New traffic light algorithm cuts travel time by more than 1/4

Bradley Wint
By: - 11th Nov 2013
email hidden; JavaScript is required

University of Toronto Engineering graduate Samah El-Tantawy has developed a new traffic light system that combines game theory and artificial intelligence to teach traffic lights to be more efficient based on real time changing conditions.

Rather than having the road-embedded sensors send data to a central management network, El-Tantawy’s system processes data on-spot at each traffic intersection, independent of all others. The sensors also monitor traffic coming from all directions rather than traffic that runs along a single roadway. This saves on response time (since the processing happens on spot) and nullifies the problem of city-wide breakdown should the traffic management center ever break down.

One of the biggest differences is that all the intersections in the neighbourhood still collaborate with each other in a “game”, but with the objective of “winning the game”, unlikely more traditional intersections which are more time-based. With on-site processing, each intersection’s traffic situation can be assessed and passed on to other intersections so that a more optimum flow of traffic is created.

“Each intersection engages in collaboration (or “game”, in game theory terminology) with all the adjacent intersections in its neighbourhood where each one not only learns the local optimal control policy but also considers the policies of its neighbours and acts accordingly,” said El-Tantawy. “In turn, neighbours coordinate with their further neighbours in a cascading network-wide fashion.

“In lay language, the agents act as a team of players cooperating to win a game—much like players in a soccer match, where each player endeavors to score, but at the same time considers the ultimate goal of the entire team which is winning the match.”

El-Tantawy’s system was tested at 60 downtown Toronto intersections at rush hour, resulting in a 40% reduction in delays and 26% reduction in travel times, and has garnered so much attention that many traffic light management companies have shown a serious interest in her product. Each traffic light system costs about CAD $20,000-40,000 to install.

She took first place in the best PhD dissertation competition from the Institute of Electrical and Electronics Engineers’ Intelligent Transportation Systems Society. El-Tantawy, who graduated from Univeristy of Toronto in 2012 with a PhD in civil engineering, also won second place from The Institute of Operations Research and Management Sciences’ George B. Dantzig Dissertation Award.

Hopefully we can see her system being utilizing in busier areas.

[Cover Photo: Wikimedia]

Get more awesome stories shipped directly to your inbox

Want a daily dose of awesome in your inbox? Sign up for our newsletter featuring fresh and popular content.