Robot boats from MIT can now carry passengers

The latest “Roboat” is an autonomous vehicle that’s about six feet long and is being tested for use in Amsterdam.


The Roboat II is an autonomous robotic boat that navigates via artificial intelligence. 

Image: MIT

Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Senseable City Lab have recently added a new, larger autonomous vessel to the fleet it has been working on for the city of Amsterdam. Dubbed “Roboat II,” the latest robotic boat is now capable of carrying passengers and is the equivalent of roughly a “COVID-friendly” six feet, CSAIL said.

SEE: Special feature: Autonomous vehicles and the enterprise (free PDF) (TechRepublic)

The team has been working to develop the world’s first fleet of autonomous boats in a five-year project. In tandem with the Amsterdam Institute for Advanced Metropolitan Solutions, the team also created navigation and control algorithms to update the communication and collaboration among the boats. 

“Roboat II navigates autonomously using algorithms similar to those used by self-driving cars, but now adapted for water,” said MIT Professor Daniela Rus, the director of CSAIL, in a statement. “We’re developing fleets of Roboats that can deliver people and goods and connect with other Roboats to form a range of autonomous platforms to enable water activities.” 

Self-driving boats have been able to transport small items for years but adding human passengers has not been practical because of the size of the vessels, CSAIL said. Roboat II is the “half-scale” boat in the growing fleet, and joins the previously developed quarter-scale Roboat, which is one meter long. The third installment, which is under construction in Amsterdam and is considered to be “full scale,” is four meters long and aims to carry anywhere from four to six passengers, CSAIL said. 

In tests, Roboat II used algorithms to autonomously navigate the canals of Amsterdam for three hours collecting data and returned back to its start location with an error margin of fewer than seven inches, according to CSAIL. 

SEE: IBM launches autonomous ship with a trans-Atlantic crossing scheduled in 2021 (TechRepublic)

“The development of an autonomous boat system capable of accurate mapping, robust control, and human transport is a crucial step toward having the system implemented in the full-scale Roboat,” said senior postdoc Wei Wang, the lead author of a new paper about Roboat II, in a statement. “We also hope it will eventually be implemented in other boats in order to make them autonomous.”

There is no direct communication among the connected robots—only one leader knows their destinations, CSAIL said. The leader initiates movement to the destination, and then the other robots can estimate the leader’s intention and align their movements accordingly. 

SEE: AI on the high seas: Digital transformation is revolutionizing global shipping (TechRepublic)

The algorithms currently being used do not consider dynamic systems on the water, such as inertia and vehicle load, which make the system harder to control, said Carlo Ratti, director of the Senseable City Lab, in a statement.  

Looking ahead, the team plans to use machine learning to estimate the key parameters of the robots, CSAIL said. Another goal is to explore adaptive controllers that allow for dynamic change to the structure when objects are placed on the boat. Eventually, the boats will be moved to outdoor water environments, where real-world disturbances such as currents and waves exist.