***PREPRINT*** Developing a Robotic Hybrid Network for Coastal Surveillance: the INFORE Experience Gabriele Ferri 1 , Raffaele Grasso 1 , Elena Camossi 1 , Alessandro Faggiani 1 , Konstantina Bereta 2 , Marios Vodas 2 , Dimitris Kladis 2 , Dimitris Zissis 2 , Kevin D. LePage 1 Abstract INFORE EU H2020 project has the objective of developing a real-time, interactive extreme-scale analytics and forecasting system capable of handling and analysing massive data streams. The system is validated in three different real-world use cases, In this paper we describe one of them, presenting the development of the INFORE system for a coastal surveillance Maritime Situational Awareness (MSA) application. The MSA INFORE system exploits the synergy between global view (AIS data, ESA Sentinel satellite data), providing contextual information over a wider area, and local view produced by a sensorised hybrid robotic network. The network is composed of an RGB/thermal camera onshore and of two Wave Gliders robots equipped with passive sonars. We focus on the development of this network, describing the cooperative autonomy framework to control the robots. The framework enables the robots to make decisions on their navigation for improving vessel detection and tracking. The INFORE MSA network demonstrates the benefits that the synergy between machine learning, AI and autonomous robots can bring in this kind of monitoring systems. The developed autonomy strategies increase the quality of the information produced by robots. These high-quality real-time observations are fused with the global view in the INFORE MSA and decision-support platform. Data fusion from multi-modal data sources results crucial for the detection of complex events (e.g. illegal fishing), which can then be communicated to decision-makers. Different modules of the systems are ready and under testing. The whole system will be validated in a trial in 2022. Index Terms MSA, coastal surveillance, cooperative autonomy, Wave Glider, Autonomous Surface Vehicles (ASVs), robotic networks I. I NTRODUCTION The Maritime Situational Awareness (MSA) is the capability of understanding events, circumstances and activities impacting the maritime environment [1]. This is achieved through an effective Situational Assessment, which is the process that seamlessly condenses the acquisition of information from the real world, its interpretation to understand the ongoing situation and the projection into the future to support decision making. The improvement of MSA is therefore vital for many important maritime scenarios, such as coastal monitoring and maritime security applications, which are addressed in this paper. These applications are traditionally conducted by means of manned vessels, sensors placed on-shore, such as radars and, more recently, using remote sensing from space [2]. The development of advanced monitoring platforms, composed of a multitude of data sources, imposes that the systems are capable of handling massive data flows streaming from multiple sources, of fusing the received information with the objective of producing significant event notifications. For achieving this, a variety of approaches can be used like machine learning, signal processing, statistical analysis and rule-based approaches. The objective is to analyse historical and real-time data to generate meaningful information and future forecasts for the decision-maker. For instance, in a maritime security applications, the monitoring system has to be capable to raise alarms in case of anomalous ship behaviours, reducing the false alarms and providing valid information both from the content and time perspective. The system operator is then called to verify and closely inspect the alarms. Typically, this happens by means of a manned vessel approaching the suspect ship for the final investigation. An effective and fast analysis of the real-time streams and historical data is therefore crucial to notify significant alarms and to forecast possible situations of interest. To this aim, MSA can highly benefit from recent advances in marine robotics [3]–[5], which suggest that Maritime Unmanned Systems (MUS) can offer novel approaches to many scenarios such as coastal surveillance [6]. MUS are characterised by lower sensing, computational and communication capabilities if compared to traditional assets. However, they can build intelligent networks to accomplish complex missions with features of reliability, persistence, scalability and adaptability [6], [7]. Such robotic networks can complement fixed sensors and remote sensing providing persistent monitoring of an area [8]. Furthermore, they can relieve the system operators activity. Robots can move, upon indication either of an automatic system or of the operator This work has been supported by the INFORE EU H2020 project, grant agreement No 825070. 1 NATO STO Centre for Maritime Research and Experimentation (CMRE), Viale San Bartolomeo 400, 19126 La Spezia (SP), Italy Gabriele.Ferri@cmre.nato.int. 2 Marine Traffic, Katekachi 75, 32 Vassar Street Athens, 115 25, Greece.