CN116469245A - Network-connected hybrid driving formation integrated test system and method for multiple traffic simulation fusion - Google Patents
Network-connected hybrid driving formation integrated test system and method for multiple traffic simulation fusion Download PDFInfo
- Publication number
- CN116469245A CN116469245A CN202310352111.8A CN202310352111A CN116469245A CN 116469245 A CN116469245 A CN 116469245A CN 202310352111 A CN202310352111 A CN 202310352111A CN 116469245 A CN116469245 A CN 116469245A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driving
- following
- formation
- traffic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000015572 biosynthetic process Effects 0.000 title claims abstract description 140
- 238000004088 simulation Methods 0.000 title claims abstract description 59
- 238000012360 testing method Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000004927 fusion Effects 0.000 title claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 230000006399 behavior Effects 0.000 claims description 30
- 230000003993 interaction Effects 0.000 claims description 21
- 238000005516 engineering process Methods 0.000 claims description 20
- 230000001133 acceleration Effects 0.000 claims description 18
- 238000005265 energy consumption Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000005096 rolling process Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 5
- 230000035699 permeability Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000011161 development Methods 0.000 claims description 4
- 238000009960 carding Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000010998 test method Methods 0.000 claims description 2
- 238000009966 trimming Methods 0.000 claims description 2
- 238000012512 characterization method Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 7
- 230000006855 networking Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Geometry (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Physiology (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Fluid Mechanics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Pure & Applied Mathematics (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention provides a network hybrid driving formation integrated test system and method for multiple traffic simulation fusion, wherein the system adopts a network hybrid driving formation mode of pilot vehicle-network manual driving and vehicle-network automatic driving, and comprises a network hybrid driving formation traffic human factor test subsystem, a formation vehicle-vehicle model comparison and selection calibration subsystem and a traffic system comprehensive influence evaluation subsystem, and the system is used for respectively evaluating pilot vehicle driving behavior characteristics (reaction, decision, control and operation) and network hybrid driving formation operation characteristics (ecology, safety, efficiency, comfort and stability) and comprehensive influence characteristics (ecology, safety and efficiency) on a traffic system by integrating driving simulation tests, numerical simulation and microscopic traffic simulation. The invention is helpful for describing the driving behavior characteristics of the pilot vehicle under the condition of the network combined driving formation, defining the operation state rule of the pilot vehicle, quantifying the comprehensive influence of the pilot vehicle on a traffic system, and providing reference for the automatic driving industry and enterprises to realize the feasibility and effectiveness test demonstration of the network combined driving formation.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a network-connected hybrid driving formation integrated test system and method for integrating multiple transportation simulations.
Background
Along with the continuous improvement of the intelligent level of vehicles, the automatic driving formation utilizes the advantages of the cooperation of multiple vehicles, the reduction of the distance between the vehicles, the reduction of the air resistance of the rear vehicles by means of the wake flow of the front vehicles and the like, and is hopeful to bring help for improving the traffic operation safety, ecology and smoothness. The intelligent networking technology is used as an emerging technology in the intelligent traffic field, and the front traffic state and the running information of surrounding vehicles are acquired through technologies such as a high-precision sensor, wireless communication and the like, so that better driving decision assistance can be provided for a driver. The development of intelligent networking technology also provides powerful technical support for realizing the expansion from single vehicle to multi-vehicle cooperation. The intelligent networking technology and the automatic driving formation are combined, so that the overall benefit of traffic operation can be doubly improved.
Due to the soundness of the automatic driving standard regulation, the popularization of emerging technologies to the public and the like, partial users cannot fully trust the automatic driving technology at present. Particularly, when each vehicle in the formation is in an automatic driving mode and the formation queue is in a driving condition of a vehicle following distance, drivers and passengers in the following vehicles cannot comprehensively sense and acquire the traffic state in front of the pilot vehicle and cannot timely and safely take over to control the vehicles, most drivers and passengers cannot trust and accept the pilot vehicle to run in the automatic driving mode. Therefore, considering the current state of development of online automatic driving formation, it is necessary to consider an online hybrid driving formation mode in which pilot vehicles are operated by a driver. However, because the individual attribute, the driving style, the daily driving habit, the acceptance attitude to the emerging technology and the use will of each driver are different, and because the individual behaviors of the drivers are not easy to prejudge under special events, and especially the behavior change of pilot drivers caused by the networking conditions and the formation modes is not clear, the evolution and propagation influence on the driving state of the following vehicles is not clear, therefore, the comprehensive operation characteristics and the influence mechanism of the networking mixed driving formation need to be explored. In summary, the invention provides a network-connected hybrid driving formation integrated test system and method for multiple traffic simulation fusion.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a network hybrid driving formation integrated test system with multiple traffic simulation fusion, which adopts a network hybrid driving formation mode of a pilot vehicle-network man-machine interaction terminal and a manual driving and car-network automatic driving and car following model, and comprises a network hybrid driving traffic human factor test subsystem, a formation car following model comparison and selection calibration subsystem and a traffic system comprehensive influence evaluation subsystem, and the three technologies of the fusion driving simulation, the numerical simulation and the microscopic traffic simulation are adopted to evaluate individual driving behavior characteristics (reaction, decision, control and operation) of the pilot vehicle, the integral operation characteristics (ecology, safety, efficiency, comfort and stability) of the network hybrid driving formation and the influence (ecology, safety and efficiency) of the traffic system.
Preferably, the online hybrid driving formation traffic human factor testing subsystem comprises a driving simulation system, an online human-computer interaction terminal, a data cooperative processing center and a human data acquisition system, and is used for constructing an online hybrid driving formation mode and a virtual online driving environment, so as to evaluate driving behavior characteristics of a pilot vehicle driver in the online hybrid driving formation from driving behavior reaction, decision, control and operation dimensions.
Preferably, the formation following model comparison and selection calibration subsystem is used for simulating different networked automatic driving vehicle following models by taking the pilot vehicle driving track acquired in the traffic human factor test subsystem as a reference and adopting a numerical simulation method as a formation driving state when following the vehicle, and comparing and selecting to determine an optimal following model of the following vehicle; extracting characteristics of the pilot vehicle track by adopting a genetic algorithm, and calibrating a pilot vehicle following model; and determining an optimal hybrid driving formation operation mode through a following model stability judging formula, and further evaluating the overall operation characteristics of the network hybrid driving formation from ecology, safety, efficiency, comfort and stable dimensions.
Preferably, the traffic system comprehensive influence evaluation subsystem is used for guiding the calibrated pilot vehicle following model and the calibrated pilot vehicle following model into microscopic traffic simulation software, and further evaluating the influence of the network combined hybrid driving formation on the traffic system level from the formation scale, formation permeability, different mixed traffic flow levels, traffic safety, traffic smoothness and traffic ecology dimension, wherein the attribute difference between the formation vehicle and an individual single workshop is represented by trimming an air resistance coefficient and an energy consumption emission coefficient.
Preferably, in the online hybrid driving formation mode, a pilot vehicle of a driving simulator is controlled and driven by a driver, the vehicle is set to be a vehicle with an L2-level or more auxiliary automatic driving function, and a human-vehicle interaction online environment is built through an online human-computer interaction terminal; the following vehicle simulates the following state through an automatic driving vehicle following model, wherein the network connection and non-network connection state representation of the following vehicle is realized through the differentiated setting of key parameters in the following model.
Preferably, the formation following model comparison and selection calibration subsystem selects a following vehicle following model with the optimal following pilot vehicle effect from the current main stream automatic driving following models; programming and reproducing the following models of the formulas I to III, importing pilot vehicle track data, simulating formation operation effects of the following models and the pilot vehicles by adopting a numerical simulation method, comparing the similarity between the three models and the pilot vehicle track by using a dynamic regulation algorithm of the formula IV, and selecting the following model with the best following effect as the following model of the following vehicle;
acceleration＝1.12*(Δx-T*v)+1.70*Δv (I)
acceleration＝0.23*(Δx-T*v)+0.07*Δv (Ⅱ)
acceleration＝1.1*a+0.23*(Δ*-T*v)+0.07*Δv (Ⅲ)
in the above description, accelerationis the expected acceleration of the following vehicle, a is the current acceleration of the following vehicle, deltax is the distance between two vehicle heads, T is the current time interval of the vehicle heads, v is the current speed of the following vehicle, and Deltav is the speed difference of the two vehicles;
in the above description, DTW is the minimum error value of track data of the following car and the pilot car, L is track data of the pilot car, and F n The n following vehicle track data is K is the track point number, W k Is the corresponding data of the track points.
Preferably, calibrating a pilot vehicle following model, and extracting features of the pilot vehicle driving behavior by adopting a following model calibration method to enable the following model to have the driving behavior features of the formation pilot vehicle; dividing pilot vehicle track data into a calibration group and a verification group according to a 3:1 principle, taking a relative root mean square error (RMSPE) in a formula V as a fitting goodness function, and searching an optimal value of a target function by using a genetic algorithm to calibrate a following model parameter;
in the above formula, K is the number of track points; li is pilot vehicle track data, and Fi is following vehicle track data;
preferably, judging the stability of the following model, and obtaining a following model stability judging formula VII by carrying out Taylor formula expansion on the following model, and judging that the following model is stable when the result of the judging formula VII is more than 0;
in the above, f v To follow the speed variable coefficient of the car, f Δv Is the variable coefficient of the speed difference of two vehicles, f t Is the variable coefficient of the headway.
Preferably, the formation is followed by the correction of the air resistance coefficient of the car and the correction of the energy consumption emission formula coefficient, which means that the air resistance coefficient of the following car is reduced and the energy consumption emission of the following car is reduced compared with that of a pilot car due to the fact that the speed of vehicles is faster and the distance between the vehicles is closer when the vehicle formation runs, so that the air resistance of the following car is requiredRecalibrating the force coefficient and the energy consumption emission formula coefficient; according to test experience and literature carding, the air resistance coefficient of a second vehicle in formation is about 0.85 times of that of a first vehicle, the air resistance coefficient of a third vehicle in formation is about 0.8 times of that of the first vehicle, and the air resistance of a fourth vehicle and more following vehicles in formation is similar to that of the third vehicle; therefore, the air resistance of the following vehicle is set as: the pilot vehicle is C D0 The method comprises the steps of carrying out a first treatment on the surface of the Air resistance coefficient C of first following car D1 ＝C D0 *0.85; air resistance coefficient C of the 2 nd to i th following vehicles Di(i＝2,3,4) ＝C D0 *0.80；
In the above, S n The unit is m, which is the distance between two vehicles; when n=1, default S n Toward infinity, at this time, c=c D0 I.e. the air resistance coefficient of the pilot vehicle is C D0 ；
Selecting a microscopic emission model formula IX of specific power (VSP) of the motor vehicle, and calculating vehicle energy consumption and emission data, wherein the rolling resistance coefficient is 0.105802 KW/m, and the rotational rolling resistance coefficient is 0.00135375KW s 2 /m 2 The air resistance coefficient is 0.00033311KW s 3 /m 3 The method comprises the steps of carrying out a first treatment on the surface of the Therefore, the air resistance coefficient of the pilot vehicle is required to be C D0 = 0.00033311, and the following vehicle VSP model is constructed accordingly;
VSP＝0.105802v+0.00135375v 2 +0.00033311v 3 +va(Ⅸ)
in the above formula, v is the speed of the vehicle, and a is the acceleration of the vehicle.
The application also relates to a network-connected hybrid driving formation integrated test method for the integration of multiple traffic simulation, which comprises the following steps:
s1, a pilot vehicle-net connected man-machine interaction terminal, a manual driving, a car following and net connected automatic driving and following model are built, driving simulation, numerical simulation and microscopic traffic simulation technologies are fused, and a net connected mixed driving traffic human factor testing subsystem, a formation and following model comparison and selection calibration subsystem and a traffic system comprehensive influence evaluation subsystem are formed;
s2, designing a development network man-machine interaction terminal, constructing a virtual network driving environment, developing a network hybrid driving formation driving simulation experiment, and collecting pilot vehicle driving track data;
s3, simulating different automatic driving vehicle following models by using a numerical simulation method with the pilot vehicle driving track acquired in the traffic human factor testing subsystem as a reference as a formation driving state during following, and comparing and selecting to determine an optimal following model of the following vehicle;
s4, calibrating a pilot vehicle following model, and extracting features of pilot vehicle driving behaviors to enable the following model to have the driving behavior features of the formation pilot vehicle;
s5, developing a Taylor formula on the following model to obtain a following model stability discriminant, and judging that the following model is stable when a discriminant result is more than 0;
s6, importing the calibrated pilot vehicle following model and the calibrated following vehicle following model into microscopic traffic simulation software, and further evaluating the influence of the network combined hybrid driving formation on the traffic system level from the formation scale, formation permeability, different mixed traffic flow levels, traffic safety, traffic smoothness and traffic ecology dimension.
The above-described features may be combined in various suitable ways or replaced by equivalent features as long as the object of the present invention can be achieved.
Compared with the prior art, the system and the method for testing the integration of the network hybrid driving formation by integrating various traffic simulation technologies have the following beneficial effects: the integrated test system for the network hybrid driving formation based on the fusion of various traffic simulation technologies is provided, the test of the network hybrid driving formation efficiency and the influence mechanism is supported to be developed from the three dimensional systematization of individual driving behaviors of pilot vehicles, the overall operation characteristics of the vehicle formation and the influence mechanism of the traffic system, the optimum driving mode of the pilot vehicles is drawn, the operation characteristics and the evolution rules of the network hybrid driving formation are clarified, the comprehensive influence of the network hybrid driving formation on the traffic system is quantized, and the obtained result can provide scheme reference, technical support and platform support for the research, test and popularization of the network automatic driving formation operation mode of government authorities, automatic driving technology research enterprises, highway operation management companies and the like.
Drawings
The invention will be described in more detail hereinafter on the basis of embodiments and with reference to the accompanying drawings. Wherein:
FIG. 1 is a diagram of a network hybrid driving formation integrated test system based on fusion of multiple traffic simulation technologies according to an embodiment of the present invention;
FIG. 2 is a flow chart of an online hybrid driving formation test according to an embodiment of the present invention;
FIG. 3 illustrates a networked hybrid drive formation mode according to an embodiment of the present invention;
FIG. 4 is a diagram of a networked hybrid driving formation effect disclosed in one embodiment of the invention;
fig. 5 is an exemplary diagram of an internet protocol man-machine interaction terminal according to an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the accompanying drawings.
The invention provides a network hybrid driving formation integrated test system with multiple traffic simulation fusion, which adopts a network hybrid driving formation mode of a pilot vehicle-network human-computer interaction terminal plus manual driving and a car-network automatic driving and car following model, and comprises a network hybrid driving formation traffic human factor test subsystem, a formation car following model comparison and selection calibration subsystem and a traffic system comprehensive influence evaluation subsystem, wherein the pilot vehicle individual driving behavior characteristics (reaction, decision, control and operation) and network hybrid driving formation integral operation characteristics (ecology, safety, efficiency, comfort and stability) and traffic system influences (ecology, safety and efficiency) are evaluated through three technologies of fusion driving simulation, numerical simulation and microscopic traffic simulation.
In one embodiment, fig. 1 is a framework diagram of an integrated network hybrid driving formation test system based on fusion of multiple traffic simulation technologies, and as can be seen from fig. 1, the integrated network hybrid driving formation test system is designed by fusion of driving simulation, numerical simulation and microscopic traffic simulation technologies, and the network hybrid driving formation efficiency and impact mechanism test is supported to be developed from three-dimensional systematization of individual driving behaviors of pilot vehicles, overall operation characteristics of vehicle formation and comprehensive impact of a traffic system.
In one embodiment, the integrated test system for the online hybrid driving formation is used for forming an integrated influence evaluation subsystem (figure 2) of the online hybrid driving formation traffic human factor test subsystem, the formation and driving model comparison and selection calibration subsystem and the traffic system by constructing a hybrid driving formation mode of a pilot vehicle-online human-computer interaction terminal plus manual driving, a following vehicle-online automatic driving and following model and fusing driving simulation, numerical simulation and microscopic traffic simulation technologies, so as to evaluate the integrated influence of three dimensions of individual driving behaviors of the pilot vehicle, the integral operation characteristics of the online hybrid driving formation and the influence of the traffic system.
In one embodiment, the network hybrid driving formation traffic human factor test subsystem is composed of a driving simulation system, a network human-computer interaction terminal, a data cooperative processing center and a human factor data acquisition system and is used for constructing a network hybrid driving formation mode and a virtual network driving environment, and further evaluating driving behavior characteristics of a pilot vehicle driver in the network hybrid driving formation from driving behavior reaction, decision, control and operation dimensions.
In one embodiment, the formation following model comparison and selection calibration subsystem uses the pilot vehicle driving track collected in the traffic human factor test subsystem as a reference, and adopts a numerical simulation method to simulate different networked automatic driving vehicle following models as formation driving states during following, and compares and selects to determine an optimal following model of the following vehicle; extracting characteristics of the pilot vehicle track by adopting a genetic algorithm, and calibrating a pilot vehicle following model; and determining an optimal hybrid driving formation operation mode through a following model stability judging formula, and further evaluating the overall operation characteristics of the network hybrid driving formation from ecology, safety, efficiency, comfort and stable dimensions.
In one embodiment, the traffic comprehensive influence evaluation subsystem is used for guiding the calibrated pilot vehicle following model and the calibrated pilot vehicle following model into microscopic traffic simulation software, and further evaluating the influence of the network combined hybrid driving formation on the traffic system level from the formation scale, formation permeability, different mixed traffic flow levels, traffic safety, traffic smoothness and traffic ecology dimension, wherein the attribute difference between the formation vehicle and an individual single workshop is represented by determining an air resistance coefficient and an energy consumption emission coefficient.
In one embodiment, fig. 3 is a schematic diagram of a network hybrid driving formation mode, fig. 4 is a network hybrid driving formation effect diagram, and it can be known from the diagram that a pilot vehicle in a driving simulator is controlled and driven by a driver, is set as an automatic driving vehicle with more than level L2, and builds a network environment of human-vehicle interaction through a network HMI; the following vehicle simulates the following state through an automatic driving vehicle following model, wherein the network connection and non-network connection state representation of the following vehicle is realized through the differentiated setting of key parameters in the following model.
In one embodiment, the internet connection human-computer interaction terminal (HMI) refers to a human-computer interaction vehicle-mounted terminal with an internet connection function, which can report contents such as a driving state, surrounding vehicle information, a front traffic state, a driving behavior guidance prompt and the like to a pilot vehicle driver, and the internet connection HMI performs design optimization on the contents such as an HMI interface layout, content information, a broadcasting form and the like by referring to a user-centered design method in L2 and L3 level automatic driving human factor design guidelines, UI design principles and international standard ISO 9241-210. The method comprises the steps of adopting an interface layout form of important information close to one side of a driver, adopting an early warning content form of highlighting networking information and driving behavior guiding information, adopting a broadcasting form of voice prompt, word prompt, picture prompt and warning sound prompt, and upgrading and optimizing the HMI through an iterative optimization form of inviting driving behaviors, intelligent traffic, computers and UI design field experts to carry out expert evaluation scoring and inviting pre-experiment to be tested to put forward using experience.
As shown in fig. 5, the network-connected man-machine interaction terminal is divided into four areas according to the above division basis. The area 1 is a driving behavior prompt area and is used for correcting bad driving behaviors of a driver; the area 2 is a real-time oil consumption display area and is used for displaying vehicle oil consumption data in real time; the area 3 is a vehicle state display area and is used for displaying the distance between the front vehicle and the running state information of the front vehicle; the area 4 is a speed limit sign prompt area and is used for displaying the current lane type and the speed limit range. Taking fig. 2 as an example, the vehicle is located on an ecological lane section, the front vehicle is in an accelerating state, the accelerator of the driver is stepped deep, and the internet-access human-computer interaction terminal prompts the driver to slowly step on the accelerator in a text and voice broadcasting mode.
In one embodiment, the calibration comparison of the following models of the following vehicles refers to selecting the following model with the optimal following pilot vehicle effect from the following models of the automatic driving with more current applications; programming and reproducing three following models in a formula 1, a formula 2 and a formula 3, importing pilot vehicle track data, simulating formation operation effects of the three following models and the pilot vehicle by adopting a numerical simulation method, comparing similarity between the three models and the pilot vehicle track by a dynamic regulation algorithm (formula 4), and selecting the following model with the best following effect as the following model of the following vehicle.
acceleration＝1.12*(Δx-T*v)+1.70*Δv (1)
acceleration＝0.23*(Δx-T*v)+0.07*Δv (2)
acceleration＝1.1*a+0.23*(Δx-T*v)+0.07*Δv (3)
In the above description, accelerationis the expected acceleration of the following vehicle, a is the current acceleration of the following vehicle, deltax is the distance between two vehicle heads, T is the current time interval of the vehicle heads, v is the current speed of the following vehicle, and Deltav is the speed difference of the two vehicles.
In the above description, DTW is the minimum error value of track data of the following car and the pilot car, L is track data of the pilot car, and F n For following the track data of the car, K is the number of track points and W k Is the corresponding data of the track points.
In one embodiment, the calibration of the pilot vehicle following model refers to feature extraction of the pilot vehicle driving behavior by adopting a following model calibration method, so that the following model has the driving behavior features of the formation pilot vehicle; and (3) distributing the pilot vehicle track data into a calibration group and a verification group according to a 3:1 principle, respectively taking relative root mean square error (RMSPE) (formula 5) as a fitting goodness function, and searching an optimal value of the objective function by using a genetic algorithm to calibrate the following model parameters.
In the above formula, K is the number of track points; l (L) i For piloting vehicle track data, F i Is following car track data.
In one embodiment, the following model stability determination refers to that the change of the driving state of the pilot vehicle during the formation driving causes the disturbance of the driving state of the following vehicle at the rear, the unstable driving state of the following vehicle affects the overall operation of the formation vehicle, the following model stability discriminant (formula 7) can be obtained by performing taylor formula expansion on the following model, and when the discriminant result is >0, the following model stability can be determined.
In the above, f v To follow the speed variable coefficient of the car, f Δv Is the variable coefficient of the speed difference of two vehicles, f t Is the variable coefficient of the headway.
In one embodiment, the formation is formed to fix the air resistance coefficient of the following car and the energy consumption emission formula coefficient, that is, the air resistance coefficient of the following car is reduced when the vehicle formation runs due to the fact that the speed between vehicles is faster and the distance between vehicles is closer, and the energy consumption emission of the following car is smaller than that of the pilot car, so that the air resistance coefficient of the following car and the energy consumption emission formula coefficient are required to be recalibrated. The air resistance calculation formula is shown as formula (8), according to test experience and literature carding, the air resistance coefficient of the second vehicle in the formation is about 0.85 times of that of the first vehicle, the air resistance coefficient of the third vehicle in the formation is about 0.8 times of that of the first vehicle, and the air resistance of the fourth vehicle and more following vehicles in the formation are similar to those of the third vehicle. Therefore, the air resistance of the following vehicle is set as: the pilot vehicle is C D0 The method comprises the steps of carrying out a first treatment on the surface of the First following car C D1 ＝C D0 *0.85; following vehicle C from No. 2 to No. i Di(i＝2,3,4) ＝C D0 *0.80。
In the above, C D0 、C D1 C D2 Is the air resistance coefficient; s is S n The unit is m, which is the distance between two vehicles. When n=1, default S n Toward infinity, at this time, c=c D0 I.e. the air resistance coefficient of the guided vehicle takes a value of C D0 。
Selecting a microscopic emission model (formula 9) of specific power (VSP) of the motor vehicle to calculate vehicle energy consumption and emission data, wherein the rolling resistance coefficient is 0.105802 KW/m, and the rotational rolling resistance coefficient is 0.00135375KW 2 /m 2 The air resistance coefficient is 0.00033311KW s 3 /m 3 . Therefore, the air resistance coefficient of the pilot vehicle is required to be C D0 = 0.00033311, and the following car VSP model was developed accordingly.
VSP＝0.105802v+0.00135375v 2 +0.00033311v 3 +va(9)
In the above formula, v is the speed of the vehicle, and a is the acceleration of the vehicle.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the different dependent claims and the features described herein may be combined in ways other than as described in the original claims. It is also to be understood that features described in connection with separate embodiments may be used in other described embodiments.
Claims (10)
1. A network hybrid driving formation integrated test system with multiple traffic simulation fusion is characterized by adopting a network hybrid driving formation mode of a pilot vehicle-network human-computer interaction terminal plus manual driving and a car-network automatic driving and car following model, and the network hybrid driving formation integrated test system comprises a network hybrid driving formation traffic human factor test subsystem, a formation car following model comparison and selection calibration subsystem and a traffic system comprehensive influence evaluation subsystem, and the pilot vehicle individual driving behavior characteristic, the network hybrid driving formation integral operation characteristic and the comprehensive influence on the traffic system are evaluated through three technologies of fusion driving simulation test, numerical simulation and microscopic traffic simulation.
2. The integrated testing system for the online mixed driving formation with the multiple traffic simulation fusion according to claim 1, wherein the integrated testing subsystem for the online mixed driving formation traffic human factor comprises a driving simulation system, an online human-computer interaction terminal, a data cooperative processing center and a human data acquisition system, and is used for constructing an online mixed driving formation mode and a virtual online driving environment, and further evaluating driving behavior characteristics of a pilot vehicle driver in the online mixed driving formation from driving behavior reaction, decision, control and operation dimensionality.
3. The integrated test system for the networked hybrid driving formation of the multiple traffic simulation fusion according to claim 1, wherein the formation following model is selected from a calibration subsystem, a numerical simulation method is adopted to simulate different networked automatic driving vehicle following models as the formation driving state during following by taking the pilot driving track acquired in the traffic human factor test subsystem as a reference, and the optimal following model of the following vehicle is determined by comparing; extracting characteristics of the pilot vehicle track by adopting a genetic algorithm, and calibrating a pilot vehicle following model; and determining an optimal hybrid driving formation operation mode through a following model stability judging formula, and further evaluating the overall operation characteristics of the network hybrid driving formation from ecology, safety, efficiency, comfort and stable dimensions.
4. The integrated test system for the network hybrid driving formation with the integration of multiple traffic simulation according to claim 1, wherein the integrated influence evaluation subsystem of the traffic system is used for guiding the calibrated pilot vehicle following model and the calibrated following vehicle following model into microscopic traffic simulation software so as to evaluate the integrated influence of the network hybrid driving formation on the traffic system level from the formation scale, formation permeability, different hybrid traffic flow levels, traffic safety, traffic smoothness and traffic ecology dimension, wherein the difference of the driving attribute of the formation vehicle and an individual single workshop is characterized by trimming an air resistance coefficient and an energy consumption emission coefficient.
5. The integrated test system for the network hybrid driving formation with the integration of multiple traffic simulation according to claim 1, wherein in the network hybrid driving formation mode, a pilot vehicle of a driving simulator is controlled and driven by a driver, the vehicle is set to be provided with a vehicle with an L2-level or more auxiliary automatic driving function, and a network environment of human-vehicle interaction is built through a network man-machine interaction terminal; the following vehicle simulates the following state through an automatic driving vehicle following model, wherein different driving behavior characterization of the following vehicle under the condition of network connection and non-network connection is realized through carrying out differentiated setting on key parameters in the following model.
6. The integrated test system for networked hybrid driving formation with multiple traffic simulation fusion according to claim 1, wherein the formation following model is selected from the following models of the current main stream automatic driving by a calibration subsystem, and a following vehicle following model with the optimal following pilot vehicle effect is selected from the following models of the current main stream automatic driving; programming and reproducing the following models of the formulas I to III, importing pilot vehicle track data, simulating formation operation effects of the following models and the pilot vehicles by adopting a numerical simulation method, comparing the similarity between the three models and the pilot vehicle track by using a dynamic regulation algorithm of the formula IV, and selecting the following model with the best following effect as the following model of the following vehicle;
acceleration＝1.12*(Δx-T*v)+1.70*Δv (I)
acceleration＝0.23*(Δx-T*v)+0.07*Δv (Ⅱ)
acceleration＝1.1*a+0.23*(Δx-T*v)+0.07*Δv (Ⅲ)
in the above description, accelerationis the expected acceleration of the following vehicle, a is the current acceleration of the following vehicle, deltax is the distance between two vehicle heads, T is the current time interval of the vehicle heads, v is the current speed of the following vehicle, and Deltav is the speed difference of the two vehicles;
in the above description, DTW is the minimum error value of track data of the following car and the pilot car, L is track data of the pilot car, and F n The n following vehicle track data is K is the track point number, W k Is the corresponding data of the track points.
7. The integrated test system for networked hybrid driving formation with multiple traffic simulation fusion according to claim 3, wherein the pilot vehicle is calibrated with a following model, and the driving behavior of the pilot vehicle is extracted by adopting a following model calibration method, so that the following model has the driving behavior characteristics of the formation pilot vehicle; dividing pilot vehicle track data into a calibration group and a verification group according to a proportion, taking a relative root mean square error (RMSPE) in a formula V as a fitting goodness function, and searching an optimal value of an objective function by using a genetic algorithm to calibrate a following model parameter;
in the above formula, K is the number of track points; li is pilot vehicle track data, and Fi is following vehicle track data.
8. The integrated test system for networked hybrid driving formation with multiple traffic simulation fusion according to claim 3, wherein the following model stability is judged, a taylor formula expansion is carried out on the following model to obtain a following model stability judging formula VII, and when a judging formula VII result is more than 0, the following model is judged to be stable;
in the above, f v To follow the speed variable coefficient of the car, f Δv Is the variable coefficient of the speed difference of two vehicles, f t Is the variable coefficient of the headway.
9. The integrated test system for the networked hybrid driving formation with the integration of multiple traffic simulation according to claim 1, wherein the formation is characterized in that the correction of the air resistance coefficient and the correction of the energy consumption emission formula coefficient of the following vehicles are that the air resistance coefficient of the following vehicles is reduced and the energy consumption emission of the following vehicles is reduced due to the fact that the speed between vehicles is faster and the distance between vehicles is closer when the vehicles are in formation driving, so that the air resistance coefficient and the energy consumption emission formula coefficient of the following vehicles are required to be recalibrated; according to test experience and literature carding, when the formation vehicles run stably, the air resistance coefficient of a second vehicle in the formation is about 0.85 times of that of the first vehicle, the air resistance coefficient of a third vehicle in the formation is about 0.8 times of that of the first vehicle, and the air resistance of a fourth vehicle and more following vehicles in the formation is similar to that of the third vehicle; therefore, the vehicle air resistance coefficient may be set to: the air resistance coefficient of the pilot vehicle is C D0 The method comprises the steps of carrying out a first treatment on the surface of the The air resistance coefficient of the first following car is C D1 ＝C D0 *0.85; the air resistance coefficient of the following vehicles from the 2 nd to the i th is C Di(i＝2,3,4) ＝C D0 *0.80; because the change of the vehicle distance is the main reason for changing the air resistance of the rear vehicle, and the air resistance of the vehicle under different vehicle distances is considered, the air resistance coefficient of the vehicle is further modified by introducing the vehicle distance variable, as shown in a formula VIII,
in the above, d i The distance between the ith vehicle and the front vehicle is m; when i=1, if d i Tends to infinity at the moment of air resistance coefficient C D (d i )＝C D0 I.e. the air resistance coefficient of the pilot vehicle is C D0 ；
Selecting a ratio of motor vehiclesThe microscopic emission model formula IX of the power (VSP) calculates the energy consumption and emission data of the vehicle, wherein the rolling resistance coefficient is 0.105802 KW/m, and the rotation rolling resistance coefficient is 0.00135375KW s 2 /m 2 The air resistance coefficient is 0.00033311KW s 3 /m 3 The method comprises the steps of carrying out a first treatment on the surface of the Therefore, the air resistance coefficient of the pilot vehicle is required to be C D0 = 0.00033311, and the following vehicle VSP model is constructed accordingly;
VSP＝0.105802v+0.00135375v 2 +0.00033311v 3 +va (Ⅸ)
in the above formula, v is the speed of the vehicle, and a is the acceleration of the vehicle.
10. The test method of the integrated test system for the networked hybrid driving of the multiple traffic simulation fusion according to claim 1, which is characterized by comprising the following steps:
s1, a pilot vehicle-net connected man-machine interaction terminal, a manual driving, a car following and net connected automatic driving and following model are built, driving simulation, numerical simulation and microscopic traffic simulation technologies are fused, and a net connected mixed driving traffic human factor testing subsystem, a formation and following model comparison and selection calibration subsystem and a traffic system comprehensive influence evaluation subsystem are formed;
s2, designing a development network man-machine interaction terminal, constructing a virtual network driving environment, developing a network hybrid driving formation driving simulation experiment, and collecting pilot vehicle driving track data;
s3, simulating different automatic driving vehicle following models by using a numerical simulation method with the pilot vehicle driving track acquired in the traffic human factor testing subsystem as a reference as a formation driving state during following, and comparing and selecting to determine an optimal following model of the following vehicle;
s4, calibrating a pilot vehicle following model, and extracting features of pilot vehicle driving behaviors to enable the following model to have the driving behavior features of the formation pilot vehicle;
s5, developing a Taylor formula on the following model to obtain a following model stability discriminant, and judging that the following model is stable when a discriminant result is more than 0;
s6, importing the calibrated pilot vehicle following model and the calibrated following vehicle following model into microscopic traffic simulation software, and further evaluating the influence of the network combined hybrid driving formation on the traffic system level from the formation scale, formation permeability, different mixed traffic flow levels, traffic safety, traffic smoothness and traffic ecology dimension.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310352111.8A CN116469245A (en) | 2023-04-04 | 2023-04-04 | Network-connected hybrid driving formation integrated test system and method for multiple traffic simulation fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310352111.8A CN116469245A (en) | 2023-04-04 | 2023-04-04 | Network-connected hybrid driving formation integrated test system and method for multiple traffic simulation fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116469245A true CN116469245A (en) | 2023-07-21 |
Family
ID=87181699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310352111.8A Pending CN116469245A (en) | 2023-04-04 | 2023-04-04 | Network-connected hybrid driving formation integrated test system and method for multiple traffic simulation fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116469245A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112477846A (en) * | 2020-11-13 | 2021-03-12 | 东南大学 | Intelligent networking electric automobile queue control method giving consideration to stability and energy conservation |
| CN112519777A (en) * | 2019-08-30 | 2021-03-19 | 北京图森智途科技有限公司 | Control method of automatic driving fleet, vehicle-mounted device, vehicle and system |
| CN113791615A (en) * | 2021-08-20 | 2021-12-14 | 北京工业大学 | Hybrid vehicle queue distributed model prediction control method |
| CN114516328A (en) * | 2022-03-08 | 2022-05-20 | 武汉科技大学 | Rule-based motorcade following model method in intelligent network environment |
| CN115081227A (en) * | 2022-06-29 | 2022-09-20 | 西安理工大学 | Optimal speed-based vehicle following model and safety analysis method thereof |
| US20230063010A1 (en) * | 2020-12-15 | 2023-03-02 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for controlling vehicle to drive as platoon, electronic device, and storage medium |
-
2023
- 2023-04-04 CN CN202310352111.8A patent/CN116469245A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112519777A (en) * | 2019-08-30 | 2021-03-19 | 北京图森智途科技有限公司 | Control method of automatic driving fleet, vehicle-mounted device, vehicle and system |
| CN112477846A (en) * | 2020-11-13 | 2021-03-12 | 东南大学 | Intelligent networking electric automobile queue control method giving consideration to stability and energy conservation |
| US20230063010A1 (en) * | 2020-12-15 | 2023-03-02 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for controlling vehicle to drive as platoon, electronic device, and storage medium |
| CN113791615A (en) * | 2021-08-20 | 2021-12-14 | 北京工业大学 | Hybrid vehicle queue distributed model prediction control method |
| CN114516328A (en) * | 2022-03-08 | 2022-05-20 | 武汉科技大学 | Rule-based motorcade following model method in intelligent network environment |
| CN115081227A (en) * | 2022-06-29 | 2022-09-20 | 西安理工大学 | Optimal speed-based vehicle following model and safety analysis method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 常鑫等: ""基于驾驶模拟器的车联网环境搭建及对驾驶行为的影响"", 《科学技术与工程》, vol. 19, no. 15, 31 May 2019 (2019-05-31), pages 330 - 335 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106874597B (en) | highway overtaking behavior decision method applied to automatic driving vehicle | |
| JP5375805B2 (en) | Driving support system and driving support management center | |
| US10829065B1 (en) | Vehicle power management system | |
| CN103914985B (en) | A kind of hybrid power passenger car following speed of a motor vehicle trajectory predictions method | |
| US9623721B2 (en) | Energy saving automatic air conditioning control system and method | |
| JP5051542B2 (en) | Driver model processor | |
| Rios-Torres et al. | Fuel consumption for various driving styles in conventional and hybrid electric vehicles: Integrating driving cycle predictions with fuel consumption optimization | |
| US20070112475A1 (en) | Power management systems and devices | |
| Bareket et al. | Methodology for assessing adaptive cruise control behavior | |
| Torabi et al. | Energy minimization for an electric bus using a genetic algorithm | |
| CN116134292A (en) | Tool for performance testing and/or training an autonomous vehicle planner | |
| Fleming et al. | Real‐time predictive eco‐driving assistance considering road geometry and long‐range radar measurements | |
| Alshayeb et al. | Investigating impacts of various operational conditions on fuel consumption and stop penalty at signalized intersections | |
| CN116432448B (en) | Variable speed limit optimization method based on intelligent network coupling and driver compliance | |
| CN108711285B (en) | Hybrid traffic simulation method based on road intersection | |
| CN115422747A (en) | Method and device for calculating discharge amount of pollutants in tail gas of motor vehicle | |
| CN116596380A (en) | Optimization determination method, platform, equipment and medium for expressway construction organization scheme and management and control scheme | |
| Deng et al. | A novel real‐time energy management strategy for plug‐in hybrid electric vehicles based on equivalence factor dynamic optimization method | |
| Su et al. | Integrated framework for test and evaluation of autonomous vehicles | |
| Shang et al. | Modeling adaptive cruise control vehicles: A continuous asymmetric car-following perspective | |
| Henzler et al. | Optimal parameter selection of a model predictive control algorithm for energy efficient driving of heavy duty vehicles | |
| CN116469245A (en) | Network-connected hybrid driving formation integrated test system and method for multiple traffic simulation fusion | |
| CN115979679A (en) | Method, apparatus and storage medium for testing actual road of automatic driving system | |
| Su et al. | Personalized adaptive cruise control considering drivers’ characteristics | |
| Fancher | Research on desirable adaptive cruise control behavior in traffic streams |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |