Game-theoretic cooperative coverage using autonomous vehicles

This paper presents a game-theoretic method for cooperative coverage of a priori unknown environments using a team of autonomous vehicles. These autonomous vehicles are required to cooperatively scan the search area without human supervision as autonomous entities. However, due to the lack of a priori knowledge of the exact obstacle locations, the trajectories of autonomous vehicles cannot be computed offline and need to be adapted as the environment is discovered in situ. In this regard, the cooperative coverage method is based upon the concept of multi-resolution navigation that consists of local navigation and global navigation. The main advantages of this algorithm are: i) the local navigation enables real-time locally optimal decisions with a reduced computational complexity by avoiding unnecessary global computations, and ii) the global navigation offers a wider view of the area seeking for unexplored regions. This algorithm prevents the autonomous vehicles from getting trapped into local minima, which is commonly encountered in potential field based algorithms. The neighboring agents among the team of autonomous vehicles exchange the most up-to-date environment information for collaborations. Given sufficient operation time, the team of autonomous vehicles are capable of achieving complete coverage in their own regions. However, in order to further improve cleaning efficiency and reduce operation time, the vehicles that finish early should participate in assisting others that are in need of help. In this sense, a cooperative game is designed to be played among involved agents for optimal task reallocation. This paper considers the cooperative oil spill cleaning application; however the concepts can be applied to general class of coverage problems. The efficacy of the algorithm is validated using autonomous vehicles equipped with lasers in an obstacle-rich environment on the high-fidelity Player/Stage simulator.