Title: Bayesian design of experiments for unmanned aerial vehicles path planning Authors:  Yiolanda Englezou - University of Cyprus (Cyprus) [presenting]
Stelios Timotheou - University of Cyprus (Cyprus)
Christos Panayiotou - University of Cyprus (Cyprus)
Abstract: Traffic monitoring is one of the major tools used for transportation operations and planning. With the emergence of Unmanned Aerial Vehicles (UAVs), new capabilities for enhancing traffic management have emerged. Despite their potential, UAV applications in traffic management have primarily focused on sporadic surveillance of road networks and historical traffic data extraction. Path planning stands out as a critical challenge for UAVs, aiming to optimise routes from initial to target points. For such complex tasks, an optimal design often depends on uncertain model parameters. This dependence leads naturally to a Bayesian approach which can (a) make use of any prior information, and (b) be tailored to the reduction of posterior uncertainty. Towards this, we propose an online Bayesian optimal UAV trajectory design methodology. The proposed method strategically selects the next UAV sampling points to obtain traffic density measurements, while minimising the total uncertainty of the traffic density across all time-space points within the studied time-horizon. The proposed approach integrates the Gaussian Process model into a Bayesian framework to accurately estimate traffic density in multi-lane highways, considering both temporal and spatial correlations, even when data points are sparse. Employing a decision-theoretic approach, we develop a Bayesian optimal UAV trajectory design scheme to mitigate uncertainty.