CN116558469A - Distance error evaluation method, device, electronic equipment and storage medium - Google Patents
Distance error evaluation method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116558469A CN116558469A CN202310432165.5A CN202310432165A CN116558469A CN 116558469 A CN116558469 A CN 116558469A CN 202310432165 A CN202310432165 A CN 202310432165A CN 116558469 A CN116558469 A CN 116558469A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- sensor
- value
- distance
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 68
- 238000005259 measurement Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 27
- 230000008447 perception Effects 0.000 claims abstract description 26
- 230000001133 acceleration Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 11
- 230000001186 cumulative effect Effects 0.000 claims description 11
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000035484 reaction time Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
- G01B21/04—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness by measuring coordinates of points
- G01B21/042—Calibration or calibration artifacts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/16—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring distance of clearance between spaced objects
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a distance error evaluation method, a device, an electronic device and a storage medium, comprising the following steps: first data is received, the first data being a measurement between the vehicle and the perception object as measured by a sensor of the vehicle. A measured nominal value of the sensor in an ideal environment is obtained and a difference between the measured nominal value and the first data is obtained based on the first data. And acquiring a normal distribution curve of hardware failure rate corresponding to the ASIL grade of the vehicle. And acquiring a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold value, wherein the first threshold value is used for evaluating whether the measured value of the sensor is qualified or not. And evaluating the difference value, if the difference value exceeds a first threshold value, evaluating that the measured value of the sensor is qualified, otherwise, evaluating that the measured value is unqualified. The method limits and evaluates the perceived ranging error from the aspect of functional safety, enhances the ranging accuracy of the sensor and ensures the driving safety of the vehicle.
Description
Technical Field
The present invention relates to the field of automatic driving technologies, and in particular, to a distance error evaluation method, a device, an electronic apparatus, and a storage medium.
Background
Automatic driving (Self-driving), also known as unmanned, is a vehicle driving method implemented by a computer system. With the popularization of the automatic driving vehicle, the automatic driving vehicle can be used as a taxi or a public transport means, a passenger needs to input a destination when using the automatic driving vehicle, and the automatic driving vehicle generates a driving route based on the current position and the destination and drives according to the generated driving route. The road condition on the driving route is not invariable, and the driving state of other vehicles driving on the road is constantly changing, so that the distance between the surrounding vehicles and the automatic driving vehicle can be accurately judged in the driving process, the automatic driving vehicle can ensure to drive in a safety area, and traffic accidents caused by collision with other driving vehicles or obstacles are avoided, and injuries are caused to passengers and other people.
At present, although the conventional automatic driving vehicle can range the surrounding vehicles and the obstacles through a sensing system of the vehicle, the automatic driving vehicle can avoid other driving vehicles and the obstacles in time. However, the sensing system has a certain error in measuring the distance between vehicles, so that the automatic driving vehicle is easy to collide and rub with other vehicles or obstacles influencing the safety of the vehicles due to the instability of the sensing distance measurement error in the driving process, and traffic accidents are easy to be caused in the driving process in the planned path.
Therefore, the conventional automatic driving vehicle is more easily affected by the sensing distance measurement error in the sensing distance measurement process, so that the accuracy of the sensing distance measurement is reduced, and the safe driving of the automatic driving vehicle is further affected.
Disclosure of Invention
The invention provides a distance error evaluation method, a device, electronic equipment and a storage medium, which are used for solving the defect of poor accuracy of sensing distance measurement in the prior art, realizing stable vehicle sensing distance measurement and ensuring the running safety of an automatic driving vehicle.
The invention provides a distance error evaluation method, which comprises the following steps:
receiving first data, wherein the first data is a measured value between a vehicle and a perception object, which is measured by a sensor of the vehicle;
acquiring a measurement nominal value of the sensor in an ideal environment, and acquiring a difference value between the measurement nominal value and the first data based on the first data;
acquiring a normal distribution curve of hardware failure rate corresponding to the ASIL grade of the vehicle;
acquiring a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold value, wherein the first threshold value is used for evaluating whether the measured value of the sensor is qualified or not;
and evaluating the difference value, if the difference value exceeds the first threshold value, evaluating that the measured value of the sensor is qualified, otherwise, evaluating that the measured value is unqualified.
According to the distance error evaluation method provided by the invention, the receiving of the first data comprises the following steps:
receiving the lateral velocity and the lateral acceleration of the perception object;
a lateral safety distance between the vehicle and the perceived object is calculated based on the lateral velocity and lateral acceleration.
According to the distance error evaluation method provided by the invention, the receiving of the first data further comprises the following steps:
receiving the longitudinal speed and the longitudinal acceleration of the perception object;
a longitudinal safety distance between the vehicle and the perceived object is calculated based on the longitudinal speed and the longitudinal acceleration.
According to the distance error evaluation method provided by the invention, the method further comprises the following steps:
acquiring a first boundary value according to the first data, wherein the first boundary value is a transverse safety distance and a longitudinal safety distance between the vehicle and the perception object;
and acquiring a first driving area of the vehicle based on the transverse safety distance and the longitudinal safety distance, wherein the first driving area is a safety area for normal driving of the vehicle in the first boundary value.
According to the distance error evaluation method provided by the invention, the method further comprises the following steps:
when no sensing object exists in the sensing range of the sensor, a second driving area is acquired, wherein the second driving area is a safe driving area without the sensing object;
wherein the second travel region is not limited by the first boundary value.
According to the distance error evaluation method provided by the invention, the obtaining of the normal distribution curve of the hardware failure rate corresponding to the ASIL grade of the vehicle comprises the following steps:
acquiring a hardware failure rate corresponding to an ASIL grade of the vehicle;
determining a confidence interval of the hardware failure rate according to the ASIL grade of the vehicle;
and constructing a normal distribution curve of the hardware failure rate in the confidence interval.
According to the distance error evaluation method provided by the invention, the data relationship between the maximum allowable error of the sensor and the hardware failure rate is obtained based on the normal distribution curve so as to determine a first threshold value, and the method comprises the following steps:
acquiring a boundary distance between the first boundary value and the vehicle;
acquiring the probability of the error of which the first data is larger than the boundary distance from the normal distribution curve, and carrying out inverse cumulative distribution operation on the basis of the probability to acquire an inverse cumulative distribution value;
the ratio between the boundary distance and the inverse cumulative distribution value is taken as a first threshold value.
According to the distance error evaluation method provided by the invention, the ASIL class is divided into a plurality of ASIL classes, and each ASIL class has corresponding hardware failure rate.
The invention also provides a distance error evaluation device, which comprises:
the data receiving module is used for receiving first data, wherein the first data is a measured value between a vehicle and a perception object, and the measured value is measured by a sensor of the vehicle;
a first acquisition module for acquiring a measurement nominal value of the sensor in an ideal environment and acquiring a difference value between the measurement nominal value and the first data based on the first data;
the second acquisition module is used for acquiring a normal distribution curve of hardware failure rate corresponding to the ASIL grade of the vehicle;
the determining module is used for acquiring a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve so as to determine a first threshold value, wherein the first threshold value is used for evaluating whether the measured value of the sensor is qualified or not;
and the evaluation module is used for evaluating the difference value, evaluating whether the measured value of the sensor is qualified or not if the difference value exceeds the first threshold value, otherwise, evaluating whether the measured value of the sensor is unqualified.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes any one of the distance error evaluation methods when executing the program.
The present invention also provides a computer storage medium storing a computer program which, when executed by a processor, implements any one of the above-described distance error evaluation methods.
According to the distance error evaluation method, the device, the electronic equipment and the storage medium, the current distance between the vehicle and the sensor sensing object is obtained by obtaining the sensor data on the vehicle, and the difference between the measured distance of the sensor and the measured nominal value is obtained by comparing the current distance between the vehicle and the sensing object with the measured nominal value of the sensor in an ideal environment, wherein the difference is the error generated when the sensor measures the distance. And then determining the hardware failure rate of the vehicle according to the ASIL grade of the vehicle, and constructing a normal distribution curve according to the hardware failure rate of the vehicle to acquire a data relationship between the hardware failure rate and the maximum allowable error of the sensor ranging, so as to determine a threshold range for evaluating the reliability of the sensor ranging. And finally, evaluating the current error generated during the ranging of the vehicle sensor according to the maximum allowable error of the ranging of the sensor, if the current error does not exceed the threshold range of the maximum allowable error of the ranging of the sensor, evaluating the measurement value of the sensor to be qualified, and if the current error exceeds the threshold range of the maximum allowable error of the ranging of the sensor, evaluating the measurement value to be unqualified. According to the method, the real-time error generated during ranging of the vehicle sensor is checked to generate the corresponding evaluation result of the vehicle sensing system, the ranging error of the sensor is limited and evaluated from the aspect of functional safety, the ranging accuracy of the sensor is improved to a certain extent, potential safety hazards caused by inaccurate ranging of the vehicle sensor are avoided, and the driving safety of the vehicle is guaranteed.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a distance error evaluation method provided by the invention;
FIG. 2 is a second flow chart of the distance error evaluation method according to the present invention;
FIG. 3 is a third flow chart of the distance error evaluation method according to the present invention;
FIG. 4 is a schematic flow chart of a distance error evaluation method according to the present invention;
FIG. 5 is a flowchart of a distance error evaluation method according to the present invention;
FIG. 6 is a flowchart of a distance error evaluation method according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a normal distribution of a distance error evaluation method according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a distance error evaluation device according to the present invention;
fig. 9 is a schematic structural diagram of an electronic device provided by the present invention.
Reference numerals:
810: a data receiving module; 820: a first acquisition module; 830: a second acquisition module; 840: a determining module; 850: an evaluation module; 910: a processor; 920: a communication interface; 930: a memory; 940: a communication bus.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The distance error evaluation method, apparatus, electronic device, and storage medium of the present invention are described below with reference to fig. 1 to 9.
As shown in fig. 1, in one embodiment, a distance error evaluation method includes the steps of:
step S110, receiving first data, where the first data is a measured value between the vehicle and the perception object, which is measured by a sensor of the vehicle.
The sensing object is other vehicles or road users or obstacles outside the vehicle, and the first data is a sensor measurement distance between the vehicle detected by the vehicle-mounted sensor and the sensing object.
Specifically, the vehicle server receives distance data measured by the on-board sensor sensing other targets in the surroundings of the autonomous vehicle, i.e. the measured values of the sensor.
Step S120, obtaining a measurement nominal value of the sensor in an ideal environment, and obtaining a difference between the measurement nominal value and the first data based on the first data.
The measured nominal value is sensor measurement data of the vehicle in an ideal environment, is used for calibrating the sensor measurement data of the vehicle in the actual running process so as to obtain the error of the ranging of the sensor in the actual running process of the vehicle, namely, the sensor is installed under the condition that weather, illumination, temperature and humidity are normal, and finally, the measured nominal value is taken as the standard of the measuring capacity of the sensor based on the statistical value of the measured result, and can be considered as the correct data of the sensor measurement. The difference is the error generated by the measured value of the sensor in practical application.
Specifically, the vehicle server obtains a real-time error generated when the vehicle-mounted sensor measures the distance according to the data measured by the vehicle-mounted sensor obtained in step S110 and the measurement nominal value in the ideal environment.
Step S130, obtaining a normal distribution curve of hardware failure rate corresponding to the ASIL level of the vehicle.
The ASIL (Automotive Safety Integrity Level) grade refers to the automobile safety integrity grade, and is a risk classification system defined by the ISO26262 standard and used for functional safety of road vehicles. The standard defines functional safety as "hazards due to faulty behaviour of electrical or electronic systems, without unreasonable risks". ASIL determines safety requirements based on the likelihood and acceptability of damage to automotive parts to comply with ISO 26262. And ISO 26262-a, B, C and D identified four ASILs, ASILA representing the lowest level and ASIL D representing the highest automotive hazard level. The hardware failure rate, namely PMHF (Probabilistic Metrics for Hardware Failure), can be used as a functional safety hardware measurement corresponding to different grades of ASIL, the unit is FIT (Failure In Time), and the corresponding ASIL grades have corresponding hardware failure rates.
Specifically, the vehicle server constructs a hardware failure rate corresponding to the vehicle ASIL grade according to the vehicle ASIL grade, and constructs a corresponding hardware failure rate normal distribution curve through the hardware failure rate.
Step S140, obtaining a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve, so as to determine a first threshold value, where the first threshold value is used to evaluate whether the measured value of the sensor is qualified.
Further, the acquiring, based on the normal distribution curve, a data relationship between a maximum allowable error of the sensor and a hardware failure rate to determine a first threshold includes:
and acquiring the boundary distance between the first boundary value and the vehicle.
And acquiring the probability of the error of which the first data is larger than the boundary distance from the normal distribution curve, and carrying out inverse cumulative distribution operation on the basis of the probability to acquire an inverse cumulative distribution value.
The ratio between the boundary distance and the inverse cumulative distribution value is taken as a first threshold value.
Specifically, the vehicle server obtains a data relationship between the maximum allowable error of the sensor ranging and the hardware failure rate according to the normal hardware failure rate distribution curve constructed in the step S130, and further determines a threshold range corresponding to the maximum allowable error of the sensor ranging, that is, a first threshold, according to the data relationship, where the threshold range is used to evaluate the error generated by the sensor ranging in the step S120.
The data relationship between the maximum allowable error and the hardware failure rate is as follows:
in sigma min For the maximum allowable error threshold of the sensing range (i.e., the first data), AL is the distance between the safety boundary (i.e., the first boundary value) and the host vehicle, F () is the Inverse Cumulative Distribution Function (ICDF), p is the probability that the sensing range is greater than the error of AL, and p is derived from the hardware failure rate normal distribution curve.
And S150, evaluating the difference value, if the difference value exceeds a first threshold value, evaluating that the measured value of the sensor is qualified, otherwise, evaluating that the measured value is unqualified.
Specifically, the vehicle server evaluates the real-time error generated during the ranging of the sensor obtained in step S120 according to the threshold range corresponding to the maximum allowable error of the ranging of the sensor obtained in step S140, and if the real-time error between other vehicles or road users or obstacles and the vehicle where the sensor is located does not exceed the threshold range corresponding to the maximum allowable error of the ranging of the sensor, the measured value of the corresponding sensor is evaluated to be qualified, and the evaluation of the measured value of the sensor is qualified to indicate that the ranging of the sensor is relatively accurate. If the real-time error between other vehicles or road users or obstacles and the vehicles where the sensors are located exceeds the threshold range corresponding to the maximum allowable error of the ranging of the sensors, the measured value of the corresponding sensor is evaluated to be unqualified, and the unqualified evaluation of the measured value of the sensor indicates that the ranging of the sensor is inaccurate, potential safety hazards exist, and the sensor is easy to collide with a sensing object of the sensor.
According to the distance error evaluation method, the current distance between the vehicle and the sensor sensing object is obtained by obtaining the sensor data on the vehicle, and the difference between the measured distance of the sensor and the measured nominal value is obtained by comparing the current distance between the vehicle and the sensing object with the measured nominal value of the sensor in an ideal environment, wherein the difference is the error generated when the sensor measures the distance. And then determining the hardware failure rate of the vehicle according to the ASIL grade of the vehicle, and constructing a normal distribution curve according to the hardware failure rate of the vehicle to acquire a data relationship between the hardware failure rate and the maximum allowable error of the sensor ranging, so as to determine a threshold range for evaluating the reliability of the sensor ranging. And finally, evaluating the current error generated during the ranging of the vehicle sensor according to the maximum allowable error of the ranging of the sensor, if the current error does not exceed the threshold range of the maximum allowable error of the ranging of the sensor, evaluating the measurement value of the sensor to be qualified, and if the current error exceeds the threshold range of the maximum allowable error of the ranging of the sensor, evaluating the measurement value to be unqualified. According to the method, the real-time error generated during ranging of the vehicle sensor is checked to generate the corresponding evaluation result of the vehicle sensing system, the ranging error of the sensor is limited and evaluated from the aspect of functional safety, the ranging accuracy of the sensor is improved to a certain extent, potential safety hazards caused by inaccurate ranging of the vehicle sensor are avoided, and the driving safety of the vehicle is guaranteed.
As shown in fig. 2, in one embodiment, the distance error evaluation method provided by the present invention receives first data, and includes the following steps:
step S112, receiving the lateral velocity and the lateral acceleration of the perception object.
Specifically, the vehicle server receives the lateral velocity and lateral acceleration of its perceived object via the sensor.
Step S114, calculating a lateral safety distance between the vehicle and the perception object based on the lateral velocity and the lateral acceleration.
Specifically, the vehicle server obtains the lateral safety distance between the perceived object and the autonomous vehicle by calculating the lateral speed and the lateral acceleration of the perceived object by the sensor acquired in step S112.
As shown in fig. 3, in one embodiment, the distance error evaluation method provided by the present invention receives first data, and includes the following steps:
in step S116, the longitudinal velocity and longitudinal acceleration of the perceived object are received.
Specifically, the vehicle server receives the longitudinal speed and longitudinal acceleration of its perceived object via the sensor.
Step S118, calculating a longitudinal safety distance between the vehicle and the perception object based on the longitudinal speed and the longitudinal acceleration.
Specifically, the vehicle server obtains the longitudinal safe distance between the perceived object and the automatic driving vehicle by calculating the longitudinal speed and the longitudinal acceleration of the perceived object of the sensor acquired in step S116.
As shown in fig. 4, in one embodiment, the distance error evaluation method provided by the present invention further includes the following steps:
in step S410, a first boundary value is obtained according to the first data, where the first boundary value is a lateral safety distance and a longitudinal safety distance between the vehicle and the perception object.
Specifically, the vehicle server obtains a lateral safety distance and a longitudinal safety distance between the automatic driving vehicle and the sensor perception object according to the measurement data of the vehicle sensor.
In step S420, a first driving area of the vehicle is acquired based on the lateral safety distance and the longitudinal safety distance, and the first driving area is a safety area for normal driving of the vehicle within a first boundary value.
The first driving area is a safe driving area surrounded by a transverse safe distance and a longitudinal safe distance between the vehicle and the sensor sensing object, namely the vehicle cannot rub or collide with the sensor sensing object in the area, and the vehicle cannot rub or collide with the sensor sensing object beyond the area.
Specifically, the vehicle server determines a safe area in which the vehicle can normally travel according to the lateral safe distance and the longitudinal safe distance acquired in step S410.
In step S430, when there is no sensing object in the sensing range of the vehicle sensor, a second driving area is acquired, and the second driving area is a safe driving area without sensing object.
Specifically, when there is no sensing object in the sensing range of the vehicle sensor, the vehicle server obtains a driving area different from the driving area in step S420, in which no other vehicle or obstacle affects the driving of the vehicle, i.e. there is no risk of collision or friction between the vehicle and other vehicle or obstacle, and the vehicle is not limited by the first boundary value.
As shown in fig. 5, in one embodiment, the distance error evaluation method provided by the present invention obtains a normal distribution curve of hardware failure rate corresponding to an ASIL level of the vehicle, and includes the following steps:
step S510, obtaining a hardware failure rate corresponding to the ASIL level of the vehicle.
Step S520, determining a confidence interval of the hardware failure rate according to the ASIL level of the vehicle.
The hardware failure rates corresponding to different ASIL grades have corresponding confidence intervals in a normal distribution curve.
Specifically, the vehicle server determines a confidence interval for the failure rate of the hardware according to the ASIL level of the vehicle.
Step S530, a normal distribution curve of hardware failure rate is constructed in the confidence interval.
Specifically, the vehicle server constructs and acquires a hardware failure rate normal distribution curve within the confidence interval determined in step S520.
In a specific embodiment, the present invention provides a distance error evaluation method, as shown in fig. 6, where an on-board server of an autonomous vehicle receives sensor data measured by sensing a surrounding environment by an autonomous vehicle sensor, and then obtains status information of other targets in a safe driving area by calculation according to the received sensor data, where the other targets include other vehicles in the surrounding environment of the autonomous vehicle or road users or obstacles affecting normal driving of the autonomous vehicle. The vehicle-mounted server determines the boundary value of the safe driving area according to the sensor data, determines the confidence interval of the distance between other vehicles or road users or obstacles in the surrounding environment of the automatic driving vehicle and the automatic driving vehicle according to the functional safety level (ASIL level) and the corresponding hardware failure rate (PMHF), and then determines the maximum allowable error threshold of the distance between the automatic driving vehicle and other surrounding targets acquired by the sensor according to the boundary value and the confidence interval of the safe driving area.
And finally, checking and evaluating the distance measurement error of the sensor according to the obtained maximum allowable error threshold value of the distance between the automatic driving vehicle and other surrounding targets by the vehicle server to generate an evaluation result of a corresponding vehicle sensing system, wherein if the distance measurement error of the sensor exceeds the maximum allowable error threshold value, the evaluation is unqualified, and if the distance measurement error of the sensor does not exceed the maximum allowable error threshold value, the evaluation is qualified.
In this embodiment, the safe driving area boundary of the autonomous vehicle includes a lateral safe distance and a longitudinal safe distance between the autonomous vehicle and other targets, and if there is no other target around the autonomous vehicle, there is no safe driving area boundary value. If the other target is in the driving direction of the own lane, the longitudinal safety distance (d min,lon ) Calculated by the following formula:
in the formula, v 0 For the longitudinal speed of an autonomous vehicle, t is the reaction time, a 0 For the longitudinal acceleration of an autonomous vehicle, (a) 0min,break ) For reasonable minimum longitudinal deceleration of autonomous vehicle, v 1 For other target longitudinal speeds, (a) 1max,break ) Maximum longitudinal deceleration reasonable for other objectives.
If the other target is in the adjacent lane, the lateral safety distance (d min,lat ) Calculated by the following formula:
wherein u is a preset transverse safety distance fluctuation value, v 2 For lateral acceleration of an autonomous vehicle, t is the reaction time, v 2t For the lateral speed of the autonomous vehicle at time t, (a) min,break ) For reasonable minimum lateral deceleration of an autonomous vehicle from other targets, v 3 For other target lateral velocity, v 3t The lateral speed of the vehicle is automatically driven for time t.
According to ISO26262:2018-5, the hardware failure rate (PMHF) value corresponding to the ASIL class is: ASILD 10FIT, ASILC 100FIT, ASILB 100FIT, and confidence interval is obtained according to hardware failure rate (PMHF) value. The error distribution of the sensor ranging follows the normal distribution, and the relation between the hardware failure rate (PMHF) value and the sensor ranging error can be obtained. Taking the asid scale as an example, and referring to fig. 7, sigma represents the standard deviation, mu represents the mathematical expectation, and percentage represents the mathematical probability distribution, that is, the reliability of the sensor measurement result, the sensor measurement error does not exceed ±0.2m at 95% reliability, and the sensor measurement error does not exceed ±0.7m at 99.999999% reliability. The confidence interval corresponding to 10FIT is 99.999999%, and is 5.73 σ according to a normal distribution formula. Then, the maximum allowable error threshold sigma of the sensing range min The calculation formula of (2) is as follows:
where 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 of an error greater than AL at the sensing distance.
In addition, sigma min The method can also be used as the functional safety requirement for the sensor ranging error, in the evaluation of the sensing ranging, the evaluation result is obtained based on repeated experiments, if the sensing ranging error exceeds sigma min If the sensing distance error is less than sigma, the evaluation result is unqualified min And if the evaluation result is qualified.
According to the distance error evaluation method, the vehicle kinematic information of the corresponding target area acquired by the target sensor is acquired based on the set sensing module, and the longitudinal and transverse safety distances of the vehicle are determined according to the vehicle kinematic information. A confidence interval is then determined based on the set ASIL level, and a maximum allowable error threshold for the longitudinal and lateral perceived distances (obtained by the sensor perception, as opposed to the safe distance) is determined from the confidence interval. And finally, checking and evaluating the sensing range errors of the automatic driving vehicle according to the maximum allowable error threshold value, and generating an evaluation result of a corresponding vehicle sensing system. The method provides a maximum allowable error range of sensing ranging from the aspect of functional safety, provides an evaluation thought for the design of an automatic driving vehicle sensing system, improves the working efficiency of vehicle functional safety verification to a certain extent, and enhances the accuracy of vehicle sensing ranging so as to ensure the driving safety of an automatic driving vehicle.
The distance error evaluation device provided by the invention is described below, and the distance error evaluation device described below and the distance error evaluation method described above can be referred to correspondingly to each other.
As shown in fig. 8, in one embodiment, a distance error evaluation apparatus includes a data receiving module 810, a first acquiring module 820, a second acquiring module 830, a determining module 840, and an evaluating module 850.
The data receiving module 810 is configured to receive first data, where the first data is a measured value between a vehicle and a perception object, which is measured by a sensor of the vehicle.
The first acquisition module 820 is configured to acquire a measured nominal value of the sensor in an ideal environment, and acquire a difference between the measured nominal value and the first data based on the first data.
The second obtaining module 830 is configured to obtain a normal distribution curve of hardware failure rate corresponding to the ASIL level of the vehicle.
The determining module 840 is configured to obtain a data relationship between a maximum allowable error of the sensor and a hardware failure rate based on the normal distribution curve, so as to determine a first threshold, where the first threshold is used to evaluate whether the measured value of the sensor is qualified.
The evaluation module 850 is configured to evaluate the difference, and if the difference exceeds the first threshold, evaluate the measured value of the sensor to be qualified, and otherwise evaluate the measured value to be unqualified.
In this embodiment, the distance error evaluation device provided by the present invention, the data receiving module is specifically configured to:
lateral velocity and lateral acceleration of the perceived object are received.
A lateral safe distance between the vehicle and the perception object is calculated based on the lateral velocity and lateral acceleration of the perception object.
In this embodiment, the distance error evaluation device provided by the present invention, the data receiving module is specifically further configured to:
longitudinal velocity and longitudinal acceleration of the perceived object are received.
A longitudinal safety distance between the vehicle and the perception object is calculated based on the longitudinal speed and the longitudinal acceleration of the perception object.
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.
The third acquisition module is used for acquiring a first boundary value according to the first data, wherein the first boundary value is a transverse safety distance and a longitudinal safety distance between the vehicle and the perception object.
The fourth acquisition module is used for acquiring a first driving area of the vehicle based on the transverse safety distance and the longitudinal safety distance, wherein the first driving area is a safety area for normal driving of the vehicle within a first boundary value.
The fifth acquisition module is used for acquiring a second driving area when no sensing object exists in the sensing range of the vehicle sensor, and the second driving area is a safe driving area without the sensing object.
In this embodiment, the distance error evaluation device provided by the present invention further includes a construction module, configured to:
acquiring a hardware failure rate corresponding to an ASIL grade of the vehicle;
and determining a confidence interval of the hardware failure rate according to the ASIL grade of the vehicle.
And constructing a normal distribution curve of hardware failure rate in the confidence interval.
Fig. 9 illustrates a physical schematic diagram of an electronic device, as shown in fig. 9, which may include: processor 910, communication interface (Communications Interface), memory 930, and communication bus 940, wherein processor 910, communication interface 920, and memory 930 communicate with each other via communication bus 940. Processor 910 may call logic instructions in memory 930 to perform a distance error assessment method comprising: receiving first data, wherein the first data is a measured value between a vehicle and a perception object, which is measured by a sensor of the vehicle; acquiring a measurement nominal value of the sensor in an ideal environment, and acquiring a difference value between the measurement nominal value and the first data based on the first data; acquiring a normal distribution curve of hardware failure rate corresponding to the ASIL grade of the vehicle; acquiring a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold value, wherein the first threshold value is used for evaluating whether the measured value of the sensor is qualified or not; and evaluating the difference value, if the difference value exceeds the first threshold value, evaluating that the measured value of the sensor is qualified, otherwise, evaluating that the measured value is unqualified.
Further, the logic instructions in the memory 930 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of executing the distance error evaluation method provided by the above methods, the method comprising: receiving first data, wherein the first data is a measured value between a vehicle and a perception object, which is measured by a sensor of the vehicle; acquiring a measurement nominal value of the sensor in an ideal environment, and acquiring a difference value between the measurement nominal value and the first data based on the first data; acquiring a normal distribution curve of hardware failure rate corresponding to the ASIL grade of the vehicle; acquiring a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold value, wherein the first threshold value is used for evaluating whether the measured value of the sensor is qualified or not; and evaluating the difference value, if the difference value exceeds the first threshold value, evaluating that the measured value of the sensor is qualified, otherwise, evaluating that the measured value is unqualified.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the distance error evaluation method provided by the above methods, the method comprising: receiving first data, wherein the first data is a measured value between a vehicle and a perception object, which is measured by a sensor of the vehicle; acquiring a measurement nominal value of the sensor in an ideal environment, and acquiring a difference value between the measurement nominal value and the first data based on the first data; acquiring a normal distribution curve of hardware failure rate corresponding to the ASIL grade of the vehicle; acquiring a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold value, wherein the first threshold value is used for evaluating whether the measured value of the sensor is qualified or not; and evaluating the difference value, if the difference value exceeds the first threshold value, evaluating that the measured value of the sensor is qualified, otherwise, evaluating that the measured value is unqualified.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for evaluating a distance error, the method comprising:
receiving first data, wherein the first data is a measured value between a vehicle and a perception object, which is measured by a sensor of the vehicle;
acquiring a measurement nominal value of the sensor in an ideal environment, and acquiring a difference value between the measurement nominal value and the first data based on the first data;
acquiring a normal distribution curve of hardware failure rate corresponding to the ASIL grade of the vehicle;
acquiring a data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve to determine a first threshold value, wherein the first threshold value is used for evaluating whether the measured value of the sensor is qualified or not;
and evaluating the difference value, if the difference value exceeds the first threshold value, evaluating that the measured value of the sensor is qualified, otherwise, evaluating that the measured value is unqualified.
2. The distance error evaluation method according to claim 1, wherein the receiving the first data includes:
receiving the lateral velocity and the lateral acceleration of the perception object;
a lateral safety distance between the vehicle and the perceived object is calculated based on the lateral velocity and lateral acceleration.
3. The distance error evaluation method according to claim 2, wherein the receiving the first data further comprises:
receiving the longitudinal speed and the longitudinal acceleration of the perception object;
a longitudinal safety distance between the vehicle and the perceived object is calculated based on the longitudinal speed and the longitudinal acceleration.
4. A distance error evaluation method according to claim 3, characterized in that the method further comprises:
acquiring a first boundary value according to the first data, wherein the first boundary value is a transverse safety distance and a longitudinal safety distance between the vehicle and the perception object;
and acquiring a first driving area of the vehicle based on the transverse safety distance and the longitudinal safety distance, wherein the first driving area is a safety area for normal driving of the vehicle in the first boundary value.
5. The distance error evaluation method according to claim 4, characterized in that the method further comprises:
when no sensing object exists in the sensing range of the sensor, a second driving area is acquired, wherein the second driving area is a safe driving area without the sensing object;
wherein the second travel region is not limited by the first boundary value.
6. The distance error evaluation method according to claim 1, wherein the acquiring a normal distribution curve of hardware failure rates corresponding to ASIL levels of the vehicle includes:
acquiring a hardware failure rate corresponding to an ASIL grade of the vehicle;
determining a confidence interval of the hardware failure rate according to the ASIL grade of the vehicle;
and constructing a normal distribution curve of the hardware failure rate in the confidence interval.
7. The distance error evaluation method according to claim 4, wherein the acquiring the data relationship between the maximum allowable error of the sensor and the hardware failure rate based on the normal distribution curve to determine the first threshold value includes:
acquiring a boundary distance between the first boundary value and the vehicle;
acquiring the probability of the error of which the first data is larger than the boundary distance from the normal distribution curve, and carrying out inverse cumulative distribution operation on the basis of the probability to acquire an inverse cumulative distribution value;
the ratio between the boundary distance and the inverse cumulative distribution value is taken as a first threshold value.
8. The distance error assessment method according to any one of claims 1 to 7, wherein said ASIL class is divided into a plurality of ASIL classes, and each of said ASIL classes has a corresponding hardware failure rate.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the distance error evaluation method according to any one of claims 1 to 8 when executing the program.
10. A computer storage medium storing a computer program, wherein the computer program when executed by a processor implements the distance error evaluation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310432165.5A CN116558469A (en) | 2023-04-20 | 2023-04-20 | Distance error evaluation method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310432165.5A CN116558469A (en) | 2023-04-20 | 2023-04-20 | Distance error evaluation method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116558469A true CN116558469A (en) | 2023-08-08 |
Family
ID=87497456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310432165.5A Pending CN116558469A (en) | 2023-04-20 | 2023-04-20 | Distance error evaluation method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116558469A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117007083A (en) * | 2023-09-22 | 2023-11-07 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle ranging capability assessment method, system, equipment and medium thereof |
-
2023
- 2023-04-20 CN CN202310432165.5A patent/CN116558469A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117007083A (en) * | 2023-09-22 | 2023-11-07 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle ranging capability assessment method, system, equipment and medium thereof |
| CN117007083B (en) * | 2023-09-22 | 2024-03-05 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle ranging capability assessment method, system, equipment and medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9704403B2 (en) | System and method for collision avoidance for vehicle | |
| US8954260B2 (en) | Method and system for collision assessment for vehicles | |
| US10019903B2 (en) | System and method for informing nearby vehicle to avoid a moving vehicle which is malfunctioning | |
| EP3971526A1 (en) | Path planning in autonomous driving environments | |
| CN105976450A (en) | Unmanned vehicle data processing method and device, and black box system | |
| EP4083871A1 (en) | Method for automated development of a path planning module for an automated driving system | |
| CN111923914B (en) | Identification of road shoulder travel of motor vehicle | |
| CN111710158B (en) | Vehicle data processing method and related equipment | |
| US12084051B2 (en) | Scenario identification in autonomous driving environments | |
| US20220080962A1 (en) | Vehicle operation using a behavioral rule model | |
| US11260876B2 (en) | Inter-vehicle sensor validation using senso-fusion network | |
| US12058552B2 (en) | Systems and methods for selecting locations to validate automated vehicle data transmission | |
| EP3971864A1 (en) | Risk estimation in autonomous driving environments | |
| CN116558469A (en) | Distance error evaluation method, device, electronic equipment and storage medium | |
| CN112046494A (en) | Vehicle control method, device, equipment and storage medium | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| CN111613060A (en) | Data processing method and equipment | |
| EP4082862A1 (en) | Platform for path planning system development for automated driving system | |
| CN110450788B (en) | Driving mode switching method, device, equipment and storage medium | |
| CN112863177A (en) | Navigation duration prediction method based on data analysis | |
| KR20220153708A (en) | Method for Controlling Controller of Vehicle And Vehicle Integrated Controller Therefor | |
| CN113962107A (en) | Method and device for simulating driving road section, electronic equipment and storage medium | |
| CN112009496B (en) | Security architecture for autonomous vehicle control | |
| CN113538894B (en) | Vehicle positioning data processing method, device, computer equipment and storage medium | |
| KR102636871B1 (en) | The safty driving evaluation method for autonomous vehicles supporting mobility for the transportation vulnerable |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |