobile robot , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Sheldon M. Ross,et al.  Introduction to probability models , 1975 .

[10]  R. Mahler Multitarget Bayes filtering via first-order multitarget moments , 2003 .

[11]  Ulrike Goldschmidt,et al.  An Introduction To The Theory Of Point Processes , 2016 .

[12]  N. Roy,et al.  Autonomous Navigation and Exploration of a Quadrotor Helicopter in GPS-denied Indoor Environments , 2009 .

[13]  Wolfram Burgard,et al.  Coordinated multi-robot exploration , 2005, IEEE Transactions on Robotics.

[14]  Ba-Ngu Vo,et al.  The GM-PHD Filter Multiple Target Tracker , 2006, 2006 9th International Conference on Information Fusion.

[15]  R. Serfozo Basics of Applied Stochastic Processes , 2012 .

[16]  Ronald P. S. Mahler,et al.  Statistical Multisource-Multitarget Information Fusion , 2007 .

[17]  Philip M. Dames,et al.  Distributed multi-target search and tracking using the PHD filter , 2017, 2017 International Symposium on Multi-Robot and Multi-Agent Systems (MRS).

[18]  Y. Bar-Shalom Tracking and data association , 1988 .

[19]  G. Grimmett,et al.  Probability and random processes , 2002 .

[20]  Gaurav S. Sukhatme,et al.  Experiments with a Large Heterogeneous Mobile Robot Team: Exploration, Mapping, Deployment and Detection , 2006, Int. J. Robotics Res..

[21]  Ali Esmaili,et al.  Probability and Random Processes , 2005, Technometrics.

[22]  Ba-Ngu Vo,et al.  The Gaussian Mixture Probability Hypothesis Density Filter , 2006, IEEE Transactions on Signal Processing.

[23]  Volkan Isler,et al.  Triangulation Based Multi Target Tracking with Mobile Sensor Networks , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[24]  Wolfram Burgard,et al.  Coordination for Multi-Robot Exploration and Mapping , 2000, AAAI/IAAI.

[25]  Vijay Kumar,et al.  Cooperative air and ground surveillance , 2006, IEEE Robotics & Automation Magazine.

[26]  Trung Dung Ngo,et al.  A Scalable, Decentralised Large-Scale Network of Mobile Robots for Multi-target Tracking , 2014, IAS.

[27]  Elizabeth L. Wilmer,et al.  Markov Chains and Mixing Times , 2008 .

[28]  Ronald P. S. Mahler,et al.  Random Set Theory for Target Tracking and Identification , 2001 .

[29]  Patric Jensfelt,et al.  Active global localization for a mobile robot using multiple hypothesis tracking , 2001, IEEE Trans. Robotics Autom..

[30]  Wolfram Burgard,et al.  The Mobile Robot Rhino , 1995, SNN Symposium on Neural Networks.