On the use of maritime training simulators with humans in the loop for understanding and evaluating algorithms for autonomous vessels

Abstract

Abstract The prospect of a future where the maritime shipping industry is dominated by autonomous vessels is appealing and gaining global interest from industry majors, research institutions, and academia. Potential advantages include increased operational safety, reduced costs, and lower environmental footprint. However, the transition will not happen overnight and is not without challenges. For example, algorithms for autonomous navigation must take into consideration safety concerns of the own ship, its crew and passengers, other surrounding ships, and the surrounding environment. This raises a need to test and verify safety, performance, and robustness of the algorithms responsible for the autonomous functionality. In addition, the transition towards fully autonomous ships is likely to be gradual and involve remote control centres and ships with varying degrees of autonomy. Hence, humans will inevitably have to interact with autonomous vessels in a variety of scenarios, including overriding own ships from land or on board, as well as communicating with autonomous ships from other fleets. Inevitably, full scale scenario testing involving real vessels and humans is costly, impractical, time-consuming, and potentially dangerous. In this paper, we propose an alternative approach, and explore how maritime navigation training simulators with humans in the loop can be used as a testbed for understanding and evaluating algorithms for autonomous vessels. In the proposed setting, we can directly compare choices made by an algorithm with those of a skilled human navigator for a variety of navigational tasks. Moreover, we can study in real-time the behaviour and decision-making of human navigators in mixed scenarios that also include autonomous ships, whether this is known beforehand or not. Our paper provides an overview of related work, details on maritime simulators and how algorithms can be tested, and some of the technical requirements. To exemplify our approach, we present two example test setups, and provide a brief discussion of our findings. We conclude that using maritime training simulators enables the study of several interesting and vital research questions, including that of the interaction between autonomous and traditional vessels operating side by side.