Method, apparatus, device, medium and program product for determining vehicle driving function

Abstract

This disclosure provides a method, apparatus, device, medium, and program product for determining vehicle driving functions. The method involves determining the initial driving route information of a vehicle in a preset operating scenario; controlling the vehicle's operating state in the preset operating scenario based on the initial driving route information and the vehicle's corresponding first positioning information; the first positioning information being positioning information that meets preset error conditions determined through a preset method; responding to the vehicle's operating state meeting the preset conditions corresponding to the preset operating scenario, injecting errors into the vehicle's first positioning information according to the error injection method corresponding to the preset operating scenario to obtain second positioning information with errors; controlling the vehicle's operating state based on the second positioning information and acquiring the vehicle's state change information under the second positioning information; and determining the vehicle's driving functions based on the vehicle's state change information in the preset operating scenario. This improves the sufficiency and reliability of the vehicle's driving function verification.

Description

Technical Field

[0001] This disclosure relates to intelligent driving technology, and in particular to a method, apparatus, device, medium, and program product for determining vehicle driving functions. Background Technology

[0002] With the rapid development of intelligent driving technologies such as autonomous driving and assisted driving, the safety of intelligent driving functions is of paramount importance. Intelligent driving functions include positioning, perception, and planning and control. Related technologies typically verify vehicle intelligent driving functions through extensive road testing or through numerical simulation to verify the overall intelligent driving algorithm. However, road testing rarely encounters high-risk scenarios, leading to insufficient verification sufficiency. Numerical simulation verification requires modeling the vehicle to simulate its behavior. Vehicle modeling requires mathematical models; however, mathematical models struggle to simulate the complex driving and dynamic characteristics of the vehicle itself, resulting in low verification reliability. Summary of the Invention

[0003] Embodiments of this disclosure provide a method, apparatus, device, medium, and program product for determining vehicle driving functions to improve the sufficiency and reliability of vehicle driving function verification.

[0004] A first aspect of this disclosure provides a method for determining a vehicle's driving function, comprising: determining initial driving route information of a vehicle in a preset operating scenario; controlling the vehicle's operating state in the preset operating scenario based on the initial driving route information and first positioning information corresponding to the vehicle; the first positioning information being positioning information that satisfies preset error conditions determined by a preset method; responding to the vehicle's operating state satisfying the preset conditions corresponding to the preset operating scenario, injecting an error into the vehicle's first positioning information according to an error injection method corresponding to the preset operating scenario to obtain second positioning information with error; controlling the vehicle's operating state based on the second positioning information and acquiring state change information of the vehicle under the second positioning information; and determining the vehicle's driving function based on the state change information of the vehicle in the preset operating scenario.

[0005] A second aspect of this disclosure provides a device for determining a vehicle's driving function, comprising: a first processing module for determining initial driving route information of a vehicle in a preset operating scenario; a second processing module for controlling the vehicle's operating state in the preset operating scenario based on the initial driving route information and first positioning information corresponding to the vehicle; the first positioning information being positioning information that satisfies preset error conditions determined by a preset method; a third processing module for injecting an error into the vehicle's first positioning information according to an error injection method corresponding to the preset operating scenario in response to the vehicle's operating state satisfying the preset conditions corresponding to the preset operating scenario, thereby obtaining second positioning information with errors; a fourth processing module for controlling the vehicle's operating state based on the second positioning information and acquiring state change information of the vehicle under the second positioning information; and a fifth processing module for determining the vehicle's driving function based on the state change information of the vehicle in the preset operating scenario.

[0006] A third aspect of this disclosure is to provide a computer-readable storage medium storing a computer program for performing the method for determining vehicle driving functions as described in any of the above embodiments of this disclosure.

[0007] A fourth aspect of this disclosure provides an electronic device, the electronic device comprising: a memory, a processor, and a vehicle driving function determining device;

[0008] The memory is used to store the processor-executable instructions;

[0009] The processor is configured to read the executable instructions from the memory and execute the instructions to control the vehicle driving function determination device to implement the vehicle driving function determination method according to any of the above embodiments of this disclosure; or, the electronic device includes: the vehicle driving function determination device provided in any of the above embodiments.

[0010] A fifth aspect of this disclosure provides a computer program product that, when instructions in the computer program product are executed by a processor, performs the method provided in any of the above embodiments of this disclosure.

[0011] A sixth aspect of this disclosure provides a vehicle driving function determination system, comprising: a vehicle driving function system and a vehicle driving function determination device provided in any of the above embodiments; the vehicle driving function determination device communicates with the vehicle driving function system to implement the method provided in any of the above embodiments.

[0012] Based on the vehicle driving function determination method, apparatus, device, medium, and program product provided in the above embodiments of this disclosure, by pre-setting the vehicle's operating scenario, configuring the vehicle's initial driving route in the preset operating scenario, and triggering the vehicle to run in the preset operating scenario based on accurate first positioning information and the initial driving route, in response to the vehicle's operating state meeting preset conditions, errors are injected into the vehicle's accurate first positioning information according to the error injection method corresponding to the preset operating scenario, enabling the vehicle to plan and control based on the error-injected second positioning information, controlling the vehicle's operating state, and obtaining the vehicle's state change information under the error-injected positioning information; thus, the vehicle's driving function can be determined based on the vehicle's state change information in the preset operating scenario. Since the performance of the vehicle's driving function in response to errors can be determined by injecting errors into the vehicle's accurate positioning information in a controllable operating scenario, and the intelligent driving function of real vehicles can participate in the verification process, the sufficiency and reliability of the vehicle's driving function verification can be improved through controllable different operating scenarios and different error injection methods. Attached Figure Description

[0013] Figure 1 This is an exemplary application scenario of the vehicle driving function determination method provided in the embodiments of this disclosure;

[0014] Figure 2 This is a flowchart illustrating a method for determining vehicle driving functions provided in an exemplary embodiment of this disclosure;

[0015] Figure 3 This is a flowchart illustrating a method for determining vehicle driving functions provided in another exemplary embodiment of this disclosure;

[0016] Figure 4 This is a schematic diagram of a process for determining error change information provided in an exemplary embodiment of this disclosure;

[0017] Figure 5 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure;

[0018] Figure 6 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure;

[0019] Figure 7 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure;

[0020] Figure 8 This is a schematic diagram of error change information provided in an exemplary embodiment of this disclosure;

[0021] Figure 9This is a schematic diagram of error change information provided in another exemplary embodiment of this disclosure;

[0022] Figure 10 This is a schematic diagram of error change information provided in yet another exemplary embodiment of this disclosure;

[0023] Figure 11 This is a schematic diagram illustrating the injection of errors based on spatial location provided in an exemplary embodiment of this disclosure;

[0024] Figure 12 This is a schematic diagram illustrating the injection of numerical simulation errors provided in an exemplary embodiment of this disclosure;

[0025] Figure 13 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure;

[0026] Figure 14 This is a schematic diagram of the structure of a vehicle driving function determination device provided in an exemplary embodiment of the present disclosure;

[0027] Figure 15 This is a schematic diagram of the structure of a vehicle driving function determination device provided in another exemplary embodiment of this disclosure;

[0028] Figure 16 This is a schematic diagram of the structure of a vehicle driving function determination device provided in yet another exemplary embodiment of the present disclosure;

[0029] Figure 17 This is a schematic diagram of the structure of a vehicle driving function determination device provided in yet another exemplary embodiment of this disclosure;

[0030] Figure 18 This is a schematic diagram of the structure of a vehicle driving function determination device provided in yet another exemplary embodiment of the present disclosure;

[0031] Figure 19 This is a structural diagram of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0032] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0033] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0034] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0035] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0036] Furthermore, the term "and / or" in this disclosure 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, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0037] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0038] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0039] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0040] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0041] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0042] This disclosure outlines

[0043] In developing this disclosure, the inventors discovered that in technologies related to intelligent driving function verification, the intelligent driving functions of vehicles are typically verified through extensive road testing, or the overall intelligent driving function algorithm is verified through numerical simulation. However, road testing rarely encounters high-risk scenarios. For example, some high-risk scenarios are long-tail scenarios (i.e., rare but significant scenarios), making it difficult to encounter the same or similar scenarios during road testing, resulting in insufficient verification sufficiency. Numerical simulation verification requires modeling the vehicle to achieve behavioral simulation. Vehicle modeling requires the use of mathematical models; however, mathematical models struggle to simulate the complex driving and dynamic characteristics of the vehicle itself, leading to low verification reliability.

[0044] Exemplary Overview

[0045] Figure 1 This is an exemplary application scenario of the vehicle driving function determination method provided in the embodiments of this disclosure. For example... Figure 1 As shown, the vehicle driving function determination device 11 can communicate with the driving function system 121 of the vehicle 12 to provide positioning information to the driving function system 121. The driving function system 121 performs path planning and control based on the positioning information, controlling the operating state of the vehicle 12. The vehicle 12 can be a real vehicle or a vehicle simulated through dynamics based on a motion platform or tire testing equipment. The driving function system 121 can include software and / or hardware components that implement the vehicle driving function. The software components may include, for example, perception function software, planning and control software, etc., and the hardware components may include, for example, devices that execute the corresponding software (e.g., processors, neural network processors, graphics processors, etc., as well as control devices and motion devices that control the vehicle's operating state, etc.). The vehicle driving function determination device 11 can execute the vehicle driving function determination method provided in the embodiments of this disclosure, effectively determining the vehicle's driving function. Specifically, the vehicle driving function determination device 11 can determine the initial driving route information of the vehicle 12 in a preset operating scenario; based on the initial driving route information and the first positioning information corresponding to the vehicle, it controls the operating state of the vehicle 12 in the preset operating scenario; the first positioning information is positioning information that meets preset error conditions determined by a preset method; in response to the operating state of the vehicle 12 meeting the preset conditions corresponding to the preset operating scenario, it injects an error into the first positioning information of the vehicle 12 according to the error injection method corresponding to the preset operating scenario, obtaining second positioning information with error; based on the second positioning information, it controls the operating state of the vehicle 12 and obtains the state change information of the vehicle 12 under the second positioning information; based on the state change information of the vehicle 12 in the preset operating scenario, it determines the driving function of the vehicle. The vehicle driving function determination device 11 can be used as an independent device to communicate with the driving function system 121 of the vehicle 12 through a certain connection method to realize the injection of positioning error and the determination of driving function. Alternatively, the vehicle driving function determination device 11 can execute the vehicle driving function determination method of this disclosure embodiment based on the existing hardware on the vehicle 12 to realize the injection of positioning error and the determination of driving function. Since the performance of a vehicle's driving function in response to errors can be determined by injecting errors into the vehicle's accurate positioning information in a controlled operating scenario, and the intelligent driving functions of real vehicles can be used in the verification process, the sufficiency and reliability of the vehicle's driving function verification can be improved through different controllable operating scenarios and different error injection methods.

[0046] Exemplary methods

[0047] Figure 2 This is a flowchart illustrating a method for determining vehicle driving functions provided in an exemplary embodiment of this disclosure. Embodiments of this disclosure can be applied to electronic devices, specifically servers, terminal devices, and other electronic equipment. Figure 2 As shown, the method provided in the embodiments of this disclosure may include the following steps:

[0048] Step 210: Determine the initial driving route information of the vehicle under the preset operating scenario.

[0049] The preset operating scenario can be a scenario set up on a real, open road test track, or it can be a constructed virtual operating scenario. The initial driving route information is pre-configured route information from a preset starting point to a preset ending point. This initial driving route information can include preset starting point information, preset ending point information, and the initially planned driving route. The preset starting point is the vehicle's initial position within this preset operating scenario.

[0050] In some optional embodiments, when the preset operating scenario is a real open road test track, the vehicle is a real vehicle. A real open road test track is an unobstructed, open test track without real obstacles. Virtual obstacles can be set in the scenario, that is, obstacle information is recorded and maintained in the test track without placing corresponding real obstacles in their respective locations. For example, virtual curbs, virtual target vehicles, and virtual pedestrians can be set. For static obstacles, obstacle information can include the obstacle's position, orientation, and size. For dynamic obstacles, obstacle information can include the obstacle's trajectory and size.

[0051] In some optional embodiments, when the preset operating scenario is a constructed virtual operating scenario, the vehicle can be a vehicle whose dynamics are simulated using a motion platform or tire testing equipment. A motion platform is a device used to simulate a real driving environment, providing a realistic driving experience through multi-degree-of-freedom motion simulation. For example, a motion platform may include electric cylinders, universal joints, etc., capable of simulating various motion postures of the vehicle in space, such as yaw, pitch, roll, rise, lateral (or transverse), and longitudinal movements. By simulating vehicle motion through a motion platform, combined with the constructed virtual operating scenario, the vehicle's operation under the corresponding operating scenario is simulated.

[0052] Step 220: Based on the initial driving route information and the first positioning information corresponding to the vehicle, control the vehicle's operating status in the preset operating scenario.

[0053] The first positioning information is positioning information that meets preset error conditions, determined through a preset method. The preset error conditions refer to a positioning error of 0 or close to 0 (e.g., less than an error threshold). In other words, the first positioning information can be considered error-free, accurate, and high-precision positioning information for the vehicle. The first positioning information may include the vehicle's position (X, Y, Z), attitude (yaw, pitch, roll), and speed (VX, VY, VZ). Here, X, Y, and Z represent the three-axis coordinates of the vehicle's position; yaw represents the yaw angle; pitch represents the pitch angle; roll represents the roll angle; and VX, VY, and VZ represent the vehicle's three-axis speeds.

[0054] In some alternative embodiments, for real vehicles, a high-precision positioning system can be configured on the vehicle to determine the accurate initial positioning information corresponding to the vehicle. The high-precision positioning system can be, for example, a satellite inertial navigation system.

[0055] In some optional embodiments, for a vehicle simulated by a motion platform, accurate information on changes in the vehicle's state can be obtained by monitoring the state of the motion platform and performing calculations to determine the vehicle's initial positioning information.

[0056] In some optional embodiments, controlling the vehicle's operating state in a preset operating scenario based on initial driving route information and the vehicle's corresponding first positioning information can refer to providing the initial driving route information to the vehicle's driving function system and controlling the vehicle to start running from the starting position. During operation, the vehicle's first positioning information at each moment (the current moment) is transmitted to the vehicle's driving function system in real time, enabling the driving function system to plan and control based on the first positioning information, continuously operating within the operating scenario. The sensor data required for the driving function system to perceive the environment can be input from real sensors at the test site, or it can be feedback of pre-obtained sensor data from the operating scenario, or feedback of perception result data from the operating scenario, as long as it enables the driving function system to plan and control, operating within the operating scenario. Sensor data can include, for example, at least one of image data, radar data, lidar data, millimeter-wave radar data, etc. The specific type of feedback data is not limited. For example, by simulating the real operating scenarios of a vehicle in a real open test site, the real sensor data of the vehicle in the test site can be superimposed with obstacle information and fed back into the vehicle's driving function system. This allows the driving function system to perform environmental perception, planning and control based on the sensor data, so as to control the vehicle's operating status in the corresponding operating scenario.

[0057] In some optional embodiments, the vehicle's operating status in a preset operating scenario may include the vehicle's operating time, real-time position, attitude, speed, etc. at each moment.

[0058] Step 230: In response to the vehicle's operating status meeting the preset conditions corresponding to the preset operating scenario, an error is injected into the vehicle's first positioning information according to the error injection method corresponding to the preset operating scenario to obtain the second positioning information with error.

[0059] The preset conditions can include at least one of the following: pre-configured time conditions, distance conditions (or position conditions), and speed conditions. The time condition can refer to the vehicle's running time reaching a specified time. The distance condition can refer to the vehicle's position reaching a specified location. The speed condition can refer to the vehicle's speed reaching a specified speed. The error injection method can include the error injection object and error change information. The error injection object can include at least one of the position, speed, and attitude in the first positioning information. Specifically, the error injection object can be at least one of X, Y, Z, VX, VY, VZ, yaw, pitch, and roll. For example, if the error injection object is Y, it means that an error needs to be injected into Y in the first positioning information. The error change information refers to the change in the error injected into the error injection object during vehicle operation. The error change information can include information on the change of error with running time, information on the change of error with vehicle running distance (or vehicle position), information on the change of error with vehicle speed, etc., without specific limitations.

[0060] For example, taking the relationship between error and time as an example, when the vehicle's running time reaches a designated time, an error that changes linearly with time is injected into the Y coordinate of the first positioning information. Then, the error injected into the Y coordinate of the first positioning information at different times satisfies a linear relationship with time, for example, error e = at + b, where t represents the current running time, and a and b represent the linear relationship coefficients. Therefore, the error value injected into the first positioning information at the current time t can be determined as time progresses, and this error value is superimposed on the Y coordinate of the first positioning information at the current time to obtain the second positioning information with error. In practical applications, error change information is not limited to linear changes; for example, it can also be instantaneous jumps, other curvilinear relationships, etc.

[0061] Step 240: Based on the second positioning information, control the vehicle's operating state and obtain the vehicle's state change information under the second positioning information.

[0062] The principle of controlling the vehicle's operating state based on the second positioning information is similar to that of the first positioning information. The second positioning information is provided to the vehicle's driving function system, enabling the system to perceive, plan, and control the vehicle based on the error-laden second positioning information. This allows the vehicle to travel along the planned route within the operating scenario and acquire information about the vehicle's state changes under the second positioning information. State change information can include position changes, speed changes, angle changes, etc., or it can include the vehicle's trajectory information, speed information at each time point, etc. The trajectory information can include the vehicle's position and attitude at each time point.

[0063] Understandably, the vehicle operates continuously in the scenario, and error injection can include injection at one or more time points. Steps 220 to 240 are processes that are repeatedly executed as the vehicle operates. At the initial time, the vehicle travels according to the initial driving route information and plans the driving path for the next time point based on the first positioning information at the initial time. In each subsequent time point, route planning and control are performed based on the first positioning information at that time until the vehicle's operating state meets preset conditions, at which point the vehicle begins route planning and control based on the second positioning information. Since the second positioning information contains a specified error, it may cause the vehicle's driving route to deviate from the driving route under accurate positioning. By obtaining the vehicle's state change information under the second positioning information, it can be used to subsequently analyze the vehicle's performance under the corresponding error.

[0064] Step 250: Determine the vehicle's driving function based on the vehicle's state change information in the preset operating scenario.

[0065] Among them, the vehicle's state change information in the preset operating scenario can characterize the vehicle's performance in the operating scenario after the injection of errors. Based on the vehicle's state change information in the preset operating scenario, the vehicle's driving functions can be determined. For example, it can verify (or test) the vehicle's driving function's tolerance to different positioning errors, verify whether the driving function will cause a collision under different positioning errors, verify whether the driving function will accelerate or decelerate suddenly or vibrate under different speed errors, and so on.

[0066] In some optional embodiments, the preset operating scenario may include one or more operating scenarios. For example, the preset operating scenario may include operating scenarios for one or more road types. Road types may include, for example, highways, urban roads, etc. Different operating scenarios can be set for each road type according to the different situations of traffic participants to simulate the vehicle's operation under different operating scenarios. In the case of multiple operating scenarios, the vehicle's driving function in the corresponding operating scenario can be determined according to the method of the embodiments of this disclosure for each operating scenario. Therefore, the vehicle's driving function can be fully verified through multiple operating scenarios, ensuring the sufficiency and reliability of the verification.

[0067] The method for determining vehicle driving functions provided in the embodiments of this disclosure can determine the performance of vehicle driving functions in response to errors by injecting errors into the accurate positioning information of the vehicle in a controllable operating scenario. Furthermore, it can involve the intelligent driving functions of real vehicles in the verification process. Thus, it can improve the sufficiency and reliability of vehicle driving function verification through different controllable operating scenarios and different error injection methods.

[0068] In some optional embodiments of this disclosure, the preset operating scenario is a preset real and controllable road test site, and the vehicle is a real vehicle. The real and controllable road test site (i.e., a real, open road test site) can be found in the foregoing description.

[0069] In some optional embodiments of this disclosure, the preset operating scenario is a pre-constructed simulated test scenario (i.e., a virtual operating scenario), and the vehicle is a vehicle simulated by dynamics based on a motion platform or tire testing equipment. See the foregoing embodiments for details.

[0070] In the embodiments of this disclosure, since both the real road test site and the simulated test scenario are controllable test sites and there is no actual collision risk, and the dynamic simulation vehicle can simulate the movement of the real vehicle, the combination of the real vehicle or the dynamic simulation vehicle enables the real vehicle to participate in the simulation test, ensuring the reliability of the verification, and the test scenario is controllable, which is convenient to cover various high-risk scenarios and ensure the sufficiency of the verification of the vehicle's driving function.

[0071] Figure 3 This is a flowchart illustrating a method for determining vehicle driving functions provided in another exemplary embodiment of this disclosure.

[0072] In some alternative embodiments, in the above... Figure 2 Based on the illustrated embodiments, as Figure 3 As shown, step 230, in response to the vehicle's operating state satisfying preset conditions corresponding to a preset operating scenario, injects an error into the vehicle's first positioning information according to the error injection method corresponding to the preset operating scenario to obtain second positioning information with error, which may include:

[0073] Step 2310: In response to the vehicle's operating status meeting the preset conditions corresponding to the preset operating scenario, determine the error injection object and error change information based on the error injection method corresponding to the preset operating scenario.

[0074] The error injection object includes at least one of the position, velocity, and attitude from the first positioning information. Error change information may include information on how the error changes over time, how it changes over vehicle distance (or vehicle position), how it changes over vehicle speed, and so on.

[0075] Step 2320: Based on the error change information, determine the error value corresponding to the current moment during vehicle operation.

[0076] The current time changes continuously as the vehicle moves. For example, starting from the vehicle's initial position, the current time is successively the initial time (t0), the first time (t1), the second time (t2), and so on. The current time can be represented as t. Error change information characterizes how the error changes with any factor such as time, position, or speed. Therefore, based on the error change information, i.e., the time, position, and speed of the current moment, the error value corresponding to the vehicle at the current moment can be determined. For example, the error value at the current moment can be determined by the error change information over time, e = at + b. As another example, the error value at the current moment can be determined by the error change information over speed, e = f(v), where f(v) represents the mapping function between error and speed v.

[0077] In some optional embodiments, the error variation information may include error values ​​at one or more discrete time points during the operation. For example, the error value at time ti is ei, the error value at time tj is ej, and no error is injected at other time points.

[0078] Step 2330: The error value corresponding to the current moment is superimposed on the error injection object in the first positioning information at the current moment to obtain the second positioning information with error at the current moment, which is used to control the vehicle's operating status.

[0079] For example, if the error injection object is position Y and the current error value is e, then e is superimposed on Y to obtain Y' = Y + e. The error value e can be positive or negative to achieve error superposition in different directions.

[0080] The embodiments of this disclosure configure the error injection object and error change information of the operating scenario, so that the vehicle can accurately inject errors into the specified error injection object in the high-precision positioning information during the operation of the operating scenario, thereby realizing the effective verification of the vehicle driving function.

[0081] In some optional embodiments of this disclosure, the error change information includes at least one of the following: error change over time, error change over vehicle travel distance, and error change over vehicle speed.

[0082] The error over time information describes how the error changes over time. This relationship can be linear, instantaneous, or a specific waveform error curve (e.g., sine, sawtooth, etc.), without specific limitations. The error over time information can include the curve type and curve coefficients. For example, the linear coefficient for a linear relationship, the coefficient for a cubic curve, the coefficient for a sine curve, etc. Similarly, the error over distance information describes how the error changes with distance. This relationship can be linear, instantaneous, or a specific waveform curve, etc. The error over speed information characterizes how the error changes with speed. For example, when the vehicle speed reaches a specified speed, the error is superimposed on the initial positioning information to simulate the positioning deviation of the vehicle under high-speed driving conditions.

[0083] In some optional embodiments, the error variation information can be determined based on simulation error from numerical simulation of the driving function. The simulation error is the error between the positioning information obtained by the positioning function (positioning algorithm) in the driving function and the high-precision positioning information obtained by a preset method. Based on the variation information of the simulation error, the error variation information to be injected into the vehicle is determined.

[0084] The embodiments of this disclosure can inject corresponding errors into the accurate positioning information of a vehicle according to time, vehicle travel distance, vehicle speed, etc., to verify the vehicle's functional performance under the corresponding errors. This facilitates the effective verification of driving functions under various operating scenarios and different positioning errors, thereby improving the sufficiency and reliability of the verification.

[0085] Figure 4 This is a schematic diagram of a process for determining error change information provided in an exemplary embodiment of this disclosure.

[0086] In some optional embodiments of this disclosure, such as Figure 4 As shown, the method provided in the embodiments of this disclosure may further include the step of determining error change information as follows:

[0087] Step 310: Obtain the simulation positioning information and corresponding positioning ground truth value of the vehicle's corresponding driving function application in the numerical simulation test.

[0088] Driving function applications refer to the functional algorithms (software) used to implement driving functions, corresponding to the software component of the driving function system. Driving function applications may include, for example, positioning applications, perception applications, and planning and control applications. Numerical simulation testing is based on the actual sensor outputs recorded by the vehicle, and simulation results are obtained through software algorithms. The simulated positioning information of driving function applications in numerical simulation testing is based on the perception results of the driving function applications, and is calculated using the positioning algorithms of the driving function applications to obtain the vehicle's positioning information. The true positioning value is the vehicle's actual positioning information at the moment the sensor data is collected. The true positioning value can be obtained through a high-precision positioning system on the vehicle.

[0089] Step 320: Determine the simulation error based on the simulation positioning information and the true positioning value.

[0090] The difference between the simulated positioning information and the true positioning value is the simulation error.

[0091] Step 330: Based on the simulation error, determine the error change information of the vehicle in the preset operating scenario.

[0092] Among them, the error change information of the vehicle in the preset operating scenario can be determined based on the error change of the simulation error in the corresponding real scenario.

[0093] In some optional embodiments, when using simulation errors to determine error change information, the preset operating scenario can be a setting that is the same as or similar to the real scenario that generates the simulation error, in order to verify the real performance of the real vehicle under the corresponding error.

[0094] In the embodiments of this disclosure, simulation errors are obtained through numerical simulation and used for real vehicle simulation. This facilitates the verification of the impact of simulation error changes on vehicle driving functions, thereby determining the tolerance of driving functions to positioning algorithm errors and ultimately determining the functional safety of the current driving function application.

[0095] In some optional embodiments of this disclosure, controlling the vehicle's operating state based on the second positioning information includes:

[0096] The second location information is transmitted to the vehicle so that the vehicle can use the driving function application on the vehicle to plan a driving route based on the second location information and drive according to the planned driving route.

[0097] The second positioning information can be transmitted to the vehicle's driving function system through the corresponding data interface on the vehicle. The driving function system plans the driving route based on the second positioning information through the driving function application, issues control commands according to the planned driving route, controls the vehicle's steering wheel, accelerator, and other actions, adjusts the vehicle's operating status, and makes the vehicle drive according to the planned driving route.

[0098] In the embodiments of this disclosure, during vehicle operation in a driving scenario, second positioning information of the injected error is transmitted to the vehicle for controlling the vehicle's operating state. Since the injected error and the operating scenario are controllable, the actual state change information of the vehicle under the injected error condition can effectively characterize the performance of the vehicle's driving function. Therefore, it can effectively verify the real performance of the vehicle's driving function in various aspects.

[0099] Figure 5 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure.

[0100] In some optional embodiments of this disclosure, based on any of the above embodiments, such as Figure 5 As shown, step 250, which determines the vehicle's driving functions based on the vehicle's state change information in a preset operating scenario, may include:

[0101] Step 2510: Determine the vehicle's performance status in the preset operating scenario based on the vehicle's status change information in the preset operating scenario.

[0102] The performance status can include the vehicle's performance in one or more aspects (e.g., whether a collision occurs, whether it causes sudden acceleration or deceleration, whether it causes vehicle vibration affecting ride comfort, whether it can maintain a constant speed, etc.). Specifically, it can be set according to the test objectives (or verification objectives) corresponding to the preset operating scenario. For example, if the test objective of the preset operating scenario is to test the vehicle's driving function's tolerance to different injection errors, then the vehicle's trajectory can be obtained based on the vehicle's state change information. Based on the trajectory and the virtual obstacle information set in the preset operating scenario, it can be determined whether the vehicle collided with an obstacle, thus obtaining the vehicle's performance status in that operating scenario. As another example, if the test objective is whether a certain speed fluctuation in the positioning speed will cause sudden acceleration or deceleration, or vehicle vibration, affecting ride comfort, then the vehicle's speed change information can be obtained based on the vehicle's state change information in that operating scenario. Based on the speed change information, it can be determined whether sudden acceleration or deceleration or vehicle vibration issues exist, thus obtaining the vehicle's performance status in that operating scenario.

[0103] In some optional embodiments, the vehicle's performance status under a preset operating scenario can be determined in any of the following ways:

[0104] Based on the vehicle's state change information in the preset operating scenario, the vehicle's operating trajectory is determined; based on the vehicle's operating trajectory and the preset obstacle information in the preset operating scenario, the vehicle's performance status in the preset operating scenario is determined; based on the vehicle's state change information in the preset operating scenario, the vehicle's speed change information is determined; based on the speed change information, the vehicle's performance status in the preset operating scenario is determined; based on the vehicle's state change information in the preset operating scenario, the vehicle's heading angle change information is determined; based on the heading angle change information, the vehicle's performance status in the preset operating scenario is determined.

[0105] The vehicle's trajectory can include its position (or position and orientation) at each point in time. Preset obstacle information is pre-configured virtual obstacle information within a preset operating scenario. This information can include at least one of static or dynamic obstacle information. Static obstacle information may include, for example, the position, size, and orientation of static obstacles such as cones and curbs. Dynamic obstacle information may include the dynamic trajectories, size, and orientation of other vehicles, pedestrians, cyclists, and other dynamic obstacles. Dynamic trajectories include the position of an obstacle at each point in time, or the position and orientation of an obstacle at each point in time. Based on the relative relationship between the vehicle's trajectory and the area or position information occupied by static obstacles in the operating scenario, it can be determined whether the vehicle collides with a static obstacle. Similarly, based on the relative relationship between the vehicle's trajectory and the dynamic trajectories of dynamic obstacles, it can be determined whether the vehicle collides with a dynamic obstacle. The state of whether the vehicle collides with an obstacle can be defined as the vehicle's performance state within the preset operating scenario. Alternatively, the tolerance level of the vehicle's driving function to injection errors can be determined based on whether a collision occurs between the vehicle and an obstacle, and this tolerance level can be defined as the vehicle's performance state under preset operating scenarios. Specific limitations are not specified.

[0106] Based on vehicle speed change information, the vehicle's speed-related performance status under a preset operating scenario can be determined. For example, in the event of an injection error, it can be determined whether the vehicle experiences sudden acceleration or deceleration, or whether it shakes, affecting ride comfort. Combined with preset obstacle information under the preset operating scenario, it can be determined whether a rear-end collision occurs, or whether the vehicle maintains a constant speed, and so on.

[0107] Based on the changes in heading angle (or yaw angle), the vehicle's performance related to the heading angle in a preset operating scenario can be determined. For example, in the event of an injection error, it can be determined whether the vehicle swerves or yaws, leading to a collision with a preset obstacle in the operating scenario.

[0108] In some optional embodiments, a corresponding method for determining the performance state can be set for each operating scenario based on the test objectives of that scenario. Then, during the test, the vehicle's performance state in that operating scenario is determined based on the method corresponding to each operating scenario.

[0109] Step 2520: Determine the vehicle's driving functions based on the vehicle's performance in the preset operating scenario.

[0110] Based on the vehicle's performance in preset operating scenarios, the response (or tolerance) of the vehicle's driving functions to corresponding errors can be determined. For example, if the vehicle does not collide in the preset operating scenario, it is determined that the vehicle's driving functions can tolerate the injected error and can effectively avoid a collision under this error. If a collision occurs, it is determined that the vehicle's driving functions cannot tolerate the error. Based on this, different errors can be injected under different operating scenarios to test the tolerance boundary of the vehicle's driving functions to errors. For another example, if the vehicle does not experience sudden deceleration or vibration when a positioning speed error is injected, it can be determined that the vehicle's driving functions have the ability to tolerate the positioning speed error.

[0111] The embodiments of this disclosure determine the true driving capability of a vehicle by assessing its performance under operating conditions and with the injection of positioning errors, thereby achieving effective verification of the vehicle's driving function and improving verification reliability.

[0112] Figure 6 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure.

[0113] In some optional embodiments of this disclosure, based on any of the above embodiments, the error injection method corresponding to the preset operating scenario includes multiple error change information for an error injection object; the error injection object is one of the position, speed, and attitude in the vehicle's first positioning information.

[0114] Among these, multiple error change information can cover different error ranges to verify the vehicle's driving function's tolerance to different errors. For example, taking the linear change of error over time as an example, multiple different maximum errors can be set, such as 0.1 meters, 0.2 meters, ..., 1 meter. The error change information includes gradually increasing from 0 to the maximum error within a preset time period, such as increasing from 0 to 0.1 meters, increasing from 0 to 0.2 meters, etc., to obtain multiple different error change information.

[0115] In some optional embodiments of this disclosure, based on any of the above embodiments, step 250, which determines the vehicle's driving function based on the vehicle's state change information in a preset operating scenario, includes:

[0116] Step 25a0: Based on the information on each state change, determine the performance state of the vehicle under each error change information.

[0117] Specifically, for each error change, simulation tests can be performed under a preset operating scenario to obtain the vehicle's state change information under that error change information. The state change information of the vehicle under each error change information is obtained based on multiple error change information. Furthermore, the vehicle's performance state under the corresponding error change information can be determined based on each state change information; the specific determination method can be found in the aforementioned embodiments.

[0118] Step 25b0: Based on the vehicle's performance status under each error change information, determine the error tolerance boundary value of the vehicle's driving function for the error injection object.

[0119] By combining the vehicle's performance under various error changes, the tolerance level of the vehicle's driving function for the corresponding error can be determined. This tolerance level can be categorized as either tolerable or intolerable. For any given error change, if a collision or other safety issue occurs under that error change, the vehicle's driving function's tolerance level for that error change is determined to be intolerable. If the vehicle can avoid a safety issue, the driving function can be determined to tolerate the error corresponding to that error change. Based on this, the tolerance boundary of the vehicle's driving function can be determined by combining its tolerance levels for various error changes. For example, taking lateral positioning error as an example, in 10 real-vehicle simulation tests with maximum errors of 0.1 meters, 0.2 meters, ..., 1 meter, if a collision can be avoided when the maximum error is less than 0.6 meters, the tolerance boundary of the vehicle's driving function for lateral positioning error can be determined to be 0.6 meters.

[0120] In some alternative embodiments, the obtained error tolerance boundary values ​​can be used to guide the improvement and optimization of the positioning algorithm for vehicle driving functions, or to verify whether the improvement of the positioning algorithm is effective. For example, if the positioning algorithm can control the lateral positioning error to 0.5 meters, and the vehicle driving function's tolerance boundary value for lateral positioning error is 0.6 meters, it can be determined that the improvement of the positioning algorithm is effective.

[0121] In some optional examples, if a vehicle experiences a 1-meter lateral positioning error in a tunnel during a real-world road test, causing it to collide with the tunnel shoulder, this scenario is quite challenging. While improvements to the positioning algorithm can control the lateral positioning error to 0.5 meters in numerical simulations, it's uncertain whether this improvement is sufficient to prevent the same accident from occurring. Therefore, the method described in this disclosure can be used to simulate the aforementioned real-world road test scenario in a realistic and controllable test environment, constructing a corresponding operating scenario. During the simulation test, after the vehicle enters the corresponding tunnel stage in the operating scenario, a linear error that varies with distance is applied, reaching its maximum value after traveling 50 meters and maintaining that maximum error. For example, ten maximum error values ​​(0.1m, 0.2m, ..., 1m) can be set, and ten real-vehicle simulation tests can be conducted. Each of the ten error curves is injected into the vehicle's accurate positioning information. The vehicle's operating state is controlled under the injected error conditions, and the vehicle's state change information is acquired. After completing the test, the state change information from each test can be used to calculate whether the vehicle collides with the virtual tunnel shoulder in the operating scenario, determining the vehicle's driving function's tolerance level for that error curve. Combining the ten tests, it was determined that when the error is less than 0.6m, collision with the tunnel shoulder can be avoided. Therefore, it can be confirmed that the improved positioning algorithm (error 0.5m) is effective and can prevent collisions.

[0122] The embodiments of this disclosure, by combining multiple error change information of an error injection object with the operating scenario, can effectively test and obtain the tolerance boundary of the vehicle driving function for the positioning error of the corresponding error injection object. Since the operating scenario and the injection error are controllable, it is convenient to simulate and test high-risk scenarios multiple times, thereby improving the sufficiency and reliability of the verification of high-risk scenarios.

[0123] Figure 7 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure.

[0124] In some optional embodiments of this disclosure, the preset operating scenarios include a variety of different operating scenarios. For example, the preset operating scenarios may include a variety of different highway driving scenarios, a variety of different urban road driving scenarios, etc. The specific scenarios can be set according to actual testing needs.

[0125] Step 250, which determines the vehicle's driving functions based on the vehicle's state change information in a preset operating scenario, may include:

[0126] Step 2501: Based on the vehicle's state change information in each operating scenario, determine the vehicle's performance status under the error injection method in each operating scenario.

[0127] For each operating scenario, the specific steps for determining the vehicle's performance status can be found in the aforementioned embodiments, and will not be repeated here.

[0128] Step 2502: Determine the vehicle's driving functions based on the vehicle's performance in various operating scenarios.

[0129] This can be achieved by combining the vehicle's performance in various operating scenarios to verify the real-world response of the vehicle's driving functions under different operating conditions. The specific settings can be configured according to the actual testing objectives.

[0130] In some optional examples, the vehicle's driving function response to positioning speed fluctuations can be verified through various different highway driving scenarios. For example, it can be determined whether a positioning speed fluctuation of up to 1 m / s will cause the vehicle to accelerate or decelerate suddenly, cause vehicle vibration, thereby affecting ride comfort, or cause a rear-end collision. Using the method of the embodiments of this disclosure, vehicle simulation tests can be performed to simulate n (e.g., n=50) different highway driving scenarios. That is, n simulation test scenarios can be set up based on a real open test site, or n corresponding virtual test scenarios can be constructed. In the simulation test, the error injection object is speed, and the error change information is the speed error that changes over time. The relationship between the error and time can be a sine wave, for example, with an amplitude of 1 m / s and a period of 20 seconds. During the vehicle's driving in each scenario, the aforementioned speed error that changes over time is superimposed on the vehicle's accurate first positioning information, and the state change information of the vehicle under the injected error is obtained. Based on the state change information, it is determined whether the vehicle can maintain a constant speed or whether it will cause sudden acceleration or deceleration. If, after testing in n different operating scenarios, it is determined that the vehicle will not accelerate or decelerate suddenly, provides a good riding experience, and will not collide with virtual obstacles in the operating scenarios, then it can be determined that the current vehicle driving function has the ability to tolerate speed error fluctuations of 1 meter per second.

[0131] In some optional examples, to address the heading deviation problem in the positioning algorithm, the positioning algorithm is iteratively optimized to obtain an optimized positioning algorithm. This optimized algorithm can correct the heading angle and gradually restore it to the correct heading angle after a heading deviation occurs. Numerical simulation of the optimized positioning algorithm reveals that during the heading angle recovery process, the heading angle exhibits a certain degree of irregular sawtooth-like jitter. It is uncertain whether this recovery process will adversely affect vehicle (autonomous vehicle) behavior in real-world scenarios, such as serpentine driving. To address this, the method provided in the embodiments of this disclosure can be used to record the error change curve of the numerical simulation process to determine the error change information in the real-vehicle simulation test. During the real-vehicle simulation test, the vehicle is controlled to operate in the corresponding operating scenario. The heading angle (yaw) in the vehicle's accurate first positioning information is used as the error injection object. During vehicle operation, errors are injected into the vehicle's first positioning information according to the error change curve of the numerical simulation process, resulting in second positioning information with errors. The vehicle's driving function system plans and controls based on the second positioning information, controlling the vehicle's operating state in the operating scenario and recording the vehicle's state change information. Based on the vehicle's state changes in the operating scenario, the vehicle's heading angle changes are determined. This heading angle change information is then used to determine if the vehicle exhibits serpentine driving behavior (i.e., its performance state). Based on the test results, the response state of the vehicle's driving functions to this recovery process is determined. This allows us to determine whether the optimized localization algorithm meets the specified requirements. If it does not meet the requirements, the localization algorithm can be iteratively optimized further.

[0132] The embodiments of this disclosure can conduct real vehicle simulation tests through various different operating scenarios. By combining the vehicle's performance in various different operating scenarios, the true capability of the vehicle's driving function in different operating scenarios can be effectively determined, ensuring the sufficiency and reliability of the verification.

[0133] In some alternative embodiments, Figure 8 This is a schematic diagram illustrating error variation information provided in an exemplary embodiment of this disclosure. For example... Figure 8 As shown, the error change information is the instantaneous jump error that changes with time or distance. That is, when the vehicle travels for a specified time or travels a specified distance, an error value is injected instantaneously, and the same error magnitude is maintained for the subsequent preset time period.

[0134] In some alternative embodiments, Figure 9 This is a schematic diagram illustrating error variation information provided in another exemplary embodiment of this disclosure. For example... Figure 9As shown, the error change information is a linear cumulative error, meaning that the error amplitude gradually increases at regular time intervals or distance intervals to simulate the error accumulation process. In practical applications, the error amplitude can also be gradually decreased at regular time intervals or distance intervals to test the performance of the vehicle's driving function system during the gradual correction of positioning errors.

[0135] In some alternative embodiments, Figure 10 This is a schematic diagram illustrating error variation information provided in yet another exemplary embodiment of this disclosure. For example... Figure 10 As shown, the error change information is a curve showing how the error changes over time.

[0136] In some alternative embodiments, Figure 11 This is a schematic diagram illustrating the injection of errors based on spatial location, provided in an exemplary embodiment of this disclosure. For example... Figure 11 As shown, if there is no error in the positioning information, the vehicle's driving trajectory should be the actual driving trajectory at the bottom of the figure. According to the spatial location, after applying (i.e. superimposing) errors to the accurate positioning information at one or more specified locations, the positioning information becomes the positioning result with applied errors at the top of the figure (i.e., the second positioning information with errors).

[0137] In some alternative embodiments, Figure 12 This is a schematic diagram illustrating the injection of numerical simulation errors provided in an exemplary embodiment of this disclosure. For example... Figure 12As shown, the error change information is obtained from numerical simulation. In the numerical simulation test, the error value between each simulation positioning result (i.e., the positioning result with error obtained based on the positioning algorithm) and the true positioning value is recorded. During the real vehicle simulation (i.e., vehicle-in-the-loop simulation), the corresponding numerical simulation error is applied to the accurate positioning information of the vehicle (i.e., the first positioning information) to obtain the second positioning information with error, which is used for the verification of the vehicle driving function. Vehicle-in-the-loop simulation refers to the system formed by the vehicle, the vehicle driving function determination device provided in the embodiments of this disclosure, and the controllable operating scenario, simulating the working situation of the driving function application (or driving function system) in a real scenario, and realizing the closed-loop verification of the vehicle driving function. That is, the various hardware and software of the real vehicle are used as a link in the simulation test system, working in real time in the simulation test to obtain the performance of the vehicle driving function system in the corresponding operating scenario. For a real and controllable test site, the system-in-the-loop is a hardware-in-the-loop system, which can be formed with the vehicle through a customized video injection board and a host computer. High-precision positioning information (first positioning information) or second positioning information with errors, along with high-precision map information, is injected into the vehicle's driving function controller via a hardware injection board. Perception video data can also be injected. Driving function applications are deployed within the driving function controller, and planning and control are performed based on the received information to regulate the vehicle's operation in the test area. For virtual operating scenarios, corresponding operating scenarios can be constructed based on configuration files (e.g., map files, scene description files showing the position, speed, angle, size, etc. of the vehicle and surrounding obstacles). These scenarios are then combined with a motion platform to simulate vehicle motion, forming an in-loop system for in-loop simulation testing.

[0138] The embodiments disclosed herein can simulate various high-risk scenarios through real vehicle-in-the-loop simulation testing. Due to the controllability of the operating scenarios and injection errors, the sufficiency and reliability of the verification results of vehicle driving functions can be effectively improved.

[0139] Figure 13 This is a flowchart illustrating a method for determining vehicle driving functions provided in yet another exemplary embodiment of this disclosure.

[0140] In some optional embodiments of this disclosure, based on any of the above embodiments, such as Figure 13 As shown, the method provided in the embodiments of this disclosure may further include:

[0141] Step 260: Determine whether the current driving function application of the vehicle meets the safety conditions based on the vehicle's driving functions.

[0142] Specifically, the safety conditions of the current driving function application can be determined based on the vehicle's responsiveness in preset operating scenarios. For example, if the driving function can avoid collisions or other safety accidents in a large number of operating scenarios, it can be determined that the current driving function application meets the safety conditions.

[0143] In some optional embodiments, the current driving function application may include at least one of a positioning function application, a perception function application, a planning function application, and a control function application. For example, determining whether the positioning function application meets safety conditions (e.g., the positioning error is less than a specified error threshold), determining whether the planning and control function applications meet safety conditions (e.g., whether the planning and control results can effectively prevent the vehicle from causing a safety accident), and determining whether the overall driving function system meets safety conditions, etc.

[0144] Step 270: In response to the current driving function application not meeting safety conditions, output a prompt message.

[0145] The prompts can include specific functions in the current driving function application that do not meet safety requirements, such as a large positioning algorithm error that is outside the tolerance range of the planning and control function application. The specific content of the prompts can be set according to the corresponding test objectives.

[0146] In some optional embodiments, the prompt information can be output in any way, such as being displayed on a specified screen or output as a file in a certain format.

[0147] The embodiments of this disclosure can effectively test whether the vehicle driving function meets the corresponding safety conditions through different controllable operating scenarios and controllable error injection methods. If the safety conditions are not met, prompt information can be output to promptly remind relevant R&D personnel to iterate and optimize the application of the driving function or take other countermeasures.

[0148] In the application of vehicle driving functions, there are the following requirements: to know the error tolerance boundary of the downstream planning and control function for the positioning function, and to verify whether related problems have been solved in high-risk scenarios. Specifically, positioning and planning and control can affect each other. In actual vehicle road testing, this mutual influence can make it impossible to determine the main cause of road test problems, and it is difficult to verify even after iterative optimization of the algorithm. For example, the positioning function can affect the planning and control function. If there is an error in the positioning function's observation, this error will lead to inaccurate vehicle position estimation, which in turn will cause the planning and control function to issue incorrect control commands, resulting in the vehicle failing to complete the intended driving, or even causing a safety accident. In addition, unreasonable control commands from the planning and control function can affect the positioning function. Because there is a delay in the calculation and transmission between different functional modules, unreasonable control commands from the planning and control function will produce large or rapid vehicle movements, which may prevent the positioning function from observing such changes in vehicle pose in time. This causes the positioning information provided to the planning and control function to lag behind the actual positioning information. This loop between the positioning function and the planning and control function will amplify the error step by step, leading to loss of vehicle control, such as sudden steering and swerving. Furthermore, the observation results of the positioning function are subject to certain errors, and the error level may vary in different scenarios, time periods, and road sections. Due to scene changes, the observation accuracy and performance of sensors may vary. For example, lidar depends on scenes with obvious structured features, cameras depend on scene lighting conditions, GNSS (Global Navigation Satellite System) requires unobstructed signals, and IMU (Inertial Measurement Unit) signals are sensitive to bumps and temperature changes. Moreover, ensuring vehicle safety is crucial, and errors in the positioning or planning control functions may lead to safety accidents, such as collisions with other vehicles, curbs, or fences. Furthermore, different driving scenarios (such as high-speed driving, traffic jams, turning, U-turns, lane changes, and overtaking) have different tolerance levels for positioning errors. Before the driving function is launched, it is necessary to verify whether the problems related to safety accidents or high-risk scenarios have been fixed by the corresponding functional algorithms. Road testing is not enough to verify whether the problems in high-risk scenarios have been solved, and numerical simulation is not enough to simulate the complex driving and dynamic characteristics of the vehicle itself. Therefore, relying solely on verifying the magnitude of the positioning algorithm error has low reliability, and it is difficult to determine to what level the positioning error needs to be reduced to ensure the safety of specific high-risk scenarios.

[0149] The method of this disclosure can perform real-vehicle simulation tests based on controllable operating scenarios and error injection, effectively obtaining the error tolerance boundary of downstream planning and control functions for positioning functions. Furthermore, the operating scenario is controllable, open, and unobstructed, allowing for the simulation of various high-risk scenarios and multiple real-vehicle simulation tests while ensuring vehicle safety, effectively verifying whether high-risk scenario issues have been resolved. Therefore, the method of this disclosure can meet various verification requirements before the vehicle driving function goes live, ensuring the reliability of the vehicle driving function and thus guaranteeing the functional safety of the vehicle.

[0150] The embodiments described above can be implemented individually or in any combination without conflict. The specific implementation can be set according to actual needs, and this disclosure does not limit them.

[0151] The method for determining any vehicle driving function provided in this disclosure can be executed by any suitable electronic device with data processing capabilities, including but not limited to electronic devices such as terminal devices and servers. Alternatively, the method for determining any vehicle driving function provided in this disclosure can be executed by a processor, such as by a processor executing the method for determining any vehicle driving function mentioned in this disclosure by calling corresponding instructions stored in memory. Further details will not be elaborated below.

[0152] Exemplary device

[0153] Figure 14 This is a schematic diagram of a vehicle driving function determination apparatus provided in an exemplary embodiment of the present disclosure. The apparatus of this embodiment can be used to implement corresponding vehicle driving function determination method embodiments of the present disclosure, such as… Figure 14 The apparatus shown may include: a first processing module 51, a second processing module 52, a third processing module 53, a fourth processing module 54, and a fifth processing module 55.

[0154] The first processing module 51 is used to determine the initial driving route information of the vehicle in a preset operating scenario.

[0155] The second processing module 52 is used to control the vehicle's operating status in a preset operating scenario based on the initial driving route information and the vehicle's corresponding first positioning information; the first positioning information is positioning information that meets preset error conditions and is determined by a preset method.

[0156] The third processing module 53 is used to respond to the vehicle's operating state meeting the preset conditions corresponding to the preset operating scenario, and inject errors into the vehicle's first positioning information according to the error injection method corresponding to the preset operating scenario to obtain the second positioning information with errors.

[0157] The fourth processing module 54 is used to control the vehicle's operating status based on the second positioning information and to acquire information on the vehicle's status changes under the second positioning information.

[0158] The fifth processing module 55 is used to determine the driving function of the vehicle based on the state change information of the vehicle in a preset operating scenario.

[0159] In some optional embodiments of this disclosure, the preset operating scenario is a preset real and controllable road test site, and the vehicle is a real vehicle.

[0160] In some optional embodiments of this disclosure, the preset operating scenario is a pre-built simulated test scenario, and the vehicle is a vehicle simulated by dynamics based on a motion platform or tire testing equipment.

[0161] Figure 15 This is a schematic diagram of the structure of a vehicle driving function determination device provided in another exemplary embodiment of this disclosure.

[0162] In some optional embodiments of this disclosure, in the above... Figure 14 Based on the illustrated embodiments, as Figure 15 As shown, the third processing module 53 may include: a first processing unit 531, a second processing unit 532 and a third processing unit 533.

[0163] The first processing unit 531 is used to respond to the vehicle's operating state meeting the preset conditions corresponding to the preset operating scenario, and to determine the error injection object and error change information based on the error injection method corresponding to the preset operating scenario.

[0164] The error injection object includes at least one of the position, velocity, and attitude in the first positioning information.

[0165] The second processing unit 532 is used to determine the error value corresponding to the current moment during vehicle operation based on error change information.

[0166] The third processing unit 533 is used to superimpose the error value corresponding to the current moment onto the error injection object in the first positioning information at the current moment to obtain the second positioning information with error at the current moment, which is used to control the vehicle's operating status.

[0167] In some optional embodiments of this disclosure, the error change information includes at least one of the following: error change over time, error change over vehicle travel distance, and error change over vehicle speed.

[0168] Figure 16 This is a schematic diagram of the structure of a vehicle driving function determination device provided in another exemplary embodiment of the present disclosure.

[0169] In some optional embodiments of this disclosure, based on any of the above embodiments, such as Figure 16 As shown, the apparatus provided in the embodiments of this disclosure may further include: an acquisition module 61, a first determination module 62, and a second determination module 63.

[0170] The acquisition module 61 is used to acquire the simulation positioning information and corresponding positioning true value of the driving function application of the vehicle in the numerical simulation test.

[0171] The first determining module 62 is used to determine the simulation error based on the simulation positioning information and the true positioning value.

[0172] The second determining module 63 is used to determine the error change information of the vehicle in the preset operating scenario based on the simulation error.

[0173] In some optional embodiments of this disclosure, the fourth processing module 54 is specifically used to: transmit the second positioning information to the vehicle so that the vehicle can plan a driving route based on the second positioning information through the driving function application on the vehicle and drive according to the planned driving route.

[0174] Figure 17 This is a schematic diagram of the structure of a vehicle driving function determination device provided in yet another exemplary embodiment of this disclosure.

[0175] In some optional embodiments of this disclosure, based on any of the above embodiments, such as Figure 17 As shown, the fifth processing module 55 may include: a first determining unit 551 and a second determining unit 552.

[0176] The first determining unit 551 is used to determine the performance status of the vehicle in the preset operating scenario based on the vehicle's state change information in the preset operating scenario.

[0177] In some optional embodiments, the first determining unit 551 may specifically determine the vehicle's performance state in a preset operating scenario in any of the following ways: determining the vehicle's operating trajectory based on the vehicle's state change information in the preset operating scenario; determining the vehicle's performance state in the preset operating scenario based on the vehicle's operating trajectory and preset obstacle information in the preset operating scenario; determining the vehicle's speed change information based on the vehicle's state change information in the preset operating scenario; determining the vehicle's performance state in the preset operating scenario based on the speed change information; determining the vehicle's heading angle change information based on the vehicle's state change information in the preset operating scenario; and determining the vehicle's performance state in the preset operating scenario based on the heading angle change information.

[0178] The second determining unit 552 is used to determine the driving function of the vehicle based on the vehicle's performance status in a preset operating scenario.

[0179] In some optional embodiments of this disclosure, based on any of the above embodiments, the error injection method corresponding to the preset operating scenario includes multiple error change information for an error injection object; the error injection object is one of the position, speed, and attitude in the vehicle's first positioning information.

[0180] In some optional embodiments of this disclosure, based on any of the above embodiments, such as Figure 17 As shown, the fifth processing module 55 may include: a first determining unit 551 and a second determining unit 552.

[0181] The first determining unit 551 is used to determine the performance state of the vehicle under each error change information based on each state change information.

[0182] The second determining unit 552 is used to determine the error tolerance boundary value of the vehicle's driving function for the error injection object based on the vehicle's performance state under each error change information.

[0183] In some optional embodiments of this disclosure, based on any of the above embodiments, the preset operating scenarios include a variety of different operating scenarios.

[0184] In some optional embodiments of this disclosure, based on any of the above embodiments, such as Figure 17 As shown, the fifth processing module 55 may include: a first determining unit 551 and a second determining unit 552.

[0185] The first determining unit 551 is used to determine the performance status of the vehicle under the error injection method in each operating scenario based on the vehicle's state change information in each operating scenario.

[0186] The second determining unit 552 is used to determine the driving function of the vehicle based on the vehicle's performance status in various operating scenarios.

[0187] Figure 18 This is a schematic diagram of the structure of a vehicle driving function determination device provided in another exemplary embodiment of the present disclosure.

[0188] In some optional embodiments of this disclosure, based on any of the above embodiments, such as Figure 18 As shown, the apparatus provided in the embodiments of this disclosure may further include a sixth processing module 56 and a seventh processing module 57.

[0189] The sixth processing module 56 is used to determine whether the current driving function application of the vehicle meets the safety conditions based on the vehicle's driving functions.

[0190] The seventh processing module 57 is used to output a prompt message in response to the current driving function application not meeting the safety conditions.

[0191] The embodiments described above can be implemented individually or in any combination without conflict. The specific implementation can be set according to actual needs, and this disclosure does not limit them.

[0192] The beneficial technical effects corresponding to the exemplary embodiments of this device can be found in the corresponding beneficial technical effects of the exemplary method section above, and will not be repeated here.

[0193] Exemplary electronic devices

[0194] Figure 19 This is a structural diagram of an electronic device provided in an embodiment of the present disclosure, including at least one processor 91 and a memory 92.

[0195] The processor 91 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device 90 to perform desired functions.

[0196] The memory 92 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 91 may execute one or more computer program instructions to implement the methods and / or other desired functions of the various embodiments of this disclosure described above.

[0197] In one example, the electronic device 90 may also include an input device 93 and an output device 94, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0198] The input device 93 may also include, for example, a keyboard, mouse, touchscreen, microphone, various sensors, etc. Sensors may include, for example, image sensors (e.g., cameras, webcams), LiDAR, millimeter-wave radar, ultrasonic radar, positioning sensors, pressure sensors, air quality sensors, temperature sensors, etc. Image sensors, LiDAR, millimeter-wave radar, ultrasonic radar, etc., can be used for environmental perception, i.e., detecting moving and static objects in the surrounding environment. Moving and static objects may include, for example, static objects such as lane lines, curbs, arrows, signs, trees, and buildings, as well as dynamic objects such as surrounding vehicles, pedestrians, and cyclists. Positioning sensors are used to locate the mobile device (e.g., a bicycle, a robot, etc.) where the electronic device is located. Positioning sensors may include, for example, an Inertial Measurement Unit (IMU) and a Global Positioning System (GPS). Pressure sensors can be used to detect seat pressure. Temperature sensors can be used to detect the temperature inside the vehicle cabin. Air quality sensors can be used to detect the air quality inside the vehicle cabin.

[0199] The output device 94 can output various information to the outside, including, for example, a display, a speaker, a communication network and its connected remote output devices, etc.

[0200] Of course, for the sake of simplicity, Figure 19 Only some of the components of the electronic device 90 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 90 may include any other suitable components depending on the specific application.

[0201] In some optional embodiments of this disclosure, the electronic device may include: a memory, a processor, and a means for determining vehicle driving functions; the memory is used to store processor-executable instructions; the processor is used to read the executable instructions from the memory and execute the instructions to control the means for determining vehicle driving functions to implement the method for determining vehicle driving functions provided in any of the above embodiments; or, the electronic device includes: the means for determining vehicle driving functions provided in any of the above embodiments.

[0202] Embodiments of this disclosure also provide a system for determining vehicle driving functions, such as... Figure 1 As shown, the system may include: a vehicle driving function system; a vehicle driving function determination device provided in any of the above embodiments; the vehicle driving function determination device communicates with the vehicle driving function system to implement the vehicle driving function determination method provided in any of the above embodiments.

[0203] Exemplary computer program products and computer-readable storage media

[0204] In addition to the methods and apparatus described above, embodiments of this disclosure may also provide a computer program product, including computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods in the various embodiments of this disclosure described in the "Exemplary Methods" section above.

[0205] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of embodiments of this disclosure. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0206] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods in the various embodiments of this disclosure described in the "Exemplary Methods" section above.

[0207] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, but is not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0208] The basic principles of this disclosure have been described above with reference to specific embodiments. However, the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0209] Various modifications and variations can be made to this disclosure without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

1. A method for determining vehicle driving functions, comprising: Determine the initial driving route information of the vehicle under the preset operating scenario; Based on the initial driving route information and the first positioning information corresponding to the vehicle, the operating state of the vehicle in the preset operating scenario is controlled. The first positioning information is positioning information that meets preset error conditions and is determined by a preset method; In response to the vehicle's operating state meeting the preset conditions corresponding to the preset operating scenario, an error is injected into the vehicle's first positioning information according to the error injection method corresponding to the preset operating scenario to obtain the second positioning information with error. Based on the second positioning information, the operating state of the vehicle is controlled, and the state change information of the vehicle under the second positioning information is obtained; The driving function of the vehicle is determined based on the state change information of the vehicle in the preset operating scenario.

2. The method according to claim 1, wherein, The step of injecting errors into the first positioning information of the vehicle according to the error injection method corresponding to the preset operating scenario to obtain the second positioning information with errors includes: Based on the error injection method corresponding to the preset operating scenario, the error injection object and error change information are determined; the error injection object includes at least one of the position, velocity, and attitude in the first positioning information. Based on the error change information, the error value corresponding to the current moment during the vehicle's operation is determined; The error value corresponding to the current moment is superimposed on the error injection object in the first positioning information at the current moment to obtain the second positioning information with error at the current moment, which is used to control the operating state of the vehicle.

3. The method according to claim 2, wherein, The error change information includes at least one of the following: error change over time, error change over the distance the vehicle travels, and error change over the speed of the vehicle.

4. The method according to claim 2, wherein, It also includes the following operations for determining the error change information: Obtain the simulation positioning information and corresponding positioning true value of the driving function application of the vehicle in the numerical simulation test; The simulation error is determined based on the simulated positioning information and the true positioning value. Based on the simulation error, the error change information of the vehicle in the preset operating scenario is determined.

5. The method according to claim 1, wherein, The step of determining the driving function of the vehicle based on the state change information of the vehicle in the preset operating scenario includes: The performance status of the vehicle in the preset operating scenario is determined by any of the following methods: Based on the state change information of the vehicle in the preset operating scenario, the vehicle's operating trajectory is determined; based on the vehicle's operating trajectory and the preset obstacle information in the preset operating scenario, the vehicle's performance state in the preset operating scenario is determined. Based on the state change information of the vehicle in the preset operating scenario, determine the speed change information of the vehicle; based on the speed change information, determine the performance state of the vehicle in the preset operating scenario. Based on the state change information of the vehicle in the preset operating scenario, determine the heading angle change information of the vehicle; based on the heading angle change information, determine the performance state of the vehicle in the preset operating scenario; The driving function of the vehicle is determined based on the vehicle's performance in the preset operating scenario.

6. The method according to claim 1, wherein, The error injection method corresponding to the preset operating scenario includes multiple error change information for one error injection object; the error injection object is one of the position, speed, and attitude in the first positioning information of the vehicle. The step of determining the driving function of the vehicle based on the state change information of the vehicle in the preset operating scenario includes: Based on the state change information, the performance state of the vehicle under each of the error change information is determined; Based on the vehicle's performance under each of the error change information, the error tolerance boundary value of the vehicle's driving function for the error injection object is determined.

7. The method according to claim 1, wherein, The preset operating scenarios include a variety of different operating scenarios; The step of determining the driving function of the vehicle based on the state change information of the vehicle in the preset operating scenario includes: Based on the vehicle's state change information in each operating scenario, the vehicle's performance status under the error injection method in each operating scenario is determined. The driving function of the vehicle is determined based on the vehicle's performance in each of the aforementioned operating scenarios.

8. The method according to any one of claims 1-7, wherein, The preset operating scenario is a preset real and controllable road test site, and the vehicle is a real vehicle; or, The preset operating scenario is a pre-constructed simulated test scenario, and the vehicle is a vehicle simulated by dynamics based on a motion platform or tire testing equipment.

9. The method according to any one of claims 1-7, wherein, The step of controlling the vehicle's operating status based on the second positioning information includes: The second location information is transmitted to the vehicle so that the vehicle can plan a driving route based on the second location information through the driving function application on the vehicle and drive according to the planned driving route.

10. The method according to any one of claims 1-7, wherein, Also includes: Based on the vehicle's driving functions, determine whether the current application of the vehicle's driving functions meets safety conditions; In response to the current driving function application not meeting safety conditions, a prompt message is output.

11. A device for determining a vehicle driving function, comprising: The first processing module is used to determine the initial driving route information of the vehicle under the preset operating scenario; The second processing module is used to control the operating state of the vehicle in the preset operating scenario based on the initial driving route information and the first positioning information corresponding to the vehicle. The first positioning information is positioning information that meets preset error conditions and is determined by a preset method; The third processing module is used to respond to the fact that the vehicle's operating state meets the preset conditions corresponding to the preset operating scenario, and inject errors into the vehicle's first positioning information according to the error injection method corresponding to the preset operating scenario to obtain the second positioning information with errors. The fourth processing module is used to control the operating state of the vehicle based on the second positioning information, and to obtain the state change information of the vehicle under the second positioning information; The fifth processing module is used to determine the driving function of the vehicle based on the state change information of the vehicle in the preset operating scenario.

12. A system for determining vehicle driving functions, comprising: The vehicle's driving function system; The vehicle driving function determination device as described in claim 11; the vehicle driving function determination device communicates with the vehicle's driving function system to implement the method described in any one of claims 1-10.

13. An electronic device, the electronic device comprising: Memory, processor, and device for determining vehicle driving functions; The memory is used to store the processor-executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to control the vehicle driving function of the determining device to implement the method described in any one of claims 1-10. or, The electronic device includes the apparatus described in claim 11.

14. A computer-readable storage medium storing a computer program for performing the method according to any one of claims 1-10.

15. A computer program product, wherein when instructions in the computer program product are executed by a processor, the method described in any one of claims 1-10 of this disclosure is performed.

Images