Estonian shipping company Tallink Grupp has joined researchers from the Finnish Geospatial Research Institute, Aalto University and Fleetrange Ltd. to develop techniques for autonomous navigation for ships.
The research project, carried out under a programme of, and funded by, the European Space Agency (ESA), would focus on autonomous navigation as a means of improving safety, using a combination of different sensors, machine learning and artificial intelligence.
The technology will combine data from visual images, environmental sound recordings, RADAR and LiDAR ranging, satellite navigation, and vessel transponders. These sensors would be installed on the LNG-powered fast ferry Megastar for practical field tests on the Helsinki-Tallinn route on the Baltic Sea. The parties said that data processing would be performed using innovative artificial intelligence and machine learning software.
“A single sensor is never sufficient for providing complete safety-critical information to the crew. 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,” Dr. Sarang Thombre, Research Manager at Finnish Geospatial Research Institute, said.
The goal is to automatically identify and recognize objects, such as navigation aids and other vessels and boats around the ship and provide improved situational awareness information through sensor fusion.
“When such information is combined with established vessel navigation rules and regulations, it can potentially enable the vessel to navigate with minimal human guidance even in dense traffic conditions of the Baltic Sea,” Thombre added.
ESA’s overall objective is to improve European know-how in the field of autonomous transports and to study how European space-based positioning and navigation infrastructure, such as Galileo and EGNOS, can contribute to enhancing scientific innovation and consequently business opportunities in this field.