Multi-step look-ahead policy for autonomous cooperative surveillance by UAVs in hostile environments

In this paper a real-time cooperative path decision algorithm for UAV surveillance is proposed. The surveillance mission involves multiple competing objectives. To handle these competing objectives, a layered decision framework is proposed, in which different objectives are deemed relevant at different decision layers depending on their priorities. Compared to previous work, in which multiple objectives are integrated into a single global objective function, this layered decision framework allows an objective with higher priority to be satisfied first by eliminating possible compromises from other less important ones. An important objective of the path decision algorithm is to navigate the UAV safely in a hostile environment. To achieve this, the key is to increase the time horizon of the path decisions. A multi-step look-ahead path decision strategy based on a roll-out policy is proposed. This policy has moderate complexity and, when used in the layered decision framework, it is able to find safe paths effectively and efficiently. For the guidance of a group of UAVs, the use of small path-decision groups and the assigning of different tasks to different UAVs can also be incorporated into the algorithm, which makes it more flexible in such scenarios.