Smart Targets to Avoid Observation in CTO Problem

Security is one of the values essential to the common good of society. With population growth and modernity, new challenges have emerged to ensure the safety of a large number of people in circulation with limited resources for observation. The Cooperative Targets Observation (CTO) problem consists of two groups of agents, observers and targets, in which observer agents seek to maximize the Average Number of Observed Targets (ANOT) in environments where there are more targets than observers. In most of the approaches to this problem the behavior of the target agents was modeled very simply, out of reality in competitive multiagent environments. The objective of this work is to propose and validate four strategies for the team of target agents in the CTO problem, three involving grouping algorithms and two organizational paradigms, and one using neural networks. The approaches were implemented and tested on the NetLogo agent-based simulation platform. Test results showed that target team performance increased considerably when they were modeled as rational agents in an organization.