A method for evaluating the driving adaptability of road traffic node sections for autonomous driving

Abstract

The object of the present invention is to provide a method for evaluating the driving adaptability of a road traffic node section for autonomous driving. By obtaining information related to the sight distance of autonomous driving and the design information of road traffic nodes, a sight line database that maps the effective sight distance of an autonomous vehicle is constructed. Further, the set of sight distances that can be obtained by the autonomous driving within the road traffic node area and the corresponding maximum autonomous driving speed to prevent sight distance failure are calculated. According to the speed coordination evaluation method, the driving adaptability of the road traffic node section is calculated. The present invention can effectively evaluate the driving adaptability of an autonomous vehicle on a road traffic node section, identify the driving risk positions with insufficient sight distance, and provide an effective technical means for investigating potential safety hazards in the actual operation of an autonomous vehicle on an existing road traffic node section.

Description

Technical Field

[0001] The present invention belongs to the technical field of road safety evaluation, and particularly relates to a method for evaluating the driving adaptability of a road traffic node section for autonomous driving. Background Art

[0002] According to the data of autonomous driving public accident and system disengagement reports, the main accident type is rear-end collision, and the related factors include: driving speed, road section type (such as highway, urban road, intersection, etc.), road section speed limit and roadside obstacle conditions. The direct causes of accidents (or autonomous driving system disengagement) are mainly: functional defects of the autonomous driving system, such as failure to identify the type of the target ahead, failure of the operation to activate emergency braking or failure of the function to warn the driver, etc.; or natural drivers overly rely on the system and do not pay attention to the surrounding road traffic environment, resulting in their failure to take over the vehicle operation in time after the system passive exits.

[0003] As an important application scenario of autonomous driving technology, the linear design of the road traffic node section takes the main body composed of the driver and traditional manually driven vehicles as the main service object, and the design method is mainly based on driver characteristics (such as visual characteristics) and control capabilities. Therefore, it is necessary to re-examine the driving adaptability of autonomous driving under the existing supply of road traffic node sections.

[0004] At present, discussions on issues related to "whether autonomous driving vehicles are suitable for existing road infrastructure" have begun to be taken seriously at home and abroad. However, most studies focus on ordinary road sections (such as circular curves, vertical alignment, lane width, etc.), and few studies focus on road traffic node sections to discuss the driving adaptability of autonomous driving to them. At the same time, the existing studies in this field are limited by test conditions and mainly use theoretical calculation methods, and the assumptions about the functional performance of the autonomous driving system are too ideal, which is likely to make the research results too ideal compared with the actual situation. Therefore, how to effectively evaluate the driving adaptability of autonomous driving vehicles on road traffic node sections under limited test conditions has become a key problem that needs to be solved urgently to ensure the safe driving of autonomous driving and has important practical significance. Summary of the Invention

[0005] The technical problem to be solved by the present invention is: to provide a method for evaluating the driving adaptability of a road traffic node section for autonomous driving, which helps to effectively evaluate the driving adaptability of autonomous driving vehicles on road traffic node sections, identify the driving risk positions with insufficient sight distance, and provide an effective technical means for investigating potential safety hazards in the actual operation of autonomous driving vehicles on existing road traffic node sections.

[0006] By obtaining information related to the sight distance of autonomous driving and the design information of road traffic nodes, a sight distance database that maps the effective sight distance of autonomous vehicles is constructed. Further, the set of sight distances that can be obtained by autonomous driving within the road traffic node area and the corresponding maximum autonomous driving speed to prevent sight distance failure are calculated. According to the speed coordination evaluation method, the driving adaptability of the road traffic node section is calculated. The present invention can effectively evaluate the driving adaptability of autonomous vehicles on road traffic node sections, identify the driving risk positions with insufficient sight distance, and provide an effective technical means for investigating potential safety hazards in the actual operation of autonomous vehicles on existing road traffic node sections.

[0007] The technical solution specifically adopted by the present invention to solve its technical problems is as follows:

[0008] A method for evaluating the driving adaptability of a road traffic node section for autonomous driving, characterized by obtaining information related to the sight distance of autonomous driving and the design information of road traffic nodes, constructing a sight distance database that maps the effective sight distance of autonomous vehicles, further calculating the set of sight distances that can be obtained by autonomous driving within the road traffic node area and the corresponding maximum autonomous driving speed to prevent sight distance failure, and calculating the driving adaptability of the road traffic node section according to the speed coordination evaluation method.

[0009] Furthermore, it specifically includes the following steps:

[0010] Step S1, obtain information related to the sight distance of autonomous driving and the design information of road traffic nodes;

[0011] The information related to the sight distance of autonomous driving at least includes: the effective sight distance S of the autonomous vehicle e , the relative course angle θ between the autonomous vehicle and the obstacle vehicle h , the relevant parameter information of the lidar, the takeover reaction time t of the autonomous vehicle driver T , the preset braking deceleration A of the autonomous vehicle dp , the braking deceleration A after the autonomous driving system or the driver takes over d , the perception reaction time t of the autonomous driving system S ;

[0012] The design information of the road traffic node at least includes: the plane alignment design information of the road traffic node, the design speed V of the road traffic node d ;

[0013] The relevant parameter information of the lidar at least includes: the detection distance d, the horizontal field of view angle A h , the vertical field of view angle A v , the horizontal angular resolution δ h , the vertical angular resolution δ v , the number of vertical laser beams N v, scanning frequency F, installation height h m , number of installations N, vehicle detection laser point number threshold N T ;

[0014] Step S2, using the relative heading angle θ between the autonomous vehicle and the obstacle obtained in Step S1 h and the lidar-related parameter information to construct a line-of-sight database Ω that maps the effective line-of-sight distance S of the autonomous vehicle e ;

[0015] Step S3, using the road traffic node plane alignment design information obtained in Step S1, further obtaining the lane-level driving path information of the road traffic node, and calculating the set Φ of the visible distances S that can be obtained by the autonomous vehicle in the road traffic node area according to the line-of-sight database Ω established in Step S2 a ; a ;

[0016] Step S4, using the takeover reaction time t of the autonomous vehicle driver obtained in Step S1 T , the preset braking deceleration A of the autonomous vehicle dp , the braking deceleration A after the autonomous driving system or the driver takes over d , the perception reaction time t of the autonomous driving system S , calculate the maximum autonomous driving speed V to prevent line-of-sight failure corresponding to each S a in the set Φ a ; max ;

[0017] Step S5, using V max and the road traffic node design speed V obtained in Step S1 d , calculate the set Ψ of the driving adaptability K of the road traffic node section for autonomous driving according to the speed coordination evaluation method

[0018] Furthermore, the specific process of Step S2 is as follows:

[0019] Step S21, for the obtained relative heading angle θ between the autonomous vehicle and the obstacle h , the lidar-related parameter information set η and the effective line-of-sight distance S of the autonomous vehicle e , establish a line-of-sight data chain Ω i , where the lidar-related parameter information set η = {d, A h , A v , δ h , δ v , N v , F, h m , N, N T}; i = 1, 2,..., n is the line-of-sight data chain ordinal number; n ∈ N +is the total number of line-of-sight data links;

[0020] Step S22, using all the established line-of-sight data links Ω i Construct a line-of-sight database Ω = {Ω i} n .

[0021] Furthermore, the specific process of step S3 is as follows:

[0022] Step S31, for the obtained road traffic node plane alignment design information, combined with the self-path planning results of the autonomous vehicle and its predicted results of the obstacle vehicle's path, determine the lane-level driving path information of the road traffic node, including the path stake number position p and the path length L;

[0023] Step S32, according to the order of the path stake number position p, from small to large, use it as the starting position of the autonomous vehicle in turn, that is, the autonomous vehicle can obtain the sight distance S a Check the starting position;

[0024] Step S33, according to the road traffic node plane alignment design information, determine the form of the road traffic node, further determine the conflict point position between the autonomous vehicle and the obstacle vehicle and its participating sections, and calculate the intersection angle θ of the participating sections R ; The participating section of the conflict point includes the sight distance S that the autonomous vehicle can obtain a Check the section R where the starting position is located S1 and the expected sight distance S that the autonomous vehicle can obtain a Check the section R where the termination position is located S2 ;

[0025] Step S34, input the intersection angle θ of the section R and the set η of lidar-related parameter information of the autonomous vehicle to be evaluated e to the line-of-sight database Ω, establish the index of the input parameter combination (θ R , η e ) and the corresponding property parameter combination (θ i , η) of the line-of-sight data link Ω in the line-of-sight database Ω, that is, (θ h , η R ) = (θ e , η), so as to determine the effective line-of-sight distance S of the autonomous vehicle mapped by (θ h , η R ); e ) e ;

[0026] Step S35, according to the road traffic node plane alignment design information and the effective line-of-sight distance S of the autonomous vehicle determined in step S34 e , determine the position located in section R S1 or RS2 The autonomous driving on it can obtain the sight distance S a Check the termination position;

[0027] Step S36, according to the sight distance S that the autonomous driving can obtain a Check the termination position, and calculate the distance from the sight distance S that the autonomous driving can obtain a The starting position of the check passes through the conflict point to the sight distance S that the autonomous driving can obtain a The path length L within the check termination position a , and this path length is the sum of the path length of the autonomous vehicle itself and the path length of the obstacle vehicle; the path length L a As the sight distance S that the autonomous driving can obtain determined in step S32 a The sight distance S corresponding to the starting position of the check a ;

[0028] Step S37, select the subsequent path stake number position p to update the sight distance S that the autonomous driving can obtain a Check the starting position, and repeat steps S32 - S36 until p is the end position of the path stake number, and finally obtain the section R S1 of S a set;

[0029] Step S38, replace the section R S1 with the remaining sections within the road traffic node area, and repeat steps S31 - S37 until the S a set in all sections is obtained, and finally the sight distance S that the autonomous driving can obtain within this road traffic node area a set Φ a .

[0030] Furthermore, in step S4, calculate the set Φ a in each S a corresponding maximum autonomous driving speed V to prevent sight distance failure max The formula is:

[0031]

[0032] In the formula, S o is the path length of the obstacle vehicle from the conflict point to the sight distance S a check the termination position.

[0033] Furthermore, the specific process of step S5 is as follows:

[0034] Step S51, determine the speed difference threshold Δ V1 and Δ V2 ; the speed difference threshold 0 < Δ V1 < Δ V2;

[0035] Step S52, when V max ≥ V d , K is "good"; V d > V max ≥ (V d – Δ V1 ), K is "better"; (V d – Δ V1 ) > V max ≥ (V d – Δ V2 ), K is "medium"; (V d – Δ V2 ) > V max , K is "poor";

[0036] Step S53, calculate the K corresponding to each S a in the set Φ a , and let the set be Ψ.

[0037] Compared with the prior art, the present invention and its preferred solutions have the following beneficial effects:

[0038] (1) By using the relative heading angle between the autonomous vehicle and the obstacle and the lidar-related parameter information to construct a line-of-sight database that maps the effective line-of-sight distance of the autonomous vehicle, and calculating the set of visible distances that can be obtained by the autonomous vehicle in the road traffic node area, the technical solution disclosed by the present invention can be applied to sections of any road traffic node type, breaking through the limitation of the prior art solution that is only applicable to specific types of road traffic nodes;

[0039] (2) It can be compatible with the actual data or virtual test data that reflect the information related to the autonomous vehicle's line-of-sight distance collected on-site, improving the drawback of the prior art that only uses theoretical calculations, which is likely to cause the adaptation result to be too ideal compared with the actual situation;

[0040] (3) The calculated maximum autonomous driving speed to prevent line-of-sight failure can provide a theoretical basis for formulating the speed limit scheme for road traffic node sections, making up for the deficiency of the prior art that only stipulates the perception range of the autonomous vehicle and is difficult to propose convenient management measures from the perspective of road traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described in detail below with reference to the drawings and specific embodiments:

[0042] Figure 1 is a flowchart of a method for evaluating the driving adaptability of a road traffic node section for autonomous driving provided by an embodiment of the present invention;

[0043] Figure 2It is the flowchart for constructing the line-of-sight database Ω of the effective line-of-sight distance S of the mapped autonomous vehicle in the embodiments of the present invention e ;

[0044] Figure 3 It is the flowchart for calculating the set Φ of the available line-of-sight distances S that can be obtained by the autonomous vehicle within the road traffic node area in the embodiments of the present invention a ; a ;

[0045] Figure 4 It is the flowchart for calculating the set Ψ of the driving adaptability K of the road traffic node sections for autonomous driving in the embodiments of the present invention

[0046] Figure 5 It is a schematic diagram of any road traffic node type applicable to the embodiments of the present invention (cross intersection). In the figure: 1 is the road traffic node area, 2 is the boundary of the road traffic node area section, 3 is the road marking, 4 is the conflict point between the autonomous vehicle and the obstacle vehicle, 5 is the driving direction, 6 is the autonomous vehicle, 7 is the driving path, 8 is the obstacle vehicle, 9 is the effective line-of-sight distance S of the autonomous vehicle e , 10 is the available line-of-sight distance S that can be obtained by the autonomous vehicle a , 11 is the relative course angle θ between the autonomous vehicle and the obstacle vehicle h ;

[0047] Figure 6 It is a schematic diagram of any road traffic node type applicable to the embodiments of the present invention (roundabout). Among them, 1 is the road traffic node area, 2 is the boundary of the road traffic node area section, 3 is the road marking, 4 is the conflict point between the autonomous vehicle and the obstacle vehicle, 5 is the driving direction, 6 is the autonomous vehicle, 7 is the driving path, 8 is the obstacle vehicle, 9 is the effective line-of-sight distance S of the autonomous vehicle e , 10 is the available line-of-sight distance S that can be obtained by the autonomous vehicle a , 11 is the relative course angle θ between the autonomous vehicle and the obstacle vehicle h ; Detailed implementation manners

[0048] To make the features and advantages of this patent more obvious and understandable, specific embodiments are given below and described in detail as follows:

[0049] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in this specification have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs

[0050] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular forms are also intended to include the plural forms. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they specify the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0051] As Figure 1 shown, a method for evaluating the driving adaptability of a road traffic node section for autonomous driving proposed by the present invention includes the following steps:

[0052] (1) Obtain the information related to the autonomous driving sight distance and the road traffic node design information; the information related to the autonomous driving sight distance includes the effective sight distance S of the autonomous driving vehicle e , the relative course angle θ between the autonomous driving vehicle and the obstacle vehicle h , the parameter information related to the lidar, the takeover reaction time t of the driver of the autonomous driving vehicle T , the preset braking deceleration A of the autonomous driving vehicle dp , the braking deceleration A after the autonomous driving system or the driver takes over d , the perception reaction time t of the autonomous driving system S ; the road traffic node design information includes the plane alignment design information of the road traffic node and the design speed V of the road traffic node d ; the parameter information related to the lidar includes the detection distance d, the horizontal field of view angle A h , the vertical field of view angle A v , the horizontal angular resolution δ h , the vertical angular resolution δ v , the number of vertical lidar beams N v , the scanning frequency F, the installation height h m , the number of installations N, the threshold value N of the number of vehicle detection laser points T ;

[0053] Among them, the information related to the autonomous driving sight distance can be obtained through means such as on-site collection, virtual testing, and driving simulation; the road traffic node design information can be obtained through on-site collection or provided by the road design department with relevant materials;

[0054] (2) Use the obtained relative course angle θ between the autonomous driving vehicle and the obstacle vehicle h and the parameter information related to the lidar to construct a sight database Ω that maps the effective sight distance S of the autonomous driving vehicle e ; the flowchart of this step is as Figure 2 shown;

[0055] 1) For the obtained relative course angle θ between the autonomous driving vehicle and the obstacle vehicleh , the set η of lidar-related parameter information and the effective line-of-sight distance S of the autonomous vehicle e , establish the line-of-sight data link Ω i , where the set η of lidar-related parameter information = {d, A h , A v , δ h , δ v , N v , F, h m , N, N T}; i = 1, 2, …, n is the sequence number of the line-of-sight data link; n ∈ N + is the total number of line-of-sight data links;

[0056] Among them, the establishment of the line-of-sight data link Ω i can rely on data management software such as Excel and MATLAB;

[0057] (2) Use all the established line-of-sight data links Ω i to construct the line-of-sight database Ω = {Ω i} n .

[0058] As described above, the construction of the line-of-sight database Ω can be realized relying on data management software such as Excel and MATLAB.

[0059] (3) Use the obtained road traffic node plane alignment design information to further obtain the lane-level driving path information of the road traffic node, and calculate the autonomous driving available sight distance S within the road traffic node area according to the established line-of-sight database Ω a of the set Φ a ; The flowchart of this step is as Figure 3 shown;

[0060] 1) For the obtained road traffic node plane alignment design information, combine the autonomous vehicle's own path planning results and its predicted results of the obstacle vehicle's path to determine the lane-level driving path information of the road traffic node; the lane-level driving path information of the road traffic node includes the path stake number position p and the path length L;

[0061] Among them, the autonomous vehicle's own path planning results and its predicted results of the obstacle vehicle's path can be obtained through the output data of the autonomous vehicle decision-making unit or external manual planning results; combine it with the road traffic node plane alignment design information, that is, obtain the lane-level driving path information of the road traffic node;

[0062] 2) According to the order of the path stake number position p, from small to large, use it as the starting position of the autonomous vehicle in turn, that is, the autonomous driving available sight distance S a check the starting position;

[0063] 3) Determine the form of the road traffic node according to the plane alignment design information of the road traffic node, further determine the location of the conflict point between the autonomous vehicle and the obstacle vehicle and the road sections it participates in, and calculate the intersection angle θ of the participating road sections R ; The road sections where the conflict point participates include the visible distance S that can be obtained by the autonomous vehicle a Check the road section R where the starting position is located S1 against the expected visible distance S that can be obtained by the autonomous vehicle a Check the road section R where the ending position is located S2 ;

[0064] 4) Input the intersection angle θ of the road sections R and the set of parameter information η related to the lidar of the autonomous vehicle to be evaluated e to the line-of-sight database Ω, and establish the input parameter combination (θ R , η e ) and the index of the corresponding property parameter combination (θ i , η) in the line-of-sight data chain Ω in the line-of-sight database Ω h , that is, (θ R , η e ) = (θ h , η), so as to determine the effective line-of-sight distance S of the autonomous vehicle mapped by (θ R , η e ); e ;

[0065] 5) According to the plane alignment design information of the road traffic node and the determined effective line-of-sight distance S of the autonomous vehicle e , determine the visible distance S that can be obtained by the autonomous vehicle located on the road section R S1 or R S2 to check the ending position; a ;

[0066] 6) According to the visible distance S that can be obtained by the autonomous vehicle to check the ending position, calculate the path length L within the range from the visible distance S that can be obtained by the autonomous vehicle to check the starting position, passing through the conflict point, to the visible distance S that can be obtained by the autonomous vehicle to check the ending position a , and this path length is the sum of the path length of the autonomous vehicle itself and the path length of the obstacle vehicle; The path length L a is used as the visible distance S that can be obtained by the autonomous vehicle corresponding to the visible distance S that can be obtained by the autonomous vehicle to check the starting position a ; a ; a ; a ; a ;

[0067] 7) Select the subsequent path stake number position p to update the visible distance S that can be obtained by the autonomous vehicle aCheck the starting position, and repeat the content in 2) to 6) until p is the end position of the path stake number, and finally obtain the road section R S1 of S a set;

[0068] 8) Replace the road section R S1 with the remaining road sections in the road traffic node area, and repeat the content in 1) to 7) until all the S a sets are obtained, and finally the set Φ a of the visible distances S a that can be obtained by autonomous driving in this road traffic node area is obtained.

[0069] (4) Use the takeover reaction time t T of the autonomous driving vehicle driver, the preset braking deceleration A dp of the autonomous driving vehicle, the braking deceleration A d after the autonomous driving system or the driver takes over, and the perception reaction time t S of the autonomous driving system to calculate the maximum autonomous driving speed V a corresponding to each S a in the set Φ max to prevent the loss of visible distance;

[0070]

[0071] In the formula, S o is the path length of the obstacle vehicle from the conflict point to the end position of the visible distance S a that can be obtained by autonomous driving;

[0072] (5) Use V max and the road traffic node design speed V d obtained in step 1, and calculate the set Ψ of the driving adaptability K of the road traffic node section for autonomous driving according to the speed coordination evaluation method; the flowchart of this step is as Figure 4 shown;

[0073] 1) Determine the speed difference thresholds Δ V1 and Δ V2 according to user requirements; the speed difference thresholds 0 < Δ V1 < Δ V2 ;

[0074] Among them, the general speed difference threshold Δ V1 = 10 km / h and Δ V2 = 20 km / h in the speed coordination evaluation method can be selected;

[0075] 2) When V max ≥ V d , K is "good"; V d > Vmax ≥(V d –Δ V1 ) when K is "good"; (V d –Δ V1 ) > V max ≥(V d –Δ V2 ) when K is "medium"; (V d –Δ V2 ) > V max when K is "poor";

[0076] 3) Calculate the set Φ a for each S a in it, and let the set be Ψ.

[0077] Schematic diagrams of any road traffic node types applicable to the technical solution disclosed in the present invention are as Figure 5 (Cross intersection), Figure 6 (Roundabout) shown, where 1 is the road traffic node area, 2 is the boundary of the road section in the road traffic node area, 3 is the road marking, 4 is the conflict point between the autonomous vehicle and the obstacle vehicle, 5 is the driving direction, 6 is the autonomous vehicle, 7 is the driving path, 8 is the obstacle vehicle, 9 is the effective line-of-sight distance S e of the autonomous vehicle, 10 is the visible distance S a that can be obtained by the autonomous vehicle, and 11 is the relative course angle θ h between the autonomous vehicle and the obstacle vehicle. Based on the key information above, the construction of the evaluation model can be completed according to the solution provided in this embodiment.

[0078] In summary, the present invention designs a method for evaluating the driving adaptability of road traffic node sections for autonomous driving. The method for evaluating the driving adaptability of road traffic node sections for autonomous driving in the present invention facilitates calculating the set of visible distances that can be obtained by autonomous vehicles in the road traffic node area and the corresponding maximum autonomous driving speed to prevent the failure of the line of sight by constructing a line-of-sight database that maps the effective line-of-sight distance of autonomous vehicles, and quantitatively evaluates the driving adaptability of road traffic node sections, providing an effective technical means for investigating potential safety hazards in the actual operation of autonomous vehicles on existing road traffic node sections; the design method of the present invention breaks through the limitation that the existing technical solution is only applicable to specific types of road traffic nodes, improves the drawback that the existing technology is prone to make the adaptability result too ideal compared with the actual situation, and makes up for the deficiency that the existing technology is difficult to propose convenient management measures from the perspective of road traffic management.

[0079] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0080] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0081] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0083] As described above, it is only the preferred embodiments of the present invention, and it is not a limitation of the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the technical content of the present invention still fall within the protection scope of the technical solution of the present invention.

[0084] This patent is not limited to the above-mentioned best implementation mode. Anyone inspired by this patent can come up with various other forms of a driving adaptability evaluation method for road traffic node sections for autonomous driving. All equal changes and modifications made according to the scope of the patent application of the present invention shall fall within the scope covered by this patent.

Claims

1. A method for evaluating the driving adaptability of road traffic node sections for autonomous driving, characterized in that Obtain the information related to the sight distance of autonomous driving and the design information of road traffic nodes, construct a sight database that maps the effective sight distance of autonomous vehicles, further calculate the set of sight distances that can be obtained by autonomous driving within the road traffic node area and the corresponding maximum autonomous driving speed to prevent sight distance failure, and calculate the driving adaptability of the road traffic node section according to the speed coordination evaluation method; Specifically, it includes the following steps: Step S1: Obtain the information related to the sight distance of autonomous driving and the design information of road traffic nodes; The above-mentioned information related to the line of sight for autonomous driving at least includes: the effective line-of-sight distance S of the autonomous vehicle e , the relative course angle θ between the autonomous vehicle and the obstacle h , the parameter information related to the lidar, the takeover reaction time t of the driver of the autonomous vehicle T , the preset braking deceleration A of the autonomous vehicle dp , the braking deceleration A after the takeover by the autonomous driving system or the driver d , the perception reaction time t of the autonomous driving system S ; The road traffic node design information at least includes: road traffic node horizontal alignment design information, and the design speed V of the road traffic node d ; The lidar-related parameter information at least includes: detection distance d, horizontal field of view angle A h , vertical field of view angle A v , horizontal angular resolution δ h , vertical angular resolution δ v , number of vertical laser beams N v , scanning frequency F, installation height h m , number of installations N, vehicle detection laser point number threshold N T ; Step S2, construct a line-of-sight database Ω that maps the effective line-of-sight distance S of the autonomous vehicle by using the relative heading angle θ between the autonomous vehicle and the obstacle obtained in Step S1 h and the parameter information related to the lidar e ; Step S3: Using the road traffic node horizontal alignment design information obtained in Step S1, further obtain the lane-level driving path information of the road traffic node, and calculate the available sight distance S for autonomous driving within the road traffic node area according to the sight line database Ω established in Step S2 a set Φ a ; Step S4, using the takeover response time t of the driver of the autonomous vehicle obtained in Step S1 T , the preset braking deceleration A of the autonomous vehicle dp , the braking deceleration A after the autonomous driving system or the driver takes over d , the perception reaction time t of the autonomous driving system S , calculate the maximum autonomous driving speed V to prevent line-of-sight failure corresponding to each S a in the set Φ a ; max ; Step S5, using V max and the road traffic node design speed V obtained in Step S1 d , calculate the set Ψ of the driving adaptability K of the road traffic node sections for autonomous driving according to the speed coordination evaluation method.

2. According to the method for evaluating the driving adaptability of a road traffic node section for autonomous driving described in claim 1, wherein: The specific process of step S2 is as follows: Step S21, for the relative heading angle θ between the obtained autonomous vehicle and the obstacle h , the set η of lidar-related parameter information, and the effective line-of-sight distance S of the autonomous vehicle e , establish a line-of-sight data link Ω i , where the set η of lidar-related parameter information = {d, A h , A v , δ h , δ v , N v , F, h m , N, N T}; i = 1, 2, …, n is the line-of-sight data link ordinal number; n ∈ N + is the total number of line-of-sight data links; Step S22, using all established line-of-sight data chains Ω i Construct a line-of-sight database Ω = {Ω i} n .

3. According to the method for evaluating the driving adaptability of a road traffic node section for autonomous driving described in claim 2, wherein: The specific process of step S3 is as follows: Step S31: For the obtained plane alignment design information of the road traffic node, combine the path planning results of the autonomous vehicle for itself and its path prediction results for the obstacle vehicle to determine the lane-level driving path information of the road traffic node, including the path stake number position p and the path length L; Step S32: Take the positions of the path stake numbers p in ascending order as the starting positions of the autonomous vehicle one by one, that is, the autonomous vehicle can obtain the line-of-sight distance S a Check the starting position; Step S33: Determine the form of the road traffic node according to the plane alignment design information of the road traffic node, further determine the position of the conflict point between the autonomous vehicle and the obstacle vehicle and the sections it participates in, and calculate the intersection angle θ of the participating sections R The sections where the conflict point participates include the visible distance S that can be obtained by the autonomous driving a Check the section R where the starting position is located S1 With the expected visible distance S that can be obtained by the autonomous driving a Check the section R where the ending position is located S2 ; Step S34, input the intersection angle θ of the road segment R The set of parameter information related to the laser radar of the autonomous driving vehicle to be evaluated η e To the sight database Ω, establish the input parameter combination (θ R ,η e ) and the line of sight data link Ω in the line of sight database Ω i Corresponding property parameter combination (θ h ,η), that is, (θ R ,η e )=(θ h ,η), thus determining (θ R ,η e ) The effective sight distance S of the autonomous driving vehicle mapped e ; Step S35: Determine the effective line-of-sight distance S of the autonomous vehicle based on the road traffic node horizontal alignment design information and the effective line-of-sight distance S of the autonomous vehicle determined in Step S34 e , and determine the autonomous driving available sight distance S S1 or R S2 on the road section R a to check the termination position; Step S36, obtain the visible distance S according to autonomous driving a Check the termination position and calculate the visible distance S obtained from autonomous driving a Check the path length L within the range from the starting position of the inspection, passing through the conflict point to the visible distance S obtained from autonomous driving a Check the path length L within the termination position range a , where the path length is the sum of the path length of the autonomous vehicle itself and the path length of the obstacle vehicle; the path length L a serves as the visible distance S obtained from autonomous driving determined in step S32 a Check the visible distance S corresponding to the starting position of the inspection a ; Step S37: Select the subsequent path stake number position p to update the visible distance S that can be obtained by autonomous driving a Check the starting position, and repeat Step S32 - Step S36 until p is the end position of the path stake number, and finally obtain the road section R S1 of S a set; Step S38, replace section R S1 For the remaining sections within the road traffic node area, repeat steps S31 - S37 until all S a sets are obtained, and finally the set Φ of the available sight distances S for autonomous driving within the road traffic node area is obtained a is obtained a .

4. According to the method for evaluating the driving adaptability of a road traffic node section for autonomous driving described in claim 3, wherein: In step S4, the set Φ is calculated a for each S a corresponding maximum autonomous driving speed V to prevent line-of-sight failure max The formula for is as follows: Where S o is the path length of the obstacle vehicle from the conflict point to the inspection termination position of the visible distance S a that can be obtained by the autonomous driving.

5. According to the method for evaluating the driving adaptability of a road traffic node section for autonomous driving described in claim 4, wherein: The specific process of step S5 is as follows: Step S51, determine the speed difference threshold Δ according to user requirements V1 and Δ V2 ; The speed difference threshold 0 < Δ V1 < Δ V2 ; Step S52, when V max ≥ V d , K is "good"; when V d > V max ≥ (V d – Δ V1 ), K is "better"; when (V d – Δ V1 ) > V max ≥ (V d – Δ V2 ), K is "medium"; when (V d – Δ V2 ) > V max , K is "bad"; Step S53, calculate the set Φ a for each S a in it, calculate the corresponding K, and let the set be Ψ.

Images