Icon Legend

This session is not in your schedule.

This session is in your schedule. Click again to remove it.

96 Views

ViewAttendees 1

Abstract for presentation (Poster or Podium)

Intelligent Transportation Systems

Multi-agent coordination framework for connected and automated vehicles - Case study in roundabouts

Monday, June 17, 2024

1:30 PM - 2:45 PM ET

Room: Galleria

Primary Author(s)

TS

Tom Shi, n/a

Assistant Professor
University of Wisconsin-Milwaukee
Milwaukee, Wisconsin, United States

Co-Author(s)

SH

Suzhou Huang, n/a

Senior Research Scientist
Institute for Physical Infrastructure and Transportation
Milwaukee, Wisconsin, United States

Submitter(s)

TS

Tom Shi

University of Wisconsin-Milwaukee
Milwaukee, Wisconsin, United States

Abstract: It is highly anticipated that connected and automated vehicles will drastically reduce traffic congestion and improve traffic flow. However, how this can happen exactly at a micro level is still scarcely addressed in the literature. In this paper we consider a smart multi-agent coordination framework at single-lane and double-lane roundabouts in simulated experiments. We show how we can leverage such a smart environment to coordinate the traffic flow using a game theory based algorithm. In contrast with an algorithm with only implicit coordination, we demonstrate that the average waiting time is always lower for the explicit coordination at any given incoming traffic flux. We further derive insights as to why the coordinated algorithm dominates over the non-coordinated algorithm.

Learning Objectives:

Attendees can expect to learn the following from this session:

learn the design consideration of a multi-agent coordination framework.
learn how the coordination framework can contribute to traffic congestion mitigation and safety enhancement.
learn how to solve the multi-agent planning problem in real-time.