Researchers at MIT and the National University of Singapore have gone in another direction, bringing their driverless vehicle technology to sidewalks and indoors with the development of an autonomous scooter.
The scooter uses the same sensor configuration and control software as was used in trials of the study’s autonomous cars and golf carts, demonstrating that the researchers’ control algorithms are able to work both indoors and out.
The system includes several layers of software:
- Low-level control algorithms enable the vehicle to respond immediately to changes in its environment;
- Route-planning algorithms;
- Localization algorithms that the vehicle uses to determine its location on a map;
- Map-building algorithms;
- A scheduling algorithm that allocates fleet resources and;
- An online booking system that allows users to schedule rides.
By using the same control software across the different types of vehicles, the researchers were able to keep an updated analysis of vehicle performance, transfer information and maps between vehicles and connect different vehicles together as part of the same route. If a car is unable to make the last leg of a journey, from the parking lot to the front door for example, the researcher’s system can assign a different, more appropriate vehicle.
“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,” said Daniela Rus, professor of electrical engineering and computer science at MIT and one of the project’s leaders. “That’s useful for verifying that this multilayer complexity is correct.”
“Similarly,” added Marcelo Ang, an associate professor of mechanical engineering at NUS who co-leads the project with Rus, “Once you have a better driver, you can easily transplant that to another vehicle that’s the same across different platforms.
While the scooter in particular could be a benefit to those with mobility-impairments, the whole system working in tandem could automate an entire journey. A 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 road.
“I can see its usefulness in large indoor shopping malls and amusement parks to take people from one spot to another,” said Dan Ding, an associate professor of rehabilitation science and technology at the University of Pittsburgh.
While not everyone is thrilled at the idea of their vehicles becoming autonomous, in a survey that accompanied the scooter’s trial, users scored the scooter’s safety as considerably higher after taking it for a test drive.
Perhaps with more hands-on time with autonomous vehicles, apprehension regarding the systems will take a similar turn towards confidence.
For more information on autonomous vehicles, check out these three features.