Eco-driving at signalized intersections: a parameterized reinforcement learning approach

Article Transportation

Multi-lane-merging strategy for connected automated vehicles on freeway ramps

Xiaoling Luo et al.

Summary: This paper proposes a strategy for efficiently merging automated vehicles from a multiple-lane ramp. The proposed strategy outperforms traditional strategies in reducing delay and is found to be the most reliable in various scenarios.

TRANSPORTMETRICA B-TRANSPORT DYNAMICS (2023)

添加到收藏夹

Article Engineering, Civil

Learning the Policy for Mixed Electric Platoon Control of Automated and Human-Driven Vehicles at Signalized Intersection: A Random Search Approach

Xia Jiang et al.

Summary: The upgrading and updating of vehicles have accelerated in the past decades. Electric vehicles (EVs) and connected and automated vehicles (CAVs) have become new components of transportation systems due to the need for environmental friendliness and intelligence. This paper proposes a reinforcement learning framework to implement adaptive control for an electric platoon composed of CAVs and human-driven vehicles (HDVs) at a signalized intersection. Through simulations and comparisons, it is shown that the proposed method can achieve higher rewards and save more energy compared to traditional approaches.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2023)

添加到收藏夹

Article Engineering, Civil

An Eco-Driving Strategy for Partially Connected Automated Vehicles at a Signalized Intersection

Miao Yu et al.

Summary: This paper investigates the control problem of a signalized intersection in a partially connected automated vehicle environment. By adopting model predictive control, a real-time eco-driving strategy is proposed to optimize the control center's driving decisions and minimize fuel consumption.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

添加到收藏夹

Article Engineering, Civil

Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections

Zhengwei Bai et al.

Summary: This study proposes a hybrid reinforcement learning framework to support connected eco-driving in mixed traffic. Through experiments, it shows that the proposed method can reduce energy consumption and save travel time compared to a state-of-the-art model-based approach.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

添加到收藏夹

Article Engineering, Civil

A Multiobjective Cooperative Driving Framework Based on Evolutionary Algorithm and Multitask Learning

Xia Jiang et al.

Summary: The development of connected and automated vehicle (CAV) techniques is revolutionizing traffic management. This study presents a comprehensive cooperative intelligent driving framework to optimize vehicle dispatching in on-ramp and intersection scenarios, improving safety, traffic efficiency, and energy consumption. Simulation results demonstrate satisfactory performance in terms of time and energy consumption.

JOURNAL OF ADVANCED TRANSPORTATION (2022)

添加到收藏夹

Article Energy & Fuels

Energy efficient speed planning of electric vehicles for car-following scenario using model-based reinforcement learning

Heeyun Lee et al.

Summary: This study proposes a reinforcement learning-based energy efficient speed planning strategy for autonomous electric vehicles to minimize energy consumption in diverse driving situations.

APPLIED ENERGY (2022)

添加到收藏夹

Article Engineering, Civil

Harmonious Lane Changing via Deep Reinforcement Learning

Guan Wang et al.

Summary: This paper studies a harmonious lane-changing strategy for autonomous vehicles without V2X communication support through multi-agent reinforcement learning, which is more effective in improving traffic efficiency compared to competitive strategy.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

添加到收藏夹

Article Engineering, Civil

Navigating Electric Vehicles Along a Signalized Corridor via Reinforcement Learning: Toward Adaptive Eco-Driving Control

Jian Zhang et al.

Summary: This paper proposes an adaptive eco-driving method for electric vehicles using reinforcement learning technology. It considers factors such as safety, traffic mobility, energy consumption, and comfort, and achieves balanced and stable performance in simulation studies.

TRANSPORTATION RESEARCH RECORD (2022)

添加到收藏夹

Article Energy & Fuels

Model predictive control and deep reinforcement learning based energy efficient eco-driving for battery electric vehicles

Kiwon Yeom

Summary: This article proposes a hybrid approach using Deep Reinforcement Learning (DRL) and Model Predictive Control (MPC) to improve the energy economy of electric vehicles (EVs). The MPC algorithm is used to solve the optimization problem for speed control, while the DRL networks utilize the cost value of the horizon as observed state. The proposed scheme shows promising results in terms of energy-saving performance.

ENERGY REPORTS (2022)

添加到收藏夹

Article Transportation

Enhanced speed advice for connected vehicles in the proximity of signalized intersections

Evangelos Mintsis et al.

Summary: This study focuses on improving the comfort and safety of speed advice in urban traffic while ensuring energy and traffic efficiency. Through a detailed microscopic simulation model and evaluation of the performance of dynamic eco-driving technology under different traffic conditions, the study found that speed advice can enhance comfort and safety without negatively impacting energy and traffic efficiency.

EUROPEAN TRANSPORT RESEARCH REVIEW (2021)

添加到收藏夹

Article Transportation Science & Technology

Hybrid deep reinforcement learning based eco-driving for low-level connected and automated vehicles along signalized corridors

Qiangqiang Guo et al.

Summary: The paper introduces a hybrid reinforcement learning-based Eco-Driving algorithm that reduces fuel consumption by learning longitudinal acceleration/deceleration and lane-changing operations. Numerical experiments on multi-lane urban signalized corridors demonstrate that the algorithm can significantly reduce fuel consumption.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2021)

添加到收藏夹

Article Environmental Studies

Eco-driving-based cooperative adaptive cruise control of connected vehicles platoon at signalized intersections

Fangwu Ma et al.

Summary: The Eco-CACC proposed in this study combines eco-driving and car-following techniques to minimize energy consumption of automated vehicle platoons. Testing results show that Eco-CACC can significantly improve energy performance compared to manual driving.

TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT (2021)

添加到收藏夹

Article Transportation Science & Technology

Connected automated vehicle cooperative control with a deep reinforcement learning approach in a mixed traffic environment

Haotian Shi et al.

Summary: This paper presents a cooperative strategy for longitudinal control of vehicles in a mixed connected and automated traffic environment using a deep reinforcement learning algorithm. By decomposing mixed traffic into multiple subsystems and enabling CAVs to learn from leading HDVs, the proposed method improves performance locally for each subsystem and overall for the traffic flow.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2021)

添加到收藏夹

Article Transportation Science & Technology

Automated eco-driving in urban scenarios using deep reinforcement learning

Marius Wegener et al.

Summary: Implementing eco-driving strategies for automated vehicles in urban settings is challenging due to limited information on the preceding vehicle pulk and low penetration of vehicle-to-vehicle communication. This study used Reinforcement Learning to develop energy-saving driving strategies for scenarios with limited traffic data, leading to energy savings of up to 19% compared to human drivers and up to 11% compared to a fine-tuned GLOSA algorithm in a probabilistic traffic scenario reflecting real-world conditions.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Enhanced Eco-Approach Control of Connected Electric Vehicles at Signalized Intersection With Queue Discharge Prediction

Haoxuan Dong et al.

Summary: This study introduces an enhanced eco-approach control strategy to improve energy efficiency at signalized intersections by predicting the movement of vehicle queues. Through a hierarchical framework and numerical simulations, it is shown that the EEAC strategy can effectively enhance energy utilization efficiency.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2021)

添加到收藏夹

Article Transportation Science & Technology

Adaptive signal control for bus service reliability with connected vehicle technology via reinforcement learning

Andy H. F. Chow et al.

Summary: This paper introduces an adaptive signal controller that effectively manages traffic delays and urban bus service reliability using fully adaptable acyclic timing plans. The controller is built upon a reinforcement learning framework combining model-based and data-driven components to reduce traffic delays and bus service variabilities.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2021)

添加到收藏夹

Article Transportation Science & Technology

Energy and flow effects of optimal automated driving in mixed traffic: Vehicle-in-the-loop experimental results

Tyler Ard et al.

Summary: This paper experimentally demonstrates the effectiveness of an anticipative car-following algorithm in reducing energy use of gasoline engine and electric Connected and Automated Vehicles (CAV), without sacrificing safety and traffic flow. The study shows up to 30% improved energy economy compared to realistically calibrated human driver car-following without sacrificing following headway.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Accurate physics-based modeling of electric vehicle energy consumption in the SUMO traffic microsimulator

Lucas Koch et al.

Summary: Urban mobility is shifting towards electrification rapidly, but the issues of limited range and availability of charging infrastructure for Electric Vehicles (EVs) remain. Accurate predictions of energy demand are crucial for effectively managing these limitations. Current simplistic energy consumption models are usually specific to certain vehicles, neglecting individual powertrain components' characteristics.

2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC) (2021)

添加到收藏夹

Article Transportation

Integrated multistep Markov-based velocity predictor of energy consumption prediction model for battery electric vehicles

Jianhua Guo et al.

Summary: This paper proposes an effective model for predicting energy consumption of battery electric vehicles (BEVs) through accurate velocity prediction method, combined with Markov-chain and road information. The method demonstrates acceptable results on various road types, with an average error of less than 2%, showing high precision and feasibility.

TRANSPORTMETRICA B-TRANSPORT DYNAMICS (2021)

添加到收藏夹

Article Energy & Fuels

Jointly dampening traffic oscillations and improving energy consumption with electric, connected and automated vehicles: A reinforcement learning based approach

Xiaobo Qu et al.

APPLIED ENERGY (2020)

添加到收藏夹

Article Environmental Studies

Eco-driving behaviors of electric vehicle users: A survey study

Guangjun Wang et al.

TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT (2020)

添加到收藏夹

Review Engineering, Civil

Dynamic Eco-Driving near Signalized Intersections: Systematic Review and Future Research Directions

Evangelos Mintsis et al.

JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS (2020)

添加到收藏夹

Article Energy & Fuels

Eco-driving control of connected and automated hybrid vehicles in mixed driving scenarios

Siyang Wang et al.

APPLIED ENERGY (2020)

添加到收藏夹

Article Environmental Studies

Investigation of environmental benefits of traffic signal countdown timers

Minjeong Kim et al.

TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT (2020)

添加到收藏夹

Article Engineering, Civil

Deep Reinforcement Learning Agent with Varying Actions Strategy for Solving the Eco-Approach and Departure Problem at Signalized Intersections

Saleh R. Mousa et al.

TRANSPORTATION RESEARCH RECORD (2020)

添加到收藏夹

Article Transportation

Gap-based automated vehicular speed guidance towards eco-driving at an unsignalized intersection

Wenqing Chen et al.

TRANSPORTMETRICA B-TRANSPORT DYNAMICS (2019)

添加到收藏夹

Article Thermodynamics

Evaluation of electric vehicle component performance over eco-driving cycles

Zhiming Gao et al.

ENERGY (2019)

添加到收藏夹

Article Physics, Multidisciplinary

V2I-based car-following modeling and simulation of signalized intersection

Yusheng Ci et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2019)

添加到收藏夹

Article Engineering, Environmental

Regional comparison of electric vehicle adoption and emission reduction effects in China

Fangyi Li et al.

RESOURCES CONSERVATION AND RECYCLING (2019)

添加到收藏夹

Article Transportation Science & Technology

Spatiotemporal intersection control in a connected and automated vehicle environment

Yiheng Feng et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

添加到收藏夹

Article Transportation Science & Technology

A platoon based cooperative eco-driving model for mixed automated and human-driven vehicles at a signalised intersection

Weiming Zhao et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

添加到收藏夹

Article Transportation Science & Technology

An eco-driving system for electric vehicles with signal control under V2X environment

Ming Li et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

添加到收藏夹

Article Engineering, Civil

Application and Evaluation of the Reinforcement Learning Approach to Eco-Driving at Intersections under Infrastructure-to-Vehicle Communications

Junqing Shi et al.

TRANSPORTATION RESEARCH RECORD (2018)

添加到收藏夹

Article Transportation Science & Technology

Eco approaching at an isolated signalized intersection under partially connected and automated vehicles environment

Huifu Jiang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2017)

添加到收藏夹

Article Transportation Science & Technology

Influence of connected and autonomous vehicles on traffic flow stability and throughput

Alireza Talebpour et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2016)

添加到收藏夹

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)

添加到收藏夹

Proceedings Paper Transportation Science & Technology

Intersection Vehicle Cooperative Eco-Driving in the Context of Partially Connected Vehicle Environment

M. A. S. Kamal et al.

2015 IEEE 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (2015)

添加到收藏夹

Article Engineering, Civil

Model for Optimization of Ecodriving at Signalized Intersections

Zhi Chen et al.

TRANSPORTATION RESEARCH RECORD (2014)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Implementation of an Energy Model and a Charging Infrastructure in SUMO

Tamas Kurczveil et al.

SIMULATION OF URBAN MOBILITY (2014)

添加到收藏夹

Article Transportation

Dynamic Eco-Driving for Signalized Arterial Corridors and Its Indirect Network-Wide Energy/Emissions Benefits

Haitao Xia et al.

JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS (2013)

添加到收藏夹

Article Engineering, Civil

Green Light Optimized Speed Advisory Systems Impact of Signal Phasing Information Accuracy

Aleksandar Stevanovic et al.

TRANSPORTATION RESEARCH RECORD (2013)

添加到收藏夹

Article Automation & Control Systems

Predictive Cruise Control: Utilizing Upcoming Traffic Signal Information for Improving Fuel Economy and Reducing Trip Time

Behrang Asadi et al.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2011)

添加到收藏夹

Eco-driving at signalized intersections: a parameterized reinforcement learning approach

相关参考文献

导出引文

分享论文