The recent development of artiﬁcial intelligence has increased the interest of researchers and practitioners towards applying its techniques into multiple domains like automotive, health care and air space to achieve automation. Combined to these applications, the attempt to use artiﬁcial intelligence techniques into carrying out safety issues is momentarily at a progressive state. As the artiﬁcial intelligence problems are getting even more complex, large processing power is demanded for safety-critical systems to fulﬁll real-time requirements. These challenges can be solved through edge or cloud computing, which makes the communication an integral part of the solution. This study aims at providing a comprehensive picture of the state of the art artiﬁcial intelligence based safety solutions that uses diﬀerent communication technologies in diverse application domains. To achieve this, a systematic mapping study is conducted and 565 relevant papers are shortlisted through a multi-stage selection process, which are then analyzed according to a systematically deﬁned classiﬁcation framework. The results of the study are based on these main objectives: to clarify current research gaps in the ﬁeld, to identify the possibility of increased usage of cellular communication in multiple domains, to identify the mostly used artiﬁcial intelligence algorithms and to summarize the emerging future research trends on the topic. The results demonstrate that automotive domain is the one applying artiﬁcial intelligence and communica-Raﬁa tion the most to implement safety and the most used artiﬁcial intelligence in this domain is neural networks, clustering and computer vision; applying cellular communication to automotive domain is highest; the use of non-cellular communication technologies is dominant however a clear trend of a rapid increase in the use of cellular communication is observed specially from 2020 with the roll-out of 5G technology.

A Comprehensive Study on Artificial Intelligence Algorithms to Implement Safety Using Communication Technologies

Abstract Accurate and reliable navigation systems are necessary to deploy autonomous shipping. For this purpose, georeferenced vehicle-pose information is often generated using sensor data fusion consisting of GNSS data, inertial measurement, and other applicable aiding sensors. This technical overview summarizes current European projects and international work in the field of GNSS-based maritime navigation and introduces and discusses the sensors and methods involved. The review focuses on approaches with proprioceptive sensor technology. Therefore, as a limitation, environment sensing algorithms (e. g., SLAM) are explicitly not included. It is concluded that highly accurate and reliable sensor fusion should include complementary and redundant onboard sensors, which are tightly coupled.

Review of pose estimation within European ship-automation projects using GNSS-based navigation

Misunderstanding the intentions of other vessels is one of the most common causes of ship collisions today. Such misunderstandings are particularly dangerous during navigation in restricted areas, such as fairways, port areas, and inland water ways, and may be exacerbated with the introduction of unmanned vessels. To ensure safe operations, the understanding of the intentions and future positions of manned and unmanned vessels, the PREParE SHIPS project is creating a system capable of determining a ship's position with high accuracy, predicting its future positions, and communicating the current and future positions. The positioning sub-system combines the signals of Galileo and EGNOS, EGNSS and SBAS respectively, with land based RTK corrections, providing a positioning accuracy of centimetres. Furthermore, by taking advantage of Galileo's authentication features, the positioning system provides enhanced security measures against spoofing attacks. The prediction sub-system will use a ship dynamic model and machine learning to predict the future positions of the ship and improve said predictions with time, while the communication sub-system will broadcast the prediction through VDES ship2ship and ship2shore. PREParE SHIPS will improve the navigation and handling of ships, through high accuracy positioning and dynamic predictions, as well as reduce the risk of ship collisions, through the communication of present and predicted future positions. PREParE SHIPS is expected to increase safety and efficiency significantly and will be the base of future autonomous operations and standardisations.

S Nord

Papers

“PREParE SHIPS” for Automated Ship Passages by Modern Decision Support Tools by Exchanging Future Positions