Over the years, autonomous vehicles have gained more and more evidence. But transportation is not just about cars, so MIT has already started to think about different forms of self-driving transportation.
Over the past five years, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Senseable City Lab have been working on the world’s first fleet of autonomous boats to deploy in the City of Amsterdam, the Netherlands. Last year, we saw autonomous floating vessels (Roboat), capable of assembling themselves into a series of floating structures for various uses, and now CSAIL has added a new, larger vessel to the group: “Roboat II.” Sitting at 2 meters long, the new robotic boat is capable of carrying passengers.
Roboat II, which weighs more than 50 kilograms, has four propellers that allow it to move in any direction. It also includes LiDAR, GPS, and inertial sensors to help you navigate. 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,” says MIT Professor Daniela Rus, a senior author on a new paper about Roboat and the director of CSAIL. “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.”
Although an individual boat looks small, they are modular like the original Roboat. That is, they can self-assemble into a larger vessel commanded by a main “leader boat”. MIT considered the original Roboat to be a “quarter scale” option, while Roboat II is a half-scale; they’re slowly working up to the point of a full-scale option that is 4 meters long and aims to carry anywhere from four to six passengers. This larger version is already under construction in Amsterdam, but there is still no date for testing.
Meanwhile, the Roboat II already navigates effectively around Amsterdam. According to MIT, it autonomously navigated the canals of Amsterdam for three hours collecting data and returned back to its start location with an error margin of only 0.17 meters, or fewer than 7 inches.
In the future, the MIT team hopes to continue to refine Roboat’s algorithms to make it more capable of handling the challenges that a boat may encounter, like disturbances from currents and waves. They are also working to make it more capable of identifying and understanding objects it comes across in order to better deal with the environment it is in. Everything Roboat II learns will be applied to the full-scale version that is under construction, although it is just imagination for now.