Dynamic optimal control of Multiple Depot Vehicle Routing Problem with Metric Temporal Logic

This paper discusses a class of mission planning problems that generalizes the standard Multiple Depot Vehicle Routing Problem with Time Windows (MDVRPTW) to incorporate complicated technical constraints. These constraints are specified via Metric Temporal Logic (MTL). A tree search algorithm is provided to solve that novel MDVRPTW with MTL specifications (MDVRPMTL) to optimality. In this work, we use tree search algorithm to seek the optimal flyable trajectories for teams of UAVs starting from different depots to complete missions with complicated time and technical requirements. Then a Stochastic Dynamic Programming (SDP) based algorithm is proposed to dynamically tune the UAV teams in order to secure them against adversarial actions. Examples for practical mission planning problems, in which MTL is used as a high level language to specify complex mission tasks, are presented and discussed in the paper.