+1-518-621-2074 | US-Canada Toll Free Contact Us

Researchers Quantify Impact of Autonomous Vehicles on Traffic

about us

Published on : Apr 05, 2019

In a report it was found that concurrence between autonomous and conventional vehicle will impact the outcomes autonomous driving. The report was published by UWICORE Laboratory at department of communications engineering and I3E Engineering and Research Center of Miguel Hernandez University (UMH) of Elche. The study shows benefits pertaining to free flow of traffic will not surface unless at least 15% vehicles are autonomous. Also, capabilities of motorways will not offer the desired potential, unless solutions are developed to assure efficient concurrence of autonomous and conventional vehicles.

Future vehicles will be safer and efficient and will be driven by a better medium of connectivity and automation. -Javier González, Director, UWICORE laboratory.

Various other studies in the past also showed that autonomous driving can enhance capabilities of the road while reducing fuel consumption. However, according to UMHs recent research the lack of efficient solution will produce moderate results.


How Potential of Autonomous Driving can be Improved?

The study shows that dedicated solutions can enable an efficient and safe coexistence of both types of vehicles. With the solution available and increased number of autonomous vehicles, efficiency on the roads can noticeably improve up to 40% for traffic intensity. Currently, researchers are measuring the featured appearance of autonomous vehicles. They are doing so by implementing V2X wireless communications among vehicles. This will allow vehicles to exchange information about their maneuvering to coordinate with the vehicles around them.

The research has been conducted under PREDICT (Predictions and Characterization of traffic with data from connected vehicles and autonomous vehicles) project. Which is funded by Directorate General of Traffic. Under the same project, UMH has also developed artificial Intelligence solutions based on deep neural networks. This is to optimize the traffic predictions which use data from stationary sensors and connected vehicles.