Self-adaptive coordination for fuel-constrained robot teams with periodic and aperiodic communications

Abstract

This paper introduces a novel mission-planning scheme to coordinate a heterogeneous team of mobile robots under fuel and communication constraints. The proposed scheme has a two-level structure, where the upper level is responsible for scheduling team communication, recharging and regrouping activities, while the lower level provides plans and routes for individual group members. Such decomposition allows us to relieve an overall group routing problem by singling out the harshest constraints as a separate time-management problem. Thus, the high-level planning problem is to construct a group schedule ensuring both the efficient refuelling order and the required communication periodicity. The problem is formulated in terms of workforce scheduling problems and a hybrid evolutionary algorithm is developed to solve it. The lower-level module is to arrange emergent team communication sessions in case of unpredicted events. This original problem combines features of vehicle routing problems and special aspects of multi-agent network spreading models. A few simple ruled-based heuristics are presented to treat the problem in a timely manner.

A Hierarchical Approach to Intelligent Mission Planning for Heterogeneous Fleets of Autonomous Underwater Vehicles

“…The hybrid evolutionary algorithm to efficiently solve this problem is also developed and presented. This work extends our previous studies [2,24] on high-level scheduling by introducing a more accurate mathematical model, a completely redesigned evolutionary algorithm, which allowed us to significantly improve our previous results, and a few relevant simulation studies.…”

“…It does, however, allow for group management without any scheduling at all. Also, these results were compared with the performance of our previous revision of the suggested approach [24]. The rejection of a compressed solution representation in favour of more explicit and nuanced genetic operators and local search operators, along with a more flexible solution evaluation, resulted in over twice the performance improvement in terms of both the efficiency of the final solutions and the speed of obtaining them.…”