Adaptive Intelligent Sensing Control Method for Traffic Lights under Real-Time Vehicle Conditions Based on Logic Rules

다국어 초록 (Multilingual Abstract)

Compared with traditional adaptive algorithms, the complex and changing operating environment of intelligent networks demands high real-time accuracy in data transmission, necessitating an accurate and adaptive traffic light control strategy. Machine learning (ML) techniques can predict traffic conditions based on historical data and real-time information. However, some scholars have mentioned that ML techniques are still deficient in real-time response and in coping with random traffic accidents. Traditional Reinforcement Learning (RL) requires repeated trial and error operations. Applying traditional RL techniques to the optimal control of traffic lights may lead to more serious traffic congestion in some cases. Therefore, this paper combines perceptual control with real-time adaptive control methods to provide a rule-based reasoning method for adaptive intelligent perception and precise control of traffic signals under real-time smart grid-connected hybrid vehicle conditions. IIoT (Industrial Internet of Things) devices are utilized to monitor the parking queue length, pedestrian flow, vehicle flow, and traffic flow in each lane in real time to dynamically adjust the green light duration. By adjusting the light priority according to real-time vehicle and road conditions, this method solves the problem of wasting green lights when random accidents occur in a certain lane, optimizes traffic light settings, achieves real-time precise control of lane flow, and improves the adaptability and precision of traffic lights.

참고문헌 (Reference)

1 H. Lin, "Traffic Signal Optimization Based on Fuzzy Control and Differential Evolution Algorithm" 24 (24): 8555-8566, 2023

2 M. Eom, "The traffic signal control problem for intersections: a review" 12 : 1-20, 2020

3 A. J. Miller, "Settings for Fixed-Cycle Traffic Signals" 14 (14): 373-386, 1963

4 L.Y. Deng, "Research on fuzzy control method of single intersection traffic signal" 37 (37): 83-86, 2018

5 Y. Liu, "Reinforcement-Learning-Based Decision and Control for Autonomous Vehicle at Two-Way Single-Lane Unsignalized Intersection" 11 (11): 2022

6 M. Noaeen, "Reinforcement learning in urban network traffic signal control: A systematic literature review" 199 : 2022

7 H. Wei, "Recent Advances in Reinforcement Learning for Traffic Signal Control : A Survey of Models and Evaluation" 22 (22): 12-18, 2021

8 H. Wei, "Recent Advances in Reinforcement Learning for Traffic Signal Control : A Survey of Models and Evaluation" 22 (22): 12-18, 2021

9 S. A. Celtek, "Real-time traffic signal control with swarm optimization methods" 166 : 2020

10 L. Tang, "Pedestrian crossing design and analysis for symmetric intersections : Efficiency and safety" 142 : 187-206, 2020

11 PTV Group, "PTV Vissim 7 User Manual"

12 H. Wang, "Optimizing Signal Timing Control for Large Urban Traffic Networks Using an Adaptive Linear Quadratic Regulator Control Strategy" 23 (23): 333-343, 2022

13 F. A. Butt, "On the Integration of Enabling Wireless Technologies and Sensor Fusion for Next-Generation Connected and Autonomous Vehicles" 10 : 14643-14668, 2022

14 T. Chu, "Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control" 21 (21): 1086-1095, 2020

15 A. Boukerche, "Machine Learning-based traffic prediction models for Intelligent Transportation Systems" 181 : 2020

16 J. Ko, "Intelligence in traffic simulation model : Modeling congested network" 40 (40): 7917-7923, 2021

17 H. Wei, "IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control" 2496-2505, 2018

18 N. Kumar, "Fuzzy Inference Enabled Deep Reinforcement Learning-Based Traffic Light Control for Intelligent Transportation System" 22 (22): 4919-4928, 2021

19 M. Barthauer, "Evaluation of presorted and presignaled intersections with respect to traffic efficiency and traffic safety" 47 : 307-314, 2020

20 G. Filomena, "Empirical characterisation of agents’ spatial behaviour in pedestrian movement simulation" 82 : 2022

21 J. Fabianova, "Design and evaluation of a new intersection model to minimize congestions using VISSIM software" 10 (10): 48-56, 2020

22 N. Molyneaux, "Design and analysis of control strategies for pedestrian flows" 48 (48): 1767-1807, 2021

23 X. Yang, "Deep reinforcement learning in NOMA-assisted UAV networks for path selection and resource offloading" 151 : 2023

24 B. R. Kiran, "Deep reinforcement learning for autonomous driving : A survey" 23 (23): 4909-4926, 2022

25 Y. He, "Deep Adaptive Control: Deep Reinforcement Learning-Based Adaptive Vehicle Trajectory Control Algorithms for Different Risk Levels" 9 (9): 1654-1666, 2023

26 M. Tursun, "Data-driven Evaluation of Transit Efficiency at Intersection" 23 (23): 14857-14864, 2023

27 L. Chen, "Comprehensive Evaluation of Operational Efficiency of Intersections in Arterial Considering Pedestrians Yield Rule" 2022 : 2022

28 I. Kravcovas, "Comparison of Pavement Performance Models for Urban Road Management System" 15 (15): 111-129, 2020

29 Z. Zhong, "Autonomous and Semiautonomous Intersection Management: A Survey" 13 (13): 53-70, 2021

30 Y. Ma, "Artificial intelligence applications in the development of autonomous vehicles : A survey" 7 (7): 315-329, 2020

31 Z. Ullah, "Applications of Artificial Intelligence and Machine learning in smart cities" 154 : 313-323, 2020

32 A. Atta, "An adaptive approach: Smart traffic congestion control system" 32 (32): 1012-1019, 2020

33 S. -B. Cools, "Advances in Applied Self-Organizing Systems" 45-55, 2013

34 Z. Liu, "A tailored machine learning approach for urban transport network flow estimation" 108 : 130-150, 2019

35 F.-M. Luo, "A survey on model-based reinforcement learning" 67 (67): 2024

36 Y. Fu, "A Survey of Driving Safety With Sensing, Vehicular Communications, and Artificial Intelligence-Based Collision Avoidance" 23 (23): 6142-6163, 2022

37 J. Jin, "A Multi-Objective Agent-Based Control Approach With Application in Intelligent Traffic Signal System" 20 (20): 3900-3912, 2019

38 J. Garcıa, "A Comprehensive Survey on Safe Reinforcement Learning" 16 (16): 1437-1480, 2015