Graduate Exam Abstract

Shankarachary Ragi

Ph.D. Final
January 27, 2014, 1:00 pm to 3:00 pm
ECE Conference Room (C101B)
Cooperative Control of Mobile Sensor Platforms in Dynamic Environments

Abstract: We develop guidance algorithms to control mobile sensor platforms, for both centralized and decentralized settings, in dynamic environments for various applications. Specifically, we develop control algorithms for---unmanned aerial vehicles (UAVs) with on-board sensors for multitarget tracking, autonomous amphibious vehicles for flood- rescue operations, directional sensors (e.g., surveillance cameras) for maximizing an information-gain-based objective function. The following is a brief description of each of the above-mentioned guidance control algorithms. We develop both centralized and decentralized control algorithms for UAVs based on the theories of partially observable Markov decision process (POMDP) and decentralized POMDP respectively. Both POMDPs and Dec-POMDPs are intractable to solve exactly; therefore we adopt an approximation method called nominal belief-state optimization (NBO) to solve (approximately) the control problems posed as a POMDP or a Dec-POMDP. We then address an amphibious vehicle guidance problem for a flood rescue application. Here, the goal is to control multiple amphibious vehicles while minimizing the average rescue time of multiple human targets stranded in a flood situation. We again pose this problem as a POMDP, and extend the above-mentioned NBO approximation method to solve the guidance problem. We also study the problem of controlling multiple 2-D directional sensors while maximizing an objective function based on the information gain corresponding to multiple target locations. This problem is found to be a combinatorial optimization problem, so we develop heuristic methods to solve the problem approximately, and provide analytical results on performance guarantees. We then improve the performance of our heuristics by applying an approximate dynamic programming approach called rollout.

Adviser: Edwin K. P. Chong
Co-Adviser: N/A
Non-ECE Member: Juliana Oprea, Mathematics
Member 3: Diego Krapf, ECE
Addional Members: Rockey Luo, ECE

S. Ragi, H. D. Mittelmann, E. K. P. Chong, "Directional sensor control: Heuristic Approaches," to be submitted.
S. Ragi and E. K. P. Chong, "UAV path planning in a dynamic environment via partially observable Markov decision process," IEEE Transactions on Aerospace and Electronic Systems, vol. 49, no. 4, pp. 2397--2412, October 2013.
S. Ragi and E. K. P. Chong, "Decentralized guidance control of UAVs with explicit optimization of communication," Journal of Intelligent & Robotic Systems, 2013.
S. Ragi, C. S. Tan, and E. K. P. Chong, "Guidance of autonomous amphibious vehicles for flood rescue support," Mathematical Problems in Engineering, vol. 2013, Article ID 528162, 9 pages, 2013.
S. Ragi, H. D. Mittelmann, and E. K. P. Chong, "Directional sensor control for maximizing information gain," in Proceedings of SPIE Optical Engineering + Applications, part of SPIE Optics + Photonics Symposium, San Diego, California, Aug 25--29, 2013, paper number 8857-19.
S. Ragi, C. S. Tan, and E. K. P. Chong, "Feasibility study of POMDP in autonomous amphibious vehicle guidance," in Proceedings of the 2013 IFAC Symposium on Intelligent Autonomous Vehicles (IAV 2013), Gold Coast, Australia, June 26--28, 2013, pp. 85--90.
S. Ragi and E. K. P. Chong, "Decentralized control of unmanned aerial vehicles for multitarget tracking," in Proceedings of the 2013 International Conference on Unmanned Aircraft Systems (ICUAS' 13), Atlanta, Georgia, May 28--31, 2013.
S. Ragi and E. K. P. Chong, "Dynamic UAV path planning for multitarget tracking," in Proceedings of the 2012 American Control Conference, Montreal, Canada, June 27--29, 2012, Paper ThC04.3, pp. 3845--3850.
S. Ragi and E. K. P. Chong, "UAV guidance algorithms via partially observable Markov decision processes," Chapter 59 in Handbook of Unmanned Aerial Vehicles, Dordrecht, Netherlands: Springer Science+Business Media, 2013, to appear.

Program of Study: