Eco-Driving of Connected and Autonomous Vehicles Approaching and Departing Signalized Intersections

Autonomous vehicles (AVs) commonly known as self-driving vehicles have captured the attention of the public for decades and continue to be the center of attention of academic and industrial research activities worldwide. Their proliferation has rapidly grown, largely as a result of Vehicleto- X (or V2X) technology which refers to an intelligent transportation system where all vehicles and infrastructure components are interconnected with each other. Therefore, the term “CAV”, which is short for connected and autonomous vehicles, was coined. The connected here not only refers to the connections to infrastructures, such as traffic signals and GPS information, but also includes the communication among vehicles in the same vicinity. Connected and autonomous vehicles (CAVs) will have a profound impact on various aspects of urban mobility, such as safety, energy usage, and environmental sustainability, which are considered as the driving change for smart cities. The CAV technology provides an intriguing opportunity to better monitor transportation network conditions, which in turn helps optimize traffic flows, enhance safety, reduce congestion, and minimize emissions. Recent developments in artificial intelligence would make this once science fiction-sounding idea into reality. This project is going to address the safety and energy efficiency issues of CAVs approaching and departing multiple signalized intersections. The alarming state of existing transportation systems has been well documented from various aspects. From the safety perspective, an estimated 165000 accidents occur annually in intersections caused by red light runners, where about 800-1000 cases are fatal. From the energy perspective, for instance, in 2014, congestion caused vehicles in urban areas to spend 6.9 billion additional hours on the road at a cost of an extra 3.1 billion gallons of fuel, resulting in a total cost estimated at $160 billion. The novelty of the proposal lies in establishing a framework by combining emerging Artificial Intelligent (AI) technologies and traditional control and optimization approaches to deal with existing challenges of trajectory planning of CAVs approaching and departing signalized intersections. The first question that this project addresses is the traffic signal phase detection. Traffic signal phase detection and recognition is an important application for AVs aiding and providing information about decision making on intersections. Second, we will develop an energy efficient and safe algorithm for CAVs to approach and depart signalized intersections based on identified traffic phase information. Next, we will extend this framework to the mixed traffic case of CAVs and human-driven vehicles (HDVs). This analysis will be carried out using machine learning and reinforcement learning approaches based on collected data in a simulation environment. Developed algorithms and results will be extensively tested through software simulation, such as MATLAB, and SUMO. In addition, robotic cars will be used for the hardware testing. The research results developed in this project will be disseminated in conferences to academia and industry. They will also be incorporated into existing courses (EE 3530 Introduction to Control Engineering; EE 7500 Distributed Control of Multi-Agent System; EE 7560 Optimal Control and Reinforcement Learning) offered by the Division of Electrical and Computer Engineering, Louisiana State University. Graduate students and undergraduate students will be involved with project all the time. Opportunities will be created especially for underrepresented students to work the project. We will organize seminars to introduce the new technology to local community, including high school teachers and local industrial companies for possible commercialization.

• Supplemental Notes:
  • 22ITSLSU41

Language

• English

Project

• Status: Active
• Funding: $120000
• Contract Numbers:

  69A3551747106

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Transportation Consortium of South-Central States (Tran-SET)

  Louisiana State University
  Baton Rouge, LA  United States  70803
• Project Managers:

  Mousa, Momen

• Performing Organizations:

  Louisiana State University, Baton Rouge

  P.O. Box 94245, Capitol Station
  Baton Rouge, LA  United States  70803
• Principal Investigators:

  Meng, Xiangyu

• Start Date: 20220401
• Expected Completion Date: 0
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Artificial intelligence; Autonomous vehicles; Connected vehicles; Ecodriving; Signalized intersections; Traffic safety; Trajectory control
• Subject Areas: Highways; Operations and Traffic Management; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01844793
• Record Type: Research project
• Source Agency: Transportation Consortium of South-Central States (Tran-SET)
• Contract Numbers: 69A3551747106
• Files: UTC, RIP
• Created Date: May 6 2022 3:40PM