CN111914482A - Driving condition generation method and system for automatic driving test - Google Patents
Driving condition generation method and system for automatic driving test Download PDFInfo
- Publication number
- CN111914482A CN111914482A CN202010733535.5A CN202010733535A CN111914482A CN 111914482 A CN111914482 A CN 111914482A CN 202010733535 A CN202010733535 A CN 202010733535A CN 111914482 A CN111914482 A CN 111914482A
- Authority
- CN
- China
- Prior art keywords
- encoder
- driving
- output
- input data
- sampling
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000005070 sampling Methods 0.000 claims abstract description 34
- 230000007246 mechanism Effects 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the invention provides a driving condition generation method and a system for automatic driving test, wherein the method comprises the following steps: sampling a source driving working condition of an automatic driving test to obtain input data; inputting input data into an encoder, and acquiring an implicit variable which is output by the encoder and corresponds to the input data; and (4) injecting an attention mechanism into the hidden variable to obtain a target running condition which is output by the decoder and has characteristics similar to those of the source running condition. According to the embodiment of the invention, the attention distribution probability information in the source running condition can be learned through the encoder and the attention mechanism, so that the output target running condition is similar to the characteristics of the source running condition.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to a driving condition generation method and system for automatic driving test.
Background
The driving condition of the automobile refers to the speed of the automobile driving in a certain road network under a specific driving environment, namely the time change rule, and is the basic work for evaluating the pollutant emission of the automobile, the fuel consumption and the design and development of the automobile. In addition, the construction, classification and change of the driving conditions have great influence on the vehicle control performance, so that the driving conditions need to be brought into the research scope in the process of making and implementing control strategies of new energy vehicles and automatic driving vehicles, and the driving conditions are used as evaluation basis for energy consumption and driving safety of the vehicles under a certain driving road condition.
With the increasingly complex road traffic conditions in China, the idle speed ratio, the average speed and the high-speed driving ratio of the currently borrowed European typical working condition are all far higher than the actual working condition in China, and the current automobile driving characteristics cannot be reflected. In addition, in the field of automatic driving, research on vehicle test conditions conforming to roads and traffic conditions of various countries is continuously developed at home and abroad, so that the test conditions of automatic driving are enriched. Therefore, a driving condition generating method is needed for testing automatic driving so as to enrich the testing scene of automatic driving.
Disclosure of Invention
The embodiment of the invention provides a driving condition generation method and system for an automatic driving test, which are used for the automatic driving test so as to enrich the test scene of automatic driving.
In a first aspect, an embodiment of the present invention provides a driving condition generation method for an automatic driving test, where the method includes: sampling a source driving working condition of an automatic driving test to obtain input data; inputting input data into an encoder, and acquiring an implicit variable which is output by the encoder and corresponds to the input data; and (4) injecting an attention mechanism into the hidden variable to obtain a target running condition which is output by the decoder and has characteristics similar to those of the source running condition.
The method is characterized in that the source running working condition of the automatic driving test is sampled, and the method comprises the following steps:
and sampling the source running condition based on a sliding time window with a preset length and a sampling interval.
Further, the obtaining input data includes:
and carrying out data normalization on the working condition data obtained after sampling, and taking the result obtained after normalization as the input data.
Further, before inputting the input data to the encoder, the method further includes:
setting the network structure type of the encoder as a multi-layer perceptron; setting the dimension of the neuron in the hidden layer in the encoder to be smaller than that of the input layer, and setting the dimension of the input layer to be equal to that of the output layer; setting a first connection weight and a first bias of the input layer and the hidden layer; setting a second connection weight and a second bias of the hidden layer and the output layer; and selecting the nonlinear activation function of each node as a sigmoid function.
Further, an attention mechanism is injected to the implicit variable, comprising:
embedding an attention model into seq2seq, the attention model for learning closeness of relationship between an implicit variable of the encoder output and the target driving condition of the decoder output.
Further, the decoder is configured to map the clustered sample points in the potential space back to the source driving condition to generate the target driving condition.
In a second aspect, an embodiment of the present invention provides a driving condition generation system for an automatic driving test, including:
the sampling module is used for sampling the source running condition of the automatic driving test to obtain input data;
the input module is used for inputting input data into the encoder and obtaining an implicit variable which is output by the encoder and corresponds to the input data;
and the output module is used for injecting an attention mechanism into the hidden variable to obtain the target running condition which is output by the decoder and is similar to the characteristics of the source running condition.
Further, the sampling module is specifically configured to sample the source driving condition based on a sliding time window of a preset length and a sampling interval.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the driving condition generating method for an automatic driving test, as provided in any one of the various possible implementations of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a driving condition generation method for an automatic driving test as provided in any one of various possible implementations of the first aspect.
According to the driving condition generation method and system for the automatic driving test, provided by the embodiment of the invention, attention distribution probability information in the source driving condition can be learned through the encoder and the attention mechanism, so that the characteristics of the target driving condition obtained through output are similar to those of the source driving condition.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from these without inventive effort.
FIG. 1 is a schematic flow chart of a driving condition generation method for automatic driving test according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a framework of a driving condition generation method for an automatic driving test according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a driving condition generation system for automatic driving test according to an embodiment of the present invention;
fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. 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.
In order to solve the problem that the completeness of the driving condition required by testing the automatic driving vehicle is not enough, the embodiment of the invention provides a driving condition generation method for an automatic driving test. First, the overall principle of the method provided by the embodiment of the present invention is briefly described, which specifically includes the following steps:
1) and setting the length of the sliding time window and the sampling interval, and using the sliding time window to perform sliding sampling on the input limit working condition.
2) And carrying out data normalization on the working condition data obtained by sliding sampling.
3) And taking the normalized working condition data as the input of the depth encoder network.
4) The depth encoder network extracts and outputs implicit variables of the source input data.
5) Attention mechanism is injected to the implicit variable.
6) And the decoder combines the step 4) and the step 5) to generate the running condition with the characteristic similar to the source running condition.
The following describes in detail a driving condition generation method for automatic driving test provided by an embodiment of the present invention with reference to fig. 1-2, and the method includes, but is not limited to, the following steps:
Specifically, a person skilled in the art may reasonably select a sampling mode according to actual requirements, wherein as an optional embodiment, the sampling of the source driving condition of the automatic driving test includes: and sampling the source running condition based on a sliding time window with a preset length and a sampling interval.
In other words, the length of the sliding time window and the sampling interval can be reasonably set firstly, and after the setting is completed, the sliding sampling is carried out on the input limit working condition by using the sliding time window.
After sampling is completed, as an optional embodiment, data normalization may be performed on the condition data obtained by sliding sampling, and a result obtained after normalization is used as input data.
Specifically, transient driving conditions are considered as a time series { x ] before the encoder is used to reconstruct the driving conditions1,x1,…,xnAnd may be subjected to normalization preprocessing according to the following equation (1), with the result as input to the auto-encoder:
where v is the running speed.
And 102, inputting the input data into an encoder to obtain an implicit variable which is output by the encoder and corresponds to the input data.
Before step 102 is executed, the method further includes: setting the network structure type of an encoder as a multilayer perceptron; setting the dimension of the neuron in the hidden layer in the encoder to be smaller than the dimension of the input layer, wherein the dimension of the input layer is equal to the dimension of the output layer; setting a first connection weight and a first bias of an input layer and a hidden layer; setting a second connection weight and a second bias of the hidden layer and the output layer; and selecting the nonlinear activation function of each node as a sigmoid function.
Specifically, the number m of neurons in the hidden layer is set to be smaller than the dimension n of the input layer, and W is set1∈Rn×mAnd b1∈RnRespectively representing the connection weights and offsets, W, of the input layer and the hidden layer2∈Rm×nAnd b2∈RmRespectively representing the connection weight and the bias of the hidden layer and the output layer. The nonlinear activation function of each node is selected to be sigmoid function (expressed by s), and the encoding process for the automatic encoder is as the formula (2)) As shown.
It should be noted that the above arrangement is advantageous for feature depth, and can reduce training cost, i.e., calculation cost and training data size.
In this step 102, the depth encoder network is used to extract and output implicit variables of the source input data. And, since the dimension of the input layer and the dimension of the output layer are set to be equal, and the dimension of the hidden layer is smaller than the dimension of the input layer. Therefore, the hidden layer at this time has the ability to learn more essential structures of the data, so that the automatic encoder has to look for some patterns or structures present in the input data in order to accomplish this goal.
And 103, injecting an attention mechanism into the hidden variable to obtain a target running condition which is output by the decoder and has characteristics similar to those of the source running condition.
As an alternative embodiment, the attention mechanism is injected to the hidden variable, comprising: an attention model is embedded into seq2seq, and is used for learning the degree of closeness of the relationship between the implicit variables output by the encoder and the target driving condition output by the decoder.
In particular, the attention module is actually a small model embedded in seq2seq, which is responsible for learning how closely the hidden state sequence Z output by the encoder is related to the yt output currently to be predicted by the decoder during the training phase of the model.
As an alternative embodiment, the decoder is configured to map the clustered sample points in the potential space back to the source driving profile to generate the target driving profile.
Specifically, the decoder can generate the running condition similar to the source running condition characteristic by combining the step of extracting and outputting the hidden variable of the source input data by the depth encoder network and the step of injecting the attention mechanism into the hidden variable.
The decoder module maps the clustered sampling points in the potential space back to the original input working condition, so that the purpose of generating the working condition is achieved, the noise of the collected data is filtered in the whole process, and the curve of the output result is changed from the original irregular curve into a smoother curve; and fitting the denoised data by using an encoder, and reconstructing the data by using a decoder to ensure that the reconstructed data approaches the input working condition as much as possible.
In summary, according to the driving condition generation method for the automatic driving test provided by the embodiment of the invention, the attention distribution probability information in the source driving condition can be learned through the encoder and the attention mechanism, so that the characteristics of the target driving condition obtained through output are similar to the characteristics of the source driving condition.
Based on the content of the foregoing embodiments, the embodiment of the present invention provides a driving condition generation system for an automatic driving test, which is used for executing the driving condition generation method for the automatic driving test in the foregoing method embodiments. Referring to fig. 3, the system includes: the sampling module 301 is configured to sample a source driving condition of an automatic driving test to obtain input data; an input module 302, configured to input data to an encoder, and obtain an implicit variable output by the encoder and corresponding to the input data; and the output module 303 is used for injecting an attention mechanism into the hidden variable to obtain a target driving condition which is output by the decoder and is similar to the characteristics of the source driving condition.
An embodiment of the present invention provides an electronic device, as shown in fig. 4, the electronic device includes: a processor (processor)401, a communication Interface (communication Interface)402, a memory (memory)403 and a communication bus 404, wherein the processor 401, the communication Interface 402 and the memory 403 complete communication with each other through the communication bus 404. The processor 401 may call a computer program on the memory 403 and operable on the processor 401 to execute the driving condition generating method for the automatic driving test provided by the above embodiments, for example, including: sampling a source driving working condition of an automatic driving test to obtain input data; inputting input data into an encoder, and acquiring an implicit variable which is output by the encoder and corresponds to the input data; and (4) injecting an attention mechanism into the hidden variable to obtain a target running condition which is output by the decoder and has characteristics similar to those of the source running condition.
In addition, the logic instructions in the memory 403 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. 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 instructions for causing 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: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
An embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to, when executed by a processor, perform a driving condition generating method for an automatic driving test provided in the foregoing embodiments, for example, the method includes: sampling a source driving working condition of an automatic driving test to obtain input data; inputting input data into an encoder, and acquiring an implicit variable which is output by the encoder and corresponds to the input data; and (4) injecting an attention mechanism into the hidden variable to obtain a target running condition which is output by the decoder and has characteristics similar to those of the source running condition.
The above-described embodiments of the electronic device and the like are merely illustrative, and units illustrated as separate components may or may not be physically separate, and components displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute the various embodiments or some parts of the methods of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical 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 (10)
1. A running condition generation method for an automatic driving test, characterized by comprising:
sampling a source driving working condition of an automatic driving test to obtain input data;
inputting the input data into an encoder, and obtaining an implicit variable which is output by the encoder and corresponds to the input data;
and injecting an attention mechanism into the hidden variable to obtain a target running condition which is output by the decoder and is similar to the characteristics of the source running condition.
2. The method of claim 1, wherein sampling the source driving conditions of the autopilot test comprises:
and sampling the source running condition based on a sliding time window with a preset length and a sampling interval.
3. The method of claim 1, wherein the obtaining input data comprises:
and carrying out data normalization on the working condition data obtained after sampling, and taking the result obtained after normalization as the input data.
4. The method of claim 1, wherein prior to inputting the input data to the encoder, further comprising:
setting the network structure type of the encoder as a multi-layer perceptron; setting the dimension of the neuron in the hidden layer in the encoder to be smaller than that of the input layer, and setting the dimension of the input layer to be equal to that of the output layer; setting a first connection weight and a first bias of the input layer and the hidden layer; setting a second connection weight and a second bias of the hidden layer and the output layer; and selecting the nonlinear activation function of each node as a sigmoid function.
5. The method of claim 1, wherein injecting an attention mechanism into the hidden variable comprises:
embedding an attention model into seq2seq, the attention model for learning closeness of relationship between an implicit variable of the encoder output and the target driving condition of the decoder output.
6. The method of claim 3, wherein the decoder is configured to map the clustered sample points in the potential space back to the source driving profile to generate the target driving profile.
7. A driving condition generation system for automated driving tests, comprising:
the sampling module is used for sampling the source running condition of the automatic driving test to obtain input data;
the input module is used for inputting the input data into an encoder and obtaining an implicit variable which is output by the encoder and corresponds to the input data;
and the output module is used for injecting an attention mechanism into the hidden variable to obtain a target running condition which is output by the decoder and is similar to the characteristics of the source running condition.
8. The system of claim 7, wherein the sampling module is specifically configured to sample the source driving condition based on a sliding time window of a preset length and a sampling interval.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for generating driving conditions for autopilot testing according to one of claims 1 to 6.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the driving condition generation method for automated driving tests according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010733535.5A CN111914482A (en) | 2020-07-27 | 2020-07-27 | Driving condition generation method and system for automatic driving test |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010733535.5A CN111914482A (en) | 2020-07-27 | 2020-07-27 | Driving condition generation method and system for automatic driving test |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111914482A true CN111914482A (en) | 2020-11-10 |
Family
ID=73281831
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010733535.5A Pending CN111914482A (en) | 2020-07-27 | 2020-07-27 | Driving condition generation method and system for automatic driving test |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111914482A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113111942A (en) * | 2021-04-13 | 2021-07-13 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for extracting driving condition data and electronic equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491859A (en) * | 2018-02-11 | 2018-09-04 | 郭静秋 | The recognition methods of driving behavior heterogeneity feature based on automatic coding machine |
CN109697169A (en) * | 2019-03-25 | 2019-04-30 | 深兰人工智能芯片研究院(江苏)有限公司 | A kind of test method and device of automated driving system |
WO2019155873A1 (en) * | 2018-02-06 | 2019-08-15 | オムロン株式会社 | Evaluation device, action control device, evaluation method, and evaluation program |
CN110398957A (en) * | 2019-06-18 | 2019-11-01 | 平安科技(深圳)有限公司 | Automatic Pilot behavior prediction method, apparatus, computer equipment and storage medium |
CN110555266A (en) * | 2019-08-30 | 2019-12-10 | 武汉中海庭数据技术有限公司 | simulation road network data random generation method and system for simulation test |
CN110597086A (en) * | 2019-08-19 | 2019-12-20 | 深圳元戎启行科技有限公司 | Simulation scene generation method and unmanned system test method |
CN111062347A (en) * | 2019-12-21 | 2020-04-24 | 武汉中海庭数据技术有限公司 | Traffic element segmentation method in automatic driving, electronic device and storage medium |
-
2020
- 2020-07-27 CN CN202010733535.5A patent/CN111914482A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019155873A1 (en) * | 2018-02-06 | 2019-08-15 | オムロン株式会社 | Evaluation device, action control device, evaluation method, and evaluation program |
CN108491859A (en) * | 2018-02-11 | 2018-09-04 | 郭静秋 | The recognition methods of driving behavior heterogeneity feature based on automatic coding machine |
CN109697169A (en) * | 2019-03-25 | 2019-04-30 | 深兰人工智能芯片研究院(江苏)有限公司 | A kind of test method and device of automated driving system |
CN110398957A (en) * | 2019-06-18 | 2019-11-01 | 平安科技(深圳)有限公司 | Automatic Pilot behavior prediction method, apparatus, computer equipment and storage medium |
CN110597086A (en) * | 2019-08-19 | 2019-12-20 | 深圳元戎启行科技有限公司 | Simulation scene generation method and unmanned system test method |
CN110555266A (en) * | 2019-08-30 | 2019-12-10 | 武汉中海庭数据技术有限公司 | simulation road network data random generation method and system for simulation test |
CN111062347A (en) * | 2019-12-21 | 2020-04-24 | 武汉中海庭数据技术有限公司 | Traffic element segmentation method in automatic driving, electronic device and storage medium |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113111942A (en) * | 2021-04-13 | 2021-07-13 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for extracting driving condition data and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112149316B (en) | Aero-engine residual life prediction method based on improved CNN model | |
CN104866578B (en) | A kind of imperfect Internet of Things data mixing fill method | |
CN109816032B (en) | Unbiased mapping zero sample classification method and device based on generative countermeasure network | |
CN106951512A (en) | A kind of end-to-end session control method based on hybrid coding network | |
CN109255505A (en) | A kind of short-term load forecasting method of multi-model fused neural network | |
CN113869208B (en) | Rolling bearing fault diagnosis method based on SA-ACWGAN-GP | |
Li et al. | Image manipulation localization using attentional cross-domain CNN features | |
CN117269754B (en) | IPSM rotor demagnetizing and eccentric fault diagnosis method based on convolutional neural network operation | |
CN103268484A (en) | Design method of classifier for high-precision face recognitio | |
CN112489168A (en) | Image data set generation and production method, device, equipment and storage medium | |
CN114912719B (en) | Heterogeneous traffic individual trajectory collaborative prediction method based on graph neural network | |
CN113936140B (en) | Incremental learning-based evaluation method for challenge sample attack model | |
CN111914482A (en) | Driving condition generation method and system for automatic driving test | |
CN111537207B (en) | Data enhancement method for intelligent diagnosis of mechanical fault under small sample | |
CN116127854B (en) | Automatic driving virtual test scene generation method, system and equipment | |
Chen et al. | Application of Data‐Driven Iterative Learning Algorithm in Transmission Line Defect Detection | |
Chen et al. | Research on object detection algorithm based on multilayer information fusion | |
CN116206214A (en) | Automatic landslide recognition method, system, equipment and medium based on lightweight convolutional neural network and double attention | |
CN115713032A (en) | Power grid prevention control method, device, equipment and medium | |
CN113743317A (en) | License plate picture generation method, medium and equipment based on generation countermeasure network | |
Liu et al. | A deep neural network pruning method based on gradient L1-norm | |
Luo et al. | E-commerce big data classification and mining algorithm based on artificial intelligence | |
Peng et al. | Fault prediction method for on-board equipment of CTCS based on Seq2Seq model using LSTM | |
CN116527411B (en) | Data security intelligent protection model construction method and device and collaboration platform | |
Li et al. | Infrared Small Target Detection Algorithm Based on ISTD-CenterNet. |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201110 |
|
RJ01 | Rejection of invention patent application after publication |