This paper considers the coordination of a team of Unmanned Aerial Vehicles (UAVs) that are deployed to search for a moving target within a continuous space. We present an online and decentralised coordination mechanism, based on the max-sum algorithm, to address this problem. In doing so, we introduce a novel coordination technique to the field of robotic search, and we extend the max-sum algorithm beyond the much simpler coordination problems to which it has been applied to date. Within a simulation environment, we benchmarked our max-sum algorithm against three other existing approaches for coordinating UAVs. The results showed that coordination with the max sum algorithm out-performed a best response algorithm, which represents the state of the art in the coordination of UAVs for search, by up to 26%. The results further showed that the max-sum algorithm out-performed an implicitly coordinated approach, where the coordination arises from the agents making decisions based on a common belief, by up to 34 % and finally a non-coordinated approach by up to 68%. 1.

Abstract—Game theoretical learning in potential games is a highly active research area stemming from the connection between potential games and distributed optimisation. In many settings an optimisation problem can be represented by a potential game where the optimal solution corresponds to the potential function maximizer. Accordingly, significant research attention has focused on the design of distributed learning algorithms that guarantee convergence to the potential maximizer in potential games. However, there are currently no existing algorithms that provide convergence to the potential function maximiser when utility functions are corrupted by noise. In this paper we rectify this issue by demonstrating that a version of payoff-based loglinear learning guarantees that the only stochastically stable states are potential function maximisers even in noisy settings. I.