Alexandre Bayen Leads Massive AI Traffic Experiment
An interdisciplinary team of industry and academic researchers led by Electrical Engineering and Computer Science Professor Alexandre Bayen has completed its most ambitious real-time traffic experiment to date. The project was led by the CIRCLES Consortium, an effort led by UC Berkeley and Vanderbilt University, involving collaborators from five universities and multiple government agencies. The experiment tested 100 partially automated vehicles in real traffic with the aim of improving overall traffic flow. Operating out of a massive control center designed to monitor one section of I-14 in Nashville, TN, the researchers used AI to build on existing adaptive cruise control systems to smooth phantom jams collaboratively. Their results show a positive energy impact. “Driving is very intuitive. If there’s a gap in front of you, you accelerate. If someone brakes, you slow down. But it turns out that this very normal reaction can lead to stop-and-go traffic and energy inefficiency,” said Prof. Bayen. “That’s precisely what AI technology is able to fix—it can direct the vehicle to things that are not intuitive to humans, but are overall more efficient.”
Massive traffic experiment pits machine learning against ‘phantom’ jams