Are autonomous vehicles better off without signals at intersections? A comparative computational study

Lu, Gongyuan; Shen, Zili; Liu, Xiaobo; Nie, Yu; Xiong, Zhiqiang

doi:10.1016/j.trb.2021.10.012

Cited by 30 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Longest-Queue-First (LQF) always allows the vehicles in the direction with longest queue to cross the intersection first, which originated as a pressure-based signal control [10] and was transferred to AIM with V2I communication [11]. Besides, some researches shows that the rotating through intersections enables near-optimal scheduling [12]. Rhythm controls sets rhythms for vehicular movements in each direction to stagger through the intersection seamlessly [13].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

D-HAL: Distributed Hierarchical Adversarial Learning for Multi-Agent Interaction in Autonomous Intersection Management

Li¹,

Wu²,

He³

2023

Preprint

View full text Add to dashboard Cite

Autonomous Intersection Management (AIM) provides a signal-free intersection scheduling paradigm for Connected Autonomous Vehicles (CAVs). Distributed learning method has emerged as an attractive branch of AIM research. Compared with centralized AIM, distributed AIM can be deployed to CAVs at a lower cost, and compared with rule-based and optimization-based method, learningbased method can treat various complicated real-time intersection scenarios more flexibly. Deep reinforcement learning (DRL) is the mainstream approach in distributed learning to address AIM problems. However, the large-scale simultaneous interactive decision of multiple agents and the rapid changes of environment caused by interactions pose challenges for DRL, making its reward curve oscillating and hard to converge, and ultimately leading to a compromise in safety and computing efficiency. For this, we propose a non-RL learning framework, called Distributed Hierarchical Adversarial Learning (D-HAL). The framework includes an actor network that generates the actions of each CAV at each step. The immediate discriminator evaluates the interaction performance of the actor network at the current step, while the final discriminator makes the final evaluation of the overall trajectory from a series of interactions. In this framework, the long-term outcome of the behavior no longer motivates the actor network in terms of discounted rewards, but rather through a designed adversarial loss function with discriminative labels. The proposed model is evaluated at a four-way-six-lane intersection, and outperforms several state-of-the-art methods on ensuring safety and reducing travel time.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…Rhythm controls sets rhythms for vehicular movements in each direction to stagger through the intersection seamlessly [13]. The rule-based approach performs well in simple scenarios, but the hard-coded rules not necessarily lead to optimal solutions in some complex scenarios [12].…”

Section: Literature Reviewmentioning

confidence: 99%

D-HAL: Distributed Hierarchical Adversarial Learning for Multi-Agent Interaction in Autonomous Intersection Management

Li¹,

Wu²,

He³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…AIM refers to the control strategy that the function of physical traffic signals in resolving conflicts is replaced by smart vehicles, such as CAVs, that are able to communicate with and follow the guidelines of infrastructures (Chen et al , 2020; Guillen-Perez and Cano, 2022; Lee and Park, 2012; Lu et al , 2022; Olovsson et al , 2022). For this topic, we present two prevailing streams of research: reservation-based strategy; optimization-based strategy.…”

Section: Joint Intersection and Connected And Automated Vehicle Controlmentioning

confidence: 99%

Intersection control with connected and automated vehicles: a review

2022

JICV

View full text Add to dashboard Cite

Purpose This paper aims to review the studies on intersection control with connected and automated vehicles (CAVs). Design/methodology/approach The most seminal and recent research in this area is reviewed. This study specifically focuses on two categories: CAV trajectory planning and joint intersection and CAV control. Findings It is found that there is a lack of widely recognized benchmarks in this area, which hinders the validation and demonstration of new studies. Originality/value In this review, the authors focus on the methodological approaches taken to empower intersection control with CAVs. The authors hope the present review could shed light on the state-of-the-art methods, research gaps and future research directions.

show abstract

“…A major challenge for answering the above question is the lack of appropriate model to quantitatively map the attacker's and the SO's behavior to the intersection's performance. So far, the majority of previous work on signal-free intersections is based on microscopic, trajectory-based models [18], [19], [20], [21]; very limited work has been done at the macroscopic, intersection level. Some researchers have studied potential security risks for CAV against jamming attacks in microscopic settings, such as sensor anomaly detection, access technology, etc [22], [23], [24].…”

Section: Introductionmentioning

confidence: 99%

Securing Signal-free Intersections against Strategic Jamming Attacks: A Macroscopic Approach

Bai¹,

Amin²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

We consider the security-by-design of a signal-free intersection for connected and autonomous vehicles in the face of strategic jamming attacks. We use a fluid model to characterize macroscopic traffic flow through the intersection, where the saturation rate is derived from a vehicle coordination algorithm. We model jamming attacks as sudden increase in communication latency induced on vehicle-to-infrastructure connectivity; such latency triggers the safety mode for vehicle coordination and thus reduces the intersection saturation rate. A strategic attacker selects the attacking rate, while a system operator selects key design parameters, either the saturation rate or the recovery rate. Both players' actions induce technological costs and jointly determine the mean travel delay. By analyzing the equilibrium of the security game, we study the preferable level of investment in the intersection's nominal discharging capability or recovery capability, for balance between hardware/infrastructure cost and security-by-design.

show abstract

Are autonomous vehicles better off without signals at intersections? A comparative computational study

Cited by 30 publications

References 34 publications

D-HAL: Distributed Hierarchical Adversarial Learning for Multi-Agent Interaction in Autonomous Intersection Management

D-HAL: Distributed Hierarchical Adversarial Learning for Multi-Agent Interaction in Autonomous Intersection Management

Intersection control with connected and automated vehicles: a review

Securing Signal-free Intersections against Strategic Jamming Attacks: A Macroscopic Approach

Contact Info

Product

Resources

About