CN113868873A - Automatic driving simulation scene expansion method and system based on data reinjection - Google Patents
Automatic driving simulation scene expansion method and system based on data reinjection Download PDFInfo
- Publication number
- CN113868873A CN113868873A CN202111155776.7A CN202111155776A CN113868873A CN 113868873 A CN113868873 A CN 113868873A CN 202111155776 A CN202111155776 A CN 202111155776A CN 113868873 A CN113868873 A CN 113868873A
- Authority
- CN
- China
- Prior art keywords
- data
- reinjection
- scene
- module
- information
- 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
- 238000004088 simulation Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 29
- 230000004927 fusion Effects 0.000 claims description 20
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 16
- 238000007499 fusion processing Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 238000011056 performance test Methods 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 2
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 2
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000006854 communication Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000012795 verification Methods 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automatic driving simulation scene expansion system based on data reinjection, and relates to an automobile performance test technology. Configuring sensor information required by automatic driving of an automobile, collecting all variable sets in a road test according to a preset time interval, automatically adding time sequences to all the collected variable sets according to a collection time interval, unifying time axes of all data in the variable sets to perform data classification, and ensuring that the data at the same moment are matched with each other; establishing a strategy set of data operation, modifying, expanding and splitting a scene according to the strategy set, fusing data processed by the reinjection simulation module with sensor acquisition information, a map and camera acquisition information, and storing different target information into a preset position to form a plurality of different target information. According to the invention, the scene is expanded according to the requirement of the test process, so that the scene content is greatly enriched, and the scene conversion and use efficiency is improved.
Description
Technical Field
The invention relates to an automobile performance testing technology, in particular to a method for combining different data types into a new scene based on scene data acquired by an automobile by adding, modifying, deleting and the like, thereby achieving the purpose of scene expansion. And the scene data is reinjected, so that an automobile test scene library is effectively enriched.
Background
In the simulation test scheme of the automatic driving automobile, in order to save the test cost, a part of tests are replaced by simulation. In the alternative, a data acquisition reinjection scheme is a preferred approach. Aiming at the existing data reinjection method, the following disadvantages exist: according to the existing collection reinjection testing technology, special equipment is needed in the reinjection process, the customized development degree is high, if multiple tests are needed, multiple pieces of equipment need to be purchased, the testing cost is increased, and the testing process management is complex.
Publication No.: the name CN 111025248A, "a data acquisition playback device and a data acquisition playback system" discloses a system for data acquisition playback, wherein an information processing module is connected with an acquisition interface, an upper computer interface and a recharge interface, and is used for receiving an acquisition interface signal through the acquisition interface in an acquisition state, converting the acquisition interface signal into an upper computer interface signal, and then sending the upper computer interface signal to the information processing module; and when in a recharging state, receiving an upper computer interface signal through the upper computer interface, converting the upper computer interface signal into a recharging interface signal and then sending the recharging interface signal to the recharging interface. The same system is used for data acquisition and recharging of the radar system, so that the complexity of data acquisition and in-loop test work is simplified, and the production cost is effectively reduced. The scene data played back by the device is the same as the real vehicle scene, and only the same scene can be tested each time, and the scene expansion cannot be carried out. The method needs to use data processing circuits such as an FPGA and the like, and has certain defects in use convenience and usability.
The chinese patent application publication No. CN113256976A entitled "a vehicle-road cooperative system, an analog simulation method, a vehicle-mounted device, and a roadside device" provides a vehicle-road cooperative system, an analog simulation method, a vehicle-mounted device, and a roadside device, and performs analog simulation of a vehicle-road cooperative environment according to configuration information, data collected by the roadside device, and data collected by the vehicle-mounted device to obtain a simulation result; and making a behavior decision according to the simulation result; the scheme can solve the problems that the traditional vehicle-road cooperative system is long in communication process, full of noise and high in development and verification cost.
The invention discloses a Chinese patent application with the name of 'auxiliary driving closed-loop test method based on data reinjection' in the publication number CN112925221A, and discloses an auxiliary driving closed-loop test method based on data reinjection, which is used for analyzing and splitting collected real vehicle data and extracting scene data; the ADAS algorithm module processes, arbitrates and decides according to the received data, acquires corresponding signals from the bus system module according to the required vehicle information, matches and connects the signals with the bus system module, and inputs the vehicle information and the scene data into the ADAS algorithm module to form closed-loop simulation.
Above-mentioned prior art is to same section data collection, and data are fixed, lead to the scene can not be modified, and one section data can only test a scene, and the availability factor of data can not be promoted, causes the data waste.
Disclosure of Invention
The method is based on the prior art that scene data are collected by a real vehicle, the collected scene is low in use efficiency, the scene cannot be expanded and the like, so that the problem of data waste is caused, and the collected data are processed according to a certain rule strategy. The invention adopts a new data processing mode to solve the problems and can expand the collected scenes. One scene can be evolved into a plurality of scenes according to the requirements, and then the reinjection test is carried out.
The method specifically comprises the following steps: the invention provides a technical scheme for solving the technical problems, and provides an automatic driving simulation scene expansion system based on data reinjection, which comprises the following steps: the system comprises a sensor configuration module, a data acquisition module, a reinjection simulation module, a fusion data module, a target information module and a user control module, wherein the sensor configuration module configures sensor information required by automatic driving of an automobile; the data acquisition module acquires all variable sets in the road test according to a preset time interval; the reinjection simulation module makes rule strategies according to the reinjection test requirements, the scene data are transformed according to the variable set, different rule strategies correspondingly generate different scene data, and various rule strategies can be combined to generate more scene data; the fusion data module fuses the data processed by the reinjection simulation module with sensor acquisition information, a map and camera acquisition information; and storing different target information into a preset position to form a plurality of different target information.
Further, the reinjection simulation module reads a signal sequence of the acquired data, a time tag is marked on each signal to obtain a time sequence for marking each signal, and if the frequency of the acquired signal is inconsistent with the required frequency, the acquired signal is converted into the required frequency by adopting an interpolation or secondary sampling mode.
Further, the fusion data module unifies a coordinate system, fusion processing is carried out on received data, sensor information, vehicle state information and switching value, perceived targets are matched with lane lines, the lane lines are matched with map data, after data fusion, the targets in original sensor information are sorted according to rules, and the targets are divided into different areas according to the relative position relation of the targets and the lane lines.
Further, the reinjection simulation module performs signal synchronization by using the time tag, operates the signal with the time sequence, copies the acquired single data into a copy, selects a signal sequence to be operated, manually or automatically adds the signal sequence, modifies a corresponding numerical value, or deletes a value in the signal sequence to make the sequence empty.
And the reinjection simulation module classifies data according to a determined data acquisition format, the classified data automatically adds time sequences according to the acquired time intervals, the time axes of all data are unified, the data at the same moment are ensured to be matched with each other during reinjection, a strategy set of data operation is established, and the scene is modified, expanded and split according to the strategy set.
The invention also provides an automatic driving simulation scene expansion method based on data reinjection, which is characterized in that a sensor configuration module configures sensor information required by automatic driving of an automobile; the data acquisition module acquires all variable sets in the road test according to a preset time interval; the reinjection simulation module makes rule strategies according to the reinjection test requirements, changes scene data, correspondingly generates different scene data according to different rule strategies, and can combine various rule strategies to generate more scene data; the fusion data module fuses the data processed by the reinjection simulation module with sensor acquisition information, a map and camera acquisition information; and storing different target information into a preset position to form a plurality of different target information.
According to the invention, the scene data is used for multiple times, and multiple rounds of iterative tests are carried out by using the same data, so that the use efficiency and the simulation value of the data are improved. According to the needs of the test process, the scene can be modified by expanding the scene, various scenes can be tested by one section of data, the use efficiency of the data is improved, the cost of collection, storage and the like can be saved for enterprises, the scene can be modified in a self-defined mode, a plurality of reinjection scenes can be generated in the same collection scene, the number of the scenes is greatly enriched, and the use efficiency of scene conversion is improved.
Drawings
FIG. 1 is a schematic diagram of a scene expansion function module structure based on data reinjection;
fig. 2 is a schematic diagram of a reinjection simulation module.
Detailed Description
The invention is further described in the following with reference to the figures and the specific embodiments.
Fig. 1 shows a scene expanding system based on data reinjection, which includes: the device comprises a sensor configuration module, a data acquisition module, a reinjection simulation module, a fusion data module and a user scene module. The sensor configuration module determines initial information such as the number, the types, the installation positions, the calibration coordinate system and the output information of the collected vehicle sensors, the data collection module collects a variable set formed by related data in a road test, specifically comprises detected lane lines (comprising a lane line equation, the length of the lane lines, the color of the lane lines, the types of the lane lines and the like), target information (transverse distance, longitudinal distance, transverse speed, longitudinal speed, the type movement state of obstacles and the like) of the detected obstacles, vehicle state information of the vehicle, guideboard information, speed limit information, switching amount and the like, and covers all information which can be provided by the collected vehicle sensors. The collected related data is input into the reinjection simulation module, and a section of collected data is called as an original scene.
The reinjection simulation module classifies data according to a determined data acquisition variable set format, time sequences are automatically added to the classified variable sets according to acquired time intervals, time axes of all variable sets are unified, matching between the variable sets at the same moment is guaranteed during reinjection, meanwhile, the reinjection simulation module can perform operations such as screening, modification and deletion on data values of record classification, a specific strategy set of data operation is established, a scene is modified, expanded and split according to the strategy set, and scene elements after expansion are consistent with those before expansion. The scene data is processed by the reinjection simulation module and then input into the fusion data module, the fusion data module performs fusion processing on the received data, sensor information, vehicle state information and switching value, and the fusion method can be matching the sensed target with a lane line, matching the lane line with map data and the like. After data fusion, the targets in the original sensor information are sorted according to a certain rule, for example, the target in the front of the vehicle is the target No. 1, the target in the left lane is the target No. 2, and the target in the right lane is the target No. 3. The fused information is packaged into a user scene library through a user scene module for the user to use.
The sensor configuration module sets the type, the number, the installation position, the information output by each sensor, an information unit, a calibration coordinate system, a time sequence and other information according to various sensors (including the sensors such as a camera, a radar and the like which are installed at different positions of a vehicle body and collect different information) required by the automatic driving vehicle. The information jointly forms a sensor information set, and the information set output by the sensor configuration module and the information set output by the reinjection simulation module have the same attribute.
The data acquisition module acquires relevant data in road testing, and performs sampling recording on data output by the sensor in the testing process at a preset frequency, wherein the acquired information comprises a sensor information set, vehicle state information, switching value and the like, and covers all information which can be provided by the automobile sensor.
Each information collects data according to the own natural frequency, and the collected data is subjected to data processing (such as Matlab/Simulink). Arranging data of each target (including longitudinal speed, longitudinal distance, transverse speed, transverse distance, target type, target state and the like), each lane line and the like according to a column sequence, wherein the first column is acquisition time, subsequent data are arranged in sequence, and each column of data is called a signal.
As shown in fig. 2, which is a schematic diagram of a reinjection simulation module, data processed by a data processing module enters the reinjection simulation module, a signal sequence of acquired data is read, a time tag is marked on each signal, and a time sequence for marking each signal is obtained and becomes a signal with a time sequence; based on the required frequency (frequency = 1/acquisition interval), if the acquired signal frequency is not consistent with the required frequency, the acquired signal frequency is converted into the required frequency by means of interpolation or subsampling,
and the time tag is utilized to carry out signal synchronization on the signals required by the reinjection module so as to solve the problem of signal disorder. The method comprises the steps of carrying out operations including screening, adding, modifying, deleting and the like on signals with time sequences, formulating a scene rule strategy, copying acquired single data into a copy, selecting a signal sequence needing to be operated, manually or automatically adding the signal sequence, modifying corresponding numerical values, or deleting original values in the signal sequence to make the sequence empty. Noise may also be added to the selected sequence to make the sequence values more realistic.
For example, the distance in the target information attribute is screened, various noises are superimposed on the distance attribute signal, the distance information fluctuates according to the noises, a certain lane line can also be screened, the lane line is deleted, the type, length, color and the like of the lane line are modified, all information attributes of a certain target can also be screened, and a certain attribute of the target is modified, for example, the target is modified into an animal, and a trolley is modified into a truck; all attributes of the object may be deleted, and the object information may disappear after deletion.
According to the reinjection testing requirement, rule strategies are formulated, scene data are transformed, different scene data can be generated by different rule strategies, and various rule strategies can be combined to generate more scene data.
The data after the reinjection simulation is input into the fusion data module, and the fusion data module matches a target information sequence, such as a target longitudinal distance, a target transverse distance and a specific lane line, a lane line and a map and the like. The specific fusion mode is that a coordinate system is unified firstly, and the transverse distance of the target is compared with the coordinate of the lane line. If the target is right in front of the lane and is in the middle of the two nearest lane lines, the target is the target No. 1, and all information under the target is marked with the label 1. If the target is in the left front of the own lane and is at the left side of the left lane line, the target is the target No. 2, all information under the target is labeled with the label 2, and so on. And finally, dividing the target into different areas according to the relative position relation between the target and the lane line. The fusion information module also calculates parameters such as curvature radius and the like according to the lane line information to control the automobile driving path.
The user scene module is simply an interface program, and can build an information interface framework according to the use requirement of the back end. Different information is placed at the designated interface position, and all interfaces in the requirement are placed at the designated position in the frame, so that a scene is packaged. In the whole process, data flows in a single direction from the front-end sensor scheme to the user scene module, and an open-loop test is performed.
Claims (10)
1. An automatic driving simulation scene expansion system based on data reinjection, comprising: the system comprises a sensor configuration module, a data acquisition module, a reinjection simulation module, a fusion data module, a target information module and a user control module, wherein the sensor configuration module configures sensor information required by automatic driving of an automobile; the data acquisition module acquires all variable sets in the road test according to a preset time interval; the reinjection simulation module makes rule strategies according to the reinjection test requirements, the scene data are transformed according to the variable set, different rule strategies correspondingly generate different scene data, and various rule strategies can be combined to generate more scene data; and the fusion data module fuses the variable set processed by the reinjection simulation module with the sensor acquisition information, the map and the camera acquisition information, and divides the target into different areas according to the relative position relationship between the target and the lane line.
2. The system of claim 1, wherein the reinjection simulation module reads a signal sequence of the acquired variable set, time-stamps each signal to obtain a time sequence for marking each signal, and converts the acquired variable set signal frequency into the required frequency by interpolation or subsampling if the acquired variable set signal frequency is not consistent with the required frequency.
3. The system of claim 1, wherein the fusion data module unifies a coordinate system, performs fusion processing on the received variable sets, the sensor information, the vehicle state information and the switching value, matches the sensed targets with lane lines, matches the lane lines with map data, sorts the targets in the original sensor information according to rules after data fusion, and divides the targets into different regions according to the relative position relationship between the targets and the lane lines.
4. The system of claim 2, wherein the reinjection simulation module uses the time tag to synchronize signals, manipulate time-sequenced signals, copy acquired individual data as duplicates, select a signal sequence to be manipulated, manually or automatically add a signal sequence, modify a corresponding value, or delete a value in the signal sequence leaving the sequence empty.
5. The system of claim 2, wherein the reinjection simulation module classifies data according to a determined data acquisition format, the classified data is automatically added with time sequences according to an acquisition time interval, time axes of all data are unified, mutual matching of the data at the same time is guaranteed during reinjection, a strategy set of data operation is established, and a scene is modified, expanded and split according to the strategy set.
6. An automatic driving simulation scene expansion method based on data reinjection is characterized in that a sensor configuration module configures sensor information required by automatic driving of an automobile; the data acquisition module acquires all variable sets in the road test according to a preset time interval; the reinjection simulation module makes rule strategies according to the reinjection test requirements, the scene data are transformed according to the variable set, different rule strategies correspondingly generate different scene data, and various rule strategies can be combined to generate more scene data; the fusion data module fuses the data processed by the reinjection simulation module with sensor acquisition information, a map and camera acquisition information; and dividing the target into different areas according to the relative position relation between the target and the lane line.
7. The automatic driving simulation scene expanding method of claim 6, wherein the reinjection simulation module reads a signal sequence of the acquisition variable set, time tags are applied to each signal to obtain a time sequence for marking each signal, and if the frequency of the acquired signal is not consistent with the required frequency, the signal is converted into the required frequency by adopting an interpolation or secondary sampling mode.
8. The automatic driving simulation scene expanding method of claim 6, wherein the fusion data module unifies a coordinate system, performs fusion processing on received data, sensor information, vehicle state information and switching value, matches a sensed target with a lane line, matches the lane line with map data, sorts the targets in the original sensor information according to rules after data fusion, and divides the targets into different areas according to the relative position relationship between the targets and the lane line.
9. The method of claim 7, wherein the reinjection simulation module synchronizes signals using time tags, operates signals with time series, copies single collected data as a copy, selects a signal sequence to be operated, manually or automatically adds a signal sequence, modifies a corresponding numerical value, or deletes a value in the signal sequence to make the sequence empty.
10. The method for expanding the automatic driving simulation scene according to claim 7, wherein the reinjection simulation module classifies data according to a determined data acquisition format, the classified data automatically adds time sequences according to the acquired time intervals, the time axes of all data are unified, mutual matching of the data at the same time is guaranteed during reinjection, a strategy set of data operation is established, and the scene is modified, expanded and split according to the strategy set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111155776.7A CN113868873A (en) | 2021-09-30 | 2021-09-30 | Automatic driving simulation scene expansion method and system based on data reinjection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111155776.7A CN113868873A (en) | 2021-09-30 | 2021-09-30 | Automatic driving simulation scene expansion method and system based on data reinjection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113868873A true CN113868873A (en) | 2021-12-31 |
Family
ID=79000873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111155776.7A Pending CN113868873A (en) | 2021-09-30 | 2021-09-30 | Automatic driving simulation scene expansion method and system based on data reinjection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113868873A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114415898A (en) * | 2022-01-14 | 2022-04-29 | 重庆长安汽车股份有限公司 | Method and system for reinjecting real vehicle data into Simulink model |
| CN114488854A (en) * | 2022-01-26 | 2022-05-13 | 上海和夏新能源科技有限公司 | Intelligent driving and ADAS analog simulation method and system based on test data |
| CN115167374A (en) * | 2022-08-09 | 2022-10-11 | 科大国创合肥智能汽车科技有限公司 | Automatic driving sensor recharging virtual simulation test method and system thereof |
| CN115797442A (en) * | 2022-12-01 | 2023-03-14 | 昆易电子科技(上海)有限公司 | Simulation image reinjection method of target position and related equipment thereof |
| CN117763342A (en) * | 2023-11-01 | 2024-03-26 | 上海泽尔汽车科技有限公司 | Automatic driving data reinjection method and system based on environment awareness |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111897305A (en) * | 2020-06-02 | 2020-11-06 | 浙江吉利汽车研究院有限公司 | Data processing method, device, equipment and medium based on automatic driving |
| CN112287566A (en) * | 2020-11-24 | 2021-01-29 | 北京亮道智能汽车技术有限公司 | Automatic driving scene library generation method and system and electronic equipment |
| CN112528477A (en) * | 2020-12-03 | 2021-03-19 | 安徽江淮汽车集团股份有限公司 | Road scene simulation method, equipment, storage medium and device |
| CN113160454A (en) * | 2021-05-31 | 2021-07-23 | 重庆长安汽车股份有限公司 | Method and system for recharging historical sensor data of automatic driving vehicle |
-
2021
- 2021-09-30 CN CN202111155776.7A patent/CN113868873A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111897305A (en) * | 2020-06-02 | 2020-11-06 | 浙江吉利汽车研究院有限公司 | Data processing method, device, equipment and medium based on automatic driving |
| CN112287566A (en) * | 2020-11-24 | 2021-01-29 | 北京亮道智能汽车技术有限公司 | Automatic driving scene library generation method and system and electronic equipment |
| CN112528477A (en) * | 2020-12-03 | 2021-03-19 | 安徽江淮汽车集团股份有限公司 | Road scene simulation method, equipment, storage medium and device |
| CN113160454A (en) * | 2021-05-31 | 2021-07-23 | 重庆长安汽车股份有限公司 | Method and system for recharging historical sensor data of automatic driving vehicle |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114415898A (en) * | 2022-01-14 | 2022-04-29 | 重庆长安汽车股份有限公司 | Method and system for reinjecting real vehicle data into Simulink model |
| CN114415898B (en) * | 2022-01-14 | 2023-06-06 | 重庆长安汽车股份有限公司 | Method and system for reinjecting real vehicle data into Simulink model |
| CN114488854A (en) * | 2022-01-26 | 2022-05-13 | 上海和夏新能源科技有限公司 | Intelligent driving and ADAS analog simulation method and system based on test data |
| CN115167374A (en) * | 2022-08-09 | 2022-10-11 | 科大国创合肥智能汽车科技有限公司 | Automatic driving sensor recharging virtual simulation test method and system thereof |
| CN115797442A (en) * | 2022-12-01 | 2023-03-14 | 昆易电子科技(上海)有限公司 | Simulation image reinjection method of target position and related equipment thereof |
| CN115797442B (en) * | 2022-12-01 | 2024-06-07 | 昆易电子科技(上海)有限公司 | Simulation image reinjection method of target position and related equipment thereof |
| CN117763342A (en) * | 2023-11-01 | 2024-03-26 | 上海泽尔汽车科技有限公司 | Automatic driving data reinjection method and system based on environment awareness |
| CN117763342B (en) * | 2023-11-01 | 2024-10-11 | 上海泽尔汽车科技有限公司 | Automatic driving data reinjection method and system based on environment awareness |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113868873A (en) | Automatic driving simulation scene expansion method and system based on data reinjection | |
| US5608858A (en) | Method and system for registering and filing image data | |
| CN113343461A (en) | Simulation method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN112396093B (en) | Driving scene classification method, device and equipment and readable storage medium | |
| CN104679658A (en) | Test method and test system for WEB pages | |
| EP2735984A1 (en) | Video query method, device and system | |
| CN109033338A (en) | Method and system for generating database file of automobile communication protocol | |
| CN111797526A (en) | Simulation test scene construction method and device | |
| CN116484971A (en) | Automatic driving perception self-learning method and device for vehicle and electronic equipment | |
| CN114462233A (en) | Microscopic traffic simulation method, computer device and storage medium | |
| CN110515543A (en) | Object bucket-based snapshot method, device and system | |
| CN106484789A (en) | The storage management system and method for pictorial information | |
| CN113934885A (en) | ADAS video data recharge performance verification system and method based on local area network | |
| CN111881121A (en) | Automatic driving data filling method and device | |
| CN115987865A (en) | Routing code generation method and device, matrix detection method and storage medium | |
| CN115543809A (en) | Method and device for constructing test scene library of automatic driving function | |
| CN114089773B (en) | Test method, device, equipment and storage medium for automatic driving vehicle | |
| CN115937352A (en) | Mine scene simulation method, mine scene simulation system, electronic equipment and storage medium | |
| CN115858456A (en) | Data acquisition system and method for automatic driving vehicle | |
| CN115661723A (en) | Multi-scene monitoring method based on Haesi SD3403 | |
| CN114428738A (en) | Virtual test scene processing method, management platform, device, equipment and medium | |
| CN111143423B (en) | Dynamic scene labeling data mining method and device and terminal | |
| CN114048120A (en) | Unmanned equipment multi-stage system testing method, device, equipment and storage medium | |
| CN106372121A (en) | Server and data processing method | |
| KR102668354B1 (en) | Data Acquisition System for Tractor Autonomous Driving, and Method Thereof |
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 |