A Multiagent Approach to Autonomous Intersection Management

By Kurt M. Dresner, Peter Stone. Journal of Artificial Intelligence Research, 2008

1,340 citations recorded by the source corpus.

Artificial intelligence research is ushering in a new era of sophisticated, mass-market transportation technology. While computers can already fly a passenger jet better than a trained human pilot, people are still faced with the dangerous yet tedious task of driving automobiles. Intelligent Transportation Systems (ITS) is the field that focuses on integrating information technology with vehicles and transportation infrastructure to make transportation safer, cheaper, and more efficient. Recent advances in ITS point to a future in which vehicles themselves handle the vast majority of the driving task. Once autonomous vehicles become popular, autonomous interactions amongst multiple vehicles will be possible. Current methods of vehicle coordination, which are all designed to work with human drivers, will be outdated. The bottleneck for roadway efficiency will no longer be the drivers, but rather the mechanism by which those drivers' actions are coordinated. While open-road driving is a well-studied and more-or-less-solved problem, urban traffic scenarios, especially intersections, are much more challenging. We believe current methods for controlling traffic, specifically at intersections, will not be able to take advantage of the increased sensitivity and precision of autonomous vehicles as compared to human drivers. In this article, we suggest an alternative mechanism for coordinating the movement of autonomous vehicles through intersections. Drivers and intersections in this mechanism are treated as autonomous agents in a multiagent system. In this multiagent system, intersections use a new reservation-based approach built around a detailed communication protocol, which we also present. We demonstrate in simulation that our new mechanism has the potential to significantly outperform current intersection control technology--traffic lights and stop signs. Because our mechanism can emulate a traffic light or stop sign, it subsumes the most popular current methods of intersection control. This article also presents two extensions to the mechanism. The first extension allows the system to control human-driven vehicles in addition to autonomous vehicles. The second gives priority to emergency vehicles without significant cost to civilian vehicles. The mechanism, including both extensions, is implemented and tested in simulation, and we present experimental results that strongly attest to the efficacy of this approach.

Subfields: Automotive Engineering, Building and Construction, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/d8182c81f9e69c87ec7a181b3369dda3c2a2a939

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Building and Construction

In Control and Systems Engineering

Citations in the corpus

A Review of the Applications of Agent Technology in Traffic and Transportation Systems (2010, background): “Table II lists some of the agent applications in roadway transportation.”
A decentralized energy-optimal control framework for connected automated vehicles at signal-free intersections (2016, neutral): “Since then, numerous centralized approaches have been reported in the literature, e.g., de La Fortelle (2010); Dresner and Stone (2008); Huang et al. (2012), to achieve safe and eﬃcient control of traﬃc through intersections.”
Suboptimal Variants of the Conflict-Based Search Algorithm for the Multi-Agent Pathfinding Problem (2014, background): “MAPF has practical applications in video games, traffic control (Silver 2005; Dresner and Stone 2008), robotics (Bennewitz, Burgard, and Thrun 2002) and aviation (Pallottino et al.”
Policy and society related implications of automated driving: A review of literature and directions for future research (2017, background): “Similarly, Dresner and Stone (2008) proposed a multi-agent, reservation-based control system for efficient management of fully automated vehicles (level 4 or 5) in intersections that could widely outperform current control systems like traffic lights and stop signs.”
Agents, Bodies, Constraints, Dynamics, and Evolution (2009, background): “Consider the fact that cars could negotiate at intersections, the way Dresner and Stone (2008) have simulated to show you could get maybe two to three times the throughput in cities in terms of traffic if these cars could talk to each other instead of having to wait for dumb stop signs and traffic l”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, background): “In [526]– [528], they achieve the cooperative inter-section control by reservation schemes, in which each vehicle has to make a reservation from a centralized control infrastructure before passing through the intersection.”
Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control (2017, background): “monly studied cases where AVs are few enough to not affect the environment [3], [4], [5], such as the surrounding trafﬁc dynamics, or so many as to reduce the problem to primarily one of coordination [6], [7], [8]. For clarity, we refer to these as the isolated autonomy and full autonomy cases, resp”
Conflict-based search for optimal multi-agent pathfinding (2012, methodology): “Prominent examples include reducing to Boolean Satisﬁability (SAT) [50], Integer Linear Programming (ILP) [55] and Answer Set Programming (ASP) [13 These methods return the optimal solution and are usually designed for the makespan cost function .”
A Survey on the Coordination of Connected and Automated Vehicles at Intersections and Merging at Highway On-Ramps (2017, background): “Cell reservation process at time t (as proposed in [29]).”
A review on agent-based technology for traffic and transportation (2013, background): “In order to cope with these issues, in Dresner and Stone (2005, 2008), some of the previous assumptions were relaxed, especially the requirement that autonomous vehicles maintain a constant velocity in the intersection, and that they do not make turns.”
Development and Evaluation of a Cooperative Vehicle Intersection Control Algorithm Under the Connected Vehicles Environment (2012, methodology): “In addition, most of those studies, except for [8], were performed with only a few test vehicles, which are insufficient to cover varying traffic congestion cases.”
Automated and Cooperative Vehicle Merging at Highway On-Ramps (2017, neutral): “In this paper, we categorize an approach as centralized if there is at least one task in the system that is globally decided for all vehicles by a single central controller.”
Energy saving potentials of connected and automated vehicles (2018, background): “not needed anymore as shown in concept papers by [169], [170], [171].”
VANET security surveys (2014, background): “They are then able to suggest a detour route computation based on the information received [35].”
Infotainment and road safety service support in vehicular networking : From a communication perspective $ (2010, background): “A token-based intersection traffic management scheme is presented in [28], in which each vehicle waits for a token before entering an intersection.”
Platoons of connected vehicles can double throughput in urban roads (2015, background): “The papers of Dresner and Stone (2008); Huang et al. (2012); Jin et al. (2013) present simulations of control algorithms that coordinate the movement of connected and autonomous vehicles through an intersection with no traffic signals as such, but with a sophisticated “agent” who schedules the use…”