CN112987593B - Visual positioning hardware-in-the-loop simulation platform and simulation method - Google Patents
Visual positioning hardware-in-the-loop simulation platform and simulation method Download PDFInfo
- Publication number
- CN112987593B CN112987593B CN202110191097.9A CN202110191097A CN112987593B CN 112987593 B CN112987593 B CN 112987593B CN 202110191097 A CN202110191097 A CN 202110191097A CN 112987593 B CN112987593 B CN 112987593B
- Authority
- CN
- China
- Prior art keywords
- visual positioning
- automatic driving
- camera
- display screen
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a visual positioning hardware-in-the-loop simulation platform and a simulation method, which comprise an automatic driving simulation system, a darkroom scene system and a visual positioning system, wherein the visual positioning system comprises a visual positioning calculation platform and a camera, the visual positioning calculation platform is in communication connection with the automatic driving simulation system, and the visual positioning calculation platform acquires virtual sensor data and a virtual scene high-precision map from the automatic driving simulation system; the darkroom scene system comprises a darkroom, a high-definition display screen and a camera in a visual positioning system are placed in the darkroom, the high-definition display screen is connected with the automatic driving simulation system through a video line, the camera is placed in front of the high-definition display screen, and the camera collects videos displayed on the high-definition display screen by the automatic driving simulation system in real time. The invention accesses the visual positioning computing platform and the camera into the system, realizes hardware-in-the-loop simulation, and simulates the real drive test condition to the maximum extent.
Description
Technical Field
The invention particularly relates to a visual positioning hardware-in-the-loop simulation platform and a simulation method, and belongs to the technical field of automatic driving visual positioning.
Background
The positioning system is a basic module for automatic driving, automatic driving sensing, planning and control all depend on positioning information, high-precision inertial navigation, RTK GNSS and high-line beam laser radar are widely applied to positioning systems for high-level automatic driving, but the sensors are high in cost and hinder the popularization of automatic driving vehicles to a certain extent, and therefore the trend is that camera visual information with low cost is used for automatic driving positioning.
The traditional method for verifying the visual positioning generally comprises two methods, one is that a large number of data acquisition vehicles are used for acquiring a large number of videos and sensor data under different scenes, a high-precision map of a real scene is constructed, then the real sensor data is used for performing off-line simulation, and the performance of a visual positioning algorithm is verified, and the method needs to consume a large amount of manpower and material resources for acquiring data and constructing the high-precision map; the visual positioning is sensitive to environmental changes, especially illumination changes, and in order to verify the accuracy and robustness of the visual positioning algorithm, a large number of automatic driving vehicles are usually required to actually verify the performance of the visual positioning algorithm in a road test in different environments, for example, a road test scene needs to include combinations of different time periods, different seasons and different weathers in the same day, and the cost is very high.
The other method is pure software simulation, and patent document 1 discloses an indoor hybrid positioning semi-physical simulation method and platform, which comprise a positioning signal information actual measurement database, a positioning signal simulation module and a positioning signal output module, wherein the positioning signal information actual measurement database stores rasterized real positioning information; the positioning signal simulation module is used for performing semi-physical simulation on an input simulation path and a user-defined rule on the basis of the acquired signal information to obtain a positioning data set; and the positioning signal output module is used for arranging the stored simulation data into a fixed format and then outputting the simulation data. Sensor data and video streams of the automatic driving virtual scene are directly led into the automatic driving computing platform, a camera is not connected into a simulation system in a hardware-in-loop mode, and the influence of a real camera on a visual positioning system in various scenes cannot be evaluated.
Disclosure of Invention
Aiming at the automatic driving visual positioning system, the invention provides a visual positioning hardware-in-the-loop simulation platform and a simulation method which have low cost and can quickly verify the performance of the visual positioning system by utilizing the existing mature automatic driving simulation system, and can greatly reduce road tests. The method utilizes the automatic driving simulation system to connect the visual positioning computing platform and the camera into the system, realizes hardware-in-loop simulation, simulates the real road test condition to the maximum extent, and quickly verifies the algorithm performance of the automatic driving visual positioning system under different working conditions.
The purpose of the invention is realized by the following technical scheme:
a visual positioning hardware-in-the-loop simulation platform comprises an automatic driving simulation system, a darkroom scene system and a visual positioning system, wherein the visual positioning system comprises a visual positioning calculation platform and a camera, the visual positioning calculation platform is in communication connection with the automatic driving simulation system, and the visual positioning calculation platform acquires virtual sensor data and a virtual scene high-precision map from the automatic driving simulation system; the darkroom scene system comprises a darkroom, a high-definition display screen and a camera in a visual positioning system are placed in the darkroom, the high-definition display screen is connected with the automatic driving simulation system through a video line, the camera is placed in front of the high-definition display screen, and the camera collects videos displayed on the high-definition display screen by the automatic driving simulation system in real time.
Furthermore, the automatic driving simulation system comprises a sensor simulation module, a vehicle dynamics module, a high-precision map module and a virtual scene module; the sensor simulation module is used for providing measurement data for visual positioning; the vehicle dynamics module comprises a vehicle dynamics model used for calculating the real state of the vehicle in the automatic driving simulation system; the high-precision map module is used for providing a high-precision map of the virtual scene; the virtual scene module is used for providing a scene video stream in front of the vehicle.
Preferably, the measurement data provided by the sensor simulation module includes three-axis acceleration, three-axis angular velocity and wheel speed data of the vehicle.
Preferably, the high-precision map provided by the high-precision map module contains angular point features or visual semantic features extracted by a visual positioning algorithm, and real position information of the features.
Preferably, the virtual scene module intercepts a forward video stream of the vehicle from the simulation environment by configuring a virtual camera with parameters consistent with parameters of a real camera, and transmits and displays the video stream on a high-definition display screen in a darkroom.
Preferably, the virtual scene can be configured with different illumination, different seasons and different weather conditions.
Furthermore, in the darkroom scene system, the camera is placed at a certain distance in front of the high-definition display screen, the high-definition display screen is ensured within the field range of the camera, and the content shot by the camera is the virtual scene in front of the vehicle displayed on the high-definition display screen by the automatic driving simulation system.
Further, the visual positioning computing platform comprises a processor, a data interface, and a storage device; the data interface is used for receiving sensor data in the automatic driving simulation system and video streams collected by the camera; the storage device is used for storing a high-precision map acquired from the automatic driving simulation system; the processor extracts features by means of video streams collected by the camera, compares the features with a high-precision map in an automatic driving simulation system, fuses sensor data and calculates the pose of the vehicle.
The invention also provides a simulation method of the visual positioning hardware-in-the-loop simulation platform, which comprises the following steps:
the visual positioning computing platform acquires a virtual scene high-precision map from an automatic driving simulation system;
the visual positioning computing platform acquires IMU and wheel speed data from the automatic driving simulation system through a data interface;
the automatic driving simulation system displays a virtual scene in front of the vehicle through a high-definition display screen in the darkroom scene system;
the camera collects videos displayed on the high-definition display screen by the automatic driving simulation system in real time;
the visual positioning computing platform extracts features by means of real-time camera video stream, compares the features with a high-precision map in an automatic driving simulation system, fuses IMU (inertial measurement unit) and wheel speed data, and calculates the pose of the vehicle;
and comparing the vehicle pose calculated by the visual positioning calculation platform with the real vehicle pose given by the automatic driving simulation system, and evaluating the performance of the visual positioning system.
The invention has the following beneficial effects:
the invention utilizes the existing automatic driving simulation system to connect the visual positioning hardware computing platform and the camera into the automatic driving simulation loop, thereby realizing the hardware-in-loop simulation of the visual positioning system. The automatic driving simulation system runs in an upper computer, virtual scenes of the automatic driving simulation system are displayed on a high-definition screen, the high-definition screen is placed in a darkroom, a camera used in the visual positioning system is placed in front of the high-definition screen, the camera calculates the distance in front of the screen according to parameters such as the focal length and the field angle of the camera, the virtual scenes displayed on the screen in the visual field of the camera are ensured, the video stream of the camera is led into a visual positioning calculation platform in real time, high-precision maps and virtual IMU wheel speed meter data given by the automatic driving simulation system are connected into the visual positioning calculation platform, the visual positioning calculation platform can output the position and the posture of a vehicle which are calculated in real time, and the precision of the visual positioning system can be evaluated by comparing the visual positioning calculation result with the real pose of the vehicle given by the automatic driving simulation system; different weather, seasons and illumination changes can be set in the automatic driving simulation system, and are reflected in a high-definition screen virtual scene collected by a real camera, so that the robustness of a visual positioning algorithm can be verified; the camera is connected to the simulation system in a physical form, so that the influence of camera hardware on the performance of the whole visual positioning system can be verified, and the real performance of the visual positioning system is restored to the maximum extent.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the contents of the embodiments of the present invention and the drawings without creative efforts.
FIG. 1 is a schematic diagram of a visual positioning hardware-in-the-loop simulation platform according to the present invention;
FIG. 2 is a functional block diagram of an autopilot simulation system according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.
A visual positioning hardware-in-the-loop simulation platform comprises an automatic driving simulation system, a darkroom scene system and a visual positioning system, wherein the visual positioning system comprises a visual positioning calculation platform and a camera, the visual positioning calculation platform is in communication connection with the automatic driving simulation system, and the visual positioning calculation platform acquires virtual sensor data and a virtual scene high-precision map from the automatic driving simulation system; the darkroom scene system comprises a darkroom, a high-definition display screen and a camera in a visual positioning system are placed in the darkroom, the high-definition display screen is connected with the automatic driving simulation system through a video line, the camera is placed in front of the high-definition display screen, and the camera collects videos displayed on the high-definition display screen by the automatic driving simulation system in real time.
Further, the automatic driving simulation system comprises a sensor simulation module, a vehicle dynamics module, a high-precision map module and a virtual scene module; the sensor simulation module is used for providing measurement data for visual positioning; the vehicle dynamics module comprises a vehicle dynamics model used for calculating the real state of the vehicle in the automatic driving simulation system; the high-precision map module is used for providing a high-precision map of the virtual scene; the virtual scene module is used for providing a scene video stream in front of the vehicle.
Preferably, the measurement data provided by the sensor simulation module includes three-axis acceleration, three-axis angular velocity and wheel speed data of the vehicle.
Preferably, the high-precision map provided by the high-precision map module contains angular point features or visual semantic features extracted by a visual positioning algorithm and real position information of the features.
Preferably, the virtual scene module intercepts a forward video stream of the vehicle from the simulation environment by configuring a virtual camera with parameters consistent with parameters of a real camera, and transmits and displays the video stream on a high-definition display screen in a darkroom.
Preferably, the virtual scene can be configured with different illumination, different seasons and different weather conditions.
Furthermore, in the darkroom scene system, the camera is placed at a certain distance in front of the high-definition display screen, the high-definition display screen is ensured within the field range of the camera, and the content shot by the camera is the virtual scene in front of the vehicle displayed on the high-definition display screen by the automatic driving simulation system.
Further, the visual positioning computing platform comprises a processor, a data interface, and a storage device; the data interface is used for receiving sensor data in the automatic driving simulation system and video streams collected by the camera; the storage device is used for storing a high-precision map acquired from the automatic driving simulation system; the processor extracts features by means of video streams collected by the camera, compares the features with a high-precision map in an automatic driving simulation system, fuses sensor data and calculates the pose of the vehicle.
Example 1
As shown in fig. 1, a visual positioning hardware-in-the-loop simulation platform mainly includes three parts, namely, an automatic driving simulation system, a darkroom scene system, and a visual positioning system. The vision positioning system comprises a vision positioning computing platform and a camera, wherein vision positioning algorithm software is arranged in the vision positioning computing platform, the vision positioning computing platform and the camera are used as vision positioning system hardware to be added into the simulation system, and the vision positioning computing platform is connected with the automatic driving simulation system through a serial port or an Ethernet to perform data interaction; the darkroom scene system comprises a darkroom, wherein a high-definition display screen and a camera which is actually used in the visual positioning system are placed in the darkroom, the high-definition display screen is connected with the automatic driving simulation system through a video cable, the camera is placed in front of the high-definition display screen, and the camera collects videos displayed on the high-definition display screen by the automatic driving simulation system in real time; the visual positioning computing platform extracts features by means of real-time camera video streaming, compares the features with a high-precision map in an automatic driving simulation system, fuses IMU (inertial measurement unit) and wheel speed data, and calculates the pose of the vehicle. The vehicle pose calculated by the vision positioning calculation platform is compared with the real vehicle pose given by the automatic driving simulation system, and the vehicle pose can be used for evaluating the performance of the vision positioning system.
The IMU and wheel speed data used by the visual positioning computing platform do not use real sensor data, but directly acquire virtual sensor data from an automatic driving simulation system.
In addition, the real position of the vehicle can be easily obtained through the automatic driving simulation system, and the characteristic information in the virtual scene can be extracted, so that the automatic driving simulation system can generally provide an automatically generated high-precision map of the virtual scene.
As shown in fig. 2, the automatic driving simulation system is operated in the upper computer, and mainly includes a sensor simulation module, a vehicle dynamics module, a high-precision map module, and a virtual scene module. The sensor simulation module mainly provides inertial measurement unit data for visual positioning, including three-axis acceleration and three-axis angular velocity of the vehicle, and can also provide wheel speed data reflecting the current vehicle speed. The vehicle dynamics module comprises a vehicle dynamics model, and can calculate the real state of the vehicle in the automatic driving simulation system, such as the position and the posture of the vehicle, and can be used as a true value for evaluating the performance of the visual positioning system. The high-precision map module provides a high-precision map of a virtual scene, a general visual positioning algorithm is based on matching positioning of a pre-established high-precision map, the high-precision map contains the same features extracted by the visual positioning algorithm, such as angular point features or visual semantic features, and the high-precision map also contains real position information of the features. The virtual scene is mainly a scene video stream in front of the vehicle, the forward video stream of the vehicle can be intercepted from a simulation environment through configuring a virtual camera with the parameter consistent with that of a real camera in the automatic driving simulation system, and the video stream is transmitted and displayed on a high-definition screen in a darkroom.
The darkroom scene system comprises a darkroom, a high-definition display screen and a camera which is really used in a visual positioning system are placed in the darkroom, the high-definition display screen is connected with the automatic driving simulation system through a video cable, the camera is placed in front of the high-definition display screen, and other light sources are not arranged in the darkroom except the high-definition display screen. The high-definition display screen plays a vehicle forward virtual scene video stream transmitted in real time in the automatic driving simulation system, the camera is placed at a certain distance in front of the high-definition display screen, the distance is related to parameters such as a camera focal length and a field angle, the high-definition display screen is guaranteed within a camera field range, and the camera shooting content is the vehicle forward virtual scene displayed on the high-definition display screen by the automatic driving simulation system. The automatic driving simulation system can display scene changes caused by different illumination, different seasons and different weather conditions on a high-definition display screen, and the scene changes can be transmitted to the visual positioning computing platform through a real camera video stream and used for the visual positioning computing platform to extract visual features and perform high-precision map feature matching and positioning on a virtual scene.
The visual positioning system comprises a visual positioning computing platform, a camera and visual positioning algorithm software running in the visual positioning computing platform. The visual positioning computing platform comprises a processor, a data interface and a storage device; the processor runs a visual positioning algorithm software, extracts features by means of real-time camera video stream, compares the features with a high-precision map in an automatic driving simulation system, fuses IMU (inertial measurement unit) and wheel speed data, and solves the pose of the vehicle; the data interface is mainly used for receiving sensor data in the automatic driving simulation system, wherein the sensor data comprises IMU data, wheel speed meter data and camera video stream; the storage device is used for storing high-precision maps acquired from the automatic driving simulation system. The visual positioning vision computing platform is connected to the hardware-in-the-loop simulation platform in a physical form, IMU data and wheel speed meter data of the visual positioning vision computing platform are virtual data provided by the automatic driving simulation platform, a virtual scene high-precision map is stored in the storage device, and video stream is input to be high-definition display screen video data shot by a camera in a darkroom in real time. The visual computing platform calculates the positioning information through a visual positioning algorithm, outputs the visual positioning information calculated through hardware-in-the-loop simulation, and evaluates the performance of the visual positioning algorithm through comparison with the real position of the vehicle in the virtual scene provided by the automatic driving simulation platform. The visual positioning algorithm belongs to the visual positioning system mentioned above and runs in a visual positioning computing platform.
Example 2
A simulation method of a visual positioning hardware-in-the-loop simulation platform comprises the following steps:
the visual positioning computing platform acquires a virtual scene high-precision map from an automatic driving simulation system;
the visual positioning computing platform acquires IMU and wheel speed data from the automatic driving simulation system through a data interface;
the automatic driving simulation system displays a virtual scene in front of the vehicle through a high-definition display screen in the darkroom scene system;
the camera collects videos displayed on the high-definition display screen by the automatic driving simulation system in real time;
the visual positioning computing platform extracts features by means of real-time camera video stream, compares the features with a high-precision map in an automatic driving simulation system, fuses IMU (inertial measurement unit) and wheel speed data, and calculates the pose of a vehicle;
and comparing the vehicle pose calculated by the visual positioning calculation platform with the real vehicle pose given by the automatic driving simulation system, and evaluating the performance of the visual positioning system.
The IMU and wheel speed data used by the visual positioning computing platform do not use real sensor data, but directly acquire virtual sensor data from an automatic driving simulation system.
The automatic driving simulation environment used in the method has related products at present, and can provide the position of a vehicle in the virtual simulation environment, a high-precision map of a simulation scene, virtual IMU (inertial measurement unit) and wheel speed sensor data and a virtual vehicle operation scene video stream.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A visual positioning hardware-in-the-loop simulation platform is characterized by comprising an automatic driving simulation system, a darkroom scene system and a visual positioning system, wherein the visual positioning system comprises a visual positioning calculation platform and a camera; the darkroom scene system comprises a darkroom, wherein a high-definition display screen and a camera in a visual positioning system are arranged in the darkroom, the high-definition display screen is connected with the automatic driving simulation system through a video cable, the camera is arranged in front of the high-definition display screen, and the camera acquires videos displayed on the high-definition display screen by the automatic driving simulation system in real time;
the visual positioning computing platform comprises a processor, a data interface and a storage device; the data interface is used for receiving sensor data in the automatic driving simulation system and video streams collected by the camera; the storage device is used for storing a high-precision map acquired from the automatic driving simulation system; the processor extracts features by means of video stream collected by the camera, compares the features with a high-precision map in the automatic driving simulation system, fuses sensor data and calculates the pose of the vehicle.
2. The visual positioning hardware-in-the-loop simulation platform of claim 1, wherein the autopilot simulation system comprises a sensor simulation module, a vehicle dynamics module, a high precision map module, a virtual scene module; the sensor simulation module is used for providing measurement data for visual positioning; the vehicle dynamics module comprises a vehicle dynamics model used for calculating the real state of the vehicle in the automatic driving simulation system; the high-precision map module is used for providing a high-precision map of the virtual scene; the virtual scene module is used for providing a scene video stream in front of the vehicle.
3. The visual positioning hardware-in-the-loop simulation platform of claim 2, wherein the measurement data provided by the sensor simulation module comprises three-axis acceleration, three-axis angular velocity, and wheel speed data of the vehicle.
4. The visual positioning hardware-in-the-loop simulation platform of claim 2, wherein the high-precision map module provides the high-precision map containing the corner features or the visual semantic features extracted by the visual positioning algorithm and the real position information of the features.
5. The visual positioning hardware-in-the-loop simulation platform of claim 2, wherein the virtual scene module intercepts a vehicle forward video stream from the simulation environment by configuring a virtual camera that is consistent with real camera parameters and displays the video stream on a high definition display screen in a darkroom.
6. A visual positioning hardware-in-the-loop simulation platform as recited in claim 5, wherein the virtual scene is further configurable with different lighting, different seasons, different weather conditions.
7. The visual positioning hardware-in-the-loop simulation platform of claim 1, wherein in the darkroom scene system, the camera is placed at a certain distance in front of the high definition display screen, so as to ensure that the high definition display screen is within the field of view of the camera, and the content captured by the camera is a virtual scene in front of the vehicle displayed on the high definition display screen by the automatic driving simulation system.
8. A simulation method of a visual positioning hardware-in-the-loop simulation platform according to claim 1, wherein the simulation method comprises the steps of:
the visual positioning computing platform acquires a virtual scene high-precision map from the automatic driving simulation system;
the visual positioning computing platform acquires IMU and wheel speed data from the automatic driving simulation system through a data interface;
the automatic driving simulation system displays a virtual scene in front of the vehicle through a high-definition display screen in the darkroom scene system;
the camera collects videos displayed on the high-definition display screen by the automatic driving simulation system in real time;
the visual positioning computing platform extracts features by means of real-time camera video stream, compares the features with a high-precision map in an automatic driving simulation system, fuses IMU (inertial measurement unit) and wheel speed data, and calculates the pose of the vehicle;
and comparing the vehicle pose calculated by the visual positioning calculation platform with the real vehicle pose given by the automatic driving simulation system, and evaluating the performance of the visual positioning system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110191097.9A CN112987593B (en) | 2021-02-19 | 2021-02-19 | Visual positioning hardware-in-the-loop simulation platform and simulation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110191097.9A CN112987593B (en) | 2021-02-19 | 2021-02-19 | Visual positioning hardware-in-the-loop simulation platform and simulation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112987593A CN112987593A (en) | 2021-06-18 |
| CN112987593B true CN112987593B (en) | 2022-10-28 |
Family
ID=76394160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110191097.9A Active CN112987593B (en) | 2021-02-19 | 2021-02-19 | Visual positioning hardware-in-the-loop simulation platform and simulation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112987593B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113639764A (en) * | 2021-07-08 | 2021-11-12 | 武汉光庭信息技术股份有限公司 | ADAS synchronous testing device and method based on multi-vision sensor |
| KR102508361B1 (en) * | 2021-11-29 | 2023-03-08 | 주식회사 테크웨이즈 | Autonomous vehicle evaluation system by linking the virtual driving screen of the autonomous vehicle with the actual camera sensor |
| CN114494439B (en) * | 2022-01-25 | 2023-08-15 | 襄阳达安汽车检测中心有限公司 | Camera pose calibration method, device, equipment and medium in HIL simulation test |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020050073A (en) * | 2000-12-20 | 2002-06-26 | 이영민 | method for making simulator program and simulator system using the method |
| CN1851618A (en) * | 2006-05-31 | 2006-10-25 | 北京航空航天大学 | Single-eye vision semi-matter simulating system and method |
| WO2018187927A1 (en) * | 2017-04-11 | 2018-10-18 | SZ DJI Technology Co., Ltd. | Vision simulation system for simulating operations of a movable platform |
| 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 |
| CN109801534A (en) * | 2019-02-19 | 2019-05-24 | 上海思致汽车工程技术有限公司 | Driving behavior hardware-in-the-loop test system based on automatic Pilot simulator |
| CN109883448A (en) * | 2019-03-28 | 2019-06-14 | 北京经纬恒润科技有限公司 | Map box test method and system |
| CN110377006A (en) * | 2019-07-17 | 2019-10-25 | 中国第一汽车股份有限公司 | One kind is parked test macro and method |
| CN110389042A (en) * | 2019-07-16 | 2019-10-29 | 中国第一汽车股份有限公司 | A kind of finished vehicle electronic electric automatization integrated test system based on semi-true object emulation technology |
| EP3566103A1 (en) * | 2017-01-03 | 2019-11-13 | Qualcomm Incorporated | Capturing images of a game by an unmanned autonomous vehicle |
| CN110779730A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | L3-level automatic driving system testing method based on virtual driving scene vehicle on-ring |
| CN110793548A (en) * | 2019-11-06 | 2020-02-14 | 上海交通大学 | Navigation simulation test system based on virtual-real combination of GNSS receiver hardware in loop |
| CN210804108U (en) * | 2019-12-20 | 2020-06-19 | 郑州意昂新能源汽车科技有限公司 | Real vehicle in-loop automatic driving domain controller test bench system |
| CN111752261A (en) * | 2020-07-14 | 2020-10-09 | 同济大学 | Automatic driving test platform based on autonomous driving robot |
| CN111949544A (en) * | 2020-08-19 | 2020-11-17 | 腾讯科技（深圳）有限公司 | Test method and related device for positioning module of automatic driving vehicle |
| CN112182748A (en) * | 2020-09-18 | 2021-01-05 | 苏州星越智能科技有限公司 | Automatic driving sensor simulation test system and application method thereof |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109100155B (en) * | 2018-07-09 | 2020-06-16 | 长安大学 | Unmanned vehicle on-loop rapid simulation test system and method |
| CN109213126B (en) * | 2018-09-17 | 2020-05-19 | 安徽江淮汽车集团股份有限公司 | Automatic driving automobile test system and method |
| CN110888416B (en) * | 2019-12-03 | 2023-02-10 | 上海交通大学 | Visual ADAS-ECU hardware-in-loop simulation test system |
-
2021
- 2021-02-19 CN CN202110191097.9A patent/CN112987593B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020050073A (en) * | 2000-12-20 | 2002-06-26 | 이영민 | method for making simulator program and simulator system using the method |
| CN1851618A (en) * | 2006-05-31 | 2006-10-25 | 北京航空航天大学 | Single-eye vision semi-matter simulating system and method |
| EP3566103A1 (en) * | 2017-01-03 | 2019-11-13 | Qualcomm Incorporated | Capturing images of a game by an unmanned autonomous vehicle |
| WO2018187927A1 (en) * | 2017-04-11 | 2018-10-18 | SZ DJI Technology Co., Ltd. | Vision simulation system for simulating operations of a movable platform |
| 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 |
| CN109801534A (en) * | 2019-02-19 | 2019-05-24 | 上海思致汽车工程技术有限公司 | Driving behavior hardware-in-the-loop test system based on automatic Pilot simulator |
| CN109883448A (en) * | 2019-03-28 | 2019-06-14 | 北京经纬恒润科技有限公司 | Map box test method and system |
| CN110389042A (en) * | 2019-07-16 | 2019-10-29 | 中国第一汽车股份有限公司 | A kind of finished vehicle electronic electric automatization integrated test system based on semi-true object emulation technology |
| CN110377006A (en) * | 2019-07-17 | 2019-10-25 | 中国第一汽车股份有限公司 | One kind is parked test macro and method |
| CN110779730A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | L3-level automatic driving system testing method based on virtual driving scene vehicle on-ring |
| CN110793548A (en) * | 2019-11-06 | 2020-02-14 | 上海交通大学 | Navigation simulation test system based on virtual-real combination of GNSS receiver hardware in loop |
| CN210804108U (en) * | 2019-12-20 | 2020-06-19 | 郑州意昂新能源汽车科技有限公司 | Real vehicle in-loop automatic driving domain controller test bench system |
| CN111752261A (en) * | 2020-07-14 | 2020-10-09 | 同济大学 | Automatic driving test platform based on autonomous driving robot |
| CN111949544A (en) * | 2020-08-19 | 2020-11-17 | 腾讯科技（深圳）有限公司 | Test method and related device for positioning module of automatic driving vehicle |
| CN112182748A (en) * | 2020-09-18 | 2021-01-05 | 苏州星越智能科技有限公司 | Automatic driving sensor simulation test system and application method thereof |
Non-Patent Citations (8)
| Title |
|---|
| Özgür Tunçer,等.Vision based lane keeping assistance control triggered by a driver inattention monitor.《2010 IEEE International Conference on Systems, Man and Cybernetics》.2010, * |
| The Hardware-in-the-Loop Simulation of Vehicle-Grid Integration in a Distribution Grid;Chong Cao,等;《2019 IEEE Power & Energy Society General Meeting (PESGM)》;20200131;全文 * |
| 一种基于视觉信息的可见光通信室内定位方法;王语琪等;《计算机技术与发展》;20160131;第26卷(第01期);全文 * |
| 基于GNSS硬件在环的多源融合定位高逼真仿真方法;夏宋鹏程,等;《中国惯性技术学报》;20200430;第28卷(第02期);全文 * |
| 基于摄像头在环的HIL仿真测试与研究;于洪峰等;《汽车电器》;20191220(第12期);全文 * |
| 基于硬件在环与远程参数控制技术的半主动悬架车辆道路模拟试验;孙野,等;《汽车技术》;20200930(第09期);全文 * |
| 基于硬件在环车道偏离预警***虚拟测试研究;栾铭,等;《重型汽车》;20200415(第02期);全文 * |
| 自动驾驶封闭测试场地建设技术研究与实践;王润民等;《汽车实用技术》;20200229(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112987593A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112987593B (en) | Visual positioning hardware-in-the-loop simulation platform and simulation method | |
| WO2023207016A1 (en) | Autonomous driving test system and method based on digital twin cloud control platform | |
| CN109459734B (en) | Laser radar positioning effect evaluation method, device, equipment and storage medium | |
| CN111897305B (en) | Data processing method, device, equipment and medium based on automatic driving | |
| CN110556012B (en) | Lane positioning method and vehicle positioning system | |
| US20190043278A1 (en) | Test drive scenario system for virtual test drive scenarios | |
| US20200074652A1 (en) | Method for generating simulated point cloud data, device, and storage medium | |
| US10832478B2 (en) | Method and system for virtual sensor data generation with depth ground truth annotation | |
| CN108958266A (en) | A kind of map datum acquisition methods | |
| WO2018125939A1 (en) | Visual odometry and pairwise alignment for high definition map creation | |
| Minoda et al. | Viode: A simulated dataset to address the challenges of visual-inertial odometry in dynamic environments | |
| CN110793548B (en) | Navigation simulation test system based on virtual-real combination of GNSS receiver hardware in loop | |
| CN111324945B (en) | Sensor scheme determining method, device, equipment and storage medium | |
| CN111983936B (en) | Unmanned aerial vehicle semi-physical simulation system and evaluation method | |
| CN113260430B (en) | Scene processing method, device and system and related equipment | |
| CN113419518B (en) | VIL test platform based on VTS | |
| CN109163889A (en) | A kind of test device and method of forward sight camera ADAS algorithm | |
| CN110062916A (en) | For simulating the visual simulation system of the operation of moveable platform | |
| US20220204009A1 (en) | Simulations of sensor behavior in an autonomous vehicle | |
| CN112147632A (en) | Method, device, equipment and medium for testing vehicle-mounted laser radar perception algorithm | |
| CN117270506A (en) | Motion control method and system for host vehicle in virtual simulation scene | |
| CN115657494A (en) | Virtual object simulation method, device, equipment and storage medium | |
| CN114820504B (en) | Method and device for detecting image fusion deviation, electronic equipment and storage medium | |
| CN116105712A (en) | Road map generation method, reinjection method, computer device and medium | |
| CN110134024A (en) | The construction method of distinctive mark object in Vehicular automatic driving virtual environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |