Researchers from the Finnish Geospatial Research Institute and Aalto University are set to team up with maritime IoT startup Fleetrange and vessel operator Tallink Grupp as part of a research project to develop techniques for autonomous navigation of ships, using a combination of sensors, machine learning and artificial intelligence.
The technology being developed will combine data from visual images, environmental sound recordings, radar and LiDAR ranging, satellite navigation, and vessel transponders. The systems will be installed on a Tallink Grupp vessel, the Megastar, with the data collected to be processed using new artificial intelligence and machine learning software.
“A single sensor is never sufficient for providing complete safety-critical information to the crew,” said Dr. Sarang Thombre, Research Manager at the Finnish Geospatial Research Institute.
“They always refer to multiple devices providing overlapping information so that defects in any one device can be easily identified and excluded. An autonomous navigation system should work on a similar principle.”
Baltic Sea testing
The project is being led and funded by the European Space Agency (ESA), and is titled Artificial Intelligence / Machine Learning Sensor Fusion for Autonomous Vessel Navigation (Maritime AI-NAV). The vessel Megastar, Tallink Grupp’s newest ship, will host the practical field tests on the Helsinki-Tallinn route on the Baltic Sea.
“The choice of Megastar as a test vessel was an easy decision and we are delighted to have Tallink Grupp’s support for the project,” said Capt. Henrik Ramm-Schmidt, CEO and Founder of Fleetrange.
“Tallink is the front-runner in innovative new solutions and the Megastar is the most advanced and environmentally friendly ferry in this area. The traffic area between Tallinn and Helsinki is also highly dense with both commercial vessels and leisure boats and provides an excellent testing ground for the new techniques we aim to study.”
ESA’s overall objective is to improve European know-how in the field of autonomous transport and to study how European space-based positioning and navigation infrastructure, such as Galileo and EGNOS, can contribute to enhancing opportunities in this field.
The specific goal of this project is to create systems that can automatically identify and recognise objects, such as navigation aids and other vessels and boats around the ship and provide improved situational awareness information through sensor fusion.
“The recent advances in artificial intelligence and machine learning allow for new ways to learn to identify and predict the movement of vessels, with a better accuracy than has been possible before,” said Dr. Simo Särkkä, Professor of Aalto University.