Assessing the prediction uncertainty in a route optimization model for autonomous maritime logistics. (2nd October 2020)

• Record Type: Journal Article
• Authors: Maskooki, Alaleh; Virjonen, Petra; Kallio, Markku
• Other Names: Crainic Teodor G. guestEditor.; Guajardo Mario guestEditor.; Roy Debjit guestEditor.; Wallace Stein W. guestEditor.
• Is Part Of: International transactions in operational research. Volume 28:Number 4(2021)
• Page Start: 1765
• Page End: 1786
• Publication Date: 2020-10-02
• Subjects: maritime autonomous transport -- mean‐risk analysis -- nearest neighbour -- route prediction -- itinerary planning -- integer programming; Operations research -- Periodicals; 003
• DOI: 10.1111/itor.12882
• Languages: English
• ISSNs: 0969-6016

Abstract

Abstract: Unmanned operations and automation in modern industry create complex everyday problems, which require algorithmic thinking and creativity. Development of risk assessment methods is critical for the future of this business segment. To provide decision support for the management of an autonomous emission control boat, we begin by proposing a k ‐Nearest‐Neighbours ( k ‐NN)‐based trajectory prediction method. This is employed in a bi‐objective routing problem of finding a Hamiltonian circuit in a dynamic network defined by predicted locations of ships over time. The objectives are maximizing the number of measurement tasks to be done and minimizing the corresponding total travel distance of the emission control boat. To evaluate the impact of trajectory prediction uncertainty on Pareto‐optimal itineraries, we propose a risk measure in a mean‐risk framework. The risk is defined based on an expected shortfall when implementation of an efficient itinerary under the predicted trajectories needs rescheduling based on realized trajectories. The risk measure helps the decision maker to evaluate choice alternatives among efficient itineraries under predicted trajectories and to make a balanced risk‐adjusted decision. We show how historical data is employed in integer linear programming for the estimation of such risk measure. Empirical results demonstrate such estimation.