Accurate identification of pedestrian crossing intention is the key to ensuring pedestrian safety,and the effective analysis of crossing behavior characteristics is one of the core requirements for the establishment o...Accurate identification of pedestrian crossing intention is the key to ensuring pedestrian safety,and the effective analysis of crossing behavior characteristics is one of the core requirements for the establishment of crossing intention recognition model.In this study,pedestrian intentions were classified as waiting for crossing and direct crossing,and the influences of the absence/presence of zebra stripes and the pedestrian age on pedestrian street-crossing intentions were compared based on 3600 effective samples extracted from a real road.The results demonstrate that the two factors have significant effects on the pedestrian crossing percentage,the waiting time,the accepted time to zebra stripes(TTZ),the rejected TTZ,and other characteristic parameters.Hence,to ameliorate the performance of the identification model,an ensemble learning method with a stacking framework is proposed for the identification of pedestrian waiting and direct crossing intentions.The distance between the pedestrian and the zebra stripes,the distance between the vehicle and the zebra stripes,the vehicle velocity,the pedestrian walking speed,the TTZ,the safe vehicle deceleration,waiting time,pedestrian age,and absence/presence of zebra stripes are employed as the inputs of the recognition model.The identification results indicate that the accuracy of the proposed model reaches 96.7%when pedestrians arrive at the road curb,which is the highest accuracy as compared to those of other models.The research conclusions could provide technical support for intelligent driving systems(IDSs)to more accurately recognize pedestrian street-crossing intentions,and can provide a basis for IDSs decision-making and interaction with pedestrian.展开更多
To study the intention behind pedestrian crossing behavior,this study extracts the trajectory data of vehicles and pedestrians from intersection videos.Based on the classic traffic conflict theory,TAdv is selected as ...To study the intention behind pedestrian crossing behavior,this study extracts the trajectory data of vehicles and pedestrians from intersection videos.Based on the classic traffic conflict theory,TAdv is selected as the primary indicator to describe the pedestrian-vehicle conflict,and pedestrian crossing events are defined to represent the interaction state of pedestrians and conflicting objects at a certain time in the crossing conflict.This paper proposes a Kalman filter-based crossing event recognition method,and then uses the topic model in natural language processing technology to mine pedestrian behavior"topics"behind different crossing events,and obtains an LDA-based pedestrian crossing description model.The results show that:on the whole,pedestrians have high requirements for the right of way and will not easily change their behavior.Pedestrians have higher speeds in conflicts with non-motorized vehicles than motorized vehicles and have greater expectations of victory in conflict games.Pedestrians often adopt conservative behaviors at low risk and choose other strategies after the conflict has evolved to a certain degree(high risk).There are two types of pedestrians with the highest demand for the right of way.One is the aggressive pedestrians,who will adopt aggressive rushing strategies when facing nonmotor vehicles while adopting the most conservative avoidance strategies when facing motor vehicles.The other is the pedestrians with small impacts from the outside world,whose crossing state will not easily be affected by vehicles and changes in traffic.展开更多
The successful deployment of autonomous vehicles(AVs)relies heavily on their ability to interact safely and effectively with other road users.External human–machine interfaces(eHMIs)have emerged as critical component...The successful deployment of autonomous vehicles(AVs)relies heavily on their ability to interact safely and effectively with other road users.External human–machine interfaces(eHMIs)have emerged as critical components in facilitating these interactions.Rigorous evaluation and testing of eHMIs are essential for realizing their intended safety and communication benefits.This study provides a comprehensive review of current eHMI research,focusing on their impact on road users’behavior and perceptions,as well as the methods used for evaluation.Key behavioral factors—such as eHMI modality,information type,location,vehicle kinematics,traffic environment,and user characteristics—are systematically reviewed and summarized.The influence of eHMIs on user perceptions is also explored through indicators such as perceived safety,comprehensibility,trust,cognitive load,and user experience.Despite notable advancements,several critical research gaps remain underexplored.Most studies focus on one-toone interactions,neglecting the complexities of mixed-traffic environments involving AVs,conventional human-driven vehicles,pedestrians,and cyclists.Current evaluation methods largely rely on virtual reality and Wizard-of-Oz experiments,which may fail to fully capture real-world dynamics.Additionally,subjective questionnaires,which are often used in these studies,do not guarantee high reproducibility of findings.Moreover,insufficient attention has been given to the synchronization of eHMI signals with vehicle kinematics.Furthermore,the absence of standardized evaluation frameworks limits cross-study comparability and the development of universally applicable eHMI solutions.To address these challenges,future research should prioritize the integration of naturalistic traffic scenarios,the adoption of objective and reproducible evaluation methods,the exploration of multimodal eHMI designs,and the development of standardized assessment protocols.These efforts are crucial for improving AV communication with diverse road users and ensuring safety in increasingly complex traffic ecosystems.展开更多
With the rapid development of intelligent and autonomous systems,such as wearable health monitoring and advanced manufacturing robots,there is a growing demand for the development of advanced,miniaturized smart sensor...With the rapid development of intelligent and autonomous systems,such as wearable health monitoring and advanced manufacturing robots,there is a growing demand for the development of advanced,miniaturized smart sensors and actuator systems.In this context,a single microdevice with hybrid functionality as both a sensor and actuator demonstrates excellent performance across diverse applications,holds significant promise.Herein,we present a proof-of-concept for a high-performance bi-directional Lorentz force magnetometer and actuator,implemented within a single microelectromechanical system(MEMS)device.Moreover,the device demonstrates insensitivity to magnetic fields,making it highly suitable for applications that require anti-crossing behavior in magnetic environments.The design is based on a clamped-guided curved microresonator connected to straight and V-shaped beams of micro-actuators.The operation of the proposed device relies on the flexibility to control the applied electrothermal excitation in different ways,offering smart thermal actuation and dynamic sensing mechanisms.Furthermore,the proposed technique allows tuning of the first symmetric mode,achieving either a high or low frequency shift based on input power levels.Hence,this study provides valuable insights for improving tunability in sensitivity and power for various actuation mechanisms.At atmospheric pressure and an input power of 19.5 mW,the device functions as a high-performance biaxial magnetic sensor with a sensitivity(S)of~36.58%T^(-1),an excellent linearity in the medium-to-high magnetic field range of±400 mT,and a minimum detectable field,Bmin of 0.83μT Hz^(-1).In contrast,it can be tuned as a magnetic-field-insensitive actuator(S=3.28%T^(-1))with a transversal displacement of~4μm,utilizing a negligible power of 43 mW.The diverse operation highlights its hybrid functionality as an actuator or high-performance sensor.These features,combined with the simplicity of fabrication and low cost,make the proposed microdevice highly promising for developing a three-axis magnetic sensor and actuator network system,as well as for various industrial applications.展开更多
Accurately reconstructing the intricate structure of natural organisms is the long-standing goal of 3-dimensional(3D)bioprinting.Projection-based 3D printing boasts the highest resolution-to-manufacturing time ratio a...Accurately reconstructing the intricate structure of natural organisms is the long-standing goal of 3-dimensional(3D)bioprinting.Projection-based 3D printing boasts the highest resolution-to-manufacturing time ratio among all 3D-printing technologies,rendering it a highly promising technique in this field.However,achieving standardized,high-fidelity,and high-resolution printing of composite structures using bioinks with diverse mechanical properties remains a marked challenge.The root of this challenge lies in the long-standing neglect of multi-material printability research.Multi-material printing is far from a simple physical assembly of different materials;rather,effective control of material interfaces is a crucial factor that governs print quality.The current research gap in this area substantively hinders the widespread application and rapid development of multi-material projection-based 3D bioprinting.To bridge this critical gap,we developed a multi-material projection-based 3D bioprinter capable of simultaneous printing with 6 materials.Building upon this,we established a fundamental framework for multi-material printability research,encompassing its core logic and essential process specifications.Furthermore,we clarified several critical issues,including the cross-linking behavior of multicomponent bioinks,mechanical mismatch and interface strength in soft-hard composite structures,the penetration behavior of viscous bioinks within hydrogel polymer networks,liquid entrapment and adsorption phenomena in porous heterogeneous structures,and error source analysis along with resolution evaluation in multi-material printing.This study offers a solid theoretical foundation and guidance for the quantitative assessment of multi-material projection-based 3D bioprinting,holding promise to advance the field toward higher precision and the reconstruction of more intricate biological structures.展开更多
基金supported by National Natural Science Foundation of China(52102451)China Postdoctoral Science Foundation(2021M700531)Fundamental Research Funds for the Central Universities(CHD 300102224205,300102224501,300102224302).
文摘Accurate identification of pedestrian crossing intention is the key to ensuring pedestrian safety,and the effective analysis of crossing behavior characteristics is one of the core requirements for the establishment of crossing intention recognition model.In this study,pedestrian intentions were classified as waiting for crossing and direct crossing,and the influences of the absence/presence of zebra stripes and the pedestrian age on pedestrian street-crossing intentions were compared based on 3600 effective samples extracted from a real road.The results demonstrate that the two factors have significant effects on the pedestrian crossing percentage,the waiting time,the accepted time to zebra stripes(TTZ),the rejected TTZ,and other characteristic parameters.Hence,to ameliorate the performance of the identification model,an ensemble learning method with a stacking framework is proposed for the identification of pedestrian waiting and direct crossing intentions.The distance between the pedestrian and the zebra stripes,the distance between the vehicle and the zebra stripes,the vehicle velocity,the pedestrian walking speed,the TTZ,the safe vehicle deceleration,waiting time,pedestrian age,and absence/presence of zebra stripes are employed as the inputs of the recognition model.The identification results indicate that the accuracy of the proposed model reaches 96.7%when pedestrians arrive at the road curb,which is the highest accuracy as compared to those of other models.The research conclusions could provide technical support for intelligent driving systems(IDSs)to more accurately recognize pedestrian street-crossing intentions,and can provide a basis for IDSs decision-making and interaction with pedestrian.
基金sponsored by the scientific research program of Science and Technology Commission of Shanghai Municipality[Grant No.19DZ1209102]sponsored by Guangzhou Airport Second Expressway Co.,Ltd.[Contract No.JGN-GCKY-01-001].
文摘To study the intention behind pedestrian crossing behavior,this study extracts the trajectory data of vehicles and pedestrians from intersection videos.Based on the classic traffic conflict theory,TAdv is selected as the primary indicator to describe the pedestrian-vehicle conflict,and pedestrian crossing events are defined to represent the interaction state of pedestrians and conflicting objects at a certain time in the crossing conflict.This paper proposes a Kalman filter-based crossing event recognition method,and then uses the topic model in natural language processing technology to mine pedestrian behavior"topics"behind different crossing events,and obtains an LDA-based pedestrian crossing description model.The results show that:on the whole,pedestrians have high requirements for the right of way and will not easily change their behavior.Pedestrians have higher speeds in conflicts with non-motorized vehicles than motorized vehicles and have greater expectations of victory in conflict games.Pedestrians often adopt conservative behaviors at low risk and choose other strategies after the conflict has evolved to a certain degree(high risk).There are two types of pedestrians with the highest demand for the right of way.One is the aggressive pedestrians,who will adopt aggressive rushing strategies when facing nonmotor vehicles while adopting the most conservative avoidance strategies when facing motor vehicles.The other is the pedestrians with small impacts from the outside world,whose crossing state will not easily be affected by vehicles and changes in traffic.
基金supported by the National Natural Science Foundation of China(Nos.52472360,72101128,and 72471070)the China Postdoctoral Science Foundation(No.2023M730560).
文摘The successful deployment of autonomous vehicles(AVs)relies heavily on their ability to interact safely and effectively with other road users.External human–machine interfaces(eHMIs)have emerged as critical components in facilitating these interactions.Rigorous evaluation and testing of eHMIs are essential for realizing their intended safety and communication benefits.This study provides a comprehensive review of current eHMI research,focusing on their impact on road users’behavior and perceptions,as well as the methods used for evaluation.Key behavioral factors—such as eHMI modality,information type,location,vehicle kinematics,traffic environment,and user characteristics—are systematically reviewed and summarized.The influence of eHMIs on user perceptions is also explored through indicators such as perceived safety,comprehensibility,trust,cognitive load,and user experience.Despite notable advancements,several critical research gaps remain underexplored.Most studies focus on one-toone interactions,neglecting the complexities of mixed-traffic environments involving AVs,conventional human-driven vehicles,pedestrians,and cyclists.Current evaluation methods largely rely on virtual reality and Wizard-of-Oz experiments,which may fail to fully capture real-world dynamics.Additionally,subjective questionnaires,which are often used in these studies,do not guarantee high reproducibility of findings.Moreover,insufficient attention has been given to the synchronization of eHMI signals with vehicle kinematics.Furthermore,the absence of standardized evaluation frameworks limits cross-study comparability and the development of universally applicable eHMI solutions.To address these challenges,future research should prioritize the integration of naturalistic traffic scenarios,the adoption of objective and reproducible evaluation methods,the exploration of multimodal eHMI designs,and the development of standardized assessment protocols.These efforts are crucial for improving AV communication with diverse road users and ensuring safety in increasingly complex traffic ecosystems.
基金supported by Khalifa University of Science and Technology(KU)under Award No.FSU-2023-028King Abdullah University of Science and Technology(KAUST).
文摘With the rapid development of intelligent and autonomous systems,such as wearable health monitoring and advanced manufacturing robots,there is a growing demand for the development of advanced,miniaturized smart sensors and actuator systems.In this context,a single microdevice with hybrid functionality as both a sensor and actuator demonstrates excellent performance across diverse applications,holds significant promise.Herein,we present a proof-of-concept for a high-performance bi-directional Lorentz force magnetometer and actuator,implemented within a single microelectromechanical system(MEMS)device.Moreover,the device demonstrates insensitivity to magnetic fields,making it highly suitable for applications that require anti-crossing behavior in magnetic environments.The design is based on a clamped-guided curved microresonator connected to straight and V-shaped beams of micro-actuators.The operation of the proposed device relies on the flexibility to control the applied electrothermal excitation in different ways,offering smart thermal actuation and dynamic sensing mechanisms.Furthermore,the proposed technique allows tuning of the first symmetric mode,achieving either a high or low frequency shift based on input power levels.Hence,this study provides valuable insights for improving tunability in sensitivity and power for various actuation mechanisms.At atmospheric pressure and an input power of 19.5 mW,the device functions as a high-performance biaxial magnetic sensor with a sensitivity(S)of~36.58%T^(-1),an excellent linearity in the medium-to-high magnetic field range of±400 mT,and a minimum detectable field,Bmin of 0.83μT Hz^(-1).In contrast,it can be tuned as a magnetic-field-insensitive actuator(S=3.28%T^(-1))with a transversal displacement of~4μm,utilizing a negligible power of 43 mW.The diverse operation highlights its hybrid functionality as an actuator or high-performance sensor.These features,combined with the simplicity of fabrication and low cost,make the proposed microdevice highly promising for developing a three-axis magnetic sensor and actuator network system,as well as for various industrial applications.
基金supported by the National Natural Science Foundation of China(grant numbers:52235007,T2121004,52325504,and 2021YFC2501800)the Key R&D Program of Zhejiang(2024SSYS0027).
文摘Accurately reconstructing the intricate structure of natural organisms is the long-standing goal of 3-dimensional(3D)bioprinting.Projection-based 3D printing boasts the highest resolution-to-manufacturing time ratio among all 3D-printing technologies,rendering it a highly promising technique in this field.However,achieving standardized,high-fidelity,and high-resolution printing of composite structures using bioinks with diverse mechanical properties remains a marked challenge.The root of this challenge lies in the long-standing neglect of multi-material printability research.Multi-material printing is far from a simple physical assembly of different materials;rather,effective control of material interfaces is a crucial factor that governs print quality.The current research gap in this area substantively hinders the widespread application and rapid development of multi-material projection-based 3D bioprinting.To bridge this critical gap,we developed a multi-material projection-based 3D bioprinter capable of simultaneous printing with 6 materials.Building upon this,we established a fundamental framework for multi-material printability research,encompassing its core logic and essential process specifications.Furthermore,we clarified several critical issues,including the cross-linking behavior of multicomponent bioinks,mechanical mismatch and interface strength in soft-hard composite structures,the penetration behavior of viscous bioinks within hydrogel polymer networks,liquid entrapment and adsorption phenomena in porous heterogeneous structures,and error source analysis along with resolution evaluation in multi-material printing.This study offers a solid theoretical foundation and guidance for the quantitative assessment of multi-material projection-based 3D bioprinting,holding promise to advance the field toward higher precision and the reconstruction of more intricate biological structures.
