CN113918891B - Driving system evaluation method and device, computer equipment and storage medium - Google Patents
Driving system evaluation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113918891B CN113918891B CN202111439497.3A CN202111439497A CN113918891B CN 113918891 B CN113918891 B CN 113918891B CN 202111439497 A CN202111439497 A CN 202111439497A CN 113918891 B CN113918891 B CN 113918891B
- Authority
- CN
- China
- Prior art keywords
- current
- longitudinal acceleration
- state
- evaluated
- target
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 52
- 230000001133 acceleration Effects 0.000 claims abstract description 328
- 238000005452 bending Methods 0.000 claims abstract description 9
- 238000010606 normalization Methods 0.000 claims description 79
- 238000012545 processing Methods 0.000 claims description 47
- 238000000034 method Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012417 linear regression Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 230000008094 contradictory effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000036461 convulsion Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/04—Monitoring the functioning of the control system
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/84—Data processing systems or methods, management, administration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Probability & Statistics with Applications (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Algebra (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of intelligent driving, and provides a driving system evaluation method, a driving system evaluation device, computer equipment and a storage medium, which are used for improving the evaluation accuracy of driving comfort. The driving system evaluation method comprises the following steps: acquiring current state data of a running vehicle to be evaluated, judging whether the current state of the running vehicle to be evaluated is in a target state or not according to the current state data, and acquiring a comfort level score contribution variable according to a judgment result, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after bending; acquiring a current longitudinal acceleration absolute value and a target transverse acceleration variance of the automatic driving vehicle to be evaluated; and calculating a target driving comfort value through the comfort degree grading contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance.
Description
The present invention claims priority from chinese patent application entitled "method of evaluating a driving system, apparatus, computer device, and storage medium" filed by the chinese patent office at 09/16/2021 under the application number 202111085627.8, which is incorporated herein by reference in its entirety.
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a driving system evaluation method, a driving system evaluation device, computer equipment and a storage medium.
Background
With the development of the automatic driving technology, in order to improve the automatic driving vehicle, the driving comfort of the automatic driving vehicle is evaluated while meeting the driving requirements of the user. At present, the driving comfort evaluation method for an autonomous vehicle generally evaluates the driving comfort of the autonomous vehicle only by the acceleration of the vehicle body.
However, the above method takes into account driving state factors (e.g., a loose braking state) that do not affect driving comfort, resulting in a situation where a score that is contrary to the actual body feeling is obtained under the driving state factors that do not affect driving comfort, resulting in a low accuracy of evaluation of driving comfort.
Disclosure of Invention
The invention provides a driving system evaluation method, a driving system evaluation device, computer equipment and a storage medium, which are used for improving the evaluation accuracy of driving comfort.
The invention provides a driving system evaluation method in a first aspect, which comprises the following steps:
acquiring current state data of a running vehicle to be evaluated, judging whether the current state of the running vehicle to be evaluated is in a target state or not according to the current state data, and acquiring a comfort level score contribution variable according to a judgment result, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after bending; acquiring a current longitudinal acceleration absolute value and a target transverse acceleration variance of the automatic driving vehicle to be evaluated; and calculating a target driving comfort value through the comfort degree grading contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining current state data of a running vehicle to be evaluated, determining whether a current state of the running vehicle to be evaluated is in a target state according to the current state data, and obtaining a comfort score contribution variable according to a determination result, where the target state is that a current accelerator or brake is in a state where no external force is applied or a steering wheel returning state after a curve is formed, includes:
acquiring longitudinal acceleration trend data and a current longitudinal acceleration value of the automatic driving vehicle to be evaluated to obtain current state data; judging whether the current state data meet preset conditions or not, wherein the preset conditions are used for indicating that the longitudinal acceleration trend data are larger than a preset threshold value, and the current longitudinal acceleration value is smaller than the preset threshold value; if the current state data meet preset conditions, judging that the current state of the running vehicle to be evaluated is in a target state, setting a comfort level score contribution value to be 0, and obtaining a comfort level score contribution variable, wherein the target state is that the current accelerator or brake is in a state without external force application or a steering wheel return-to-positive state after bending; if the current state data do not meet the preset conditions, judging that the current state of the running vehicle to be evaluated is not in the target state, judging whether the current driving time of the running vehicle to be evaluated is the target state ending time, and acquiring a longitudinal acceleration variance normalization result according to the judgment result to obtain a comfort level grading contribution variable.
Optionally, in a second implementation manner of the first aspect of the present invention, if the current state data does not meet a preset condition, it is determined that the current state of the running vehicle to be evaluated is not in a target state, it is determined whether the current driving time of the running vehicle to be evaluated is a target state end time, and a longitudinal acceleration variance normalization result is obtained according to a determination result, so as to obtain a comfort level score contribution variable, where the method includes:
if the current state data do not accord with the preset conditions, judging that the current state of the running vehicle to be evaluated is not in the target state, and judging whether the current driving time of the running vehicle to be evaluated is the target state ending time or not to obtain a judgment result; acquiring longitudinal acceleration data in a preset time period window, and performing variance normalization processing or zeroing and variance normalization processing on the longitudinal acceleration data in the preset time period window according to the judgment result to obtain a longitudinal acceleration variance normalization result; and determining the result of the normalization of the longitudinal acceleration variance as a comfort level score contribution variable.
Optionally, in a third implementation manner of the first aspect of the present invention, the acquiring longitudinal acceleration data in a preset time period window, and performing variance normalization processing or zeroing and variance normalization processing on the longitudinal acceleration data in the preset time period window according to the determination result to obtain a longitudinal acceleration variance normalization result includes:
acquiring longitudinal acceleration data in a preset time period window; if the judgment result indicates that the current driving time of the running vehicle to be evaluated is not the target state ending time, calculating the variance of the longitudinal acceleration data in the preset time interval window to obtain the longitudinal acceleration variance in the preset time interval window; normalizing the longitudinal acceleration variance in the preset time interval window to obtain a longitudinal acceleration variance normalization result; and if the judgment result indicates that the current driving time of the running vehicle to be evaluated is the target state ending time, performing normalization processing after the variance is zeroed on the longitudinal acceleration data in the preset time interval window to obtain a longitudinal acceleration variance normalization result.
Optionally, in a fourth implementation manner of the first aspect of the present invention, if the determination result indicates that the current driving time of the running vehicle to be evaluated is the target state end time, performing normalization processing after the variance is zeroed on the longitudinal acceleration data within the preset time period window to obtain a longitudinal acceleration variance normalization result, where the normalization processing includes:
if the judgment result indicates that the current driving moment of the running vehicle to be evaluated is the target state ending moment, setting the longitudinal acceleration data in the preset time interval window to be 0 to obtain processed longitudinal acceleration data; and sequentially carrying out variance calculation and normalization processing on the processed longitudinal acceleration data to obtain a longitudinal acceleration variance normalization result.
Optionally, in a fifth implementation manner of the first aspect of the present invention, if the current state data does not meet a preset condition, determining that the current state of the running vehicle to be evaluated is not in a target state, and determining whether the current driving time of the running vehicle to be evaluated is a target state end time, so as to obtain a determination result, where the determining includes:
if the current state data do not accord with the preset conditions, judging that the current state of the running vehicle to be evaluated is not in the target state, and acquiring the previous frame of state data of the current state of the running vehicle to be evaluated; judging whether the previous frame state data and the current longitudinal acceleration value meet a target condition, wherein the target condition is used for indicating that the previous frame state corresponding to the previous frame state data is a target state, and the current longitudinal acceleration value is larger than or equal to the preset threshold value; if the previous frame of state data and the current longitudinal acceleration value accord with a target condition, judging that the current driving time of the running vehicle to be evaluated is the target state ending time to obtain a judgment result; and if the previous frame of state data and the current longitudinal acceleration value do not accord with the target condition, judging that the current driving time of the running vehicle to be evaluated is not the target state end time, and obtaining a judgment result.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the obtaining longitudinal acceleration trend data and a current longitudinal acceleration value of the autonomous vehicle to be evaluated to obtain current state data includes:
acquiring longitudinal acceleration data of a preset time period window of an automatic driving vehicle to be evaluated, and writing the longitudinal acceleration data of the preset time period window into a queue; performing linear regression on the longitudinal acceleration data written into the queue to obtain longitudinal acceleration trend data; extracting a longitudinal acceleration value of the automatic driving vehicle to be evaluated at the current moment to obtain a current longitudinal acceleration value; and determining the longitudinal acceleration trend data and the current longitudinal acceleration value as current state data.
Optionally, in a seventh implementation manner of the first aspect of the present invention, the calculating a target driving comfort value through the comfort score contribution variable, the current absolute value of longitudinal acceleration, and the target variance of lateral acceleration includes:
calculating a longitudinal driving comfort score according to the comfort score contribution variable and the current longitudinal acceleration absolute value; carrying out normalization processing on the target transverse acceleration variance to obtain a normalized target transverse acceleration variance; fitting the normalized target transverse acceleration variance through a preset parameter to be fitted to obtain a transverse driving comfort value; and carrying out weighted summation on the longitudinal driving comfort degree score and the transverse driving comfort degree score, and calculating a difference value with 1 to obtain a target driving comfort degree value.
Optionally, in an eighth implementation manner of the first aspect of the present invention, the calculating a longitudinal driving comfort score according to the comfort score contribution variable and the current absolute value of the longitudinal acceleration includes:
carrying out normalization processing on the current longitudinal acceleration absolute value to obtain a normalized current longitudinal acceleration absolute value; and carrying out weighted summation on the normalized current longitudinal acceleration absolute value and the comfort level score contribution variable to obtain a longitudinal driving comfort level score.
A second aspect of the present invention provides a driving system evaluation device including:
the judging module is used for acquiring current state data of a running vehicle to be evaluated, judging whether the current state of the running vehicle to be evaluated is in a target state or not according to the current state data, and acquiring a comfort level score contribution variable according to a judgment result, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel return-to-positive state after the vehicle is bent; the acquisition module is used for acquiring the current longitudinal acceleration absolute value and the target transverse acceleration variance of the automatic driving vehicle to be evaluated; and the calculation module is used for calculating a target driving comfort value through the comfort level score contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance.
Optionally, in a first implementation manner of the second aspect of the present invention, the determining module includes:
the first acquisition submodule is used for acquiring longitudinal acceleration trend data and the current longitudinal acceleration value of the automatic driving vehicle to be evaluated to obtain current state data; the judging submodule is used for judging whether the current state data meet preset conditions or not, the preset conditions are used for indicating that the longitudinal acceleration trend data are larger than a preset threshold value, and the current longitudinal acceleration value is smaller than the preset threshold value; the setting submodule is used for judging that the current state of the running vehicle to be evaluated is in a target state if the current state data meets the preset conditions, setting a comfort level grading contribution value to be 0 and obtaining a comfort level grading contribution variable, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after bending; and the second obtaining submodule is used for judging that the current state of the running vehicle to be evaluated is not in a target state if the current state data does not accord with the preset conditions, judging whether the current driving time of the running vehicle to be evaluated is the target state ending time or not, and obtaining a longitudinal acceleration variance normalization result according to the judged result to obtain a comfort level grading contribution variable.
Optionally, in a second implementation manner of the second aspect of the present invention, the second obtaining sub-module includes:
the judging unit is used for judging that the current state of the running vehicle to be evaluated is not in a target state if the current state data does not accord with preset conditions, and judging whether the current driving time of the running vehicle to be evaluated is the target state ending time or not to obtain a judgment result; the processing unit is used for acquiring longitudinal acceleration data in a preset time interval window, and performing variance normalization processing or zeroing and variance normalization processing on the longitudinal acceleration data in the preset time interval window according to the judgment result to obtain a longitudinal acceleration variance normalization result; and the determining unit is used for determining the normalization result of the longitudinal acceleration variance as a comfort level score contribution variable.
Optionally, in a third implementation manner of the second aspect of the present invention, the processing unit includes:
the acquisition subunit is used for acquiring longitudinal acceleration data in a preset time interval window; the statistical subunit is configured to calculate a variance of the longitudinal acceleration data within the preset time period window if the determination result indicates that the current driving time of the running vehicle to be evaluated is not the target state end time, so as to obtain a longitudinal acceleration variance within the preset time period window; the fitting subunit is used for carrying out normalization processing on the longitudinal acceleration variance in the preset time interval window to obtain a longitudinal acceleration variance parameter range value; and the removing subunit is used for carrying out normalization processing after the variance is zeroed on the longitudinal acceleration data in the preset time interval window to obtain a longitudinal acceleration variance normalization result if the judgment result indicates that the current driving time of the running vehicle to be evaluated is the target state end time.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the removing subunit is specifically configured to:
if the judgment result indicates that the current driving moment of the running vehicle to be evaluated is the target state ending moment, setting the longitudinal acceleration data in the preset time interval window to be 0 to obtain processed longitudinal acceleration data; and sequentially carrying out variance calculation and normalization processing on the processed longitudinal acceleration data to obtain a longitudinal acceleration variance normalization result.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the determining unit is specifically configured to:
if the current state data do not accord with the preset conditions, judging that the current state of the running vehicle to be evaluated is not in the target state, and acquiring the previous frame of state data of the current state of the running vehicle to be evaluated; judging whether the previous frame state data and the current longitudinal acceleration value meet a target condition, wherein the target condition is used for indicating that the previous frame state corresponding to the previous frame state data is a target state, and the current longitudinal acceleration value is larger than or equal to the preset threshold value; if the previous frame of state data and the current longitudinal acceleration value accord with a target condition, judging that the current driving moment of the running vehicle to be evaluated is the target state ending moment to obtain a judgment result; and if the previous frame of state data and the current longitudinal acceleration value do not accord with the target condition, judging that the current driving time of the running vehicle to be evaluated is not the target state end time, and obtaining a judgment result.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the first obtaining sub-module is specifically configured to:
acquiring longitudinal acceleration data of a preset time period window of an automatic driving vehicle to be evaluated, and writing the longitudinal acceleration data of the preset time period window into a queue; performing linear regression on the longitudinal acceleration data written into the queue to obtain longitudinal acceleration trend data; extracting a longitudinal acceleration value of the automatic driving vehicle to be evaluated at the current moment to obtain a current longitudinal acceleration value; and determining the longitudinal acceleration trend data and the current longitudinal acceleration value as current state data.
Optionally, in a seventh implementation manner of the second aspect of the present invention, the calculation module includes:
the calculation unit is used for calculating a longitudinal driving comfort degree score according to the comfort degree score contribution variable and the current longitudinal acceleration absolute value; the normalization unit is used for performing normalization processing on the target transverse acceleration variance to obtain a normalized target transverse acceleration variance; the fitting unit is used for fitting the normalized target transverse acceleration variance through a preset parameter to be fitted to obtain a transverse driving comfort degree value; and the summation unit is used for carrying out weighted summation on the longitudinal driving comfort degree score and the transverse driving comfort degree score and calculating a difference value with 1 to obtain a target driving comfort degree value.
Optionally, in an eighth implementation manner of the second aspect of the present invention, the computing unit is specifically configured to:
carrying out normalization processing on the current longitudinal acceleration absolute value to obtain a normalized current longitudinal acceleration absolute value; and carrying out weighted summation on the normalized current longitudinal acceleration absolute value and the comfort level score contribution variable to obtain a longitudinal driving comfort level score.
A third aspect of the present invention provides a computer apparatus comprising: a memory and at least one processor, the memory having stored therein a computer program; the at least one processor invokes the computer program in the memory to cause the computer device to perform the driving system evaluation method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute the above-described driving system evaluation method.
According to the technical scheme, the current state data of the running vehicle to be evaluated is obtained, whether the current state of the running vehicle to be evaluated is in a target state or not is judged according to the current state data, and a comfort level score contribution variable is obtained according to a judgment result, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after a vehicle turns out; acquiring a current longitudinal acceleration absolute value and a target transverse acceleration variance of the automatic driving vehicle to be evaluated; and calculating a target driving comfort value through the comfort degree grading contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance. In the embodiment of the invention, the driving state factors which do not influence the driving comfort level are taken into consideration, so that the problem that the comfort level score is contradictory to the actual body feeling is solved, and the evaluation accuracy of the driving comfort level is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a driving system evaluation method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of another embodiment of the driving system evaluation method according to the embodiment of the invention;
FIG. 3 is a schematic diagram of one embodiment of a longitudinal driving comfort score of a conventional comfort scoring system in an embodiment of the present invention;
FIG. 4 is a schematic diagram of an embodiment of a simulation result of a longitudinal driving comfort score of an existing comfort scoring system and a longitudinal driving comfort score of a solution of the present invention;
FIG. 5 is a schematic view of a driving system evaluation device according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of another embodiment of a driving system evaluation device according to an embodiment of the present invention;
FIG. 7 is a diagram of an embodiment of a computer device in an embodiment of the invention.
Detailed Description
The embodiment of the invention provides a driving system evaluation method and device, computer equipment and a storage medium, and improves the evaluation accuracy of driving comfort.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a detailed flow of an embodiment of the present invention is described below, with reference to fig. 1, an embodiment of a driving system evaluation method in an embodiment of the present invention includes:
101. the method comprises the steps of obtaining current state data of a running vehicle to be evaluated, judging whether the current state of the running vehicle to be evaluated is in a target state or not according to the current state data, and obtaining a comfort level score contribution variable according to a judgment result, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after bending.
It is to be understood that the execution subject of the present invention may be a driving system evaluation device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
The method includes the steps that a running vehicle to be evaluated can be an automatic driving vehicle, when a target state is that a current accelerator or a current brake is in a state without external force application, current state data of the running vehicle to be evaluated can be a change trend between a wheel speed of the automatic driving vehicle at the current moment and a wheel speed of a preset time before the current moment, the current state data of the running vehicle to be evaluated can also be a force value applied to the accelerator or the brake at the current moment, the current state data of the running vehicle to be evaluated can also be longitudinal acceleration trend data and a current longitudinal acceleration value of the automatic driving vehicle to be evaluated, no limitation is made to the situation, the state where the accelerator or the brake is not applied with external force comprises an accelerator release state and a brake release state, and the corresponding vehicle in the accelerator release scene is an automatic transmission vehicle without power recovery limitation; when the target state is a steering wheel return-to-normal state after a U-shaped bend (for example, a steering wheel quick return-to-normal state after a U-shaped bend), the current state data of the running vehicle to be evaluated may be steering wheel steering information such as a middle position, a rotating direction, a rotating angle and a rotating speed of the steering wheel, and the current state data of the running vehicle to be evaluated may also be longitudinal acceleration trend data and a current longitudinal acceleration value of the autonomous vehicle to be evaluated.
For example, taking an example that the target state is a current state in which an accelerator or a brake is in a state in which no external force is applied as an example, the server may obtain current state data of the vehicle to be evaluated by receiving current state data sent by an automatic driving system corresponding to the automatic driving vehicle; when the current state data is the change trend between the wheel speed of the automatic driving vehicle at the current moment and the wheel speed of preset time before the current moment, the server can judge whether the current accelerator of the driving vehicle to be evaluated is in a state without external force application or not by judging whether the change trend between the wheel speed of the automatic driving vehicle at the current moment and the wheel speed of the preset time before the current moment is always decelerated or not; when the current state data can also be the force value applied to the accelerator or the brake at the current moment, the server can judge whether the current accelerator or the brake of the running vehicle to be evaluated is in a state without external force application by judging whether the force value applied to the accelerator or the brake at the current moment is 0 or not.
If the judgment result indicates that the current state of the running vehicle to be evaluated is in the target state, setting the contributed comfort level score to be 0, and obtaining a comfort level score contribution variable; if the judged result indicates that the current state of the running vehicle to be evaluated is in the target state, acquiring a longitudinal acceleration variance normalization result to obtain a comfort level score contribution variable, or matching the current state data from a preset variable library to obtain a corresponding comfort level score contribution variable, wherein the variable library comprises interval numerical values which are obtained through tests and correspond to different current state data and have good influence on longitudinal comfort level score.
102. And acquiring the current longitudinal acceleration absolute value and the target transverse acceleration variance of the automatic driving vehicle to be evaluated.
The server can receive real-time acceleration data or a preset time window (for example, the current moment is t) sent by a mobile terminal or acceleration detection equipment (for example, an accelerometer) on the automatic driving vehicle to be evaluated 0 The preset time interval window is t 0 A short time window before), obtaining current acceleration data along the vehicle body from the real-time acceleration data or the acceleration data in a preset time window, and calculating the absolute value of the current acceleration data along the vehicle body to obtain the absolute value of the current longitudinal acceleration; and extracting acceleration data of a vertical vehicle body in a preset time period window from the real-time acceleration data or the acceleration data in the preset time period window to obtain target transverse acceleration data, and sequentially performing variance calculation on the target transverse acceleration data to obtain a target transverse acceleration variance.
It should be noted that, in the present invention, the longitudinal direction refers to a direction along the vehicle body, and the lateral direction refers to a direction perpendicular to the vehicle body.
103. And calculating a target driving comfort value through the comfort degree grading contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance.
After the server obtains the comfort degree grading contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance, longitudinal driving comfort degree scores are calculated through the comfort degree grading contribution variable and the current longitudinal acceleration absolute value, the longitudinal driving comfort degree scores refer to driving comfort degree scores of the driving vehicle to be evaluated in the direction along the vehicle body, transverse driving comfort degree scores are calculated through the target transverse acceleration variance, and the transverse driving comfort degree scores refer to driving comfort degree scores of the driving vehicle to be evaluated in the direction perpendicular to the vehicle body.
Optionally, the server may obtain a longitudinal driving comfort score by obtaining a longitudinal driving comfort score parameter, performing weighted summation on the comfort score contribution variable and the current longitudinal acceleration absolute value, and calculating a sum of the comfort score contribution variable and the longitudinal driving comfort; and normalizing the target transverse acceleration variance to obtain a transverse driving comfort degree scoring parameter, and calculating the normalized target transverse acceleration variance through the transverse driving comfort degree scoring parameter to obtain a transverse driving comfort degree score.
In the embodiment of the invention, the driving state factors which do not influence the driving comfort level are taken into consideration, so that the problem that the comfort level score is contradictory to the actual body feeling is solved, and the evaluation accuracy of the driving comfort level is improved.
Referring to fig. 2, another embodiment of the driving system evaluation method according to the embodiment of the present invention includes:
201. and acquiring longitudinal acceleration trend data and the current longitudinal acceleration value of the automatic driving vehicle to be evaluated to obtain current state data.
Specifically, the server acquires longitudinal acceleration data of a preset time period window of the automatic driving vehicle to be evaluated, and writes the longitudinal acceleration data of the preset time period window into a queue; performing linear regression on the longitudinal acceleration data written into the queue to obtain longitudinal acceleration trend data; extracting a longitudinal acceleration value of the automatic driving vehicle to be evaluated at the current moment to obtain a current longitudinal acceleration value; and determining the longitudinal acceleration trend data and the current longitudinal acceleration value as the current state data.
For example, the preset time window is the current time t 0 In the first 0.5s time window, the server obtains the current time t of the autonomous vehicle to be evaluated 0 Longitudinal acceleration data within the first 0.5s time window; the current time t 0 First 0.5s timeCopying the longitudinal acceleration data in the window into a queue, and then continuously updating the queue to maintain the whole calculation process, namely when calculating the comfort score (namely, longitudinal driving comfort score) of the next frame, filling the longitudinal acceleration of the next frame to the end of the queue, and simultaneously popping up the head data of the queue, wherein the longitudinal comfort score (namely, longitudinal driving comfort score) completely depends on the data of the queue, and the slope of acceleration is fitted by a least square method to represent the overall trend of the longitudinal acceleration in the time window (namely, a preset time window), namely, the longitudinal acceleration data written into the queue is subjected to least square fitting (namely, linear regression) to obtain the longitudinal acceleration trend data, optionally, the longitudinal acceleration data written into the queue can be fitted by a maximum likelihood estimation algorithm or a gradient descent algorithm, obtaining longitudinal acceleration trend data; and extracting the longitudinal acceleration value of the automatic driving vehicle to be evaluated at the current moment from the database to obtain the current longitudinal acceleration value, so as to obtain the current state data comprising the longitudinal acceleration trend data and the current longitudinal acceleration value.
202. And judging whether the current state data accords with a preset condition, wherein the preset condition is used for indicating that the longitudinal acceleration trend data is greater than a preset threshold value, and the current longitudinal acceleration value is smaller than the preset threshold value.
For example, if the longitudinal acceleration trend data is Lon _ acc _ jerk and the current longitudinal acceleration value is Lon _ acc, the server determines whether the current state data is Lon _ acc _ jerk > 0 and Lon _ acc <0, so as to determine whether the current state data meets the preset condition.
203. And if the current state data meet the preset conditions, judging that the current state of the running vehicle to be evaluated is in a target state, setting the comfort level score contribution value to be 0, and obtaining a comfort level score contribution variable, wherein the target state is that the current accelerator or brake is in a state without external force application or the steering wheel returns to a positive state after the vehicle turns out.
If the current state data meet the preset conditions, the server judges that the current state of the running vehicle to be evaluated is in the target state, the comfort level score contribution value is set to be 0, a comfort level score contribution variable is obtained, and at the moment, the comfort level score contributed by the acceleration variance is not calculated.
204. If the current state data do not accord with the preset conditions, judging that the current state of the running vehicle to be evaluated is not in the target state, judging whether the current driving time of the running vehicle to be evaluated is the target state ending time, and acquiring a longitudinal acceleration variance normalization result according to the judgment result to obtain a comfort level grading contribution variable.
If the current state data do not accord with the preset conditions, the server judges that the current state of the running vehicle to be evaluated is not in a target state; and optionally, judging whether the current driving time of the running vehicle to be evaluated is the target state end time according to the previous frame state and the current acceleration of the running vehicle to be evaluated. The normalization result of the variance of the longitudinal acceleration may be a result of normalization processing of the variance of the longitudinal acceleration data in a preset time period window, or may be a result of preprocessing the variance of the longitudinal acceleration data in the preset time period window to obtain a preprocessed variance, and normalizing the preprocessed variance, where the preprocessing may be acceleration zeroing processing.
Optionally, if the current state data does not meet the preset conditions, determining that the current state of the running vehicle to be evaluated is not in the target state, and determining whether the current driving time of the running vehicle to be evaluated is the target state end time to obtain a determination result; acquiring longitudinal acceleration data in a preset time interval window, and performing variance normalization processing or zeroing and variance normalization processing on the longitudinal acceleration data in the preset time interval window according to a judgment result to obtain a longitudinal acceleration variance normalization result; and determining the normalization result of the longitudinal acceleration variance as a comfort degree score contribution variable.
Specifically, if the current state data does not meet the preset conditions, the server judges that the current state of the running vehicle to be evaluated is not in the target state, and acquires the previous frame state data of the current state of the running vehicle to be evaluated; judging whether the previous frame state data and the current longitudinal acceleration value meet a target condition, wherein the target condition is used for indicating that the previous frame state corresponding to the previous frame state data is a target state, and the current longitudinal acceleration value is larger than or equal to a preset threshold value; if the previous frame of state data and the current longitudinal acceleration value accord with the target condition, judging that the current driving time of the running vehicle to be evaluated is the target state ending time to obtain a judgment result; and if the previous frame of state data and the current longitudinal acceleration value do not accord with the target condition, judging that the current driving time of the running vehicle to be evaluated is not the target state ending time, and obtaining a judgment result.
And judging whether the current driving time of the running vehicle to be evaluated is the target state ending time or not according to the previous frame of state data and the current longitudinal acceleration value to obtain a judgment result. The execution process for determining the previous frame status as the target status according to the previous frame status data is similar to the execution process of steps 101 and steps 201 and 204, and is not repeated herein.
Specifically, the server acquires longitudinal acceleration data in a preset time period window; if the judgment result indicates that the current driving moment of the running vehicle to be evaluated is not the target state ending moment, calculating the variance of the longitudinal acceleration data in the preset time period window to obtain the longitudinal acceleration variance in the preset time period window; normalizing the longitudinal acceleration variance in a preset time interval window to obtain a longitudinal acceleration variance normalization result; and if the judgment result indicates that the current driving time of the running vehicle to be evaluated is the target state ending time, performing normalization processing after the variance is zeroed on the longitudinal acceleration data in the preset time interval window to obtain a longitudinal acceleration variance normalization result.
Optionally, if the determination result indicates that the current driving time of the running vehicle to be evaluated is the target state end time, the server performs normalization processing after the variance is zeroed on the longitudinal acceleration data in the preset time interval window to obtain a longitudinal acceleration variance normalization result, which specifically includes: if the judgment result indicates that the current driving time of the running vehicle to be evaluated is the target state ending time, setting the longitudinal acceleration data in the preset time interval window to be 0, and obtaining the processed longitudinal acceleration data; and sequentially carrying out variance calculation and normalization processing on the processed longitudinal acceleration data to obtain a longitudinal acceleration variance normalization result.
And when the judgment result indicates that the current driving moment of the running vehicle to be evaluated is the target state ending moment, the influence on the comfort level score at the subsequent moment is eliminated by setting the longitudinal acceleration data in the preset time interval window to be 0.
205. And acquiring the current longitudinal acceleration absolute value and the target transverse acceleration variance of the automatic driving vehicle to be evaluated.
The process of step 205 is similar to the process of step 102, and is not described herein again.
206. And calculating a target driving comfort value through the comfort degree grading contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance.
Specifically, the server calculates a longitudinal driving comfort score according to a comfort score contribution variable and a current longitudinal acceleration absolute value; carrying out normalization processing on the target transverse acceleration variance to obtain a normalized target transverse acceleration variance; fitting the normalized target transverse acceleration variance through a preset parameter to be fitted to obtain a transverse driving comfort value; and carrying out weighted summation on the longitudinal driving comfort degree score and the transverse driving comfort degree score, and calculating a difference value with 1 to obtain a target driving comfort degree value.
Optionally, the server calculates a longitudinal driving comfort score through the comfort score contribution variable and the current longitudinal acceleration absolute value, and specifically includes: normalizing the current longitudinal acceleration absolute value to obtain a normalized current longitudinal acceleration absolute value; and carrying out weighted summation on the normalized current longitudinal acceleration absolute value and the comfort level score contribution variable to obtain a longitudinal driving comfort level score. And performing parameter fitting on the current longitudinal acceleration absolute value through a sigmod function, so that an intermediate result is compressed into a determined parameter space to realize normalization processing, and obtaining the normalized current longitudinal acceleration absolute value.
Performing parameter fitting on the target transverse acceleration variance through a sigmod function, so that an intermediate result is compressed into a determined parameter space to realize normalization processing, and obtaining a normalized target transverse acceleration variance; and calculating the product between the first parameter (or the second parameter) and the normalized target lateral acceleration variance through preset parameters to be fitted, wherein the parameters to be fitted comprise the first parameter and the second parameter, and calculating the product and the second parameter (or the first parameter) to obtain a lateral driving comfort degree value so as to realize the fitting treatment of the normalized target lateral acceleration variance.
And carrying out weighted summation on the longitudinal driving comfort degree score and the transverse driving comfort degree score to obtain a weighted sum value, calculating a difference value between the weighted sum value and 1 to obtain a target driving comfort degree value, wherein the target driving comfort degree value is an interval [ -1,1], and the target driving comfort degree value is the maximum and indicates that the driving is more comfortable.
Please refer to fig. 3 and 4; in fig. 3, an s1 solid line represents the filtered longitudinal acceleration data within the preset time period window, an s2 solid line represents a slope of the filtered longitudinal acceleration data within the preset time period window, wherein the data acquired in the field (i.e., the longitudinal acceleration data within the preset time period window) may have noise, unreal, and other factors, and thus, the data acquired during data analysis may be filtered, an s3 dotted line represents that when the longitudinal acceleration data within the preset time period window is 0, comparison of the data is facilitated, an s4 dotted line represents a comfort level score obtained based on an acceleration variance within the preset time period window in an existing comfort level scoring system, an X1 area represents a loose-braking state of the running vehicle to be evaluated, and an X2 area represents that the current driving time of the running vehicle to be evaluated is a loose-braking ending time; the solid line s5 in fig. 4 represents the filtered longitudinal acceleration data within the preset time period window, the solid line s6 represents the longitudinal driving comfort score of the existing comfort scoring system, and the dashed line s7 represents the longitudinal driving comfort score of the present invention. Fig. 3 shows the longitudinal driving comfort score of the existing comfort scoring system, as can be seen from fig. 3, in the scenario of a loose braking state of the running vehicle to be evaluated, the acceleration in the existing comfort scoring system is rapidly reduced, so that the acceleration variance in the time window w (i.e. the preset time period window) is very large, thereby resulting in a very low longitudinal driving comfort score; fig. 4 shows simulation results of the longitudinal driving comfort score of the existing comfort scoring system and the longitudinal driving comfort score of the scheme of the present invention, as can be seen from fig. 4, the scheme of the present invention only shows a behavior of a comfort score reduction for one braking release behavior, while the existing comfort scoring system can give a two-time score reduction behavior, wherein one is caused by braking release; in conclusion, the driving system evaluation method can solve the problem, and the problem that the comfort level score is contradictory to the actual feeling is solved by considering the driving state factors which do not affect the driving comfort level, so that the evaluation accuracy of the driving comfort level is improved.
In the embodiment of the invention, the driving state factors which do not influence the driving comfort level are taken into consideration, so that the problem that the comfort level score is contradictory to the actual body feeling is solved, and the evaluation accuracy of the driving comfort level is improved.
With reference to fig. 5, the driving system evaluation method in the embodiment of the present invention is described above, and a driving system evaluation device in the embodiment of the present invention is described below, where an embodiment of the driving system evaluation device in the embodiment of the present invention includes:
the judging module 51000 is configured to obtain current state data of a running vehicle to be evaluated, judge whether the current state of the running vehicle to be evaluated is in a target state according to the current state data, and obtain a comfort level score contribution variable according to a judgment result, where the target state is that a current accelerator or brake is in a state where no external force is applied or a steering wheel returns to a positive state after a curve is formed;
an obtaining module 52000, configured to obtain a current longitudinal acceleration absolute value and a target lateral acceleration variance of the autonomous vehicle to be evaluated;
the calculating module 53000 is configured to calculate a target driving comfort value according to the comfort score contribution variable, the current absolute value of the longitudinal acceleration, and the target variance of the lateral acceleration.
The function implementation of each module in the driving system evaluation device corresponds to each step in the driving system evaluation method embodiment, and the function and implementation process are not described in detail herein.
In the embodiment of the invention, the driving state factors which do not influence the driving comfort are taken into consideration, so that the problem that the comfort score is contradictory to the actual body feeling is solved, and the evaluation accuracy of the driving comfort is improved.
Referring to fig. 6, another embodiment of the driving system evaluation apparatus according to the embodiment of the present invention includes:
the judging module 51000 is configured to obtain current state data of a running vehicle to be evaluated, judge whether the current state of the running vehicle to be evaluated is in a target state according to the current state data, and obtain a comfort level score contribution variable according to a judgment result, where the target state is that a current accelerator or brake is in a state where no external force is applied or a steering wheel returns to a positive state after a curve is formed;
the judging module 51000 specifically includes:
the first obtaining sub-module 51100 is used for obtaining longitudinal acceleration trend data and a current longitudinal acceleration value of the autonomous vehicle to be evaluated to obtain current state data;
the judging submodule 51200 is configured to judge whether the current state data meets a preset condition, where the preset condition is used to indicate that the longitudinal acceleration trend data is greater than a preset threshold, and the current longitudinal acceleration value is smaller than the preset threshold;
the setting submodule 51300 is used for judging that the current state of the running vehicle to be evaluated is in a target state if the current state data meets the preset conditions, and setting the comfort level scoring contribution value to be 0 to obtain a comfort level scoring contribution variable, wherein the target state is that the current accelerator or brake is in a state without external force application or the steering wheel returns to a positive state after bending;
the second obtaining submodule 51400 is configured to, if the current state data does not meet the preset condition, determine that the current state of the running vehicle to be evaluated is not in the target state, determine whether the current driving time of the running vehicle to be evaluated is the target state end time, and obtain a longitudinal acceleration variance normalization result according to a determination result to obtain a comfort level score contribution variable;
an obtaining module 52000, configured to obtain a current longitudinal acceleration absolute value and a target lateral acceleration variance of the autonomous vehicle to be evaluated;
the calculating module 53000 is configured to calculate a target driving comfort value according to the comfort score contribution variable, the current absolute value of the longitudinal acceleration, and the target variance of the lateral acceleration.
Optionally, the second obtaining sub-module 51400 includes:
a determining unit 51410, configured to determine that the current state of the running vehicle to be evaluated is not in the target state if the current state data does not meet the preset condition, and determine whether the current driving time of the running vehicle to be evaluated is the target state end time, so as to obtain a determination result;
the processing unit 51420 is configured to obtain longitudinal acceleration data within a preset time period window, and perform variance normalization processing or zeroing and variance normalization processing on the longitudinal acceleration data within the preset time period window according to the determination result to obtain a longitudinal acceleration variance normalization result;
a determining unit 51430 is configured to determine the normalized result of the longitudinal acceleration variance as the comfort score contribution variable.
Optionally, the processing unit 51420 includes:
an acquiring subunit 51421, configured to acquire longitudinal acceleration data within a preset time period window;
a statistics subunit 51422, configured to, if the determination result indicates that the current driving time of the running vehicle to be evaluated is not the target state end time, calculate a variance of the longitudinal acceleration data within a preset time period window, to obtain a longitudinal acceleration variance within the preset time period window;
the fitting subunit 51423 is configured to perform normalization processing on the longitudinal acceleration variance within the preset time period window to obtain a parameter range value of the longitudinal acceleration variance;
and a removal subunit 51424, configured to, if the determination result indicates that the current driving time of the running vehicle to be evaluated is the target state end time, perform normalization processing after the variance is zeroed on the longitudinal acceleration data within the preset time period window, and obtain a longitudinal acceleration variance normalization result.
Optionally, the removal subunit 51424 may be further specifically configured to:
if the judgment result indicates that the current driving time of the running vehicle to be evaluated is the target state ending time, setting the longitudinal acceleration data in the preset time interval window to be 0, and obtaining the processed longitudinal acceleration data;
and sequentially carrying out variance calculation and normalization processing on the processed longitudinal acceleration data to obtain a longitudinal acceleration variance normalization result.
Optionally, the determining unit 51410 may be further specifically configured to:
if the current state data do not accord with the preset conditions, judging that the current state of the running vehicle to be evaluated is not in the target state, and acquiring the previous frame state data of the current state of the running vehicle to be evaluated;
judging whether the previous frame state data and the current longitudinal acceleration value meet a target condition, wherein the target condition is used for indicating that the previous frame state corresponding to the previous frame state data is a target state, and the current longitudinal acceleration value is larger than or equal to a preset threshold value;
if the previous frame of state data and the current longitudinal acceleration value accord with the target condition, judging that the current driving time of the running vehicle to be evaluated is the target state ending time to obtain a judgment result;
and if the previous frame of state data and the current longitudinal acceleration value do not accord with the target condition, judging that the current driving time of the running vehicle to be evaluated is not the target state ending time, and obtaining a judgment result.
Optionally, the first obtaining sub-module 51100 may be further specifically configured to:
acquiring longitudinal acceleration data of a preset time period window of the automatic driving vehicle to be evaluated, and writing the longitudinal acceleration data of the preset time period window into a queue;
performing linear regression on the longitudinal acceleration data written into the queue to obtain longitudinal acceleration trend data;
extracting a longitudinal acceleration value of the automatic driving vehicle to be evaluated at the current moment to obtain a current longitudinal acceleration value;
and determining the longitudinal acceleration trend data and the current longitudinal acceleration value as the current state data.
Optionally, the computing module 53000 includes:
the calculating unit 53100 is used for calculating a longitudinal driving comfort score through the comfort score contribution variable and the current longitudinal acceleration absolute value;
the normalization unit 53200 is configured to perform normalization processing on the target lateral acceleration variance to obtain a normalized target lateral acceleration variance;
the fitting unit 53300 is configured to perform fitting processing on the normalized target lateral acceleration variance through a preset parameter to be fitted to obtain a lateral driving comfort score;
and the summing unit 53400 is configured to perform weighted summation on the longitudinal driving comfort score and the lateral driving comfort score and calculate a difference value from 1 to obtain a target driving comfort value.
Optionally, the computing unit 53100 may further be specifically configured to:
normalizing the current longitudinal acceleration absolute value to obtain a normalized current longitudinal acceleration absolute value;
and carrying out weighted summation on the normalized current longitudinal acceleration absolute value and the comfort level score contribution variable to obtain a longitudinal driving comfort level score.
The function implementation of each module and each unit in the driving system evaluation device corresponds to each step in the driving system evaluation method embodiment, and the function and implementation process thereof are not described in detail herein.
In the embodiment of the invention, the driving state factors which do not influence the driving comfort level are taken into consideration, so that the problem that the comfort level score is contradictory to the actual body feeling is solved, and the evaluation accuracy of the driving comfort level is improved.
Fig. 5 and 6 describe the driving system evaluation device in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the computer device in the embodiment of the present invention is described in detail from the perspective of the hardware processing.
Fig. 7 is a schematic structural diagram of a computer device 700 according to an embodiment of the present invention, where the computer device 700 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 710 (e.g., one or more processors) and a memory 720, one or more storage media 730 (e.g., one or more mass storage devices) for storing applications 733 or data 732. Memory 720 and storage medium 730 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a sequence of computer program operations in the computer device 700. Still further, the processor 710 may be configured to communicate with the storage medium 730 to execute a series of computer program operations in the storage medium 730 on the computer device 700.
The computer device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input-output interfaces 760, and/or one or more operating systems 731, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and so forth. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 7 does not constitute a limitation of computer devices, and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.
The present invention also provides a computer apparatus comprising: a memory and at least one processor, the memory having stored therein a computer program, the memory and the at least one processor being interconnected by a line; the at least one processor invokes a computer program in the memory to cause the computer device to perform the steps of the driving system assessment method described above. The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, which may also be a volatile computer-readable storage medium, having stored thereon a computer program which, when run on a computer, causes the computer to perform the steps of the driving system assessment method.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several computer programs to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (11)
1. A driving system evaluation method, characterized by comprising:
acquiring current state data of an automatic driving vehicle to be evaluated, judging whether the current state of the automatic driving vehicle to be evaluated is in a target state or not according to the current state data, and acquiring a comfort level score contribution variable according to a judgment result, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after bending;
the method comprises the steps of obtaining current state data of an automatic driving vehicle to be evaluated, judging whether the current state of the automatic driving vehicle to be evaluated is in a target state or not according to the current state data, obtaining a comfort level score contribution variable according to a judgment result, and enabling the target state to be a state that a current accelerator or a current brake is not applied by external force or a steering wheel returns to a positive state after the vehicle turns out of a bend, and comprises the following steps:
acquiring longitudinal acceleration trend data and a current longitudinal acceleration value of the automatic driving vehicle to be evaluated to obtain current state data;
judging whether the current state data meet preset conditions or not, wherein the preset conditions are used for indicating that the longitudinal acceleration trend data are larger than a preset threshold value, and the current longitudinal acceleration value is smaller than the preset threshold value;
if the current state data meet preset conditions, judging that the current state of the to-be-evaluated automatic driving vehicle is in a target state, setting a comfort level score contribution value to be 0, and obtaining a comfort level score contribution variable, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after bending;
if the current state data do not meet the preset conditions, judging that the current state of the automatic driving vehicle to be evaluated is not in a target state, judging whether the current driving time of the automatic driving vehicle to be evaluated is the target state ending time, and acquiring a longitudinal acceleration variance normalization result according to the judgment result to obtain a comfort level grading contribution variable;
acquiring a current longitudinal acceleration absolute value and a target transverse acceleration variance of the automatic driving vehicle to be evaluated;
and calculating a target driving comfort value through the comfort degree grading contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance.
2. The driving system evaluation method according to claim 1, wherein if the current state data does not meet a preset condition, it is determined that the current state of the autonomous vehicle to be evaluated is not in a target state, it is determined whether a current driving time of the autonomous vehicle to be evaluated is a target state end time, and a longitudinal acceleration variance normalization result is obtained according to a result of the determination, so as to obtain a comfort level score contribution variable, including:
if the current state data do not meet the preset conditions, judging that the current state of the automatic driving vehicle to be evaluated is not in the target state, and judging whether the current driving time of the automatic driving vehicle to be evaluated is the target state ending time or not to obtain a judgment result;
acquiring longitudinal acceleration data in a preset time interval window, and performing variance normalization processing or zeroing and variance normalization processing on the longitudinal acceleration data in the preset time interval window according to the judgment result to obtain a longitudinal acceleration variance normalization result;
and determining the result of the normalization of the longitudinal acceleration variance as a comfort level score contribution variable.
3. The driving system evaluation method according to claim 2, wherein the obtaining longitudinal acceleration data within a preset time period window and performing variance normalization processing or zeroing and variance normalization processing on the longitudinal acceleration data within the preset time period window according to the determination result to obtain a longitudinal acceleration variance normalization result comprises:
acquiring longitudinal acceleration data in a preset time period window;
if the judgment result indicates that the current driving moment of the automatic driving vehicle to be evaluated is not the target state ending moment, calculating the variance of the longitudinal acceleration data in the preset time period window to obtain the longitudinal acceleration variance in the preset time period window;
normalizing the longitudinal acceleration variance in the preset time interval window to obtain a longitudinal acceleration variance normalization result;
and if the judgment result indicates that the current driving moment of the automatic driving vehicle to be evaluated is the target state ending moment, performing normalization processing after the variance is zeroed on the longitudinal acceleration data in the preset time period window to obtain a longitudinal acceleration variance normalization result.
4. The driving system evaluation method of claim 3, wherein if the determination result indicates that the current driving time of the autonomous vehicle to be evaluated is the target state end time, performing normalization processing after the variance is zeroed on the longitudinal acceleration data within the preset time period window to obtain a longitudinal acceleration variance normalization result, comprising:
if the judgment result indicates that the current driving time of the automatic driving vehicle to be evaluated is the target state ending time, setting the longitudinal acceleration data in the preset time period window to be 0, and obtaining the processed longitudinal acceleration data;
and sequentially carrying out variance calculation and normalization processing on the processed longitudinal acceleration data to obtain a longitudinal acceleration variance normalization result.
5. The driving system evaluation method according to claim 2, wherein if the current state data does not meet a preset condition, determining that the current state of the autonomous vehicle to be evaluated is not in a target state, and determining whether the current driving time of the autonomous vehicle to be evaluated is a target state end time, to obtain a determination result, includes:
if the current state data do not accord with the preset conditions, judging that the current state of the automatic driving vehicle to be evaluated is not in the target state, and acquiring the previous frame of state data of the current state of the automatic driving vehicle to be evaluated;
judging whether the previous frame state data and the current longitudinal acceleration value meet a target condition, wherein the target condition is used for indicating that the previous frame state corresponding to the previous frame state data is a target state, and the current longitudinal acceleration value is larger than or equal to the preset threshold value;
if the previous frame of state data and the current longitudinal acceleration value meet the target condition, judging that the current driving time of the automatic driving vehicle to be evaluated is the target state ending time, and obtaining a judgment result;
and if the previous frame of state data and the current longitudinal acceleration value do not accord with the target condition, judging that the current driving time of the automatic driving vehicle to be evaluated is not the target state ending time, and obtaining a judgment result.
6. The driving system evaluation method of claim 1, wherein obtaining longitudinal acceleration trend data and a current longitudinal acceleration value of the autonomous vehicle under evaluation to obtain current status data comprises:
acquiring longitudinal acceleration data of a preset time period window of the automatic driving vehicle to be evaluated, and writing the longitudinal acceleration data of the preset time period window into a queue;
performing linear regression on the longitudinal acceleration data written into the queue to obtain longitudinal acceleration trend data;
extracting a longitudinal acceleration value of the automatic driving vehicle to be evaluated at the current moment to obtain a current longitudinal acceleration value;
and determining the longitudinal acceleration trend data and the current longitudinal acceleration value as current state data.
7. The driving system evaluation method according to any one of claims 1 to 6, wherein the calculating a target driving comfort value from the comfort score contribution variable, the current absolute value of longitudinal acceleration, and the target variance of lateral acceleration comprises:
calculating a longitudinal driving comfort score according to the comfort score contribution variable and the current longitudinal acceleration absolute value;
normalizing the target lateral acceleration variance to obtain a normalized target lateral acceleration variance;
fitting the normalized target transverse acceleration variance through a preset parameter to be fitted to obtain a transverse driving comfort value;
and carrying out weighted summation on the longitudinal driving comfort degree score and the transverse driving comfort degree score, and calculating a difference value with 1 to obtain a target driving comfort degree value.
8. The driving system evaluation method of claim 7, wherein the calculating a longitudinal driving comfort score from the comfort score contribution variable and the current longitudinal acceleration absolute value comprises:
carrying out normalization processing on the current longitudinal acceleration absolute value to obtain a normalized current longitudinal acceleration absolute value;
and carrying out weighted summation on the normalized current longitudinal acceleration absolute value and the comfort level score contribution variable to obtain a longitudinal driving comfort level score.
9. A driving system evaluation device characterized by comprising:
the judging module is used for acquiring current state data of the automatic driving vehicle to be evaluated, judging whether the current state of the automatic driving vehicle to be evaluated is in a target state or not according to the current state data, and acquiring a comfort level score contribution variable according to a judgment result, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returning state after the current accelerator or brake is bent;
the method comprises the steps of obtaining current state data of an automatic driving vehicle to be evaluated, judging whether the current state of the automatic driving vehicle to be evaluated is in a target state or not through the current state data, and obtaining a comfort level score contribution variable according to a judgment result, wherein the target state is that a current accelerator or a brake is in a state without external force application or a steering wheel return-to-positive state after the vehicle turns out, and the method comprises the following steps:
acquiring longitudinal acceleration trend data and a current longitudinal acceleration value of the automatic driving vehicle to be evaluated to obtain current state data;
judging whether the current state data meet preset conditions or not, wherein the preset conditions are used for indicating that the longitudinal acceleration trend data are larger than a preset threshold value, and the current longitudinal acceleration value is smaller than the preset threshold value;
if the current state data meet preset conditions, judging that the current state of the to-be-evaluated automatic driving vehicle is in a target state, setting a comfort level score contribution value to be 0, and obtaining a comfort level score contribution variable, wherein the target state is that a current accelerator or brake is in a state without external force application or a steering wheel returns to a positive state after bending;
if the current state data do not meet the preset conditions, judging that the current state of the automatic driving vehicle to be evaluated is not in a target state, judging whether the current driving time of the automatic driving vehicle to be evaluated is the target state ending time, and acquiring a longitudinal acceleration variance normalization result according to the judgment result to obtain a comfort level grading contribution variable;
the acquisition module is used for acquiring the current longitudinal acceleration absolute value and the target transverse acceleration variance of the automatic driving vehicle to be evaluated;
and the calculation module is used for calculating a target driving comfort value through the comfort level score contribution variable, the current longitudinal acceleration absolute value and the target transverse acceleration variance.
10. A computer device, characterized in that the computer device comprises: a memory and at least one processor, the memory having stored therein a computer program;
the at least one processor invokes the computer program in the memory to cause the computer device to perform the driving system assessment method of any one of claims 1-8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a driving system assessment method according to any one of claims 1 to 8.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111085627 | 2021-09-16 | ||
CN2021110856278 | 2021-09-16 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113918891A CN113918891A (en) | 2022-01-11 |
CN113918891B true CN113918891B (en) | 2022-08-23 |
Family
ID=79248333
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111439497.3A Active CN113918891B (en) | 2021-09-16 | 2021-11-30 | Driving system evaluation method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113918891B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110001653A (en) * | 2019-03-29 | 2019-07-12 | 腾讯科技(深圳)有限公司 | A kind of driving behavior appraisal procedure, server and computer-readable medium |
CN110588661A (en) * | 2018-06-13 | 2019-12-20 | 丰田自动车株式会社 | Driving evaluation device, driving evaluation method, and non-transitory readable recording medium storing driving evaluation program |
CN110949370A (en) * | 2019-03-18 | 2020-04-03 | 长城汽车股份有限公司 | Safety monitoring method and system for automatic driving vehicle and motion control system |
CN113071497A (en) * | 2021-04-28 | 2021-07-06 | 中国第一汽车股份有限公司 | Driving scene judging method, device, equipment and storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7040307B2 (en) * | 2018-06-13 | 2022-03-23 | トヨタ自動車株式会社 | A recording medium that records an operation evaluation device, an operation evaluation method, and an operation evaluation program. |
-
2021
- 2021-11-30 CN CN202111439497.3A patent/CN113918891B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110588661A (en) * | 2018-06-13 | 2019-12-20 | 丰田自动车株式会社 | Driving evaluation device, driving evaluation method, and non-transitory readable recording medium storing driving evaluation program |
CN110949370A (en) * | 2019-03-18 | 2020-04-03 | 长城汽车股份有限公司 | Safety monitoring method and system for automatic driving vehicle and motion control system |
CN110001653A (en) * | 2019-03-29 | 2019-07-12 | 腾讯科技(深圳)有限公司 | A kind of driving behavior appraisal procedure, server and computer-readable medium |
CN113071497A (en) * | 2021-04-28 | 2021-07-06 | 中国第一汽车股份有限公司 | Driving scene judging method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN113918891A (en) | 2022-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108814618B (en) | Motion state identification method and device and terminal equipment | |
CN110807436A (en) | Dangerous driving behavior recognition and dangerous event prediction method, device and storage medium | |
CN110263628B (en) | Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium | |
CN114491383B (en) | Abnormal data processing method and system for bridge monitoring | |
CN112214934B (en) | Suspension system life prediction method based on multiple sensors and related device | |
CN113918891B (en) | Driving system evaluation method and device, computer equipment and storage medium | |
CN110415710B (en) | Parameter adjusting method, device, equipment and medium for vehicle-mounted voice interaction system | |
CN111340074A (en) | Driver braking intention identification method based on improved RBF neural network | |
JP2005216202A (en) | Device and method for predicting future value | |
CN112462759B (en) | Evaluation method, system and computer storage medium of rule control algorithm | |
CN113401130A (en) | Driving style recognition method and device based on environmental information and storage medium | |
CN113658426B (en) | Vehicle accident identification method and device | |
CN112163521A (en) | Vehicle driving behavior identification method, device and equipment | |
CN112781556A (en) | Well lid transaction monitoring method and device based on multi-data fusion filtering | |
CN114564110B (en) | Driving learning ability detection method and system based on brain electrical data | |
CN116910552A (en) | Vehicle fault detection method and device, vehicle-mounted terminal and storage medium | |
CN115083154A (en) | Method and device for detecting vehicle driving event, electronic equipment and medium | |
CN114783052A (en) | Tumbling identification method, device, equipment and storage medium based on human body multiple characteristics | |
CN113044046B (en) | Driver style recognition method, system, electronic device and readable storage medium | |
CN114707354A (en) | Method and system for extracting vehicle interaction scene data and computer equipment | |
CN114940177A (en) | Evaluation method, device, equipment and storage medium for somatosensory comfort of driver | |
CN113878575B (en) | Method and device for processing bucket passing of wheel type chassis, computer equipment and storage medium | |
CN115127545B (en) | Motion state identification method and device, electronic equipment and storage medium | |
CN109740470B (en) | Target tracking method, computer device, and computer-readable storage medium | |
CN114896547A (en) | Evaluation method, device, equipment and storage medium for somatosensory comfort of driver |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |