CN110599025A - Method for evaluating reliability index of driving behavior of automatic driving automobile - Google Patents
Method for evaluating reliability index of driving behavior of automatic driving automobile Download PDFInfo
- Publication number
- CN110599025A CN110599025A CN201910843020.8A CN201910843020A CN110599025A CN 110599025 A CN110599025 A CN 110599025A CN 201910843020 A CN201910843020 A CN 201910843020A CN 110599025 A CN110599025 A CN 110599025A
- Authority
- CN
- China
- Prior art keywords
- automatic driving
- driving
- automobile
- index
- average
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention discloses a method for evaluating the driving behavior reliability index of an automatic driving automobile, which comprises the following steps: planning a running path of the automatic driving automobile according to an automatic driving function test rule of the automatic driving automobile; acquiring driving behavior data from a starting point to a terminal point of the automatic driving automobile in a driving path of the automatic driving automobile according to unreliable driving behaviors generated by the automatic driving automobile in the driving process; calculating reliability index values including a first-level index and a second-level index according to the driving behavior data; and calculating the reliability of the driving behavior of the automatic driving automobile according to the calculated reliability index value and the preset corresponding weight. According to the method, the reliability of software and hardware of the automatic driving automobile does not need to be analyzed, and the reliability evaluation result of the automatic driving automobile can be obtained only by calculating and analyzing the driving behavior data of the automatic driving automobile, so that the reliability analysis efficiency of the automatic driving automobile is improved, and the reliability of the whole automatic driving automobile is guided and improved.
Description
Technical Field
The invention relates to the technical field of evaluation of reliability indexes of an automatic driving automobile, in particular to a method for evaluating the reliability indexes of driving behaviors of the automatic driving automobile.
Background
With the rapid development and application of artificial intelligence technology, the automatic driving of automobiles becomes the main trend of the development of the modern automobile industry. The automatic driving automobile is a mobile machine which independently completes driving tasks by means of an intelligent computer system, can replace human drivers to transport personnel and goods, and effectively reduces traffic accidents. However, the reliability of the currently studied automatic driving technology still needs to be improved, which seriously hinders the pace of large-scale commercial use of automatic driving automobiles. From the beginning of the development of automotive autodrive technology to the present, many autodrive automotive traffic safety accidents have occurred globally, with severe direct consequences for the death of drivers and pedestrians. The reliability is an important index for representing the comprehensive quality of products, improves the reliability of the automatic driving automobile, and has important significance for improving the safety of the automatic driving automobile and reducing the occurrence of traffic accidents of the automatic driving automobile.
At present, the reliability research methods for the automatic driving automobile at home and abroad are few, and the reliability research is generally carried out from the reliability perspective of hardware and software of the automatic driving automobile, the method has a certain guiding effect on the whole automobile reliability of the automatic driving automobile and has a certain reference value, but in the actual driving process of the automatic driving automobile, the traditional software and hardware reliability evaluation method lacks consideration on the actual situation, and cannot completely carry out reliability analysis on the automatic driving automobile.
Disclosure of Invention
The invention aims to overcome the limitation of the existing reliability evaluation method in the evaluation of the reliability index of the automatic driving automobile and provides a driving behavior reliability index evaluation method of the automatic driving automobile.
The technical scheme adopted by the invention for achieving the purpose is as follows:
the method for evaluating the driving behavior reliability index of the automatic driving automobile comprises the following steps:
step 1, planning a running path of an automatic driving automobile according to an automatic driving function test rule of the automatic driving automobile;
step 2, acquiring driving behavior data from a starting point to a terminal point of the automatic driving automobile in a driving path of the automatic driving automobile according to unreliable driving behaviors generated by the automatic driving automobile in the driving process;
and 3, calculating a reliability index value according to the driving behavior data, wherein the reliability index value comprises a first-level index and a second-level index, and the first-level index comprises: the system comprises a non-fault index, a maintainability index and a comprehensive index, wherein the non-fault index comprises a secondary index average non-fault operation mileage, an average non-fault operation time, an average first fault mileage and reliability, the maintainability index comprises a secondary index average unscheduled repair interval time, an average repair time and a repair rate, and the comprehensive index comprises a secondary index effectiveness and a driving track error;
and 4, calculating the reliability of the driving behavior of the automatic driving automobile according to the calculated reliability index value and the preset corresponding weight.
According to the technical scheme, in the step 1, the planned driving path of the automatic driving automobile comprises a test scene specified by an automatic driving function test regulation of the automatic driving automobile, wherein the test scene comprises road width, road surface requirements, environmental requirements and traffic sign line requirements.
According to the technical scheme, the driving behavior data in the step 2 comprises the following steps: the total mileage of the automatic driving automobile after completing the path, the total length of the automatic driving automobile after completing the path, the times of unreliable driving behaviors and the mileage of the automatic driving automobile with the first driving behavior fault after leaving the factory.
According to the technical scheme, in the step 3:
the average fault-free running mileage is the average running mileage of the automatic driving automobile between two driving behavior faults;
the average no-fault running time is the average running time of the automatic driving automobile between two behavior faults;
the average first fault mileage is the average running mileage of the automatic driving automobile when the automatic driving automobile enters a planned path and runs until the first behavior fault occurs;
the reliability is the failure-free probability of the automatic driving automobile in the driving between two unreliable driving behaviors;
the average unscheduled repair interval time is the average time between two unscheduled repairs other than the scheduled repair of the autonomous vehicle;
the average repair time is the average time for repairing the automatic driving automobile after the automatic driving automobile fails;
the repair rate is the ratio of the total number of failures repaired at any given repair level to the total time for repairable repair at that level for an autonomous vehicle under given conditions and for a given period of time, and can be expressed as the inverse of the average repair time.
The effectiveness is the probability that the autonomous vehicle will maintain its normal function at any point in time when it is used under specified conditions;
the running track error is an error value between an actual running path and a planned expected path when the automatic driving automobile runs in the planned path.
According to the technical scheme, the specific calculation mode of each reliability index value is as follows:
average fault-free operating mileage:
in the formula: m is the total kilometer number of the recorded planned path where the automatic driving automobile runs, and r is the total number of driving behavior faults of the automatic driving automobile in the automatic driving state;
mean time to failure:
in the formula: t is the recorded total driving time of each automatic driving automobile for completing the route planning driving in the automatic driving state, N is the recorded total number of the automatic driving automobiles, and r is the total times of driving behavior faults of the automatic driving automobiles in the automatic driving state;
average first failure mileage:
in the formula: n is the total number of recorded autodrome cars, miThe mileage of the ith automatic driving automobile with the first driving behavior fault;
reliability:
R(x)＝exp[-x/MMBBF]
in the formula: x is a random variable of fault interval kilometer number, and MMBBF is the average fault-free running mileage of the automatic driving automobile;
average unplanned repair interval:
in the formula: t is the total recorded driving time of each automatic driving automobile for completing the planned path driving in the automatic driving state, N is the total recorded number of the automatic driving automobiles, and TsThe method comprises the steps that total repair time in N automatic driving automobiles in time T is planned, in days, and N is the total number of times of unscheduled repair of the N automatic driving automobiles in time T;
average repair time:
in the formula: t is tiN is the number of unscheduled total repairs of the N autodrome within the time T, wherein i is 1,2, …, N;
the degree of effectiveness:
in the formula: lambda is the failure rate of the autonomous vehicle,mu is the repair rate of the automatic driving automobile,
error of the running track:
LER＝sqrt(((x1-xe1)2+(y1-ye1)2+(x2-xe2)2+(y2-ye2)2+…+(xn-xen)2+(yn-yen)2)/n)
in the formula: x is the number ofn，ynCoordinates, x, representing the nth reference point of the path actually travelled in the planned pathen，yenAnd coordinates of the nth path reference point expected to be driven in the planned path are shown.
According to the technical scheme, unreliable driving behaviors generated in the driving process of the automatic driving automobile comprise: the traffic sign, all automatic driving behaviors when the identification of the marking line is wrong, all automatic driving behaviors when the identification of the traffic signal lamp is wrong, automatic driving behaviors when the identification of surrounding obstacles is wrong, automatic driving behaviors when the identification of pedestrians and non-motor vehicles is wrong, automatic driving behaviors when the driving state of the front vehicle is judged in a wrong way when the vehicle follows the vehicle, automatic driving behaviors when the vehicle is taken over by manual operation, unreliable driving behaviors when the vehicle is parked by the roadside, unreliable driving behaviors when the vehicle overtakes the vehicle, unreliable driving behaviors when the vehicle passes through the intersection and unreliable driving behaviors when the vehicle merges the road.
According to the technical scheme, the weight of the non-fault index is 0.4; the weights of the maintainability index and the comprehensive index are both 0.3.
The invention also provides an evaluation system for the driving behavior reliability index of the automatic driving automobile, which comprises the following steps:
the path planning module is used for planning the running path of the automatic driving automobile according to the automatic driving function test rule of the automatic driving automobile;
the behavior data acquisition module is used for acquiring driving behavior data from a starting point to a terminal point of the automatic driving automobile in a driving path of the automatic driving automobile according to unreliable driving behaviors generated by the automatic driving automobile in the driving process;
the reliability index value calculation module is used for calculating the reliability index value according to the driving behavior data, and comprises a first-level index and a second-level index, wherein the first-level index comprises: the system comprises a non-fault index, a maintainability index and a comprehensive index, wherein the non-fault index comprises a secondary index average non-fault operation mileage, an average non-fault operation time, an average first fault mileage and reliability, the maintainability index comprises a secondary index average unscheduled repair interval time, an average repair time and a repair rate, and the comprehensive index comprises a secondary index effectiveness and a driving track error;
and the reliability evaluation module is used for comparing the requirements of the intelligent networked automobile automatic driving function test regulations issued by the automatic driving automobile industry according to the calculated reliability index value and calculating the reliability of the automatic driving automobile driving behavior.
According to the technical scheme, unreliable driving behaviors generated in the driving process of the automatic driving automobile comprise: the traffic sign, all automatic driving behaviors when the identification of the marking line is wrong, all automatic driving behaviors when the identification of the traffic signal lamp is wrong, automatic driving behaviors when the identification of surrounding obstacles is wrong, automatic driving behaviors when the identification of pedestrians and non-motor vehicles is wrong, automatic driving behaviors when the driving state of the front vehicle is judged in a wrong way when the vehicle follows the vehicle, automatic driving behaviors when the vehicle is taken over by manual operation, unreliable driving behaviors when the vehicle is parked by the roadside, unreliable driving behaviors when the vehicle overtakes the vehicle, unreliable driving behaviors when the vehicle passes through the intersection and unreliable driving behaviors when the vehicle merges the road.
According to the technical scheme, the weight of the non-fault index is 0.4; the weights of the maintainability index and the comprehensive index are both 0.3.
The invention has the following beneficial effects: from the aspect of the driving behavior reliability of the automatic driving automobile, the reliability of hardware and software of the automatic driving automobile does not need to be analyzed, the reliability evaluation period is shortened, the reliability evaluation efficiency of the automatic driving automobile is improved, the reliability evaluation method is suitable for the reliability evaluation of the whole automatic driving automobile, and the development requirement of the current automobile industry for the reliability evaluation of the automatic driving automobile is met.
In addition, the method calculates the reliability index measurement parameters of the automatic driving automobile by using a statistical method, has the advantages of less data quantity required to be collected, small calculated quantity, firm theoretical foundation and strong practicability, and has guiding significance for improving the reliability of the automatic driving automobile.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method for evaluating a driving behavior reliability indicator of an autonomous vehicle in accordance with an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a system for evaluating a driving behavior reliability index of an autonomous vehicle according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the method for evaluating the driving reliability index of the autonomous vehicle according to the embodiment of the present invention includes the following steps:
s1, planning a running path of the automatic driving automobile according to the automatic driving function test rule of the automatic driving automobile;
in the step, the driving path of the automatic driving automobile is planned according to the requirement of an automatic driving function test regulation, and comprises the paths of traffic elements such as a speed limit sign, a parking yielding sign, a lane line, a pedestrian crossroad line, a motor vehicle signal lamp, a direction indicating signal lamp, a speed reducing belt, an intersection, a circular intersection, a pedestrian, a motor vehicle, a non-motor vehicle and the like required by the automatic driving function test regulation, wherein the road is a flat and dry asphalt or concrete road surface; the width of the single lane is 3.5 m-3.75 m; the environment is good, no bad weather such as rainfall, snowfall, hail and the like exists, and the horizontal visibility is not lower than 500 m; the traffic signs and the marked lines of the test scene are clearly visible and meet the requirements of GB 5768 plus 2017 road traffic signs and marked lines; in the planned path, sensors such as cameras are arranged at key positions of road traffic, such as traffic intersections and traffic signs, so as to sense the running state of the automatic driving vehicle.
S2, acquiring driving behavior data of the automatic driving automobile from a starting point to a terminal point of a planned path according to unreliable driving behaviors generated by the automatic driving automobile in the driving process;
in this step, the unreliable driving behaviors and the driving behavior data thereof are shown in table 1 below (the numbers in the table indicate the types and numbers of the unreliable driving behaviors, and there are 9 types of the perception-type unreliable driving behaviors):
TABLE 1 unreliable driving behaviour and driving behaviour data thereof
Further, the specific unreliable driving behavior is mainly obtained through a vehicle-mounted sensor, a high-precision map and a traffic road sensing facility, wherein the vehicle-mounted sensor mainly comprises a laser radar, an image sensor (camera), a millimeter wave radar and an ultrasonic radar and is used for obtaining the surrounding environment information of the vehicle body, such as pedestrians, vehicles and states thereof, road traffic signs, marking lines, traffic signal indicator lights and the like; the high-precision map has the functions of high-precision positioning, auxiliary environment sensing, planning, decision making and the like, the vehicle is positioned and environment sensed in an auxiliary manner, detailed road information is marked on the high-precision map, and the vehicle is assisted to verify in the sensing process, and if a vehicle sensor senses the surrounding environment of a vehicle body, the vehicle sensor can compare the surrounding environment with data in the high-precision map to perform verification and judgment; the traffic road perception facility is mainly characterized in that a sensor, a camera and the like are arranged at a key position of road traffic to perceive the state of a vehicle and the surrounding environment information of the vehicle; the three methods can acquire the surrounding environment information and the driving information of the automatic driving automobile in the driving process of the automatic driving automobile, such as vehicle speed, vehicle position, vehicle steering, real-time state of vehicle light and signals, transverse and longitudinal distances and the like, and compare and verify the acquired environment information and the vehicle state information with the traffic rules specified by the road traffic safety law, thereby judging whether the driving behavior of the automatic driving automobile in the environment where the automatic driving automobile is located is reliable or not.
Further, when the vehicle is in the corresponding road traffic environment, the vehicle state information and the environment information thereof can be transmitted to the remote intelligent vehicle cloud platform center in real time, the driving behavior of the vehicle can be judged in time, and the corresponding information can be recorded and stored, so that the reliability of the driving behavior of the automatic driving vehicle can be evaluated.
S3, calculating reliability index values according to the driving behavior data, wherein the reliability index values comprise primary indexes and secondary indexes, and the primary indexes comprise: the system comprises a non-fault index, a maintainability index and a comprehensive index, wherein the non-fault index comprises a secondary index average non-fault operation mileage, an average non-fault operation time, an average first fault mileage and reliability, the maintainability index comprises a secondary index average unscheduled repair interval time, an average repair time and a repair rate, and the comprehensive index comprises a secondary index effectiveness and a driving track error; the details are shown in table 2 below:
table 2: behavioral reliability index
And S4, calculating the reliability of the driving behavior of the automatic driving automobile according to the calculated reliability index value and the preset corresponding weight value. And comparing the requirements of the intelligent networked automobile automatic driving function test regulations issued by the automatic driving automobile industry, and evaluating the driving behavior reliability of the automatic driving automobile.
In this step, the evaluation index values and the empowerments of the driving behavior of the automatic driving car are shown in the following table 3:
TABLE 3 reliability index values and assigned weights
In the first-level index weighting, the non-fault index is the basis of reliability evaluation in the automobile industry and is more important, so the weighting is 0.4; the maintainability index and the comprehensive index are established on the basis of the non-failure index, so that the ownership of the maintainability index and the comprehensive index is the same as 0.3.
Further, the driving behavior data includes: the total mileage of the automatic driving automobile after completing the path, the total length of the automatic driving automobile after completing the path, the times of unreliable driving behaviors and the mileage of the automatic driving automobile with the first driving behavior fault after leaving the factory. Wherein the content of the first and second substances,
the average fault-free running mileage is the average running mileage of the automatic driving automobile between two driving behavior faults;
the average no-fault running time is the average running time of the automatic driving automobile between two behavior faults;
the average first fault mileage is the average running mileage of the automatic driving automobile when the automatic driving automobile enters a planned path and runs until the first behavior fault occurs;
the reliability is the failure-free probability of the automatic driving automobile in the driving between two unreliable driving behaviors;
the average unscheduled repair interval time is the average time between two unscheduled repairs other than the scheduled repair of the autonomous vehicle;
the average repair time is the average time for repairing the automatic driving automobile after the automatic driving automobile fails;
the repair rate is the ratio of the total number of failures repaired at any given repair level to the total time for repairable repair at that level for an autonomous vehicle under given conditions and for a given period of time, and can be expressed as the inverse of the average repair time.
The effectiveness is the probability that the autonomous vehicle will maintain its normal function at any point in time when it is used under specified conditions;
the running track error is an error value between an actual running path and a planned expected path when the automatic driving automobile runs in the planned path.
The specific calculation formula is as follows:
average fault-free operating mileage:
in the formula: m is the total kilometer number of the recorded planned path where the automatic driving automobile runs, and r is the total number of driving behavior faults of the automatic driving automobile in the automatic driving state;
mean time to failure:
in the formula: t is the recorded total driving time of each automatic driving automobile for completing the route planning driving in the automatic driving state, N is the recorded total number of the automatic driving automobiles, and r is the total times of driving behavior faults of the automatic driving automobiles in the automatic driving state;
average first failure mileage:
in the formula: n is the total number of recorded autodrome cars, miThe mileage of the ith automatic driving automobile with the first driving behavior fault;
reliability:
R(x)＝exp[-x/MMBBF]
in the formula: x is a random variable of fault interval kilometer number, and MMBBF is the average fault-free running mileage of the automatic driving automobile;
average unplanned repair interval:
in the formula: t is the total recorded driving time of each automatic driving automobile for completing the planned path driving in the automatic driving state, N is the total recorded number of the automatic driving automobiles, and TsThe total repair time (days) in the N automatic driving automobiles in the time T is planned, and N is the total number of times of the unplanned repair of the N automatic driving automobiles in the time T;
average repair time:
in the formula: t is ti(i is 1,2, …, N) is the repair time of N repairs, N is the total number of unplanned repairs of N autodrive cars in the time T;
the degree of effectiveness:
in the formula: lambda is the failure rate of the autonomous vehicle,mu is the repair rate of the automatic driving automobile,
error of the running track:
LER＝sqrt(((x1-xe1)2+(y1-ye1)2+(x2-xe2)2+(y2-ye2)2+…+(xn-xen)2+(yn-yen)2)/n)
in the formula: x is the number ofn，ynCoordinates, x, representing the nth reference point of the path actually travelled in the planned pathen，yenAnd coordinates of the nth path reference point expected to be driven in the planned path are shown.
The secondary index values were performed as follows in table 4:
TABLE 4 two-stage index value-taking table
The reliability calculation formula of the driving behavior of the automatic driving automobile is as follows:
B＝(B11+B12+B13+B14)×α+(B21+B22+B23)×β+(B31+B32)×γ
in the formula: α ═ 0.4, β ═ γ ═ 0.3; b isijThe value cannot be 0, i is 1,2, 3, j is 1,2, 3, 4.
The reliability evaluation of the driving behavior of the automatic driving automobile in the step specifically comprises the following steps:
and determining the values of the secondary indexes according to the established driving behavior reliability evaluation indexes of the automatic driving automobile and the calculated driving behavior reliability measurement parameter values of the automatic driving automobile, calculating the driving behavior reliability of the automatic driving automobile, and comparing the requirements of the automatic driving function test regulations of the intelligent networked automobile released by the automatic driving automobile industry to obtain the reliability evaluation result of the driving behavior of the automatic driving automobile.
In order to implement the method, the invention further provides an evaluation system for reliability index of driving behavior of an autonomous vehicle, as shown in fig. 2, comprising:
the path planning module is used for planning the running path of the automatic driving automobile according to the automatic driving function test rule of the automatic driving automobile;
the behavior data acquisition module is used for acquiring driving behavior data from a starting point to a terminal point of the automatic driving automobile in a driving path of the automatic driving automobile according to unreliable driving behaviors generated by the automatic driving automobile in the driving process;
the reliability index value calculation module is used for calculating the reliability index value according to the driving behavior data, and comprises a first-level index and a second-level index, wherein the first-level index comprises: the system comprises a non-fault index, a maintainability index and a comprehensive index, wherein the non-fault index comprises a secondary index average non-fault operation mileage, an average non-fault operation time, an average first fault mileage and reliability, the maintainability index comprises a secondary index average unscheduled repair interval time, an average repair time and a repair rate, and the comprehensive index comprises a secondary index effectiveness and a driving track error;
and the reliability evaluation module is used for comparing the requirements of the intelligent networked automobile automatic driving function test regulations issued by the automatic driving automobile industry according to the calculated reliability index value and calculating the reliability of the automatic driving automobile driving behavior.
The system may also implement other specific processes of the above method, which are not described herein.
From the aspect of the driving behavior reliability of the automatic driving automobile, the reliability of hardware and software of the automatic driving automobile does not need to be analyzed, the reliability evaluation period is shortened, the reliability evaluation efficiency of the automatic driving automobile is improved, the reliability evaluation method is suitable for the reliability evaluation of the whole automatic driving automobile, and the development requirement of the current automobile industry for the reliability evaluation of the automatic driving automobile is met. In addition, the method calculates the reliability index measurement parameters of the automatic driving automobile by using a statistical method, has the advantages of less data quantity required to be collected, small calculated quantity, firm theoretical foundation and strong practicability, and has guiding significance for improving the reliability of the automatic driving automobile.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (10)
1. A method for evaluating the driving behavior reliability index of an automatic driving automobile is characterized by comprising the following steps:
step 1, planning a running path of an automatic driving automobile according to an automatic driving function test rule of the automatic driving automobile;
step 2, acquiring driving behavior data from a starting point to a terminal point of the automatic driving automobile in a driving path of the automatic driving automobile according to unreliable driving behaviors generated by the automatic driving automobile in the driving process;
and 3, calculating a reliability index value according to the driving behavior data, wherein the reliability index value comprises a first-level index and a second-level index, and the first-level index comprises: the system comprises a non-fault index, a maintainability index and a comprehensive index, wherein the non-fault index comprises a secondary index average non-fault operation mileage, an average non-fault operation time, an average first fault mileage and reliability, the maintainability index comprises a secondary index average unscheduled repair interval time, an average repair time and a repair rate, and the comprehensive index comprises a secondary index effectiveness and a driving track error;
and 4, calculating the reliability of the driving behavior of the automatic driving automobile according to the calculated reliability index value and the preset corresponding weight.
2. The method for evaluating the reliability index of the driving behavior of the autopilot according to claim 1, wherein in step 1, the planned driving path of the autopilot includes test scenarios specified by the test rules for the autopilot's driving function, including road width, road surface requirements, environmental requirements, and traffic sign requirements.
3. The method of claim 1, wherein the driving behavior data in step 2 comprises: the total mileage of the automatic driving automobile after completing the path, the total length of the automatic driving automobile after completing the path, the times of unreliable driving behaviors and the mileage of the automatic driving automobile with the first driving behavior fault after leaving the factory.
4. The method for evaluating the reliability index of the driving behavior of the autonomous vehicle as claimed in claim 1, wherein in step 3:
the average fault-free running mileage is the average running mileage of the automatic driving automobile between two driving behavior faults;
the average no-fault running time is the average running time of the automatic driving automobile between two behavior faults;
the average first fault mileage is the average running mileage of the automatic driving automobile when the automatic driving automobile enters a planned path and runs until the first behavior fault occurs;
the reliability is the failure-free probability of the automatic driving automobile in the driving between two unreliable driving behaviors;
the average unscheduled repair interval time is the average time between two unscheduled repairs other than the scheduled repair of the autonomous vehicle;
the average repair time is the average time for repairing the automatic driving automobile after the automatic driving automobile fails;
the repair rate is the ratio of the total number of failures repaired at any given repair level to the total time for repairable repair at that level for an autonomous vehicle under given conditions and for a given period of time, and can be expressed as the inverse of the average repair time.
The effectiveness is the probability that the autonomous vehicle will maintain its normal function at any point in time when it is used under specified conditions;
the running track error is an error value between an actual running path and a planned expected path when the automatic driving automobile runs in the planned path.
5. The method for evaluating the driving behavior reliability index of an autonomous vehicle according to any of claims 1 to 4, characterized in that each reliability index value is calculated in a specific manner as follows:
average fault-free operating mileage:
in the formula: m is the total kilometer number of the recorded planned path where the automatic driving automobile runs, and r is the total number of driving behavior faults of the automatic driving automobile in the automatic driving state;
mean time to failure:
in the formula: t is the recorded total driving time of each automatic driving automobile for completing the route planning driving in the automatic driving state, N is the recorded total number of the automatic driving automobiles, and r is the total times of driving behavior faults of the automatic driving automobiles in the automatic driving state;
average first failure mileage:
in the formula: n is the total number of recorded autodrome cars, miThe mileage of the ith automatic driving automobile with the first driving behavior fault;
reliability:
R(x)＝exp[-x/MMBBF]
in the formula: x is a random variable of fault interval kilometer number, and MMBBF is the average fault-free running mileage of the automatic driving automobile;
average unplanned repair interval:
in the formula: t is the total recorded driving time of each automatic driving automobile for completing the planned path driving in the automatic driving state, N is the total recorded number of the automatic driving automobiles, and TsThe method comprises the steps that total repair time in N automatic driving automobiles in time T is planned, in days, and N is the total number of times of unscheduled repair of the N automatic driving automobiles in time T;
average repair time:
in the formula: t is tiRepair time for N repairs, N being the number of unplanned total repairs of N autodrive vehicles within time T, where i＝1,2,…,n；
The degree of effectiveness:
in the formula: lambda is the failure rate of the autonomous vehicle,mu is the repair rate of the automatic driving automobile,
error of the running track:
LER＝sqrt(((x1-xe1)2+(y1-ye1)2+(x2-xe2)2+(y2-ye2)2+…+(xn-xen)2+(yn-yen)2)/n)
in the formula: x is the number ofn，ynCoordinates, x, representing the nth reference point of the path actually travelled in the planned pathen，yenAnd coordinates of the nth path reference point expected to be driven in the planned path are shown.
6. The method of claim 5, wherein the unreliable driving behavior generated by the autonomous vehicle during driving comprises: the traffic sign, all automatic driving behaviors when the identification of the marking line is wrong, all automatic driving behaviors when the identification of the traffic signal lamp is wrong, automatic driving behaviors when the identification of surrounding obstacles is wrong, automatic driving behaviors when the identification of pedestrians and non-motor vehicles is wrong, automatic driving behaviors when the driving state of the front vehicle is judged in a wrong way when the vehicle follows the vehicle, automatic driving behaviors when the vehicle is taken over by manual operation, unreliable driving behaviors when the vehicle is parked by the roadside, unreliable driving behaviors when the vehicle overtakes the vehicle, unreliable driving behaviors when the vehicle passes through the intersection and unreliable driving behaviors when the vehicle merges the road.
7. The method of claim 1, wherein the weight of the non-failure indicator is 0.4; the weights of the maintainability index and the comprehensive index are both 0.3.
8. An automated driving vehicle driving behavior reliability index evaluation system, comprising:
the path planning module is used for planning the running path of the automatic driving automobile according to the automatic driving function test rule of the automatic driving automobile;
the behavior data acquisition module is used for acquiring driving behavior data from a starting point to a terminal point of the automatic driving automobile in a driving path of the automatic driving automobile according to unreliable driving behaviors generated by the automatic driving automobile in the driving process;
the reliability index value calculation module is used for calculating the reliability index value according to the driving behavior data, and comprises a first-level index and a second-level index, wherein the first-level index comprises: the system comprises a non-fault index, a maintainability index and a comprehensive index, wherein the non-fault index comprises a secondary index average non-fault operation mileage, an average non-fault operation time, an average first fault mileage and reliability, the maintainability index comprises a secondary index average unscheduled repair interval time, an average repair time and a repair rate, and the comprehensive index comprises a secondary index effectiveness and a driving track error;
and the reliability evaluation module is used for comparing the requirements of the intelligent networked automobile automatic driving function test regulations issued by the automatic driving automobile industry according to the calculated reliability index value and calculating the reliability of the automatic driving automobile driving behavior.
9. The system of claim 8, wherein the unreliable driving behavior generated by the autonomous vehicle during driving comprises: the traffic sign, all automatic driving behaviors when the identification of the marking line is wrong, all automatic driving behaviors when the identification of the traffic signal lamp is wrong, automatic driving behaviors when the identification of surrounding obstacles is wrong, automatic driving behaviors when the identification of pedestrians and non-motor vehicles is wrong, automatic driving behaviors when the driving state of the front vehicle is judged in a wrong way when the vehicle follows the vehicle, automatic driving behaviors when the vehicle is taken over by manual operation, unreliable driving behaviors when the vehicle is parked by the roadside, unreliable driving behaviors when the vehicle overtakes the vehicle, unreliable driving behaviors when the vehicle passes through the intersection and unreliable driving behaviors when the vehicle merges the road.
10. The system of claim 8, wherein the non-fault indicator has a weight of 0.4; the weights of the maintainability index and the comprehensive index are both 0.3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843020.8A CN110599025A (en) | 2019-09-06 | 2019-09-06 | Method for evaluating reliability index of driving behavior of automatic driving automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843020.8A CN110599025A (en) | 2019-09-06 | 2019-09-06 | Method for evaluating reliability index of driving behavior of automatic driving automobile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110599025A true CN110599025A (en) | 2019-12-20 |
Family
ID=68858016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910843020.8A Pending CN110599025A (en) | 2019-09-06 | 2019-09-06 | Method for evaluating reliability index of driving behavior of automatic driving automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110599025A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767651A (en) * | 2020-06-28 | 2020-10-13 | 北京百度网讯科技有限公司 | Index prediction model construction method, index prediction method and device |
| CN112258830A (en) * | 2020-10-23 | 2021-01-22 | 上海博泰悦臻电子设备制造有限公司 | Method for evaluating reliability of vehicle formation driving and application thereof |
| CN113343448A (en) * | 2021-05-25 | 2021-09-03 | 京东鲲鹏(江苏)科技有限公司 | Control effect evaluation method and device, electronic equipment and storage medium |
| CN113428168A (en) * | 2020-03-19 | 2021-09-24 | 上海擎感智能科技有限公司 | Control method, system and medium for automatically driving vehicle and automobile |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105699095A (en) * | 2016-01-27 | 2016-06-22 | 常州加美科技有限公司 | A test method for a remotely piloted vehicle (PRV) |
| CN107085768A (en) * | 2017-04-25 | 2017-08-22 | 交通运输部公路科学研究所 | A kind of system and method for being used to evaluate vehicle operational reliability |
| US20190064799A1 (en) * | 2017-08-22 | 2019-02-28 | Elmira Amirloo Abolfathi | System, method, and processor-readable medium for autonomous vehicle reliability assessment |
| CN109435955A (en) * | 2018-10-22 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | A kind of automated driving system performance estimating method, device, equipment and storage medium |
-
2019
- 2019-09-06 CN CN201910843020.8A patent/CN110599025A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105699095A (en) * | 2016-01-27 | 2016-06-22 | 常州加美科技有限公司 | A test method for a remotely piloted vehicle (PRV) |
| CN107085768A (en) * | 2017-04-25 | 2017-08-22 | 交通运输部公路科学研究所 | A kind of system and method for being used to evaluate vehicle operational reliability |
| US20190064799A1 (en) * | 2017-08-22 | 2019-02-28 | Elmira Amirloo Abolfathi | System, method, and processor-readable medium for autonomous vehicle reliability assessment |
| CN109435955A (en) * | 2018-10-22 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | A kind of automated driving system performance estimating method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 滕云: "国产汽车使用可靠性评价研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 王毅 等: "机车可靠性指标体系及可靠性评估", 《铁道学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113428168A (en) * | 2020-03-19 | 2021-09-24 | 上海擎感智能科技有限公司 | Control method, system and medium for automatically driving vehicle and automobile |
| CN113428168B (en) * | 2020-03-19 | 2022-11-15 | 上海擎感智能科技有限公司 | Control method, system and medium for automatically driving vehicle and automobile |
| CN111767651A (en) * | 2020-06-28 | 2020-10-13 | 北京百度网讯科技有限公司 | Index prediction model construction method, index prediction method and device |
| CN111767651B (en) * | 2020-06-28 | 2023-07-25 | 北京百度网讯科技有限公司 | Index prediction model construction method, index prediction method and device |
| CN112258830A (en) * | 2020-10-23 | 2021-01-22 | 上海博泰悦臻电子设备制造有限公司 | Method for evaluating reliability of vehicle formation driving and application thereof |
| CN113343448A (en) * | 2021-05-25 | 2021-09-03 | 京东鲲鹏(江苏)科技有限公司 | Control effect evaluation method and device, electronic equipment and storage medium |
| CN113343448B (en) * | 2021-05-25 | 2024-03-05 | 京东鲲鹏(江苏)科技有限公司 | Control effect evaluation method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110675656B (en) | Intelligent vehicle lane change early warning method based on instantaneous risk identification | |
| CN111524357B (en) | Method for fusing multiple data required for safe driving of vehicle | |
| CN110599025A (en) | Method for evaluating reliability index of driving behavior of automatic driving automobile | |
| CN110647056B (en) | Intelligent networking automobile environment simulation system based on whole automobile hardware-in-loop | |
| US20190155291A1 (en) | Methods and systems for automated driving system simulation, validation, and implementation | |
| CN110606093A (en) | Vehicle performance evaluation method, device, equipment and storage medium | |
| US20210309231A1 (en) | Driving Environment Information Generation Method, Driving Control Method, Driving Environment Information Generation Device | |
| CN107784848A (en) | Information processor and information processing method | |
| CN110395258A (en) | Pavement state apparatus for predicting and pavement state estimating method | |
| CN110562222B (en) | Emergency braking control method for curve scene, vehicle-mounted device and storage medium | |
| CN109849816B (en) | Driving capability evaluation method, device and system for automatic driving automobile | |
| CN113065685B (en) | High-precision map traffic rule model based on automatic driving application scene and implementation method thereof | |
| CN113190921B (en) | Automatic evaluation method and system for intelligent automobile driving performance test | |
| CN112116031A (en) | Target fusion method and system based on road side equipment, vehicle and storage medium | |
| CN111422202B (en) | Intelligent driving test judging method | |
| CN113247014A (en) | Confidence identification method and system for automatic driving system | |
| CN112937598A (en) | Method and device for evaluating and/or adjusting vehicle driving assistance or automatic driving functions | |
| DE112018005030T5 (en) | ADMINISTRATIVE DEVICE, VEHICLE, INSPECTION DEVICE, AND VEHICLE INSPECTION SYSTEM, AND INFORMATION PROCESSING METHOD THEREFOR | |
| CN113781471A (en) | Automatic driving test field system and method | |
| CN116597690B (en) | Highway test scene generation method, equipment and medium for intelligent network-connected automobile | |
| CN116631187B (en) | Intelligent acquisition and analysis system for case on-site investigation information | |
| CN113227831B (en) | Guardrail estimation method based on multi-sensor data fusion and vehicle-mounted equipment | |
| CN117198057A (en) | Experimental method and system for road side perception track data quality inspection | |
| CN116740940A (en) | Severe weather high-impact road section risk prediction and safety management method, device and equipment | |
| CN115985096B (en) | Evaluation system and method for navigation driving assistance system under road traffic scene |
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 |