Connection-Based Scheduling for Real-Time Intersection Control

TL;DR

This paper presents a real-time heuristic scheduling algorithm for traffic signals at intersections, reducing congestion by estimating vehicle arrivals and optimizing signal timing with A* search, outperforming previous methods in speed and effectiveness.

Contribution

It introduces a lane-based model and an A*-based heuristic approach for real-time intersection scheduling, demonstrating improved performance over prior methods.

Findings

Outperforms previous A*-based approaches in run-time efficiency.

Generates intersection schedules in real-time, every second.

Proven effective in both simulations and real-world tests.

Abstract

We introduce a heuristic scheduling algorithm for real-time adaptive traffic signal control to reduce traffic congestion. This algorithm adopts a lane-based model that estimates the arrival time of all vehicles approaching an intersection through different lanes, and then computes a schedule (i.e., a signal timing plan) that minimizes the cumulative delay incurred by all approaching vehicles. State space, pruning checks and an admissible heuristic for A* search are described and shown to be capable of generating an intersection schedule in real-time (i.e., every second). Due to the effectiveness of the heuristics, the proposed approach outperforms a less expressive Dynamic Programming approach and previous A*-based approaches in run-time performance, both in simulated test environments and actual field tests.