MIT Develops Autonomous 3D-printed Boats to Reduce Traffic in Water-way Rich Cities

Waterway-rich cities may soon see their traffic reduced by the introduction of autonomous multi-purpose boats. Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Senseable City Lab in the Department of Urban Studies and Planning (DUSP) have designed a fleet of low-cost 3D printed self-driving boats that could be used to ferry people and goods, carry out city services at night and even assemble themselves into various structures. 

“Imagine shifting some of infrastructure services that usually take place during the day on the road — deliveries, garbage management, waste management — to the middle of the night, on the water, using a fleet of autonomous boats,” said CSAIL Director Daniela Rus and a co-author on the new boats’ paper presented at the IEEE International Conference on Robotics and Automation (ICRA). 

Self-assembly features included 

More impressively, these 4-by-2-meter boats would be equipped with hardware enabling them to self-assemble into a variety of structures in just a few hours such as floating bridges or entertainment platforms. The boats would also have the potential to monitor the waters they navigate through environmental detectors. 

[see-also]

The boats were created on a 16 piece rectangular hull 3D-printed in about 60 hours and sealed with fiberglass. The hull is equipped with features such as power supply, Wi-Fi antenna, indoor ultrasound beacon system, outdoor real-time kinematic GPS modules and an inertial measurement unit (IMU) module. 

The boat’s rectangular shape means it can move sideways and attach to other boats for a useful creation of other structures. The boat can also track its position swiftly and accurately through a nonlinear model predictive control (NMPC) algorithm so efficiently that it takes less than 1 millisecond to function.

An efficient control algorithm

The team tested the control algorithm’s efficacy using a smaller prototype of the boat in a swimming pool and in the Charles River. Through 10 test runs, the researchers found less tracking errors than in traditional control algorithms due to the algorithm being implemented in a controller computer regulating each thruster individually every 0.2 seconds. 

“The controller considers the boat dynamics, current state of the boat, thrust constraints, and a reference position for the coming several seconds, to optimize how the boat drives on the path,”  first author of the paper Wei Wang, a joint postdoc in CSAIL and the Senseable City Lab said. “We can then find optimal force for the thrusters that can take the boat back to the path and minimize errors.” 

The researchers are now working on adaptive controllers suitable to conditions for the transportation of people and cargo as well as for wave disturbances and stronger currents. “We actually found that the Charles River has much more current than in the canals in Amsterdam,” Wang added. “But there will be a lot of boats moving around, and big boats will bring big currents, so we still have to consider this.”