Article
Engineering, Civil
Yifan Zhang, Qian Xu, Jianping Wang, Kui Wu, Zuduo Zheng, Kejie Lu
Summary: In this paper, a new model for discretionary lane change (DLC) decision-making is proposed, which integrates human factors represented by driving styles and considers contextual traffic information and driving styles of surrounding vehicles. The model can imitate human drivers' decision-making maneuvers and achieves a prediction accuracy of 98.66%. The impact of the model on improving traffic safety and speed compared to human drivers is also analyzed.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Weida Wang, Tianqi Qie, Chao Yang, Wenjie Liu, Changle Xiang, Kun Huang
Summary: This article proposes a prediction method based on a fuzzy inference system and a long short-term memory neural network to accurately predict the lane-changing behavior of surrounding vehicles, as well as an intelligent decision-making strategy for path planning of autonomous vehicles to enhance driving safety.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Computer Science, Hardware & Architecture
Oumaima El Joubari, Jalel Ben Othman, Veronique Veque
Summary: Traffic congestion is a significant global challenge with harmful consequences. Vehicle-to-anything (V2X) communication technology is regarded as a promising solution to alleviate traffic burden through real-time exchange of traffic information. This study develops a traffic model based on Markov chain to address highway congestion by predicting future traffic conditions.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Engineering, Civil
Longsheng Jiang, Dong Chen, Zhaojian Li, Yue Wang
Summary: This study proposes a computational model that integrates perception, reasoning, emotion, and decision-making to describe driver lane-change decision-making. The model performs well in modeling risk perception and risk propensity, and shows better prediction performance than other models.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Green & Sustainable Science & Technology
Junfeng Yao, Longhao Yan, Zhuohang Xu, Ping Wang, Xiangmo Zhao
Summary: With the continuous increase in highway mileage and vehicles in China, accidents on highways are also increasing. The complicated on-site disposal procedures of highway accidents make it difficult for emergency departments to fully observe the scene, resulting in a lack of communication and cooperation. This paper proposes a multi-agent-based collaborative emergency decision-making algorithm to optimize emergency disposal procedures and improve collaboration efficiency. Through simulation experiments and comparisons, it is shown that the proposed algorithm can greatly reduce emergency response time and improve rescue efficiency.
Article
Chemistry, Analytical
Ming Ye, Lei Pu, Pan Li, Xiangwei Lu, Yonggang Liu
Summary: In recent years, autonomous driving technology has shifted towards vehicle adapting to humans. A personalized lane change decision model based on time-series data is proposed to improve the adaptability of autonomous driving systems. By identifying driving styles and considering interaction between vehicles, the model accurately predicts lane change behavior and enables personalized driving.
Article
Computer Science, Artificial Intelligence
Anders Hansson, Ellen Korsberg, Roza Maghsood, Eliza Norden, Selpi
Summary: Lane-level map matching is crucial for autonomous driving, and a Hidden Markov Model (HMM) is proposed in this study to improve the accuracy of matching trajectory with noisy GPS measurements using yaw rate data and visual cues. The model achieves 95.1% recall and 3.3% median path length error for motorway trajectories, demonstrating its effectiveness in lane-level map matching.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2021)
Article
Automation & Control Systems
Wen Hu, Zejian Deng, Dongpu Cao, Bangji Zhang, Amir Khajepour, Lei Zeng, Yang Wu
Summary: This study proposed a probabilistic decision-making and trajectory planning framework for the autonomous heavy trucks, utilizing utility theory and risk assessment for decision process, developing aggressiveness index and stability domains as constraints, providing human-like lane-change decisions and truck-friendly trajectories.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Green & Sustainable Science & Technology
Kekun Zhang, Dayi Qu, Hui Song, Tao Wang, Shouchen Dai
Summary: With the help of an intelligent networking environment, autonomous driving technology has entered a new stage of development, leading to fundamental changes in the decision-making behavior of autonomous vehicles. Therefore, it is urgent to explore the lane-changing decision-making behavior mechanism of autonomous driving. This study introduces the concept of molecular interaction potential to analyze and model the lane-changing process of vehicles, taking into account the dynamic factors in the traffic environment. The results show that the molecular interaction potential lane-changing model improves the safety, stability, and efficiency of autonomous vehicles.
Article
Mathematics
Federico Bizzarri, Chiara Mocenni, Silvia Tiezzi
Summary: We propose a Markov Decision Process Model that combines ideas from Psychological research and Economics to study decision-making in people with self-control issues. From Psychological research, we borrow a dual-process of decision-making with self-awareness, and from Economics, we introduce present bias in inter-temporal preferences. We examine both exogenous and endogenous, state-dependent, present bias in inter-temporal decision-making, and use numerical simulations to explore the impact on well-being. Our findings suggest that self-awareness can alleviate present bias and suboptimal choice behavior over time.
Article
Engineering, Civil
Shurong Li, Chong Wei, Ying Wang
Summary: This paper presents an integrated methodology that addresses the limitations of existing works in the context of Automated Lane Change system. The methodology utilizes a deep Reinforcement Learning algorithm and a specially devised trajectory planning model to improve the operational effectiveness of lane-changing maneuvers.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Automation & Control Systems
Gabriele Oliva, Roberto Setola, Andrea Gasparri
Summary: In this article, the problem of modifying the transition probabilities of a Markov chain in a distributed way is considered. The objective is to achieve a desired limiting distribution while minimizing the variation from the current weights. The authors propose a solution that involves solving a relaxed problem, deriving an algebraic optimality condition, and designing a distributed algorithm that converges towards this condition.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
Article
Mathematics
Pan Zheng, Wenqin Zhao, Yaqiong Lv, Lu Qian, Yifan Li
Summary: This paper proposes a novel equipment maintenance decision-making method based on Long Short-Term Memory (LSTM) and Markov decision process. The remaining service life of equipment is predicted using the LSTM model to distinguish its health state quantitatively. A degradation process model is constructed based on the bearing residual life prediction curve, and the corresponding parameters of the model are identified. The Markov decision process model is then constructed based on the bearing degradation curve to provide accurate maintenance strategies for different health conditions of the system. An experimental study with the full life cycle data set of rolling bearings demonstrates the effectiveness of the proposed method in achieving efficient maintenance decisions for bearings under different health states, providing a feasible solution for bearing system maintenance.
Article
Physics, Multidisciplinary
Yangsheng Jiang, Siyuan Sun, Fangyi Zhu, Yunxia Wu, Zhihong Yao
Summary: In the future, traffic flow will consist of both connected automated vehicles (CAVs) and human-driven vehicles (HDVs). The random spatial distribution of different vehicle types hinders the stability and safety of traffic flow and decreases traffic capacity. Therefore, organizing and managing the spatial distribution of vehicles in mixed traffic flow is crucial for improving transportation system performance. This paper proposes a mixed capacity and lane management model that takes into account platoon size and intensity of CAVs in order to effectively organize CAVs and manage automated dedicated lanes. Numerical analyses demonstrate that increasing the market penetration rate, platoon size, and platooning intensity of CAVs improves single-lane capacity. Furthermore, optimal lane management is found to be associated with the market penetration rate of CAVs. These findings provide insights and a strategy for the future operation and management of dedicated CAV lanes.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Operations Research & Management Science
Rokhsaneh Yousef Zehi, Adli Mustafa
Summary: In this paper, a new bi-objective model is proposed for evaluating decision making units (DMUs) with semi-discretionary variables in DEA, where the modification of variables to target values is managed by decision makers in a voting system. One of the advantages is the direct inclusion of decision making conditions into the DEA model.
RAIRO-OPERATIONS RESEARCH
(2021)