CN114676211A - Method, device and equipment for generating automobile driving data and storage medium - Google Patents
Method, device and equipment for generating automobile driving data and storage medium Download PDFInfo
- Publication number
- CN114676211A CN114676211A CN202210228016.2A CN202210228016A CN114676211A CN 114676211 A CN114676211 A CN 114676211A CN 202210228016 A CN202210228016 A CN 202210228016A CN 114676211 A CN114676211 A CN 114676211A
- Authority
- CN
- China
- Prior art keywords
- road
- data
- kinematic
- working condition
- segments
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000006073 displacement reaction Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 22
- 230000007704 transition Effects 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 18
- 230000001133 acceleration Effects 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 239000012634 fragment Substances 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000003042 antagnostic effect Effects 0.000 description 4
- 238000007621 cluster analysis Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013028 emission testing Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Remote Sensing (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for generating automobile driving data, wherein the method comprises the following steps: acquiring original GPS data of an automobile on each road section and road length of the road section; clustering after dividing the kinematics segments, dividing the kinematics segments into a plurality of working condition types, and fitting the kinematics segments of each working condition type into a function of the road speed and the time by combining the corresponding road speed; dividing the road section into a plurality of road conditions, and calculating the displacement generated by the kinematic segments of various working condition types; inputting the road length, the road condition and the displacement into a generation countermeasure network for training, and obtaining a position sequence through the trained generation countermeasure network; and performing transition processing on the position sequence to obtain the driving data of the automobile under the specific road condition. According to the method and the device, the automobile driving data similar to the driving condition of the automobile on the real road can be generated according to the road length, the road speed and the road condition, and the authenticity and the accuracy of the generated data are effectively improved.
Description
Technical Field
The invention relates to the technical field of automobile data processing, in particular to a method, a device, equipment and a storage medium for generating automobile driving data.
Background
The current technology in the field of automobile driving data generation mainly focuses on the technology of generating automobile driving condition data. The automobile running working condition refers to the working condition of the automobile in the transportation running process, and mainly comprises the following steps according to the motion form of the automobile: starting, accelerating, constant speed, decelerating, turning, ascending and descending, parking and other running conditions. The Driving Cycle (also called as a vehicle test Cycle) describes a speed-time curve of vehicle Driving, and can embody the kinematic characteristics of vehicle road Driving.
The automobile running condition data constructed in the prior art is mainly used for testing various aspects of performances of automobiles, is an important and common basic technology for the automobile industry, is the basis of an automobile energy consumption/emission testing method and a limit value standard, is also a main reference for calibrating and optimizing various performance indexes of the automobiles, and the data of a test result is also oriented to consumers and published in the market. In fact, however, the vehicle performance data obtained under such vehicle driving condition tests deviate from the actual performance of the vehicle. Because the test process is only carried out for some typical driving situations, the data generated based on the test process is mainly formed by simply splicing typical multiple motion segments, and the details of the data can be generated according to a single condition. However, only a single feature is used for describing the driving scene, so that only a single feature is focused in the data processing, data classification and data learning processes, and the generated driving condition data is far from the data of driving of the automobile on a real road.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide a method, an apparatus, a device and a storage medium for generating automobile driving data, which can generate automobile driving data similar to the driving condition of an automobile on a real road according to the road length, the road speed and the road condition, thereby effectively improving the authenticity and the accuracy of the generated data.
In order to achieve the above object, an embodiment of the present invention provides a method for generating vehicle driving data, including:
acquiring original GPS data of the automobile running on each road section and the road length of each road section;
dividing the original GPS data into a plurality of kinematic segments;
clustering analysis is carried out on the plurality of kinematic segments, the plurality of kinematic segments are divided into a plurality of working condition types, and the kinematic segments of each working condition type are fitted into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type;
dividing the road section into a plurality of road conditions according to the proportion of the kinematic segments of various working condition types in each road section data, and calculating the displacement generated by the kinematic segments of various working condition types in each road section data;
Training a generated confrontation network constructed by the road length, the road condition and the displacement input, and obtaining position sequences of various working condition types through the trained generated confrontation network;
and performing transition processing on the kinematic segments in the position sequence to obtain driving data of the automobile under specific road conditions.
As an improvement of the above scheme, the dividing of the kinematic segment of the original GPS data specifically includes:
and extracting all extreme points in the original GPS data, and dividing the kinematics segments according to the extreme points.
As an improvement of the above solution, after the dividing the original GPS data into a plurality of kinematic segments, the method further includes:
calculating the acceleration of each kinematic segment, and judging whether abnormal acceleration exists or not;
and if the abnormal acceleration exists, removing the kinematic segment corresponding to the abnormal acceleration.
As an improvement of the above scheme, the clustering analysis of the plurality of kinematic segments, the dividing of the plurality of kinematic segments into a plurality of operating condition types, and the fitting of the kinematic segments of each operating condition type into a function of a road speed with respect to time in combination with a road speed corresponding to each operating condition type specifically includes:
Clustering analysis is carried out on the plurality of kinematic segments by adopting a K-means algorithm, and the plurality of kinematic segments are divided into a plurality of working condition types; the working condition types at least comprise constant-speed driving, overtaking, avoiding and traffic lights;
selecting a classification central point of each working condition type and N points closest to the classification central point, and fitting the kinematic fragments of each working condition type into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type; wherein N is a positive integer.
As an improvement of the above scheme, the dividing the road segment into a plurality of road conditions according to the proportion of the kinematic segments of various working condition types in each road segment data, and calculating the displacement generated by the kinematic segments of various working condition types in each road segment data specifically includes:
calculating the proportion of the kinematic segments of various working condition types in each road section data;
dividing the road sections into a plurality of road conditions according to the proportion by adopting a K-means algorithm; wherein the road conditions at least comprise smooth, slow running, congestion and severe congestion;
and calculating the displacement generated by the kinematic segments of various working condition types in each road section data.
As an improvement of the above scheme, the training method for generating the countermeasure network specifically includes:
inputting the road length, the road condition and the displacement into a generator in a generation countermeasure network, and generating initial position sequences of various working condition types by the generator;
inputting the initial position sequence into a discriminator in the generation countermeasure network, and judging whether the initial position sequence conforms to the actual driving condition or not by the discriminator;
and iteratively updating the generator and the discriminator according to the judgment result until the discriminator judges that the initial position sequence generated by the generator conforms to the actual driving condition, and obtaining a trained generated countermeasure network.
As an improvement of the above scheme, the performing transition processing on the kinematic segment in the position sequence to obtain the driving data of the automobile under the specific road condition specifically includes:
extracting two node data before and after the connection point of any two adjacent kinematic segments in the position sequence;
and supplementing intermediate data between the two node data by adopting a Newton interpolation method so as to enable any two adjacent kinematic segments to be in smooth transition, thereby obtaining driving data of the automobile under the specific road condition.
The embodiment of the invention also provides a device for generating the automobile driving data, which comprises the following components:
the acquisition module is used for acquiring original GPS data of the automobile running on each road section and the road length of each road section;
the kinematic segment dividing module is used for dividing the kinematic segments of the original GPS data to obtain a plurality of kinematic segments;
the first clustering module is used for carrying out clustering analysis on the plurality of kinematic segments, dividing the plurality of kinematic segments into a plurality of working condition types, and fitting the kinematic segments of each working condition type into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type;
the second clustering module is used for dividing the road sections into multiple road conditions according to the proportion of the kinematic segments of various working condition types in each road section data and calculating the displacement generated by the kinematic segments of various working condition types in each road section data;
the training module is used for training the generated countermeasure network constructed by the road length, the road condition and the displacement input, and obtaining position sequences of various working condition types through the trained generated countermeasure network;
and the transition processing module is used for performing transition processing on the kinematic segments in the position sequence to obtain the driving data of the automobile under the specific road condition.
The embodiment of the present invention further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the processor implements the method for generating the vehicle driving data described in any one of the above.
The embodiment of the invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for generating the automobile running data.
Compared with the prior art, the method, the device, the equipment and the storage medium for generating the automobile driving data have the advantages that: the countermeasure network is trained by selecting real driving data and road length characteristics of the automobile on different road sections, so that the characteristic of the countermeasure training is fully utilized, and a good driving data generation effect is achieved. In the data processing stage, the road condition features in each piece of data are extracted, and the automobile driving data are generated by combining the road length, the road speed and the road condition, so that the automobile driving data are closer to the real driving condition, and the authenticity and the accuracy of the generated data are effectively improved. The generation countermeasure network can flexibly adjust the input road length, road speed and road condition according to different data requirements, and generate the driving data of the automobile under specific road conditions.
Drawings
Fig. 1 is a schematic flow chart of a preferred embodiment of a method for generating vehicle driving data according to the present invention;
FIG. 2 is a diagram illustrating exemplary operation conditions of a kinematic segment in a method for generating driving data of an automobile according to the present invention;
fig. 3 is a schematic structural diagram of a preferred embodiment of a device for generating vehicle driving data according to the present invention;
fig. 4 is a schematic structural diagram of a preferred embodiment of a terminal device provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for generating vehicle driving data according to a preferred embodiment of the present invention. The method for generating the automobile driving data comprises the following steps:
s1, acquiring original GPS data of the automobile running on each road section and the road length of each road section;
S2, dividing the original GPS data into a plurality of kinematics segments;
s3, performing cluster analysis on the plurality of kinematic segments, dividing the plurality of kinematic segments into a plurality of working condition types, and fitting the kinematic segments of each working condition type into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type;
s4, dividing the road section into multiple road conditions according to the proportion of the kinematics segments of various working condition types in each road section data, and calculating the displacement generated by the kinematics segments of various working condition types in each road section data;
s5, training the generated confrontation network constructed by the road length, the road condition and the displacement input, and obtaining the position sequences of various working condition types through the trained generated confrontation network;
and S6, performing transition processing on the kinematic segments in the position sequence to obtain the driving data of the automobile under the specific road conditions.
Specifically, in this embodiment, first, original GPS data of an automobile running on a plurality of different road segments and a road length of each road segment are acquired, and the acquired original GPS data are divided into a plurality of kinematic segments, so as to obtain the plurality of kinematic segments. Secondly, clustering analysis is carried out on the plurality of kinematic segments, the plurality of kinematic segments are divided into a plurality of working condition types, and the kinematic segments of each working condition type are fitted into a function of the corresponding road speed with respect to time by combining the road speed corresponding to the kinematic segments of each working condition type. And dividing the road section into a plurality of road conditions according to the proportion of the kinematic segments of various working condition types in each road section data, and calculating the displacement generated by the kinematic segments of various working condition types in each road section data. Then, training a generated countermeasure network constructed by inputting the road length, the road condition and the displacement to obtain a trained generated countermeasure network, and obtaining a position sequence containing kinematic segments of various working condition types through the trained generated countermeasure network. For example, assuming that the uniform speed driving, overtaking, avoidance and traffic lights correspond to 1, 2, 3 and 4 respectively, the generated position sequence is 123211143. Because the generated position sequence is only the position sequence of each kinematic segment, and each kinematic segment is not connected, the kinematic segments in the position sequence need to be subjected to transition processing, so that the complete driving data of the automobile under the specific road condition can be obtained.
The embodiment trains the countermeasure network by selecting the real driving data and road length characteristics of the automobile on different road sections, makes full use of the characteristics of the countermeasure training, and achieves a good driving data generation effect. In the data processing stage, the road condition features in each piece of data are extracted, and the automobile driving data are generated by combining the road length, the road speed and the road condition, so that the automobile driving data are closer to the real driving condition, and the authenticity and the accuracy of the generated data are effectively improved. The generation countermeasure network can flexibly adjust the input road length, road speed and road condition according to different data requirements, and generate the driving data of the automobile under specific road conditions.
In another preferred embodiment, in the S2, the raw GPS data is divided into kinematic segments, specifically:
and extracting all extreme points in the original GPS data, and dividing the kinematics segments according to the extreme points.
Specifically, this embodiment extracts all extreme points from the acquired raw GPS data, and divides the kinematics segment according to the extreme points. For example, the present embodiment starts from the first extreme point of the starting point, and every three extreme points are a kinematic segment. And if the speed of the second extreme point and the third extreme point is 0, adding a fourth extreme point as a kinematic segment to realize effective division of the kinematic segment.
In another preferred embodiment, the S2, after the dividing the original GPS data into a plurality of kinematic segments, further includes:
calculating the acceleration of each kinematic segment, and judging whether abnormal acceleration exists or not;
and if the abnormal acceleration exists, removing the kinematic segment corresponding to the abnormal acceleration.
Specifically, in this embodiment, after the original GPS data is divided into a plurality of kinematic segments, the acceleration of each kinematic segment is calculated, and whether an abnormal acceleration exists is determined. And if the abnormal acceleration exists, removing the kinematics segment corresponding to the abnormal acceleration so as to ensure the accuracy of the data.
In a further preferred embodiment, the S3, performing cluster analysis on the plurality of kinematic segments, dividing the plurality of kinematic segments into a plurality of operating condition types, and fitting the kinematic segments of each operating condition type into a function of the road speed with respect to time by combining the road speed corresponding to each operating condition type specifically includes:
s301, performing clustering analysis on the plurality of kinematic segments by adopting a K-means algorithm, and dividing the plurality of kinematic segments into a plurality of working condition types; the working condition types at least comprise constant-speed driving, overtaking, avoiding and traffic lights;
S302, selecting a classification central point of each working condition type and N points closest to the classification central point, and combining the road speed corresponding to each working condition type to fit the kinematic fragment of each working condition type into a function of the road speed with respect to time; wherein N is a positive integer.
Specifically, the K-means algorithm is adopted in the embodiment to perform cluster analysis on the multiple kinematic segments, and the multiple kinematic segments are divided into multiple working condition types. For example, please refer to fig. 2, fig. 2 is a diagram illustrating an exemplary operation condition type of a kinematic segment in a method for generating driving data of an automobile according to the present invention. The working condition types of the kinematics segments at least comprise constant-speed driving, overtaking, avoiding and traffic lights. Then, a classification central point of each working condition type and N points closest to the classification central point are selected, and the kinematic segments of each working condition type are fitted into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type. In this embodiment, N is a positive integer, and N is preferably 10, that is, a classification center point of each operating condition type and 10 points closest to the classification center point are selected.
It should be noted that the algorithm used in the clustering analysis of the kinematic segment in this embodiment is not limited to the K-means algorithm, and other algorithms capable of achieving the clustering analysis effect in this embodiment are within the protection scope of the present invention.
The embodiment can obtain the influence of the road speed on the kinematic segment by fitting the kinematic segment of each working condition type into the function of the road speed with respect to time, so that the input road speed can determine the kinematic segment corresponding to the road speed.
In a further preferred embodiment, the step S4, dividing the road segment into a plurality of road conditions according to the proportion of the kinematic segments of the various operating modes in each road segment data, and calculating the displacement generated by the kinematic segments of the various operating modes in each road segment data specifically includes:
s401, calculating the proportion of the kinematic segments of various working condition types in each road section data;
s402, dividing the road sections into a plurality of road conditions according to the proportion by adopting a K-means algorithm; wherein the road conditions at least comprise smooth, slow running, congestion and severe congestion;
and S403, calculating the displacement generated by the kinematic segments of various working condition types in each road section data.
Specifically, in this embodiment, the proportion of the kinematic segments of various working condition types in each road section data is calculated first, for example, in a certain road section data, the constant speed driving segment accounts for 80%, the overtaking segment accounts for 8%, the avoidance segment accounts for 10%, and the traffic light segment accounts for 2%. Then, a plurality of road sections are divided into a plurality of road conditions according to the proportion of the kinematic segments of various working condition types in each road section data by adopting a K-means algorithm. The road conditions at least include smooth, slow running, congestion and severe congestion. Finally, the corresponding kinematic segment of the road speed can be determined by inputting the road speed, and then the displacement generated by the kinematic segments of various working conditions in each road section data can be calculated.
It should be noted that the algorithm used in the clustering analysis of the proportion of the kinematic segments of various working condition types in each road section data in this embodiment is not limited to the K-means algorithm, and other algorithms capable of achieving the clustering analysis effect in this embodiment are all within the protection scope of the present invention.
In another preferred embodiment, the training method for generating an antagonistic network specifically includes:
a generator in a generation countermeasure network constructed by inputting the road length, the road condition and the displacement, wherein the generator generates initial position sequences of various working condition types;
inputting the initial position sequence into a discriminator in the generation countermeasure network, and judging whether the initial position sequence conforms to the actual driving condition or not by the discriminator;
and iteratively updating the generator and the discriminator according to the judgment result until the discriminator judges that the initial position sequence generated by the generator conforms to the actual driving condition, and obtaining a trained generated countermeasure network.
Specifically, the generated countermeasure network (GAN) mainly includes two parts, i.e., a generator and an identifier translator. The generation countermeasure network is used for generating data, the generator is mainly used for learning real data so as to enable the data generated by the generator to be more real, and therefore the discriminator is cheated, and the discriminator needs to conduct true and false discrimination on the received data. In the whole process, the generator tries to make the generated data more real, and the discriminator tries to identify the true and false of the data, the process is equivalent to a two-person game, the generator and the discriminator continuously resist against each other over time, and finally, two networks reach a dynamic balance: the data generated by the generator is close to the true data distribution, and the discriminator can not identify the true data and the false data. When the countermeasure network is generated and trained, the generator in the generation countermeasure network is constructed by inputting the road length, the road condition and the displacement, the generator generates the initial position sequence of various working condition types, and the initial position sequence is input into the discriminator in the generation countermeasure network. The discriminator judges whether the generated track characteristics are consistent with the characteristics (including road length, road speed and road condition) input by the generator according to the characteristic input in the generator, thereby judging whether the position sequence generated by the generator is consistent with the actual driving condition. And then, further carrying out iterative updating on the generator and the discriminator according to the judgment result until the discriminator judges that the initial position sequence generated by the generator conforms to the actual driving condition, and obtaining a trained generated countermeasure network.
The embodiment selects real driving data and road length characteristics of the automobile on different road sections to generate the antagonistic network for training, fully utilizes the antagonistic training characteristics of the antagonistic network, and achieves a good driving data generation effect. In the data processing stage, the road condition features in each piece of data are extracted, and the automobile driving data is generated by combining the road length, the road speed and the road condition, so that the automobile driving data is closer to the real driving condition, and the authenticity and the accuracy of the generated data are effectively improved. The generation countermeasure network can flexibly adjust the input road length, road speed and road condition according to different data requirements, and generate the driving data of the automobile under specific road conditions.
In another preferred embodiment, in S6, the performing a transition process on the kinematic segment in the position sequence to obtain the driving data of the automobile under the specific road condition specifically includes:
s601, extracting two node data before and after the connection point of any two adjacent kinematic segments in the position sequence;
and S602, supplementing intermediate data between the two node data by adopting a Newton interpolation method to enable any two adjacent kinematic segments to be in smooth transition, thereby obtaining driving data of the automobile under a specific road condition.
Specifically, since the trained generated countermeasure network only generates the position sequence of each kinematic segment, and each kinematic segment is not connected, for example, assuming that uniform speed driving, overtaking, avoiding, and traffic lights respectively correspond to 1, 2, 3, and 4, the generated position sequence is 123211143. Therefore, the kinematics segments in the position sequence need to be subjected to transition processing, two node data before and after the connection point of any two adjacent kinematics segments in the position sequence are firstly extracted, and then, the newton interpolation method is adopted to supplement the intermediate data between the two node data, so that smooth transition can be performed between any two adjacent kinematics segments, and thus complete driving data of the automobile under the specific road condition can be obtained.
Accordingly, the present invention further provides a device for generating vehicle driving data, which can implement all the processes of the method for generating vehicle driving data in the above embodiments.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a device for generating driving data of an automobile according to a preferred embodiment of the present invention. The device for generating the automobile driving data comprises:
the acquisition module 301 is configured to acquire original GPS data of a vehicle running on each road segment and a road length of each road segment;
A kinematics segment division module 302, configured to perform kinematics segment division on the original GPS data to obtain a plurality of kinematics segments;
the first clustering module 303 is configured to perform clustering analysis on the plurality of kinematic segments, divide the plurality of kinematic segments into a plurality of working condition types, and fit the kinematic segments of each working condition type into a function of a road speed with respect to time by combining a road speed corresponding to each working condition type;
the second clustering module 304 is configured to divide the road segment into multiple road conditions according to the proportion of the kinematic segments of the various working condition types in each road segment data, and calculate the displacement generated by the kinematic segments of the various working condition types in each road segment data;
a training module 305, configured to train the generated countermeasure network constructed by the road length, the road condition, and the displacement input, and obtain position sequences of various working condition types through the trained generated countermeasure network;
and the transition processing module 306 is configured to perform transition processing on the kinematic segments in the position sequence to obtain driving data of the automobile under the specific road condition.
Preferably, the kinematic segmentation module 302 is specifically configured to:
And extracting all extreme points in the original GPS data, and dividing a kinematics segment according to the extreme points.
Preferably, the kinematic segmentation module 302 is further configured to:
calculating the acceleration of each kinematic fragment, and judging whether abnormal acceleration exists or not;
and if the abnormal acceleration exists, removing the kinematic segment corresponding to the abnormal acceleration.
Preferably, the first clustering module 303 specifically includes:
the first clustering unit 313 is used for performing clustering analysis on the plurality of kinematic segments by adopting a K-means algorithm and dividing the plurality of kinematic segments into a plurality of working condition types; the working condition types at least comprise constant-speed driving, overtaking, avoiding and traffic lights;
the fitting unit 323 is used for selecting a classification central point of each working condition type and N points closest to the classification central point, and fitting the kinematic fragments of each working condition type into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type; wherein N is a positive integer.
Preferably, the second clustering module 304 specifically includes:
the proportion calculation unit 314 is used for calculating the proportion of the kinematic segments of various working condition types in each road section data;
A second clustering unit 324 for classifying the road segments into a plurality of road conditions according to the proportions using a K-means algorithm; wherein the road conditions at least comprise smooth, slow running, congestion and severe congestion;
and the displacement calculation unit 334 is used for calculating the displacement generated by the kinematic segments of various working condition types in each road section data.
Preferably, the training method for generating the countermeasure network specifically includes:
inputting the road length, the road condition and the displacement into a generator in a generation countermeasure network, and generating initial position sequences of various working condition types by the generator;
inputting the initial position sequence into a discriminator in the generation countermeasure network, and judging whether the initial position sequence conforms to the actual driving condition or not by the discriminator;
and iteratively updating the generator and the discriminator according to the judgment result until the discriminator judges that the initial position sequence generated by the generator conforms to the actual driving condition, and obtaining a trained generated countermeasure network.
Preferably, the transition processing module 306 specifically includes:
an extracting unit 316, configured to extract two node data before and after a connection point of any two adjacent kinematic segments in the position sequence;
And a transition unit 326, configured to supplement the intermediate data between the two node data by using a newton interpolation method, so as to enable a smooth transition between any two adjacent kinematic segments, thereby obtaining driving data of the vehicle under a specific road condition.
In a specific implementation, the working principle, the control flow and the technical effect of the device for generating vehicle driving data according to the embodiment of the present invention are the same as those of the method for generating vehicle driving data according to the embodiment described above, and are not described herein again.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a terminal device according to a preferred embodiment of the present invention. The terminal device includes a processor 401, a memory 402, and a computer program stored in the memory 402 and configured to be executed by the processor 401, and the processor 401 implements the method for generating the vehicle travel data according to any one of the embodiments when executing the computer program.
Preferably, the computer program may be divided into one or more modules/units (e.g., computer program 1, computer program 2, … …) that are stored in the memory 402 and executed by the processor 401 to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device.
The Processor 401 may be a Central Processing Unit (CPU), other general purpose processors, Digital Signal Processors (DSP), Application Specific Integrated Circuits (ASIC), Field Programmable Gate Array (FPGA) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc., the general purpose Processor may be a microprocessor, or the Processor 401 may be any conventional Processor, the Processor 401 is a control center of the terminal device, and various interfaces and lines are used to connect various parts of the terminal device.
The memory 402 mainly includes a program storage area that may store an operating system, an application program required for at least one function, and the like, and a data storage area that may store related data and the like. In addition, the memory 402 may be a high speed random access memory, a non-volatile memory such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), and the like, or the memory 402 may be other volatile solid state memory devices.
It should be noted that the terminal device may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the structural diagram in fig. 4 is only an example of the terminal device, and does not constitute a limitation of the terminal device, and may include more or less components than those shown in the drawing, or may combine some components, or may include different components.
The embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, a device where the computer-readable storage medium is located is controlled to execute the method for generating vehicle driving data according to any one of the foregoing embodiments.
The embodiment of the invention provides a method, a device, equipment and a storage medium for generating automobile driving data. In the data processing stage, the road condition features in each piece of data are extracted, and the automobile driving data is generated by combining the road length, the road speed and the road condition, so that the automobile driving data is closer to the real driving condition, and the authenticity and the accuracy of the generated data are effectively improved. The generation countermeasure network can flexibly adjust the input road length, road speed and road condition according to different data requirements, and generate the driving data of the automobile under specific road conditions.
It should be noted that the above-described system embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the system provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A method for generating vehicle travel data, comprising:
Acquiring original GPS data of the automobile running on each road section and the road length of each road section;
dividing the original GPS data into a plurality of kinematic segments;
clustering analysis is carried out on the plurality of kinematic segments, the plurality of kinematic segments are divided into a plurality of working condition types, and the kinematic segments of each working condition type are fitted into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type;
dividing the road section into a plurality of road conditions according to the proportion of the kinematic segments of various working condition types in each road section data, and calculating the displacement generated by the kinematic segments of various working condition types in each road section data;
training a generated countermeasure network constructed by inputting the road length, the road condition and the displacement, and obtaining position sequences of various working condition types through the trained generated countermeasure network;
and performing transition processing on the kinematic segments in the position sequence to obtain driving data of the automobile under specific road conditions.
2. The method for generating vehicle driving data according to claim 1, wherein the dividing of the original GPS data into the kinematic segments is specifically:
And extracting all extreme points in the original GPS data, and dividing a kinematics segment according to the extreme points.
3. The method for generating driving data of a vehicle according to claim 2, wherein after the dividing of the original GPS data into a plurality of kinematic segments, the method further comprises:
calculating the acceleration of each kinematic fragment, and judging whether abnormal acceleration exists or not;
and if the abnormal acceleration exists, removing the kinematic segment corresponding to the abnormal acceleration.
4. The method for generating vehicle driving data according to claim 1, wherein the clustering analysis is performed on the plurality of kinematic segments, the plurality of kinematic segments are divided into a plurality of working condition types, and the kinematic segments of each working condition type are fitted to a function of a road speed with respect to time in combination with a road speed corresponding to each working condition type, and specifically comprises:
clustering analysis is carried out on the plurality of kinematic segments by adopting a K-means algorithm, and the plurality of kinematic segments are divided into a plurality of working condition types; the working condition types at least comprise constant-speed driving, overtaking, avoiding and traffic lights;
selecting a classification central point of each working condition type and N points closest to the classification central point, and fitting the kinematic segments of each working condition type into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type; wherein N is a positive integer.
5. The method for generating driving data of an automobile according to claim 1, wherein the step of dividing the road segment into a plurality of road conditions according to the proportion of the kinematic segments of the various operating modes in each road segment data, and calculating the displacement generated by the kinematic segments of the various operating modes in each road segment data specifically comprises:
calculating the proportion of the kinematic fragments of various working condition types in each road section data;
dividing the road sections into a plurality of road conditions according to the proportion by adopting a K-means algorithm; wherein the road conditions at least comprise smooth, slow running, congestion and severe congestion;
and calculating the displacement generated by the kinematic segments of various working condition types in each road section data.
6. The method for generating vehicle travel data according to any one of claims 1 to 5, wherein the training method for generating the countermeasure network specifically includes:
inputting the road length, the road condition and the displacement into a generator in a generation countermeasure network, and generating initial position sequences of various working condition types by the generator;
inputting the initial position sequence into a discriminator in the generation countermeasure network, and judging whether the initial position sequence conforms to the actual driving condition or not by the discriminator;
And iteratively updating the generator and the discriminator according to the judgment result until the discriminator judges that the initial position sequence generated by the generator conforms to the actual driving condition, and obtaining a trained generated countermeasure network.
7. The method for generating driving data of an automobile according to claim 6, wherein the performing transition processing on the kinematic segment in the position sequence to obtain the driving data of the automobile under specific road conditions specifically comprises:
extracting two node data before and after the connection point of any two adjacent kinematic segments in the position sequence;
and supplementing intermediate data between the two node data by adopting a Newton interpolation method so as to enable any two adjacent kinematic segments to be in smooth transition, thereby obtaining driving data of the automobile under the specific road condition.
8. An apparatus for generating vehicle travel data, comprising:
the acquisition module is used for acquiring original GPS data of the automobile running on each road section and the road length of each road section;
the kinematic segment dividing module is used for dividing the kinematic segments of the original GPS data to obtain a plurality of kinematic segments;
The first clustering module is used for carrying out clustering analysis on the plurality of kinematic segments, dividing the plurality of kinematic segments into a plurality of working condition types, and fitting the kinematic segments of each working condition type into a function of the road speed with respect to time by combining the road speed corresponding to each working condition type;
the second clustering module is used for dividing the road sections into multiple road conditions according to the proportion of the kinematic segments of various working condition types in each road section data and calculating the displacement generated by the kinematic segments of various working condition types in each road section data;
the training module is used for training the generated countermeasure network constructed by the road length, the road condition and the displacement input, and obtaining position sequences of various working condition types through the trained generated countermeasure network;
and the transition processing module is used for performing transition processing on the kinematic segments in the position sequence to obtain the driving data of the automobile under the specific road condition.
9. A terminal device characterized by comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the method for generating automobile travel data according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls a device to execute the method for generating vehicle travel data according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210228016.2A CN114676211A (en) | 2022-03-08 | 2022-03-08 | Method, device and equipment for generating automobile driving data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210228016.2A CN114676211A (en) | 2022-03-08 | 2022-03-08 | Method, device and equipment for generating automobile driving data and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114676211A true CN114676211A (en) | 2022-06-28 |
Family
ID=82072480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210228016.2A Pending CN114676211A (en) | 2022-03-08 | 2022-03-08 | Method, device and equipment for generating automobile driving data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114676211A (en) |
-
2022
- 2022-03-08 CN CN202210228016.2A patent/CN114676211A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10636161B2 (en) | Image recognition system | |
| WO2021232229A1 (en) | Virtual scene generation method and apparatus, computer device and storage medium | |
| CN110717248A (en) | Method and system for generating automatic driving simulation scene, server and medium | |
| CN112307978B (en) | Target detection method and device, electronic equipment and readable storage medium | |
| US11302122B2 (en) | Apparatus and method for predicting injury level | |
| CN109034086A (en) | Vehicle recognition methods, apparatus and system again | |
| JP2022050380A (en) | Method for monitoring vehicle, apparatus, electronic device, storage medium, computer program, and cloud control platform | |
| CN113313110B (en) | License plate type recognition model construction and license plate type recognition method | |
| CN110135428B (en) | Image segmentation processing method and device | |
| CN115131634A (en) | Image recognition method, device, equipment, storage medium and computer program product | |
| CN112462759B (en) | Evaluation method, system and computer storage medium of rule control algorithm | |
| CN106991436B (en) | Noise point detection method and device | |
| CN111177878B (en) | Derived simulation scene screening method, device and terminal | |
| CN114676211A (en) | Method, device and equipment for generating automobile driving data and storage medium | |
| CN109753999B (en) | Fine-grained vehicle type identification method for automobile pictures with any visual angles | |
| CN113868875B (en) | Method, device and equipment for automatically generating test scene and storage medium | |
| JPWO2018143277A1 (en) | Image feature output device, image recognition device, image feature output program, and image recognition program | |
| CN111104611B (en) | Data processing method, device, equipment and storage medium | |
| CN106097751A (en) | Vehicle travel control method and device | |
| CN113447031A (en) | Gradient point screening method, terminal equipment, medium and gradient calculation method and system | |
| CN111860090A (en) | Vehicle verification method and device | |
| CN111611846A (en) | Pedestrian re-identification method and device, electronic equipment and storage medium | |
| US20230101250A1 (en) | Method for generating a graph structure for training a graph neural network | |
| CN111310070B (en) | Method and device for determining frequent trips, storage medium and electronic equipment | |
| CN115222940B (en) | Semantic segmentation method, system, device and storage medium |
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 |