Deep Reinforcement Learning in Lane Merge Coordination for Connected Vehicles

Omar Nassef; Luis Sequeira Villarreal; Elias Salam; Toktam Mahmoodi

Deep Reinforcement Learning in Lane Merge Coordination for Connected Vehicles

Omar Nassef, Luis Sequeira Villarreal, Elias Salam, Toktam Mahmoodi

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

75 Downloads (Pure)

Abstract

In this paper, a framework for lane merge coordination
is presented utilising a centralised system, for connected
vehicles. The delivery of trajectory recommendations
to the connected vehicles on the road is based on a Traffic
Orchestrator and a Data Fusion as the main components. Deep
Reinforcement Learning and data analysis is used to predict
trajectory recommendations for connected vehicles, taking into
account unconnected vehicles for those suggestions. The results
highlight the adaptability of the Traffic Orchestrator, when employing
Dueling Deep Q-Network in an unseen real world merging
scenario. A performance comparison of different reinforcement
learning models and evaluation against Key Performance Indicator
(KPI) are also presented.

Original language	English
Title of host publication	IEEE PIMRC 2020
Publication status	Accepted/In press - 2020

Access to Document

PIMRC20_Lane-merge_RLAccepted author manuscript, 1.07 MB

Cite this

@inbook{abe2e0f5260846e7bdb6cfb88d65d962,

title = "Deep Reinforcement Learning in Lane Merge Coordination for Connected Vehicles",

abstract = "In this paper, a framework for lane merge coordinationis presented utilising a centralised system, for connectedvehicles. The delivery of trajectory recommendationsto the connected vehicles on the road is based on a TrafficOrchestrator and a Data Fusion as the main components. DeepReinforcement Learning and data analysis is used to predicttrajectory recommendations for connected vehicles, taking intoaccount unconnected vehicles for those suggestions. The resultshighlight the adaptability of the Traffic Orchestrator, when employingDueling Deep Q-Network in an unseen real world mergingscenario. A performance comparison of different reinforcementlearning models and evaluation against Key Performance Indicator(KPI) are also presented.",

author = "Omar Nassef and {Sequeira Villarreal}, Luis and Elias Salam and Toktam Mahmoodi",

year = "2020",

language = "English",

booktitle = "IEEE PIMRC 2020",

}

TY - CHAP

T1 - Deep Reinforcement Learning in Lane Merge Coordination for Connected Vehicles

AU - Nassef, Omar

AU - Sequeira Villarreal, Luis

AU - Salam, Elias

AU - Mahmoodi, Toktam

PY - 2020

Y1 - 2020

N2 - In this paper, a framework for lane merge coordinationis presented utilising a centralised system, for connectedvehicles. The delivery of trajectory recommendationsto the connected vehicles on the road is based on a TrafficOrchestrator and a Data Fusion as the main components. DeepReinforcement Learning and data analysis is used to predicttrajectory recommendations for connected vehicles, taking intoaccount unconnected vehicles for those suggestions. The resultshighlight the adaptability of the Traffic Orchestrator, when employingDueling Deep Q-Network in an unseen real world mergingscenario. A performance comparison of different reinforcementlearning models and evaluation against Key Performance Indicator(KPI) are also presented.

AB - In this paper, a framework for lane merge coordinationis presented utilising a centralised system, for connectedvehicles. The delivery of trajectory recommendationsto the connected vehicles on the road is based on a TrafficOrchestrator and a Data Fusion as the main components. DeepReinforcement Learning and data analysis is used to predicttrajectory recommendations for connected vehicles, taking intoaccount unconnected vehicles for those suggestions. The resultshighlight the adaptability of the Traffic Orchestrator, when employingDueling Deep Q-Network in an unseen real world mergingscenario. A performance comparison of different reinforcementlearning models and evaluation against Key Performance Indicator(KPI) are also presented.

M3 - Conference paper

BT - IEEE PIMRC 2020

ER -