MIT’s New Algorithm Aims to Curb Distracted Driving

The Massachusetts Institute of Technology (MIT) in partnership with the Age Lab and Touchstone Evaluation group have released a research paper on their new algorithm, AttenD, to better learn what factors distract drivers. While car fatalities within the US have experienced a decline over the past two decades, rates of distracted driving are soaring. The team at MIT aim to better understand the visual, audio, and contextual issues that divert drivers’ attention. 
Linda Angell, a former General Motors engineer now heading the Touchstone group wrote, “how can I keep the driver’s awareness of the situation high while they search for something to listen to on their new infotainment system? How can I structure this task in a way that their eyes are on the road, and give them frequent enough breaks, and cue them to look at the road once in a while?” This is accomplished by studying a driver’s glances using camera rigs and eye glance analyzing software, which are then processed by the AttenD algorithm. By examining the driver’s behavior 20 seconds prior to an accident, the AttenD software is capable of intelligently predicting future collisions. Journalist, Aarian Marshall, suggests that the technology may eventually be able to apply its predictive power to adapting to individual drivers.
This research has the potential to help inform policy makers and car manufacturers on how to decrease distractions and increase safety, which will be vital as self-driving cars are introduced into the mass market. Source:  Aarian Marshall, Wired


The contents of this website were developed under a grant from the National Institute on Disability, Independent Living, and Rehabilitation Research (NIDILRR grant number 90RE5025-01-00). NIDILRR is a Center within the Administration for Community Living (ACL), Department of Health and Human Services (HHS). The contents of this website do not necessarily represent the policy of NIDILRR, ACL, HHS, and you should not assume endorsement by the Federal Government.