Driverless-vehicle options now include scooters

Researchers have developed an autonomous mobility scooter which 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.
November 9, 2016 Read time: 2 mins

Researchers have developed an autonomous mobility scooter which 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.

Developed by researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), the National University of Singapore and the Singapore-MIT Alliance for Research and Technology (SMART), the system includes several layers of 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. It also includes route-planning algorithms; localisation 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.

The researchers had previously used the same sensor configuration and software in trials of autonomous cars and golf carts, so the new trial completes the demonstration of a comprehensive autonomous mobility system.

Using the same control algorithms for all types of vehicles, scooters, golf carts, and city cars, has several advantages. One is that it becomes much more practical to perform reliable analyses of the system’s overall performance.

“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,” says Daniela Rus, of the 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.”

Software uniformity also means that the scheduling algorithm has more flexibility in its allocation of system resources.

“I can see its usefulness in large indoor shopping malls and amusement parks to take [mobility-impaired] people from one spot to another,” says Dan Ding, an associate professor of rehabilitation science and technology at the University of Pittsburgh, about the system.

The researchers described the design of the scooter system and the results of the trial in a paper they presented recently at the IEEE International Conference on Intelligent Transportation Systems in Rio de Janeiro, Brazil.

Location Based Systems

Related Content

  • September 8, 2015
    Hackers can fool self-driving car sensors into evasive action
    The laser ranging (LIDAR) systems that most self-driving cars rely on to sense obstacles can be hacked by a setup costing just US$60, a security researcher has told IEEE spectrum. According to Jonathan Petit, principal scientist at software security company Security Innovation, he can take echoes of a fake car, pedestrian or wall and put them in any location. Using such a system, which he designed using a low-power laser and pulse generator, attackers could trick a self-driving car into thinking somethin
    Read More
  • February 27, 2012
    No ifs or buts
    For twenty-some years I lived in Crawley in south-east England.
    Read More
  • March 14, 2012
    Automatic signal control to prevent emergency vehicle collisions?
    Field trials under way in Arizona promise eradication of accidents between emergency vehicles at intersections – as part of a national focus on ‘intelligent signal’ infrastructure. Collisions between police cars, ambulances and fire crews as they reach intersections at the same time, with equal priority given by all signals set on red, are as serious as they sound absurd. For emergency teams and those in need of their help, the consequences are dire. The solution could come from application of connected veh
    Read More
  • November 23, 2018
    Venkat Sumantran: ‘Smart cities are more hype than reality’
    For all the talk of smart cities, investment in systems lags significantly behind organic expansion in most places. Andrew Stone talks to Venkat Sumantran, who has been looking at how to create a coherent framework which could help authorities answer multiple mobility questions Two megatrends are posing unprecedented challenges to those trying to keep people moving around the world’s urban areas now - and in the years and decades to come. The first is rapid urbanisation. One in six of us lived in urban a
    Read More

Highlighted Content