Researchers from Massachusetts Institute of Technology’s (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) have created a driverless scooter, using new algorithms that they hope can be applied across different platforms in the future.

Working in coordination with the National University of Singapore and the Singapore-MIT Alliance for Research and Technology, the team from CSAIL created an autonomous mobility system that includes sensors and software from experiments that were conducted with other driverless systems.

The scooter also comes equipped with three layers of software for its new algorithms. There’s a low level of algorithms that helps a vehicle react to real world situations, in an effort to stay on its path and avoid accidents. There’s a layer that is responsible for the localization of algorithms, which helps with the creation of maps for navigation. The final layer is responsible for making the vehicle capable of operating as part of a fleet, and put it in a position where it can be shared with multiple users. 

According to New Atlas, the algorithms have been successfully tested for indoor and outdoor operation. Because the algorithms are new, they are better suited to provide reliable analysis of a system’s performance.

Researchers hope that the technology can be used for multiple platforms, in an effort to allow users to switch from one autonomous system to another based on the situation.

Video footage of the scooter in action can be seen here.

<< Back to the News