Roboat II from MIT can now carry passengers in Amsterdam waters
There have been several research, innovations and discussion on autonomous vehicles’ future on land and air. But what about autonomous vehicles in the water? A fully autonomous ship or underwater vehicle would be considered a vessel that can operate on its own without a crew. While Lloyd’s Register has defined seven levels of autonomy (from AL 0 to AL 6) transitioning from manned (AL 0), through the intermediate stages, to fully autonomous (AL 6), the technology is already being tested using machine learning. Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Senseable City Lab have collaborated to develop the world’s first fleet of autonomous boats for the City of Amsterdam, the Netherlands, for around five years. Apart from developing autonomous floating vessels for Amsterdam, it also investigates the potential of self-driving technology to change our cities and their waterways. Recently, they added a new, larger vessel to the group: “Roboat II.”
This boat weighs over 50 kg, 2 meters long, which is claimed as a “COVID-friendly” 6 feet and can carry two passengers. Alongside the MIT team worked with the Amsterdam Institute for Advanced Metropolitan Solutions to create navigation and control algorithms to update the communication and collaboration among the boats. Daniela Rus, a Professor at MIT, explains that Roboat II navigates autonomously using algorithms similar to those used by self-driving cars, but now adapted for the water. Daniela is also a senior author on a new paper about Roboat and the director of CSAIL. As per an official statement by CSAIL, 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. Alongside developing the next vehicle, the CSAIL and Senseable team are now exploring adaptive controllers for dynamic changes when goods and other objects are placed on a boat, and they also plan to extend their tests to water sources with more challenging conditions to navigate, such as strong currents and waves.
Roboat II autonomously navigated Amsterdam canals for three hours collecting data using Simultaneous Localization and Mapping (SLAM) algorithms and returned to its start location with an error margin of only 0.17 meters or fewer than 7 inches. According to the team, the algorithms map waterways and plot paths between a series of “goal points.” As water conditions can be disruptive, the use of goal points is “noisy” and may not be fully direct, but are a safer way to navigate. The boat utilizes four propellers to move down waterways and is equipped with state of the art LiDAR-inertial navigation system, LiDAR time-of-flight sensor, camera, that can enable autonomously move from point to point around the canals, and an inertial measurement unit (IMU).
In case a passenger pickup task is required from a user at a specific position, the system coordinator will assign the task to an unoccupied boat that’s closest to the passenger. After Roboat II picks up the passenger, it will create a feasible path to the desired destination based on the current traffic conditions.
The Roboat project commenced in 2016 with the vision of creating a series of floating platforms that could navigate waterways on their own, ferrying passengers and cargo around, monitoring the environment or connecting together to form temporary bridges or stages. In 2018, researchers designed low-cost, 3-D-printed, one-quarter scale versions of the boats, which were more efficient and agile, and came equipped with advanced trajectory-tracking algorithms. Last year, the robots were updated to “shapeshift” by autonomously disconnecting and reassembling into a variety of configurations. Carlo Ratti, Director of Senseable City Lab, suggests that a fleet of Roboats can be ordered to quickly assemble structures like bridges or floating platforms during a disaster situation or similar incident.
The advantage of autonomous floating vehicles is the elimination of human error, the reduction of crewing costs, the increase in the safety of life, and the efficient use of space in ship design and efficient use of fuel. A reduction of crew minimizes the personnel and additional costs (such as onboard provisions and insurance) on a voyage. Companies like Rolls-Royce Marine, Sea Machine Robotics, and Nippon Yusen are currently working on developing such autonomous vehicles (ships) for the future. Rolls-Royce has partnered with Intel (INTC) for an intelligence shipping platform, which uses AI and edge computing to manage navigation, obstacle detection, and communications. Last year, in December, it completed sea trials of an autonomous ferry in Finland.
“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,” says Senior postdoc Wei Wang, lead author on a paper about Roboat II. He wrote the paper alongside MIT Senseable City Lab postdoc Tixiao Shan, research fellow Pietro Leoni, postdoc David Fernandez-Gutierrez, research fellow Drew Meyers, and MIT professors Carlo Ratti and Daniela Rus. The work was supported by a grant from the Amsterdam Institute for Advanced Metropolitan Solutions in the Netherlands. A paper on Roboat II is said to be virtually presented at the International Conference on Intelligent Robots and Systems.
The post MIT Announces Roboat II with Advanced Improvements appeared first on Analytics Insight.
