Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Roadside Unit for Infrastructure Assisted Intersection Control of Autonomous Vehicles

Michael Evans, Marcial Machado, Rickey Johnson, Anna Vadella, Luis Escamilla, Beñat Froemming-Aldanondo, Tatiana Rastoskueva, Milan Jostes, Devson Butani, Ryan Kaddis, Chan-Jin Chung, Joshua Siegel

TL;DR

Addressing safety and fuel-efficiency at intersections for autonomous vehicles, the paper proposes an infrastructure-assisted control framework using a low-cost RSU to enable V2I communication and adaptive speed control. The method combines GazelleSim-based virtual testing with a real-world two-vehicle testbed, implemented in a modular ROS architecture and backed by a cost-conscious hardware setup. The key contributions include a waypoint-driven adaptive speed algorithm, a three-tier software/hardware architecture, and a teaching deployment model with about $200 hardware cost, showing up to $75.35\%$ reductions in acceleration/braking through intersections. The results indicate meaningful safety and energy benefits and provide a scalable platform for further research toward connected-infrastructure intersection control in intelligent cities.

Abstract

Recent advances in autonomous vehicle technologies and cellular network speeds motivate developments in vehicle-to-everything (V2X) communications. Enhanced road safety features and improved fuel efficiency are some of the motivations behind V2X for future transportation systems. Adaptive intersection control systems have considerable potential to achieve these goals by minimizing idle times and predicting short-term future traffic conditions. Integrating V2X into traffic management systems introduces the infrastructure necessary to make roads safer for all users and initiates the shift towards more intelligent and connected cities. To demonstrate our control algorithm, we implement both a simulated and real-world representation of a 4-way intersection and crosswalk scenario with 2 self-driving electric vehicles, a roadside unit (RSU), and a traffic light. Our architecture reduces acceleration and braking through intersections by up to 75.35%, which has been shown to minimize fuel consumption in gas vehicles. We propose a cost-effective solution to intelligent and connected intersection control to serve as a proof-of-concept model suitable as the basis for continued research and development. Code for this project is available at https://github.com/MMachado05/REU-2024.

A Roadside Unit for Infrastructure Assisted Intersection Control of Autonomous Vehicles

TL;DR

Addressing safety and fuel-efficiency at intersections for autonomous vehicles, the paper proposes an infrastructure-assisted control framework using a low-cost RSU to enable V2I communication and adaptive speed control. The method combines GazelleSim-based virtual testing with a real-world two-vehicle testbed, implemented in a modular ROS architecture and backed by a cost-conscious hardware setup. The key contributions include a waypoint-driven adaptive speed algorithm, a three-tier software/hardware architecture, and a teaching deployment model with about 75.35\%$ reductions in acceleration/braking through intersections. The results indicate meaningful safety and energy benefits and provide a scalable platform for further research toward connected-infrastructure intersection control in intelligent cities.

Abstract

Recent advances in autonomous vehicle technologies and cellular network speeds motivate developments in vehicle-to-everything (V2X) communications. Enhanced road safety features and improved fuel efficiency are some of the motivations behind V2X for future transportation systems. Adaptive intersection control systems have considerable potential to achieve these goals by minimizing idle times and predicting short-term future traffic conditions. Integrating V2X into traffic management systems introduces the infrastructure necessary to make roads safer for all users and initiates the shift towards more intelligent and connected cities. To demonstrate our control algorithm, we implement both a simulated and real-world representation of a 4-way intersection and crosswalk scenario with 2 self-driving electric vehicles, a roadside unit (RSU), and a traffic light. Our architecture reduces acceleration and braking through intersections by up to 75.35%, which has been shown to minimize fuel consumption in gas vehicles. We propose a cost-effective solution to intelligent and connected intersection control to serve as a proof-of-concept model suitable as the basis for continued research and development. Code for this project is available at https://github.com/MMachado05/REU-2024.
Paper Structure (13 sections, 5 equations, 4 figures, 1 table)

This paper contains 13 sections, 5 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Review of Literature
  3. System Design and Methods
  4. Gazelle Simulation
  5. Software Architecture
  6. RSU Hardware and Traffic Light Visualization
  7. Adaptive Speed Control
  8. Cost-Effectiveness and Scalability
  9. Experiment and Results
  10. Experimental Setup
  11. Performance Analysis
  12. Conclusion and Future Work
  13. Acknowledgment

Figures (4)

  • Figure 1: Image of the Polaris GEM e2 "ACTor 1" vehicle.
  • Figure 2: Map of the Lot H test course in GazelleSim.
  • Figure 3: Acceleration vs time comparison of a human driver against our adaptive speed algorithms during 3 different light state configurations. The highlighted region is from 35s to 65s and captures the vehicle crossing the intersection.
  • Figure 4: Velocity vs time comparison of all driving methods against 3 light state configurations.