Project Number DUAL USE/0922/0048
Investigator(s) Algolysis
Funding Research and Innovation Foundation
Jun 2023 - May 202
Status In progress
Summary CHARISMA, aims to devise next-generation Maritime Surveillance technology leveraging on heterogeneous autonomous robotic architectures, including unmanned aerial, sea surface and underwater vehicles. Key to this innovation is devising both hardware and software that can be attached as an add-on to existing fleets of Unmanned Vehicles (UVs). The addon will enable UVs to collectively form a mesh network for communication at the lower-level, on top of which a Distributed Shared Memory (DSM) service will be deployed. The DSM will act as the connective tissue for decentralised data exchange that will be critical for devising advanced swarming algorithms to conduct Maritime Surveillance. These swarming behaviours will be largely based on data fusion Machine Learning models. To monitor and control these capability-augmented UV swarms, a Maritime Surveillance Digital Twin will also be implemented.
By combining the expertise, intellectual property and Proof of Concepts in distributed applications (Algolysis Ltd), maritime research and robotics (CMMI), and digital twins and machine learning (CYENS), we will develop a next generation framework for Maritime Surveillance, that will ensure reliable, robust and dependable data collection, provide a comprehensive digital representation of critical situations for better assessment, and will support decision making and high-level control of UV Swarms by competent operators. The entire framework will be validated and demonstrated in a relevant environment (TRL6). Specifically, the addon device will be deployed over a set of heterogeneous UVs with advanced swarming behaviours capable of specifically monitoring maritime infrastructure (e.g. aquaculture facilities).

Current developments of distributed architectures handle concurrency by either providing weak consistency guarantees (e.g. eventual consistency), or by relying on the bounded life span of inconsistent states. However, recent scientific works are shifting the viewpoint around the practicality of strongly consistent distributed storage spaces by proposing latency-efficient algorithms of atomic read/write Distributed Shared Memory (DSM) with provable consistency guarantees.

Our approach is to combine a DSM implementation of ERATO with a hybrid approach leveraging the simplicity of the client-server architecture. This, allows us to take the best features of the Multi-Server architecture and combine them with a low-level Distributed Shared Memory algorithm offering (A) ease of integration with existing VEs and implementation of new ones, since the DSM promises to take care of synchronization and consistency across servers, without application-specific interventions at client nodes and no special hand-off mechanisms between servers for users joining and leaving; and (B) reduced system complexity, and in turn faster development time and lower deployment and maintenance costs.