Autonomous intersection management algorithms found in simulation to reduce delays at intersections by eight times compared to conventional traffic lights.

The paper proposes a new algorithm that takes advantage of the abilities of connected and automated vehicles to increase the effect even further.


Summary Information

The advent of autonomous vehicle technologies will enable the optimization of driving patterns to allow for travel that is faster and more efficient than ever. Of particular interest is the management of intersections, which have long been bottlenecks in traffic systems because of manually operated vehicles' inherent lack of coordination. Automated vehicles will be able to overcome barriers such as reaction time and lead to more efficient travel, lower collision rates, and overall lower congestion. However, the problem of intersection management is a complex one, relies on a number of different variables.

The authors of the paper performed a literature review of autonomous intersection management and proposed an original heuristic algorithm to maximize efficiency. They then used a traffic simulation to compare their algorithm with two others to gauge its effectiveness. The program used was the SUMO traffic simulator. The other selected algorithms were chosen to represent fundamentally different approaches to autonomous intersection management for the purpose of a robust comparison. The researchers also included a default scenario where only conventional traffic lights are used. The simulation tracked an intersection over the course of one hour at varying traffic density values, and compared the average delay for each of the four algorithms.

It is worth noting that the researchers did not include a statistical analysis of the significance of their results; however, based on their results several broad relationships emerge.


The paper's proposed algorithm outperformed all other examined systems over all tested traffic densities. Its average delay in seconds, across all densities, was never higher than .4 seconds, while the two other examined algorithms were generally between four and eight times less efficient, with average delays ranging up to four seconds.

Notably, all three "intelligent" algorithms significantly outperformed the default scenario of a conventional traffic light. The average delay of the tested systems (at approximately 1-5 seconds, depending on density) was typically at least eight times smaller than that of the traffic light (at approximately 15-30 seconds).

Thus, while the researchers' proposed algorithm is notably more effective than the other CAV-informed intersection management systems, it is apparent that all three represented a significant step up in effectiveness compared to its current state.

Benefit Comments

No comments posted to date

Comment on this Benefit

To comment on this summary, fill in the information below and click on submit. An asterisk (*) indicates a required field. Your name and email address, if provided, will not be posted, but are to contact you, if needed to clarify your comments.


Autonomous Intersection Management: A Heuristic Approach

Author: Chouhan and Banda

Published By: IEEE

Source Date: 10/1/2016



Average User Rating

0 ( ratings)

Rate this Benefit

(click stars to rate)

Goal Areas


Typical Deployment Locations

Metropolitan Areas


None defined

Benefit ID: 2018-01328