Autonomous ships are expected to improve the level of safety and efficiency in future maritime navigation. Such vessels need perception for two purposes: to perform autonomous situational awareness and to monitor the integrity of the sensor system itself. In order to meet these needs, the perception system must fuse data from novel and traditional perception sensors using Artificial Intelligence (AI) techniques. This article overviews the recognized operational requirements that are imposed on regular and autonomous seafaring vessels, and then proceeds to consider suitable sensors and relevant AI techniques for an operational sensor system. The integration of four sensors families is considered: sensors for precise absolute positioning (Global Navigation Satellite System (GNSS) receivers and Inertial Measurement Unit (IMU)), visual sensors (monocular and stereo cameras), audio sensors (microphones), and sensors for remote-sensing (RADAR and LiDAR). Additionally, sources of auxiliary data, such as Automatic Identification System (AIS) and external data archives are discussed. The perception tasks are related to well-defined problems, such as situational abnormality detection, vessel classification, and localization, that are solvable using AI techniques. Machine learning methods, such as deep learning and Gaussian processes, are identified to be especially relevant for these problems. The different sensors and AI techniques are characterized keeping in view the operational requirements, and some example state-of-the-art options are compared based on accuracy, complexity, required resources, compatibility and adaptability to maritime environment, and especially towards practical realization of autonomous systems.

We present Galileo Open Service Navigation Message Authentication (OSNMA) observed operational information and key performance indicators (KPIs) from the analysis of a ten-day-long dataset collected in static open-sky conditions in southern Finland and using our in-house-developed OSNMA implementation. In particular, we present a timeline with authentication-related events, such as authentication status and type, dropped navigation pages, and failed cyclic redundancy checks. We also report other KPIs, such as the number of simultaneously authenticated satellites over time, time to first authenticated fix, and percentage of authenticated fixes, and we evaluate the accuracy of the authenticated position solution. We also study how satellite visibility affects these figures. Finally, we analyze situations where it was not possible to reach an authenticated fix, and offer our findings on the observed patterns.

Ultra Wideband (UWB) signals are a promising choice for indoor positioning applications, since they are able to penetrate walls to a certain extent. Nevertheless, signal reflections and Non-Line-of-Sight (NLOS) propagation cause bias in the measured range. This ranging error can be corrected with Machine Learning (ML) methods such as Convolutional Neural Networks (CNNs). However, these ML models often generalize poorly between different environments. In this work we present an instance-based Transfer Learning (TL) approach, that enables generalizing a CNN-based ranging error mitigation approach to a new situation with only a few unlabeled training samples. The performance of the UWB error correction approach is demonstrated in a real-life infrastructure-free cooperative positioning setting.

Global Navigation Satellite Systems (GNSSs) have become a critical service in modern society, and this has increased the need for GNSS situational awareness. On top of this, the GNSS field is rapidly changing. Increased signal interference has been observed in the last few decades, requiring more prominent GNSS services, in addition to flexibility and adaptability from GNSS monitoring systems. With the emergence of new Galileo features, such as Open Service Navigation Message Authentication (OSNMA) and the High Accuracy Service (HAS), monitoring systems have the opportunity to leverage these new services to enhance GNSS situational awareness. The Finnish Geospatial Research Institute (FGI) has developed an open GNSS situational awareness service called GNSS-Finland, which monitors signal quality, detects potential interference, and informs users of the expected level of performance of different services around 47 stations in the Finnish Continuously Operating Reference Station (CORS) network (FinnRef). Recently GNSS-Finland’s capabilities have been extended to monitor and leverage OSNMA and the HAS around FinnRef stations. Due to the novelty of both OSNMA and the HAS, custom software solutions are needed to integrate these services into GNSS-Finland. We give an overview of GNSS-Finland and its flexible architecture, present the integration of the new Galileo services into GNSS-Finland, and finally discuss how these new services can be leveraged from a monitoring system point of view.

This paper presents an end-to-end solution towards authenticated positioning using only Galileo E1B signal by utilizing the Open Service Navigation Message Authentication (OSNMA). One of the primary objectives of this work is to offer a complete OSNMA-based authenticated position solution by releasing FGI-GSRx-v2.1.0 (an open-source software-defined multi-constellation GNSS receiver) update. The idea is to bridge the gap between two open-source implementations by the Finnish Geospatial Research Institute (FGI): FGI-GSRx and FGI-OSNMA (an open-source Python software package). FGI-GSRx-v2.1.0 utilizes FGI-OSNMA as an OSNMA computation engine to generate the authentication events with the information of whether a tag is valid or not. FGI-GSRx computes the position authentication at the navigation layer with the Galileo E1B satellites that are OSNMA verified and have $C/N_0$ greater than 30 dB-Hz. OSNMA-based position authentication is shown through the findings from two real-world open sky use cases: (i) a clean nominal scenario and (ii) a spoofing scenario recorded during the Jammertest 2023 in Andøya, Norway. In the case of the spoofing scenario, the software receiver stops offering an authenticated position solution. A detailed comparison between the authenticated and non-authenticated position solutions also highlights the damage spoofing could cause to the end user in deviating the user’s position on a target spoofed location.