Cooperative Observation of Malicious Targets in a 3D Urban Traffic Environment Using UAVs

The Cooperative Multi-Robot Observation of Multiple Moving Targets (CMOMMT) considers two types of robots, observers and targets, in a partially observable 2D environment. The observers' task is to monitor the target robots under a limited radial range of the sensor, minimizing the total time the targets escape observation. The Cooperative Target Observation (CTO), a variant of the CMOMMT problem, considers the environment to be fully observable, where target agents cooperate with observers by reporting their locations. These problems are at the center of many issues that occur in surveillance situations. This work proposes an approach to the extended CTO problem. We call the CTO-URBAN3D problem: a simplified urban traffic scenario in three dimensions for the CTO, considering that suspect transport like cars or buses are targets and Unmanned Aerial Vehicles (UAVs) are observers agents. The approach employs genetic algorithms and recurrent deep neural networks to improve the performance of transport-targets robots and an observer organizational behavior hierarchical consolidated in the CTO literature for UAV-observers robots. The first results were promising, as the average number of transport-targets evasion increased, considering the other approaches to the problem. It raises the need to research new organizations for UAV robots.