Maureen Kingsley

November 9, 2016

3 Min Read
How Driverless Scooters Could Boost Healthcare

Advanced software algorithms guide the autonomous vehicle, which could have applications in hospitals, retirement homes, and elsewhere.

Maureen Kingsley

MIT Driverless ScooterThe latest entry to the growing fleet of driverless vehicles is the autonomous mobility scooter, developed jointly by MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), the National University of Singapore, and the Singapore-MIT Alliance for Research and Technology (SMART).

Designed with the same sensor configuration and software used in SMART-developed autonomous cars and golf carts, this new driverless personal scooter "completes the demonstration of a comprehensive autonomous mobility system," according to Larry Hardesty of the MIT News Office. "A mobility-impaired user could, in principle, use a scooter to get down the hall and through the lobby of an apartment building, take a golf cart across the building's parking lot, and pick up an autonomous car on the public roads," he writes.

The successful trial runs of the scooter are significant in that they prove that the researchers' control algorithms work indoors as well as outside. "We were testing them in tighter spaces," says Scott Pendleton, a graduate student in mechanical engineering at the National University of Singapore and a research fellow at SMART, in MIT's news release. "One of the spaces that we tested in was the Infinite Corridor of MIT, which is a very difficult localization problem, being a long corridor without very many distinctive features. You can lose your place along the corridor. But our algorithms proved to work very well in this new environment."

The scooter--and other autonomous vehicles--could be life-changing for individuals whose mobility is impaired for reasons ranging from illness to injury to advanced age.

"We are very excited about the potential applications of self-driving scooters and self-driving wheelchairs in hospitals and retirement facilities. These systems will improve the operations efficiency and the quality of life of the residents," Daniela Rus, PhD,  an electrical engineering and computer science professor at MIT, tells Qmed. And, Rus added, "they will be fun to ride!"

The SMART vehicles, including the scooter, feature "several layers of expertly engineered software: low-level control algorithms that enable a vehicle to respond immediately to changes in its environment, such as a pedestrian darting across its path; route-planning algorithms; localization algorithms that the vehicle uses to determine its location on a map; map-building algorithms that it uses to construct the map in the first place; a scheduling algorithm that allocates fleet resources; and an online booking system that allows users to schedule rides," according to MIT.

Rus points out that using the same control algorithms for all types of driverless vehicles--including scooters, golf carts, and city cars--makes sense for a number of reasons. One is that performing reliable analyses of the system's overall performance is easier.

"If you have a uniform system where all the algorithms are the same, the complexity is much lower than if you have a heterogeneous system where each vehicle does something different," Rus says. "That's useful for verifying that this multilayer complexity is correct."

Additionally, software uniformity facilitates transferring information acquired by one vehicle to another. Before the mobility scooter was shipped to MIT from Singapore, for instance, it was tested in Singapore where it used maps that had been created by the autonomous golf cart.

The researchers detailed the design of the scooter system and its trial results in a paper they presented during the first week of November at the IEEE International Conference on Intelligent Transportation Systems

Maureen Kingsley is a contributor to Qmed. 

Like what you're reading? Subscribe to our daily e-newsletter.

[Image courtesy of the autonomous Vehicle Team of the SMART Future of Urban Mobility Project]

Sign up for the QMED & MD+DI Daily newsletter.

You May Also Like