The randomness and complexity of urban traffic scenes make it a difficult task for self-driving cars to detect drivable areas, Inspired by human driving behaviors, we propose a novel method of drivable area detection ...The randomness and complexity of urban traffic scenes make it a difficult task for self-driving cars to detect drivable areas, Inspired by human driving behaviors, we propose a novel method of drivable area detection for self-driving cars based on fusing pixel information from a monocular camera with spatial information from a light detection and ranging (LIDAR) scanner, Similar to the bijection of collineation, a new concept called co-point mapping, which is a bijection that maps points from the LIDAR scanner to points on the edge of the image segmentation, is introduced in the proposed method, Our method posi- tions candidate drivable areas through self-learning models based on the initial drivable areas that are obtained by fusing obstacle information with superpixels, In addition, a fusion of four features is applied in order to achieve a more robust performance, In particular, a feature called drivable degree (DD) is pro- posed to characterize the drivable degree of the LIDAR points, After the initial drivable area is characterized by the features obtained through self-learning, a Bayesian framework is utilized to calculate the final probability map of the drivable area, Our approach introduces no common hypothesis and requires no training steps; yet it yields a state-of-art performance when tested on the ROAD-KITTI benchmark, Experimental results demonstrate that the proposed method is a general and efficient approach for detecting drivable area.展开更多
To enhance the efficiency and accuracy of environmental perception for autonomous vehicles,we propose GDMNet,a unified multi-task perception network for autonomous driving,capable of performing drivable area segmentat...To enhance the efficiency and accuracy of environmental perception for autonomous vehicles,we propose GDMNet,a unified multi-task perception network for autonomous driving,capable of performing drivable area segmentation,lane detection,and traffic object detection.Firstly,in the encoding stage,features are extracted,and Generalized Efficient Layer Aggregation Network(GELAN)is utilized to enhance feature extraction and gradient flow.Secondly,in the decoding stage,specialized detection heads are designed;the drivable area segmentation head employs DySample to expand feature maps,the lane detection head merges early-stage features and processes the output through the Focal Modulation Network(FMN).Lastly,the Minimum Point Distance IoU(MPDIoU)loss function is employed to compute the matching degree between traffic object detection boxes and predicted boxes,facilitating model training adjustments.Experimental results on the BDD100K dataset demonstrate that the proposed network achieves a drivable area segmentation mean intersection over union(mIoU)of 92.2%,lane detection accuracy and intersection over union(IoU)of 75.3%and 26.4%,respectively,and traffic object detection recall and mAP of 89.7%and 78.2%,respectively.The detection performance surpasses that of other single-task or multi-task algorithm models.展开更多
Technological trends in the automotive industry toward a software-defined and autonomous vehicle require a reassessment of today’s vehicle development process.The validation process soaringly shapes after starting wi...Technological trends in the automotive industry toward a software-defined and autonomous vehicle require a reassessment of today’s vehicle development process.The validation process soaringly shapes after starting with hardware-in-the-loop testing of control units and reproducing real-world maneuvers and physical interaction chains.Here,the road-to-rig approach offers a vast potential to reduce validation time and costs significantly.The present research study investigates the maneuver reproduction of drivability phenomena at a powertrain test bed.Although drivability phenomena occur in the frequency range of most up to 30∙Hz,the design and characteristics substantially impact the test setup’s validity.By utilization of modal analysis,the influence of the test bed on the mechanical characteristic is shown.Furthermore,the sensitivity of the natural modes of each component,from either specimen or test bed site,is determined.In contrast,the uncertainty of the deployed measurement equipment also affects the validity.Instead of an accuracy class indication,we apply the ISO/IEC Guide 98 to the measurement equipment and the test bed setup to increase the fidelity of the validation task.In conclusion,the present paper contributes to a traceable validity determination of the road-to-rig approach by providing objective metrics and methods.展开更多
Driven piles are used in many geological environments as a practical and convenient structural component.Hence,the determination of the drivability of piles is actually of great importance in complex geotechnical appl...Driven piles are used in many geological environments as a practical and convenient structural component.Hence,the determination of the drivability of piles is actually of great importance in complex geotechnical applications.Conventional methods of predicting pile drivability often rely on simplified physicalmodels or empirical formulas,whichmay lack accuracy or applicability in complex geological conditions.Therefore,this study presents a practical machine learning approach,namely a Random Forest(RF)optimized by Bayesian Optimization(BO)and Particle Swarm Optimization(PSO),which not only enhances prediction accuracy but also better adapts to varying geological environments to predict the drivability parameters of piles(i.e.,maximumcompressive stress,maximum tensile stress,and blow per foot).In addition,support vector regression,extreme gradient boosting,k nearest neighbor,and decision tree are also used and applied for comparison purposes.In order to train and test these models,among the 4072 datasets collected with 17model inputs,3258 datasets were randomly selected for training,and the remaining 814 datasets were used for model testing.Lastly,the results of these models were compared and evaluated using two performance indices,i.e.,the root mean square error(RMSE)and the coefficient of determination(R2).The results indicate that the optimized RF model achieved lower RMSE than other prediction models in predicting the three parameters,specifically 0.044,0.438,and 0.146;and higher R^(2) values than other implemented techniques,specifically 0.966,0.884,and 0.977.In addition,the sensitivity and uncertainty of the optimized RF model were analyzed using Sobol sensitivity analysis and Monte Carlo(MC)simulation.It can be concluded that the optimized RF model could be used to predict the performance of the pile,and it may provide a useful reference for solving some problems under similar engineering conditions.展开更多
Piles are long, slender structural elements used to transfer the loads from the superstructure through weak strata onto stiffer soils or rocks. For driven piles, the impact of the piling hammer induces compression and...Piles are long, slender structural elements used to transfer the loads from the superstructure through weak strata onto stiffer soils or rocks. For driven piles, the impact of the piling hammer induces compression and tension stresses in the piles. Hence, an important design consideration is to check that the strength of the pile is sufficient to resist the stresses caused by the impact of the pile hammer. Due to its complexity, pile drivability lacks a precise analytical solution with regard to the phenomena involved.In situations where measured data or numerical hypothetical results are available, neural networks stand out in mapping the nonlinear interactions and relationships between the system’s predictors and dependent responses. In addition, unlike most computational tools, no mathematical relationship assumption between the dependent and independent variables has to be made. Nevertheless, neural networks have been criticized for their long trial-and-error training process since the optimal configuration is not known a priori. This paper investigates the use of a fairly simple nonparametric regression algorithm known as multivariate adaptive regression splines（MARS）, as an alternative to neural networks, to approximate the relationship between the inputs and dependent response, and to mathematically interpret the relationship between the various parameters. In this paper, the Back propagation neural network（BPNN） and MARS models are developed for assessing pile drivability in relation to the prediction of the Maximum compressive stresses（MCS）, Maximum tensile stresses（MTS）, and Blow per foot（BPF）. A database of more than four thousand piles is utilized for model development and comparative performance between BPNN and MARS predictions.展开更多
For a single-motor parallel hybrid electric vehicle, during mode transitions （especially the transition from electric drive mode to engine/parallel drive mode, which requires the clutch engagement）, the drivability ...For a single-motor parallel hybrid electric vehicle, during mode transitions （especially the transition from electric drive mode to engine/parallel drive mode, which requires the clutch engagement）, the drivability of the vehicle will be signifi- cantly affected by a clutch torque induced disturbance, driveline oscillations and jerks which can occur without adequate controls. To improve vehicle drivability during mode transitions for a single-motor parallel hybrid electric vehicle, two controllers are proposed. The first controller is the engine-side controller for engine cranking/starting and speed synchronization. The second controller is the motor-side controller for achieving a smooth mode transition with reduced driveline oscillations and jerks under the clutch torque induced disturbance and system uncertainties. The controllers are all composed of a feed-forward control and a robust feedback control. The robust controllers are designed by using the mu synthesis method. In the design process, control- oriented system models that take account of various parameter uncertainties and un-modeled dynamics are used. The results of the simulation demonstrate the effectiveness of the proposed control algorithms.展开更多
During shift,power flow is not interrupted in powertrains equipped with continuously variable transmission（CVT）.When hard acceleration is commanded,engine speed will flare and corresponding torque will be consumed,w...During shift,power flow is not interrupted in powertrains equipped with continuously variable transmission（CVT）.When hard acceleration is commanded,engine speed will flare and corresponding torque will be consumed,which leads to a drop in vehicle drive torque and also the vehicle acceleration.This is the reason why CVT vehicles have poor drivability during hard acceleration maneuver.Conventional method such as torque compensation doesn＇t always work due to the limited backup torque of engine.According to this,means to evaluate the drivability of CVT vehicles are studied,affect factors of drivability are analyzed in detail.Hard acceleration process of CVT vehicle is studied by theoretical analysis,based on which engine torque and ratio change rate of CVT are identified as two key control parameters that decide the drivability of CVT vehicles during hard acceleration maneuver.Therefore,a control strategy based on restricting the change rate of CVT ratio together with torque compensation is proposed,and two different algorithms to establish the limitation of ratio change rate are proposed.These two algorithms are simulated and compared with each other,results indicate that drop of vehicle acceleration is eliminated evidently by limit the change rate of CVT ratio,but small ratio change rate also results in a longer time to finish the accelerate process,an algorithm to decide a proper ratio change rate is needed in order to tune these different characteristics.In order to get better control effects,a new fuzzy logic based algorithm is proposed to decide a proper ratio change rate during kick down conditions,simulation and experiment results indicate that,the amount of vehicle acceleration decrease is reduced from about 1 m/s2 to almost 0,in the mean time the accelerate process only delayed for about 0.3 s.The proposed control strategy and algorithm can effectively tune the characteristics of CVT equipped vehicle during kick down conditions.展开更多
Pile drivability is a key problem during the stage of design and construction installation of pile foundations. The solution to the one dimensional wave equation was used to determine the impact force at the top of a...Pile drivability is a key problem during the stage of design and construction installation of pile foundations. The solution to the one dimensional wave equation was used to determine the impact force at the top of a concrete pile for a given ram mass, cushion stiffness, and pile impedance. The kinematic equation of pile toe was established and solved based on wave equation theory. The movements of the pile top and pile toe were presented, which clearly showed the dynamic displacement, including rebound and penetration of pile top and toe. A parametric study was made with a full range of practical values of ram weight, cushion stiffness, dropheight, and pile impedance. Suggestions for optimizing the parameters were also presented. Comparisons between the results obtained by the present solution and in-situ measurements indicated the reliability and validity of the method.展开更多
Desktop calibration of automatic transmission(AT) is a method which can reduce cost, enhance efficiency and shorten the development periods of a vehicle effectively. We primary introduced the principle and approach of...Desktop calibration of automatic transmission(AT) is a method which can reduce cost, enhance efficiency and shorten the development periods of a vehicle effectively. We primary introduced the principle and approach of desktop calibration of AT based on the condition of coupling characteristics between engine and torque converter and obtained right point exactly. It is shown to agree with experimental measurements reasonably well. It was used in different applications abroad based on AT technology and achieved a good performance of the vehicle compared with traditional AT technology which primary focuses on the drivability, performance and fuel consumption.展开更多
Field measurements of driving resistances and heights of soil core during driving were made offshore and onshore of steel pipe piles. Measured data show that the height of soil core varies differently for piles of dif...Field measurements of driving resistances and heights of soil core during driving were made offshore and onshore of steel pipe piles. Measured data show that the height of soil core varies differently for piles of different diameters with the increase of penetration. Dynamic plugging could be assumed never to occur for steel pipe piles with diameters over 900 mm. Soil resistances at the time of continuous driving (SRD) are back analyzed from blow counts with an empirical distribution of resistances suppported by many early dynamic measurements. A method of predicting SRD is finally suggested.展开更多
A panoptic driving perception system is an essential part of autonomous driving.A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving.We present a panopti...A panoptic driving perception system is an essential part of autonomous driving.A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving.We present a panoptic driving perception network(you only look once for panoptic(YOLOP))to perform traffic object detection,drivable area segmentation,and lane detection simultaneously.It is composed of one encoder for feature extraction and three decoders to handle the specific tasks.Our model performs extremely well on the challenging BDD100K dataset,achieving state-of-the-art on all three tasks in terms of accuracy and speed.Besides,we verify the effectiveness of our multi-task learning model for joint training via ablative studies.To our best knowledge,this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS),and maintain excellent accuracy.To facilitate further research,the source codes and pre-trained models are released at https://github.com/hustvl/YOLOP.展开更多
Driving space for autonomous vehicles(AVs)is a simplified representation of real driving environments that helps facilitate driving decision processes.Existing literatures present numerous methods for constructing dri...Driving space for autonomous vehicles(AVs)is a simplified representation of real driving environments that helps facilitate driving decision processes.Existing literatures present numerous methods for constructing driving spaces,which is a fundamental step in AV development.This study reviews the existing researches to gain a more systematic understanding of driving space and focuses on two questions:how to reconstruct the driving environment,and how to make driving decisions within the constructed driving space.Furthermore,the advantages and disadvantages of different types of driving space are analyzed.The study provides further understanding of the relationship between perception and decision-making and gives insight into direction of future research on driving space of AVs.展开更多
基金This research was partially supported by the National Natural Science Foundation of China (61773312), the National Key Research and Development Plan (2017YFC0803905), and the Program of Introducing Talents of Discipline to University (B13043).
文摘The randomness and complexity of urban traffic scenes make it a difficult task for self-driving cars to detect drivable areas, Inspired by human driving behaviors, we propose a novel method of drivable area detection for self-driving cars based on fusing pixel information from a monocular camera with spatial information from a light detection and ranging (LIDAR) scanner, Similar to the bijection of collineation, a new concept called co-point mapping, which is a bijection that maps points from the LIDAR scanner to points on the edge of the image segmentation, is introduced in the proposed method, Our method posi- tions candidate drivable areas through self-learning models based on the initial drivable areas that are obtained by fusing obstacle information with superpixels, In addition, a fusion of four features is applied in order to achieve a more robust performance, In particular, a feature called drivable degree (DD) is pro- posed to characterize the drivable degree of the LIDAR points, After the initial drivable area is characterized by the features obtained through self-learning, a Bayesian framework is utilized to calculate the final probability map of the drivable area, Our approach introduces no common hypothesis and requires no training steps; yet it yields a state-of-art performance when tested on the ROAD-KITTI benchmark, Experimental results demonstrate that the proposed method is a general and efficient approach for detecting drivable area.
文摘To enhance the efficiency and accuracy of environmental perception for autonomous vehicles,we propose GDMNet,a unified multi-task perception network for autonomous driving,capable of performing drivable area segmentation,lane detection,and traffic object detection.Firstly,in the encoding stage,features are extracted,and Generalized Efficient Layer Aggregation Network(GELAN)is utilized to enhance feature extraction and gradient flow.Secondly,in the decoding stage,specialized detection heads are designed;the drivable area segmentation head employs DySample to expand feature maps,the lane detection head merges early-stage features and processes the output through the Focal Modulation Network(FMN).Lastly,the Minimum Point Distance IoU(MPDIoU)loss function is employed to compute the matching degree between traffic object detection boxes and predicted boxes,facilitating model training adjustments.Experimental results on the BDD100K dataset demonstrate that the proposed network achieves a drivable area segmentation mean intersection over union(mIoU)of 92.2%,lane detection accuracy and intersection over union(IoU)of 75.3%and 26.4%,respectively,and traffic object detection recall and mAP of 89.7%and 78.2%,respectively.The detection performance surpasses that of other single-task or multi-task algorithm models.
文摘Technological trends in the automotive industry toward a software-defined and autonomous vehicle require a reassessment of today’s vehicle development process.The validation process soaringly shapes after starting with hardware-in-the-loop testing of control units and reproducing real-world maneuvers and physical interaction chains.Here,the road-to-rig approach offers a vast potential to reduce validation time and costs significantly.The present research study investigates the maneuver reproduction of drivability phenomena at a powertrain test bed.Although drivability phenomena occur in the frequency range of most up to 30∙Hz,the design and characteristics substantially impact the test setup’s validity.By utilization of modal analysis,the influence of the test bed on the mechanical characteristic is shown.Furthermore,the sensitivity of the natural modes of each component,from either specimen or test bed site,is determined.In contrast,the uncertainty of the deployed measurement equipment also affects the validity.Instead of an accuracy class indication,we apply the ISO/IEC Guide 98 to the measurement equipment and the test bed setup to increase the fidelity of the validation task.In conclusion,the present paper contributes to a traceable validity determination of the road-to-rig approach by providing objective metrics and methods.
基金supported by the National Science Foundation of China(42107183).
文摘Driven piles are used in many geological environments as a practical and convenient structural component.Hence,the determination of the drivability of piles is actually of great importance in complex geotechnical applications.Conventional methods of predicting pile drivability often rely on simplified physicalmodels or empirical formulas,whichmay lack accuracy or applicability in complex geological conditions.Therefore,this study presents a practical machine learning approach,namely a Random Forest(RF)optimized by Bayesian Optimization(BO)and Particle Swarm Optimization(PSO),which not only enhances prediction accuracy but also better adapts to varying geological environments to predict the drivability parameters of piles(i.e.,maximumcompressive stress,maximum tensile stress,and blow per foot).In addition,support vector regression,extreme gradient boosting,k nearest neighbor,and decision tree are also used and applied for comparison purposes.In order to train and test these models,among the 4072 datasets collected with 17model inputs,3258 datasets were randomly selected for training,and the remaining 814 datasets were used for model testing.Lastly,the results of these models were compared and evaluated using two performance indices,i.e.,the root mean square error(RMSE)and the coefficient of determination(R2).The results indicate that the optimized RF model achieved lower RMSE than other prediction models in predicting the three parameters,specifically 0.044,0.438,and 0.146;and higher R^(2) values than other implemented techniques,specifically 0.966,0.884,and 0.977.In addition,the sensitivity and uncertainty of the optimized RF model were analyzed using Sobol sensitivity analysis and Monte Carlo(MC)simulation.It can be concluded that the optimized RF model could be used to predict the performance of the pile,and it may provide a useful reference for solving some problems under similar engineering conditions.
文摘Piles are long, slender structural elements used to transfer the loads from the superstructure through weak strata onto stiffer soils or rocks. For driven piles, the impact of the piling hammer induces compression and tension stresses in the piles. Hence, an important design consideration is to check that the strength of the pile is sufficient to resist the stresses caused by the impact of the pile hammer. Due to its complexity, pile drivability lacks a precise analytical solution with regard to the phenomena involved.In situations where measured data or numerical hypothetical results are available, neural networks stand out in mapping the nonlinear interactions and relationships between the system’s predictors and dependent responses. In addition, unlike most computational tools, no mathematical relationship assumption between the dependent and independent variables has to be made. Nevertheless, neural networks have been criticized for their long trial-and-error training process since the optimal configuration is not known a priori. This paper investigates the use of a fairly simple nonparametric regression algorithm known as multivariate adaptive regression splines（MARS）, as an alternative to neural networks, to approximate the relationship between the inputs and dependent response, and to mathematically interpret the relationship between the various parameters. In this paper, the Back propagation neural network（BPNN） and MARS models are developed for assessing pile drivability in relation to the prediction of the Maximum compressive stresses（MCS）, Maximum tensile stresses（MTS）, and Blow per foot（BPF）. A database of more than four thousand piles is utilized for model development and comparative performance between BPNN and MARS predictions.
基金Project supported by the International S&T Cooperation Program of China(No.2010DFA72760)
文摘For a single-motor parallel hybrid electric vehicle, during mode transitions （especially the transition from electric drive mode to engine/parallel drive mode, which requires the clutch engagement）, the drivability of the vehicle will be signifi- cantly affected by a clutch torque induced disturbance, driveline oscillations and jerks which can occur without adequate controls. To improve vehicle drivability during mode transitions for a single-motor parallel hybrid electric vehicle, two controllers are proposed. The first controller is the engine-side controller for engine cranking/starting and speed synchronization. The second controller is the motor-side controller for achieving a smooth mode transition with reduced driveline oscillations and jerks under the clutch torque induced disturbance and system uncertainties. The controllers are all composed of a feed-forward control and a robust feedback control. The robust controllers are designed by using the mu synthesis method. In the design process, control- oriented system models that take account of various parameter uncertainties and un-modeled dynamics are used. The results of the simulation demonstrate the effectiveness of the proposed control algorithms.
基金supported by Chongqing Municipal Sci & Tech Research Project of China (Grant No. 2010AC6049)Tianjin Municipal Fundamental and Application of Frontier Technology Research Program of China (Grant No. 09JCYBJC04800)
文摘During shift,power flow is not interrupted in powertrains equipped with continuously variable transmission（CVT）.When hard acceleration is commanded,engine speed will flare and corresponding torque will be consumed,which leads to a drop in vehicle drive torque and also the vehicle acceleration.This is the reason why CVT vehicles have poor drivability during hard acceleration maneuver.Conventional method such as torque compensation doesn＇t always work due to the limited backup torque of engine.According to this,means to evaluate the drivability of CVT vehicles are studied,affect factors of drivability are analyzed in detail.Hard acceleration process of CVT vehicle is studied by theoretical analysis,based on which engine torque and ratio change rate of CVT are identified as two key control parameters that decide the drivability of CVT vehicles during hard acceleration maneuver.Therefore,a control strategy based on restricting the change rate of CVT ratio together with torque compensation is proposed,and two different algorithms to establish the limitation of ratio change rate are proposed.These two algorithms are simulated and compared with each other,results indicate that drop of vehicle acceleration is eliminated evidently by limit the change rate of CVT ratio,but small ratio change rate also results in a longer time to finish the accelerate process,an algorithm to decide a proper ratio change rate is needed in order to tune these different characteristics.In order to get better control effects,a new fuzzy logic based algorithm is proposed to decide a proper ratio change rate during kick down conditions,simulation and experiment results indicate that,the amount of vehicle acceleration decrease is reduced from about 1 m/s2 to almost 0,in the mean time the accelerate process only delayed for about 0.3 s.The proposed control strategy and algorithm can effectively tune the characteristics of CVT equipped vehicle during kick down conditions.
文摘Pile drivability is a key problem during the stage of design and construction installation of pile foundations. The solution to the one dimensional wave equation was used to determine the impact force at the top of a concrete pile for a given ram mass, cushion stiffness, and pile impedance. The kinematic equation of pile toe was established and solved based on wave equation theory. The movements of the pile top and pile toe were presented, which clearly showed the dynamic displacement, including rebound and penetration of pile top and toe. A parametric study was made with a full range of practical values of ram weight, cushion stiffness, dropheight, and pile impedance. Suggestions for optimizing the parameters were also presented. Comparisons between the results obtained by the present solution and in-situ measurements indicated the reliability and validity of the method.
文摘Desktop calibration of automatic transmission(AT) is a method which can reduce cost, enhance efficiency and shorten the development periods of a vehicle effectively. We primary introduced the principle and approach of desktop calibration of AT based on the condition of coupling characteristics between engine and torque converter and obtained right point exactly. It is shown to agree with experimental measurements reasonably well. It was used in different applications abroad based on AT technology and achieved a good performance of the vehicle compared with traditional AT technology which primary focuses on the drivability, performance and fuel consumption.
文摘Field measurements of driving resistances and heights of soil core during driving were made offshore and onshore of steel pipe piles. Measured data show that the height of soil core varies differently for piles of different diameters with the increase of penetration. Dynamic plugging could be assumed never to occur for steel pipe piles with diameters over 900 mm. Soil resistances at the time of continuous driving (SRD) are back analyzed from blow counts with an empirical distribution of resistances suppported by many early dynamic measurements. A method of predicting SRD is finally suggested.
基金supported by National Natural Science Foundation of China(Nos.61876212 and 1733007)Zhejiang Laboratory,China(No.2019NB0AB02)Hubei Province College Students Innovation and Entrepreneurship Training Program,China(No.S202010487058).
文摘A panoptic driving perception system is an essential part of autonomous driving.A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving.We present a panoptic driving perception network(you only look once for panoptic(YOLOP))to perform traffic object detection,drivable area segmentation,and lane detection simultaneously.It is composed of one encoder for feature extraction and three decoders to handle the specific tasks.Our model performs extremely well on the challenging BDD100K dataset,achieving state-of-the-art on all three tasks in terms of accuracy and speed.Besides,we verify the effectiveness of our multi-task learning model for joint training via ablative studies.To our best knowledge,this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS),and maintain excellent accuracy.To facilitate further research,the source codes and pre-trained models are released at https://github.com/hustvl/YOLOP.
基金This work was supported in part by the National Natural Science Foundation of China(Grant No.U1864203)in part by the International Science,and Technology Cooperation Program of China(No.2016YFE0102200).
文摘Driving space for autonomous vehicles(AVs)is a simplified representation of real driving environments that helps facilitate driving decision processes.Existing literatures present numerous methods for constructing driving spaces,which is a fundamental step in AV development.This study reviews the existing researches to gain a more systematic understanding of driving space and focuses on two questions:how to reconstruct the driving environment,and how to make driving decisions within the constructed driving space.Furthermore,the advantages and disadvantages of different types of driving space are analyzed.The study provides further understanding of the relationship between perception and decision-making and gives insight into direction of future research on driving space of AVs.
