Distance error evaluation methods, devices, electronic equipment and storage media

Abstract

This invention provides a distance error evaluation method, apparatus, electronic device, and storage medium, comprising: receiving first data, wherein the first data is the measurement value between the vehicle and the sensed object measured by the vehicle's sensors; acquiring the nominal measurement value of the sensor under ideal conditions, and acquiring the difference between the nominal measurement value and the first data based on the first data; acquiring a normal distribution curve of the hardware failure rate corresponding to the vehicle's ASIL level; acquiring the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold, which is used to evaluate whether the sensor's measurement value is qualified; evaluating the difference, and if the difference exceeds the first threshold, the sensor's measurement value is evaluated as qualified; otherwise, it is evaluated as unqualified. This method limits and evaluates the sensing distance measurement error from a functional safety perspective, enhances the accuracy of sensor distance measurement, and ensures the safety of vehicle operation.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a distance error evaluation method, device, electronic device, and storage medium. Background Technology

[0002] Self-driving, also known as driverless driving, is a vehicle driving method implemented through computer systems. With the increasing prevalence of self-driving vehicles, they can be used as taxis or public transportation. When using a self-driving vehicle, passengers need to input their destination. The self-driving vehicle generates a route based on its current location and destination and then travels along that route. Road conditions are not static; the driving status of other vehicles on the road is constantly changing. This requires self-driving vehicles to accurately judge the distance between themselves and surrounding vehicles during operation, ensuring they stay within a safe zone and avoid traffic accidents caused by collisions with other vehicles or obstacles, thus preventing injury to passengers and others.

[0003] Currently, while traditional autonomous vehicles can use their onboard sensors to measure distances to surrounding vehicles and obstacles, enabling them to avoid these obstacles in time, these sensors have inherent errors in distance measurement. This instability in distance measurement makes autonomous vehicles prone to collisions with other vehicles or obstacles that could affect their safety, potentially leading to traffic accidents while traveling along their planned paths.

[0004] Therefore, traditional autonomous vehicles are more susceptible to sensing errors during the sensing distance process, which reduces the accuracy of the sensing distance and thus affects the safe operation of autonomous vehicles. Summary of the Invention

[0005] This invention provides a distance error evaluation method, device, electronic device, and storage medium to address the shortcomings of poor distance accuracy in existing technologies, achieve stable vehicle distance sensing, and ensure the safety of autonomous vehicles.

[0006] This invention provides a distance error evaluation method, the method comprising:

[0007] Receive first data, which is the measurement value between the vehicle and the sensing object obtained by the vehicle's sensors;

[0008] Obtain the nominal measurement value of the sensor under ideal conditions, and obtain the difference between the nominal measurement value and the first data based on the first data;

[0009] Obtain the normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle;

[0010] Based on the normal distribution curve, the data relationship between the maximum permissible error of the sensor and the hardware failure rate is obtained to determine a first threshold, which is used to evaluate whether the sensor's measurement value is qualified.

[0011] The difference is evaluated. If the difference exceeds the first threshold, the sensor's measurement value is evaluated as qualified; otherwise, it is evaluated as unqualified.

[0012] According to a distance error evaluation method provided by the present invention, receiving the first data includes:

[0013] Receive the lateral velocity and lateral acceleration of the sensed object;

[0014] The lateral safe distance between the vehicle and the sensed object is calculated based on the lateral velocity and lateral acceleration.

[0015] According to a distance error evaluation method provided by the present invention, receiving the first data further includes:

[0016] Receive the longitudinal velocity and longitudinal acceleration of the sensed object;

[0017] The longitudinal safe distance between the vehicle and the perceived object is calculated based on the longitudinal velocity and longitudinal acceleration.

[0018] According to a distance error evaluation method provided by the present invention, the method further includes:

[0019] A first boundary value is obtained based on the first data, wherein the first boundary value is the lateral safety distance and the longitudinal safety distance between the vehicle and the sensing object;

[0020] The first driving area of ​​the vehicle is obtained based on the lateral safety distance and the longitudinal safety distance. The first driving area is a safe area within the first boundary value for normal vehicle driving.

[0021] According to a distance error evaluation method provided by the present invention, the method further includes:

[0022] When there is no object to be sensed within the sensing range of the sensor, a second driving area is obtained, which is a safe driving area without the object to be sensed.

[0023] The second driving area is not restricted by the first boundary value.

[0024] According to a distance error evaluation method provided by the present invention, obtaining the normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle includes:

[0025] Obtain the hardware failure rate corresponding to the ASIL level of the vehicle;

[0026] The confidence interval for the hardware failure rate is determined based on the vehicle's ASIL level.

[0027] Construct a normal distribution curve of the hardware failure rate within the confidence interval.

[0028] According to a distance error evaluation method provided by the present invention, the step of obtaining the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold includes:

[0029] Obtain the boundary distance between the first boundary value and the vehicle;

[0030] Obtain the probability that the error in the first data is greater than the boundary distance from the normal distribution curve, and perform an inverse cumulative distribution operation based on the probability to obtain the inverse cumulative distribution value;

[0031] The ratio between the boundary distance and the inverse cumulative distribution value is used as the first threshold.

[0032] According to a distance error evaluation method provided by the present invention, the ASIL level is divided into multiple ASIL levels, and each ASIL level has a corresponding hardware failure rate.

[0033] The present invention also provides a distance error evaluation device, the device comprising:

[0034] A data receiving module is used to receive first data, which is the measurement value between the vehicle and the sensing object measured by the vehicle's sensors.

[0035] The first acquisition module is used to acquire the nominal measurement value of the sensor under ideal conditions, and to acquire the difference between the nominal measurement value and the first data based on the first data;

[0036] The second acquisition module is used to acquire the normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle.

[0037] The determination module is used to obtain the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve, so as to determine a first threshold, which is used to evaluate whether the measurement value of the sensor is qualified;

[0038] The evaluation module is used to evaluate the difference. If the difference exceeds the first threshold, the sensor's measurement value is evaluated as qualified; otherwise, it is evaluated as unqualified.

[0039] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the distance error evaluation methods described above.

[0040] The present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, implements any of the distance error evaluation methods described above.

[0041] The distance error evaluation method, apparatus, electronic device, and storage medium provided by this invention acquire sensor data from a vehicle to obtain the current distance between the vehicle and the object sensed by the sensor. The difference between the current distance and the sensor's nominal measurement value under ideal conditions is obtained by comparing the current distance with the sensor's nominal measurement value; this difference represents the error generated by the sensor during distance measurement. Subsequently, the vehicle's hardware failure rate is determined based on its ASIL level, and a normal distribution curve is constructed based on the hardware failure rate to obtain the data relationship between the hardware failure rate and the maximum permissible error of the sensor distance measurement, thereby determining a threshold range for evaluating the reliability of the sensor distance measurement. Finally, the current error generated by the vehicle's sensor distance measurement is evaluated based on the maximum permissible error of the sensor distance measurement. If the current error does not exceed the threshold range of the maximum permissible error of the sensor distance measurement, the sensor's measurement value is evaluated as qualified; if it exceeds the threshold range of the maximum permissible error of the sensor distance measurement, it is evaluated as unqualified. This method generates an evaluation result of the vehicle perception system by verifying the real-time error generated when the vehicle sensor measures distance. From the perspective of functional safety, it limits and evaluates the sensor ranging error, which improves the accuracy of sensor ranging to a certain extent, avoids the safety hazards caused by inaccurate vehicle sensor ranging, and ensures the safety of vehicle driving. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is one of the flowcharts illustrating the distance error evaluation method provided by the present invention;

[0044] Figure 2 This is the second flowchart of the distance error evaluation method provided by the present invention;

[0045] Figure 3 This is the third flowchart of the distance error evaluation method provided by the present invention;

[0046] Figure 4 This is the fourth flowchart of the distance error evaluation method provided by the present invention;

[0047] Figure 5 This is the fifth flowchart illustrating the distance error evaluation method provided by the present invention;

[0048] Figure 6 This is a flowchart illustrating the distance error evaluation method in a specific embodiment of the present invention;

[0049] Figure 7 This is a schematic diagram of the normal distribution of the distance error evaluation method in a specific embodiment provided by the present invention;

[0050] Figure 8 This is a schematic diagram of the distance error evaluation device provided by the present invention;

[0051] Figure 9 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0052] Figure label:

[0053] 810: Data receiving module; 820: First acquisition module; 830: Second acquisition module; 840: Determination module; 850: Evaluation module; 910: Processor; 920: Communication interface; 930: Memory; 940: Communication bus. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0055] The following is combined with Figures 1-9 The present invention describes a distance error evaluation method, apparatus, electronic device, and storage medium.

[0056] like Figure 1 As shown, in one embodiment, a distance error evaluation method includes the following steps:

[0057] Step S110: Receive first data, which is the measurement value between the vehicle and the perceived object measured by the vehicle's sensors.

[0058] The sensing object is other vehicles, road users, or obstacles besides the vehicle itself, and the first data is the sensor-measured distance between the vehicle and the sensing object detected by the on-board sensor.

[0059] Specifically, the vehicle server receives distance data measured by the onboard sensors from other targets in the environment surrounding the autonomous vehicle, i.e., the sensor measurements.

[0060] Step S120: Obtain the nominal measurement value of the sensor under ideal conditions, and obtain the difference between the nominal measurement value and the first data based on the first data.

[0061] The nominal measurement value represents the sensor measurement data of the vehicle under ideal conditions. It is used to calibrate the sensor measurement data during actual driving to obtain the sensor ranging error during real-world driving. This involves installing the sensor under normal weather, lighting, temperature, and humidity conditions, conducting numerous measurements, and then using the statistical values ​​of the measurement results as a benchmark for the sensor's measurement capability. This nominal measurement value can also be considered the correct data measured by the sensor. The difference represents the error in the sensor measurement values ​​during actual application.

[0062] Specifically, the vehicle server obtains the real-time error generated by the vehicle sensor during ranging based on the data obtained from the on-board sensor in step S110 and the nominal measurement value under ideal conditions.

[0063] Step S130: Obtain the normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle.

[0064] ASIL (Automotive Safety Integrity Level) refers to the safety integrity level of a vehicle. It is a risk classification system defined by the ISO 26262 standard for the functional safety of road vehicles. This standard defines functional safety as "a hazard arising from the failure of an electrical or electronic system, where there is no unreasonable risk." ASIL determines safety requirements based on the probability and acceptability of damage to ensure that automotive components comply with ISO 26262. ISO 26262-A, B, C, and D identify four ASIL levels, with ASIL A representing the lowest level and ASIL D representing the highest automotive hazard level. The hardware failure rate, abbreviated as PMHF (Probabilistic Metrics for Hardware Failure), serves as a measure of functional safety hardware corresponding to different ASIL levels. The unit is FIT (Failure In Time), and each ASIL level has a corresponding hardware failure rate.

[0065] Specifically, the vehicle server constructs a hardware failure rate corresponding to the vehicle's ASIL level, and constructs a corresponding hardware failure rate normal distribution curve based on this hardware failure rate.

[0066] Step S140: Obtain the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve, so as to determine the first threshold. The first threshold is used to evaluate whether the sensor's measurement value is qualified.

[0067] Further, the step of obtaining the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve to determine the first threshold includes:

[0068] Obtain the boundary distance between the first boundary value and the vehicle.

[0069] The probability of the error in the first data being greater than the boundary distance is obtained from the normal distribution curve, and an inverse cumulative distribution operation is performed based on the probability to obtain the inverse cumulative distribution value.

[0070] The ratio between the boundary distance and the inverse cumulative distribution value is used as the first threshold.

[0071] Specifically, the vehicle server obtains the data relationship between the maximum permissible error of sensor ranging and the hardware failure rate based on the normal distribution curve of hardware failure rate constructed in step S130, and then determines the threshold range corresponding to the maximum permissible error of sensor ranging, i.e., the first threshold, through the data relationship. This threshold range is used to evaluate the error generated by sensor ranging in step S120.

[0072] The relationship between the maximum permissible error and the hardware failure rate is as follows:

[0073]

[0074] In the formula, σ min AL is the maximum permissible error threshold for the sensing distance (i.e., the first data), F() is the distance between the safety boundary (i.e., the first boundary value) and the vehicle, p is the inverse cumulative distribution function (ICDF), and p is the probability that the sensing distance is greater than AL, and p is obtained from the hardware failure rate normal distribution curve.

[0075] Step S150: Evaluate the difference. If the difference exceeds the first threshold, the sensor's measurement value is evaluated as qualified; otherwise, it is evaluated as unqualified.

[0076] Specifically, the vehicle server evaluates the real-time error generated during sensor ranging in step S120 based on the threshold range corresponding to the maximum permissible error of sensor ranging obtained in step S140. If the real-time error between other vehicles, road users, or obstacles and the vehicle where the sensor is located does not exceed the threshold range corresponding to the maximum permissible error of sensor ranging, the measurement value of the corresponding sensor is evaluated as qualified, indicating that the sensor's ranging is relatively accurate. If the real-time error between other vehicles, road users, or obstacles and the vehicle where the sensor is located exceeds the threshold range corresponding to the maximum permissible error of sensor ranging, the measurement value of the corresponding sensor is evaluated as unqualified, indicating that the sensor's ranging is inaccurate, posing a safety hazard and making it prone to collisions with the object sensed by the sensor.

[0077] The aforementioned distance error evaluation method obtains the current distance between the vehicle and the object being sensed by acquiring sensor data from the vehicle. This current distance is then compared to the sensor's nominal measurement value under ideal conditions to obtain the difference between the sensor's measured distance and the nominal value. This difference represents the error generated by the sensor during ranging. Subsequently, the vehicle's hardware failure rate is determined based on its ASIL level, and a normal distribution curve is constructed based on this failure rate to obtain the data relationship between the hardware failure rate and the maximum permissible error of the sensor ranging. This data determines the threshold range used to evaluate the reliability of the sensor ranging. Finally, the current error generated by the vehicle's sensor ranging is evaluated based on the maximum permissible error of the sensor ranging. If the current error does not exceed the threshold range of the maximum permissible error of the sensor ranging, the sensor's measurement value is considered acceptable; otherwise, it is considered unacceptable. This method generates an evaluation result of the vehicle perception system by verifying the real-time error generated when the vehicle sensor measures distance. From the perspective of functional safety, it limits and evaluates the sensor ranging error, which improves the accuracy of sensor ranging to a certain extent, avoids the safety hazards caused by inaccurate vehicle sensor ranging, and ensures the safety of vehicle driving.

[0078] like Figure 2 As shown, in one embodiment, the distance error evaluation method provided by the present invention receives first data and includes the following steps:

[0079] Step S112: Receive the lateral velocity and lateral acceleration of the sensed object.

[0080] Specifically, the vehicle server receives the lateral velocity and lateral acceleration of the objects it senses through sensors.

[0081] Step S114: Calculate the lateral safe distance between the vehicle and the perceived object based on the lateral velocity and lateral acceleration.

[0082] Specifically, the vehicle server calculates the lateral safety distance between the perceived object and the autonomous vehicle by analyzing the lateral velocity and lateral acceleration of the sensor-perceived object obtained in step S112.

[0083] like Figure 3 As shown, in one embodiment, the distance error evaluation method provided by the present invention receives first data and includes the following steps:

[0084] Step S116: Receive the longitudinal velocity and longitudinal acceleration of the perceived object.

[0085] Specifically, the vehicle server receives the longitudinal velocity and longitudinal acceleration of the objects it senses through sensors.

[0086] Step S118: Calculate the longitudinal safety distance between the vehicle and the perceived object based on the longitudinal velocity and longitudinal acceleration.

[0087] Specifically, the vehicle server calculates the longitudinal safety distance between the perceived object and the autonomous vehicle by analyzing the longitudinal velocity and longitudinal acceleration of the sensor-perceived object obtained in step S116.

[0088] like Figure 4 As shown, in one embodiment, the distance error evaluation method provided by the present invention further includes the following steps:

[0089] Step S410: Obtain the first boundary value based on the first data. The first boundary value is the lateral safety distance and the longitudinal safety distance between the vehicle and the perceived object.

[0090] Specifically, the vehicle server obtains the lateral and longitudinal safe distances between the autonomous vehicle and the objects perceived by the sensors based on the measurement data from the vehicle's sensors.

[0091] Step S420: Obtain the first driving area of ​​the vehicle based on the lateral safety distance and the longitudinal safety distance. The first driving area is a safe area within the first boundary value for normal vehicle driving.

[0092] The first driving area is a safe driving area surrounded by the lateral and longitudinal safe distances between the vehicle and the sensor-sensing object. Within this area, the vehicle will not rub or collide with the sensor-sensing object, while beyond this area, it will rub or collide with the sensor-sensing object.

[0093] Specifically, the vehicle server determines the safe zone in which the vehicle can drive normally based on the lateral and longitudinal safety distances obtained in step S410.

[0094] Step S430: When there is no object to be sensed within the sensing range of the vehicle sensor, a second driving area is obtained. The second driving area is a safe driving area without any objects to be sensed.

[0095] Specifically, when there is no object to be sensed within the sensing range of the vehicle sensors, the vehicle server will obtain a driving area different from step S420. Within this driving area, there are no other vehicles or obstacles affecting the vehicle's driving, meaning there is no risk of collision or friction between the vehicle and other vehicles or obstacles, and it is not limited by the first boundary value.

[0096] like Figure 5 As shown, in one embodiment, the distance error evaluation method provided by the present invention obtains a normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle, including the following steps:

[0097] Step S510: Obtain the hardware failure rate corresponding to the ASIL level of the vehicle.

[0098] Step S520: Determine the confidence interval of the hardware failure rate based on the vehicle's ASIL level.

[0099] Among them, the hardware failure rate corresponding to different ASIL levels has a corresponding confidence interval in its normal distribution curve.

[0100] Specifically, the vehicle server determines the confidence interval of the hardware failure rate based on the vehicle's ASIL level.

[0101] Step S530: Construct a normal distribution curve of hardware failure rate within the confidence interval.

[0102] Specifically, the vehicle server constructs and obtains the hardware failure rate normal distribution curve within the confidence interval determined in step S520.

[0103] In a specific embodiment, the present invention provides a distance error evaluation method, see [link to relevant documentation]. Figure 6 As shown, the onboard server of an autonomous vehicle receives sensor data from the vehicle's sensors, which perceive the surrounding environment. Based on this data, it calculates the state information of other targets within the safe driving area. These targets include other vehicles or road users in the surrounding environment, or obstacles that could affect the vehicle's normal operation. The onboard server determines the boundary values ​​of the safe driving area based on the sensor data and, according to the functional safety level (ASIL) and its corresponding hardware failure rate (PMHF), determines the confidence interval for the distance between the autonomous vehicle and other vehicles, road users, or obstacles in the surrounding environment. Finally, based on the boundary values ​​and confidence intervals of the safe driving area, it determines the maximum permissible error threshold for the distance between the autonomous vehicle and other surrounding targets, as obtained by the sensors.

[0104] Finally, the vehicle server verifies and evaluates the sensor ranging error based on the maximum permissible error threshold between the autonomous vehicle and other surrounding targets to generate the corresponding evaluation result of the vehicle sensing system. If the sensor ranging error exceeds the maximum permissible error threshold, the evaluation is unqualified; if the sensor ranging error does not exceed the maximum permissible error threshold, the evaluation is qualified.

[0105] In this embodiment, the safe driving area boundary of the autonomous vehicle includes the lateral and longitudinal safe distances between the autonomous vehicle and other targets. If there are no other targets around the autonomous vehicle, there is no safe driving area boundary value. If other targets are traveling in the same lane, then the longitudinal safe distance (d) is defined. min,lon Calculated using the following formula:

[0106]

[0107] In the formula, v0 is the longitudinal velocity of the autonomous vehicle, t is the reaction time, a0 is the longitudinal acceleration of the autonomous vehicle, (a 0min,break (a) represents the reasonable minimum longitudinal deceleration for the autonomous vehicle, v1 represents the longitudinal velocity of other targets, and (a) represents the longitudinal velocity of other targets. 1max,break () is the maximum longitudinal deceleration that is reasonable for other objectives.

[0108] If other targets are in the adjacent lane, the lateral safety distance (d) min,lat Calculated using the following formula:

[0109]

[0110] In the formula, u is the preset lateral safety distance fluctuation value, v2 is the lateral acceleration of the autonomous vehicle, t is the reaction time, and v 2t Let be the lateral velocity of the autonomous vehicle at time t, (a min,break v1 represents the reasonable minimum lateral deceleration of the autonomous vehicle relative to other targets, v2 represents the lateral velocity of the other targets, and v3 represents the lateral velocity of the other targets. 3t Let t be the lateral velocity of the autonomous vehicle.

[0111] According to ISO 26262:2018-5, the hardware failure rate (PMHF) values ​​corresponding to ASIL levels are: ASILD: 10 FIT, ASILC: 100 FIT, ASILB: 100 FIT. Based on the PMHF values, confidence intervals are obtained. The error distribution of sensor ranging follows a normal distribution, thus the relationship between the PMHF value and the sensor ranging error can be obtained. Taking ASILD level as an example, combined with... Figure 7 As shown, sigma represents the standard deviation, mu represents the expected value, and the percentage represents the mathematical probability distribution, i.e., the confidence level of the sensor measurement results. At 95% confidence level, the sensor measurement error will not exceed ±0.2m; at 99.999999% confidence level, the sensor measurement error will not exceed ±0.57m. The confidence interval corresponding to 10 FIT is 99.999999%, which, according to the normal distribution formula, is 5.73σ. Therefore, the maximum permissible error threshold σ for the sensor sensing distance is... min The calculation formula is as follows:

[0112]

[0113] In the formula, AL is the distance between the safe driving boundary and the autonomous vehicle, F() is the inverse cumulative distribution function (ICDF), and p is the probability that the sensing distance is greater than the error of AL.

[0114] In addition, σ min This can also be used as a functional safety requirement for sensor ranging errors. In the evaluation of sensor ranging, the evaluation results are obtained based on multiple repeated tests. If the sensor ranging error exceeds σ... min If the sensing distance error is less than σ, the evaluation result is unqualified. min If so, the evaluation result is qualified.

[0115] The aforementioned distance error evaluation method acquires vehicle kinematic information of the corresponding target area collected by the target sensor using a set perception module, and determines the longitudinal and lateral safe distances of the vehicle based on this kinematic information. Subsequently, a confidence interval is determined based on a set ASIL level, and the maximum permissible error threshold for the longitudinal and lateral perceived distances (obtained through sensor perception, which differs from the safe distance) is determined based on this confidence interval. Finally, the sensing distance error of the autonomous vehicle is verified and evaluated based on this maximum permissible error threshold, generating the corresponding evaluation result for the vehicle perception system. This method proposes a maximum permissible error range for perception distance measurement from a functional safety perspective, provides an evaluation approach for the design of autonomous vehicle perception systems, and to a certain extent improves the efficiency of vehicle functional safety verification and enhances the accuracy of vehicle sensing distance measurement, thereby ensuring the safety of autonomous vehicle operation.

[0116] The distance error evaluation device provided by the present invention is described below. The distance error evaluation device described below can be referred to in correspondence with the distance error evaluation method described above.

[0117] like Figure 8 As shown, in one embodiment, a distance error evaluation device includes a data receiving module 810, a first acquisition module 820, a second acquisition module 830, a determination module 840, and an evaluation module 850.

[0118] The data receiving module 810 is used to receive first data, which is the measurement value between the vehicle and the sensing object measured by the vehicle's sensors.

[0119] The first acquisition module 820 is used to acquire the nominal measurement value of the sensor under ideal conditions, and to acquire the difference between the nominal measurement value and the first data based on the first data.

[0120] The second acquisition module 830 is used to acquire the normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle.

[0121] The determination module 840 is used to obtain the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve, so as to determine the first threshold, which is used to evaluate whether the sensor's measurement value is qualified.

[0122] The evaluation module 850 is used to evaluate the difference. If the difference exceeds the first threshold, the sensor's measurement value is evaluated as qualified; otherwise, it is evaluated as unqualified.

[0123] In this embodiment, the distance error evaluation device provided by the present invention has a data receiving module specifically used for:

[0124] Receive the lateral velocity and lateral acceleration of the perceived object.

[0125] The lateral safe distance between the vehicle and the perceived object is calculated based on the lateral velocity and lateral acceleration of the perceived object.

[0126] In this embodiment, the distance error evaluation device provided by the present invention, the data receiving module is further used for:

[0127] Receive the longitudinal velocity and longitudinal acceleration of the perceived object.

[0128] The longitudinal safe distance between the vehicle and the perceived object is calculated based on the longitudinal velocity and longitudinal acceleration of the perceived object.

[0129] In this embodiment, the distance error evaluation device provided by the present invention further includes a third acquisition module, a fourth acquisition module, and a fifth acquisition module.

[0130] The third acquisition module is used to acquire the first boundary value based on the first data. The first boundary value is the lateral safety distance and the longitudinal safety distance between the vehicle and the perceived object.

[0131] The fourth acquisition module is used to acquire the first driving area of ​​the vehicle based on the lateral safety distance and the longitudinal safety distance. The first driving area is the safe area within the first boundary value for normal vehicle driving.

[0132] The fifth acquisition module is used to acquire a second driving area when there is no object to be sensed within the sensing range of the vehicle sensors. The second driving area is a safe driving area without any objects to be sensed.

[0133] In this embodiment, the distance error evaluation device provided by the present invention further includes a construction module, used for:

[0134] Obtain the hardware failure rate corresponding to the ASIL level of the vehicle;

[0135] The confidence interval for hardware failure rate is determined based on the vehicle's ASIL level.

[0136] Construct a normal distribution curve of hardware failure rate within the confidence interval.

[0137] Figure 9 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 9As shown, the electronic device may include a processor 910, a communications interface 920, a memory 930, and a communication bus 940, wherein the processor 910, the communications interface 920, and the memory 930 communicate with each other via the communication bus 940. The processor 910 can call logical instructions in the memory 930 to execute a distance error evaluation method. This method includes: receiving first data, the first data being measurement values ​​between the vehicle and the perceived object measured by the vehicle's sensors; acquiring the nominal measurement value of the sensor under ideal conditions, and acquiring the difference between the nominal measurement value and the first data based on the first data; acquiring a normal distribution curve of the hardware failure rate corresponding to the vehicle's ASIL level; acquiring the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold, the first threshold being used to evaluate whether the sensor's measurement value is qualified; evaluating the difference, and if the difference exceeds the first threshold, the sensor's measurement value is evaluated as qualified; otherwise, it is evaluated as unqualified.

[0138] Furthermore, the logical instructions in the aforementioned memory 930 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0139] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the distance error evaluation method provided by the above methods. The method includes: receiving first data, the first data being a measurement value between the vehicle and the perceived object measured by a sensor of the vehicle; obtaining a nominal measurement value of the sensor under ideal conditions, and obtaining a difference between the nominal measurement value and the first data based on the first data; obtaining a normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle; obtaining a data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold, the first threshold being used to evaluate whether the measurement value of the sensor is qualified; evaluating the difference, and if the difference exceeds the first threshold, evaluating the measurement value of the sensor as qualified, otherwise evaluating it as unqualified.

[0140] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a distance error evaluation method provided by the methods described above. The method includes: receiving first data, the first data being measurement values ​​between the vehicle and a sensed object measured by a vehicle's sensor; acquiring a nominal measurement value of the sensor under ideal conditions, and acquiring a difference between the nominal measurement value and the first data based on the first data; acquiring a normal distribution curve of the hardware failure rate corresponding to the vehicle's ASIL level; acquiring a data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold, the first threshold being used to evaluate whether the sensor's measurement value is qualified; evaluating the difference, and if the difference exceeds the first threshold, evaluating the sensor's measurement value as qualified, otherwise evaluating it as unqualified.

[0141] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distance error evaluation method, characterized in that, The method includes: Receive first data, which is the measurement value between the vehicle and the sensing object obtained by the vehicle's sensors; Obtain the nominal measurement value of the sensor under ideal conditions, and obtain the difference between the nominal measurement value and the first data based on the first data; Obtain the normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle; Based on the normal distribution curve, the data relationship between the maximum permissible error of the sensor and the hardware failure rate is obtained to determine a first threshold, which is used to evaluate whether the sensor's measurement value is qualified. The difference is evaluated. If the difference does not exceed the first threshold, the sensor's measurement value is evaluated as qualified; otherwise, it is evaluated as unqualified. The step of obtaining the data relationship between the maximum permissible error of the sensor and the hardware failure rate based on the normal distribution curve to determine the first threshold includes: Obtain the boundary distance between the first boundary value and the vehicle, wherein the first boundary value is the lateral safety distance and the longitudinal safety distance between the vehicle and the sensing object; Obtain the probability that the error in the first data is greater than the boundary distance from the normal distribution curve, and perform an inverse cumulative distribution operation based on the probability to obtain the inverse cumulative distribution value; The ratio between the boundary distance and the inverse cumulative distribution value is used as the first threshold; the formula for calculating the first threshold is as follows: ； In the formula, Let be the first threshold, AL be the distance between the safe driving boundary and the autonomous vehicle, F() be the inverse cumulative distribution function (ICDF), and p be the probability that the sensing distance is greater than AL.

2. The distance error evaluation method according to claim 1, characterized in that, The receiving of the first data includes: Receive the lateral velocity and lateral acceleration of the sensed object; The lateral safe distance between the vehicle and the sensed object is calculated based on the lateral velocity and lateral acceleration.

3. The distance error evaluation method according to claim 2, characterized in that, The receiving of the first data further includes: Receive the longitudinal velocity and longitudinal acceleration of the sensed object; The longitudinal safe distance between the vehicle and the perceived object is calculated based on the longitudinal velocity and longitudinal acceleration.

4. The distance error evaluation method according to claim 3, characterized in that, The method further includes: The first boundary value is obtained based on the first data; The first driving area of ​​the vehicle is obtained based on the lateral safety distance and the longitudinal safety distance. The first driving area is a safe area within the first boundary value for normal vehicle driving.

5. The distance error evaluation method according to claim 4, characterized in that, The method further includes: When there is no object to be sensed within the sensing range of the sensor, a second driving area is obtained, which is a safe driving area without the object to be sensed. The second driving area is not restricted by the first boundary value.

6. The distance error evaluation method according to claim 1, characterized in that, The process of obtaining the normal distribution curve of the hardware failure rate corresponding to the ASIL level of the vehicle includes: Obtain the hardware failure rate corresponding to the ASIL level of the vehicle; The confidence interval for the hardware failure rate is determined based on the vehicle's ASIL level. Construct a normal distribution curve of the hardware failure rate within the confidence interval.

7. The distance error evaluation method according to any one of claims 1 to 6, characterized in that, The ASIL level is divided into multiple ASIL levels, and each ASIL level has a corresponding hardware failure rate.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the distance error evaluation method as described in any one of claims 1 to 7.

9. A computer storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the distance error evaluation method according to any one of claims 1 to 7.

Images