CN113160454A - Method and system for recharging historical sensor data of automatic driving vehicle - Google Patents
Method and system for recharging historical sensor data of automatic driving vehicle Download PDFInfo
- Publication number
- CN113160454A CN113160454A CN202110602603.9A CN202110602603A CN113160454A CN 113160454 A CN113160454 A CN 113160454A CN 202110602603 A CN202110602603 A CN 202110602603A CN 113160454 A CN113160454 A CN 113160454A
- Authority
- CN
- China
- Prior art keywords
- data
- camera
- dat
- automatic driving
- file
- 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 25
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims description 23
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method for realizing data recharging of a historical sensor based on a data splicing technology, which comprises the following steps of (1) matching whole vehicle information in a dat file with whole vehicle information in a camera pack file, finding out the position of each frame of data of a camera to be inserted into the dat, and storing the position of each frame to be inserted as a map; (2) converting the lane line of each frame in the camera pack data and the target vehicle information into a data format in dat by using the map obtained after matching, and inserting the data format into the dat for data splicing; (3) and (5) recharging the spliced data into an automatic driving fusion algorithm, and verifying whether the automatic driving error problem still occurs in the historical scene. The method and the system perform secondary utilization on the historical driving scene and the historical data of the automatic driving vehicle, avoid data waste and are beneficial to verifying the effectiveness of the automatic driving algorithm on the historical scene.
Description
Technical Field
The present invention relates to a technique for reusing history sensor data of an autonomous vehicle.
Background
In the development process of the automatic driving technology, a large number of road tests are required to be carried out nationwide so as to verify the safety and feasibility of the automatic driving technology. Since the number of sensors mounted on the autonomous vehicle is large, a huge amount of data is generated during the test. Secondary usage of historical driving scenes and historical data of an autonomous vehicle is a desirable direction. For example, a tesla camera has two chips, one is responsible for running an autopilot algorithm and the other is responsible for collecting data to train a neural network, and for data of an actual road, tesla uses the data to continuously optimize the autopilot algorithm.
Chinese patent document CN202010436745.8 discloses an automatic driving data processing method, device and electronic device, which proposes a method for intercepting and recharging data of problem scene data, comprising: acquiring initial scene data of an automatic driving vehicle running an automatic driving system when the automatic driving vehicle runs in a real environment, wherein the initial scene data comprises data of a defect scene; intercepting data of the defect scene from the initial scene data; and inputting the data of the defect scene into a simulation platform, and running the updated automatic driving system by the simulation platform based on the data of the defect scene to obtain a running result of the updated automatic driving system in the defect scene. According to the method, only data corresponding to a scene with a problem is intercepted from test data, but for the situation that the scene with the problem is caused by the recognition error of the sensor, the method cannot effectively utilize the test data, and the problem cannot be solved because only the data is intercepted.
Disclosure of Invention
The invention provides a method for realizing automatic driving vehicle historical sensor data recharging based on a data splicing technology, and aims to carry out secondary utilization on historical driving scenes and historical data of an automatic driving vehicle, utilize massive historical data in the automatic driving field, avoid data waste and be beneficial to verifying the effectiveness of an automatic driving algorithm on the historical scenes.
The technical scheme of the invention is as follows:
a method for realizing automatic driving vehicle historical sensor data recharging based on a data splicing technology is applied to a scene that automatic driving is wrong due to the fact that camera data are out of order during road test, and on the premise that a supplier modifies a camera algorithm and provides new camera data (namely new pack data) in the scene. The method comprises the following steps:
step (1), matching vehicle information in a dat file storing data received from each sensor with vehicle information in a camera pack file, finding out which position of each frame of data of a camera needs to be inserted into the dat, storing the position of each frame needing to be inserted as a map, wherein the absolute time matched in the dat is key, and the absolute time matched in the pack is value;
step (2), by using the map obtained after matching, converting the lane line of each frame in the camera pack data and the target vehicle information into a data format in dat and inserting the data format into the dat for data splicing;
and (3) recharging the spliced data into an automatic driving fusion algorithm, and verifying whether the automatic driving error problem still occurs in the historical scene.
The dat file is a data file which is sent out by a camera and other sensors through a peakCan, enters a fusion algorithm and is stored, and comprises original sensor data and processed intermediate variable data; the whole vehicle information in the dat file comprises the speed of the vehicle, the steering wheel angle, the steering wheel angular speed and the like;
the camera pack file is data stored by a supplier, and the whole vehicle information in the pack file comprises images recorded by the camera, target vehicles and lane line data.
The present invention still further provides an autonomous vehicle history sensor data recharging system comprising:
and the matching module is used for matching the whole vehicle information in the dat file with the whole vehicle information in the pack file of the camera to find out which position of each frame of data of the camera needs to be inserted into the dat file, the position of each frame needing to be inserted is stored as a map, the absolute time matched in the dat is key, and the absolute time matched in the pack is value.
And the data splicing module is used for converting the lane line of each frame in the camera pack data and the target vehicle information into a data format in the dat file by using the map obtained after matching, and inserting the data format into the dat file for data splicing.
And the recharging module recharges the spliced data into an automatic driving fusion algorithm and verifies whether the historical scene has the problem of automatic driving errors.
The method has the starting point that historical data is utilized, automatic driving is caused to be problematic due to the fact that a camera identifies a target and a lane line in a wrong mode, a camera supplier recharges data in a pack file, and then the camera supplier provides a new pack file after rectification and modification are completed. And splicing the data processed by the camera and the historical data of other sensors together, and recharging the data into the automatic driving fusion algorithm so as to verify whether the automatic driving fusion algorithm has the empty vehicle error aiming at the scene.
Therefore, the method can be used as a part of data processing in the automatic driving technology, can greatly utilize historical data in the testing process, and can effectively verify the performance of the automatic driving sensor fusion algorithm in the process of saving the testing cost.
Description of the drawings:
FIG. 1: the invention relates to a processing flow of an automatic driving real road test on a camera problem;
FIG. 2: the invention relates to vehicle information in camera data (pack format file);
FIG. 3: blf converts the information of the whole vehicle in dat (dat format file); blf is a general binary data file for recording CAN data;
FIG. 4: the matched dat and pack data are obtained in the invention.
Detailed Description
The techniques of the present invention are described in further detail below with reference to the accompanying drawings:
the invention mainly aims at the splicing technology of historical data of a plurality of sensors on the existing automatic driving vehicle.
For example, data of a camera is recorded in an actual road testing process, wherein one part of data is pack data stored by a supplier, and the other part of data is a dat data set which is sent out by the camera through a peakCan, enters a fusion algorithm and is stored. When a scene with automatic driving errors caused by camera data problems is encountered, firstly, a supplier modifies a camera algorithm, then new camera data under the scene are provided, at this time, the data (the camera data stored in the pack and including targets and lane lines) and data of other sensors (front radar, angle radar, look around and the like stored in the dat) need to be spliced together, and then whether the fusion algorithm can pass the test of the scene is verified.
The processing flow of the automatic driving real road test to the camera problem refers to fig. 1:
Step 2, road test problem: there are generally two categories, one is that sensor identification problems cause autopilot errors, and the other is that algorithm problems cause autopilot errors.
Step 3, FC problem: front camera problem.
Step 4, the supplier modifies the algorithm: the camera problem is firstly fed back to a supplier, and a pack file obtained in a road test is sent to the supplier, so that the problem is waited to be determined by the supplier and a camera algorithm is modified.
Step 5, real vehicle testing: after the supplier modifies the camera algorithm, the host factory needs to verify whether the new camera algorithm solves the previous road test problem through the road test.
Step 6, data splicing: in the step 5, the actual vehicle road test cannot find the environment which is the same as the road test problem scene in the step 1 (the environment is different, which brings difficulty to the verification of the sensor algorithm), and the spliced data is completely consistent with the scene data in the step 1 by adopting data splicing.
In step 1: generally, the data cycle of the camera pack is about 20ms, the information cycle of the whole vehicle stored in dat is about 10ms, and the matched dat and pack data shown in fig. 4 are taken as an example of speed. As can be seen from the figure, only a part of the pack data and dat data can be matched, and the purpose of step 1 is to find out when the pack data and dat data are matched from, and store the time of all the matches into the map for splicing the subsequent data.
And 2, converting lane lines (6) of each frame in the camera pack data and targets (20 pieces of target vehicle information) into a data format in dat by using the map obtained after matching, and inserting the data format into the dat.
The step 2 specifically comprises the following steps: from the matching information (map) obtained in step 1, the matching time of each frame data can be known, the targets (20) and lane lines (6) in the pack data are converted into the format of CANFD, and then the data are inserted into the dat data, so that the data insertion is completed.
And 3, recharging the spliced data into an automatic driving fusion algorithm, and verifying whether the historical scene has a vehicle control problem.
The step 3 specifically comprises the following steps: and (3) building a data reinjection rack (comprising an industrial personal computer, a controller, a voltage-stabilized power supply and the like), performing offline reinjection on the spliced data on the rack, and verifying whether the fusion algorithm can cause control errors in a problem scene. The data reinjection rack is a tool for an offline running algorithm simply understood, data received by a real vehicle test are also sent to the controller through PeakCan, the principle of the data reinjection rack is the same, and can signals are sent to the controller in a simulation mode to conduct offline simulation.
Therefore, the invention can splice the modified data (the data is obtained by taking back the pack file by the sensor supplier and modifying the algorithm to obtain new sensor data) with the historical data by the data splicing technology, thereby not only utilizing the road test data with problems, but also verifying whether the sensor manufacturer is in place or not.
Embodiment 2 provides an autonomous vehicle history sensor data recharging system implementing the method of an embodiment, comprising:
and the matching module is used for matching the whole vehicle information in the dat file with the whole vehicle information in the pack file of the camera to find out which position of each frame of data of the camera needs to be inserted into the dat file, the position of each frame needing to be inserted is stored as a map, the absolute time matched in the dat is key, and the absolute time matched in the pack is value.
And the data splicing module is used for converting the lane line of each frame in the camera pack data and the target vehicle information into a data format in the dat file by using the map obtained after matching, and inserting the data format into the dat file for data splicing.
And the recharging module recharges the spliced data into an automatic driving fusion algorithm and verifies whether the historical scene has the problem of automatic driving errors.
Claims (5)
1. A history sensor data recharging method for an automatic driving vehicle is applied to a scene that automatic driving is wrong due to the fact that data of a camera is in a problem during vehicle road test, and under the premise that a supplier modifies a camera algorithm and provides new camera data under the scene; the method comprises the following steps:
step (1), matching the whole vehicle information in the dat file with the whole vehicle information in the pack file of the camera to find out which position of each frame of data of the camera needs to be inserted into the dat file, storing the position of each frame needing to be inserted as a map, wherein the absolute time matched in the dat is key, and the absolute time matched in the pack is value;
step (2), by using the map obtained after matching, converting the lane line of each frame in the camera pack data and the target vehicle information into a data format in the dat file, inserting the data format into the dat file, and performing data splicing;
and (3) recharging the spliced data into an automatic driving fusion algorithm, and verifying whether the automatic driving error problem still occurs in the historical scene.
2. The method of recharging history sensor data of an autonomous vehicle as claimed in claim 1, wherein the dat files are data files sent by cameras and other sensors through peakCan into a fusion algorithm and stored, containing raw sensor data and processed intermediate variable data; the whole vehicle information in the dat file comprises the speed of the vehicle, the steering wheel angle, the steering wheel angular speed and the like;
the camera pack file is data stored by a supplier, and the whole vehicle information in the pack file comprises images recorded by the camera, target vehicles and lane line data.
3. The method of claim 1, wherein each frame of data has a plurality of lane lines and a plurality of target vehicle information.
4. The method of recharging historical sensor data of an autonomous vehicle as claimed in claim 1, wherein step (3) is performed in a built data recharging stand, and spliced data is recharged offline on the stand; the data reinjection rack comprises an industrial personal computer, a controller, a voltage-stabilized power supply and the like.
5. Implementing the autonomous vehicle history sensor data recharging system of any of claims 1-4, comprising:
the matching module is used for matching the whole vehicle information in the dat file with the whole vehicle information in the pack file of the camera to find out which position of each frame of data of the camera needs to be inserted into the dat file, the position of each frame needing to be inserted is stored as a map, the absolute time matched in the dat is key, and the absolute time matched in the pack is value;
the data splicing module is used for converting the lane line of each frame in the camera pack data and the target vehicle information into a data format in the dat file by using the map obtained after matching, inserting the data format into the dat file and splicing the data;
and the recharging module recharges the spliced data into an automatic driving fusion algorithm and verifies whether the historical scene has the problem of automatic driving errors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110602603.9A CN113160454A (en) | 2021-05-31 | 2021-05-31 | Method and system for recharging historical sensor data of automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110602603.9A CN113160454A (en) | 2021-05-31 | 2021-05-31 | Method and system for recharging historical sensor data of automatic driving vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113160454A true CN113160454A (en) | 2021-07-23 |
Family
ID=76875481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110602603.9A Pending CN113160454A (en) | 2021-05-31 | 2021-05-31 | Method and system for recharging historical sensor data of automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113160454A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113868873A (en) * | 2021-09-30 | 2021-12-31 | 重庆长安汽车股份有限公司 | Automatic driving simulation scene expansion method and system based on data reinjection |
| CN114722249A (en) * | 2022-03-17 | 2022-07-08 | 福思(杭州)智能科技有限公司 | Vehicle recharge data analysis method and system, electronic equipment and storage medium |
| 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 |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090248224A1 (en) * | 2003-10-03 | 2009-10-01 | Kurt Tschannen | Integrated Air Navigation and Flight Control System |
| CN101620542A (en) * | 2009-07-30 | 2010-01-06 | 深圳市蓝韵实业有限公司 | Compatible updating method of ultrasonic imaging equipment software data |
| CN107528757A (en) * | 2017-08-30 | 2017-12-29 | 北京润科通用技术有限公司 | A kind of monitoring method of MVB data, apparatus and system |
| CN108957413A (en) * | 2018-07-20 | 2018-12-07 | 重庆长安汽车股份有限公司 | Sensor target positional accuracy test method |
| CN109188932A (en) * | 2018-08-22 | 2019-01-11 | 吉林大学 | A kind of multi-cam assemblage on-orbit test method and system towards intelligent driving |
| CN109212499A (en) * | 2017-07-07 | 2019-01-15 | 英飞凌科技股份有限公司 | Use the system and method for radar sensor identification target |
| CN109407547A (en) * | 2018-09-28 | 2019-03-01 | 合肥学院 | Multi-camera in-loop simulation test method and system for panoramic visual perception |
| CN110009765A (en) * | 2019-04-15 | 2019-07-12 | 合肥工业大学 | A kind of automatic driving vehicle contextual data system and scene format method for transformation |
| US20190383631A1 (en) * | 2018-06-18 | 2019-12-19 | Nio Usa, Inc. | Autonomous vehicle sensor data and map integration |
| CN111104535A (en) * | 2019-11-20 | 2020-05-05 | 中国第一汽车股份有限公司 | Data management system and data management method |
| CN111327857A (en) * | 2020-03-23 | 2020-06-23 | 维沃软件技术有限公司 | Video data recovery method, electronic device, and storage medium |
| CN111516673A (en) * | 2020-04-30 | 2020-08-11 | 重庆长安汽车股份有限公司 | Lane line fusion system and method based on intelligent camera and high-precision map positioning |
| CN111735642A (en) * | 2020-07-30 | 2020-10-02 | 北汽福田汽车股份有限公司 | Road test method and device of automatic braking system |
| CN112099481A (en) * | 2019-06-18 | 2020-12-18 | 宝马股份公司 | Method and system for constructing road model |
| CN112115552A (en) * | 2020-09-16 | 2020-12-22 | 天津津航计算技术研究所 | Airborne flight data recharging method and device |
| CN112492294A (en) * | 2019-09-12 | 2021-03-12 | 北京地平线机器人技术研发有限公司 | Application program testing method, device and system, network camera and medium |
| 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 |
| CN112541261A (en) * | 2020-12-09 | 2021-03-23 | 中国航空工业集团公司沈阳飞机设计研究所 | Target track fusion assessment method based on data recharging function |
| US11001231B1 (en) * | 2019-02-28 | 2021-05-11 | Ambarella International Lp | Using camera data to manage a vehicle parked outside in cold climates |
| CN112817873A (en) * | 2021-03-02 | 2021-05-18 | 上海初斟智能科技有限公司 | Millimeter wave radar alarm automatic testing method |
-
2021
- 2021-05-31 CN CN202110602603.9A patent/CN113160454A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090248224A1 (en) * | 2003-10-03 | 2009-10-01 | Kurt Tschannen | Integrated Air Navigation and Flight Control System |
| CN101620542A (en) * | 2009-07-30 | 2010-01-06 | 深圳市蓝韵实业有限公司 | Compatible updating method of ultrasonic imaging equipment software data |
| CN109212499A (en) * | 2017-07-07 | 2019-01-15 | 英飞凌科技股份有限公司 | Use the system and method for radar sensor identification target |
| CN107528757A (en) * | 2017-08-30 | 2017-12-29 | 北京润科通用技术有限公司 | A kind of monitoring method of MVB data, apparatus and system |
| US20190383631A1 (en) * | 2018-06-18 | 2019-12-19 | Nio Usa, Inc. | Autonomous vehicle sensor data and map integration |
| CN108957413A (en) * | 2018-07-20 | 2018-12-07 | 重庆长安汽车股份有限公司 | Sensor target positional accuracy test method |
| CN109188932A (en) * | 2018-08-22 | 2019-01-11 | 吉林大学 | A kind of multi-cam assemblage on-orbit test method and system towards intelligent driving |
| CN109407547A (en) * | 2018-09-28 | 2019-03-01 | 合肥学院 | Multi-camera in-loop simulation test method and system for panoramic visual perception |
| US11001231B1 (en) * | 2019-02-28 | 2021-05-11 | Ambarella International Lp | Using camera data to manage a vehicle parked outside in cold climates |
| CN110009765A (en) * | 2019-04-15 | 2019-07-12 | 合肥工业大学 | A kind of automatic driving vehicle contextual data system and scene format method for transformation |
| CN112099481A (en) * | 2019-06-18 | 2020-12-18 | 宝马股份公司 | Method and system for constructing road model |
| CN112492294A (en) * | 2019-09-12 | 2021-03-12 | 北京地平线机器人技术研发有限公司 | Application program testing method, device and system, network camera and medium |
| CN111104535A (en) * | 2019-11-20 | 2020-05-05 | 中国第一汽车股份有限公司 | Data management system and data management method |
| CN111327857A (en) * | 2020-03-23 | 2020-06-23 | 维沃软件技术有限公司 | Video data recovery method, electronic device, and storage medium |
| CN111516673A (en) * | 2020-04-30 | 2020-08-11 | 重庆长安汽车股份有限公司 | Lane line fusion system and method based on intelligent camera and high-precision map positioning |
| CN111735642A (en) * | 2020-07-30 | 2020-10-02 | 北汽福田汽车股份有限公司 | Road test method and device of automatic braking system |
| CN112115552A (en) * | 2020-09-16 | 2020-12-22 | 天津津航计算技术研究所 | Airborne flight data recharging method and device |
| 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 |
| CN112541261A (en) * | 2020-12-09 | 2021-03-23 | 中国航空工业集团公司沈阳飞机设计研究所 | Target track fusion assessment method based on data recharging function |
| CN112817873A (en) * | 2021-03-02 | 2021-05-18 | 上海初斟智能科技有限公司 | Millimeter wave radar alarm automatic testing method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113868873A (en) * | 2021-09-30 | 2021-12-31 | 重庆长安汽车股份有限公司 | Automatic driving simulation scene expansion method and system based on data reinjection |
| CN114722249A (en) * | 2022-03-17 | 2022-07-08 | 福思(杭州)智能科技有限公司 | Vehicle recharge data analysis method and system, electronic equipment and storage medium |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113160454A (en) | Method and system for recharging historical sensor data of automatic driving vehicle | |
| CN108919785B (en) | Test system and test method | |
| CN112102646B (en) | Parking lot entrance positioning method and device in parking positioning and vehicle-mounted terminal | |
| CN110775073B (en) | Method, controller and storage medium for identifying degraded performance of a sensor | |
| CN113815453B (en) | Charging method, charging system, medium and computer equipment | |
| CN109450582A (en) | Sensor time stabs synchronous detecting method, device, equipment, medium and vehicle | |
| US20210073626A1 (en) | System, method, and apparatus for a neural network model for a vehicle | |
| CN107571864A (en) | The collecting method and device of automatic driving vehicle | |
| CN110116727B (en) | Real vehicle testing method of lane center keeping system | |
| WO2024131678A1 (en) | Intelligent driving in-loop test method and environment with real road scenario fused therein, and storage medium | |
| CN111267860B (en) | Sensor fusion target prediction device and method for vehicle and vehicle | |
| US20200401150A1 (en) | Autonomous transportation vehicle image augmentation | |
| CN112414415B (en) | High-precision point cloud map construction method | |
| CN111324044A (en) | Simulation system and test platform for unmanned automobile | |
| CN112671487B (en) | Vehicle testing method, server and testing vehicle | |
| KR102545109B1 (en) | Apparatus and method for removing false target in vehicle and vehicle including the same | |
| CN114841188A (en) | Vehicle fusion positioning method and device based on two-dimensional code | |
| CN113433840A (en) | Digital rail-mounted automatic driving vehicle simulation system based on magnetic positioning technology | |
| CN110823253B (en) | Data processing method, device and equipment based on unmanned vehicle technology and storage medium | |
| CN115729269B (en) | Unmanned aerial vehicle intelligent recognition system based on machine vision | |
| CN111240298A (en) | Test method for vehicle automatic driving simulation system | |
| CN111462243A (en) | Vehicle-mounted streaming media rearview mirror calibration method, system and device | |
| CN115775379A (en) | Three-dimensional target detection method and system | |
| CN114579088A (en) | Unmanned algorithm development method based on data mining and test closed loop | |
| CN113139299B (en) | Sensor fusion verification method and device and electronic equipment |
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: 20210723 |
|
| RJ01 | Rejection of invention patent application after publication |