MIT Algorithm Computes Oncoming Car's Possibility of Running Red Light

By

MIT researchers have developed an algorithm that can quickly compute in milliseconds the likelihood of a vehicle running a red light based on its rate of deceleration as it approaches the intersection. According to the Los Angeles Times, MIT professor of aeronautics and astronautics Jonathan How and three of his colleagues have come up with an algorithm that can predict whether an oncoming car is about to run a red light one or two seconds before a possible collision.

The LA Times report says that the algorithm is described in a paper that will be published in the journal IEEE Transactions on Intelligent Transportation Systems.

“That might not sound like a lot of time, but it could be enough to save a life,” according to How. As per the LA Times report, How and his team applied the algorithm to more than 15,000 vehicles at a busy intersection in Christianburg, Va., that was already outfitted with instruments that monitor vehicle speed and location as well as when the lights turned red. “They found that they were able to correctly predict who would run a red light 85 percent of the time,” wrote the LA Times.

According to the LA Times, that accuracy is the highest that has been computed so far. Interestingly, the researchers are now looking at the next logical step, how to avoid the accident. For that, MIT researchers are working on getting information about who is going to run a red light to other drivers on the road, so they can slow down and not drive into that intersection during that crucial time, wrote LA Times.

The LA Times quoted How, as saying, “that might be possible in smart cars of the future. If you had some type of heads-up display for the driver, it might be something where the algorithms are analyzing and saying, ‘We’re concerned.’”

In fact, “Even though your light might be green, it may recommend you not go, because there are people behaving badly that you may not be aware of,” noted How. However, How said that for such decisions, the cars must talk to each other and wirelessly trade information like speed and position data. In other words, there must be vehicle-to-vehicle (V2V) communications.

Both, according to the LA Times, the U.S. Department of Transportation and the Ford Motor Company are currently exploring V2V technologies.



Ashok Bindra is a veteran writer and editor with more than 25 years of editorial experience covering RF/wireless technologies, semiconductors and power electronics. To read more of his articles, please visit his columnist page.

Edited by Jennifer Russell

TechZone360 Contributor

SHARE THIS ARTICLE
Related Articles

Coding and Invention Made Fun

By: Special Guest    10/12/2018

SAM is a series of kits that integrates hardware and software with the Internet. Combining wireless building blocks composed of sensors and actors con…

Read More

Facebook Marketplace Now Leverages AI

By: Paula Bernier    10/3/2018

Artificial intelligence is changing the way businesses interact with customers. Facebook's announcement this week is just another example of how this …

Read More

Oct. 17 Webinar to Address Apache Spark Benefits, Tools

By: Paula Bernier    10/2/2018

In the upcoming webinar "Apache Spark: The New Enterprise Backbone for ETL, Batch and Real-time Streaming," industry experts will offer details on clo…

Read More

It's Black and White: Cybercriminals Are Spending 10x More Than Enterprises to Control, Disrupt and Steal

By: Cynthia S. Artin    9/26/2018

In a stunning new report by Carbon Black, "Hacking, Escalating Attacks and The Role of Threat Hunting" the company revealed that 92% of UK companies s…

Read More

6 Challenges of 5G, and the 9 Pillars of Assurance Strategy

By: Special Guest    9/17/2018

To make 5G possible, everything will change. The 5G network will involve new antennas and chipsets, new architectures, new KPIs, new vendors, cloud di…

Read More