Self-adaptive cruise function test method and device, electronic equipment, medium and product

Abstract

The invention discloses an adaptive cruise function test method and device, electronic equipment, a medium and a product. The method comprises the following steps: in a pre-constructed test scene, acquiring surrounding environment information of a test vehicle to obtain environment sensing data; constructing a vehicle surrounding environment model according to the environment perception data; according to the vehicle surrounding environment model and a preset adaptive cruise control strategy, adaptive cruise control is carried out; acquiring operation data generated when adaptive cruise control is carried out in the test scene; and analyzing the operation data according to a preset performance index to obtain a test evaluation result for evaluating the performance of the adaptive cruise control system. The method can solve the problem that a traditional adaptive cruise test method is insufficient in test coverage in a complex dynamic scene.

Description

Technical Field

[0001] This application relates to the field of vehicle testing technology, specifically to an adaptive cruise control function testing method, device, electronic equipment, readable storage medium, and computer program product. Background Technology

[0002] Adaptive cruise control, as a core function of intelligent driving, has evolved into an advanced system integrating multiple sensors and complex control algorithms, widely used in scenarios such as highway cruising and urban expressway following. Existing testing methods typically verify its basic performance through real-vehicle testing on standard straight roads and fixed-radius curves. However, existing testing schemes severely lack coverage of complex dynamic scenarios such as high-speed ramp merging, continuous lane changes by vehicles, and continuous tracking of lateral targets on curves, leading to an increased false alarm rate in real-world road environments. The root cause of this problem lies in the difficulty of traditional testing methods in constructing high-fidelity models of complex environments, failing to fully verify the adaptability and robustness of sensor fusion algorithms in real-world dynamic traffic scenarios, thus hindering the effective assessment of the safety and reliability of adaptive cruise control systems. Summary of the Invention

[0003] In view of the above problems, this application provides an adaptive cruise function testing method, device, electronic device, readable storage medium and computer program product, which can solve the problem of insufficient test coverage in complex dynamic scenarios by traditional adaptive cruise testing methods.

[0004] Firstly, this application provides a method for testing adaptive cruise control functionality, including: In a pre-built test scenario, environmental information around the test vehicle is collected to obtain environmental perception data; A model of the vehicle's surrounding environment is constructed based on the environmental perception data. Adaptive cruise control is performed based on the vehicle's surrounding environment model and the preset adaptive cruise control strategy. Acquire operational data generated during adaptive cruise control in the test scenario; The operating data is analyzed based on preset performance indicators to obtain test evaluation results for assessing the performance of the adaptive cruise control system.

[0005] In the above technical solution, the method can construct a model of the vehicle's surrounding environment by collecting environmental perception data in a pre-built high-fidelity test scenario, and perform adaptive cruise control in combination with a preset cruise control strategy. At the same time, it can also analyze performance based on operational data, thereby comprehensively covering complex dynamic scenarios such as high-speed ramp merging and continuous entry and exit of vehicles in multiple lanes, thereby improving the adaptability and robustness in real dynamic traffic scenarios and achieving an effective assessment of the safety and reliability of the adaptive cruise control system.

[0006] In some embodiments, the method includes: Obtain pre-set test configuration data; Based on the test configuration data and the preset basic scenario template, construct the test scenario.

[0007] In the above technical solution, the method can quickly generate high-fidelity complex dynamic test scenarios, solving the problem that traditional methods have difficulty in constructing such scenarios.

[0008] In some implementations, the process of collecting environmental information around the test vehicle to obtain environmental perception data includes: Environmental perception data is obtained by collecting information about the environment around the test vehicle through a pre-arranged sensor array. The sensor array includes at least a radar, a camera, and a positioning device.

[0009] In the above technical solution, the method can collect environmental information through the collaborative collection of multiple types of sensors to obtain comprehensive and accurate environmental perception data.

[0010] In some implementations, constructing a vehicle surrounding environment model based on the environmental perception data includes: The environmental perception data is fused to obtain multimodal fused data; A model of the vehicle's surrounding environment is constructed based on the multimodal fusion data.

[0011] In the above technical solution, the method can reduce the limitations of single sensor data by fusing multimodal environmental perception data, improve data accuracy and completeness, and thus construct a high-fidelity vehicle surrounding environment model.

[0012] In some implementations, the fusion processing of the environmental perception data to obtain multimodal fusion data includes: The environmental perception data is spatiotemporally aligned to obtain aligned data; The aligned data is subjected to front-end fusion processing to obtain front-end fused data; The front-end fused data is then subjected to back-end fusion processing to obtain multimodal fused data.

[0013] In the above technical solution, the method can gradually solve the problem of spatiotemporal deviation of multi-sensor data through phased spatiotemporal alignment, front-end fusion and back-end fusion processing, improve data consistency and fusion depth, and finally output high-precision and high-reliability multimodal fusion data.

[0014] In some implementations, the step of performing front-end fusion processing on the aligned data to obtain front-end fused data includes: The radar point cloud data and image pixel data in the alignment data are correlated using the Hungarian algorithm to obtain front-end fusion data with semantically labeled 3D target bounding boxes.

[0015] In the above technical solution, the method can use the Hungarian algorithm to achieve accurate association between radar point cloud and image pixel data, assign semantic labels to 3D target boxes, efficiently generate front-end fusion data with both spatial location and semantic information, and improve the accuracy of target recognition and data correlation.

[0016] In some implementations, the backend fusion processing of the frontend fused data to obtain multimodal fused data includes: The front-end fused data is integrated with multimodal confidence using a preset evidence theory algorithm to obtain multimodal fused data.

[0017] In the above technical solution, the method can integrate the multimodal confidence of the front-end fused data through the evidence theory algorithm, effectively integrate the credibility information of different modal data, reduce the uncertainty of single modal data, and output highly credible multimodal fused data.

[0018] In some implementations, constructing a vehicle surrounding environment model based on the multimodal fusion data includes: The vehicle trajectory is determined based on the target tracking algorithm and the multimodal fusion data; A road model is constructed based on a preset sampling algorithm and the multimodal fusion data; Based on the vehicle's trajectory and the road model, a model of the vehicle's surrounding environment is constructed.

[0019] In the above technical solution, the method can determine the vehicle's trajectory through a target tracking algorithm, construct a road model through a sampling algorithm, and then integrate the two to construct a model of the vehicle's surrounding environment, thereby achieving accurate modeling of dynamic vehicles and static roads in the environment and improving the completeness and realism of the environment model.

[0020] In some implementations, the adaptive cruise control based on the vehicle's surrounding environment model and a preset adaptive cruise control strategy includes: The decision command is determined based on the environmental model surrounding the vehicle and the preset adaptive cruise control strategy; Based on the decision-making instructions and the operation control algorithm, the control instructions are determined; The adaptive cruise actuator is controlled accordingly based on the control commands.

[0021] In the above technical solution, the method can generate decision commands based on the environmental model and control strategy, then convert them into control commands and drive the actuators to achieve precise control of adaptive cruise and ensure the safe and stable driving of the vehicle in complex dynamic environments.

[0022] Secondly, this application provides an adaptive cruise function testing device, comprising: The data acquisition unit is used to collect environmental information around the test vehicle in a pre-built test scenario to obtain environmental perception data. A construction unit is used to construct a model of the environment surrounding the vehicle based on the environmental perception data. The control unit is used to perform adaptive cruise control based on the vehicle's surrounding environment model and a preset adaptive cruise control strategy. The acquisition unit is used to acquire the operational data generated during adaptive cruise control in the test scenario. The analysis unit is used to analyze the operating data according to preset performance indicators to obtain test evaluation results for evaluating the performance of the adaptive cruise control system.

[0023] In the above technical solution, the device can construct a model of the vehicle's surrounding environment by collecting environmental perception data in a pre-built high-fidelity test scenario, and perform adaptive cruise control in combination with a preset cruise control strategy. At the same time, it can also analyze performance based on operational data, thereby comprehensively covering complex dynamic scenarios such as high-speed ramp merging and continuous entry and exit of vehicles in multiple lanes, thereby improving the adaptability and robustness in real dynamic traffic scenarios and achieving an effective assessment of the safety and reliability of the adaptive cruise control system.

[0024] Thirdly, this application provides an electronic device including a memory and a processor, the memory storing a computer program, and the processor running the computer program to cause the electronic device to perform the adaptive cruise function testing method described in any one of the first aspects.

[0025] Fourthly, this application provides a readable storage medium storing a computer program, which, when executed by a processor, performs the adaptive cruise function testing method described in any one of the first aspects.

[0026] Fifthly, this application provides a computer program product, which includes a computer program that, when run by a processor, executes the adaptive cruise function testing method described in any one of the first aspects.

[0027] The beneficial effects of this application are as follows: it can effectively solve the limitations of a single sensor in extreme weather or occlusion scenarios through multi-sensor collaboration and data fusion, thereby significantly improving the accuracy and robustness of environmental perception; it can also be optimized through safety redundancy design, so that the system can still maintain 80% of its basic functions when a single sensor fails; in addition, relying on the improved JPDA filter and RANSAC road modeling algorithm, it can also realize multi-target tracking in complex traffic flow, thereby greatly enhancing the system's adaptability to dynamic scenarios; finally, by supporting automated batch testing, it can also effectively accelerate testing and verification efficiency and shorten the development cycle. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a flowchart illustrating the adaptive cruise function testing method in some embodiments of this application; Figure 2 This is a system schematic diagram of the ACC function testing system in some embodiments of this application; Figure 3 This is a schematic diagram of the structure of the adaptive cruise function test device in some embodiments of this application; Figure 4 This is a schematic diagram of the structure of an electronic device in some embodiments of this application. Detailed Implementation

[0030] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0032] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more (including two), similarly, "multiple sets" refers to two or more sets (including two sets), and "multiple pieces" refers to two or more pieces (including two pieces) unless otherwise explicitly defined.

[0033] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0034] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0035] In existing technologies, adaptive cruise control (ACC) systems have evolved into complex systems integrating multiple sensors and control algorithms. The mainstream approach employs a hierarchical control structure: the upper layer outputs the desired acceleration / deceleration based on a driver-following model, while the lower layer achieves target tracking by controlling the throttle and brakes. Furthermore, its testing adheres to relevant standards, primarily verifying performance such as detection distance, target recognition, and cornering adaptation through real-vehicle testing, and collecting data using devices such as CANoe and RT3000.

[0036] However, current test scenarios are mostly simple environments, which cannot cover complex road conditions, thus increasing the misjudgment rate of ACC systems in real roads. At the same time, current tests are mostly isolated single-vehicle tests, which lack networking and collaboration, resulting in test results that often deviate significantly from real driving scenarios. In addition, tests rely on preset scripts and manual analysis, lacking real-time fault diagnosis capabilities, and when facing long-tail scenarios, they usually need to rely on repeated real-vehicle tests (3000+ kilometers of road testing per vehicle), resulting in high costs and long cycles, while the fidelity of virtual simulation is insufficient.

[0037] To address the aforementioned technical issues, this application provides an adaptive cruise function testing method. This method employs the PTPv2 protocol to achieve millisecond-level time synchronization and combines it with a nine-point calibration method to unify the radar-camera spatial coordinates (error <0.1°), thus resolving the data drift problem caused by heterogeneous sensors. Simultaneously, based on the DS evidence theory, an adaptive confidence allocation model adjusts sensor weights in real time according to environmental conditions (such as visibility and target motion state). Finally, through hardware redundancy design (CANFD / FlexRay dual channels) coupled with software degradation logic, it can also ensure that the system can maintain basic functions (such as pure vision mode speed limiting control) even in the event of a single failure.

[0038] like Figure 1 As shown, some embodiments of this application provide a method for testing adaptive cruise control functionality, which includes: S101. In a pre-built test scenario, collect environmental information around the test vehicle to obtain environmental perception data. S102. Construct a model of the vehicle's surrounding environment based on environmental perception data; S103. Perform adaptive cruise control based on the vehicle's surrounding environment model and the preset adaptive cruise control strategy. S104. Obtain the operational data generated during adaptive cruise control in the test scenario; S105. Analyze the operating data according to the preset performance indicators to obtain test evaluation results for evaluating the performance of the adaptive cruise control system.

[0039] In some embodiments, the test scenario refers to a pre-built scenario used to simulate the actual working environment of the ACC system. It can cover different road conditions such as straight roads, curves, multi-lane interactions, ramp merging, and sudden obstacles, and can provide a controllable test environment for collecting environmental information and verifying the ACC function.

[0040] In some embodiments, environmental perception data refers to the environmental information around the test vehicle collected by sensors (such as radar, cameras, positioning devices, etc.) in the test scenario, including data such as the position / speed of surrounding vehicles, road boundaries, traffic signs, and obstacle information.

[0041] In some embodiments, the vehicle surrounding environment model refers to a digital model that is constructed based on collected environmental perception data through data fusion and modeling algorithms, and can intuitively reflect the dynamic (such as the motion state of other vehicles) and static (such as road structure) environment around the test vehicle.

[0042] In some embodiments, the adaptive cruise control strategy refers to the preset rules and logic that guide the ACC system to achieve cruise function, including following distance setting, acceleration and deceleration thresholds, target vehicle recognition priority, and cornering speed adjustment strategy.

[0043] In some embodiments, operational data refers to various types of data generated when the test vehicle performs adaptive cruise control in a test scenario, including the vehicle's own speed, acceleration, throttle opening, braking pressure, as well as target recognition results and decision commands from the ACC system.

[0044] In some embodiments, performance indicators refer to pre-defined quantitative or qualitative standards used to evaluate the performance of the ACC system, including indicators such as detection accuracy, target tracking stability, acceleration and deceleration smoothness (comfort indicators), response delay, and ability to handle hazardous conditions.

[0045] In some embodiments, the test evaluation result refers to the conclusions drawn about the performance of the ACC system in the test scenario after comparing and analyzing the running data with preset performance indicators. It can directly reflect the level of the system's security, reliability, adaptability, etc.

[0046] In the above embodiments, the method can construct a model of the vehicle's surrounding environment by collecting environmental perception data in a pre-built high-fidelity test scenario, and perform adaptive cruise control in combination with a preset cruise control strategy. At the same time, it can also analyze performance based on operational data, thereby comprehensively covering complex dynamic scenarios such as high-speed ramp merging and continuous entry and exit of vehicles in multiple lanes, thereby improving the adaptability and robustness in real dynamic traffic scenarios and achieving an effective assessment of the safety and reliability of the adaptive cruise control system.

[0047] In some embodiments, the method includes: Obtain pre-set test configuration data; Based on the test configuration data and the preset basic scenario template, construct the test scenario.

[0048] In the above embodiments, the method can quickly generate high-fidelity complex dynamic test scenarios, solving the problem that traditional methods have difficulty in constructing such scenarios.

[0049] In some embodiments, environmental information surrounding the test vehicle is collected to obtain environmental perception data, including: Environmental perception data is obtained by collecting information about the environment around the test vehicle through a pre-arranged sensor array. The sensor array includes at least radar, camera, and positioning device.

[0050] For example, this method can use a sensor array consisting of a 4D imaging radar (detection range 300m, 10% reflectivity) + an 8-megapixel camera (120° FOV) + ​​RTK / IMU combined navigation (positioning accuracy ±2cm), achieve μs-level time synchronization through the PTPv2 protocol, and complete spatial alignment based on the nine-point calibration method.

[0051] In the above embodiments, the method can collect environmental information through the collaborative collection of multiple types of sensors to obtain comprehensive and accurate environmental perception data.

[0052] In some embodiments, constructing a model of the vehicle's surrounding environment based on environmental perception data includes: Environmental perception data is fused to obtain multimodal fused data; A model of the vehicle's surrounding environment is constructed based on multimodal fusion data.

[0053] In the above embodiments, the method can reduce the limitations of single sensor data by fusing multimodal environmental perception data, improve data accuracy and completeness, and thus construct a high-fidelity vehicle surrounding environment model.

[0054] In some embodiments, environmental perception data is fused to obtain multimodal fused data, including: Spatiotemporal alignment processing is performed on environmental perception data to obtain aligned data; The aligned data is then subjected to front-end fusion processing to obtain front-end fused data; The front-end fused data is processed by the back-end fused data to obtain multimodal fused data.

[0055] For example, during the front-end fusion process, radar point clouds and image pixels are associated through the Hungarian algorithm to generate 3D target boxes with semantic labels (such as vehicle / pedestrian classification accuracy of 98.2%).

[0056] For example, during the backend fusion process, this method can use DS evidence theory to integrate multimodal confidence to solve the problem of sensor conflict (such as camera misjudgment correction in rainy or foggy weather).

[0057] In the above embodiments, the method can gradually solve the spatiotemporal deviation problem of multi-sensor data through phased spatiotemporal alignment, front-end fusion and back-end fusion processing, improve data consistency and fusion depth, and finally output high-precision and high-reliability multimodal fusion data.

[0058] In some embodiments, the aligned data undergoes front-end fusion processing to obtain front-end fused data, including: By using the Hungarian algorithm to correlate radar point cloud data and image pixel data in the alignment data, front-end fusion data with semantically labeled 3D target bounding boxes is obtained.

[0059] In the above embodiments, the method can use the Hungarian algorithm to achieve accurate association between radar point cloud and image pixel data, assign semantic labels to 3D target boxes, efficiently generate front-end fusion data with both spatial location and semantic information, and improve the accuracy of target recognition and data correlation.

[0060] In some embodiments, backend fusion processing is performed on the frontend fused data to obtain multimodal fused data, including: A pre-defined evidence theory algorithm is used to integrate multimodal confidence scores from the front-end fused data to obtain multimodal fused data.

[0061] In the above embodiments, the method can integrate the multimodal confidence of front-end fused data through evidence theory algorithms, effectively integrate the credibility information of different modal data, reduce the uncertainty of single modal data, and output highly credible multimodal fused data.

[0062] In some embodiments, constructing a vehicle surrounding environment model based on multimodal fusion data includes: The vehicle's trajectory is determined based on the target tracking algorithm and multimodal fusion data; A road model is constructed based on a pre-defined sampling algorithm and multimodal fusion data; Based on the vehicle's trajectory and the road model, a model of the vehicle's surrounding environment is constructed.

[0063] In the above embodiments, the method can determine the vehicle's trajectory through a target tracking algorithm, construct a road model through a sampling algorithm, and then integrate the two to construct a vehicle's surrounding environment model, thereby achieving accurate modeling of dynamic vehicles and static roads in the environment and improving the completeness and realism of the environment model.

[0064] In some embodiments, adaptive cruise control is performed based on a vehicle surrounding environment model and a preset adaptive cruise control strategy, including: The decision command is determined based on the environmental model surrounding the vehicle and the preset adaptive cruise control strategy; Based on the decision-making instructions and the operation control algorithm, the control instructions are determined; The adaptive cruise actuator is controlled accordingly based on the control commands.

[0065] In the above embodiments, the method can generate decision commands based on the environmental model and control strategy, then convert them into control commands and drive the actuators to achieve precise control of adaptive cruise control, ensuring the safe and stable driving of the vehicle in complex dynamic environments.

[0066] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below. In some embodiments, Figure 2 An ACC functional testing system for implementing multimodal perception is shown. The ACC functional testing system includes: Test management platform 210 is used to monitor and manage the entire testing process, including setting test parameters, recording and analyzing test data, etc. The multimodal data fusion layer 220 is used to fuse data from different sensors (such as radar, camera, GPS, etc.) to improve the accuracy and reliability of environmental perception. Sensor array 230 is used to acquire and collect data information in the test from multiple dimensions; The environmental perception module 240 is used to construct an environmental model around the vehicle based on the results of multimodal data fusion. The decision control module 250 is used to decide the actions that the vehicle should take based on the information provided by the environmental perception module and the preset ACC control strategy. The ACC actuator interface 260 is responsible for executing the control commands output by the decision and control module, and achieving adaptive cruise control by adjusting the vehicle's throttle and braking system.

[0067] In some embodiments, the test management platform 210 includes: The scene configuration engine adopts XML+Python dual-mode script configuration and supports 12 basic scene templates defined by the ISO15622 standard; at the same time, it integrates a data visualization dashboard to display the raw data and fusion results of 8-channel sensors in real time. The testing and evaluation system includes five core indicators: following distance error (±0.3m), acceleration smoothness (jerk<2.5m / s²), and acceleration smoothness. 3 ), response latency (<150ms), false trigger rate (<0.1%), and extreme condition survival rate.

[0068] In some embodiments, the multimodal data fusion layer 220 includes: The spatiotemporal alignment subsystem uses the PTPv2 protocol to achieve millisecond-level time synchronization at the hardware level; at the same time, it can control the coordinate system deviation between the 77GHz radar and the 8MP camera within ±3cm based on the nine-point calibration method of the checkerboard target. The feature fusion architecture performs region matching (Hungarian algorithm) on the front end based on millimeter-wave radar point cloud and visual ROI; and performs confidence-weighted decision-making based on DS evidence theory on the back end.

[0069] In some embodiments, the sensor array 230 includes: Radar: Used to detect the distance and speed of vehicles ahead.

[0070] Cameras are used to identify the type and size of vehicles ahead, as well as information such as road signs and markings.

[0071] GPS: Used to provide the vehicle's own location information and speed.

[0072] In some embodiments, the environment sensing module 240 includes: The target tracking algorithm, based on an improved JPDA filter, handles the trajectory correlation problem in dense scenes; at the same time, it can support the simultaneous tracking of up to 20 dynamic targets. The road modeling unit can reduce the curvature estimation error to 0.01m based on the RANSAC algorithm. -1 The following applies; and the slope detection range is ±15°. In some embodiments, the decision control module 250 includes: The action strategy calculation submodule is used to decide the actions that the vehicle should take (such as accelerating, decelerating, or maintaining the current speed) based on the information provided by the environmental perception module and the preset ACC control strategy. The operation control submodule is used to calculate and output control commands in real time according to the control algorithm to drive the ACC actuator to perform corresponding operations.

[0073] In some embodiments, the actuator interface 260 includes: The drive-by-wire protocol supports dual-bus redundancy of CANFD (8MHz) and FlexRay. Throttle control resolution is 0.1%, and brake pressure control accuracy is ±0.2MPa. The fault recovery mechanism is used for fault recovery processing based on a three-level degradation strategy (normal mode → restricted mode → limp mode); among which, the watchdog timer timeout threshold is 150ms.

[0074] Figure 3 A schematic diagram of an adaptive cruise function testing device is shown. It should be understood that this device is related to... Figure 1 The method executed in the middle corresponds to the steps involved in the aforementioned method. The specific functions and effects of the device can be found in the description above. To avoid repetition, detailed descriptions are omitted here.

[0075] The adaptive cruise control test device includes: The acquisition unit 310 is used to acquire environmental information around the test vehicle in a pre-built test scenario to obtain environmental perception data. Construction unit 320 is used to construct a model of the environment surrounding the vehicle based on environmental perception data; The control unit 330 is used to perform adaptive cruise control based on the vehicle's surrounding environment model and a preset adaptive cruise control strategy. The acquisition unit 340 is used to acquire the operating data generated during adaptive cruise control in the test scenario; The analysis unit 350 is used to analyze the operating data according to preset performance indicators to obtain test evaluation results for evaluating the performance of the adaptive cruise control system.

[0076] In some embodiments, the acquisition unit 340 is further configured to acquire pre-set test configuration data; The building unit 320 is also used to build test scenarios based on test configuration data and preset basic scenario templates.

[0077] In some embodiments, the acquisition unit 310 is specifically used to acquire environmental information around the test vehicle through a pre-arranged sensor array to obtain environmental perception data. The sensor array includes at least radar, camera, and positioning device.

[0078] In some embodiments, the building unit 320 includes: The fusion subunit 321 is used to fuse environmental perception data to obtain multimodal fusion data; Subunit 322 is constructed to build a model of the vehicle's surrounding environment based on multimodal fusion data.

[0079] In some embodiments, the fusion subunit 321 is specifically used to perform spatiotemporal alignment processing on environmental perception data to obtain aligned data; The aligned data is then subjected to front-end fusion processing to obtain front-end fused data; The front-end fused data is processed by the back-end fused data to obtain multimodal fused data.

[0080] In some embodiments, the fusion subunit 321 is specifically used to associate radar point cloud data and image pixel data in the alignment data using a Hungarian algorithm to obtain front-end fusion data with semantically labeled 3D target boxes.

[0081] In some embodiments, the fusion subunit 321 is specifically used to integrate the multimodal confidence of the front-end fusion data using a preset evidence theory algorithm to obtain multimodal fusion data.

[0082] In some embodiments, subunit 322 is specifically used to determine the vehicle trajectory based on the target tracking algorithm and multimodal fusion data; A road model is constructed based on a pre-defined sampling algorithm and multimodal fusion data; Based on the vehicle's trajectory and the road model, a model of the vehicle's surrounding environment is constructed.

[0083] In some embodiments, the control unit 330 includes: The determination subunit 331 is used to determine decision commands based on the environmental model around the vehicle and the preset adaptive cruise control strategy; The determination subunit 331 is used to determine the control instructions based on the decision instructions and the operation control algorithm; The control subunit 332 is used to control the adaptive cruise actuator according to the control command.

[0084] like Figure 4 As shown, this application provides an electronic device 400, which includes a processor 401 and a memory 402. The processor 401 and the memory 402 are interconnected and communicate with each other through a communication bus 403 and / or other forms of connection mechanism (not shown). The memory 402 stores a computer program that can be executed by the processor 401. When the computing device is running, the processor 401 executes the computer program to perform the method in any of the aforementioned optional implementations.

[0085] This application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the method in any of the aforementioned optional implementations.

[0086] The computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0087] This application provides a computer program product, which includes a computer program that, when run by a processor, executes the method in any of the aforementioned optional implementations.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for testing adaptive cruise control function, characterized in that, include: In a pre-built test scenario, environmental information around the test vehicle is collected to obtain environmental perception data; A model of the vehicle's surrounding environment is constructed based on the environmental perception data. Adaptive cruise control is performed based on the vehicle's surrounding environment model and the preset adaptive cruise control strategy. Acquire operational data generated during adaptive cruise control in the test scenario; The operating data is analyzed based on preset performance indicators to obtain test evaluation results for assessing the performance of the adaptive cruise control system.

2. The adaptive cruise function test method according to claim 1, characterized in that, The method includes: Obtain pre-set test configuration data; Based on the test configuration data and the preset basic scenario template, construct the test scenario.

3. The adaptive cruise function test method according to claim 1, characterized in that, The environmental information surrounding the test vehicle is collected to obtain environmental perception data, including: Environmental perception data is obtained by collecting information about the environment around the test vehicle through a pre-arranged sensor array. The sensor array includes at least radar, camera, and positioning device.

4. The adaptive cruise control function test method according to claim 1, characterized in that, The step of constructing a vehicle surrounding environment model based on the environmental perception data includes: The environmental perception data is fused to obtain multimodal fused data; A model of the vehicle's surrounding environment is constructed based on the multimodal fusion data.

5. The adaptive cruise function test method according to claim 4, characterized in that, The process of fusing the environmental perception data to obtain multimodal fused data includes: The environmental perception data is spatiotemporally aligned to obtain aligned data; The aligned data is subjected to front-end fusion processing to obtain front-end fused data; The front-end fused data is then subjected to back-end fusion processing to obtain multimodal fused data.

6. The adaptive cruise function test method according to claim 4, characterized in that, The step of performing front-end fusion processing on the aligned data to obtain front-end fused data includes: The radar point cloud data and image pixel data in the alignment data are correlated using the Hungarian algorithm to obtain front-end fusion data with semantically labeled 3D target bounding boxes.

7. The adaptive cruise control function test method according to claim 4, characterized in that, The backend fusion processing of the front-end fused data to obtain multimodal fused data includes: The front-end fused data is integrated with multimodal confidence using a preset evidence theory algorithm to obtain multimodal fused data.

8. The adaptive cruise function test method according to claim 4, characterized in that, The step of constructing a vehicle surrounding environment model based on the multimodal fusion data includes: The vehicle trajectory is determined based on the target tracking algorithm and the multimodal fusion data; A road model is constructed based on a preset sampling algorithm and the multimodal fusion data; Based on the vehicle's trajectory and the road model, a model of the vehicle's surrounding environment is constructed.

9. The adaptive cruise function test method according to claim 1, characterized in that, The adaptive cruise control based on the vehicle's surrounding environment model and a preset adaptive cruise control strategy includes: The decision command is determined based on the environmental model surrounding the vehicle and the preset adaptive cruise control strategy; Based on the decision-making instructions and the operation control algorithm, the control instructions are determined; The adaptive cruise actuator is controlled accordingly based on the control commands.

10. An adaptive cruise function testing device, characterized in that, The adaptive cruise function testing device includes: The data acquisition unit is used to collect environmental information around the test vehicle in a pre-built test scenario to obtain environmental perception data. A construction unit is used to construct a model of the environment surrounding the vehicle based on the environmental perception data. The control unit is used to perform adaptive cruise control based on the vehicle's surrounding environment model and a preset adaptive cruise control strategy. The acquisition unit is used to acquire the operational data generated during adaptive cruise control in the test scenario. The analysis unit is used to analyze the operating data according to preset performance indicators to obtain test evaluation results for evaluating the performance of the adaptive cruise control system.

11. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the adaptive cruise function test method according to any one of claims 1 to 9.

12. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, performs the adaptive cruise function test method according to any one of claims 1 to 9.

13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, performs the adaptive cruise function test method according to any one of claims 1 to 9.

Images