Production Line Technique for Autonomous Vehicle Scheduling

TL;DR

This paper introduces a production line-based scheduling system for autonomous vehicles at intersections, aiming to eliminate collisions and reduce waiting times, especially under unpredictable traffic flows, using predictive algorithms.

Contribution

It proposes a novel production line technique for autonomous vehicle scheduling that improves safety and efficiency over existing models like AIM.

Findings

No collisions observed in experiments

Reduces waiting time in unpredictable traffic

Requires more lane space

Abstract

This paper considers the problem of scheduling autonomous vehicles in intersections. A new system is proposed that could be an additional choice to the recently introduced Autonomous Intersection Management (AIM) model. The proposed system is based on the production line technique, where the environment of the intersection, vehicles position, speeds and turning are specified and determined in advance. The goal of the proposed system is to eliminate vehicle collision and the waiting time inside the intersection. Three different patterns of the vehicles flow toward the intersection have been considered for the evaluation of the model. The system requires less waiting time (compared to the other models) in the random case where the flow is unpredictable. The KNN algorithm is used to predict the right turn vehicle. The experimental results show that there is no single chance of collision inside the intersection, however, the system requires more free space in the traffic lane.