Monte Carlo Tree Search-Based Mixed Traffic Flow Control Algorithm for Arterial Intersections

Cheng, Yanqiu; Hu, Xianbiao; Tang, Qing; Qi, Hongsheng; Yang, Hong

doi:10.1177/0361198120919746

Cited by 12 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e second benchmark scenario used the MCTF-MTF algorithm that was previously developed by the research team [34]. is second benchmark model, however, was developed with the objective of minimize fuel consumption and travel time of the mixed traffic flow, which makes the comparison with this newly proposed model interesting and demonstrates the safety benefits of this new MCTS-AVS algorithm.…”

Section: Algorithm Results Analysismentioning

confidence: 99%

Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach

Cheng

Chen

et al. 2021

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

The longitudinal trajectory planning of connected and autonomous vehicle (CAV) has been widely studied in the literature to reduce travel time or fuel consumptions. The safety impact of CAV trajectory planning to the mixed traffic flow with both CAV and human-driven vehicle (HDV), however, is not well understood yet. This study presents a reinforcement learning modeling approach, named Monte Carlo tree search-based autonomous vehicle safety algorithm, or MCTS-AVS, to optimize the safety of mixed traffic flow, on a one-lane roadway with signalized intersection control. Crash potential index (CPI) is defined to quantitively measure the safety performance of the mixed traffic flow. The CAV trajectory planning problem is firstly formulated as an optimization model; then, the solution procedure based on reinforcement learning is proposed. The tree-expansion determination module and rollout termination module are developed to identify and reduce the unnecessary tree expansion, so as to train the model more efficiently towards the desired direction. The case study results showed that the proposed algorithm was able to reduce the CPI by 76.56%, when compared with a benchmark model without any intelligence, and 12.08%, when compared with another benchmark model that the team developed earlier. These results demonstrated the satisfactory performance of the proposed algorithm in enhancing the safety of the mixed traffic flow.

show abstract

Section: Algorithm Results Analysismentioning

confidence: 99%

Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach

Cheng

Chen

et al. 2021

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, their lack of adaptability leads to inefficient signal phases, particularly in high-traffic areas and complex urban environments. Researchers explore search-based methods 19 and model optimization, such as tree search 20 , genetic algorithms 21 , and swarm optimization 22 , to address these challenges. Prediction-based TSC methods use road state models learned by dynamic Bayesian networks to predict future traffic conditions and adjust signal lights accordingly 23 .…”

Section: Related Workmentioning

confidence: 99%

A scalable approach to optimize traffic signal control with federated reinforcement learning

Bao,

Wu,

Lin

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Intelligent Transportation has seen significant advancements with Deep Learning and the Internet of Things, making Traffic Signal Control (TSC) research crucial for reducing congestion, travel time, emissions, and energy consumption. Reinforcement Learning (RL) has emerged as the primary method for TSC, but centralized learning poses communication and computing challenges, while distributed learning struggles to adapt across intersections. This paper presents a novel approach using Federated Learning (FL)-based RL for TSC. FL integrates knowledge from local agents into a global model, overcoming intersection variations with a unified agent state structure. To endow the model with the capacity to globally represent the TSC task while preserving the distinctive feature information inherent to each intersection, a segment of the RL neural network is aggregated to the cloud, and the remaining layers undergo fine-tuning upon convergence of the model training process. Extensive experiments demonstrate reduced queuing and waiting times globally, and the successful scalability of the proposed model is validated on a real-world traffic network in Monaco, showing its potential for new intersections.

show abstract

“…ATMA is a quickly emerging technology that combines the usage of TMAs and connected and autonomous vehicles (CAV) in work zones. CAV has great potential for changing our daily life and has attracted significant research attention recently ( 23 ). Because of the complex roadway environment and other challenging issues, however, the question of when an autonomous vehicle could become fully functional in a real situation remains unanswered ( 24 ).…”

Section: Literature Reviewmentioning

confidence: 99%

Evaluation Methodology of Leader-Follower Autonomous Vehicle System for Work Zone Maintenance

Tang

Cheng

et al. 2021

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Mobile and slow-moving operations, such as striping, sweeping, bridge flushing, and pothole patching, are critical for efficient and safe operation of a highway transportation system. However, reducing hazards for roadway workers and achieving a safer environment for both roadway maintenance operators and the public is a challenging problem. In 2017 alone, a total of 158,000 vehicle crashes occurred in work zones in the U.S.A., accounting for 61,000 injuries. The autonomous truck-mounted attenuator (ATMA) vehicle, sometimes referred to as an autonomous impact protection vehicle (AIPV), offers a promising solution to eliminate injuries to roadway maintenance workers and the public. This paper presents the evaluation methodology for the ATMA system, as well as the outcomes of field testing in Sedalia, Missouri. To the best of the authors’ knowledge, this is the first academic research to focus on ATMA. The ATMA system is first reviewed, followed by an introduction to the field testing procedures that includes descriptions of test cases and data collected, and their format. An analysis methodology is then proposed to quantitatively evaluate the system’s performance, and statistical models and hypothesis testing procedures are developed and presented. The numerical analysis results from real-world field testing under a controlled environment are presented, and the ATMA system’s performance is summarized. This paper can serve as a reference for transportation agencies that are interested in deploying similar technologies or for academic researchers to assess characteristics of autonomous vehicles and to apply knowledge gained in transportation modeling and simulation practices.

show abstract

Monte Carlo Tree Search-Based Mixed Traffic Flow Control Algorithm for Arterial Intersections

Cited by 12 publications

References 25 publications

Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach

Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach

A scalable approach to optimize traffic signal control with federated reinforcement learning

Evaluation Methodology of Leader-Follower Autonomous Vehicle System for Work Zone Maintenance

Contact Info

Product

Resources

About