Optimizing Fault-Tolerant Quality-Guaranteed Sensor Deployments for UAV Localization in Critical Areas via Computational Geometry
Marco Esposito, Toni Mancini, Enrico Tronci. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2024.
Marco Esposito, Toni Mancini, Enrico Tronci.
Optimizing Fault-Tolerant Quality-Guaranteed Sensor Deployments for UAV Localization in Critical Areas via Computational Geometry.
IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2024.
DOI: 10.1109/TSMC.2023.3327432BibTex entry
@ARTICLE{esposito-etal:2024:tsmc, AUTHOR = {Esposito, M. and Mancini, T. and Tronci, E.}, DOI = {10.1109/TSMC.2023.3327432}, JOURNAL = {{IEEE} Transactions on Systems, Man and Cybernetics: Systems}, NUMBER = {3}, PAGES = {1515--1526}, PUBLISHER = {IEEE}, TITLE = {Optimizing Fault-Tolerant Quality-Guaranteed Sensor Deployments for {UAV} Localization in Critical Areas via Computational Geometry}, VOLUME = {54}, YEAR = {2024} }
The increasing spreading of small commercial Unmanned Aerial Vehicles (UAVs, aka drones) presents serious threats for critical areas such as airports, power plants, governmental and military facilities. In fact, such UAVs can easily disturb or jam radio communications, collide with other flying objects, perform espionage activity, and carry offensive payloads, e.g., weapons or explosives.
A central problem when designing surveillance solutions for the localisation of unauthorised UAVs in critical areas is to decide how many triangulating sensors to use, and where to deploy them to optimise both coverage and cost effectiveness.
We propose an AI-based black-box optimisation algorithm to compute deployments of triangulating sensors for UAV localisation, optimising a given blend of metrics, namely: coverage under multiple sensing quality levels, cost-effectiveness, fault-tolerance.
Our algorithm enables sensor placements on large, complex 3D regions, which exhibit obstacles (e.g., buildings), varying terrain elevation, different coverage priorities, constraints on possible sensors placement. Our novel approach relies on computational geometry and statistical model checking, and enables the effective use of off-the-shelf AI-based black-box optimisers. Moreover, our method allows us to compute a closed-form, analytical representation of the region uncovered by a sensor deployment, which provides the means for rigorous, formal certification of the quality of the latter.




Results
- Practical feasibility of our approach shown by computing optimal sensor deployments for UAV localisation in two large, complex 3D critical regions, the Rome Leonardo Da Vinci International Airport (FCO) and the Vienna International Center (VIC)
- Results show that we can compute optimal sensor deployments within a few hours on a standard workstation and within minutes on a small parallel infrastructure.