Bounded Rational Unmanned Aerial Vehicle Coordination for Adversarial Target Tracking

This paper addresses the problem of tracking an actively evading target by employing a team of coordinating unmanned aerial vehicles while also learning the level of intelligence for appropriate countermeasures. Initially, under infinite cognitive resources, we formulate a game between the evader and the pursuing team, with an evader being the maximizing player and the pursuing team being the minimizing one. We derive optimal pursuing and evading policies while taking into account the physical constraints imposed by Dubins vehicles. Subsequently, we relax the infinite rationality assumption, via the use of level-k thinking. Such rationality policies are computed by using a reinforcement learning-based architecture and are proven to converge to the Nash policies as the thinking levels increase. Finally, simulation results verify the efficacy of the approach.