Google and Rolls-Royce Partner on Autonomous Ships

Rolls-Royce has signed a deal with Google to develop Rolls-Royce’s intelligent awareness software, which is already in use on ships today and will play a central role in the company’s drive towards autonomous vessels. 

The agreement allows Rolls-Royce to use Google’s Cloud Machine Learning Engine to train Rolls-Royce’s artificial intelligence (AI)-based object classification system – a software suite intended to detect, identify and track surface objects. Rolls-Royce believes that its AI systems will make vessels safer and more efficient by automatically analyzing data from a range of new sensors, along with the ship’s own AIS and radar.

Karno Tenovuo, SVP for Ship Intelligence at Rolls-Royce, suggested that this system is already useful today. “While intelligent awareness systems will help to facilitate an autonomous future, they can benefit maritime businesses right now making vessels and their crews safer and more efficient,” he said. 

“Machine learning” is a set of algorithms, tools and techniques that mimic human learning to solve specific computing problems. Machine learning methods analyse existing data sets with the objective of “teaching” a software system to recognize patterns in training data, enhancing the system’s ability to make predictions based on new data. The bigger the data set, the more complex the patterns the model can recognize and the more accurate the predictions. 

The Google Cloud Machine Learning Engine uses the same neural net-based machine intelligence software that powers many of Google’s products, including image and voice search. Rolls-Royce will use Google Cloud’s software to create bespoke machine learning models which can interpret large and diverse marine data sets created by Rolls-Royce. As part of the machine learning process, the models’ predictions are evaluated in practical marine applications, allowing the models to be further refined.

In the longer term, Rolls-Royce and Google will also test whether speech recognition and computer-generated speech would be a workable solution for human-machine interfaces on board a vessel.