Method and device for testing performance of platooning autonomous vehicles

Abstract

The application provides a performance testing method and device for a platoon automatic driving vehicle, the method comprising: in response to receiving a search condition input by a user, determining a target scene matching the search condition based on a pre-constructed scene database, wherein the pre-constructed scene database stores at least a plurality of first-level scene tags and second-level scene tags, the first-level scene tags comprise a plurality of second-level scene tags, and the plurality of second-level scene tags are in a mutual exclusion relationship; running the platoon automatic driving vehicle in the target scene and obtaining performance data of the platoon automatic driving vehicle; and verifying an automatic driving strategy of the platoon automatic driving vehicle according to the performance data. Through the application, automatic label management is realized, and new and old data are uniformly managed. When the judgment standard of the scene database is updated, only the historical data needs to be refreshed according to the new clustering standard, the historical data can be effectively utilized, and the retrieval difficulty or loss of the historical data is avoided.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a performance testing method and apparatus for platooning autonomous vehicles. Background Technology

[0002] With the development of autonomous driving technology, platooning of autonomous vehicles has become one of the key paths to improve road traffic efficiency and reduce energy consumption. Against this backdrop, using simulation software to conduct performance testing and safety verification of autonomous platooning vehicles has become indispensable, and building a high-quality scenario library is the cornerstone of this simulation verification process.

[0003] The autonomous driving scenario library is the foundation and starting point for autonomous driving simulation testing and evaluation, playing a crucial role in the autonomous vehicle testing and evaluation system. Formation driving involves multi-vehicle collaborative decision-making and control, making its test scenarios more complex than single-vehicle autonomous driving. These scenarios not only need to cover traditional dimensions such as road structure, traffic participant behavior, and obstacle types, but also repeatedly consider the unique interaction logic of formations, such as the state switching between the lead vehicle and following vehicles, formation maintenance and transformation, and various complex operating conditions like coordinated obstacle avoidance. However, the current management of the corresponding scenario library, especially for formation scenarios, lacks a unified standard, resulting in scenario management problems such as the complexity and diversity of formation autonomous driving scenario types, unclear scenario type definitions, and difficulties in retrieving target scenarios, further affecting the inaccuracy of performance testing for formation autonomous vehicles.

[0004] Therefore, how to effectively test the performance of platooned autonomous vehicles has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a performance testing method and apparatus for platooned autonomous vehicles to partially or completely solve the above-mentioned technical problems.

[0006] In a first aspect, embodiments of this application provide a performance testing method for platooned autonomous vehicles, comprising: responding to receiving search conditions input by a user, determining a target scene matching the search conditions based on a pre-built scene database, wherein the pre-built scene database stores at least a plurality of first-level scene tags and second-level scene tags, the first-level scene tags including a plurality of second-level scene tags, the plurality of second-level scene tags being mutually exclusive; running the platooned autonomous vehicles in the target scene and acquiring performance data of the platooned autonomous vehicles; and verifying the autonomous driving strategy of the platooned autonomous vehicles based on the performance data.

[0007] Secondly, embodiments of this application provide a performance testing device for platooned autonomous vehicles, including a first acquisition module, configured to, in response to receiving search conditions input by a user, determine a target scene matching the search conditions based on a pre-built scene database, wherein the pre-built scene database stores at least a plurality of first-level scene tags and second-level scene tags, the first-level scene tags including a plurality of second-level scene tags, and the plurality of second-level scene tags being mutually exclusive; a second acquisition module, configured to run the platooned autonomous vehicles in the target scene and acquire the performance data of the platooned autonomous vehicles; and a testing module, configured to verify the autonomous driving strategy of the platooned autonomous vehicles based on the performance data.

[0008] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the methods described above when executing the computer program.

[0009] Fourthly, embodiments of this application provide a computer program product, including computer instructions, wherein the computer instructions, when executed by a processor, implement any of the above methods.

[0010] Fifthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the methods described above.

[0011] Compared with the prior art, this application has the following advantages:

[0012] According to the embodiments of this application, firstly, in response to receiving the search conditions input by the user, a target scene matching the search conditions is determined based on a pre-built scene database. The pre-built scene database stores at least multiple first-level scene tags and second-level scene tags. The first-level scene tags include multiple second-level scene tags, and these multiple second-level scene tags are mutually exclusive. Then, platooned autonomous vehicles are run in the target scene, and the performance data of the platooned autonomous vehicles is obtained. Subsequently, the autonomous driving strategy of the platooned autonomous vehicles is verified based on the performance data. Due to the scarcity of platooned autonomous driving services and the regional characteristics of platooned transportation, platooned autonomous driving has a low interaction frequency and uncertainty in interaction types. Therefore, collecting more real-world road test interaction data requires higher mileage accumulation, resulting in very high data collection costs. The above solution not only achieves the uniqueness of fine-grained scenes based on multi-level mutually exclusive scene tags, but also eliminates the resource waste of repeatedly tagging scenes when the target scene changes, enabling accurate and rapid retrieval of target scenes. Furthermore, it enables efficient utilization of platooned autonomous driving scene management, supporting efficient performance testing of platooned autonomous vehicles and accurate performance evaluation.

[0013] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0014] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments according to this application and should not be construed as limiting the scope of this application.

[0015] Figure 1 A flowchart illustrating a performance testing method for platooned autonomous vehicles provided in an embodiment of this application;

[0016] Figure 2 A schematic diagram of scene factors and scene labels for a performance testing method for platooned autonomous vehicles provided in an embodiment of this application;

[0017] Figure 3 This is a schematic diagram of vehicle behavior scene labels for a performance testing method for platooned autonomous vehicles provided in an embodiment of this application;

[0018] Figure 4 This is a schematic diagram of target scene clustering for a performance testing method for platooned autonomous vehicles provided in an embodiment of this application;

[0019] Figure 5 This is a structural block diagram of a performance testing device for platooned autonomous vehicles according to an embodiment of this application;

[0020] Figure 6 This is a block diagram of an electronic device used to implement embodiments of this application. Detailed Implementation

[0021] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the concept or scope of this application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0022] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and all of them fall within the protection scope of the embodiments of this application.

[0023] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise stated, the same reference numerals in the drawings represent the same structures or operations.

[0024] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other words can achieve the same purpose, they may be replaced by other expressions.

[0025] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0026] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0027] In the field of autonomous driving, existing performance testing methods mostly use offline tables to manage the operating scenarios of autonomous vehicles. Each system manages these tables according to its own R&D needs, lacking a unified scenario classification method and failing to support online database scenario retrieval. Furthermore, due to the scarcity of platooning autonomous driving services and the regional characteristics of platooning freight transport (outside urban areas), platooning autonomous driving has a low interaction frequency and uncertainty in interaction types. Collecting more real-world road test interaction data requires higher mileage accumulation, resulting in very high data collection costs. For autonomous passenger vehicles, however, the operating area is mainly in urban areas, with a higher interaction frequency. Moreover, there is a large amount of open-source and driver assistance data available in the industry, making the efficiency and cost of collecting target scenarios much higher. Therefore, the management of platooning data is more important than that for passenger vehicles. Historical data needs to be fully utilized, requiring a comprehensive and continuously iterative management system for scenario management.

[0028] In view of the above problems, this application provides a performance testing method for platooned autonomous vehicles to solve all or part of the above technical problems.

[0029] The technical solution of this application and how it solves the aforementioned technical problems are described in detail below with specific embodiments. The listed specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0030] Figure 1 This is a flowchart illustrating a performance testing method for platooned autonomous vehicles provided in an embodiment of this specification.

[0031] like Figure 1 As shown, the above method may include the following steps:

[0032] Step S101: In response to receiving the search conditions input by the user, the target scene matching the search conditions is determined based on the pre-built scene database. The pre-built scene database stores at least a number of first-level scene tags and second-level scene tags. The first-level scene tags include a number of second-level scene tags, and the number of second-level scene tags are mutually exclusive.

[0033] To connect users' testing intentions with a pre-built scenario database, users input search criteria for matching. This is not keyword matching, but rather a structured or semantic query instruction that comprehensively expresses the testing objective, scenario elements, and performance concerns. The search criteria are designed to allow testers to accurately locate the specific scenario that needs to be verified. These criteria can be expressed as natural language descriptions or structured combinations to accommodate different query habits and accuracy requirements. This application does not impose specific limitations on this, as long as the target scenario matching the search criteria can be determined based on the pre-built scenario database.

[0034] In this embodiment of the application, the above method further includes constructing a scene database, including: obtaining historical road test data of target interaction moments during the driving process of the target autonomous vehicle; and performing hierarchical classification processing on the historical road test data based on the characteristics of the platooned autonomous vehicles to obtain the multiple first-level scene labels and second-level scene labels.

[0035] To ensure the diversity, representativeness, and high fidelity of the scenario database, data from various types and configurations of autonomous vehicles were collected during its construction. It is understandable that different vehicles with autonomous driving capabilities exhibit differences in their perception, decision-making, and control characteristics, which directly impact their interaction behavior during platooning. Therefore, acquiring historical road test data of target interaction moments during the driving of a target autonomous vehicle requires data from various types and configurations of autonomous vehicles. Data from a single vehicle model often only reflects interaction patterns under specific sensor configurations, control algorithms, and vehicle dynamics, resulting in a limited scope of the scenario database. Different brands of autonomous vehicles (such as passenger cars, buses, and heavy trucks) may employ different following strategies, lane-changing logics, and communication protocols. Multi-vehicle data can capture these differences, generating more comprehensive platooning interaction scenarios and preventing the scenario database from being biased towards a particular behavioral pattern.

[0036] In this embodiment of the application, determining the target scene that matches the search conditions based on the pre-built scene database includes: matching the search conditions with the first-level scene tags in the pre-built scene database; setting the second-level scene tags corresponding to the matched first-level scene tags as the initial target scene; and clustering the initial target scene according to the interaction scene of the platooned autonomous vehicles to obtain the target scene.

[0037] In this embodiment of the application, the first-level scene label includes a first type of scene label and a second type of scene label shared with the target autonomous vehicle. The first type of scene label includes at least one of the following: map presence or absence label, lane type label, environment label, obstacle label. The second type of scene label includes at least one of the following: road structure label, preceding vehicle behavior label, self-vehicle behavior label, other vehicle behavior label.

[0038] Figure 2 This is a schematic diagram of scene factors and scene labels for a performance testing method for platooned autonomous vehicles according to this application. For example... Figure 2 As shown, the first category of scene factors includes map presence / absence, lane type, environment (weather or lighting), road structure, and obstacle.

[0039] Figure 3 This is a schematic diagram of vehicle behavior scenario labels for a performance testing method for platooned autonomous vehicles according to this application. Figure 3 As shown, the second category of scene tags under vehicle behavior scene tags includes tags for the vehicle in front, the vehicle's own behavior, and other vehicles' behavior. It should be noted that the presence or absence of map tags, lane type tags, lighting tags, rainy weather tags under weather tags, road structure tags, and the vehicle in front behavior tags are all automatically determined tags; while the vehicle's own behavior tags and other vehicles' behavior tags need to be manually set.

[0040] In this embodiment of the application, the initial target scene is clustered based on the interaction scenarios of the platooned autonomous vehicles to obtain the target scene, including:

[0041] For the interaction scenario of platooning and lane sharing, the initial target scenario is subjected to the first clustering process based on the lane type label and the vehicle behavior label to obtain the target scenario.

[0042] For the interaction scenario of platooning lane change, the initial target scenario is subjected to a second clustering process based on the lane type label and the vehicle behavior label to obtain the target scenario. The second clustering process has a different second-level scenario label than the first clustering process.

[0043] For the interaction scenario with oncoming vehicles, the initial target scenario is subjected to a third clustering process based on the behavior label of the other vehicle to obtain the target scenario;

[0044] For the interaction scenario at the intersection, the initial target scenario is subjected to a fourth clustering process based on the road structure label and the other vehicle behavior label to obtain the target scenario;

[0045] For interaction scenarios that are not at intersections or cut-in points in the same direction, the initial target scenario is subjected to five-cluster processing based on the road structure label and the other vehicle behavior label to obtain the target scenario. The second-level scenario label of the fifth cluster processing is different from that of the fourth cluster processing.

[0046] Furthermore, for static obstacle scenarios, VRU (Vulnerable Road User) scenarios (pedestrians / animals / motorcycles), merging scenarios, ramp merging scenarios, heterogeneous vehicle scenarios, and narrow space scenarios, corresponding scenario label filtering rules can be set to perform corresponding clustering processing.

[0047] In the embodiments of this application, according to the requirements of the clustering scenario, during the scenario screening process, the clustering process first performs the screening of the first-level labels to the second-level labels, where each type of label is not mandatory and can be freely combined according to the requirements.

[0048] Furthermore, the first clustering process identifies two-way single lanes in the lane type label, vehicle-to-lane-change-overtaking, lane-change-non-overtaking, and lane-change-overtaking-return-to-original-lane in the vehicle behavior label, or vehicle-to-borrowing oncoming lanes in the vehicle behavior label as interaction scenarios for platooning lane borrowing. The target scenarios obtained by the clustering process in this application embodiment cover the regional characteristics of platooning transportation, the characteristics of low interaction frequency, and the uncertainty of interaction types. It is suitable for matching target scenarios of platooning autonomous driving, which is more efficient, accurate, and adaptable than manual matching.

[0049] For example, Figure 4 This is a schematic diagram of target scene clustering for a performance testing method for platooned autonomous vehicles according to this application. Figure 4 As shown, various interactive scenarios established based on requirements need to provide filtering logic to retrieve target scenarios. For example, if the target scenario is "non-motorized vehicles crossing the queue at a turn on the unmanned Phase I area", the scenario parsing is as follows:

[0050] Road structure: Crossroads / T-junctions / Y-junctions / Other intersections;

[0051] The vehicle in front is turning left at the intersection / turning right at the intersection;

[0052] Vehicle behavior: Turning left at the intersection / Turning right at the intersection;

[0053] His vehicle's behavior: crossing the queue;

[0054] Obstacle type: Non-motorized vehicles;

[0055] Area: Phase I of unmanned operation.

[0056] Step S102: Run the platooned autonomous vehicles in the target scenario and obtain the performance data of the platooned autonomous vehicles.

[0057] In this embodiment of the application, a performance testing method for platooned autonomous vehicles further includes updating the first-level scene label and the second-level scene label.

[0058] To ensure the continuous evolution of the performance testing methodology's verification system, scenario labels can be dynamically updated, rather than simply serving as a static checklist. By feeding back performance data from testing into the construction and optimization of the scenario database, a complete closed loop from testing to optimization and back to testing is formed. This dynamic update mechanism systematically improves the coverage of unknown risks by continuously incorporating new scenarios discovered during testing, effectively addressing the long-tail challenges of autonomous driving.

[0059] Step S103: Verify the autonomous driving strategy of the platooned autonomous vehicles based on performance data.

[0060] In this embodiment of the application, the verification of the autonomous driving strategy of the platooned autonomous vehicles based on the performance data includes: in response to the anomaly in the indicator data, acquiring abnormal data; and adjusting the autonomous driving strategy based on the abnormal data.

[0061] When one or more performance metrics deviate from the preset normal range (e.g., following distance fluctuations exceed safety thresholds, or the coordinated lane-changing trajectory deviates significantly from the expected path), the metric data is deemed abnormal. Performance metrics can include safety, comfort, and consistency metrics. Abnormal data includes a complete contextual data packet surrounding the anomaly, including vehicle status, environmental perception information, vehicle-to-vehicle / vehicle-to-infrastructure communication data, and decision-making and control logs. After acquiring the abnormal data, by replaying and analyzing the abnormal data packet, it's possible to determine whether the root cause of the performance anomaly is due to unsuitable control parameters (e.g., in heavy truck platooning, traditional passenger car following parameters may lead to slow response) or blind spots in the decision-making model (e.g., poor handling of vehicle entry scenarios at specific angles).

[0062] In this embodiment of the application, the platooned autonomous vehicles may include cars, freight trucks, buses, emergency rescue vehicles, agricultural machinery vehicles, etc.

[0063] Through the above steps S101~S103, the pre-built scene database and search conditions can be used to match the target scene, and the platooned autonomous vehicles can be run in the target scene to obtain performance data. Finally, the autonomous driving strategy of the platooned autonomous vehicles can be verified based on the performance data, realizing automated label management and supporting unified management of new and old data. When the judgment criteria of the scene database are updated, only the historical data needs to be refreshed according to the new clustering criteria, which can effectively utilize the historical data and will not cause difficulties in retrieving historical data or data loss.

[0064] Corresponding to the application scenarios and methods provided in the embodiments of this application, the embodiments of this application also provide a performance testing device for platooning autonomous vehicles. For example... Figure 4The diagram shown is a structural block diagram of a performance testing apparatus for platooned autonomous vehicles according to an embodiment of this application. The performance testing apparatus for platooned autonomous vehicles may include:

[0065] The first acquisition module 501 is used to respond to receiving a search condition input by a user, and determine the target scene that matches the search condition based on a pre-built scene database. The pre-built scene database stores at least a plurality of first-level scene tags and second-level scene tags. The first-level scene tags include a plurality of second-level scene tags, and the plurality of second-level scene tags are mutually exclusive.

[0066] The second acquisition module 502 is used to run the platooned autonomous vehicles in the target scenario and acquire the performance data of the platooned autonomous vehicles.

[0067] Test module 503 is used to verify the autonomous driving strategy of the platoon's autonomous vehicles based on the performance data.

[0068] pass Figure 5 The device shown, through the coordinated operation of its first acquisition module, second acquisition module, and testing module, enables efficient, accurate, and secure automated performance testing and verification. The device, via the first acquisition module, rapidly matches user search criteria with target scenarios based on a pre-built hierarchical scene database (containing mutually exclusive second-level scene tags), significantly improving the retrieval efficiency of test scenarios and the targeting of platooning autonomous driving. The testing module verifies the autonomous driving strategy based on performance data and can dynamically adjust the strategy in response to abnormal data, forming a closed-loop feedback system from testing to optimization and back to testing. This effectively improves the robustness and adaptability of the platooning autonomous driving algorithm and provides reliable support for the standardized evaluation and large-scale application of platooning autonomous driving technology.

[0069] In this embodiment of the application, the first acquisition module 401 includes:

[0070] The scenario database pre-construction sub-module is used to obtain historical road test data of target interaction moments during the driving process of the target autonomous vehicle; based on the characteristics of the platooned autonomous vehicles, the historical road test data is classified and processed to obtain multiple first-level scenario labels and second-level scenario labels.

[0071] In this embodiment of the application, the first acquisition module 401 includes:

[0072] The retrieval and matching submodule is used to match the retrieval conditions with the first-level scene labels in the pre-built scene database; set the second-level scene labels corresponding to the matched first-level scene labels as the initial target scene; and cluster the initial target scene according to the interaction scene of the autonomous vehicles in the formation to obtain the target scene.

[0073] In this embodiment of the application, the first-level scene label includes a first type of scene label and a second type of scene label shared with the target autonomous vehicle. The first type of scene label includes at least one of the following: map presence or absence label, lane type label, environment label, obstacle label. The second type of scene label includes at least one of the following: road structure label, preceding vehicle behavior label, self-vehicle behavior label, other vehicle behavior label.

[0074] In this embodiment of the application, the retrieval and matching submodule includes:

[0075] The clustering submodule is used to perform a first clustering process on the initial target scene for platooning lane-changing interaction scenarios, based on the lane type label and the vehicle behavior label, to obtain the target scene; for platooning lane-changing interaction scenarios, a second clustering process is performed on the initial target scene based on the lane type label and the vehicle behavior label, to obtain the target scene, wherein the second clustering process has a different second-level scene label than the first clustering process; for oncoming vehicle interaction scenarios, a third clustering process is performed on the initial target scene based on the other vehicle behavior label, to obtain the target scene; for intersection interaction scenarios, a fourth clustering process is performed on the initial target scene based on the road structure label and the other vehicle behavior label, to obtain the target scene; for same-direction non-intersection non-entry interaction scenarios, a fifth clustering process is performed on the initial target scene based on the road structure label and the other vehicle behavior label, to obtain the target scene, wherein the fifth clustering process has a different second-level scene label than the fourth clustering process.

[0076] In this embodiment of the application, the performance testing device for platooned autonomous vehicles further includes:

[0077] The update module is used to update the first-level scene label and the second-level scene label.

[0078] In this embodiment of the application, the test module 403 includes:

[0079] The anomaly adjustment submodule is used to respond to anomalies in the indicator data, obtain the abnormal data, and adjust the autonomous driving strategy based on the abnormal data.

[0080] The functions of each module in each device in the embodiments of this application can be found in the corresponding description in the above method, and they have corresponding beneficial effects, which will not be repeated here.

[0081] Figure 6 This is a block diagram of an electronic device used to implement embodiments of this application. For example... Figure 6As shown, the electronic device includes a memory 610 and a processor 620. The memory 610 stores a computer program that can run on the processor 620. When the processor 620 executes the computer program, it implements the methods described in the above embodiments. The number of memories 610 and processors 620 can be one or more.

[0082] The electronic device also includes:

[0083] The communication interface 630 is used to communicate with external devices and perform data exchange and transmission.

[0084] If the memory 610, processor 620, and communication interface 630 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0085] Optionally, in a specific implementation, if the memory 610, processor 620, and communication interface 630 are integrated on a single chip, then the memory 610, processor 620, and communication interface 630 can communicate with each other through an internal interface.

[0086] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in this application.

[0087] This application also provides a chip including a processor for calling and executing instructions stored in a memory, causing a communication device with the chip installed to perform the method provided in this application.

[0088] This application also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in the application embodiment.

[0089] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0090] Further, optionally, the aforementioned memory may include read-only memory and random access memory. The memory may be volatile memory or non-volatile memory, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Sync Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0091] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0092] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0093] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0094] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0095] The logic and / or steps described in the flowchart or otherwise herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0096] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0097] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0098] The above description is merely an exemplary embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope described in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for testing performance of a platoon of autonomous vehicles, the method comprising: The method comprises the following steps: ​ determining a target scene matching the search condition based on a pre-constructed scene database in response to receiving a user input search condition, wherein the pre-constructed scene database at least stores a plurality of first-level scene tags and second-level scene tags, the first-level scene tags include a plurality of second-level scene tags, and the plurality of second-level scene tags are in a mutually exclusive relationship; running a platoon automatic driving vehicle in the target scene and obtaining performance data of the platoon automatic driving vehicle; verifying an automatic driving strategy of the platoon automatic driving vehicle according to the performance data; wherein the step of determining a target scene matching the search condition based on a pre-constructed scene database comprises the following steps: matching the search condition with the first-level scene tags in the pre-constructed scene database; setting the second-level scene tags corresponding to the matched first-level scene tags as initial target scenes; and clustering the initial target scenes according to the interaction scenes of the platoon automatic driving vehicle to obtain the target scene.

2. The method of claim 1, wherein, The method for constructing the scene database comprises the following steps: obtaining historical road test data of a target interaction moment in a driving process of a target automatic driving vehicle; performing hierarchical classification processing on the historical road test data based on the characteristics of the platoon automatic driving vehicle to obtain the plurality of first-level scene tags and second-level scene tags.

3. The method of claim 1, wherein, The first-level scene tags include first-type scene tags and second-type scene tags commonly used by the target automatic driving vehicle, wherein the first-type scene tags include at least one of the following: a map label, a lane type label, an environment label, and an obstacle label, and the second-type scene tags include at least one of the following: a road structure label, a front vehicle behavior label, a self-vehicle behavior label, and a he-vehicle behavior label.

4. The method of claim 3, wherein, The step of clustering the initial target scenes according to the interaction scenes of the platoon automatic driving vehicle to obtain the target scene comprises the following steps: for a platoon lane borrowing interaction scene, performing first clustering processing on the initial target scenes based on the lane type label and the self-vehicle behavior label to obtain the target scene; for a platoon lane changing interaction scene, performing second clustering processing on the initial target scenes based on the lane type label and the self-vehicle behavior label to obtain the target scene, wherein the second-level scene tags of the second clustering processing and the first clustering processing are different; for a head-on vehicle interaction scene, performing third clustering processing on the initial target scenes based on the he-vehicle behavior label to obtain the target scene; for an intersection interaction scene, performing fourth clustering processing on the initial target scenes based on the road structure label and the he-vehicle behavior label to obtain the target scene; for a same-direction non-intersection non-cutting interaction scene, performing fifth clustering processing on the initial target scenes based on the road structure label and the he-vehicle behavior label to obtain the target scene, wherein the second-level scene tags of the fifth clustering processing and the fourth clustering processing are different. The method further comprises the following steps:

5. The method of claim 2, wherein, updating the first-level scene tags and the second-level scene tags. ​ 6. The method of claim 1, wherein, The verifying the automatic driving strategy of the platoon automatic driving vehicle according to the performance data comprises: in response to the performance data being abnormal, acquiring abnormal data; adjusting the automatic driving strategy based on the abnormal data.

7. A performance test device for platooning autonomous vehicles, characterized in that, The method comprises: a first acquiring module, configured to acquire a target scene matched with a search condition input by a user based on a pre-constructed scene database in response to receiving the search condition, wherein the pre-constructed scene database stores at least a plurality of first-level scene tags and second-level scene tags, the first-level scene tags comprise a plurality of second-level scene tags, and the plurality of second-level scene tags are in a mutual exclusive relationship; a second acquiring module, configured to run a platoon automatic driving vehicle in the target scene and acquire performance data of the platoon automatic driving vehicle; a testing module, configured to verify an automatic driving strategy of the platoon automatic driving vehicle according to the performance data; wherein the first acquiring module is further configured to match the search condition with the first-level scene tags in the pre-constructed scene database, set the second-level scene tags corresponding to the matched first-level scene tags as initial target scenes, and cluster the initial target scenes according to interaction scenes of the platoon automatic driving vehicle to obtain the target scene. 8.An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor implements the method of any one of claims 1-6 when executing the computer program. 9.A computer program product comprising computer instructions, wherein the computer instructions implement the method of any one of claims 1-6 when executed by a processor. 10.A computer-readable storage medium having a computer program stored therein, wherein the computer program implements the method of any one of claims 1-6 when executed by a processor.

Images