Distributed Mission Planning of Complex Tasks for Heterogeneous\n Multi-Robot Teams

Abstract

In this paper, we propose a distributed multi-stage optimization method for\nplanning complex missions for heterogeneous multi-robot teams. This class of\nproblems involves tasks that can be executed in different ways and are\nassociated with cross-schedule dependencies that constrain the schedules of the\ndifferent robots in the system. The proposed approach involves a\nmulti-objective heuristic search of the mission, represented as a hierarchical\ntree that defines the mission goal. This procedure outputs several favorable\nways to fulfill the mission, which directly feed into the next stage of the\nmethod. We propose a distributed metaheuristic based on evolutionary\ncomputation to allocate tasks and generate schedules for the set of chosen\ndecompositions. The method is evaluated in a simulation setup of an automated\ngreenhouse use case, where we demonstrate the method's ability to adapt the\nplanning strategy depending on the available robots and the given optimization\ncriteria.\n