Skip to main content
  1. Home
  2. News

MIT’s autonomous boat takes on Amsterdam’s vast canal network

Trevor Mogg
By

If you’re going to test an autonomous boat then there’s surely no better place to do it than on Amsterdam’s vast network of canals.

Recommended Videos

MIT’s Computer Science and Artificial Intelligence Laboratory and Senseable City Lab have been developing an autonomous boat for the last five years with a view to one day using the vessel to transport people, ship goods, or clean up waterways in urban areas.

Related

The second version of “Roboat” is two meters long, has four propellers, and, just like autonomous cars that tend to grab all the headlines when it comes to self-driving technology, operates using a suite of sensors and powerful software to help ensure safe travel.

The Massachusetts Institute of Technology research team recently conducted a successful test of Roboat on the canals of Amsterdam, navigating the narrow waterways for three hours with an impressive error margin of just 7 inches (17.8cm). You can see it in action in the video at the top.

The updated Roboat is actually designed to travel as part of a fleet, and so some of the team’s work has been focusing on updating navigation and control algorithms to improve communication and collaboration between the boats, according to MIT News.

Interestingly, Carlo Ratti, director of Senseable City Lab, has suggested a fleet of Roboats could be ordered to quickly assemble structures such as bridges or floating platforms in the case of a disaster situation or some such incident.

At the current time, the team is particularly interested in creating a Roboat specifically for carrying human passengers, so the third version, which is under construction, will be four meters long with enough space to carry up to six passengers.

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

Companies have also been working on autonomous vessels at the other end of the size scale, with Rolls-Royce Marine and Japanese shipping giant Nippon Yusen both developing enormous driverless cargo ships.

Editors' Recommendations

Topics
Trevor Mogg
Trevor Mogg
Contributing Editor
Not so many moons ago, Trevor moved from one tea-loving island nation that drives on the left (Britain) to another (Japan)…
Setback for GM’s autonomous car unit as it delays launch of robo-taxi service
Cruise

General Motors’ autonomous car unit has made much of its plan to launch a robo-taxi service by the end of 2019, but on Wednesday, July 24, it said it could no longer meet that deadline.

Cruise Automation CEO Dan Ammann explained in a blog post that the company has decided it wants to conduct further road tests of its autonomous technology — built into Chevrolet Bolt EVs — before launching a large-scale robo-taxi service “beyond the end of the year.”

Read more
How Intel and Microsoft are teaming up to take on Apple
An Intel Meteor Lake system-on-a-chip.

It seems like Apple might need to watch out, because Intel and Microsoft are coming for it after the latter two companies reportedly forged a close partnership during the development of Intel Lunar Lake chips. Lunar Lake refers to Intel's upcoming generation of mobile processors that are aimed specifically at the thin and light segment. While the specs are said to be fairly modest, some signs hint that Lunar Lake may have enough of an advantage to pose a threat to some of the best processors.

Today's round of Intel Lunar Lake leaks comes from Igor's Lab. The system-on-a-chip (SoC), pictured above, is Intel's low-power solution made for thin laptops that's said to be coming out later this year. Curiously, the chips weren't manufactured on Intel's own process, but on TSMC's N3B node. This is an interesting development because Intel typically sticks to its own fabs, and it even plans to sell its manufacturing services to rivals like AMD. This time, however, Intel opted for the N3B node for its compute tile.

Read more
How much does an AI supercomputer cost? Try $100 billion
A Microsoft datacenter.

It looks like OpenAI's ChatGPT and Sora, among other projects, are about to get a lot more juice. According to a new report shared by The Information, Microsoft and OpenAI are working on a new data center project, one part of which will be a massive AI supercomputer dubbed "Stargate." Microsoft is said to be footing the bill, and the cost is astronomical as the name of the supercomputer suggests -- the whole project might cost over $100 billion.

Spending over $100 billion on anything is mind-blowing, but when put into perspective, the price truly shows just how big a venture this might be: The Information claims that the new Microsoft and OpenAI joint project might cost a whopping 100 times more than some of the largest data centers currently in operation.

Read more