Vehicle-mounted sensor precision determination method and system, vehicle and computer storage medium

Abstract

The invention relates to a vehicle-mounted sensor precision determination method and system, a vehicle and a computer storage medium, and belongs to the technical field of automatic driving, and the sensor precision determination method comprises the steps: obtaining the measurement motion data of a target moving object collected by a to-be-measured vehicle-mounted sensor; real motion data of the target moving object is obtained, and the real motion data is used for representing the motion state of the target moving object; determining a precision threshold value of the to-be-measured vehicle-mounted sensor based on the performance requirement of the to-be-measured vehicle-mounted sensor, the category of the measured motion data and the numerical value interval of the measured motion data when the error is within a preset error range; and calculating a difference value between the measured motion data and the real motion data, and determining the precision of the to-be-measured vehicle-mounted sensor based on a size relationship between the difference value and the precision threshold value. According to the invention, the precision of the vehicle-mounted sensor can be determined with low cost and high precision.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and system for determining the accuracy of an on-board sensor, a vehicle, and a computer storage medium. Background Art

[0002] Autonomous driving technology has been widely used, and the safety of autonomous driving has always been a controversial topic. The accuracy of sensors is an important factor affecting the safety of autonomous driving. Therefore, accurately determining the accuracy of sensors is a direction that needs to be studied.

[0003] In the existing technology, the accuracy of vehicle-mounted sensors is determined by building a road truth system. The data collected by the vehicle sensors is compared with the true value data collected by the road truth system to determine the accuracy of the sensors. However, the road truth system is expensive, which increases project development costs. Without the road truth system, it is impossible to accurately measure the dynamic sensing accuracy of the sensors.

[0004] It can be seen that the existing technology cannot accurately measure the dynamic sensing accuracy of the sensor at a low cost. Summary of the Invention

[0005] In view of this, it is necessary to provide a sensor accuracy determination method, system, vehicle and computer storage medium, which can accurately measure the sensing accuracy of vehicle-mounted sensors without using a road truth system, thereby achieving low-cost measurement purposes.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for determining the accuracy of a vehicle-mounted sensor, comprising: Obtaining the measured motion data of the target moving object collected by the onboard sensor of the vehicle to be tested; Acquiring real motion data of the target moving object, wherein the real motion data is used to represent the motion state of the target moving object, and the error is within a preset error range; Determining an accuracy threshold of the on-board sensor to be tested based on the performance requirements of the on-board sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data; The difference between the measured motion data and the actual motion data is calculated, and the accuracy of the vehicle sensor to be tested is determined based on the relationship between the difference and the accuracy threshold.

[0007] In one possible implementation, obtaining measured motion data of a target moving object collected by a sensor mounted on a vehicle to be tested includes: Obtain measured motion data of the target mobile object collected by the on-board sensor to be tested when the target mobile object is in different motion states, wherein the measured motion data includes the longitudinal distance between the target mobile object and the on-board sensor to be tested, the lateral distance between the target mobile object and the on-board sensor to be tested, the longitudinal relative speed between the target mobile object and the on-board sensor to be tested, the lateral relative speed between the target mobile object and the on-board sensor to be tested, and the heading angle of the target mobile object.

[0008] In a possible implementation, different motion states include different relative positions, different relative speeds, and different relative heading angles between the vehicle carrying the on-board sensor to be measured and the target moving object.

[0009] In one possible implementation, obtaining real motion data of a target moving object includes: While acquiring the measured motion data, a calibrated motion data acquisition module installed on the same vehicle as the on-board sensor to be measured is used to collect the real motion data of the target moving object.

[0010] In one possible implementation, determining the accuracy threshold of the onboard sensor to be tested based on the performance requirements of the onboard sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data includes: Determining a first accuracy threshold interval based on performance requirements of the vehicle-mounted sensor to be tested; determining a second accuracy threshold interval based on the category of the measured motion data; determining a third precision threshold interval based on the numerical interval of the measured motion data; The accuracy threshold of the vehicle-mounted sensor to be tested is determined based on the first accuracy threshold interval, the second accuracy threshold interval, and the third accuracy threshold interval.

[0011] In a possible implementation, before calculating the difference between the measured motion data and the actual motion data, the following steps are included: The measured motion data and the real motion data are time-aligned based on the acquisition moments of the measured motion data and the real motion data.

[0012] In one possible implementation, calculating a difference between measured motion data and actual motion data, and determining the accuracy of the vehicle-mounted sensor to be tested based on a relationship between the difference and an accuracy threshold, includes: Calculate the difference between each measured motion data and the corresponding real motion data, and calculate the relationship between each difference and the accuracy threshold; The accuracy of the onboard sensor to be tested is determined based on the number of differences that are less than the accuracy threshold.

[0013] In a second aspect, the present invention further provides a vehicle-mounted sensor accuracy determination system, applicable to the vehicle-mounted sensor accuracy determination method described in any of the aforementioned embodiments, comprising: The sensor to be tested is used to collect the measured motion data of the target moving object and send the measured motion data to the data analysis module; a calibrated motion data acquisition module, configured to acquire the real motion data of the target moving object and send the real motion data to the data analysis module; A data analysis module is used to determine the accuracy threshold of the vehicle-mounted sensor to be tested based on the performance requirements of the vehicle-mounted sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data; calculate the difference between the measured motion data and the actual motion data, and determine the accuracy of the vehicle-mounted sensor to be tested based on the relationship between the difference and the accuracy threshold.

[0014] In a third aspect, the present invention further provides a vehicle, comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps in the sensor accuracy determination method described in any one of the above embodiments.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the sensor accuracy determination method described in any of the above embodiments.

[0016] The beneficial effects of the present invention are as follows: the vehicle-mounted sensor accuracy determination method provided by the present invention obtains the real motion data of the target moving object and the measured motion data of the target moving object collected by the vehicle-mounted sensor to be tested, without the need to build a road truth value system, thus saving costs; and determines corresponding sensor accuracy thresholds based on different sensor performance requirements, different measured motion data types and different numerical intervals, and determines corresponding sensor accuracy thresholds according to different requirements and different motion scenarios, and divides the sensor accuracy thresholds more accurately, ensuring the accuracy of the accuracy determination of the sensor to be tested; and then calculates the difference between the real motion data and the measured motion data, compares the difference with the sensor accuracy threshold, and determines the accuracy of the sensor. In the absence of a road truth value system, the accuracy of the sensor can still be determined relatively accurately, and the cost of determining the sensor accuracy is low and the accuracy is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of a method for determining the accuracy of a vehicle-mounted sensor provided by an embodiment of the present invention; Figure 2 A flowchart of a method for determining an accuracy threshold provided by an embodiment of the present invention; Figure 3 A schematic flow chart of an implementation method of S103 provided in an embodiment of the present invention; Figure 4 A schematic structural diagram of a vehicle-mounted sensor accuracy determination system provided by an embodiment of the present invention; Figure 5 A schematic structural diagram of a vehicle provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0020] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] In the prior art, when determining the accuracy of on-board sensors, a road truth system is usually built. The road truth system is a data collection system composed of on-board sensors such as meter-wave radar, laser radar, and high-precision combined inertial navigation, plus efficient data recording equipment. Among them, the meter-wave radar, laser radar, and high-precision combined inertial navigation are directly installed on both sides of the road. They can collect motion data of vehicles traveling on the road and obtain the true value of the vehicle motion data through a series of complex calculations. This true value is then compared with the motion data collected by the on-board sensors of the vehicle to be tested to determine the accuracy of the on-board sensors of the vehicle to be tested. However, the road truth system requires the use of multiple sensors, and the number of each sensor is also large. It also requires a dedicated site, efficient data recording equipment, and a data processing center, resulting in a high cost of the road truth system. Without the road truth system, the prior art cannot accurately test the accuracy of on-board sensors. To this end, the present invention provides a method for determining the accuracy of on-board sensors that can still accurately determine the accuracy of sensors in the absence of a road truth system. The cost of determining sensor accuracy is low and the accuracy is high.

[0022] A specific embodiment of the present invention, as Figure 1 As shown, a method for determining the accuracy of a vehicle-mounted sensor is disclosed, comprising: S101, obtaining measured motion data of a target moving object collected by a sensor mounted on a vehicle to be measured.

[0023] In an embodiment of the present invention, the on-board sensor to be tested refers to the sensor carried by the test vehicle that needs to be tested for accuracy. It can be a visual sensor, a lidar sensor, etc., which is generally used for autonomous vehicles and can also be used for non-autonomous vehicles. The on-board sensor to be tested carried by the test vehicle can be one or more, and can be sensors of the same type or different types. The target moving object refers to other vehicles around the vehicle when the simulated vehicle is driving on the road. The target moving object can be a vehicle or other moving object. The present invention does not limit this. Among them, the relative position of the target moving object and the test vehicle can be set according to the actual scenario. Specifically, multiple practical use cases can be set to simulate scenarios where the test vehicle and the target moving object are in different relative positions, thereby obtaining more comprehensive motion data. In an embodiment of the present invention, the measured motion data refers to the motion data of the target moving object collected by the on-board sensor to be tested on the test vehicle. According to the type of the on-board sensor to be tested, the type of the measured motion data is also different. Specifically, it can include but is not limited to data such as distance, speed, acceleration, angular velocity, etc.

[0024] S102 , obtaining real motion data of the target moving object, wherein the real motion data is used to represent the motion state of the target moving object, and an error is within a preset error range.

[0025] In an embodiment of the present invention, real motion data refers to the precise motion data of the target moving object collected by other means. The precise motion data can represent the real motion state of the target moving object, and the error of the motion state of the target moving object represented by the real motion data is within an acceptable range. Specifically, a calibrated motion data acquisition module can be used to collect the real motion data of the target moving object.

[0026] S103 : determining an accuracy threshold of the vehicle-mounted sensor to be tested based on the performance requirements of the vehicle-mounted sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data.

[0027] In the embodiments of the present invention, different sensor performance requirements, different data categories, and different numerical ranges all result in different sensor accuracy requirements. Therefore, when determining the sensor accuracy threshold, the present invention needs to determine the corresponding sensor accuracy threshold based on the performance requirements of the different on-board sensors to be tested, the category of the measured motion data, and the numerical range of the measured motion data, so as to ensure that each sensor can have a corresponding relatively accurate accuracy standard, thereby ensuring the accuracy of the sensor accuracy determination. The specific method for determining the accuracy threshold is described in detail later in the present invention.

[0028] S104 , calculating the difference between the measured motion data and the actual motion data, and determining the accuracy of the vehicle-mounted sensor to be measured based on a relationship between the difference and an accuracy threshold.

[0029] In an embodiment of the present invention, after determining the accuracy threshold of the vehicle-mounted sensor to be tested, the difference between the measured motion data and the actual motion data can be calculated, and the difference can be compared with the accuracy threshold. The accuracy of the vehicle-mounted sensor to be tested can be determined based on the comparison result. The specific accuracy determination method will be described in detail later in the present invention.

[0030] The method for determining the accuracy of an on-board sensor provided by the present invention obtains the real motion data of the target moving object and the measured motion data of the target moving object collected by the on-board sensor to be tested, without the need to build a road truth value system, thus saving costs. The method also determines corresponding sensor accuracy thresholds based on different sensor performance requirements, different types of measured motion data, and different numerical intervals. The corresponding sensor accuracy thresholds are determined according to different requirements and different motion scenarios, and the division of the sensor accuracy thresholds is more precise, ensuring the accuracy of the determination of the accuracy of the sensor to be tested. The method then calculates the difference between the real motion data and the measured motion data, compares the difference with the sensor accuracy threshold, and determines the accuracy of the sensor. In the absence of a road truth value system, the accuracy of the sensor can still be determined relatively accurately, and the cost of determining the sensor accuracy is low and the accuracy is high.

[0031] In some possible implementations of the present invention, obtaining measured motion data of a target moving object collected by a sensor mounted on a vehicle to be measured includes: Obtain measured motion data of the target mobile object collected by the on-board sensor to be tested when the target mobile object is in different motion states, wherein the measured motion data includes the longitudinal distance between the target mobile object and the on-board sensor to be tested, the lateral distance between the target mobile object and the on-board sensor to be tested, the longitudinal relative speed between the target mobile object and the on-board sensor to be tested, the lateral relative speed between the target mobile object and the on-board sensor to be tested, and the heading angle of the target mobile object.

[0032] In an embodiment of the present invention, in order to realistically simulate a driving scenario of a vehicle on a road, when the on-board sensor to be tested collects the measured motion data of the target moving object, both the on-board sensor to be tested and the target moving object are in motion. There are multiple on-board sensors to be tested, so the types of measured motion data collected are also multiple. At the same time, in order to ensure the diversity of the collected data, it is also necessary to put the on-board sensor to be tested and the target moving object in different motion states. Specifically, the different motion states include different relative positions, different relative speeds, and different relative heading angles of the vehicle equipped with the on-board sensor to be tested and the target moving object, such as the test vehicle in front of, behind, to the left, or to the right of the target moving object, the test vehicle accelerating to overtake the target moving object, the target moving object accelerating to overtake the test vehicle, and other scenarios. In these multiple scenarios, the longitudinal distance between the target moving object and the on-board sensor to be tested, the lateral distance between the target moving object and the on-board sensor to be tested, the longitudinal relative speed between the target moving object and the on-board sensor to be tested, the lateral relative speed between the target moving object and the on-board sensor to be tested, and the heading angle of the target moving object are collected by multiple on-board sensors to be tested.

[0033] Furthermore, to facilitate data processing, the collected measured motion data can be represented in the form of a data set, which includes 5 rows and n columns of data, where the first row is the longitudinal distance between the target moving object and the vehicle-mounted sensor to be measured, the second row is the lateral distance between the target moving object and the vehicle-mounted sensor to be measured, the third row is the longitudinal relative speed between the target moving object and the vehicle-mounted sensor to be measured, the fourth row is the lateral relative speed between the target moving object and the vehicle-mounted sensor to be measured, and the fifth row is the heading angle of the target moving object, and the n columns correspond to different data collection times.

[0034] The embodiment of the present invention ensures the comprehensiveness of the acquisition of the measured motion data by acquiring the measured motion data of the target moving object collected by the on-board sensor to be tested when the target moving object is in different motion states, and can determine the accuracy of multiple sensors.

[0035] In some possible embodiments of the present invention, obtaining real motion data of a target moving object includes: While acquiring the measured motion data, a calibrated motion data acquisition module installed on the same vehicle as the on-board sensor to be measured is used to collect the real motion data of the target moving object.

[0036] In an embodiment of the present invention, the real motion data of the target moving object can be acquired using a calibrated motion data acquisition module (such as a calibrated inertial navigation module) installed on the same vehicle as the onboard sensor to be tested. Furthermore, the calibrated motion data acquisition module and the onboard sensor to be tested should simultaneously acquire the real motion data and measured motion data of the target moving object. The real motion data and the measured motion data should correspond one-to-one. That is, for the same data of the target moving object, the onboard sensor to be tested collects measured motion data, while the calibrated motion data acquisition module collects real motion data. As in the above embodiment, to facilitate data processing, the real motion data can be represented as a data set, and the specific representation should be consistent with the representation of the measured motion data data set.

[0037] The embodiment of the present invention collects the real motion data of the target moving object through a calibrated motion data collection module while collecting the measured motion data of the target moving object, eliminating the need to build a road truth system and saving costs.

[0038] In some possible embodiments of the present invention, Figure 2 As shown, the accuracy threshold of the vehicle-mounted sensor to be tested is determined based on the performance requirements of the vehicle-mounted sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data, including: S201, determining a first accuracy threshold interval based on performance requirements of the vehicle-mounted sensor to be tested; S202, determining a second accuracy threshold interval based on the category of the measured motion data; S203, determining a third accuracy threshold interval based on the numerical interval of the measured motion data; S204 : Determine an accuracy threshold of the vehicle-mounted sensor to be tested based on the first accuracy threshold interval, the second accuracy threshold interval, and the third accuracy threshold interval.

[0039] In an embodiment of the present invention, when determining the accuracy threshold of a vehicle-mounted sensor to be tested, the accuracy requirements of the vehicle-mounted sensor to be tested can be first determined based on the accuracy constraints of each sensor. The sensor accuracy constraints include the performance requirements of the vehicle-mounted sensor to be tested, the type of measured motion data, and the numerical range of the measured motion data. Specifically, a first accuracy threshold range is determined for each vehicle-mounted sensor to be tested based on the performance requirements of the vehicle-mounted sensor to be tested. For example, for a vehicle-mounted sensor to be tested with a higher sensor performance requirement, a smaller accuracy threshold is determined based on a pre-set accuracy threshold determination rule. For a vehicle-mounted sensor to be tested with a lower sensor performance requirement, a larger accuracy threshold can be determined. This accuracy threshold can be a single value or a range of values. A second accuracy threshold range is determined based on the type of measured motion data. For example, a higher accuracy threshold can be determined for a visual sensor or a lidar sensor, while a lower accuracy threshold can be determined for an acoustic sensor. A third accuracy threshold range is determined based on the numerical range of the measured motion data. For example, for a distance sensor, one accuracy threshold can be set within 0-10 meters, and another accuracy threshold can be set within 10-20 meters. This satisfies the sensor accuracy requirements at different distances. For example, the greater the distance, the lower the accuracy requirement and the larger the accuracy threshold. After determining the accuracy threshold of each sensor based on different sensor accuracy constraints, the accuracy threshold of the on-board sensor to be tested is obtained. The accuracy threshold of the on-board sensor to be tested should include accuracy thresholds corresponding to various accuracy requirements, various sensor types, and various data intervals. To facilitate data processing, the accuracy thresholds of each sensor can be represented in the form of a set. Specifically, for a sensor accuracy constraint, a set of accuracy thresholds is constructed to represent the accuracy thresholds corresponding to different situations under the sensor accuracy constraint. Specifically, after constructing the set of accuracy thresholds, for the sensor whose accuracy needs to be judged, a binary search and match can be performed in the set based on its accuracy requirements, the type of motion data collected, and the numerical interval in which the motion data collected is located to obtain the corresponding accuracy threshold.

[0040] The embodiment of the present invention determines corresponding sensor accuracy thresholds according to different sensor accuracy restriction conditions, which facilitates hierarchical representation of sensor accuracy thresholds and helps to accurately determine the accuracy of the sensor.

[0041] In some possible embodiments of the present invention, before calculating the difference between the measured motion data and the actual motion data, the following steps are included: The measured motion data and the real motion data are time-aligned based on the acquisition moments of the measured motion data and the real motion data.

[0042] In an embodiment of the present invention, in order to ensure that there is no data mismatch when comparing the measured motion data collected by the on-board sensor to be tested and the real motion data collected by the calibrated motion data acquisition module, it is necessary to time-align the measured motion data and the real motion data. Specifically, the timestamps of each measured motion data and each real motion data can be obtained respectively, and the measured motion data and the real motion data with the same timestamp are compared as a group of data to ensure the accuracy of the data comparison. Optionally, a timing tool can also be used to time the collected data when the on-board sensor to be tested collects the measured motion data and the calibrated motion data acquisition module collects the real motion data, and then the measured motion data set and the real motion data set are constructed according to the timing, and processing is performed based on the data set.

[0043] In some possible embodiments of the present invention, Figure 3 As shown, the difference between the measured motion data and the actual motion data is calculated, and the accuracy of the vehicle sensor to be tested is determined based on the relationship between the difference and the accuracy threshold, including: S301, calculating the difference between each measured motion data and the corresponding real motion data, and calculating the relationship between each difference and the accuracy threshold; S302 : Determine the accuracy of the vehicle-mounted sensor to be tested based on the number of differences that are smaller than an accuracy threshold.

[0044] In an embodiment of the present invention, when determining the accuracy of the on-board sensor to be tested, the difference between each set of measured motion data and the corresponding real motion data can be calculated. Specifically, for the measured motion data and the real motion data with the same timestamp, the absolute value of the difference is calculated, and then the absolute value of the difference is compared with the corresponding accuracy threshold. The measurement accuracy data corresponding to the absolute value of the difference less than the accuracy threshold is regarded as qualified measurement accuracy data. Then, the number of qualified measured motion data collected by each sensor is counted, and the accuracy of the on-board sensor to be tested is determined based on this number. For example, if the number of qualified measured motion data collected accounts for more than 95% of all measured motion data, it means that the accuracy of the on-board sensor to be tested meets the requirements. Furthermore, to facilitate data processing, data operations can be performed based on the measured motion data set and the real motion data set constructed in the above embodiment. For example, for each set of data in the measured motion data set A and the real motion data set B, the corresponding accuracy threshold is determined, and an accuracy threshold data set C is constructed. Then, a difference operation is performed between data set A and data set B, and the operation result is compared with data set C to determine the accuracy of the on-board sensor to be tested. Specifically, the accuracy of the on-board sensor under test can be determined by subtracting the absolute value of data set A minus the absolute value of data set B from data set C and determining the proportion of negative numbers in the result. The above method for calculating the accuracy of the on-board sensor under test is only one possible implementation of the present invention and is not intended to limit the present invention.

[0045] The present invention judges the accuracy of the vehicle-mounted sensor to be tested by comparing the measured motion data with the real motion data and combining the accuracy threshold determined in the above embodiments. It has low cost, low difficulty and high accuracy.

[0046] In order to better implement the sensor accuracy determination method in the embodiment of the present invention, based on the sensor accuracy determination method, correspondingly, Figure 4 As shown, an embodiment of the present invention further provides a sensor accuracy determination system, and the sensor accuracy determination system 400 includes: The sensor to be tested 401 is used to collect the measured motion data of the target moving object and send the measured motion data to the data analysis module; The calibrated motion data acquisition module 402 is used to obtain the real motion data of the target moving object and send the real motion data to the data analysis module; The data analysis module 403 is used to determine the accuracy threshold of the vehicle-mounted sensor to be tested based on the performance requirements of the vehicle-mounted sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data; calculate the difference between the measured motion data and the actual motion data, and determine the accuracy of the vehicle-mounted sensor to be tested based on the relationship between the difference and the accuracy threshold.

[0047] In an embodiment of the present invention, the vehicle-mounted sensor to be tested can be any sensor mounted on the vehicle, such as a lidar sensor, a visual sensor, etc. The data of these sensors can be transmitted through the CAN bus. The calibrated motion data acquisition module can adopt an inertial navigation module with higher precision on the market to achieve accurate collection of the real motion data of the target moving object. The data analysis module can adopt host computer software to achieve data analysis.

[0048] The sensor accuracy determination system 400 provided in the above embodiment can implement the technical solution described in the above sensor accuracy determination method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above sensor accuracy determination method embodiment, which will not be repeated here.

[0049] like Figure 5 As shown, the present invention also provides a vehicle 500. The vehicle 500 includes a processor 501, a memory 502 and a sensor 503 to be tested. Figure 5 Only some of the components of vehicle 500 are shown, but it should be understood that implementation of all of the shown components is not a requirement, and greater or fewer components may alternatively be implemented.

[0050] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 502 , such as the sensor accuracy determination method of the present invention.

[0051] In some embodiments, the processor 501 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 501 may be local or remote. In some embodiments, the processor 501 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, multiple clouds, or any combination thereof.

[0052] In some embodiments, the memory 502 may be an internal storage unit of the vehicle 500, such as a hard drive or memory of the vehicle 500. In other embodiments, the memory 502 may be an external storage device of the vehicle 500, such as a plug-in hard drive, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped in the vehicle 500.

[0053] Furthermore, the memory 502 may include both an internal storage unit of the vehicle 500 and an external storage device. The memory 502 is used to store application software installed in the vehicle 500 and various data.

[0054] In some embodiments, the sensor 503 to be tested may be a laser radar sensor, a visual sensor, etc. The sensor 503 to be tested is used to collect motion data of a target moving object near the test vehicle. The components 501-503 of the vehicle 500 communicate with each other via a system bus.

[0055] In some embodiments, when the processor 501 executes the sensor accuracy determination program in the memory 502, the following steps may be implemented: Obtaining the measured motion data of the target moving object collected by the onboard sensor of the vehicle to be tested, and obtaining the real motion data of the target moving object; Determining an accuracy threshold of the on-board sensor to be tested based on the performance requirements of the on-board sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data; The difference between the measured motion data and the actual motion data is calculated, and the accuracy of the vehicle sensor to be tested is determined based on the relationship between the difference and the accuracy threshold.

[0056] It should be understood that, when the processor 501 executes the sensor accuracy determination program in the memory 502 , in addition to the above functions, it can also implement other functions. For details, please refer to the description of the corresponding method embodiment above.

[0057] Furthermore, the embodiment of the present invention does not specifically limit the type of the vehicle 500 mentioned. It can be an electric vehicle, a hybrid vehicle, a commercial vehicle, a passenger vehicle, a special vehicle, etc. It can be an unmanned vehicle, a manned vehicle, etc., and the present invention does not impose any restrictions on this.

[0058] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions in the sensor accuracy determination method provided in the above-mentioned method embodiments.

[0059] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0060] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for determining the accuracy of a vehicle-mounted sensor, characterized in that: include: Obtaining the measured motion data of the target moving object collected by the onboard sensor of the vehicle to be tested; Acquiring real motion data of the target moving object, wherein the real motion data is used to represent the motion state of the target moving object, and the error is within a preset error range; Determining an accuracy threshold of the onboard sensor to be tested based on the performance requirements of the onboard sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data; A difference between the measured motion data and the actual motion data is calculated, and the accuracy of the vehicle-mounted sensor to be tested is determined based on a magnitude relationship between the difference and the accuracy threshold.

2. The method for determining the accuracy of an on-vehicle sensor according to claim 1, wherein: The obtaining of the measured motion data of the target moving object collected by the onboard sensor to be measured includes: Obtaining measured motion data of a target mobile object collected by a vehicle-mounted sensor to be tested when the target mobile object is in different motion states, wherein the measured motion data includes a longitudinal distance between the target mobile object and the vehicle-mounted sensor to be tested, a lateral distance between the target mobile object and the vehicle-mounted sensor to be tested, a longitudinal relative speed between the target mobile object and the vehicle-mounted sensor to be tested, a lateral relative speed between the target mobile object and the vehicle-mounted sensor to be tested, and a heading angle of the target mobile object.

3. The method for determining the accuracy of an on-vehicle sensor according to claim 2, wherein: The different motion states include different relative positions, different relative speeds, and different relative heading angles between the vehicle carrying the vehicle-mounted sensor to be tested and the target moving object.

4. The method for determining the accuracy of an on-vehicle sensor according to claim 2, wherein: The obtaining of the real motion data of the target moving object includes: While acquiring the measured motion data, a calibrated motion data acquisition module installed on the same vehicle as the vehicle-mounted sensor to be measured is used to acquire the real motion data of the target moving object.

5. The method for determining the accuracy of an on-vehicle sensor according to claim 2, wherein: The determining the accuracy threshold of the on-board sensor to be tested based on the performance requirement of the on-board sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data includes: Determining a first accuracy threshold interval based on performance requirements of the vehicle-mounted sensor to be tested; determining a second accuracy threshold interval based on the category of the measured motion data; determining a third precision threshold interval based on the numerical interval of the measured motion data; The accuracy threshold of the vehicle-mounted sensor to be tested is determined based on the first accuracy threshold interval, the second accuracy threshold interval, and the third accuracy threshold interval.

6. The method for determining the accuracy of an on-vehicle sensor according to claim 1, wherein: Before calculating the difference between the measured motion data and the real motion data, the method includes: The measured motion data and the real motion data are time-aligned based on acquisition times of the measured motion data and the real motion data.

7. The method for determining the accuracy of an on-vehicle sensor according to claim 1, wherein: The calculating the difference between the measured motion data and the actual motion data, and determining the accuracy of the vehicle-mounted sensor to be tested based on a magnitude relationship between the difference and the accuracy threshold, includes: Calculating the difference between each of the measured motion data and the corresponding real motion data, and calculating the relationship between each difference and the accuracy threshold; The accuracy of the onboard sensor to be tested is determined based on the number of differences that are less than the accuracy threshold.

8. A vehicle-mounted sensor accuracy determination system, applicable to the vehicle-mounted sensor accuracy determination method according to any one of claims 1 to 7, comprising: The sensor to be tested is used to collect the measured motion data of the target moving object and send the measured motion data to the data analysis module; a calibrated motion data acquisition module, configured to acquire the real motion data of the target moving object and send the real motion data to the data analysis module; a data analysis module, configured to determine an accuracy threshold of the onboard sensor to be tested based on the performance requirements of the onboard sensor to be tested, the category of the measured motion data, and the numerical range of the measured motion data; A difference between the measured motion data and the actual motion data is calculated, and the accuracy of the vehicle-mounted sensor to be tested is determined based on a magnitude relationship between the difference and the accuracy threshold.

9. A vehicle, characterized in that: comprising a memory and a processor, wherein, The memory is used to store programs; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the sensor accuracy determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the sensor accuracy determination method according to any one of claims 1 to 7.

Images