Multi-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy
Sensors · 11.05.2023 · 23 (10) · 4659
DOI: 10.3390/s23104659 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 11.05.2023. Verfasst von Jianshuai Feng und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
In advanced transportation-management systems, variable speed limits are a crucial application. Deep reinforcement learning methods have been shown to have superior performance in many applications, as they are an effective approach to learning environment dynamics for decision-making and control. However, they face two significant difficulties in traffic-control applications: reward engineering with delayed reward and brittle convergence properties with gradient descent. To address these challenges, evolutionary strategies are well suited as a class of black-box optimization techniques inspired by natural evolution. Additionally, the traditional deep reinforcement learning framework struggles to handle the delayed reward setting. This paper proposes a novel approach using covariance matrix adaptation evolution strategy (CMA-ES), a gradient-free global optimization method, to handle the task of multi-lane differential variable speed limit control. The proposed method uses a deep-learning-based method to dynamically learn optimal and distinct speed limits among lanes. The parameters of the neural network are sampled using a multivariate normal distribution, and the dependencies between the variables are represented by a covariance matrix that is optimized dynamically by CMA-ES based on the freeway’s throughput. The proposed approach is tested on a freeway with simulated recurrent bottlenecks, and the experimental results show that it outperforms deep reinforcement learning-based approaches, traditional evolutionary search methods, and the no-control scenario. Our proposed method demonstrates a 23% improvement in average travel time and an average of a 4% improvement in CO, HC, and NOx emission.Furthermore, the proposed method produces explainable speed limits and has desirable generalization power.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China.
- Intelligent Transportation Systems Centre, University of Toronto, Toronto, ON M5S 1A4, Canada.
- National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China.
- School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China.
- Advanced Research Institute of Multidisciplinary Sciences, Beijing Institute of Technology, Beijing 100081, China.
ORCID-Profile: Jianshuai Feng, Hongwen He
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Feng, J., Shi, T., Wu, Y., Xie, X., He, H., & Tan, H. (2023). Multi-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy. Sensors, 23(10), 4659. https://doi.org/10.3390/s23104659
Vancouver
Feng J, Shi T, Wu Y, Xie X, He H, Tan H. Multi-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy. Sensors. 2023;23(10):4659. doi:10.3390/s23104659
BibTeX
@article{Feng2023,
author = {Feng, Jianshuai and Shi, Tianyu and Wu, Yuankai and Xie, Xiang and He, Hongwen and Tan, Huachun},
title = {Multi-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy},
journal = {Sensors},
year = {2023},
volume = {23},
number = {10},
pages = {4659},
doi = {10.3390/s23104659}
}
EUVIMED