Google has joined the revolutionary trend of developing autonomous ships by partnering with Rolls-Royce Marine. The two companies have agreed to develop intelligent awareness systems for vessels, which are thought to be essential for making autonomous ships a reality.
Rolls-Royce has signed a deal to use Google’s Cloud machine learning engine to further the artificial intelligence (AI)-based object classification system used for detecting, identifying and tracking the objects a vessel can encounter at sea.
This is part of Rolls-Royce’s drive to introduce the first commercial autonomous vessel, whether it is in offshore services, passenger shipping or cargo transport, by 2020, Rolls-Royce Marine senior vice president for concepts, innovation and digital systems, Oskar Levandar told Marine Propulsion at a recent conference in the UAE.
Google head of cloud sales in Scandinavia, Eva Fors said this agreement will bring greater machine learning power to the ship propulsion and automation group. “Rolls-Royce can combine the latest technology advancements with its deep knowledge of the maritime industry, ultimately bringing significant improvements to the sector,” she said.
Machine learning is a set of algorithms, tools and techniques that mimic human learning to solve specific problems. It can analyse existing data sets, recognises patterns and can make predictions from previously unseen data. It uses online machine intelligence software that analyses complex patterns to create more accurate predictions.
Rolls-Royce will use Google Cloud’s software to create bespoke machine learning models that can interpret large and diverse marine data sets created by itself. The terabytes data will be used to further develop the models. Predictions from these models will be evaluated in practical marine applications, allowing the models to be further refined.
Rolls-Royce senior vice president for ship intelligence Karno Tenovuo said intelligent awareness systems will help to drive forward an autonomous future. “This can benefit maritime businesses right now by making vessels and crews safer and more efficient,” he added.
In the longer term, Rolls-Royce and Google intend to jointly develop unsupervised and multimodal learning. They plan to test whether speech recognition and synthesis are viable solutions for human-machine interfaces in marine applications. They will also work on optimising the performance of local neural network computing on board ships using open source machine intelligence software libraries such as Google’s TensorFlow.
Intelligent awareness systems will make vessels safer, easier and more efficient to operate by providing crew with an enhanced understanding of their vessel’s surroundings. This will be achieved by fusing data from a range of sensors with information from existing ship systems, such as automatic identification system and radar.