Communications of the ACM
Seeking Ways to Reduce Traffic Jams, USC Engineers Turn to AI
University of Southern California researchers have added a new type of artificial intelligence to speed-forecasting technology in an effort to provide drivers predictive information for the fastest commute in every possible way.
Credit: Myriam Thyes
Researchers at the University of Southern California's Viterbi School of Engineering are adding a new type of artificial intelligence to speed-forecasting technology in an effort to reduce the amount of congestion on America's roads.
They say the new technology should give drivers predictive information for the fastest commute in every possible way, improving on other state-of-the-art technologies by up to 15%.
The new system pulls from both historical and real-time data to process and predict future speeds along a road, boosting accuracy by learning which methods predict the most accurate speeds.
The model also helps to improve the driving ability of autonomous vehicles, synthesizing information that sends self-driving cars the answers to various questions related to driving. This enables the vehicle to exhibit an "anticipation" characteristic, similar to a human driver.
From USC News
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found