A highway suitability evaluation method for an automatic driving vehicle fleet

Abstract

The application relates to a highway suitability evaluation method for an automatic driving vehicle team, and belongs to the field of road traffic control. The method obtains basic information of an evaluation highway section, traffic flow information, automatic driving vehicle team information and automatic driving and traditional manual driving interactive vehicle information as input information, adopts a virtual test method, calculates the available visual distance of the automatic driving vehicle team and the interactive vehicle under the obtained traffic flow and the automatic driving vehicle team formation scheme, constructs a visual distance safety failure function function of the automatic driving vehicle team and the interactive vehicle according to a demand visual distance model and a structure reliability theory, calculates a visual distance safety failure probability, and finally determines the highway section suitability evaluation result for the automatic driving vehicle team according to the visual distance safety allowable failure probability of different levels. The application can efficiently and safely quantitatively evaluate the suitability of the automatic driving vehicle team on the evaluation highway section, and identify dangerous sections with insufficient visual distance of the automatic driving vehicle team.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of road traffic control, and particularly relates to a highway suitability evaluation method for an automatic driving vehicle fleet. BACKGROUND

[0002] With the continuous iteration and maturity of intelligent driving technology, and the gradual perfection of the compact cooperative control form of the vehicle fleet, the automatic driving vehicle fleet has become a key technical entity deployment direction in the intelligent transportation system, due to its significant potential in improving road traffic efficiency, optimizing the travel comfort of the driver and passenger, reducing the operation load of the driver, and even reducing the emission pollution in the collective driving process of the vehicle. At present, the automatic driving vehicle fleet has been initially implemented in scenarios such as logistics transportation, port cargo transfer, and fixed route area connection, but the current main operating environment is mostly in a closed or semi-closed form, the road conditions are relatively stable, the traffic participants are simple, and the automatic driving vehicle fleet is less affected by factors such as complex traffic flow interaction and dynamic road condition changes in the actual structured road environment, which makes it difficult for the existing technical solutions to directly adapt to the open highway scenario, and seriously restricts the application process of the automatic driving vehicle fleet in a wider field.

[0003] At present, the research on the highway suitability evaluation of automatic driving mostly focuses on the single vehicle level, and is carried out around the traffic capacity and safety performance of a single vehicle model under specific highway conditions, and a systematic evaluation framework for the automatic driving vehicle fleet has not yet been formed. At present, the automatic driving vehicle fleet usually adopts a truck model, and the highway is the core scenario for the operation of the truck. The core difference between the closed scenario and the highway is that there are a large number of dynamic interactive vehicles, which include small cars, trucks and other vehicle models, and the driving behavior of these interactive vehicles has a high degree of uncertainty. Therefore, in order to promote the safe and efficient application of the automatic driving vehicle fleet in the open highway environment, it is urgent to build a highway suitability evaluation method for the automatic driving vehicle fleet. SUMMARY

[0004] The purpose of the present application is to provide a highway suitability evaluation method for an automatic driving vehicle fleet, which comprehensively considers the sight distance safety of the automatic driving vehicle fleet and the surrounding vehicles on the highway, and can efficiently and safely quantitatively evaluate the suitability of the automatic driving vehicle fleet on the evaluation highway section.

[0005] To achieve the above-mentioned purpose, the technical solution of the present application is: a highway suitability evaluation method for an automatic driving vehicle fleet, comprising the following steps:

[0006] Step S1, obtaining the basic information of the evaluation highway section, the traffic flow information, the automatic driving vehicle fleet information and the interactive vehicle information;

[0007] Step S2, using a virtual test method to calculate the available sight distance of the automatic driving vehicle fleet and the interactive vehicles under the obtained traffic flow and automatic driving vehicle fleet formation scheme.

[0008] Step S3, according to the required visibility model, using the structural reliability theory to construct the visibility safety failure function function of the automatic driving vehicle team and the interactive vehicle, and calculate the visibility safety failure probability;

[0009] Step S4, according to the visibility safety allowable failure probability of different levels, determine the road section suitability evaluation result for the automatic driving vehicle team.

[0010] Further, in step S1, the basic information of the evaluated road section includes the design speed, the number of lanes, the lane width, the hard shoulder width, the soil shoulder width, the super-elevation, the lateral clearance, the roadside and the in-road obstacle type; the traffic flow information includes the opposite traffic flow, the same direction traffic flow, the opposite vehicle speed, the same direction vehicle speed; the automatic driving vehicle team information includes the lead vehicle and the following vehicle system type, the perception-braking reaction time, the braking deceleration, the system preset braking deceleration in the driver takeover time, the driver takeover time, the lead vehicle speed, the following vehicle spacing, the number of following vehicles; the interactive vehicle information includes: vehicle system type, vehicle-mounted perception sensor configuration and layout scheme, perception function information, driving speed, perception-braking reaction time, perception-steering reaction time, braking deceleration, overtaking acceleration, system preset braking deceleration in the driver takeover time, driver takeover time.

[0011] Further, the lead vehicle system type includes 0 to 5 levels of driving automation level, and the following vehicle system type includes 3 to 5 levels of driving automation level.

[0012] Further, the interactive vehicle includes passenger cars and trucks, and the interactive vehicle system type includes 0 to 5 levels of driving automation level.

[0013] Further, the vehicle-mounted perception sensor configuration and layout scheme at least includes: perception sensor type, detection distance, horizontal plane field of view angle, vertical plane field of view angle, horizontal angle resolution, vertical angle resolution, installation position; the perception function information at least includes: static and dynamic obstacle perception algorithm.

[0014] Further, in step S2, the specific implementation is:

[0015] Step S21, taking the obtained basic information of the evaluated road section, traffic flow information, automatic driving vehicle team information and interactive vehicle information as an input parameter set, using a virtual test method to automatically build a virtual analysis scene in a software environment; the virtual analysis scene includes the automatic driving vehicle team self-vehicle lane visibility failure scene, the interactive vehicle overtaking the automatic driving vehicle team self-vehicle lane visibility failure scene and the interactive vehicle overtaking the automatic driving vehicle team slow lane visibility failure scene;

[0016] Step S22, based on the established automatic driving vehicle fleet itself lane visibility failure scene, the interactive vehicle overtaking the automatic driving vehicle fleet when the self-vehicle lane visibility failure scene and the interactive vehicle overtaking the automatic driving vehicle fleet when the slow lane visibility failure scene, respectively carry out virtual testing, the specific process is as follows:

[0017] Step S221, output the farthest driving path distance between the leading vehicle and the static obstacle in front of the self-vehicle lane that can be detected by the interactive vehicle, as the available visibility ASD1 of the leading vehicle of the automatic driving vehicle fleet;

[0018] Step S222, output the farthest driving path distance between the static obstacle in front of the self-vehicle lane that can be detected by the interactive vehicle located in all lanes except the slow lane on the same side, as the available visibility ASD2 of the self-vehicle lane visibility failure scene when the interactive vehicle overtakes the automatic driving vehicle fleet;

[0019] Step S223, output the farthest driving path distance between the static obstacle in front of the slow lane that can be detected by the interactive vehicle located in all lanes except the slow lane on the same side, as the available visibility ASD3 of the slow lane visibility failure scene when the interactive vehicle overtakes the automatic driving vehicle fleet;

[0020] Step S23, assuming that the arrival of the opposite vehicle follows a Poisson process, the available visibility function of the interactive vehicle visibility failure scene is established:

[0021]

[0022] In the formula, V0 represents the average speed of the opposite vehicle; P represents the assumed probability that the observed gap is greater than or equal to the calculated gap; q represents the average flow of the opposite traffic flow;

[0023] Step S24, according to steps S222, S23, determine the minimum value of the available visibility of the self-vehicle lane visibility failure scene when the interactive vehicle overtakes the automatic driving vehicle fleet:

[0024]

[0025] Step S25, according to steps S223, S23, determine the minimum value of the available visibility of the slow lane visibility failure scene when the interactive vehicle overtakes the automatic driving vehicle fleet:

[0026] .

[0027] Further, step S3, the specific implementation is:

[0028] Step S31, according to the driving automation level, establish the required stopping distance function RSD1 of the leading vehicle of the automatic driving vehicle fleet:

[0029]

[0030] In the formula, RSD 1-j t represents the required stopping sight distance for the j-th level of driving automation; p_s It refers to the sensing response time of an L1 or L2 automation system; A d It refers to the automatic deceleration of the autonomous driving system or after the driver takes over; t pb_h It is the human driver's perception-braking reaction time; t pb_s It refers to the perception-braking reaction time of L3 and L4 autonomous driving systems; t T This is the time when a human driver takes over from the disengaged Level 3 automated system; A dp It is in t T The preset deceleration is activated during the process by the L3 automation system preparing to disengage;

[0031] Step S32: Establish the parking sight distance function RSD2 for the interactive vehicle based on the driving automation level:

[0032]

[0033] In the formula, RSD 2-i-j This represents the required stopping sight distance for the j-th level driving automation system in the i-th lane on the left, excluding the slow lane.

[0034] Step S33: Establish the overtaking sight distance function RSD3 for the interactive vehicle based on the driving automation level.

[0035]

[0036] In the formula, RSD 3-i-j t1 represents the required overtaking sight distance for the j-th level driving automation system in the i-th lane on the left (excluding the slow lane); t1 is the acceleration time when the interactive vehicle begins overtaking; M is the speed difference between the interactive vehicle and the autonomous driving fleet; t2 is the travel time of the interactive vehicle in the overtaking lane; a P d is the preset acceleration during the lane change phase; d is the safe distance between the overtaking vehicle and the oncoming vehicle after the overtaking maneuver is completed.

[0037] Step S34: Construct the line-of-sight safety failure function Z for the autonomous driving fleet and interactive vehicles based on structural reliability theory. s The formula is:

[0038]

[0039] Step S35: Based on the obtained basic information of the evaluation highway segment, traffic flow information, autonomous driving fleet information, and interactive vehicle information, determine A. dp t1, t2, M, a P The calculated value of d, t pb_h t p_st T t pb_s t ps_h t ps_s The mean, standard deviation, and probability distribution form;

[0040] Step S36: Calculate Z s The line-of-sight safety tolerance failure probability P f The formula is:

[0041]

[0042] In the formula, P(ASD5-RSD) 1-j <0 indicates the probability of line-of-sight failure for an autonomous driving fleet, P(ASD6-RSD) 2-i-j <0 indicates the probability of lane sight failure when the interactive vehicle overtakes the autonomous vehicle convoy, P(ASD3-RSD) 4-i-j <0) indicates the probability of slow lane visibility failure when the interactive vehicle overtakes the autonomous vehicle fleet.

[0043] Furthermore, step S4 is implemented as follows:

[0044] Step S41: Set the line-of-sight safety tolerance failure probability threshold P threshold ;

[0045] Step S42: Determine the acceptable failure probability P for line-of-sight safety. f With P threshold By performing a difference comparison, the drivability assessment result W is obtained, and the formula is:

[0046]

[0047] In the formula, when W=1, it indicates that the current road drivability of the autonomous driving fleet meets the safe driving condition; when W=0, it indicates that the current road drivability of the autonomous driving fleet is in a critical safe state; when W=-1, it indicates that the current road drivability of the autonomous driving fleet does not meet the safe driving requirements.

[0048] The present invention also provides an electronic device including a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method described above.

[0049] The present invention also provides a computer-readable storage medium having stored thereon computer program instructions that can be executed by a processor, wherein when the processor executes the computer program instructions, it can implement the steps of the method described above.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] (1) The present application considers evaluating the comprehensive influence of the basic information of the road section, the traffic flow information, the automatic driving vehicle team information, and the automatic driving and traditional manual driving interactive vehicle information, and can be compatible with different system types and driving levels, so that the evaluation result is more real and effective, and the vacancy in the field is filled;

[0052] (2) The present application has good compatibility with existing automatic driving virtual testing technology, which on the one hand solves the problem that the calculation result of the theoretical calculation mode is often unrealistic and too ideal, and on the other hand, compared with field testing, both cost control and safety guarantee are significantly optimized, and practicality and economy are taken into account;

[0053] (3) The method of the present application can efficiently and safely quantitatively evaluate the adaptability of the automatic driving vehicle team in the evaluation road section, identify dangerous road sections with insufficient visibility of the automatic driving vehicle team, provide theoretical reference for the design and optimization of the warning function of the automatic driving system, and conduct safety hazard investigation for the actual operation of the automatic driving system function test and the existing road infrastructure. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 is the implementation flowchart of the road adaptability evaluation method for the automatic driving vehicle team provided by the embodiment of the present application;

[0055] Figure 2 is the flowchart of constructing the link between the input information and the available visibility database according to the embodiment of the present application;

[0056] Figure 3 is the automatic driving vehicle team visibility failure scene diagram divided by the embodiment of the present application, wherein 1 is the road center line, 2 is the road lane line, 3 is the interactive vehicle, 4 is the automatic driving vehicle team following vehicle, 5 is the automatic driving vehicle team leading vehicle, 6 is the road obstacle, 7 is the farthest available visibility of the leading vehicle in theory, 8 is the right side line of the road, and 9 is the following vehicle following distance;

[0057] Figure 4 is the automatic driving vehicle team visibility failure scene diagram when the interactive vehicle overtakes the automatic driving vehicle team, wherein 1 is the road center line, 2 is the road lane line, 3 is the interactive vehicle, 4 is the automatic driving vehicle team following vehicle, 5 is the automatic driving vehicle team leading vehicle, 6 is the road obstacle, 8 is the right side line of the road, 9 is the following vehicle following distance, and 11 is the farthest available visibility of the interactive vehicle in theory;

[0058] Figure 5is a slow lane visual range failure scene diagram when the interactive vehicle overtakes the automatic driving vehicle team, wherein 1 is a highway center line, 3 is an interactive vehicle, 4 is a following vehicle of an automatic driving vehicle team, 5 is a leading vehicle of an automatic driving vehicle team, 6 is an in-road obstacle, 8 is a right side line of the highway, 9 is a following vehicle distance, 10 is an oncoming vehicle in the slow lane, 11 is the farthest available visual range of the interactive vehicle in theory, and 12 is a left side line of the highway;

[0059] Figure 6 is a flow chart of a visual range safety failure function of matching the automatic driving vehicle team and the interactive vehicle and calculating the visual range safety failure probability according to an embodiment of the present application;

[0060] Figure 7 is a flow chart of a highway suitability evaluation method for an automatic driving vehicle team according to an embodiment of the present application. DETAILED DESCRIPTION

[0061] The technical solutions of the present application will be described in detail below with reference to the accompanying drawings.

[0062] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present specification have the same meaning as generally understood by those skilled in the art to which the present application belongs.

[0063] It should be noted that the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form unless the context clearly indicates otherwise, and furthermore, it should be understood that when the terms "comprise" and / or "include" are used in the present specification, there is a feature, step, operation, device, component and / or combination thereof.

[0064] As shown in Figure 1 The present embodiment provides a highway suitability evaluation method for an automatic driving vehicle team, comprising the following steps:

[0065] Step S1, obtaining basic information of an evaluation highway section, traffic flow information, automatic driving vehicle team information and automatic driving and traditional human driving interactive vehicle information;

[0066] In step S1, the basic information of the evaluation highway section includes design speed, number of lanes, lane width, hard shoulder width, soil shoulder width, overheight, lateral clearance, and roadside and in-road obstacle type;

[0067] The traffic flow information includes oncoming traffic flow, same direction traffic flow, oncoming vehicle speed and same direction vehicle speed;

[0068] The automatic driving vehicle fleet information includes a lead vehicle and a following vehicle system type, a perception-braking reaction time t pbr , a braking deceleration A d , a braking deceleration A preset by the system within a driver takeover time dp , a driver takeover time t T , a lead vehicle speed, a following vehicle spacing, and a following vehicle number, wherein the lead vehicle system type includes a 0-5 level driving automation level, and the following vehicle system type includes a 3-5 level driving automation level.

[0069] The automatic driving and traditional manual driving interactive vehicle information includes a vehicle system type, a vehicle-mounted perception sensor configuration and layout scheme, perception function information, a driving speed V, a perception-braking reaction time t pbr , a perception-steering reaction time t pbs , a braking deceleration A d , an overtaking acceleration A p , a braking deceleration A preset by the system within a driver takeover time dp , a driver takeover time t T , wherein the automatic driving and traditional manual driving interactive vehicle includes two types of passenger cars and trucks, and the corresponding vehicle system type is 0-5 level driving automation.

[0070] The vehicle-mounted perception sensor configuration and layout scheme at least includes a perception sensor type, a detection distance, a horizontal plane field of view angle, a vertical plane field of view angle, a horizontal angle resolution, a vertical angle resolution, and a mounting position.

[0071] The perception function information at least includes a static and dynamic obstacle perception algorithm.

[0072] The traffic flow information of the evaluated highway section, the automatic driving vehicle fleet information, and the automatic driving and traditional manual driving interactive vehicle information can be obtained by field collection or collection of existing research results and product data, and the basic information of the evaluated highway section can be obtained by field collection or provided by a road design department.

[0073] In step S2, a virtual testing method is used to calculate the available sight distance of the automatic driving vehicle fleet and the interactive vehicle under the obtained traffic flow and automatic driving vehicle fleet formation scheme.

[0074] As shown in Figure 2 , the implementation method of step S2 is as follows:

[0075] In step S21, the obtained basic information of the evaluated highway section, the traffic flow information, the automatic driving vehicle fleet information, and the automatic driving and traditional manual driving interactive vehicle information are taken as an input parameter set, and a virtual analysis scene is automatically built in a software environment by using a virtual testing method in batches.

[0076] Wherein, the input parameter set and the subsequent management can rely on SPSS, Origin, Excel, MATLAB and other data management software; the virtual test method based on software-in-the-loop environment can rely on CarSim, PreScan, MATLAB / Simulink and other software joint simulation, and the effectiveness of independent or joint modeling of the above software has been widely verified in the field;

[0077] Step S22, the analysis scene includes the automatic driving vehicle team self-vehicle lane visibility failure scene, the interactive vehicle overtaking the automatic driving vehicle team when the self-vehicle lane visibility failure scene and the interactive vehicle overtaking the automatic driving vehicle team when the slow lane visibility failure scene;

[0078] The automatic driving vehicle team visibility failure scene risk factors include: the automatic driving vehicle team pilot vehicle causes the visibility failure due to the existence of static obstacles in front of the self-vehicle lane under the condition of horizontal clearance distance, thereby causing the automatic driving vehicle team follower to produce the rear-end collision, and the scene is schematically shown as Figure 3 .

[0079] The interactive vehicle overtaking the automatic driving vehicle team when the self-vehicle lane visibility failure scene risk factors include: the interactive vehicle causes the visibility failure due to the existence of static obstacles in front of the self-vehicle lane under the condition that the automatic driving vehicle team drives on the highway slow lane, and the scene is schematically shown as Figure 4 .

[0080] The interactive vehicle overtaking the automatic driving vehicle team when the slow lane visibility failure scene risk factors include: the interactive vehicle causes the visibility failure due to the existence of static obstacles in front of the slow lane under the condition that the automatic driving vehicle team drives on the highway slow lane, and the scene is schematically shown as Figure 5 .

[0081] Step S23, based on the automatic driving vehicle team self-lane visibility failure scene, the interactive vehicle overtaking the automatic driving vehicle team when the self-vehicle lane visibility failure scene and the interactive vehicle overtaking the automatic driving vehicle team when the slow lane visibility failure scene, virtual testing is carried out respectively, and the specific process is as follows:

[0082] Step S231, output the farthest driving path distance between the pilot vehicle and the static obstacle in front of the self-vehicle lane that can be detected as the automatic driving vehicle team pilot vehicle available visibility ASD1;

[0083] Step S232, output the farthest driving path distance between the interactive vehicle located in all lanes except the slow lane and the static obstacle in front of the self-vehicle lane that can be detected as the available visibility ASD2 of the interactive vehicle overtaking the automatic driving vehicle team when the self-vehicle lane visibility failure scene;

[0084] Step S233, output the farthest driving path distance between the static obstacles in front of the slow lane that can be detected by the interactive vehicle in all lanes except the slow lane on the same side as the interactive vehicle, as the available sight distance ASD3 of the slow lane sight distance failure scenario when the interactive vehicle overtakes the automatic driving vehicle group;

[0085] Step S24, assuming that the arrival of the oncoming vehicle follows a Poisson process, the available sight distance function of the interactive vehicle sight distance failure scenario is established:

[0086]

[0087] In the formula, V0 represents the average speed of the oncoming vehicle; P represents the assumed probability that the observed gap is greater than or equal to the calculated gap; q represents the average flow of the oncoming traffic flow;

[0088] Step S25, according to steps S232, S24, determine the minimum value of the available sight distance of the self-lane sight distance failure scenario when the interactive vehicle overtakes the automatic driving vehicle group:

[0089]

[0090] Step S26, according to steps S233, S24, determine the minimum value of the available sight distance of the slow lane sight distance failure scenario when the interactive vehicle overtakes the automatic driving vehicle group:

[0091]

[0092] Step S3, according to the required sight distance model, use the structural reliability theory to construct the sight distance safety failure function function of the automatic driving vehicle group and the interactive vehicle, and calculate the sight distance safety failure probability;

[0093] As shown in Figure 6 , the implementation method of step S3 is as follows:

[0094] Step S31, according to the automatic driving level, establish the required stopping sight distance function RSD1 of the automatic driving vehicle group leader:

[0095]

[0096] In the formula, RSD 1-j represents the required stopping sight distance (m) of the jth level of driving automation system; t p_s is the perception reaction time (s) of L1 or L2 automation system; A d is the automatic deceleration after the automatic driving system or the driver takes over; t pb_h is the perception-braking reaction time (s) of human driver; t pb_s is the perception-braking reaction time (s) of L3 and L4 automatic driving system; t Tis the time (s) for a human driver to take over from the disengaged L3 automated system; A dp is the preset deceleration (m / s T ) activated by the L3 automated system preparing to disengage during t 2 ;

[0097] Step S32, establish an interactive vehicle demand stopping sight distance function RSD2 according to the automatic driving level:

[0098]

[0099] In the formula, RSD 2-i-j represents the demand stopping sight distance (m) of the jth level of driving automation system in the ith lane on the left side except for the slow lane; t p_s is the perception reaction time (s) of the L1 or L2 automated system; t d is the automatic deceleration after the automatic driving system or the driver takes over; t pb_h is the perception-braking reaction time (s) of the human driver; t pb_s is the perception-braking reaction time (s) of the L3 and L4 automatic driving system; t T is the time (s) for a human driver to take over from the disengaged L3 automated system; A dp is the preset deceleration (m / s T ) activated by the L3 automated system preparing to disengage during t 2 ;

[0100] Step S33, establish an interactive vehicle demand overtaking sight distance function RSD3 according to the automatic driving level:

[0101]

[0102] In the formula, RSD 3-i-j represents the demand overtaking sight distance (m) of the jth level of driving automation system in the ith lane on the left side except for the slow lane; t p_s is the perception reaction time (s) of the L1 or L2 automated system; t ps_h is the perception-steering reaction time (s) of the human driver; t1 is the acceleration time (s) for the interactive vehicle to start overtaking; M is the speed difference (km / h) between the interactive vehicle and the vehicle group; t2 is the driving time (s) of the interactive vehicle in the overtaking lane; t ps_s is the perception-steering reaction time (s) of the L3 or L4 automatic driving system, t T is the time (s) for a human driver to take over from the disengaged L3 automated system; a P is the preset acceleration (m / s 2 ) in the lane changing stage; d is the safety distance (m) of the interactive vehicle completing the overtaking action from the oncoming vehicle;

[0103] Step S34, constructing the visual range safety failure function Z of the automatic driving vehicle fleet and the interactive vehicle according to the structure reliability theory s , the formula is:

[0104]

[0105] Step S35, according to the obtained basic information of the evaluated highway section, traffic flow information, automatic driving vehicle fleet information, and automatic driving and traditional manual driving interactive vehicle information, determining the calculation values of A dp , t1, t2, M, a P , d, the mean value, standard deviation and probability distribution form of t pb_h , t p_s , t T , t pb_s , t ps_h , t ps_s ;

[0106] Step S36, calculating the visual range safety allowable failure probability P s of Z f , the formula is:

[0107]

[0108] In the formula, P(ASD5-RSD 1-j <0) represents the visual range failure probability of the automatic driving vehicle fleet, P(ASD6-RSD 2-i-j <0) represents the visual range failure probability of the interactive vehicle when overtaking the automatic driving vehicle fleet, and P(ASD3-RSD 4-i-j <0) represents the visual range failure probability of the slow lane when the interactive vehicle overtakes the automatic driving vehicle fleet.

[0109] Among them, the structure reliability theory method such as the first-order second-moment method and Monte Carlo simulation can be used to solve the visual range safety failure function of the automatic driving vehicle fleet and the interactive vehicle, and calculate the visual range failure probability of the automatic driving vehicle fleet.

[0110] Step S4, determining the highway section suitability evaluation result for the automatic driving vehicle fleet according to the visual range safety allowable failure probability of different levels.

[0111] As shown in Figure 7 , the implementation method of step S4 is as follows:

[0112] Step S41, setting the visual range safety allowable failure probability threshold P threshold ;

[0113] In one embodiment, the visual range safety allowable failure probability is set to 50%;

[0114] Step S42, the safety allowable failure probability P of the sight distance f P threshold The difference comparison is obtained to obtain the suitability evaluation result W, and the formula is:

[0115]

[0116] In the formula, when W=1, it indicates that the suitability of the current road facing the automatic driving vehicle team meets the safety driving state; when W=0, it indicates that the suitability of the current road facing the automatic driving vehicle team is in a critical safety state; and when W=-1, it indicates that the suitability of the current road facing the automatic driving vehicle team does not meet the safety driving requirement.

[0117] The application further provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method.

[0118] The application further provides a computer readable storage medium, which stores computer program instructions capable of being executed by a processor, and when the processor executes the computer program instructions, the steps of the method can be implemented.

[0119] The above is the preferred embodiment of the application, and any change made according to the technical solution of the application, as long as the function effect does not exceed the range of the technical solution of the application, belongs to the protection scope of the application.

Claims

1. A method for assessing the road drivability of autonomous driving fleets, characterized in that, Includes the following steps: Step S1: Obtain basic information, traffic flow information, autonomous driving fleet information, and interactive vehicle information for the assessed highway segment; traffic flow information includes oncoming traffic flow, same-direction traffic flow, oncoming vehicle speed, and same-direction vehicle speed; autonomous driving fleet information includes the system type of the lead vehicle and following vehicles, perception-braking reaction time, braking deceleration, the system's preset braking deceleration during driver takeover time, driver takeover time, lead vehicle speed, following vehicle spacing, and number of following vehicles; interactive vehicle information includes: vehicle system type, onboard perception sensor configuration and deployment scheme, perception function information, driving speed, perception-braking reaction time, perception-steering reaction time, braking deceleration, overtaking acceleration, the system's preset braking deceleration during driver takeover time, and driver takeover time; Step S2: Using a virtual testing method, calculate the available line of sight for the autonomous driving fleet and the interactive vehicle under the acquired traffic flow and autonomous driving fleet formation scheme; the specific implementation method is as follows: Step S21: The basic information, traffic flow information, autonomous vehicle fleet information, and interactive vehicle information of the acquired evaluation highway section are used as the input parameter set. Virtual analysis scenarios are automatically built in batches in the software environment using virtual testing methods. The virtual analysis scenarios include the autonomous vehicle fleet lane line-of-sight failure scenario, the interactive vehicle lane line-of-sight failure scenario when overtaking the autonomous vehicle fleet, and the slow lane line-of-sight failure scenario when overtaking the autonomous vehicle fleet. Step S22: Conduct virtual tests based on the scenarios of lane sight distance failure of the autonomous vehicle fleet itself, lane sight distance failure of the interactive vehicle when overtaking the autonomous vehicle fleet, and slow lane sight distance failure of the interactive vehicle when overtaking the autonomous vehicle fleet. The specific process is as follows: Step S221: Output the furthest driving path distance between the lead vehicle and the stationary obstacle in front of the detectable lane of the autonomous vehicle, which is used as the available line of sight ASD1 for the lead vehicle of the autonomous driving fleet; Step S222: Output the farthest travel path distance between stationary obstacles in front of the vehicle lane that the interactive vehicle can detect in all lanes except the slow lane on the same side, as the available line of sight ASD2 in the scenario where the line of sight of the vehicle lane fails when the interactive vehicle overtakes the autonomous vehicle fleet. Step S223: Output the farthest driving path distance between stationary obstacles in front of the slow lane that the interactive vehicle can detect in all lanes on the same side except the slow lane, as the available line of sight ASD3 when the interactive vehicle overtakes the autonomous driving vehicle fleet. Step S23: Assuming the arrival of oncoming vehicles follows a Poisson process, establish a usable line-of-sight function for the interaction vehicle line-of-sight failure scenario: In the formula, V0 represents the average speed of oncoming vehicles; P represents the hypothetical probability that the observed gap is greater than or equal to the calculated gap; and q represents the average flow rate of oncoming traffic. Step S24: Based on steps S222 and S23, determine the minimum available line of sight for the autonomous vehicle in the scenario where the lane line of sight fails when the interactive vehicle overtakes the autonomous vehicle convoy. Step S25: Based on steps S223 and S23, determine the minimum available line of sight in the slow lane when the interactive vehicle overtakes the autonomous driving convoy, assuming the line of sight fails. Step S3: Based on the demand line-of-sight model, construct the line-of-sight safety failure function function for the autonomous driving fleet and the interactive vehicle using structural reliability theory, and calculate the line-of-sight safety failure probability. Step S4: Determine the road section drivability assessment results for autonomous driving fleets based on the graded line-of-sight safety tolerance failure probability.

2. The method for assessing the road drivability of autonomous driving fleets according to claim 1, characterized in that, In step S1, the basic information of the highway segment being evaluated includes the design speed, number of lanes, lane width, hard shoulder width, earth shoulder width, superelevation, lateral clearance, and types of roadside and in-road obstacles.

3. The method for assessing the road drivability of autonomous driving fleets according to claim 1, characterized in that, The navigator system includes levels of driving automation from 0 to 5, while the follower system includes levels of driving automation from 3 to 5.

4. The method for assessing the road drivability of autonomous driving fleets according to claim 1, characterized in that, Interactive vehicles include passenger cars and trucks, and the types of interactive vehicle systems include driving automation levels from 0 to 5.

5. The method for assessing the road drivability of autonomous driving fleets according to claim 1, characterized in that, The configuration and deployment scheme of vehicle-mounted perception sensors shall include at least the following: sensor type, detection distance, horizontal field of view, vertical field of view, horizontal angular resolution, vertical angular resolution, and installation location; perception function information shall include at least the following: static and dynamic obstacle perception algorithms.

6. The method for assessing the road drivability of autonomous driving fleets according to claim 1, characterized in that, Step S3 is implemented as follows: Step S31: Establish the required parking line-of-sight function RSD1 for the autonomous driving fleet's navigator based on the driving automation level. In the formula, RSD 1-j t represents the required stopping sight distance for the j-th level of driving automation; p_s It refers to the sensing response time of an L1 or L2 automation system; A d It refers to the automatic deceleration of the autonomous driving system or after the driver takes over; t pb_h It is the human driver's perception-braking reaction time; t pb_s It refers to the perception-braking reaction time of L3 and L4 autonomous driving systems; t T This is the time when a human driver takes over from the disengaged Level 3 automated system; A dp It is in t T The preset deceleration is activated during the process by the L3 automation system preparing to disengage; Step S32: Establish the parking sight distance function RSD2 for the interactive vehicle based on the driving automation level: In the formula, RSD 2-i-j This represents the required stopping sight distance for the j-th level driving automation system in the i-th lane on the left, excluding the slow lane. Step S33: Establish the overtaking sight distance function RSD3 for the interactive vehicle based on the driving automation level. In the formula, RSD 3-i-j t1 represents the required overtaking sight distance for the j-th level driving automation system in the i-th lane on the left (excluding the slow lane); t1 is the acceleration time for the interactive vehicle to begin overtaking. M is the speed difference between the interactive vehicle and the autonomous vehicle fleet; t2 is the travel time of the interactive vehicle in the overtaking lane; a P It is the preset acceleration during the lane change phase; d is the safe distance between the overtaking vehicle and the oncoming vehicle after the overtaking maneuver is completed; Step S34: Construct the line-of-sight safety failure function Z for the autonomous driving fleet and interactive vehicles based on structural reliability theory. s The formula is: Step S35: Based on the obtained basic information of the evaluation highway segment, traffic flow information, autonomous driving fleet information, and interactive vehicle information, determine A. dp t1, t2, M, a P The calculated values ​​of d and t pb_h t p_s t T t pb_s t ps_h t ps_s The mean, standard deviation, and probability distribution form; Step S36: Calculate Z s The line-of-sight safety tolerance failure probability P f The formula is: In the formula, P(ASD5-RSD) 1-j <0 indicates the probability of line-of-sight failure for an autonomous driving fleet, P(ASD6-RSD) 2-i-j <0 indicates the probability of lane sight failure when the interactive vehicle overtakes the autonomous vehicle convoy, P(ASD3-RSD) 4-i-j <0) indicates the probability of slow lane visibility failure when the interactive vehicle overtakes the autonomous vehicle fleet.

7. The method for assessing the road drivability of an autonomous driving fleet according to claim 6, characterized in that, Step S4 is implemented as follows: Step S41: Set the line-of-sight safety tolerance failure probability threshold P threshold ; Step S42: Determine the acceptable failure probability P for line-of-sight safety. f With P threshold By performing a difference comparison, the drivability assessment result W is obtained, and the formula is: In the formula, when W=1, it indicates that the road drivability of the current autonomous driving fleet meets the safe driving condition. When W=0, it indicates that the current road drivability for autonomous vehicle fleets is in a critical safety state; when W=-1, it indicates that the current road drivability for autonomous vehicle fleets does not meet the requirements for safe driving.

8. An electronic device comprising a processor and a memory, wherein, The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1-7.

9. A computer-readable storage medium having stored thereon computer program instructions executable by a processor, wherein when the processor executes the computer program instructions, it is able to implement the steps of the method as described in any one of claims 1-7.

Images