Reinforcement learning(RL)has been widely studied as an efficient class of machine learning methods for adaptive optimal control under uncertainties.In recent years,the applications of RL in optimised decision-making ...Reinforcement learning(RL)has been widely studied as an efficient class of machine learning methods for adaptive optimal control under uncertainties.In recent years,the applications of RL in optimised decision-making and motion control of intelligent vehicles have received increasing attention.Due to the complex and dynamic operating environments of intelligent vehicles,it is necessary to improve the learning efficiency and generalisation ability of RL-based decision and control algorithms under different conditions.This survey systematically examines the theoretical foundations,algorithmic advancements and practical challenges of applying RL to intelligent vehicle systems operating in complex and dynamic environments.The major algorithm frameworks of RL are first introduced,and the recent advances in RL-based decision-making and control of intelligent vehicles are overviewed.In addition to self-learning decision and control approaches using state measurements,the developments of DRL methods for end-to-end driving control of intelligent vehicles are summarised.The open problems and directions for further research works are also discussed.展开更多
Decision-making of connected and automated vehicles(CAV)includes a sequence of driving maneuvers that improve safety and efficiency,characterized by complex scenarios,strong uncertainty,and high real-time requirements...Decision-making of connected and automated vehicles(CAV)includes a sequence of driving maneuvers that improve safety and efficiency,characterized by complex scenarios,strong uncertainty,and high real-time requirements.Deep reinforcement learning(DRL)exhibits excellent capability of real-time decision-making and adaptability to complex scenarios,and generalization abilities.However,it is arduous to guarantee complete driving safety and efficiency under the constraints of training samples and costs.This paper proposes a Mixture of Expert method(MoE)based on Soft Actor-Critic(SAC),where the upper-level discriminator dynamically decides whether to activate the lower-level DRL expert or the heuristic expert based on the features of the input state.To further enhance the performance of the DRL expert,a buffer zone is introduced in the reward function,preemptively applying penalties before insecure situations occur.In order to minimize collision and off-road rates,the Intelligent Driver Model(IDM)and Minimizing Overall Braking Induced by Lane changes(MOBIL)strategy are designed by heuristic experts.Finally,tested in typical simulation scenarios,MOE shows a 13.75%improvement in driving efficiency compared with the traditional DRL method with continuous action space.It ensures high safety with zero collision and zero off-road rates while maintaining high adaptability.展开更多
Information plays a crucial role in guiding behavioral decisions during public health emergencies. Individuals communicate to acquire relevant knowledge about an epidemic, which influences their decisions to adopt pro...Information plays a crucial role in guiding behavioral decisions during public health emergencies. Individuals communicate to acquire relevant knowledge about an epidemic, which influences their decisions to adopt protective measures.However, whether to disseminate specific information is also a behavioral decision. In light of this understanding, we develop a coupled information–vaccination–epidemic model to depict these co-evolutionary dynamics in a three-layer network. Negative information dissemination and vaccination are treated as separate decision-making processes. We then examine the combined effects of herd and risk motives on information dissemination and vaccination decisions through the lens of game theory. The microscopic Markov chain approach(MMCA) is used to describe the dynamic process and to derive the epidemic threshold. Simulation results indicate that increasing the cost of negative information dissemination and providing timely clarification can effectively control the epidemic. Furthermore, a phenomenon of diminishing marginal utility is observed as the cost of dissemination increases, suggesting that authorities do not need to overinvest in suppressing negative information. Conversely, reducing the cost of vaccination and increasing vaccine efficacy emerge as more effective strategies for outbreak control. In addition, we find that the scale of the epidemic is greater when the herd motive dominates behavioral decision-making. In conclusion, this study provides a new perspective for understanding the complexity of epidemic spreading by starting with the construction of different behavioral decisions.展开更多
The exploration of unmanned aerial vehicle(UAV)swarm systems represents a focal point in the research of multiagent systems,with the investigation of their fission-fusion behavior holding significant theoretical and p...The exploration of unmanned aerial vehicle(UAV)swarm systems represents a focal point in the research of multiagent systems,with the investigation of their fission-fusion behavior holding significant theoretical and practical value.This review systematically examines the methods for fission-fusion of UAV swarms from the perspective of multi-agent systems,encompassing the composition of UAV swarm systems and fission-fusion conditions,information interaction mechanisms,and existing fission-fusion approaches.Firstly,considering the constituent units of UAV swarms and the conditions influencing fission-fusion,this paper categorizes and introduces the UAV swarm systems.It further examines the effects and limitations of fission-fusion methods across various categories and conditions.Secondly,a comprehensive analysis of the prevalent information interaction mechanisms within UAV swarms is conducted from the perspective of information interaction structures.The advantages and limitations of various mechanisms in the context of fission-fusion behaviors are summarized and synthesized.Thirdly,this paper consolidates the existing implementation research findings related to the fission-fusion behavior of UAV swarms,identifies unresolved issues in fission-fusion research,and discusses potential solutions.Finally,the paper concludes with a comprehensive summary and systematically outlines future research opportunities.展开更多
With the maturation of autonomous driving technology, the use of autonomous vehicles in a socially acceptable manner has become a growing demand of the public. Human-like autonomous driving is expected due to the impa...With the maturation of autonomous driving technology, the use of autonomous vehicles in a socially acceptable manner has become a growing demand of the public. Human-like autonomous driving is expected due to the impact of the differences between autonomous vehicles and human drivers on safety.Although human-like decision-making has become a research hotspot, a unified theory has not yet been formed, and there are significant differences in the implementation and performance of existing methods. This paper provides a comprehensive overview of human-like decision-making for autonomous vehicles. The following issues are discussed: 1) The intelligence level of most autonomous driving decision-making algorithms;2) The driving datasets and simulation platforms for testing and verifying human-like decision-making;3) The evaluation metrics of human-likeness;personalized driving;the application of decisionmaking in real traffic scenarios;and 4) The potential research direction of human-like driving. These research results are significant for creating interpretable human-like driving models and applying them in dynamic traffic scenarios. In the future, the combination of intuitive logical reasoning and hierarchical structure will be an important topic for further research. It is expected to meet the needs of human-like driving.展开更多
Planning and decision-making technology at intersections is a comprehensive research problem in intelligent transportation systems due to the uncertainties caused by a variety of traffic participants.As wireless commu...Planning and decision-making technology at intersections is a comprehensive research problem in intelligent transportation systems due to the uncertainties caused by a variety of traffic participants.As wireless communication advances,vehicle infrastructure integrated algorithms designed for intersection planning and decision-making have received increasing attention.In this paper,the recent studies on the planning and decision-making technologies at intersections are primarily overviewed.The general planning and decision-making approaches are presented,which include graph-based approach,prediction base approach,optimization-based approach and machine learning based approach.Since connected autonomous vehicles(CAVs)is the future direction for the automated driving area,we summarized the evolving planning and decision-making methods based on vehicle infrastructure cooperative technologies.Both four-way signalized and unsignalized intersection(s)are investigated under purely automated driving traffic and mixed traffic.The study benefit from current strategies,protocols,and simulation tools to help researchers identify the presented approaches’challenges and determine the research gaps,and several remaining possible research problems that need to be solved in the future.展开更多
The decision-making under complex urban environment become one of the key issues that restricts the rapid development of the autonomous vehicles. The difficulty in making timely and accurate decisions like human being...The decision-making under complex urban environment become one of the key issues that restricts the rapid development of the autonomous vehicles. The difficulty in making timely and accurate decisions like human beings under highly dynamic traffic environment is a major challenge for autonomous driving. Car-following has been regarded as the simplest but essential driving behavior among driving tasks and has received extensive attention from researchers around the world. This work addresses this problem and proposes a novel method RSAN(rough-set artificial neural network) to learn the decisions from excellent human drivers. A virtual urban traffic environment was built by Pre Scan and driving simulation was conducted to obtain a broad set of relevant data such as experienced drivers' behavior data and surrounding vehicles' motion data. Then, rough set was used to preprocess these data to extract the key influential factors on decision and reduce the impact of uncertain data and noise data. And the car-following decision was learned by neural network in which key factor was the input and acceleration was the output. The result shows the better convergence speed and the better decision accuracy of RSAN than ANN. Findings of this work contributes to the empirical understanding of driver's decision-making process and it provides a theoretical basis for the study of car-following decision-making under complex and dynamic environment.展开更多
While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present...While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.展开更多
With the development of intelligent vehicles and autonomous driving technology,the safety of vulnerable road user(VRU)in traffic has been more guaranteed,and many research achievements have been made in the key area o...With the development of intelligent vehicles and autonomous driving technology,the safety of vulnerable road user(VRU)in traffic has been more guaranteed,and many research achievements have been made in the key area of collision avoidance decision-making methods.In this paper,the knowledge mapping method is used to mine the available literature in depth,and it is found that the research focus has shifted from the traditional accident cause analysis to emerging deep learning and virtual reality technology.This paper summarizes research on the three core dimensions of environmental perception,behavior cognition and collision avoidance decision-making in intelligent vehicle systems.In terms of perception,accurate identification of pedestrians and cyclists in complex environments is a major demand for VRU perception;in terms of behavior cognition,the coupling of VRU intention identification and motion trajectory prediction and other multiple factors needs further research;in terms of decision-making,the intention identification and trajectory prediction of collision objects are not included in the risk assessment model,and there is a lack of exploration specifically for cyclists'collision risk.On this basis,this paper provides guidance for the improvement of traffic safety of contemporary VRU under the conditions of intelligent and connected transportation.展开更多
Behavioral decision-making at urban intersections is one of the primary difficulties currently impeding the development of intelligent vehicle technology.The problem is that existing decision-making algorithms cannot ...Behavioral decision-making at urban intersections is one of the primary difficulties currently impeding the development of intelligent vehicle technology.The problem is that existing decision-making algorithms cannot effectively deal with complex random scenarios at urban intersections.To deal with this,a deep deterministic policy gradient(DDPG)decision-making algorithm(T-DDPG)based on a time-series Markov decision process(T-MDP)was developed,where the state was extended to collect observations from several consecutive frames.Experiments found that T-DDPG performed better in terms of convergence and generalizability in complex intersection scenarios than a traditional DDPG algorithm.Furthermore,model-agnostic meta-learning(MAML)was incorporated into the T-DDPG algorithm to improve the training method,leading to a decision algorithm(T-MAML-DDPG)based on a secondary gradient.Simulation experiments of intersection scenarios were carried out on the Gym-Carla platform to verify and compare the decision models.The results showed that T-MAML-DDPG was able to easily deal with the random states of complex intersection scenarios,which could improve traffic safety and efficiency.The above decision-making models based on meta-reinforcement learning are significant for enhancing the decision-making ability of intelligent vehicles at urban intersections.展开更多
The results from a number of investigations and fire experiments are presented and analyzed in order to characterize the fire behavior of mining vehicles in underground hard rock mines. The analysis also includes fire...The results from a number of investigations and fire experiments are presented and analyzed in order to characterize the fire behavior of mining vehicles in underground hard rock mines. The analysis also includes fire safety and fire protection measures with respect to the mining vehicle fire behavior.Earlier studies on fires in underground hard rock mines have shown that vehicles or mobile equipment are the dominant sources of fire. A better knowledge about the fire behavior of vehicles in underground hard rock mines is therefore needed. During the analysis the direction and flow rate of the ventilation in a drift was found to have a significant impact on the fire behavior, causing for example flame tilt with rapid fire spread. The shielded sections of a vehicle will be less affected by the ventilation flow resulting in for example a decreased flame spread. It was also found that spray fires may result in considerable heat release rate but are generally of shorter duration and will not make any significant contributions to the overall heat release rate of the fully developed vehicle fire. The fire duration of a loader tire from a full-scale fire experiment was found to be at least 200 min and will largely determine the total fire duration of the vehicle. A different scenario with different conditions with for example a slower flame spread resulted in an even longer fire duration. The radiative and convective fraction will be a key factor when determining the heat transfer mechanisms involved in a fire and will vary from material to material.Calculations show that the radiative fraction of the tire fires on two mining vehicles is significantly lower than found in earlier experiments. The design and construction of the mining vehicle will have an important impact on the fire behavior and could possibly mitigate the consequences of a fire and allow fire personnel to extinguish a fire that otherwise would have had a too high heat release rate.展开更多
The adoption and usage of electric vehicles(EVs)have emerged recently due to the increasing concerns on the greenhouse gas issues and energy revolution.As a part of the smart grid,EVs can provide valuable ancillary se...The adoption and usage of electric vehicles(EVs)have emerged recently due to the increasing concerns on the greenhouse gas issues and energy revolution.As a part of the smart grid,EVs can provide valuable ancillary services beyond consumers of electricity.However,EVs are gradually considered as nonnegligible loads due to their increasing penetration,which may result in negative effects such as voltage deviations,lines saturation,and power losses.Relationship and interaction among EVs,charging stations,and micro grid have to be considered in the next generation of smart grid.Therefore,the topic of smart charging has been the focus of many works where a wide range of control methods have been developed.As one of the bases of simulation,the EV charging behavior and characteristics have also become the focus of many studies.In this work,we review the charging behavior of EVs from the aspects of data,model,and control.We provide the links for most of the data sets reviewed in this work,based on which interested researchers can easily access these data for further investigation.展开更多
Suicide risk constitutes a complex set of interacting demographic, clinical, psychobiological and environmental variables. Impulsivity is a long-known risk factor for suicide attempts. However, research based on clear...Suicide risk constitutes a complex set of interacting demographic, clinical, psychobiological and environmental variables. Impulsivity is a long-known risk factor for suicide attempts. However, research based on clearer conceptual refinement in this area is imperative. One emerging field of study is that of decision-making. Impulsivity involves a failure of higher-order control, including decision-making. Using standardized operational definitions that take into consideration relevant aspects of impulsivity, including state- and trait-components and a deeper understanding of the process of decision-making in the suicidal mind, we may come a step closer to understanding suicidality and winning the fight in this scourge of human suffering.展开更多
In order to increase the accuracy of microscopic traffic flow simulation,two acceleration models are presented to simulate car-following behaviors of the lane-changing vehicle and following putative vehicle during the...In order to increase the accuracy of microscopic traffic flow simulation,two acceleration models are presented to simulate car-following behaviors of the lane-changing vehicle and following putative vehicle during the discretionary lanechanging preparation( DLCP) process, respectively. The proposed acceleration models can reflect vehicle interaction characteristics. Samples used for describing the starting point and the ending point of DLCP are extracted from a real NGSIM vehicle trajectory data set. The acceleration model for a lanechanging vehicle is supposed to be a linear acceleration model.The acceleration model for the following putative vehicle is constructed by referring to the optimal velocity model,in which optimal velocity is defined as a linear function of the velocity of putative leading vehicle. Similar calibration,a hypothesis test and parameter sensitivity analysis were conducted on the acceleration model of the lane-changing vehicle and following putative vehicle,respectively. The validation results of the two proposed models suggest that the training and testing errors are acceptable compared with similar works on calibrations for car following models. The parameter sensitivity analysis shows that the subtle observed error does not lead to severe variations of car-following behaviors of the lane-changing vehicle and following putative vehicle.展开更多
To define the diffusion behavior of harmful exhaust substances from diesel vehicles and support safety risk assessments of underground coal mines,we performed a multi-species coupling calculation of the emission and d...To define the diffusion behavior of harmful exhaust substances from diesel vehicles and support safety risk assessments of underground coal mines,we performed a multi-species coupling calculation of the emission and diffusion of harmful substances from a trackless rubber-wheel diesel vehicle.A computational fluid dynamics(CFD)model of the diffusion of harmful emissions was hence established and verified.From the perspective of risk analysis,the diffusion behavior and distribution of hazardous substances emitted by the diesel vehicle were studied under 4 different conditions;moreover,we identified areas characterized by hazardous levels of emissions.When the vehicle idled upwind in the roadway,high-risk areas formed behind and to the right of the vehicle:particularly high concentrations of pollutants were measured near the rear floor of the vehicle and within 5 m behind the vehicle.When the vehicle idled downwind,high-risk areas formed in front of it:particularly high concentrations of pollutants were measured near the floor and within 5 m from the front of the vehicle.In the above cases,the driver would not breathe highly polluted air and would be relatively safe.When the vehicle idled into the chamber,however,high-risk areas formed on both sides of the vehicle and near the upper roof.Forward entry of the vehicle caused a greater increase in the concentration of pollutants in the chamber and in the driver’s breathing zone compared with reverse entry.展开更多
Analyzing a vehicle’s abnormal behavior in surveillance videos is a challenging field,mainly due to the wide variety of anomaly cases and the complexity of surveillance videos.In this study,a novel intelligent vehicl...Analyzing a vehicle’s abnormal behavior in surveillance videos is a challenging field,mainly due to the wide variety of anomaly cases and the complexity of surveillance videos.In this study,a novel intelligent vehicle behavior analysis framework based on a digital twin is proposed.First,detecting vehicles based on deep learning is implemented,and Kalman filtering and feature matching are used to track vehicles.Subsequently,the tracked vehicle is mapped to a digital-twin virtual scene developed in the Unity game engine,and each vehicle’s behavior is tested according to the customized detection conditions set up in the scene.The stored behavior data can be used to reconstruct the scene again in Unity for a secondary analysis.The experimental results using real videos from traffic cameras illustrate that the detection rate of the proposed framework is close to that of the state-of-the-art abnormal event detection systems.In addition,the implementation and analysis process show the usability,generalization,and effectiveness of the proposed framework.展开更多
To prevent and reduce road traffic accidents and improve driver safety awareness and bad driving be-haviors,we propose a safety evaluation method for commercial vehicle driving behavior.Three driving style clas-sifica...To prevent and reduce road traffic accidents and improve driver safety awareness and bad driving be-haviors,we propose a safety evaluation method for commercial vehicle driving behavior.Three driving style clas-sification indexes were extracted using driving data from commercial vehicles and four primary and ten secondary safety evaluation indicators.Based on the stability of commercial vehicles transporting goods,the acceleration index is divided into three levels according to the statistical third quartile,and the evaluation expression of the safety index evaluation is established.Drivers were divided into conservative,moderate,and radical using K-means++.The weights corresponding to each index were calculated using a combination of the analytic hierarchy process(AHP)and criteria importance through intercriteria correlation(CRITIC),and the driving behavior scores of various drivers were calculated according to the safety index score standard.The established AHP-CRITIC safety evaluation model was verified using the actual driving behavior data of commercial vehicle drivers.The calculation results show that the proposed evaluation model can clearly distinguish between the types of drivers with different driving styles,verifying its rationality and validity.The evaluation results can provide a reference for transportation management departments and enterprises.展开更多
The micro modeling for electric vehicle and its solution were investigated. A new car-following model for electric vehicle was proposed based on the existing car-following models. The impacts of the electric vehicle&#...The micro modeling for electric vehicle and its solution were investigated. A new car-following model for electric vehicle was proposed based on the existing car-following models. The impacts of the electric vehicle's charging electricity were studied from the numerical perspective. The numerical results show that the electric vehicle's charging electricity will destroy the stability of uniform flow and produce some prominent queues and these traffic phenomena are directly related to the initial headway, the distance between two adjacent charging stations and the number of charging stations. The above results can help traffic engineer to choose the position of charging station and the electric vehicle's driver to adjust his/her driving behavior in the traffic system with charging station.展开更多
Driver errors contribute to more than 94% of traffic crashes. Automotive companies are striving to enhance their vehicles to eliminate driver errors and reduce the number of crashes. Various advanced features like lan...Driver errors contribute to more than 94% of traffic crashes. Automotive companies are striving to enhance their vehicles to eliminate driver errors and reduce the number of crashes. Various advanced features like lane departure warning (LDW), blind spot warning (BSW), over speed warning (OSW), forward collision warning (FCW), lane keep assist (LKA), adaptive cruise control (ACC), cooperative ACC (CACC), and automated emergency braking (AEB) are designed to assist with, or in some cases take over, certain driving maneuvers. They can be broadly categorized into advanced driver assistance system (ADAS) and automated features. Each of these advanced features focuses on addressing a particular task of driving, thereby, aiding the driver, influencing their behavior, and enhancing safety. Many vehicles with these advanced features are penetrating into the market, yet the total reported number of crashes has increased in recent years. This paper presents a systematic review of these advanced features on driver behavior and safety. The review is categorized into 1) survey and mathematical methods to assess driver behavior, 2) field test methods to assess driver behavior, 3) microsimulation methods to assess driver behavior, 4) driving simulator methods to assess driver behavior, and 5) driver understanding and the effectiveness of advanced features. It is followed by conclusions, knowledge gaps, and need for further research.展开更多
This paper explores the decision-making mechanism of the consuming behavior hidden behind the sudden popularity of the Oriental Selection Company in terms of the mental accounting theory.Firstly,according to the“Non-...This paper explores the decision-making mechanism of the consuming behavior hidden behind the sudden popularity of the Oriental Selection Company in terms of the mental accounting theory.Firstly,according to the“Non-alternative”characteristics of mental accounting,this paper expounds how the strategy of the bilingual live-streaming of Oriental Selection promoters stimulates consumers’desire to buy the advertised products and services whilst using the utility theory of mental accounting to analyze how Oriental Selection promoters improve consumers’acquisition utility and total utility.Secondly,we sum up the successful experiences of Oriental Selection:The live-streaming industry should apply the theory of mental accounting in effectively overcoming the shortcomings of the live-streamed marketing by stimulating consumers’desire and influencing their decision-making behavior through the streaming of content that triggers them to make purchases.This is achievable by abandoning the traditional ways of loudly urging consumers to buy goods.Finally,this paper puts forward some suggestions on how to use the mental accounting theory in promoting sustainable consumption and points out the prospects for Oriental Selection.展开更多
基金supported by the National Natural Science Foundation of China under Grant T2521006,Grant 62403483,Grant 62533021 and Grant U24A20279.
文摘Reinforcement learning(RL)has been widely studied as an efficient class of machine learning methods for adaptive optimal control under uncertainties.In recent years,the applications of RL in optimised decision-making and motion control of intelligent vehicles have received increasing attention.Due to the complex and dynamic operating environments of intelligent vehicles,it is necessary to improve the learning efficiency and generalisation ability of RL-based decision and control algorithms under different conditions.This survey systematically examines the theoretical foundations,algorithmic advancements and practical challenges of applying RL to intelligent vehicle systems operating in complex and dynamic environments.The major algorithm frameworks of RL are first introduced,and the recent advances in RL-based decision-making and control of intelligent vehicles are overviewed.In addition to self-learning decision and control approaches using state measurements,the developments of DRL methods for end-to-end driving control of intelligent vehicles are summarised.The open problems and directions for further research works are also discussed.
基金Supported by National Key R&D Program of China(Grant No.2022YFB2503203)National Natural Science Foundation of China(Grant No.U1964206).
文摘Decision-making of connected and automated vehicles(CAV)includes a sequence of driving maneuvers that improve safety and efficiency,characterized by complex scenarios,strong uncertainty,and high real-time requirements.Deep reinforcement learning(DRL)exhibits excellent capability of real-time decision-making and adaptability to complex scenarios,and generalization abilities.However,it is arduous to guarantee complete driving safety and efficiency under the constraints of training samples and costs.This paper proposes a Mixture of Expert method(MoE)based on Soft Actor-Critic(SAC),where the upper-level discriminator dynamically decides whether to activate the lower-level DRL expert or the heuristic expert based on the features of the input state.To further enhance the performance of the DRL expert,a buffer zone is introduced in the reward function,preemptively applying penalties before insecure situations occur.In order to minimize collision and off-road rates,the Intelligent Driver Model(IDM)and Minimizing Overall Braking Induced by Lane changes(MOBIL)strategy are designed by heuristic experts.Finally,tested in typical simulation scenarios,MOE shows a 13.75%improvement in driving efficiency compared with the traditional DRL method with continuous action space.It ensures high safety with zero collision and zero off-road rates while maintaining high adaptability.
基金Project supported by the National Natural Science Foundation of China (Grant No. 72174121)the Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning, and the Soft Science Research Project of Shanghai (Grant No. 22692112600)。
文摘Information plays a crucial role in guiding behavioral decisions during public health emergencies. Individuals communicate to acquire relevant knowledge about an epidemic, which influences their decisions to adopt protective measures.However, whether to disseminate specific information is also a behavioral decision. In light of this understanding, we develop a coupled information–vaccination–epidemic model to depict these co-evolutionary dynamics in a three-layer network. Negative information dissemination and vaccination are treated as separate decision-making processes. We then examine the combined effects of herd and risk motives on information dissemination and vaccination decisions through the lens of game theory. The microscopic Markov chain approach(MMCA) is used to describe the dynamic process and to derive the epidemic threshold. Simulation results indicate that increasing the cost of negative information dissemination and providing timely clarification can effectively control the epidemic. Furthermore, a phenomenon of diminishing marginal utility is observed as the cost of dissemination increases, suggesting that authorities do not need to overinvest in suppressing negative information. Conversely, reducing the cost of vaccination and increasing vaccine efficacy emerge as more effective strategies for outbreak control. In addition, we find that the scale of the epidemic is greater when the herd motive dominates behavioral decision-making. In conclusion, this study provides a new perspective for understanding the complexity of epidemic spreading by starting with the construction of different behavioral decisions.
基金supported by the National Natural Science Foundation of China(U20B2042).
文摘The exploration of unmanned aerial vehicle(UAV)swarm systems represents a focal point in the research of multiagent systems,with the investigation of their fission-fusion behavior holding significant theoretical and practical value.This review systematically examines the methods for fission-fusion of UAV swarms from the perspective of multi-agent systems,encompassing the composition of UAV swarm systems and fission-fusion conditions,information interaction mechanisms,and existing fission-fusion approaches.Firstly,considering the constituent units of UAV swarms and the conditions influencing fission-fusion,this paper categorizes and introduces the UAV swarm systems.It further examines the effects and limitations of fission-fusion methods across various categories and conditions.Secondly,a comprehensive analysis of the prevalent information interaction mechanisms within UAV swarms is conducted from the perspective of information interaction structures.The advantages and limitations of various mechanisms in the context of fission-fusion behaviors are summarized and synthesized.Thirdly,this paper consolidates the existing implementation research findings related to the fission-fusion behavior of UAV swarms,identifies unresolved issues in fission-fusion research,and discusses potential solutions.Finally,the paper concludes with a comprehensive summary and systematically outlines future research opportunities.
基金supported by the National Key R&D Program of China (2022YFB2502900)the National Natural Science Foundation of China (62088102, 61790563)。
文摘With the maturation of autonomous driving technology, the use of autonomous vehicles in a socially acceptable manner has become a growing demand of the public. Human-like autonomous driving is expected due to the impact of the differences between autonomous vehicles and human drivers on safety.Although human-like decision-making has become a research hotspot, a unified theory has not yet been formed, and there are significant differences in the implementation and performance of existing methods. This paper provides a comprehensive overview of human-like decision-making for autonomous vehicles. The following issues are discussed: 1) The intelligence level of most autonomous driving decision-making algorithms;2) The driving datasets and simulation platforms for testing and verifying human-like decision-making;3) The evaluation metrics of human-likeness;personalized driving;the application of decisionmaking in real traffic scenarios;and 4) The potential research direction of human-like driving. These research results are significant for creating interpretable human-like driving models and applying them in dynamic traffic scenarios. In the future, the combination of intuitive logical reasoning and hierarchical structure will be an important topic for further research. It is expected to meet the needs of human-like driving.
文摘Planning and decision-making technology at intersections is a comprehensive research problem in intelligent transportation systems due to the uncertainties caused by a variety of traffic participants.As wireless communication advances,vehicle infrastructure integrated algorithms designed for intersection planning and decision-making have received increasing attention.In this paper,the recent studies on the planning and decision-making technologies at intersections are primarily overviewed.The general planning and decision-making approaches are presented,which include graph-based approach,prediction base approach,optimization-based approach and machine learning based approach.Since connected autonomous vehicles(CAVs)is the future direction for the automated driving area,we summarized the evolving planning and decision-making methods based on vehicle infrastructure cooperative technologies.Both four-way signalized and unsignalized intersection(s)are investigated under purely automated driving traffic and mixed traffic.The study benefit from current strategies,protocols,and simulation tools to help researchers identify the presented approaches’challenges and determine the research gaps,and several remaining possible research problems that need to be solved in the future.
基金Project(9142020013)support by the National Natural Science Foundation of China
文摘The decision-making under complex urban environment become one of the key issues that restricts the rapid development of the autonomous vehicles. The difficulty in making timely and accurate decisions like human beings under highly dynamic traffic environment is a major challenge for autonomous driving. Car-following has been regarded as the simplest but essential driving behavior among driving tasks and has received extensive attention from researchers around the world. This work addresses this problem and proposes a novel method RSAN(rough-set artificial neural network) to learn the decisions from excellent human drivers. A virtual urban traffic environment was built by Pre Scan and driving simulation was conducted to obtain a broad set of relevant data such as experienced drivers' behavior data and surrounding vehicles' motion data. Then, rough set was used to preprocess these data to extract the key influential factors on decision and reduce the impact of uncertain data and noise data. And the car-following decision was learned by neural network in which key factor was the input and acceleration was the output. The result shows the better convergence speed and the better decision accuracy of RSAN than ANN. Findings of this work contributes to the empirical understanding of driver's decision-making process and it provides a theoretical basis for the study of car-following decision-making under complex and dynamic environment.
基金supported in part by the Start-Up Grant-Nanyang Assistant Professorship Grant of Nanyang Technological Universitythe Agency for Science,Technology and Research(A*STAR)under Advanced Manufacturing and Engineering(AME)Young Individual Research under Grant(A2084c0156)+2 种基金the MTC Individual Research Grant(M22K2c0079)the ANR-NRF Joint Grant(NRF2021-NRF-ANR003 HM Science)the Ministry of Education(MOE)under the Tier 2 Grant(MOE-T2EP50222-0002)。
文摘While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.
基金funded by the National Natural Science Foundation of China,grant numbers 52072214 and 52242213.
文摘With the development of intelligent vehicles and autonomous driving technology,the safety of vulnerable road user(VRU)in traffic has been more guaranteed,and many research achievements have been made in the key area of collision avoidance decision-making methods.In this paper,the knowledge mapping method is used to mine the available literature in depth,and it is found that the research focus has shifted from the traditional accident cause analysis to emerging deep learning and virtual reality technology.This paper summarizes research on the three core dimensions of environmental perception,behavior cognition and collision avoidance decision-making in intelligent vehicle systems.In terms of perception,accurate identification of pedestrians and cyclists in complex environments is a major demand for VRU perception;in terms of behavior cognition,the coupling of VRU intention identification and motion trajectory prediction and other multiple factors needs further research;in terms of decision-making,the intention identification and trajectory prediction of collision objects are not included in the risk assessment model,and there is a lack of exploration specifically for cyclists'collision risk.On this basis,this paper provides guidance for the improvement of traffic safety of contemporary VRU under the conditions of intelligent and connected transportation.
基金supported in part by the Beijing Municipal Science and Technology Project(No.Z191100007419010)Automobile Industry Joint Fund(No.U1764261)of the National Natural Science Foundation of China+1 种基金Shandong Key R&D Program(No.2020CXGC010118)Key Laboratory for New Technology Application of Road Conveyance of Jiangsu Province(No.BM20082061706)。
文摘Behavioral decision-making at urban intersections is one of the primary difficulties currently impeding the development of intelligent vehicle technology.The problem is that existing decision-making algorithms cannot effectively deal with complex random scenarios at urban intersections.To deal with this,a deep deterministic policy gradient(DDPG)decision-making algorithm(T-DDPG)based on a time-series Markov decision process(T-MDP)was developed,where the state was extended to collect observations from several consecutive frames.Experiments found that T-DDPG performed better in terms of convergence and generalizability in complex intersection scenarios than a traditional DDPG algorithm.Furthermore,model-agnostic meta-learning(MAML)was incorporated into the T-DDPG algorithm to improve the training method,leading to a decision algorithm(T-MAML-DDPG)based on a secondary gradient.Simulation experiments of intersection scenarios were carried out on the Gym-Carla platform to verify and compare the decision models.The results showed that T-MAML-DDPG was able to easily deal with the random states of complex intersection scenarios,which could improve traffic safety and efficiency.The above decision-making models based on meta-reinforcement learning are significant for enhancing the decision-making ability of intelligent vehicles at urban intersections.
文摘The results from a number of investigations and fire experiments are presented and analyzed in order to characterize the fire behavior of mining vehicles in underground hard rock mines. The analysis also includes fire safety and fire protection measures with respect to the mining vehicle fire behavior.Earlier studies on fires in underground hard rock mines have shown that vehicles or mobile equipment are the dominant sources of fire. A better knowledge about the fire behavior of vehicles in underground hard rock mines is therefore needed. During the analysis the direction and flow rate of the ventilation in a drift was found to have a significant impact on the fire behavior, causing for example flame tilt with rapid fire spread. The shielded sections of a vehicle will be less affected by the ventilation flow resulting in for example a decreased flame spread. It was also found that spray fires may result in considerable heat release rate but are generally of shorter duration and will not make any significant contributions to the overall heat release rate of the fully developed vehicle fire. The fire duration of a loader tire from a full-scale fire experiment was found to be at least 200 min and will largely determine the total fire duration of the vehicle. A different scenario with different conditions with for example a slower flame spread resulted in an even longer fire duration. The radiative and convective fraction will be a key factor when determining the heat transfer mechanisms involved in a fire and will vary from material to material.Calculations show that the radiative fraction of the tire fires on two mining vehicles is significantly lower than found in earlier experiments. The design and construction of the mining vehicle will have an important impact on the fire behavior and could possibly mitigate the consequences of a fire and allow fire personnel to extinguish a fire that otherwise would have had a too high heat release rate.
基金This work was supported in part by the National Key Research and Development Program of China(No.2016YFB0901900)the National Natural Science Foundation of China under grants(No.61673229)the 111 International Collaboration Project of China(No.BP2018006).
文摘The adoption and usage of electric vehicles(EVs)have emerged recently due to the increasing concerns on the greenhouse gas issues and energy revolution.As a part of the smart grid,EVs can provide valuable ancillary services beyond consumers of electricity.However,EVs are gradually considered as nonnegligible loads due to their increasing penetration,which may result in negative effects such as voltage deviations,lines saturation,and power losses.Relationship and interaction among EVs,charging stations,and micro grid have to be considered in the next generation of smart grid.Therefore,the topic of smart charging has been the focus of many works where a wide range of control methods have been developed.As one of the bases of simulation,the EV charging behavior and characteristics have also become the focus of many studies.In this work,we review the charging behavior of EVs from the aspects of data,model,and control.We provide the links for most of the data sets reviewed in this work,based on which interested researchers can easily access these data for further investigation.
文摘Suicide risk constitutes a complex set of interacting demographic, clinical, psychobiological and environmental variables. Impulsivity is a long-known risk factor for suicide attempts. However, research based on clearer conceptual refinement in this area is imperative. One emerging field of study is that of decision-making. Impulsivity involves a failure of higher-order control, including decision-making. Using standardized operational definitions that take into consideration relevant aspects of impulsivity, including state- and trait-components and a deeper understanding of the process of decision-making in the suicidal mind, we may come a step closer to understanding suicidality and winning the fight in this scourge of human suffering.
基金The National Basic Research Program of China(No.2012CB725405)the National Natural Science Foundation of China(No.51308115)+1 种基金the Science and Technology Demonstration Project of Ministry of Transport of China(No.2015364X16030)Fundamental Research Funds for the Central Universities,the Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYLX15_0153)
文摘In order to increase the accuracy of microscopic traffic flow simulation,two acceleration models are presented to simulate car-following behaviors of the lane-changing vehicle and following putative vehicle during the discretionary lanechanging preparation( DLCP) process, respectively. The proposed acceleration models can reflect vehicle interaction characteristics. Samples used for describing the starting point and the ending point of DLCP are extracted from a real NGSIM vehicle trajectory data set. The acceleration model for a lanechanging vehicle is supposed to be a linear acceleration model.The acceleration model for the following putative vehicle is constructed by referring to the optimal velocity model,in which optimal velocity is defined as a linear function of the velocity of putative leading vehicle. Similar calibration,a hypothesis test and parameter sensitivity analysis were conducted on the acceleration model of the lane-changing vehicle and following putative vehicle,respectively. The validation results of the two proposed models suggest that the training and testing errors are acceptable compared with similar works on calibrations for car following models. The parameter sensitivity analysis shows that the subtle observed error does not lead to severe variations of car-following behaviors of the lane-changing vehicle and following putative vehicle.
基金supported by the National Natural Science Foundation of China(Nos.52174191 and 51874191)the National Key R&D Program of China(No.2017YFC0805201)+1 种基金Qingchuang Science and Technology Project of Shandong Province University(No.2020KJD002)Taishan Scholars Project Special Funding(No.TS20190935).
文摘To define the diffusion behavior of harmful exhaust substances from diesel vehicles and support safety risk assessments of underground coal mines,we performed a multi-species coupling calculation of the emission and diffusion of harmful substances from a trackless rubber-wheel diesel vehicle.A computational fluid dynamics(CFD)model of the diffusion of harmful emissions was hence established and verified.From the perspective of risk analysis,the diffusion behavior and distribution of hazardous substances emitted by the diesel vehicle were studied under 4 different conditions;moreover,we identified areas characterized by hazardous levels of emissions.When the vehicle idled upwind in the roadway,high-risk areas formed behind and to the right of the vehicle:particularly high concentrations of pollutants were measured near the rear floor of the vehicle and within 5 m behind the vehicle.When the vehicle idled downwind,high-risk areas formed in front of it:particularly high concentrations of pollutants were measured near the floor and within 5 m from the front of the vehicle.In the above cases,the driver would not breathe highly polluted air and would be relatively safe.When the vehicle idled into the chamber,however,high-risk areas formed on both sides of the vehicle and near the upper roof.Forward entry of the vehicle caused a greater increase in the concentration of pollutants in the chamber and in the driver’s breathing zone compared with reverse entry.
文摘Analyzing a vehicle’s abnormal behavior in surveillance videos is a challenging field,mainly due to the wide variety of anomaly cases and the complexity of surveillance videos.In this study,a novel intelligent vehicle behavior analysis framework based on a digital twin is proposed.First,detecting vehicles based on deep learning is implemented,and Kalman filtering and feature matching are used to track vehicles.Subsequently,the tracked vehicle is mapped to a digital-twin virtual scene developed in the Unity game engine,and each vehicle’s behavior is tested according to the customized detection conditions set up in the scene.The stored behavior data can be used to reconstruct the scene again in Unity for a secondary analysis.The experimental results using real videos from traffic cameras illustrate that the detection rate of the proposed framework is close to that of the state-of-the-art abnormal event detection systems.In addition,the implementation and analysis process show the usability,generalization,and effectiveness of the proposed framework.
基金the Natural Science Foundation of Guangxi(No.2020GXNSFDA238011)the Open Fund Project of Guangxi Key Laboratory of Automation Detection Technology and Instrument(No.YQ21203)the Independent Research Project of Guangxi Key Laboratory of Auto Parts and Vehicle Technology(No.2020GKLACVTZZ02)。
文摘To prevent and reduce road traffic accidents and improve driver safety awareness and bad driving be-haviors,we propose a safety evaluation method for commercial vehicle driving behavior.Three driving style clas-sification indexes were extracted using driving data from commercial vehicles and four primary and ten secondary safety evaluation indicators.Based on the stability of commercial vehicles transporting goods,the acceleration index is divided into three levels according to the statistical third quartile,and the evaluation expression of the safety index evaluation is established.Drivers were divided into conservative,moderate,and radical using K-means++.The weights corresponding to each index were calculated using a combination of the analytic hierarchy process(AHP)and criteria importance through intercriteria correlation(CRITIC),and the driving behavior scores of various drivers were calculated according to the safety index score standard.The established AHP-CRITIC safety evaluation model was verified using the actual driving behavior data of commercial vehicle drivers.The calculation results show that the proposed evaluation model can clearly distinguish between the types of drivers with different driving styles,verifying its rationality and validity.The evaluation results can provide a reference for transportation management departments and enterprises.
基金Project(71271016)supported the National Natural Science Foundation of China
文摘The micro modeling for electric vehicle and its solution were investigated. A new car-following model for electric vehicle was proposed based on the existing car-following models. The impacts of the electric vehicle's charging electricity were studied from the numerical perspective. The numerical results show that the electric vehicle's charging electricity will destroy the stability of uniform flow and produce some prominent queues and these traffic phenomena are directly related to the initial headway, the distance between two adjacent charging stations and the number of charging stations. The above results can help traffic engineer to choose the position of charging station and the electric vehicle's driver to adjust his/her driving behavior in the traffic system with charging station.
文摘Driver errors contribute to more than 94% of traffic crashes. Automotive companies are striving to enhance their vehicles to eliminate driver errors and reduce the number of crashes. Various advanced features like lane departure warning (LDW), blind spot warning (BSW), over speed warning (OSW), forward collision warning (FCW), lane keep assist (LKA), adaptive cruise control (ACC), cooperative ACC (CACC), and automated emergency braking (AEB) are designed to assist with, or in some cases take over, certain driving maneuvers. They can be broadly categorized into advanced driver assistance system (ADAS) and automated features. Each of these advanced features focuses on addressing a particular task of driving, thereby, aiding the driver, influencing their behavior, and enhancing safety. Many vehicles with these advanced features are penetrating into the market, yet the total reported number of crashes has increased in recent years. This paper presents a systematic review of these advanced features on driver behavior and safety. The review is categorized into 1) survey and mathematical methods to assess driver behavior, 2) field test methods to assess driver behavior, 3) microsimulation methods to assess driver behavior, 4) driving simulator methods to assess driver behavior, and 5) driver understanding and the effectiveness of advanced features. It is followed by conclusions, knowledge gaps, and need for further research.
文摘This paper explores the decision-making mechanism of the consuming behavior hidden behind the sudden popularity of the Oriental Selection Company in terms of the mental accounting theory.Firstly,according to the“Non-alternative”characteristics of mental accounting,this paper expounds how the strategy of the bilingual live-streaming of Oriental Selection promoters stimulates consumers’desire to buy the advertised products and services whilst using the utility theory of mental accounting to analyze how Oriental Selection promoters improve consumers’acquisition utility and total utility.Secondly,we sum up the successful experiences of Oriental Selection:The live-streaming industry should apply the theory of mental accounting in effectively overcoming the shortcomings of the live-streamed marketing by stimulating consumers’desire and influencing their decision-making behavior through the streaming of content that triggers them to make purchases.This is achievable by abandoning the traditional ways of loudly urging consumers to buy goods.Finally,this paper puts forward some suggestions on how to use the mental accounting theory in promoting sustainable consumption and points out the prospects for Oriental Selection.
