Multi-objective four-dimensional glider path planning using NSGA-II

Abstract

Gliders have a big role in data collecting for multiple areas of interest. However, as these vehicles move slowly, in an unknown environment, a good mission planning is crucial, both for vehicle safety and mission accomplishment, therefore ocean currents need to be taken into account in order to generate valid navigation commands. Planning a glider mission in an uncertain environment, with multiple parameters at the same time is a hard 4D (longitude, latitude, depth, time) Multi-Objective Optimization Problem. Multiple approaches are being used to do Glider Path Planning. In this work, we present a new system for helping multi-objective glider path planning in real missions, composed by a path simulator, coupled with the genetic algorithm NSGA-II (Non-dominated Sorting Genetic Algorithm II), producing a set of multiple Pareto-optimal solutions for the specified objectives: goal distance and trajectory safety. Different experiments have been carried out to obtain significant assessment of the proposal. Results show that the system can quickly find multiple Pareto-optimal solutions for a given scenario with fixed obstacles. The proposed approach is suitable to be used during real missions as it does not need high computer specifications. All things considered, the system was able to optimize a multi-objective mission, presenting Pareto-optimal solutions that respond to the specified objectives, thus being a useful tool to help glider pilots decide a priori on the best path.