A deep reinforcement learning-based intelligent intervention framework for real-time proactive road safety management. (February 2022)

• Record Type: Journal Article
• Authors: Roy, Ananya; Hossain, Moinul; Muromachi, Yasunori
• Is Part Of: Accident analysis and prevention. Volume 165(2022)
• Publication Date: 2022-02
• Subjects: Cell transmission model -- Dynamic Bayesian network -- Real-time crash prediction and intervention model -- Deep reinforcement learning; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2021.106512
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: A VSL based proactive road safety management system was proposed. The system consists of a real-time crash prediction model and a VSL control system. Real-time crash prediction model was constructed using Dynamic Bayesian Network. Cell Transmission Model based experimental setup was used. VSL was applied using DQN reinforcement learning algorithm. Abstract: We propose a variable speed limit (VSL) system for improving the safety of urban expressways in real time. The system has two main functions: monitoring traffic data and then using the data to assess crash risk through a real-time crash prediction model (RTCPM). When the risk is high, the system triggers VSL control to restore traffic conditions to normal. The study addresses several weaknesses in existing VSL-based real-time safety interventions. Existing models are not widely applicable due to varying detector spacing among different freeways, and even within a study area. Therefore, with the existing detector spacing as an input, a cell transmission model (CTM) is used to simulate traffic states for the desired cell size. A dynamic Bayesian network (DBN) is used for modeling in the RTCPM. The proposed CTM model is then modified to allow VSL control. Whereas existing studies selected various VSL strategies from a predefined list, we employ a deep Q-network, which is a reinforcement learning-based machine learning algorithm, for the VSL control. Two busy segments of the Tokyo Metropolitan Expressway were used as the study area. After several iterations, our proposed real-time system reduced the crash risk by 19%.