Autonomous surface vehicles are gaining increasing attention worldwide due to the potential benefits of improving safety and efficiency. This has raised the interest in developing methods for path planning that can reduce the risk of collisions, groundings, and stranding accidents at sea, as well as costs and time expenditure. In this paper, we review guidance, and more specifically, path planning algorithms of autonomous surface vehicles and their classification. In particular, we highlight vessel autonomy, regulatory framework, guidance, navigation and control components, advances in the industry, and previous reviews in the field. In addition, we analyse the terminology used in the literature and attempt to clarify ambiguities in commonly used terms related to path planning. Finally, we summarise and discuss our findings and highlight the potential need for new regulations for autonomous surface vehicles.

Artificial intelligence is an enabling technology for autonomous surface vehicles, with methods such as evolutionary algorithms, artificial potential fields, fast marching methods, and many others becoming increasingly popular for solving problems such as path planning and collision avoidance. However, there currently is no unified way to evaluate the performance of different algorithms, for example with regard to safety or risk. This paper is a step in that direction and offers a comparative study of current state-of-the art path planning and collision avoidance algorithms for autonomous surface vehicles. Across 45 selected papers, we compare important performance properties of the proposed algorithms related to the vessel and the environment it is operating in. We also analyse how safety is incorporated, and what components constitute the objective function in these algorithms. Finally, we focus on comparing advantages and limitations of the 45 analysed papers. A key finding is the need for a unified platform for evaluating and comparing the performance of algorithms under a large set of possible real-world scenarios.

No abstract

Deep neural networks are a tool for acquiring an approximation of the robot mathematical model without available information about its parameters. This paper compares the LSTM, stacked LSTM and phased LSTM architectures for time series forecasting. In this paper, motion sensor data from mobile robot driving episodes are used as the experimental data. From the experiment, the models show better results for short-term prediction, where the LSTM stacked model slightly outperforms the other two models. Finally, the predicted and actual trajectories of the robot are compared.

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.