DDDAMS-based Urban Surveillance and Crowd Control via UAVs and UGVs

Abstract : The main goal of this project was to investigate algorithmic approaches to create scalable, robust, multi-scale, and effective urban surveillance and crowd control strategies using UAVs and UGVs. To achieve the goal, a comprehensive planning and control framework was designed and developed based on dynamic-data-driven, adaptive multi-scale simulation (DDDAMS), where dynamic data is incorporated into simulation, simulation steers the measurement process for data update and system control, and an appropriate level of simulation fidelity is selected based on the time constraints for evaluating alternative control policies using simulation. An information-aggregation approach was developed for crowd dynamics modeling by incorporating multi-resolution data, where a grid-based method is used to model crowd motion with UAVs low-resolution global perception, and an autoregressive model is used to model individuals motion based on UGVs detailed perception. Also, a vision-based target detection and localization via a team of cooperative UAV and UGVs was developed. Finally, a testbed was successfully developed, involving hardware (UAVs and UGVs), software (agent-based simulation, GIS), and human components, and used to demonstrate the proposed framework.

[1]  Zhonghua Xi,et al.  Online collision prediction among 2D polygonal and articulated obstacles , 2016, Int. J. Robotics Res..

[2]  Jian Liu,et al.  Analysis of UAV/UGV control strategies in a DDDAMS-based surveillance system , 2015 .

[3]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Takeo Kanade,et al.  Background Subtraction for Freely Moving Cameras , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Jian Liu,et al.  A comparative study of control architectures in UAV/UGV-based surveillance system , 2014 .

[6]  Frederica Darema,et al.  Dynamic Data Driven Applications Systems: A New Paradigm for Application Simulations and Measurements , 2004, International Conference on Computational Science.

[7]  Jian Liu,et al.  DDDAMS-based Crowd Control via UAVs and UGVs , 2013, ICCS.

[8]  Markus H. Gross,et al.  Visibility Transition Planning for Dynamic Camera Control , 2010, MIG.

[9]  Jian Liu,et al.  Crowd detection and localization using a team of cooperative UAV/UGVs , 2015 .

[10]  Craig Becker,et al.  An Intelligent Observer , 1995, ISER.

[11]  Jian Liu,et al.  Agent-based hardware-in-the-loop simulation for UAV/UGV surveillance and crowd control system , 2013, 2013 Winter Simulations Conference (WSC).

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

[13]  Jian Liu,et al.  A dddams-based UAV and UGV team formation approach for surveillance and crowd control , 2014, Proceedings of the Winter Simulation Conference 2014.

[14]  Nikhil Garg,et al.  Following a Group of Targets in Large Environments , 2012, MIG.

[15]  Young-Jun Son,et al.  Vision-Based Target Detection and Localization via a Team of Cooperative UAV and UGVs , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.