Despite great achievement has been made in autonomous driving technologies,autonomous vehicles(AVs)still exhibit limitations in intelligence and lack social coordination,which is primarily attributed to their reliance...Despite great achievement has been made in autonomous driving technologies,autonomous vehicles(AVs)still exhibit limitations in intelligence and lack social coordination,which is primarily attributed to their reliance on single-agent technologies,neglecting inter-AV interactions.Current research on multi-agent autonomous driving(MAAD)predominantly focuses on either distributed individual learning or centralized cooperative learning,ignoring the mixed-motive nature of MAAD systems,where each agent is not only self-interested in reaching its own destination but also needs to coordinate with other traffic participants to enhance efficiency and safety.Inspired by the mixed motivation of human driving behavior and their learning process,we propose a novel mixed motivation driven social multi-agent reinforcement learning method for autonomous driving.In our method,a multi-agent reinforcement learning(MARL)algorithm,called Social Learning Policy Optimization(SoLPO),which takes advantage of both the individual and social learning paradigms,is proposed to empower agents to rapidly acquire self-interested policies and effectively learn socially coordinated behavior.Based on the proposed SoLPO,we further develop a mixed-motive MARL method for autonomous driving combined with a social reward integration module that can model the mixed-motive nature of MAAD systems by integrating individual and neighbor rewards into a social learning objective for improved learning speed and effectiveness.Experiments conducted on the MetaDrive simulator show that our proposed method outperforms existing state-of-the-art MARL approaches in metrics including the success rate,safety,and efficiency.More-over,the AVs trained by our method form coordinated social norms and exhibit human-like driving behavior,demonstrating a high degree of social coordination.展开更多
A diverse range of light and waves,spanning from near-infrared to ultraviolet,alongside ultrasound,have proven effective in propelling nanomotors.This review encapsulates the advancements in nanomotor research propell...A diverse range of light and waves,spanning from near-infrared to ultraviolet,alongside ultrasound,have proven effective in propelling nanomotors.This review encapsulates the advancements in nanomotor research propelled by waves of varying frequencies.It delves into the driving mechanisms and control methodologies of different nanomotor types,emphasizing the role of frequency.Nanomotors can be classified based on the frequency of the driving wave,encompassing ultraviolet light-driven,visible light-driven,near-infrared-driven,and ultrasounddriven variants.Each category corresponds to distinct propulsion mechanisms,including momentum transfer,photothermal effects,self-electrophoresis,and acoustic radiation force.Notably,visible light and near-infrared radiation predominantly propel momentum transfer nanomotors,while photothermal nanomotors are chiefly active within the infrared spectrum.Ultraviolet light drives most self-electrophoretic nanomotors,while ultrasound-driven nanomotors respond to acoustic radiation force.Furthermore,precise control over nanomotor speed and direction is achievable by adjusting the frequency of incident waves within a narrow range,modulating wave absorption rates.Lastly,this paper explores microwave nanomotors,an area yet to be reported,shedding light on potential driving mechanisms.展开更多
Landslides pose a formidable natural hazard across the Qinghai-Tibet Plateau(QTP),endangering both ecosystems and human life.Identifying the driving factors behind landslides and accurately assessing susceptibility ar...Landslides pose a formidable natural hazard across the Qinghai-Tibet Plateau(QTP),endangering both ecosystems and human life.Identifying the driving factors behind landslides and accurately assessing susceptibility are key to mitigating disaster risk.This study integrated multi-source historical landslide data with 15 predictive factors and used several machine learning models—Random Forest(RF),Gradient Boosting Regression Trees(GBRT),Extreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost)—to generate susceptibility maps.The Shapley additive explanation(SHAP)method was applied to quantify factor importance and explore their nonlinear effects.The results showed that:(1)CatBoost was the best-performing model(CA=0.938,AUC=0.980)in assessing landslide susceptibility,with altitude emerging as the most significant factor,followed by distance to roads and earthquake sites,precipitation,and slope;(2)the SHAP method revealed critical nonlinear thresholds,demonstrating that historical landslides were concentrated at mid-altitudes(1400-4000 m)and decreased markedly above 4000 m,with a parallel reduction in probability beyond 700 m from roads;and(3)landslide-prone areas,comprising 13%of the QTP,were concentrated in the southeastern and northeastern parts of the plateau.By integrating machine learning and SHAP analysis,this study revealed landslide hazard-prone areas and their driving factors,providing insights to support disaster management strategies and sustainable regional planning.展开更多
This article studies the problem of image segmentation-based semantic communication in autonomous driving.In real traffic scenes,the detecting of objects(e.g.,vehicles and pedestrians)is more important to guarantee dr...This article studies the problem of image segmentation-based semantic communication in autonomous driving.In real traffic scenes,the detecting of objects(e.g.,vehicles and pedestrians)is more important to guarantee driving safety,which is always ignored in existing works.Therefore,we propose a vehicular image segmentation-oriented semantic communication system,termed VIS-SemCom,focusing on transmitting and recovering image semantic features of high-important objects to reduce transmission redundancy.First,we develop a semantic codec based on Swin Transformer architecture,which expands the perceptual field thus improving the segmentation accuracy.To highlight the important objects'accuracy,we propose a multi-scale semantic extraction method by assigning the number of Swin Transformer blocks for diverse resolution semantic features.Also,an importance-aware loss incorporating important levels is devised,and an online hard example mining(OHEM)strategy is proposed to handle small sample issues in the dataset.Finally,experimental results demonstrate that the proposed VIS-SemCom can achieve a significant mean intersection over union(mIoU)performance in the SNR regions,a reduction of transmitted data volume by about 60%at 60%mIoU,and improve the segmentation accuracy of important objects,compared to baseline image communication.展开更多
With the continuous progress of automatic driving technology,automatic driving technology standards are gradually affecting the determination of criminal responsibility for traffic accidents in China.At present,the ch...With the continuous progress of automatic driving technology,automatic driving technology standards are gradually affecting the determination of criminal responsibility for traffic accidents in China.At present,the characteristics and tendency of China's automatic driving technology standards present the situation of high policy relevance coexisting with low normative binding,professionalism coexist with barriers,forefront coexist with ambiguity.Therefore,challenges are presented both theoretically and practically on the determination of criminal responsibility based on automatic driving technology standard..In this regard,the misunderstanding should be clarified in theory:The legal order under the automatic driving technology standard has constitutionality and systematic,and there is a balance between the frontier of automatic driving technology development and the lagging of criminal law.The automatic driving technology risk level system should be built to clarify the boundary of the effectiveness of criminal law norms,seeking fora breakthrough in the application of the establishment of a comprehensive judgment system of the risks and accidents and the system of evidence to prove the system,which clarifies the determination of criminal responsibility under the automatic driving technology standard.This essay hopes to pursue breakthroughs in the application-to establish a comprehensive judgment system of risks and accidents as well as an evidence proof system,so as to clarify the determination of criminal responsibility under automatic driving technology standards.展开更多
This study aimed to enhance the performance of semantic segmentation for autonomous driving by improving the 2DPASS model.Two novel improvements were proposed and implemented in this paper:dynamically adjusting the lo...This study aimed to enhance the performance of semantic segmentation for autonomous driving by improving the 2DPASS model.Two novel improvements were proposed and implemented in this paper:dynamically adjusting the loss function ratio and integrating an attention mechanism(CBAM).First,the loss function weights were adjusted dynamically.The grid search method is used for deciding the best ratio of 7:3.It gives greater emphasis to the cross-entropy loss,which resulted in better segmentation performance.Second,CBAM was applied at different layers of the 2Dencoder.Heatmap analysis revealed that introducing it after the second block of 2D image encoding produced the most effective enhancement of important feature representation.The training epoch was chosen for optimizing the best value by experiments,which improved model convergence and overall accuracy.To evaluate the proposed approach,experiments were conducted based on the SemanticKITTI database.The results showed that the improved model achieved higher segmentation accuracy by 64.31%,improved 11.47% in mIoU compared with the conventional 2DPASS model(baseline:52.84%).It was more effective at detecting small and distant objects and clearly identifying boundaries between different classes.Issues such as noise and variations in data distribution affected its accuracy,indicating the need for further refinement.Overall,the proposed improvements to the 2DPASS model demonstrated the potential to advance semantic segmentation technology and contributed to a more reliable perception of complex,dynamic environments in autonomous vehicles.Accurate segmentation enhances the vehicle’s ability to distinguish different objects,and this improvement directly supports safer navigation,robust decision-making,and efficient path planning,making it highly applicable to real-world deployment of autonomous systems in urban and highway settings.展开更多
Bottom-up and top-down endogenous automobile clusters exhibit distinct evolutionary traits and driving mechanisms,yet their comparative analysis remains understudied.Therefore,using Taizhou automobile industry cluster...Bottom-up and top-down endogenous automobile clusters exhibit distinct evolutionary traits and driving mechanisms,yet their comparative analysis remains understudied.Therefore,using Taizhou automobile industry cluster(TAIC)and Wuhu automobile industry cluster(WAIC)as cases,using historical statistical data and field interview data from the 1980s to 2023,combined with qualitative research methods of thematic and diachronic analysis,and quantitative research methods of social network analysis,we compare both endogenous automobile clusters’evolutionary traits and driving mechanisms.The results confirm both clusters undergo multi-scale spatial reconfiguration,organizational complexification,and intelligent networking technological transformation,yet diverge fundamentally:TAIC evolves through market-driven progressive expansion,transitioning from single to dual-core structures via private enterprise networking,with innovation following market-integrated logic and institutional thickness built on demand-driven evolution.Conversely,WAIC follows planned expansion,maintaining state-led hierarchical single-core stability through policy-driven breakthrough innovation and supply-dominated institutional construction-though both ultimately require formal-informal system synergy.Their coevolution is driven by dynamic interactions of path dependence(weakening influence),learning-innovation(strengthening influence),and relationship selection(inverted U-shaped trajectory),with divergent development paths rooted in TAIC’s grassroots self-organization genes versus WAIC’s top-level design genes,amplified by core enterprises’strategic disparities.The research findings can not only provide decision-making support for China’s industrial upgrading,but also contribute China’s insights to global economic governance.展开更多
In order to eliminate the meshing interference between the flexspline and circular spline after the taper deformation of the flexspline,the radial deformation difference method,major and minor axis fitting method,and ...In order to eliminate the meshing interference between the flexspline and circular spline after the taper deformation of the flexspline,the radial deformation difference method,major and minor axis fitting method,and ellipse fitting method are used to modify the tooth thickness of the flexspline and analyze the performance indexes such as the assembly stress,transmission error,and fatigue life.Firstly,the conjugate tooth profile is solved based on the quadruple-circular-arc tooth profile and modified kinematic method.Then,based on the finite element radial deformation of the flexspline,the principle and characteristics of three modification methods are analyzed,and the modification amount of each section of the flexspline tooth is calculated.Finally,the influence of the three modification methods on the performance of the harmonic drive is compared.The results show that the radial deformation difference method can initially determine the modification amount.The minimum static assembly stress is 406.22 MPa by the major and minor axis fitting method.The ellipse fitting method has the best dynamic performance,small transmission error fluctuation,a peak-to-peak value of 3.060",and a maximum fatigue life of 10^(7.558)cycles.展开更多
Understanding the scale-dependent dynamics of ecosystem services(ESs)and their socio-ecological drivers is essential for sustainable development.While many studies rely on static or single-scale approaches,this resear...Understanding the scale-dependent dynamics of ecosystem services(ESs)and their socio-ecological drivers is essential for sustainable development.While many studies rely on static or single-scale approaches,this research employs an integrated multi-temporal(2000–2020)and multi-scale(grid,county,and landscape levels)framework to investigate China’s Central Asian frontier,a representative dryland region.We quantified six ESs:habitat quality(HQ),net primary productivity(NPP),carbon sequestration(CS),water yield(WY),soil conservation(SC),and grain production(GP).Furthermore,we explored their interrelationships and identified the drivers influencing these services across different spatial scales.Our results revealed divergent ES trajectories:the declining HQ(−0.03 a^(−1)),NPP(−0.43 t km^(−2)a^(−1)),and SC(−3.41 t ha a^(−1))contrasted with rising WY(+2.33 mm a^(−1)),GP(+0.06 t km^(−2)a^(−1)),and CS(+0.02 t km^(−2)a^(−1)).The ES relationships were predominantly synergistic,while HQ–WY exhibited a trade-off(grid:−0.03;county:−0.02;landscape:−0.03)at temporal dimension but a synergistic relationship(grid:0.45;county:0.92;landscape:0.92)at spatial dimension.As spatial scale increased,SC–CS shifted from synergy(grid:0.001)to trade-off(county:−0.01;landscape:−0.005)in the temporal dimension,while all trade-off relationships in the spatial dimension were transformed into synergies.Key drivers of ES relationships varied with spatial scale:fraction vegetation coverage(FVC)and leaf area index(LAI)at the grid scale,annual precipitation(MAP)and soil moisture(SMA)at the county scale,and population density(POP),gross domestic product(GDP),and silt content(Silt)at the landscape scale.Based on the multi-scale findings,the study divides northern Xinjiang into Grain Priority Region,Ecological Priority Region,and Desert Containment Region,and proposes tailored management recommendations,offering a flexible framework for balancing ecological and socioeconomic needs.展开更多
To address soil salinization’s significant impact on human production and livelihood in arid regions,especially in high-salinity areas like salt lake regions,this study used multi-source remote sensing data to extrac...To address soil salinization’s significant impact on human production and livelihood in arid regions,especially in high-salinity areas like salt lake regions,this study used multi-source remote sensing data to extract 52 surface factors.Combined with measured soil salinity data,correlation analysis,multicollinearity testing,and projection importance analysis identified eight dominant factors.Subsequently,four machine learning algorithms were applied for modeling,and the optimal models were selected to study the spatiotemporal variation of soil salinization.The results indicate that the average soil salt content in the study area was 20.74%in 2020.LST(land surface temperature)can effectively identify areas with high salinity,such as saline-alkali land and salt flats.Among inversion models,the GBDT(gradient boosting decision trees)model demonstrated the highest predictive ability and minimal errors.The optimal inversion results revealed that soil salinization distribution was influenced by topographic elevation,distance from Qarhan Salt Lake,and river network density.Over the past 21 years,there was significant fluctuation in soil salinity observed in the concentrated area of grassland within the groundwater overflow zone,indicating strong variation in salinization.This fluctuation correlates with changes in groundwater levels in the groundwater overflow zone,which are influenced by temperature variations that determine the amount of snow and ice meltwater,and the precipitation in the upstream area.This study enhances understanding of soil salinization and its drivers in extremely arid salt lake regions.展开更多
The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the ...The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the uncertainties in train driving and operation,this paper analyzes the relationship between the safety of heavy-haul electric locomotive hauled trains and driving and operation.It studies the auxiliary intelligent driving safety operation control methods.Through K-means to identify the characteristics of drivers'driving manipulation,the hidden Markov model adaptively adjusts the train driving and operation sequence,and conducts auxiliary driving reconstruction for heavy-haul locomotive driving and operation.Based on the train running curve and the locomotive traction/braking characteristics,it smoothly controls the exertion of the traction/braking force of heavy-haul locomotives,thereby optimizing the driving safety control of heavy-haul trains in the vehicle-environment-track system.Finally,the train operation simulation and optimized driving verification are carried out by simulating some track sections.The results show that the proposed method can correct and pre-optimize driving operations,improving the smoothness of heavy-haul trains by approximately 10%.It verifies the effectiveness of the proposed train assisted driving control reconstruction method,facilitating the smooth and safe operation of heavy-haul trains.展开更多
Reliable detection of traffic signs and lights(TSLs)at long range and under varying illumination is essen-tial for improving the perception and safety of autonomous driving systems(ADS).Traditional object detection mo...Reliable detection of traffic signs and lights(TSLs)at long range and under varying illumination is essen-tial for improving the perception and safety of autonomous driving systems(ADS).Traditional object detection models often exhibit significant performance degradation in real-world environments characterized by high dynamic range and complex lighting conditions.To overcome these limitations,this research presents FED-YOLOv10s,an improved and lightweight object detection framework based on You Only look Once v10(YOLOv10).The proposed model integrates a C2f-Faster block derived from FasterNet to reduce parameters and floating-point operations,an Efficient Multiscale Attention(EMA)mechanism to improve TSL-invariant feature extraction,and a deformable Convolution Networks v4(DCNv4)module to enhance multiscale spatial adaptability.Experimental findings demonstrate that the proposed architecture achieves an optimal balance between computational efficiency and detection accuracy,attaining an F1-score of 91.8%,and mAP@0.5 of 95.1%,while reducing parameters to 8.13 million.Comparative analyses across multiple traffic sign detection benchmarks demonstrate that FED-YOLOv10s outperforms state-of-the-art models in precision,recall,and mAP.These results highlight FED-YOLOv10s as a robust,efficient,and deployable solution for intelligent traffic perception in ADS.展开更多
This study develops a contact performance-driven method for skiving face gear drives using a single cutter,eliminating the traditional need for separate cutters to reduce production costs and time.First,the mathematic...This study develops a contact performance-driven method for skiving face gear drives using a single cutter,eliminating the traditional need for separate cutters to reduce production costs and time.First,the mathematical models of the tooth flanks for the face gear drives are established based on the gear skiving processes.Then,load tooth contact analysis(LTCA)model is established to calculate the contact performance data.Next,a two-stage optimization model is employed to determine the optimal parameters of the cutting edge with improved contact performances.The effectiveness of this method is validated through simulations and rolling tests.Compared with the traditional method,the proposed method can machine both the face gear and its mating pinion with a single cutter.Simulation results show that the proposed method avoids tooth surface edge contact,with the maximum tooth surface contact stress reduced by 31.7%,the contact ratio decreases by 21.5%,and the transmission error increases by 22.3%.Rolling tests verify the consistency of tooth surface contact patterns between simulations and experiments.The proposed method provides a reference for the cutting edge design of skiving cutters for face gear pairs.展开更多
In real-world autonomous driving tests,unexpected events such as pedestrians or wild animals suddenly entering the driving path can occur.Conducting actual test drives under various weather conditions may also lead to...In real-world autonomous driving tests,unexpected events such as pedestrians or wild animals suddenly entering the driving path can occur.Conducting actual test drives under various weather conditions may also lead to dangerous situations.Furthermore,autonomous vehicles may operate abnormally in bad weather due to limitations of their sensors and GPS.Driving simulators,which replicate driving conditions nearly identical to those in the real world,can drastically reduce the time and cost required for market entry validation;consequently,they have become widely used.In this paper,we design a virtual driving test environment capable of collecting and verifying SiLS data under adverse weather conditions using multi-source images.The proposed method generates a virtual testing environment that incorporates various events,including weather,time of day,and moving objects,that cannot be easily verified in real-world autonomous driving tests.By setting up scenario-based virtual environment events,multi-source image analysis and verification using real-world DCUs(Data Concentrator Units)with V2X-Car edge cloud can effectively address risk factors that may arise in real-world situations.We tested and validated the proposed method with scenarios employing V2X communication and multi-source image analysis.展开更多
Ukraine,as one of the world’s largest agricultural producers and exporters,plays a critical role in global food security.It is essential to understand the spatiotemporal dynamics and drivers of productive cropland in...Ukraine,as one of the world’s largest agricultural producers and exporters,plays a critical role in global food security.It is essential to understand the spatiotemporal dynamics and drivers of productive cropland in Ukraine,particularly in the context of the 2022 Russia-Ukraine conflict.We provide the first comprehensive assessment of both conflict-and non-conflict-related factors that influenced the distribution and productivity of Ukraine’s cropland from 2013 to 2023.In addition,we propose a novel method using machine learning models to isolate the impact of conflict on cropland.Our findings reveal that,prior to the conflict,the spatial pattern of Ukraine’s mean cultivation rate was primarily shaped by natural factors—such as climate,soil properties,and elevation—whereas socio-economic factors(e.g.,GDP and population size)exerted a weaker influence.Interannual dynamics in productive cropland area were largely driven by climate variability.The onset of conflict in 2022 dramatically altered this landscape,with nearly half of the cropland grid cells experiencing a conflict-induced reduction.Notably,almost half of the interannual reduction in productive cropland in 2022 was attributed to climate change.Remarkably,in 2023,the return of displaced populations and favorable climatic conditions in many oblasts contributed to a positive trend in cropland reclamation.Despite this,the total area of productive cropland in 2023 remained below expected levels,due to ongoing conflict and localized droughts.Finally,we highlight the urgent need to adopt a two-pronged approach that addresses both the immediate impacts of conflict and the ongoing threats posed by climate change to ensure the resilience and sustainability of agricultural systems in post-conflict areas.展开更多
The development of human settlements(HS)in coastal cities is an integral component and a vital pathway toward building a strong marine power.It is also an essential requirement for achieving the coordinated developmen...The development of human settlements(HS)in coastal cities is an integral component and a vital pathway toward building a strong marine power.It is also an essential requirement for achieving the coordinated development of HS systems in these cities.In this study,we constructed an indicator system to analyze the coupling coordination degree(CCD)of HS systems in coastal cities in the Bohai Rim region of China(CCBRR).This study is based on five systems and employs methods such as the entropy weight method,CCD model,spatial trend surface analysis,and geographic detector to examine comprehensively the spatial and temporal patterns of CCD in 17 CCBRR during the period 2011–2022,as well as to explore their influencing factors.The findings are as follows:(1)Temporally,the CCD is high and exhibits a slow increasing trend,with distinct stage characteristics.(2)Spatially,the distribution of CCD reveals a“one core,many strengths”structural pattern.(3)Moreover,socioeconomic factors are the dominant force driving the CCD of the internal HS systems in the CCBRR.(4)Finally,we constructed a coupling coordination driving mechanism for HS in the CCBRR with the aim of providing scientific references and path choices for the high-quality and coordinated development of the CCBRR along with the implementation of the new quality productive forces regionalization.展开更多
Using path analysis, correlation analysis, partial correlation analysis and system dynamics method to study the driving force of cultivated land in Qinghai Lake Area, and using gradually regression analysis to establi...Using path analysis, correlation analysis, partial correlation analysis and system dynamics method to study the driving force of cultivated land in Qinghai Lake Area, and using gradually regression analysis to establish the driving force model of utilized change of cultivated land. Driving factors, action mechanism and process of utilized change of cultivated land were analyzed, and the differences during all factors were compared. The study provides some decision basis for sustainable utilization and management of land resources in Qinghai Lake Area.展开更多
Adverse weather has a considerable impact on the behavior of drivers,which puts vehicles and drivers in hazardous situations that can easily cause traffic accidents.This research examines how drivers'perceived ris...Adverse weather has a considerable impact on the behavior of drivers,which puts vehicles and drivers in hazardous situations that can easily cause traffic accidents.This research examines how drivers'perceived risk changes during car following under different adverse weather conditions by using driving simulation experiment.An expressway road scenario was built in a driving simulator.Eleven types of weather conditions,including clear sky,four levels of fog,four levels of rain and two levels of snow,were designed.Furthermore,to simulate the carfollowing behavior,three car-following situations were designed according to the motion of the lead car.Seven car-following indicators were extracted based on risk homeostasis theory.Then,the entropy weight method was used to integrate the selected indicators into an index to represent the drivers'perceived risk.Multiple linear regression was applied to measure the influence of adverse weather conditions on perceived risk,and the coefficients were considered as indicators.The results demonstrate that both the weather conditions and road type have significant effects on car-following behavior.Drivers'perceived risk tends to increase with the worsening weather conditions.Under conditions of extremely poor visibility,such as heavy dense fog,the measured drivers'perceived risk is low due to the difficulties in vehicle operation and limited visibility.展开更多
Driving a vehicle is one of the most common daily yet hazardous tasks. One of the great interests in recent research is to characterize a driver’s behaviors through the use of a driving simulation. Virtual reality te...Driving a vehicle is one of the most common daily yet hazardous tasks. One of the great interests in recent research is to characterize a driver’s behaviors through the use of a driving simulation. Virtual reality technology is now a promising alternative to the conventional driving simulations since it provides a more simple, secure and user-friendly environment for data collection. The driving simulator was used to assist novice drivers in learning how to drive in a very calm environment since the driving is not taking place on an actual road. This paper provides new insights regarding a driver’s behavior, techniques and adaptability within a driving simulation using virtual reality technology. The theoretical framework of this driving simulation has been designed using the Unity3D game engine (5.4.0f3 version) and programmed by the C# programming language. To make the driving simulation environment more realistic, the HTC Vive Virtual reality headset, powered by Steamvr, was used. 10 volunteers ranging from ages 19 - 37 participated in the virtual reality driving experiment. Matlab R2016b was used to analyze the data obtained from experiment. This research results are crucial for training drivers and obtaining insight on a driver’s behavior and characteristics. We have gathered diverse results for 10 drivers with different characteristics to be discussed in this study. Driving simulations are not easy to use for some users due to motion sickness, difficulties in adopting to a virtual environment. Furthermore, results of this study clearly show the performance of drivers is closely associated with individual’s behavior and adaptability to the driving simulator. Based on our findings, it can be said that with a VR-HMD (Virtual Reality-Head Mounted Display) Driving Simulator enables us to evaluate a driver’s “performance error”, “recognition errors” and “decision error”. All of which will allow researchers and further studies to potentially establish a method to increase driver safety or alleviate “driving errors”.展开更多
基金supported in part by the National Natural Science Foundation of China(62273135,62373356)the Natural Science Foundation of Hubei Province in China(2025AFA083)+1 种基金the Original Exploration Seed Project of Hubei University(202416403000001)the Postgraduate Education and Teaching Reform Research Project of Hubei University(1190017755).
文摘Despite great achievement has been made in autonomous driving technologies,autonomous vehicles(AVs)still exhibit limitations in intelligence and lack social coordination,which is primarily attributed to their reliance on single-agent technologies,neglecting inter-AV interactions.Current research on multi-agent autonomous driving(MAAD)predominantly focuses on either distributed individual learning or centralized cooperative learning,ignoring the mixed-motive nature of MAAD systems,where each agent is not only self-interested in reaching its own destination but also needs to coordinate with other traffic participants to enhance efficiency and safety.Inspired by the mixed motivation of human driving behavior and their learning process,we propose a novel mixed motivation driven social multi-agent reinforcement learning method for autonomous driving.In our method,a multi-agent reinforcement learning(MARL)algorithm,called Social Learning Policy Optimization(SoLPO),which takes advantage of both the individual and social learning paradigms,is proposed to empower agents to rapidly acquire self-interested policies and effectively learn socially coordinated behavior.Based on the proposed SoLPO,we further develop a mixed-motive MARL method for autonomous driving combined with a social reward integration module that can model the mixed-motive nature of MAAD systems by integrating individual and neighbor rewards into a social learning objective for improved learning speed and effectiveness.Experiments conducted on the MetaDrive simulator show that our proposed method outperforms existing state-of-the-art MARL approaches in metrics including the success rate,safety,and efficiency.More-over,the AVs trained by our method form coordinated social norms and exhibit human-like driving behavior,demonstrating a high degree of social coordination.
基金supported by the National Key Research and Development Program of China(2021YFA1401103)the National Natural Science Foundation of China(52473109,52073071)+3 种基金China Scholarship Council(CSC)(202306790056)Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX22_2301)111 Project(B23008)the Innovative Leading Talent Team supported by 2022Wuxi Taihu Talent Program(1096010241230120)。
文摘A diverse range of light and waves,spanning from near-infrared to ultraviolet,alongside ultrasound,have proven effective in propelling nanomotors.This review encapsulates the advancements in nanomotor research propelled by waves of varying frequencies.It delves into the driving mechanisms and control methodologies of different nanomotor types,emphasizing the role of frequency.Nanomotors can be classified based on the frequency of the driving wave,encompassing ultraviolet light-driven,visible light-driven,near-infrared-driven,and ultrasounddriven variants.Each category corresponds to distinct propulsion mechanisms,including momentum transfer,photothermal effects,self-electrophoresis,and acoustic radiation force.Notably,visible light and near-infrared radiation predominantly propel momentum transfer nanomotors,while photothermal nanomotors are chiefly active within the infrared spectrum.Ultraviolet light drives most self-electrophoretic nanomotors,while ultrasound-driven nanomotors respond to acoustic radiation force.Furthermore,precise control over nanomotor speed and direction is achievable by adjusting the frequency of incident waves within a narrow range,modulating wave absorption rates.Lastly,this paper explores microwave nanomotors,an area yet to be reported,shedding light on potential driving mechanisms.
基金The National Key Research and Development Program of China,No.2023YFC3206601。
文摘Landslides pose a formidable natural hazard across the Qinghai-Tibet Plateau(QTP),endangering both ecosystems and human life.Identifying the driving factors behind landslides and accurately assessing susceptibility are key to mitigating disaster risk.This study integrated multi-source historical landslide data with 15 predictive factors and used several machine learning models—Random Forest(RF),Gradient Boosting Regression Trees(GBRT),Extreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost)—to generate susceptibility maps.The Shapley additive explanation(SHAP)method was applied to quantify factor importance and explore their nonlinear effects.The results showed that:(1)CatBoost was the best-performing model(CA=0.938,AUC=0.980)in assessing landslide susceptibility,with altitude emerging as the most significant factor,followed by distance to roads and earthquake sites,precipitation,and slope;(2)the SHAP method revealed critical nonlinear thresholds,demonstrating that historical landslides were concentrated at mid-altitudes(1400-4000 m)and decreased markedly above 4000 m,with a parallel reduction in probability beyond 700 m from roads;and(3)landslide-prone areas,comprising 13%of the QTP,were concentrated in the southeastern and northeastern parts of the plateau.By integrating machine learning and SHAP analysis,this study revealed landslide hazard-prone areas and their driving factors,providing insights to support disaster management strategies and sustainable regional planning.
基金National Natural Science Foundation of China under Grants No.62171047,U22B2001,62271065,62001051Beijing Natural Science Foundation under Grant L223027BUPT Excellent Ph.D Students Foundation under Grants CX2021114。
文摘This article studies the problem of image segmentation-based semantic communication in autonomous driving.In real traffic scenes,the detecting of objects(e.g.,vehicles and pedestrians)is more important to guarantee driving safety,which is always ignored in existing works.Therefore,we propose a vehicular image segmentation-oriented semantic communication system,termed VIS-SemCom,focusing on transmitting and recovering image semantic features of high-important objects to reduce transmission redundancy.First,we develop a semantic codec based on Swin Transformer architecture,which expands the perceptual field thus improving the segmentation accuracy.To highlight the important objects'accuracy,we propose a multi-scale semantic extraction method by assigning the number of Swin Transformer blocks for diverse resolution semantic features.Also,an importance-aware loss incorporating important levels is devised,and an online hard example mining(OHEM)strategy is proposed to handle small sample issues in the dataset.Finally,experimental results demonstrate that the proposed VIS-SemCom can achieve a significant mean intersection over union(mIoU)performance in the SNR regions,a reduction of transmitted data volume by about 60%at 60%mIoU,and improve the segmentation accuracy of important objects,compared to baseline image communication.
基金The National Social Science Foundation Youth Project of China:Research on the collaborative govemance path of administrative law and criminal law against dangerous driving behaviors in the digital-intelligent society(25CFX108)。
文摘With the continuous progress of automatic driving technology,automatic driving technology standards are gradually affecting the determination of criminal responsibility for traffic accidents in China.At present,the characteristics and tendency of China's automatic driving technology standards present the situation of high policy relevance coexisting with low normative binding,professionalism coexist with barriers,forefront coexist with ambiguity.Therefore,challenges are presented both theoretically and practically on the determination of criminal responsibility based on automatic driving technology standard..In this regard,the misunderstanding should be clarified in theory:The legal order under the automatic driving technology standard has constitutionality and systematic,and there is a balance between the frontier of automatic driving technology development and the lagging of criminal law.The automatic driving technology risk level system should be built to clarify the boundary of the effectiveness of criminal law norms,seeking fora breakthrough in the application of the establishment of a comprehensive judgment system of the risks and accidents and the system of evidence to prove the system,which clarifies the determination of criminal responsibility under the automatic driving technology standard.This essay hopes to pursue breakthroughs in the application-to establish a comprehensive judgment system of risks and accidents as well as an evidence proof system,so as to clarify the determination of criminal responsibility under automatic driving technology standards.
文摘This study aimed to enhance the performance of semantic segmentation for autonomous driving by improving the 2DPASS model.Two novel improvements were proposed and implemented in this paper:dynamically adjusting the loss function ratio and integrating an attention mechanism(CBAM).First,the loss function weights were adjusted dynamically.The grid search method is used for deciding the best ratio of 7:3.It gives greater emphasis to the cross-entropy loss,which resulted in better segmentation performance.Second,CBAM was applied at different layers of the 2Dencoder.Heatmap analysis revealed that introducing it after the second block of 2D image encoding produced the most effective enhancement of important feature representation.The training epoch was chosen for optimizing the best value by experiments,which improved model convergence and overall accuracy.To evaluate the proposed approach,experiments were conducted based on the SemanticKITTI database.The results showed that the improved model achieved higher segmentation accuracy by 64.31%,improved 11.47% in mIoU compared with the conventional 2DPASS model(baseline:52.84%).It was more effective at detecting small and distant objects and clearly identifying boundaries between different classes.Issues such as noise and variations in data distribution affected its accuracy,indicating the need for further refinement.Overall,the proposed improvements to the 2DPASS model demonstrated the potential to advance semantic segmentation technology and contributed to a more reliable perception of complex,dynamic environments in autonomous vehicles.Accurate segmentation enhances the vehicle’s ability to distinguish different objects,and this improvement directly supports safer navigation,robust decision-making,and efficient path planning,making it highly applicable to real-world deployment of autonomous systems in urban and highway settings.
基金Under the auspices of National Natural Science Foundation of China(No.42571219)Key Project of Zhejiang Province Soft Science Research Plan(No.2023C25014)。
文摘Bottom-up and top-down endogenous automobile clusters exhibit distinct evolutionary traits and driving mechanisms,yet their comparative analysis remains understudied.Therefore,using Taizhou automobile industry cluster(TAIC)and Wuhu automobile industry cluster(WAIC)as cases,using historical statistical data and field interview data from the 1980s to 2023,combined with qualitative research methods of thematic and diachronic analysis,and quantitative research methods of social network analysis,we compare both endogenous automobile clusters’evolutionary traits and driving mechanisms.The results confirm both clusters undergo multi-scale spatial reconfiguration,organizational complexification,and intelligent networking technological transformation,yet diverge fundamentally:TAIC evolves through market-driven progressive expansion,transitioning from single to dual-core structures via private enterprise networking,with innovation following market-integrated logic and institutional thickness built on demand-driven evolution.Conversely,WAIC follows planned expansion,maintaining state-led hierarchical single-core stability through policy-driven breakthrough innovation and supply-dominated institutional construction-though both ultimately require formal-informal system synergy.Their coevolution is driven by dynamic interactions of path dependence(weakening influence),learning-innovation(strengthening influence),and relationship selection(inverted U-shaped trajectory),with divergent development paths rooted in TAIC’s grassroots self-organization genes versus WAIC’s top-level design genes,amplified by core enterprises’strategic disparities.The research findings can not only provide decision-making support for China’s industrial upgrading,but also contribute China’s insights to global economic governance.
文摘In order to eliminate the meshing interference between the flexspline and circular spline after the taper deformation of the flexspline,the radial deformation difference method,major and minor axis fitting method,and ellipse fitting method are used to modify the tooth thickness of the flexspline and analyze the performance indexes such as the assembly stress,transmission error,and fatigue life.Firstly,the conjugate tooth profile is solved based on the quadruple-circular-arc tooth profile and modified kinematic method.Then,based on the finite element radial deformation of the flexspline,the principle and characteristics of three modification methods are analyzed,and the modification amount of each section of the flexspline tooth is calculated.Finally,the influence of the three modification methods on the performance of the harmonic drive is compared.The results show that the radial deformation difference method can initially determine the modification amount.The minimum static assembly stress is 406.22 MPa by the major and minor axis fitting method.The ellipse fitting method has the best dynamic performance,small transmission error fluctuation,a peak-to-peak value of 3.060",and a maximum fatigue life of 10^(7.558)cycles.
基金National Natural Science Foundation of China,No.42377302Ministry of Science and Technology of the People’s Republic of China,No.2022XJKK0904State Key Laboratory of Soil and Sustainable Agriculture,No.SKLSSA25K03。
文摘Understanding the scale-dependent dynamics of ecosystem services(ESs)and their socio-ecological drivers is essential for sustainable development.While many studies rely on static or single-scale approaches,this research employs an integrated multi-temporal(2000–2020)and multi-scale(grid,county,and landscape levels)framework to investigate China’s Central Asian frontier,a representative dryland region.We quantified six ESs:habitat quality(HQ),net primary productivity(NPP),carbon sequestration(CS),water yield(WY),soil conservation(SC),and grain production(GP).Furthermore,we explored their interrelationships and identified the drivers influencing these services across different spatial scales.Our results revealed divergent ES trajectories:the declining HQ(−0.03 a^(−1)),NPP(−0.43 t km^(−2)a^(−1)),and SC(−3.41 t ha a^(−1))contrasted with rising WY(+2.33 mm a^(−1)),GP(+0.06 t km^(−2)a^(−1)),and CS(+0.02 t km^(−2)a^(−1)).The ES relationships were predominantly synergistic,while HQ–WY exhibited a trade-off(grid:−0.03;county:−0.02;landscape:−0.03)at temporal dimension but a synergistic relationship(grid:0.45;county:0.92;landscape:0.92)at spatial dimension.As spatial scale increased,SC–CS shifted from synergy(grid:0.001)to trade-off(county:−0.01;landscape:−0.005)in the temporal dimension,while all trade-off relationships in the spatial dimension were transformed into synergies.Key drivers of ES relationships varied with spatial scale:fraction vegetation coverage(FVC)and leaf area index(LAI)at the grid scale,annual precipitation(MAP)and soil moisture(SMA)at the county scale,and population density(POP),gross domestic product(GDP),and silt content(Silt)at the landscape scale.Based on the multi-scale findings,the study divides northern Xinjiang into Grain Priority Region,Ecological Priority Region,and Desert Containment Region,and proposes tailored management recommendations,offering a flexible framework for balancing ecological and socioeconomic needs.
基金The Second Tibetan Plateau Scientific Expedition and Research Program,No.2019QZKK0805-02The Innovation Team Foundation of Qinghai Office of Science and Technology,No.2022-ZJ-903+2 种基金The Comprehensive Development and Utilization of Salt Lake Resources,No.2023ZXKYA05100The Special Research Assistant of Chinese Academy of Sciences(Han Jinjun)The Kunlun Talented People of Qinghai Province,High-end Innovation and Entrepreneurship Talents,2023(Han Jinjun)。
文摘To address soil salinization’s significant impact on human production and livelihood in arid regions,especially in high-salinity areas like salt lake regions,this study used multi-source remote sensing data to extract 52 surface factors.Combined with measured soil salinity data,correlation analysis,multicollinearity testing,and projection importance analysis identified eight dominant factors.Subsequently,four machine learning algorithms were applied for modeling,and the optimal models were selected to study the spatiotemporal variation of soil salinization.The results indicate that the average soil salt content in the study area was 20.74%in 2020.LST(land surface temperature)can effectively identify areas with high salinity,such as saline-alkali land and salt flats.Among inversion models,the GBDT(gradient boosting decision trees)model demonstrated the highest predictive ability and minimal errors.The optimal inversion results revealed that soil salinization distribution was influenced by topographic elevation,distance from Qarhan Salt Lake,and river network density.Over the past 21 years,there was significant fluctuation in soil salinity observed in the concentrated area of grassland within the groundwater overflow zone,indicating strong variation in salinization.This fluctuation correlates with changes in groundwater levels in the groundwater overflow zone,which are influenced by temperature variations that determine the amount of snow and ice meltwater,and the precipitation in the upstream area.This study enhances understanding of soil salinization and its drivers in extremely arid salt lake regions.
基金Project(U2034211)supported by the National Natural Science Foundation of ChinaProject(20232ACE01013)supported by the Major Scientific and Technological Research and Development Special Project of Jiangxi Province,China。
文摘The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the uncertainties in train driving and operation,this paper analyzes the relationship between the safety of heavy-haul electric locomotive hauled trains and driving and operation.It studies the auxiliary intelligent driving safety operation control methods.Through K-means to identify the characteristics of drivers'driving manipulation,the hidden Markov model adaptively adjusts the train driving and operation sequence,and conducts auxiliary driving reconstruction for heavy-haul locomotive driving and operation.Based on the train running curve and the locomotive traction/braking characteristics,it smoothly controls the exertion of the traction/braking force of heavy-haul locomotives,thereby optimizing the driving safety control of heavy-haul trains in the vehicle-environment-track system.Finally,the train operation simulation and optimized driving verification are carried out by simulating some track sections.The results show that the proposed method can correct and pre-optimize driving operations,improving the smoothness of heavy-haul trains by approximately 10%.It verifies the effectiveness of the proposed train assisted driving control reconstruction method,facilitating the smooth and safe operation of heavy-haul trains.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,Saudi Arabia under Grant No.IPP:172-830-2025.
文摘Reliable detection of traffic signs and lights(TSLs)at long range and under varying illumination is essen-tial for improving the perception and safety of autonomous driving systems(ADS).Traditional object detection models often exhibit significant performance degradation in real-world environments characterized by high dynamic range and complex lighting conditions.To overcome these limitations,this research presents FED-YOLOv10s,an improved and lightweight object detection framework based on You Only look Once v10(YOLOv10).The proposed model integrates a C2f-Faster block derived from FasterNet to reduce parameters and floating-point operations,an Efficient Multiscale Attention(EMA)mechanism to improve TSL-invariant feature extraction,and a deformable Convolution Networks v4(DCNv4)module to enhance multiscale spatial adaptability.Experimental findings demonstrate that the proposed architecture achieves an optimal balance between computational efficiency and detection accuracy,attaining an F1-score of 91.8%,and mAP@0.5 of 95.1%,while reducing parameters to 8.13 million.Comparative analyses across multiple traffic sign detection benchmarks demonstrate that FED-YOLOv10s outperforms state-of-the-art models in precision,recall,and mAP.These results highlight FED-YOLOv10s as a robust,efficient,and deployable solution for intelligent traffic perception in ADS.
基金Project(2024YFB3410402)supported by the National Key R&D Program of ChinaProject(52075558)supported by the National Natural Science Foundation of China+2 种基金Project(2021RC3012)supported by the Science and Technology Innovation Program of Hunan Province,ChinaProject(2023CXQD050)supported by the Central South University Innovation-Driven Research Program,ChinaProject(CX20230255)supported by the Fundamental Research Funds for the Central Universities,China。
文摘This study develops a contact performance-driven method for skiving face gear drives using a single cutter,eliminating the traditional need for separate cutters to reduce production costs and time.First,the mathematical models of the tooth flanks for the face gear drives are established based on the gear skiving processes.Then,load tooth contact analysis(LTCA)model is established to calculate the contact performance data.Next,a two-stage optimization model is employed to determine the optimal parameters of the cutting edge with improved contact performances.The effectiveness of this method is validated through simulations and rolling tests.Compared with the traditional method,the proposed method can machine both the face gear and its mating pinion with a single cutter.Simulation results show that the proposed method avoids tooth surface edge contact,with the maximum tooth surface contact stress reduced by 31.7%,the contact ratio decreases by 21.5%,and the transmission error increases by 22.3%.Rolling tests verify the consistency of tooth surface contact patterns between simulations and experiments.The proposed method provides a reference for the cutting edge design of skiving cutters for face gear pairs.
基金supported by Institute of Information and Communications Technology Planning and Evaluation(IITP)grant funded by the Korean government(MSIT)(No.2019-0-01842,Artificial Intelligence Graduate School Program(GIST))supported by Korea Planning&Evaluation Institute of Industrial Technology(KEIT)grant funded by the Ministry of Trade,Industry&Energy(MOTIE,Republic of Korea)(RS-2025-25448249+1 种基金Automotive Industry Technology Development(R&D)Program)supported by the Regional Innovation System&Education(RISE)programthrough the(Gwangju RISE Center),funded by the Ministry of Education(MOE)and the Gwangju Metropolitan City,Republic of Korea(2025-RISE-05-001).
文摘In real-world autonomous driving tests,unexpected events such as pedestrians or wild animals suddenly entering the driving path can occur.Conducting actual test drives under various weather conditions may also lead to dangerous situations.Furthermore,autonomous vehicles may operate abnormally in bad weather due to limitations of their sensors and GPS.Driving simulators,which replicate driving conditions nearly identical to those in the real world,can drastically reduce the time and cost required for market entry validation;consequently,they have become widely used.In this paper,we design a virtual driving test environment capable of collecting and verifying SiLS data under adverse weather conditions using multi-source images.The proposed method generates a virtual testing environment that incorporates various events,including weather,time of day,and moving objects,that cannot be easily verified in real-world autonomous driving tests.By setting up scenario-based virtual environment events,multi-source image analysis and verification using real-world DCUs(Data Concentrator Units)with V2X-Car edge cloud can effectively address risk factors that may arise in real-world situations.We tested and validated the proposed method with scenarios employing V2X communication and multi-source image analysis.
基金supported in part by the National Natural Science Foundation of China(Grants No.41971284 and 42371321)the Key Research and Development Program of Hubei Province(Grant No.2025BAB024).
文摘Ukraine,as one of the world’s largest agricultural producers and exporters,plays a critical role in global food security.It is essential to understand the spatiotemporal dynamics and drivers of productive cropland in Ukraine,particularly in the context of the 2022 Russia-Ukraine conflict.We provide the first comprehensive assessment of both conflict-and non-conflict-related factors that influenced the distribution and productivity of Ukraine’s cropland from 2013 to 2023.In addition,we propose a novel method using machine learning models to isolate the impact of conflict on cropland.Our findings reveal that,prior to the conflict,the spatial pattern of Ukraine’s mean cultivation rate was primarily shaped by natural factors—such as climate,soil properties,and elevation—whereas socio-economic factors(e.g.,GDP and population size)exerted a weaker influence.Interannual dynamics in productive cropland area were largely driven by climate variability.The onset of conflict in 2022 dramatically altered this landscape,with nearly half of the cropland grid cells experiencing a conflict-induced reduction.Notably,almost half of the interannual reduction in productive cropland in 2022 was attributed to climate change.Remarkably,in 2023,the return of displaced populations and favorable climatic conditions in many oblasts contributed to a positive trend in cropland reclamation.Despite this,the total area of productive cropland in 2023 remained below expected levels,due to ongoing conflict and localized droughts.Finally,we highlight the urgent need to adopt a two-pronged approach that addresses both the immediate impacts of conflict and the ongoing threats posed by climate change to ensure the resilience and sustainability of agricultural systems in post-conflict areas.
基金National Natural Science Foundation of China,No.42201221,No.42471246Liaoning Province Natural Science Foundation Project,No.2023-MS-254+1 种基金Liaoning Province Social Science Planning Fund Project,No.L22CJY016Dalian Federation of Social Sciences,No.2022dlskzd037。
文摘The development of human settlements(HS)in coastal cities is an integral component and a vital pathway toward building a strong marine power.It is also an essential requirement for achieving the coordinated development of HS systems in these cities.In this study,we constructed an indicator system to analyze the coupling coordination degree(CCD)of HS systems in coastal cities in the Bohai Rim region of China(CCBRR).This study is based on five systems and employs methods such as the entropy weight method,CCD model,spatial trend surface analysis,and geographic detector to examine comprehensively the spatial and temporal patterns of CCD in 17 CCBRR during the period 2011–2022,as well as to explore their influencing factors.The findings are as follows:(1)Temporally,the CCD is high and exhibits a slow increasing trend,with distinct stage characteristics.(2)Spatially,the distribution of CCD reveals a“one core,many strengths”structural pattern.(3)Moreover,socioeconomic factors are the dominant force driving the CCD of the internal HS systems in the CCBRR.(4)Finally,we constructed a coupling coordination driving mechanism for HS in the CCBRR with the aim of providing scientific references and path choices for the high-quality and coordinated development of the CCBRR along with the implementation of the new quality productive forces regionalization.
基金Supported by The Regional Sustainable Development of the Qing-TibetPlateau(2004)~~
文摘Using path analysis, correlation analysis, partial correlation analysis and system dynamics method to study the driving force of cultivated land in Qinghai Lake Area, and using gradually regression analysis to establish the driving force model of utilized change of cultivated land. Driving factors, action mechanism and process of utilized change of cultivated land were analyzed, and the differences during all factors were compared. The study provides some decision basis for sustainable utilization and management of land resources in Qinghai Lake Area.
基金supported by the National Natural Science Foundation of China project(61672067)Science and Technology Program of Beijing(Z151100002115040)
文摘Adverse weather has a considerable impact on the behavior of drivers,which puts vehicles and drivers in hazardous situations that can easily cause traffic accidents.This research examines how drivers'perceived risk changes during car following under different adverse weather conditions by using driving simulation experiment.An expressway road scenario was built in a driving simulator.Eleven types of weather conditions,including clear sky,four levels of fog,four levels of rain and two levels of snow,were designed.Furthermore,to simulate the carfollowing behavior,three car-following situations were designed according to the motion of the lead car.Seven car-following indicators were extracted based on risk homeostasis theory.Then,the entropy weight method was used to integrate the selected indicators into an index to represent the drivers'perceived risk.Multiple linear regression was applied to measure the influence of adverse weather conditions on perceived risk,and the coefficients were considered as indicators.The results demonstrate that both the weather conditions and road type have significant effects on car-following behavior.Drivers'perceived risk tends to increase with the worsening weather conditions.Under conditions of extremely poor visibility,such as heavy dense fog,the measured drivers'perceived risk is low due to the difficulties in vehicle operation and limited visibility.
文摘Driving a vehicle is one of the most common daily yet hazardous tasks. One of the great interests in recent research is to characterize a driver’s behaviors through the use of a driving simulation. Virtual reality technology is now a promising alternative to the conventional driving simulations since it provides a more simple, secure and user-friendly environment for data collection. The driving simulator was used to assist novice drivers in learning how to drive in a very calm environment since the driving is not taking place on an actual road. This paper provides new insights regarding a driver’s behavior, techniques and adaptability within a driving simulation using virtual reality technology. The theoretical framework of this driving simulation has been designed using the Unity3D game engine (5.4.0f3 version) and programmed by the C# programming language. To make the driving simulation environment more realistic, the HTC Vive Virtual reality headset, powered by Steamvr, was used. 10 volunteers ranging from ages 19 - 37 participated in the virtual reality driving experiment. Matlab R2016b was used to analyze the data obtained from experiment. This research results are crucial for training drivers and obtaining insight on a driver’s behavior and characteristics. We have gathered diverse results for 10 drivers with different characteristics to be discussed in this study. Driving simulations are not easy to use for some users due to motion sickness, difficulties in adopting to a virtual environment. Furthermore, results of this study clearly show the performance of drivers is closely associated with individual’s behavior and adaptability to the driving simulator. Based on our findings, it can be said that with a VR-HMD (Virtual Reality-Head Mounted Display) Driving Simulator enables us to evaluate a driver’s “performance error”, “recognition errors” and “decision error”. All of which will allow researchers and further studies to potentially establish a method to increase driver safety or alleviate “driving errors”.
