CN112614344B - Hybrid traffic system efficiency evaluation method for automatic driving automobile participation - Google Patents
Hybrid traffic system efficiency evaluation method for automatic driving automobile participation Download PDFInfo
- Publication number
- CN112614344B CN112614344B CN202011468143.7A CN202011468143A CN112614344B CN 112614344 B CN112614344 B CN 112614344B CN 202011468143 A CN202011468143 A CN 202011468143A CN 112614344 B CN112614344 B CN 112614344B
- Authority
- CN
- China
- Prior art keywords
- traffic
- matrix
- layer
- model
- road
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 25
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 230000007613 environmental effect Effects 0.000 claims abstract description 9
- 230000009897 systematic effect Effects 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 56
- 238000000034 method Methods 0.000 claims description 36
- 230000006399 behavior Effects 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000035699 permeability Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000008878 coupling Effects 0.000 claims description 4
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 230000006698 induction Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000008439 repair process Effects 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000013499 data model Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000013439 planning Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 2
- 102000002274 Matrix Metalloproteinases Human genes 0.000 claims 1
- 108010000684 Matrix Metalloproteinases Proteins 0.000 claims 1
- 238000009795 derivation Methods 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 10
- 238000010276 construction Methods 0.000 abstract 1
- 230000001133 acceleration Effects 0.000 description 7
- 241000725585 Chicken anemia virus Species 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003137 locomotive effect Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 239000011541 reaction mixture Substances 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Chemical & Material Sciences (AREA)
- Educational Administration (AREA)
- Analytical Chemistry (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a mixed traffic system efficiency evaluation method under participation of an automatic-driving automobile, which takes the running requirement of the automatic-driving automobile in a mixed flow as research cut-in, constructs an automatic-driving automobile behavior model, a micro-vehicle following model under the mixed flow condition, a region traffic capacity and road network bearing capacity model, analyzes the mixed traffic flow macroscopic law and the vehicle micro-traffic behavior uncertainty, and constructs a mixed traffic flow index evaluation system under different environmental scenes. The invention has more comprehensive research and entry points on the automatic driving mixed flow, and provides systematic theoretical reference and guidance of a traffic control layer for vehicle putting, testing and the like in an automatic driving test field; the model theory in the system engineering is fully utilized to carry out the overall efficiency model construction on the hybrid traffic system, and the quantized data structure can better respond to the automatic driving participants in the vehicle-road cooperative network and provide better reference basis for traffic decision makers to carry out traffic control modes.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and particularly relates to a method for evaluating the overall operation efficiency of a hybrid traffic system under participation of an automatic driving vehicle.
Background
In the future, the road-going popularization process of the automatic driving vehicles needs to undergo a constantly-developing evolution process for a long time, and in the process, the mixed traffic flow condition of vehicles which are artificially driven and have different automatic driving grades necessarily exists. Therefore, mixed traffic flow research of different grades of autonomous vehicles under different permeability becomes the first important research content of the road getting process of the autonomous vehicles. The evaluation of the traffic running condition of the mixed traffic flow has important significance for the automatic driving automobile closing test and the actual road operation; modeling and simulation of mixed traffic flow are core elements for analyzing different traffic states of automatic driving under different environments and permeability in the future, and play an important role in the development of closed test and open actual application of automatic driving.
The first step of the overall traffic condition evaluation is to analyze and evaluate the microscopic vehicle behaviors in the mixed traffic flow, and then a following model and road traffic capacity can be constructed on the basis. Analysis of behavior of different types of vehicles under mixed traffic flow is still one of the difficulties of field research, and especially the behavior reaction mode of different traffic participants when meeting another participant is considered. However, the existing research on the automatic driving mixed flow is relatively single, most of the research is specifically carried out on single indexes such as speed, delay, conflict and the like, and the complete following behavior model is not compared with the systematic result.
After the vehicle behavior in the automatic driving mixed flow is analyzed and the following model is constructed, the traffic capacity of the whole mixed flow road section can be calculated, and the method plays an important guiding significance for the expected delivery and the operation management in the current automatic driving test process. However, in the meantime, considering different environmental interferences in an actual scene, the influence of the autonomous vehicle is different from that of the human-driven vehicle, so the interference of environmental scene factors must be fully considered for the operation condition analysis of the actual mixed stream. A complete test road bearing capacity system formed on the basis provides a good theoretical reference basis for optimizing the whole traffic operation.
On a macroscopic traffic level, due to the appearance of the automatic driving vehicles, the original significant reduction of the uncertainty factors of road traffic caused by artificial driving exists, and the reduction process becomes more obvious along with the increase of the permeability of the automatic driving vehicles and the improvement of the lane management specialization. Based on the method, the traffic process of the whole mixed flow can present a more regular, standardized and controllable large-scale system, and each traffic participant can be optimized to be a unit individual in the system. Such a traffic system would have greatly improved efficiency and less hunting and accidents than conventional human-driven systems. However, the current research on the macro mixed flow only remains in the fields of road network analysis, travel OD analysis and the like in the traditional traffic, and the data structure of the macro mixed flow is difficult to respond to the automatic driving participants in the vehicle-road cooperative network more effectively; the method can not provide a complete traffic operation condition influence relationship, and provides a better theoretical reference basis for traffic decision makers in traffic control modes.
Disclosure of Invention
The invention aims to provide a method for evaluating the efficiency of a hybrid traffic system participated in by an automatic driving automobile, which is used for researching the influence of main condition indexes on the overall traffic operation condition, constructing the evaluation of an overall traffic system operation efficiency model under a multi-level automatic driving mixed flow by combining the overall scene traffic operation condition and referring to the theoretical configuration in system engineering, and providing systematic theoretical reference and guidance of a traffic control level for vehicle release, test and the like of an automatic driving test field so as to solve the problems that the research of the automatic driving mixed flow is switched into a single and macroscopic mixed flow data structure, the automatic driving participants in a road cooperative network are difficult to effectively respond, the complete traffic operation condition influence relation cannot be provided, and a better theoretical reference basis is provided for a traffic decision maker in a traffic control mode.
The invention provides the following technical scheme:
a method for evaluating the efficiency of a hybrid traffic system under the participation of an automatic driving automobile comprises the following steps:
s1, analyzing the behavior characteristics of a vehicle in mixed traffic with automatic driving and artificial driving;
s2, constructing an optimized traffic capacity under a complex mixed flow;
s3, constructing a mixed traffic running condition environment attribute layer, wherein the step is not sequential to the step S2;
s4, constructing a hybrid traffic operation comprehensive efficiency layer to obtain the system availability
Task credibility
And system job capability function
And a system unit weight matrix T;
s5. instituteAvailability of the system
Task credibility
System operation capability function
To derive an overall system evaluation performance E, wherein E =
For the result index vector, the shunt network running condition evaluation of the traffic running actual index of the specific design aiming at the specific requirement in the system is expressed; and comprehensively evaluating the overall efficiency calculation result V according to the P-E system efficiency model calculation scheme, wherein the overall efficiency calculation result V is in functional relation with the results of various road environmental conditions and actual traffic running conditions under the actual condition.
Preferably, in step S2, the method for constructing optimal traffic capacity under complex mixed flow includes: the method comprises the steps of evaluating a basic car following mode of the whole traffic flow by adopting an optimized cooperative adaptive cruise control intelligent driver car following model according to the coupling relation among environment influence factors of actual running road scene environment, weather change, permeability of the automatic driving mixed traffic flow and sudden accidents, recalculating the traffic capacity of the mixed traffic flow participated by the automatic driving cars under different levels and different permeabilities according to the characteristics of traffic participants, describing the road bearing capacity of a mixed traffic running area on the basis, and evaluating the actual running condition of the whole mixed traffic flow.
Preferably, the step S2 includes the steps of:
s21: when the front vehicle or the side vehicle is observed to be an automatic driving vehicle, the original safety distance formula is as follows:
wherein
Is constant and refers to the headway of a vehicle driven by a person,
indicating the vehicle speed of the vehicle at time t,
showing the distance between the head of the vehicle and the tail of the front vehicle,
indicating the length of the vehicle body; describing the following behaviors of CAVs by using an intelligent driver following model and a CACC following model calibrated by a route laboratory;
s22: on the basis of the step S21, a CACC car following model is used to describe car following behaviors of the CAVs, as shown in the following formula:
in the formula (I), the compound is shown in the specification,
the speed of the previous control time;
e is the error between the actual vehicle distance and the expected vehicle distance;
Δ x is the actual headway
deriving the velocity in the above equation
Then, a calculation formula of the expected acceleration of the automatic driving automobile under the mixed flow following model can be obtained, and the calculation formula is shown as the following formula:
the speed and the acceleration of the vehicle in a following model under a specific automatic driving vehicle have basic model definition;
s23: the method for decomposing the integral mixed traffic flow into n traffic flows which have the same locomotive time interval and are theoretically and stably followed comprises the following steps:
in the formula (I), the compound is shown in the specification,
the time interval of the locomotive;
wn is the proportionality coefficient of the multi-strand vehicle;
in the standard flow, the head interval can be disassembled into:
substituting the formula into the formula, carrying out corresponding conversion, and calculating to obtain the integrated traffic flow comprehensive flow of the whole plurality of traffic flows as follows:
according to a lane change theoretical model in inference, the overall road bearing capacity is deduced to be represented as:
preferably, in step S21, an intelligent driver following model is constructed to optimize a following model of the vehicle, and the expression of the intelligent driver following model is as follows:
wherein:
preferably, in the step S4, an ADC model is used to construct a hybrid traffic operation comprehensive performance layer; the layer D is an attribute transfer unit, the layer A is a main capacity unit, the layer E is an efficiency calculation result unit, and the control mode of the model depends on a layered structure.
Preferably, the S4 step includes the steps of:
s41, adopting an efficiency influence control model for the lower model unit P frame, wherein the overall efficiency value of the P frame and the upper layer meets the functional relation condition, and the corresponding expression is as follows:
that is, P units are individual response relationships to E in the system framework, where:
P=
wherein the content of the first and second substances,
the attribute parameters of the physical layer are used for representing road traffic environment influence parameters;
for the actual road environment conversion value, the concrete calculation control formulas are generated by 2.4;
is a preset standard environment parameter value.
Preferably, the P layers are controlled by the extent of the sub-control layer X, Y layers, with the P matrix first for a particular road networkWith a standard matrix
And the fluctuation matrix
Wherein
In order to predict the various environmental parameters of the actual scene criteria,
the maximum influence change of each condition considered in the actual scene is as follows:
preferably, in step S5, the integrated system performance indicator layer V includes system availability
Task credibility
And system specified job capability function
System unit weight matrix T, using vectors
Represents:
in the formula
The method is used for evaluating the efficiency of a specific measurement index in the process of realizing a task by a system;
system availability
The system is a measure of the degree of use and a specific state metric of the system at a certain moment in executing a task;
task credibility
Representing the probability of the system completing a specified function during use;
system specified job capability function
Representing the ability of the system to run or work.
Preferably, the system availability
The index which shows that the working condition at a certain moment in a specific road section meets the capability in an actual road is shown, and in a standard equipment system, the calculation formula of A is as follows:
in a traffic system, MTBF represents free flow movement state time, MTTR represents traffic capacity reduction condition repair time, and a value is taken according to predicted peak flow change in actual traffic flow;
criteria in autonomous driving dedicated lanes according to lane management variations
Aiming at the importance of different roads in the whole traffic network, a specific road has a weight index for performing coefficient regression on the system efficiency, and a matrix T is a weight matrix:
wherein
Is a clockwise road weight;
task confidence due to n possible states of the system
Is an n x n matrix, and in the whole mixed traffic flow running state,
probability that a vehicle departing from the system at location i at the beginning of use will transfer to location j during use:
in the formula:
system specified job capability function
Is an n x n matrix, based on the traffic system operationThe actual automatic driving mixed flow test requirement divides the operation capability layer C into a main layer C and a sub-layer B, wherein
The service level from the departure point i to the destination point j is represented, namely the running speed and the ratio of the traffic volume to the basic traffic capacity, and the capacity of the system for completing the target is represented as follows:
the B sub-layer also represents the system operation capacity, represents the whole safety degree of the traffic operation in the mixed flow, the system safety degree is an n x n matrix, and the system safety degree is the whole safety degree of the traffic operation in the traffic system operation
The index calculation result in the SSAM security analysis from the departure point i to the destination point j is shown, and is a probability coefficient of collision between system links, namely:
for the C system, the selection of the sub-layer model can be considered according to the actual test requirements, and for the overall systematic planning, the system operation capacity comprises traffic capacity and a traffic safety evaluation coefficient;
deducing the overall system evaluation efficiency E according to the unit model expression of the system reliability, the system dependency and the system operation capacity, wherein E =
For the result index vector, the evaluation of the shunt network running condition of the traffic running actual index specifically designed for specific requirements in the system is represented as follows:
and regressing the numerical value of the system efficiency layer V according to the weight coefficient of the specific road network:
and finally, performing mapping regression from the V layer to the P layer according to the formula to realize the integrity of the overall system efficiency framework.
Further, the method also comprises the step of S6:
inducing according to a learning mode of the model, carrying out primary cleaning on the data sample according to the estimated value of the preparation area and the overall data of the test sample volume, carrying out anomaly evaluation analysis on the data in the primary cleaning, and carrying out secondary cleaning after the data in the primary cleaning is removed; carrying out error induction on the secondary cleaning data, and recording and warehousing the data to obtain a data regression model; analyzing and judging the operation efficiency, safety and reliability of each item of traffic in the model; and fitting the optimal operation scheme according to the model, outputting corresponding model results, and recording the test actual data model results into a warehouse.
The invention has the beneficial effects that:
the invention provides a relative systematic scheme aiming at different road test conditions based on a mixed traffic flow model under a specific test scene, and according to a multidisciplinary cross thought, a hierarchical mixed traffic flow system efficiency model is designed by referring to a system engineering model in consideration of the fact that the overall traffic environment can be in a more systematic and controllable form under the participation of an automatic driving vehicle, and the model covers most participants in the overall traffic process.
The invention has more comprehensive research entry points on the automatic driving mixed flow; the model theory in the system engineering is fully utilized to construct an overall efficiency model for the hybrid traffic system in which the automatic driving vehicles participate, and a quantized data structure can better respond to the automatic driving participants in the vehicle-road cooperative network; the complete traffic operation condition influence relationship can provide a better theoretical reference basis for traffic decision makers in traffic control modes.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description will be briefly introduced, and it is obvious that the drawings in the following description are an embodiment of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts according to the drawings:
FIG. 1 is a schematic overview of the process of the present invention;
FIG. 2 is a schematic diagram of step S1 of the present invention;
FIG. 3 is a schematic diagram of step S2 of the present invention;
FIG. 4 is a schematic diagram of step S5 of the present invention;
FIG. 5 is a mixed flow traffic system hierarchy of the present invention.
Detailed Description
The embodiment provides a method for evaluating the performance of a hybrid transportation system based on a double-layer P-ADC model (i.e., a P-E model) under the coupling of multi-scenario condition factors, which refers to a general flow diagram shown in fig. 1, and includes the following steps:
s1, as shown in a figure 1 and a figure 2, starting from the dynamics of automatic driving and man-made driving vehicles, and analyzing the behavior mode of the vehicles in a mixed traffic flow by combining the characteristics of the vehicles; firstly, starting from the dynamics of automatic driving and man-made driving vehicles, the characteristics of the vehicles are combined, and the stress characteristics of the vehicles during the driving process are determined. Based on the method, the maximum acceleration and deceleration and the turning corner speed which can be achieved by various types of vehicles in actual road running are obtained. The evaluation then calculates its closed-loop braking behavior, comfort braking behavior, speed and acceleration control behavior, acceptable clearance and merge thresholds, steering behavior, etc. Performing subsequent analysis according to the basic attribute behavior information of different vehicle types;
s2, constructing an optimized traffic capacity under a complex mixed flow;
s3, constructing a mixed traffic running condition environment attribute layer, wherein the step is not sequential to the step S2;
s4, constructing comprehensive efficiency of hybrid traffic operationLayer, obtaining system availability
Task credibility
And system job capability function
And a system unit weight matrix T;
s5, as shown in FIG. 4, simulation analysis of a typical scene environment is carried out in the step, and then an overall operation condition evaluation method and a guidance scheme are constructed. Wherein the availability of said system
Task credibility
System operation capability function
To derive an overall system evaluation performance E, wherein E =
For the result index vector, the shunt network running condition evaluation of the traffic running actual index of the specific design aiming at the specific requirement in the system is expressed; comprehensively evaluating the overall efficiency calculation result V according to the P-E system efficiency model calculation scheme, wherein the overall efficiency calculation result V is in functional relation with the results of various road environmental conditions and actual traffic running conditions under the actual condition;
s6, induction is carried out according to a learning mode of the model, a data sample is cleaned for the first time according to the pre-estimated value of the preparation area and the overall data of the test sample amount, the data in the first cleaning is evaluated and analyzed for abnormality, and the data after being removed is cleaned for the second time; carrying out error induction on the secondary cleaning data, and recording and warehousing the data to obtain a data regression model; analyzing and judging the operation efficiency, safety and reliability of each item of traffic in the model; and fitting the optimal operation scheme according to the model, outputting corresponding model results, and recording the test actual data model results into a warehouse.
As shown in fig. 1 and 3, in step S2, the method for constructing optimal traffic capacity under a complex mixed flow includes: the method comprises the steps of evaluating a basic car following mode of the whole traffic flow by adopting an optimized cooperative adaptive cruise control intelligent driver car following model according to the coupling relation among environment influence factors such as actual running road scene environment, weather change, permeability of the automatic driving mixed traffic flow, sudden accidents and the like, recalculating the traffic capacity of the mixed traffic flow in which the automatic driving car participates at different levels and different permeabilities according to the characteristics of traffic participants, describing the road bearing capacity of a mixed traffic running area on the basis, and evaluating the actual running condition of the whole mixed traffic flow.
Specifically, step S2 includes the steps of:
s21: when the front vehicle or the side vehicle is observed to be an automatic driving vehicle, the original safety distance formula is as follows:
wherein
Is constant and refers to the headway of a vehicle driven by a person,
indicating the vehicle speed of the vehicle at time t,
showing the distance between the head of the vehicle and the tail of the front vehicle,
indicating the length of the vehicle body; considering that the original IDM model has no way to better explain the difference of the mixed vehicle flowThe following behavior characteristics of the type vehicle when meeting the opposite side are obtained, so that a model is constructed to describe the following process of the vehicle in the mixed flow by referring to a following galloping path under a speed optimization model (FVD) on the basis of the IDM model and combining the following behavior under the specific behavior condition of the automatic driving adaptive cruise. The intelligent driver following model and the CACC following model calibrated by a route laboratory are used for describing the following behaviors of CAVs, and the model is based on real vehicle track data and can capture the behavior characteristics of the automatic driving vehicle.
S22: on the basis of the step S21, a CACC following model is used to describe following behaviors of the CAVs in consideration of a formal mode of the bicycle itself, as shown in the following formula:
in the formula (2), the reaction mixture is,
the speed of the previous control time;
e is the error between the actual vehicle distance and the expected vehicle distance;
Δ x is the headway
velocity in the formula (2)
Then, a calculation formula of the expected acceleration of the automatic driving automobile under the mixed flow following model can be obtained, and the calculation formula is shown as the following formula:
therefore, basic complete model definition is constructed according to basic speed, acceleration and vehicle driving modes of the vehicle in a following model under a specific automatic driving vehicle. Calibrating an optimized mixed flow following model according to results obtained in vehicle analysis and simulation experiments in real traffic flow, wherein the optimal parameters of the model are
=0.01s， 
=0.45s−1，
=0.25。
S23: the method for decomposing the integral mixed traffic flow into n traffic flows which have the same locomotive time interval and are theoretically and stably followed comprises the following steps:
in the formula (4), in the formula,
the time interval of the locomotive;
wn is the proportionality coefficient of the multi-strand vehicle;
in the standard flow, the head interval can be disassembled into:
substituting the formula into the formula, carrying out corresponding conversion, and calculating to obtain the integrated traffic flow comprehensive flow of the whole plurality of traffic flows as follows:
according to a lane change theoretical model in inference, the overall road bearing capacity is deduced to be represented as:
in step S21, an intelligent driver following model is constructed to optimize a following model of the vehicle, the expression of the intelligent driver following model is as follows:
wherein:
delta is a correlation coefficient;
referring to fig. 5, in step S4, an ADC model is used to construct a hybrid traffic operation comprehensive performance layer; the layer D is an attribute transfer unit, the layer A is a main capacity unit, the layer E is an efficiency calculation result unit, and the control mode of the model depends on a layered structure. S4 specifically includes the following steps:
s41, adopting an efficiency influence control model for the lower model unit P frame, wherein the overall efficiency value of the P frame and the upper layer meets the functional relation condition, and the corresponding expression is as follows:
that is, P units are individual response relationships to E in the system framework, where:
P=
（11）
wherein the content of the first and second substances,
the attribute parameters of the physical layer are used for representing road traffic environment influence parameters;
converting the actual road environment into a value;
is a preset standard environment parameter value.
The P layer is controlled by the range of the sub-control layer X, Y layer, and the P matrix has a standard matrix for a specific road network
And the fluctuation matrix
Wherein
In order to predict the various environmental parameters of the actual scene criteria,
the maximum influence change of each condition considered in the actual scene is as follows:
specifically, in step S5, the upper model unit is constructed by modifying the ADC performance model based on optimization in conventional system engineering. The integrated system performance indicator layer V contains system availability
Task credibility
And system specified job capability function
System unit weight matrix T, using vectors
Represents:
in the formula
The method is used for evaluating the efficiency of a specific measurement index in the process of realizing a task by a system;
system availability
The system is a measure of the degree of use and a specific state metric of the system at a certain moment in executing a task;
task credibility
Representing the probability of the system completing a specified function during use;
system specified job capability function
Representing the ability of the system to run or work.
In the system, the system availability
Consider the operation guarantee status, fault status, wait status, etc. of each subsystem. The index that the working condition at a certain moment in a specific road section meets the capability is represented in the actual road, namely the standard completion working state probability of a local road section. In a standard equipment system, the calculation formula of A is as follows:
wherein MTBF is the mean barrier-free working time, and MTTR is the mean repair time. In the traffic system, MTBF represents free stream movement condition time, and MTTR represents transit capacity reduction condition repair time. The values are taken according to the predicted peak flow changes in the actual traffic flow.
Criteria in autonomous driving dedicated lanes according to lane management variations
Aiming at the importance of different roads in the whole traffic network, a specific road has a weight index for performing coefficient regression on the system efficiency, and a matrix T is a weight matrix:
wherein
Is a clockwise road weight;
task confidence due to n possible states of the system
Is an n x n matrix, and in the whole mixed traffic flow running state,
probability that a vehicle departing from the system at location i at the beginning of use will transfer to location j during use:
in the formula:
typically, the system specifies a job capability function
Is an n-by-n matrix (also called dependency matrix), and divides the operation capability layer C into a main layer C and a sub-layer B according to the actual automatic driving mixed flow test requirement in the operation of the traffic system, wherein
The service level from the departure point i to the destination point j is represented, namely the running speed and the ratio of the traffic volume to the basic traffic capacity, and the capacity of the system for completing the target is represented as follows:
the B sub-layer also represents the system operation capacity, represents the whole safety degree of the traffic operation in the mixed flow, the system safety degree is an n x n matrix, and the system safety degree is the whole safety degree of the traffic operation in the traffic system operation
The index calculation result in the SSAM security analysis from the departure point i to the destination point j is shown, and is a probability coefficient of collision between system links, namely:
for the C system, the selection of the sub-layer model can be considered according to the actual test requirements, and for the overall systematic planning, the system operation capacity comprises the traffic capacity and the traffic safety evaluation coefficient.
Deducing the overall system evaluation efficiency E according to the unit model expression of the system reliability, the system dependency and the system operation capacity, wherein E =
For the result index vector, the evaluation of the shunt network running condition of the traffic running actual index specifically designed for specific requirements in the system is represented as follows:
and regressing the numerical value of the system efficiency layer V according to the weight coefficient of the specific road network:
and finally, performing mapping regression from the V layer to the P layer according to the formula to realize the integrity of the overall system efficiency framework.
The invention provides a high-precision dynamic stress model of a mixed flow vehicle aiming at the behavior characteristics of an automatic driving vehicle in a mixed flow, arranges the characteristics of acceleration and deceleration, optimal bearing deceleration, closed-loop braking, steering behavior and the like of all vehicles, optimizes the traffic flow following theory under the traditional intelligent driving, constructs an optimized FVD mixed traffic flow following model on a microscopic level, and calculates the road traffic capacity based on the model. On the basis, various road environment condition influence factors appearing in the actual traffic running condition are fully considered, the mixed traffic flow conditions under different permeabilities are analyzed, and a mixed traffic test area bearing capacity model is provided. The invention analyzes, summarizes and induces the whole traffic system under the automatic driving mixed traffic flow, divides the traffic system into five levels by combining the requirements of the model, optimally designs a double-layer P-E model by referring to an efficiency evaluation model in system engineering, wherein: the lower layer P model is a road environment vector, and comprises three sublayers A, D and C with the upper layer E model, and is used for respectively evaluating the usability, the reliability and the operation capacity of the system and constructing a functional relation between an environment index and an operation efficiency index. On the basis, P-E model simulation data analysis under the condition of appointed putting of a certain permeability is researched for a typical annular test area, and the optimization evaluation is carried out on the whole traffic efficiency in the test area by combining a typical traffic control method.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. A method for evaluating the efficiency of a hybrid traffic system under the participation of an automatic driving automobile is characterized by comprising the following steps:
s1, analyzing the behavior characteristics of a vehicle in mixed traffic with automatic driving and artificial driving;
s2, constructing an optimized traffic capacity under a complex mixed flow;
s3, constructing a mixed traffic running condition environment attribute layer, wherein the step is not sequential to the step S2;
s4, constructing a hybrid traffic operation comprehensive performance layer to obtain a system availability matrix
Task confidence matrix
And a system job capability matrix
And a system unit weight matrix
；
S5, the availability matrix of the system
Task confidence matrix
System operation capability matrix
The unit model is expressed, and the overall system evaluation performance is deduced, and the mathematical expression is a system performance matrix
=
Representing the evaluation of the shunt network running condition of the traffic running actual index of the specific design aiming at the specific requirement in the system for the result index vector, wherein m represents the number of roads in the design scene; comprehensively evaluating the overall efficiency calculation result V according to the P-E system efficiency model calculation scheme, wherein the overall efficiency calculation result V is in functional relation with the results of various road environmental conditions and actual traffic running conditions under the actual condition;
wherein:
in the step S4, constructing a hybrid traffic operation comprehensive performance layer by adopting an ADC model; the control mode of the model depends on a layered structure, the D layer is an attribute transfer unit, the model is a system credibility layer, and the mathematical expression form of the model is a task credibility matrix
(ii) a The A layer is a main capacity unit, and is a system availability layer in the model, and the mathematical expression of the A layer is a system availability matrix
(ii) a The layer C is a system capacity unit, and is a system operation capacity layer in the model, and the mathematical expression of the layer C is a system operation capacity matrix
(ii) a The E layer is a performance calculation result unit, and is a performance attribute layer in the model, and the mathematical expression of the E layer is a system performance matrix
；
The step of S4 includes the steps of:
s41, adopting an efficiency influence control model for the lower model unit P frame, wherein the overall efficiency value of the P frame and the upper layer meets the functional relation condition, and the corresponding expression is as follows:
that is, P units are individual response relationships to E in the system framework, where:
P=
wherein the content of the first and second substances,
the n-th item of the different influence variables, n is the total number of the influence variables, and i is the ith item of the influence variables;
is a physical layer attribute parameter for representing road traffic environment influence parameter,
converting the actual road environment into a value;
setting a preset standard environment parameter value;
the P layer is controlled by the range of the sub-control layer X, Y, and for a specific road network, the P matrix has a standard matrix X and a fluctuation matrix Y, and the two matrixes are formed as follows, wherein
In order to predict the various environmental parameters of the actual scene criteria,
the maximum influence change of each condition considered in the actual scene is as follows:
in the formula PimaxThe meaning of (A) is: the maximum influence difference coefficient of the ith influence variable;
Piminthe meaning of (A) is: the minimized influence difference coefficient of the ith influencing variable;
in step S5, the integrated system performance indicator layer V includes a system availability matrix
Task confidence matrix
And a system job capability matrix
System unit weight matrix
Vector for V
Represents:
in the formula
The system is used for evaluating the efficiency of a specific measurement index in the task realization process; m is the total amount of the efficiency index coefficient;
system availability matrix
The system is a measure of the degree of use and a specific state metric of the system at a certain moment in executing a task;
task confidence matrix
Representing the probability of the system completing a specified function during use;
system operation capability matrix
Represents the capability of a system to run or operate;
system availability matrix
In an actual road, an index indicating that the performance is satisfied at a working condition at a certain time in a specific road section, in a standard equipment system,
the calculation formula of (2) is as follows:
wherein the content of the first and second substances,
represents the f term
The coefficient of the matrix is used for measuring the using state of each sub task, namely the working capacity of the road section f; in the traffic system, it is necessary to provide a traffic light,
the time of the free stream motion state is shown,
representing the repair time of the traffic capacity reduction condition, and taking a value according to the predicted peak flow change in the actual traffic flow;
criteria in autonomous driving dedicated lanes according to lane management variations
Aiming at the importance of different roads in the whole traffic network, the specific road has a weight index for performing coefficient regression for the system efficiency, and a system unit weight matrix
As a weight matrix:
wherein
Is a clockwise road weight;
since the system has m possible states, the task confidence matrix
Is an m x m matrix, and in the whole mixed traffic flow running state,
probability of vehicle departure at u point for the system at the beginning of use transferring to w point during use:
in the formula:
system operation capability matrix
Is an m-by-m matrix, and divides the operation capability layer C into a main layer C and a sub-layer B according to the actual automatic driving mixed flow test requirement in the operation of the traffic system,
the service level from the departure point u to the destination point w is shown, namely the running speed and the ratio of the traffic volume to the basic traffic capacity, and the capacity of the system to achieve the target is shown as follows:
the B sub-layer also expresses the system operation capacity, and in the traffic flow, the mathematical expression is in the form of a matrix
Is an m-m matrix for representing the overall degree of safety of traffic operation in the mixed flow, and the traffic system operation
The index calculation result in the SSAM security analysis from the departure point u to the destination point w is shown, and is a probability coefficient of collision between system links, that is:
for the C system, the selection of the sub-layer model can be considered according to the actual test requirements, and for the overall systematic planning, the system operation capacity comprises traffic capacity and a traffic safety evaluation coefficient;
the mathematical form derivation of the system performance attribute layer E is carried out by the system availability layer A, the system credibility layer D, the system operation capability layer C and the corresponding mathematical expression matrix form, and the system performance is expressed as the matrix
And regressing the value of the performance index layer V of the specific comprehensive system according to the weight coefficient of the specific road network:
and finally, performing mapping regression from the V layer to the P layer according to the formula to realize the integrity of the overall system efficiency framework.
2. The method for evaluating the performance of a hybrid transportation system under participation of an autonomous vehicle as claimed in claim 1, wherein the method for constructing the optimized trafficability under the complex hybrid flow in step S2 comprises: the method comprises the steps of evaluating a basic car following mode of the whole traffic flow by adopting an optimized cooperative adaptive cruise control intelligent driver car following model according to the coupling relation among environment influence factors of actual running road scene environment, weather change, permeability of the automatic driving mixed traffic flow and sudden accidents, recalculating the traffic capacity of the mixed traffic flow participated by the automatic driving cars under different levels and different permeabilities according to the characteristics of traffic participants, describing the road bearing capacity of a mixed traffic running area on the basis, and evaluating the actual running condition of the whole mixed traffic flow.
3. The method for evaluating the performance of a hybrid transportation system under participation of an autonomous vehicle according to any one of claims 1 to 2, further comprising S6:
inducing according to a learning mode of the model, carrying out primary cleaning on the data sample according to the estimated value of the preparation area and the overall data of the test sample volume, carrying out anomaly evaluation analysis on the data in the primary cleaning, and carrying out secondary cleaning after the data in the primary cleaning is removed; carrying out error induction on the secondary cleaning data, and recording and warehousing the data to obtain a data regression model; analyzing and judging the operation efficiency, safety and reliability of each item of traffic in the model; and fitting the optimal operation scheme according to the model, outputting corresponding model results, and recording the test actual data model results into a warehouse.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011468143.7A CN112614344B (en) | 2020-12-14 | 2020-12-14 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011468143.7A CN112614344B (en) | 2020-12-14 | 2020-12-14 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112614344A CN112614344A (en) | 2021-04-06 |
| CN112614344B true CN112614344B (en) | 2022-03-29 |
Family
ID=75233827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011468143.7A Active CN112614344B (en) | 2020-12-14 | 2020-12-14 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614344B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010967B (en) * | 2021-04-22 | 2022-07-01 | 吉林大学 | Intelligent automobile in-loop simulation test method based on mixed traffic flow model |
| CN113382064A (en) * | 2021-06-08 | 2021-09-10 | 重庆大学 | Traffic capacity estimation method and device considering CAV (vehicle Access control) special lane of intelligent internet vehicle |
| CN113409594A (en) * | 2021-07-29 | 2021-09-17 | 苏州大学 | Ramp signal control optimization method and system based on reinforcement learning |
| CN113779864B (en) * | 2021-08-06 | 2024-04-26 | 同济大学 | Method and device for constructing running design area for automatic driving automobile |
| CN113838287B (en) * | 2021-10-18 | 2022-08-12 | 清华大学深圳国际研究生院 | Method and device for judging mixed traffic flow state in internet automatic driving environment |
| CN114187759B (en) * | 2021-11-19 | 2023-01-03 | 东南大学 | Road side unit driving assistance method and device based on data driving model |
| CN114563196B (en) * | 2022-02-22 | 2022-12-16 | 上清童子(北京)投资顾问有限公司 | Method for checking usability and reliability of automatic driving automobile |
| CN114613144B (en) * | 2022-04-07 | 2024-04-30 | 重庆大学 | Method for describing motion evolution law of hybrid vehicle group based on Embedding-CNN |
| CN115116217B (en) * | 2022-05-26 | 2023-09-26 | 东北林业大学 | Dynamic measuring and calculating method and system for saturation flow rate and starting loss time of lane |
| CN115116249B (en) * | 2022-06-06 | 2023-08-01 | 苏州科技大学 | Method for estimating different permeability and road traffic capacity of automatic driving vehicle |
| CN115206093B (en) * | 2022-06-21 | 2023-08-29 | 同济大学 | Traffic flow control method based on intelligent network-connected vehicle |
| CN115116225B (en) * | 2022-06-23 | 2023-08-04 | 上海交通大学 | Data-driven random model predictive control method for mixed traffic flow |
| CN116030632B (en) * | 2023-02-10 | 2023-06-09 | 西南交通大学 | Mixed traffic flow-oriented performance index calculation method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544934A (en) * | 2018-12-19 | 2019-03-29 | 同济大学 | Efficiency safety monitoring system based on urban intersection mixed traffic flow three-dimensional track |
| CN109709956A (en) * | 2018-12-26 | 2019-05-03 | 同济大学 | A kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding |
| CN109733415A (en) * | 2019-01-08 | 2019-05-10 | 同济大学 | A kind of automatic Pilot following-speed model that personalizes based on deeply study |
| CN111754777A (en) * | 2020-07-10 | 2020-10-09 | 清华大学 | Microscopic traffic simulation method for unmanned and manned mixed traffic flow |
| CN111862600A (en) * | 2020-06-22 | 2020-10-30 | 中汽研智能网联技术(天津)有限公司 | Traffic efficiency assessment method based on vehicle-road cooperation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11447152B2 (en) * | 2019-01-25 | 2022-09-20 | Cavh Llc | System and methods for partially instrumented connected automated vehicle highway systems |
-
2020
- 2020-12-14 CN CN202011468143.7A patent/CN112614344B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544934A (en) * | 2018-12-19 | 2019-03-29 | 同济大学 | Efficiency safety monitoring system based on urban intersection mixed traffic flow three-dimensional track |
| CN109709956A (en) * | 2018-12-26 | 2019-05-03 | 同济大学 | A kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding |
| CN109733415A (en) * | 2019-01-08 | 2019-05-10 | 同济大学 | A kind of automatic Pilot following-speed model that personalizes based on deeply study |
| CN111862600A (en) * | 2020-06-22 | 2020-10-30 | 中汽研智能网联技术(天津)有限公司 | Traffic efficiency assessment method based on vehicle-road cooperation |
| CN111754777A (en) * | 2020-07-10 | 2020-10-09 | 清华大学 | Microscopic traffic simulation method for unmanned and manned mixed traffic flow |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112614344A (en) | 2021-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112614344B (en) | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation | |
| CN111376954B (en) | Train autonomous scheduling method and system | |
| CN102044149B (en) | City bus operation coordinating method and device based on time variant passenger flows | |
| CN111369181A (en) | Train autonomous scheduling deep reinforcement learning method and module | |
| Rahmati et al. | Towards a collaborative connected, automated driving environment: A game theory based decision framework for unprotected left turn maneuvers | |
| Du et al. | A hierarchical framework for improving ride comfort of autonomous vehicles via deep reinforcement learning with external knowledge | |
| CN114283607A (en) | Multi-vehicle collaborative planning method based on distributed crowd-sourcing learning | |
| CN112784485B (en) | Automatic driving key scene generation method based on reinforcement learning | |
| CN111413932A (en) | Information management and scheduling system and method for unmanned electric cleaning vehicle | |
| Portilla et al. | Model-based predictive control for bicycling in urban intersections | |
| Yang et al. | Longitudinal tracking control of vehicle platooning using DDPG-based PID | |
| Bhouri et al. | An agent-based computational approach for urban traffic regulation | |
| CN117032203A (en) | Svo-based intelligent control method for automatic driving | |
| Miao et al. | Highly Automated Electric Vehicle (HAEV)-based mobility-on-demand system modeling and optimization framework in restricted geographical areas | |
| Guan et al. | Learn collision-free self-driving skills at urban intersections with model-based reinforcement learning | |
| Sur | UCRLF: unified constrained reinforcement learning framework for phase-aware architectures for autonomous vehicle signaling and trajectory optimization | |
| Jiang et al. | A reinforcement learning benchmark for autonomous driving in general urban scenarios | |
| Li et al. | Biobjective Optimization and Evaluation for Transit Signal Priority Strategies at Bus Stop‐to‐Stop Segment | |
| Hao et al. | Developing an adaptive strategy for connected eco-driving under uncertain traffic and signal conditions | |
| Rezaee | Decentralized coordinated optimal ramp metering using multi-agent reinforcement learning | |
| Hult et al. | A semidistributed interior point algorithm for optimal coordination of automated vehicles at intersections | |
| Othman et al. | Urban road traffic fuel consumption optimization via variable speed limits or signalized access control: A comparative study | |
| Liu | Optimizing Energy Savings for a Fleet of Commercial Autonomous Vehicles via Centralized and Decentralized Platooning Decisions | |
| Torabi | Fuel-efficient driving strategies | |
| Ekeila | Dynamic transit signal priority |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |