CN110162089B - Unmanned driving simulation method and device - Google Patents

Unmanned driving simulation method and device Download PDF

Info

Publication number
CN110162089B
CN110162089B CN201910462332.4A CN201910462332A CN110162089B CN 110162089 B CN110162089 B CN 110162089B CN 201910462332 A CN201910462332 A CN 201910462332A CN 110162089 B CN110162089 B CN 110162089B
Authority
CN
China
Prior art keywords
detection range
sensor
simulation
data
simulated
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
Application number
CN201910462332.4A
Other languages
Chinese (zh)
Other versions
CN110162089A (en
Inventor
董立龙
冯建华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN201910462332.4A priority Critical patent/CN110162089B/en
Publication of CN110162089A publication Critical patent/CN110162089A/en
Application granted granted Critical
Publication of CN110162089B publication Critical patent/CN110162089B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application discloses a simulation method and a simulation device for unmanned driving, wherein each sensor data set corresponding to the same simulation environment stored in advance is read in the method, the simulation data set is selected from each sensor data set according to the detection range of a simulation vehicle sensor and the detection range of an actual vehicle sensor corresponding to each recorded sensor data set, then, the sensor data corresponding to each unit detection range is determined in the sensor data contained in the simulation data set aiming at each unit detection range of the simulation vehicle sensor, the simulation data is obtained according to the sensor data corresponding to each unit detection range, and the simulation vehicle is simulated according to the simulation data. According to the method, three-dimensional modeling is not needed, the states of the simulated vehicle and the actual vehicle are not required to be consistent during simulation, and the flexibility of simulation is improved. Meanwhile, the selected simulation data set is real data collected by an actual vehicle, so that the authenticity of simulation is effectively ensured.

Description

Unmanned driving simulation method and device
Technical Field
The application relates to the technical field of unmanned driving, in particular to an unmanned driving simulation method and device.
Background
The existing unmanned simulation method mainly comprises two types, one is three-dimensional modeling simulation, and the other is real data playback simulation.
Three-dimensional modeling simulation needs to perform 1:1 equal-proportion three-dimensional modeling on a simulated area in advance to obtain a three-dimensional virtual simulation environment. In the simulation process, sensor data acquired by a sensor is output based on three-dimensional model data in a virtual environment according to the current spatial position and posture of the sensor such as a camera and a radar, and the sensor data is input into an automatic driving system to obtain a simulation result.
The real-acquisition data playback simulation needs to drive a vehicle to run in a simulated area according to a preset route in advance, then uses sensors such as a camera and a radar on the vehicle to acquire information such as images and point clouds on a running track, and stores the acquired sensor data in a database. In the simulation process, the sensor data are read from the database, and then the read sensor data are sequentially input into the automatic driving system according to the time sequence to obtain a simulation result.
However, when a three-dimensional virtual simulation environment is established in the three-dimensional modeling simulation, if software is used for automatic modeling, the accuracy of the established three-dimensional model is low, the rendering effect of the currently mainstream three-dimensional engine is poor, and if manual modeling is adopted, the workload is large. In addition, the sensor data output by the method during simulation is too ideal, and the deviation from the actual sensor data is large, so that the accuracy of the simulation result is low.
For the real data playback simulation method, the sensor data used by the method is acquired by the actual vehicle in a relatively fixed state (such as the speed, the driving track, the orientation of the sensor, and the like of the vehicle), so that the simulation vehicle is required to be consistent with the state of the actual vehicle during simulation, which reduces the flexibility and the reality of the simulation.
Disclosure of Invention
The embodiment of the application provides a simulation method and device for unmanned driving, which are used for partially solving the problems in the prior art.
The following technical scheme is adopted in the application:
the application provides a simulation method of unmanned driving, which comprises the following steps:
reading pre-stored sensor data sets corresponding to the same simulation environment, wherein the sensor data in different sensor data sets are acquired by actual vehicles in different states in the simulation environment;
selecting a simulation data set in each sensor data set according to the detection range of the simulation vehicle sensor and the recorded detection range of the actual vehicle sensor corresponding to each sensor data set;
for each unit detection range of the simulated vehicle sensor, determining sensor data corresponding to the unit detection range in the sensor data contained in the simulated data set;
and obtaining simulation data according to the sensor data corresponding to each unit detection range, and simulating the simulated vehicle according to the simulation data.
Optionally, for each sensor dataset, the sensor dataset comprises point cloud data and image data.
Optionally, pre-storing each sensor data set corresponding to the same simulation environment specifically includes:
aiming at different states of an actual vehicle, point cloud data and image data which are acquired when the actual vehicle runs in the simulation environment in the state are acquired;
determining the spatial coordinates of the image data according to the spatial coordinates of the point cloud data, the detection range of a radar for collecting the point cloud data and the detection range of a camera for collecting the image data;
storing the point cloud data, the image data, the spatial coordinates of the point cloud data, and the spatial coordinates of the image data.
Optionally, determining the spatial coordinate of the image data according to the spatial coordinate of the point cloud data, a detection range of a radar that acquires the point cloud data, and a detection range of a camera that acquires the image data, specifically including:
for each pixel in the image data, determining a spatial ray corresponding to the pixel according to the detection range of the camera;
judging whether an intersection point exists between the space ray corresponding to the pixel and the detection range of the radar;
if yes, determining the space coordinate of the point cloud data corresponding to the intersection point as the space coordinate of the pixel;
otherwise, determining the space coordinate of the pixel according to the state parameter of the actual vehicle in the state and the image data.
Optionally, selecting a simulation data set from each sensor data set according to the detection range of the simulation vehicle sensor and the recorded detection range of the actual vehicle sensor corresponding to each sensor data set, specifically including:
determining the coincidence degree of the detection range of the simulated vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set;
and selecting a simulation data set in each sensor data set according to the contact ratio of the detection range of the simulation vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set.
Optionally, for each unit detection range of the simulated vehicle sensor, determining sensor data corresponding to the unit detection range in the sensor data included in the simulated data set specifically includes:
determining a detection range of a radar corresponding to point cloud data contained in the simulation data set;
aiming at each unit detection range of the camera of the simulated vehicle, determining the intersection point of the space ray corresponding to the unit detection range and the determined detection range of the radar;
determining the space coordinates of the point cloud data corresponding to the intersection points;
and determining pixels corresponding to the space coordinates in the image data contained in the simulation data set as sensor data detected by a camera of the simulation vehicle in the unit detection range.
Optionally, for each unit detection range of the simulated vehicle sensor, determining sensor data corresponding to the unit detection range in the sensor data included in the simulated data set specifically includes:
determining a detection range of a radar corresponding to point cloud data contained in the simulation data set;
aiming at each unit detection range of the radar of the simulated vehicle, determining the intersection point of the space ray corresponding to the unit detection range and the detection range of the radar corresponding to the point cloud data contained in the simulated data set;
and taking the point cloud data corresponding to the intersection points as sensor data detected by the radar of the simulated vehicle in the unit detection range.
The application provides a simulation device of unmanned, includes:
the simulation system comprises a reading module, a simulation module and a control module, wherein the reading module is used for reading pre-stored sensor data sets corresponding to the same simulation environment, and the sensor data in different sensor data sets are acquired by actual vehicles in different states in the simulation environment;
the selection module is used for selecting a simulation data set in each sensor data set according to the detection range of the simulation vehicle sensor and the recorded detection range of the actual vehicle sensor corresponding to each sensor data set;
a determination module, configured to determine, for each unit detection range of the simulated vehicle sensor, sensor data corresponding to the unit detection range from among the sensor data included in the simulated data set;
and the simulation module is used for obtaining simulation data according to the sensor data corresponding to each unit detection range and simulating the simulated vehicle according to the simulation data.
A computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the above-described unmanned simulation method.
The application provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the unmanned simulation method.
The above-mentioned at least one technical scheme that this application adopted can reach following beneficial effect:
it can be seen from the above method that each sensor data set corresponding to the same simulation environment stored in advance is read, and a simulation data set is selected in each sensor data set according to the detection range of the simulated vehicle sensor and the detection range of the actual vehicle sensor corresponding to each recorded sensor data set, then, for each unit detection range of the simulated vehicle sensor, the sensor data corresponding to the unit detection range is determined in the sensor data included in the simulation data set, the simulation data is obtained according to the sensor data corresponding to each unit detection range, and the simulated vehicle is simulated according to the simulation data.
Compared with the prior art, the unmanned simulation method provided by the application does not need three-dimensional modeling, and when the simulation vehicle is simulated, the state of the simulation vehicle is consistent with that of the actual vehicle when the simulation is not required, so that the flexibility of simulation is effectively improved. Meanwhile, under the condition of giving the detection range of the simulated vehicle sensor, which sensor data sets are collected by the actual vehicle corresponding to the detection range can be determined. That is to say, the simulation data set selected through the detection range of the simulated vehicle sensor is actually the real data collected by the actual vehicle, so that when the simulated vehicle is simulated, the data does not need to be collected by the simulated vehicle, and therefore, the simulation efficiency is greatly improved, and meanwhile, the authenticity of simulation is effectively guaranteed.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic flow chart illustrating an unmanned simulation method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of determining spatial coordinates of a pixel through a spatial ray of the pixel according to an embodiment of the present application;
fig. 3 is a schematic diagram of selecting a simulation data set according to the detection range of the simulated vehicle sensor and the coincidence degree of the detection ranges of the actual vehicle sensors corresponding to the sensor data sets according to the embodiment of the present application;
FIG. 4 is a schematic diagram of selection of a simulated data set by prioritization of detection ranges of actual vehicle sensors relative to detection ranges of simulated vehicle sensors provided by an embodiment of the present application;
FIG. 5 is a schematic diagram of an unmanned simulation apparatus according to the present application;
fig. 6 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of an unmanned simulation method in an embodiment of the present application, which specifically includes the following steps:
s101: reading each pre-stored sensor data set corresponding to the same simulation environment, wherein the sensor data in different sensor data sets are acquired by actual vehicles in different states in the simulation environment.
In the embodiment of the application, a plurality of sensor data sets are stored in the database in advance, and the sensor data sets are acquired by the actual vehicle in the simulation environment. The real vehicle can carry out data acquisition through a radar and a camera which are arranged on the real vehicle in the running process of the simulation environment, data acquired through the radar is point cloud data, and data acquired through the camera is image data. Therefore, the sensor data set corresponding to the actual vehicle includes the point cloud data and the image data acquired by the actual vehicle.
In practical applications, different actual vehicles may be in different states when running in the same simulation environment. The state referred to herein is a state in which the actual vehicle itself and various sensors mounted on the actual vehicle are in a simulated environment, and may be specifically characterized by some parameters. For example, the placement angle of a camera provided on the actual vehicle, the detection range of a radar, the travel track of the actual vehicle in the simulation environment, and the like.
It can be seen from this point that these parameters will affect which sensor data the actual vehicle acquires in the simulation environment, that is, the actual vehicle has different travel tracks in the simulation environment, the actual vehicle has different placement angles of the cameras, the actual vehicle has different detection ranges of the radars, and the acquired point cloud data and image data are also different.
Therefore, for the same simulation environment, the point cloud data and the image data acquired by different actual vehicles in the simulation environment can be respectively stored as the sensor data sets acquired in the simulation environment. In other words, a set of sensor data, which corresponds in essence to sensor data collected by an actual vehicle in a state within the simulated environment.
In the embodiment of the present application, the simulation environment may refer to an actual environment in which an actual vehicle performs data acquisition. Because the point cloud data and the image data acquired by the actual vehicle in different simulation environments are different (namely, the sensor data sets are different), the different simulation environments and the different sensor data sets can be correspondingly stored in the database. That is, each simulation environment corresponds to multiple sets of sensor data. Based on this, when the simulation vehicle is simulated, the simulation environment in which the simulation vehicle is located during simulation can be determined, and each sensor data set corresponding to the simulation environment which is stored in advance is read from the database, so that in the subsequent process, according to the detection range of the sensor on the simulation vehicle, the sensor data set is selected as the simulation data set from the sensor data sets.
The execution body used for simulating the simulated vehicle may be a terminal device such as a computer or a dedicated simulation device, or may be a server. For convenience of subsequent description, the unmanned simulation method provided by the present application will be described below with only a terminal device such as a computer as an execution subject.
In the embodiment of the application, besides the point cloud data and the image data collected by the actual vehicle in the simulation environment, the sensor data set can also record the spatial coordinates of the point cloud data and the spatial coordinates of the image data. Specifically, for different states of the actual vehicle, the terminal device can acquire point cloud data and image data acquired by the actual vehicle running in the simulation environment in the state, and then can determine the space coordinate of the image data according to the space coordinate of the point cloud data, the detection range of the radar when acquiring the point cloud data and the detection range of the camera when acquiring the image data.
The spatial coordinates of the point cloud data can be obtained by directly converting the point cloud data, and the specific conversion mode is the conventional mode, which is not described in detail herein. The spatial coordinates of the image data are obtained by converting the spatial coordinates of the point cloud data in combination with the detection ranges of the radar and the camera.
Specifically, for each pixel in the image data, the terminal device may determine a spatial ray corresponding to the pixel according to a detection range of a camera of the actual vehicle. And then, the terminal device can judge whether an intersection point exists between the spatial ray corresponding to the pixel and the detection range of the radar of the actual vehicle, if so, the spatial coordinate of the point cloud data corresponding to the intersection point can be determined as the spatial coordinate of the pixel, and if not, the spatial coordinate of the pixel can be determined according to the state parameter of the actual vehicle in the state and the image data.
For each pixel in the image data, the spatial ray corresponding to the pixel can be regarded as a connection line starting from the camera as a source point and going to the pixel. After obtaining the spatial ray, the terminal device may determine whether an intersection exists between the spatial ray and a plane where a detection range of the radar is located, and whether the intersection is located within the detection range of the radar (actually, it is determined that the spatial ray cannot be within the detection range of the radar and can be hit at which point within the detection range of the radar), and if the intersection is located within the detection range of the radar, the spatial coordinate of the point cloud data corresponding to the intersection may be determined as the spatial coordinate of the pixel, as shown in fig. 2.
Fig. 2 is a schematic diagram of determining a spatial coordinate of a pixel through a spatial ray of the pixel according to an embodiment of the present application.
If the terminal device determines the spatial coordinate of the pixel point a in the image data, the camera may be used as a source point, and a connection line between the source point and the pixel point a is used as a spatial ray of the pixel point a. The terminal device can then direct the spatial ray to a plane in which the detection range of the radar lies. As can be seen from fig. 2, if the spatial ray intersects point B in the detection range of the radar, the terminal device may determine the spatial coordinate of the point cloud data corresponding to the intersection point B as the spatial coordinate of the pixel point a.
It should be noted that, due to the characteristics of the point cloud data, point cloud data corresponding to all points in the detection range of the radar does not necessarily exist at all points in the detection range of the radar, so if the terminal device determines that point cloud data corresponding to the intersection point does not exist at the intersection point, the terminal device may determine the spatial coordinates of the pixel in other manners.
For example, the terminal device may select a point closest to the intersection point from all points having point cloud data included in the detection range of the radar, and use the spatial coordinate of the point cloud data corresponding to the selected point as the spatial coordinate of the pixel. For another example, the terminal device may select three points that are closer to the intersection point from all the points included in the detection range of the radar and have point cloud data, and determine the center of gravity of the three points. If the center of gravity is determined to have the point cloud data corresponding to the center of gravity, the spatial coordinate of the point cloud data corresponding to the center of gravity can be used as the spatial coordinate of the pixel. Other ways are not illustrated in detail here.
If it is determined that no intersection point exists between the spatial ray corresponding to the pixel and the detection range of the radar, the terminal device may determine the spatial coordinate of the pixel through an image analysis technique. Since the geographic coordinate of the actual vehicle when acquiring the image data including the pixel can be determined, the terminal device can perform image analysis on the image data according to the geographic coordinate of the actual vehicle and the state parameters (such as the placement angle of the camera on the actual vehicle, the detection range of the radar, and the like) of the actual vehicle in the simulation environment, so as to determine the spatial coordinate of the pixel. Specifically, the terminal device may determine the depth of field of the image data, and then determine the spatial coordinates of the pixel through image analysis according to the viewing cone matrix of the camera, the offset matrix of the camera relative to the actual vehicle, the depth of field, the direction of the pixel, and the geographic coordinates based on which the actual vehicle acquires the image data. The specific process is conventional in the art and will not be described in detail herein.
S102: and selecting a simulation data set from the sensor data sets according to the detection range of the simulation vehicle sensor and the recorded detection range of the actual vehicle sensor corresponding to each sensor data set.
In the embodiment of the present application, each sensor data set recorded in the database actually refers to sensor data acquired by an actual vehicle in different states, and the state of the actual vehicle actually reflects the detection range of the actual vehicle sensor. The arrangement angle of the camera on the actual vehicle, the detection range of the radar and the traveling track of the actual vehicle determine which collection area corresponds to the simulation environment when the actual vehicle collects data, so that the detection range of the actual vehicle sensor mentioned here actually refers to the collection area corresponding to the simulation environment when the actual vehicle collects data according to the state.
In the embodiment of the present application, a database stores a plurality of sensor data sets of the simulation environment, and the detection range of the actual vehicle sensor corresponding to each sensor data set may be different. Therefore, when simulating the simulated vehicle, it is necessary to select which one or more sensor data sets from the sensor data sets as the simulation data set according to the detection ranges of the sensors of the simulated vehicle in the simulation environment.
That is, the terminal device needs to decide which sensor data sets collected by the actual vehicle should be selected for simulating the simulated vehicle according to the detection range of the sensor of the simulated vehicle. The detection range of the simulated vehicle sensor mentioned here is basically the same as the detection range of the actual vehicle sensor mentioned above, that is, the simulated vehicle sensor is in a corresponding acquisition area in the simulated environment according to a certain state.
Specifically, the terminal device may determine the coincidence degree of the detection range of the simulated vehicle sensor with the detection range of the actual vehicle sensor corresponding to each sensor data set, and then select the simulated data set from each sensor data set in the simulated environment according to the determined coincidence degree of the detection range of the simulated vehicle sensor with the detection range of the actual vehicle sensor corresponding to each sensor data set, as shown in fig. 3.
Fig. 3 is a schematic diagram of selecting a simulation data set according to the detection range of the simulation vehicle sensor and the coincidence degree of the detection ranges of the actual vehicle sensors corresponding to the sensor data sets according to the embodiment of the present application.
Assume that there are three actual vehicles that acquire three sets of sensor data in different trajectories within the simulated environment, the three sets of sensor data corresponding to the detection ranges of the three actual vehicle sensors A, B, C, respectively. The parameters of the state of the simulated vehicle can be represented through the advancing track of the simulated vehicle, the placing angle of the camera, the detection range of the radar and the like, and the detection range of the simulated vehicle sensor can be determined to be D. As can be seen from fig. 3, the detection range D of the simulated vehicle sensor has the highest coincidence degree with the detection range a of the actual vehicle sensor, and therefore, the sensor data set corresponding to the detection range a of the actual vehicle sensor can be selected as the simulated data set.
Since the detection range of the simulated vehicle sensor may overlap with the detection ranges of the actual vehicle sensors, in this embodiment of the application, the terminal device may determine the coincidence degree between the detection range of the simulated vehicle sensor and the detection ranges of the actual vehicle sensors, and determine the priority of the detection range of each actual vehicle sensor relative to the detection range of the simulated vehicle sensor according to the determined coincidence degree, and further select the simulated data set from each sensor data set according to each priority, as shown in fig. 4.
FIG. 4 is a schematic diagram of an embodiment of the present application for selecting a simulation data set by prioritizing detection ranges of actual vehicle sensors relative to detection ranges of simulated vehicle sensors.
The detection ranges of the plurality of real-vehicle sensors are shown in fig. 4, the detection range of the dummy vehicle sensor coincides with the detection ranges of the plurality of real-vehicle sensors, and the detection range coincides with the detection range a of the real-vehicle sensor and the detection range B of the real-vehicle sensor for the portion surrounded by the dashed frame. As can be seen from fig. 4, the detection range a of the actual vehicle sensor and the detection range of the simulated vehicle sensor overlap more, and the detection range B of the actual vehicle sensor and the detection range of the simulated vehicle sensor overlap less. Therefore, the detection range a of the actual vehicle sensor has a higher priority than the detection range B of the actual vehicle sensor.
The terminal device may select a sensor data set corresponding to the detection range a of the actual vehicle sensor and the detection range B of the actual vehicle sensor as a simulation data set. For the portion of the detection range surrounded by the broken-line frame illustrated in fig. 4, this portion of the detection range can be regarded as being composed of the detection range a of the real-vehicle sensor and the portion of the shaded region of the detection range B of the real-vehicle sensor in fig. 4. Therefore, when the selected simulation data set is used to obtain simulation data, the terminal device may determine a part of simulation data according to the sensor data set corresponding to the detection range a of the actual vehicle sensor, and then determine corresponding simulation data according to the sensor data set corresponding to the shadow region of the detection range B of the actual vehicle sensor.
That is, the terminal device determines which sensor data sets corresponding to the detection ranges of the actual vehicle sensors are needed to be spliced into the simulation data set needed when the simulation vehicle is simulated according to the detection ranges of the simulated vehicle sensors, the coincidence degrees between the detection ranges of the actual vehicle sensors corresponding to the sensor data sets, and the priorities.
S103: for each unit detection range of the simulated vehicle sensor, the sensor data corresponding to the unit detection range is determined from the sensor data included in the simulated data set.
After the terminal device selects the simulation data set, it may determine, for each unit detection range of the simulated vehicle sensors mounted on the simulated vehicle, sensor data corresponding to the unit detection range from among the sensor data included in the simulation data set. The specific data that should be collected if the data collection is performed in the detection range of the simulated vehicle sensor is determined based on the selected simulated data set.
The simulated vehicle is provided with a radar and a camera which respectively correspond to respective detection ranges, so that the terminal equipment needs to respectively determine sensor data corresponding to a unit detection range of the radar and sensor data corresponding to a unit detection range of the camera.
Specifically, in the embodiment of the present application, the database records the corresponding relationship between each sensor data set and the detection range of each actual vehicle sensor, so that the terminal device can determine the detection range of the radar corresponding to the point cloud data included in the simulation data set. Then, the terminal device can determine the intersection point of the space ray corresponding to the unit detection range and the detection range of the radar corresponding to the point cloud data contained in the simulation data set aiming at each unit detection range of the radar of the simulation vehicle, and further can use the point cloud data corresponding to the intersection point as the sensor data detected by the radar of the simulation vehicle in the unit detection range.
The spatial ray corresponding to the unit detection range mentioned here is substantially the same as the spatial ray mentioned in step S101, that is, the radar may be used as a source point, and a connection line between the source point and the unit detection range is the spatial ray corresponding to the unit detection range. The terminal device can shoot the space ray to the detection range of the radar corresponding to the point cloud data contained in the simulation data set so as to determine which point (namely, an intersection point) of the detection range of the radar corresponding to the point cloud data contained in the simulation data set the space ray hits, and further can determine the point cloud data corresponding to the intersection point as the sensor data detected by the radar of the simulation vehicle in the unit detection range.
For the camera on the simulated vehicle, after the terminal device determines the detection range of the radar corresponding to the point cloud data contained in the simulated data set, the intersection point of the space ray corresponding to the unit detection range and the determined detection range of the radar can be determined for each unit detection range of the camera of the simulated vehicle. The terminal device may further determine the spatial coordinates of the point cloud data corresponding to the intersection point, and determine the pixel corresponding to the spatial coordinates in the image data included in the simulation data set, so as to use the pixel as the sensor data detected by the camera of the simulated vehicle in the unit detection range.
The spatial ray corresponding to the unit detection range of the camera of the simulated vehicle is basically the same as the spatial ray mentioned above, that is, the camera is taken as a source point, and the ray emitted from the source point to the unit detection range is the spatial ray. The terminal device may further determine at which point within the detection range of the radar the spatial ray is directed (i.e., the intersection point). Since the spatial coordinates of the point cloud data and the point cloud data can be converted with each other in a conventional manner, the terminal device can directly determine the spatial coordinates of the point cloud data corresponding to the intersection point.
After the terminal device determines the space coordinates of the point cloud data corresponding to the intersection point, the terminal device can determine the pixels corresponding to the space coordinates in the image data contained in the simulation data set, and then the pixels are used as the sensor data detected by the camera of the simulation vehicle in the unit detection range. In other words, the terminal device determines which pixel in the image data corresponds to the intersection point according to the spatial coordinates of the point cloud data corresponding to the intersection point, and uses the pixel as a pixel acquired when the camera of the simulated vehicle acquires an image of the actual environment according to the unit detection range.
It should be noted that the unit detection range of the radar and the unit detection range of the camera may be divided by a preset dividing method, for example, by angle division, or by a unit area, and the like, which is not illustrated in detail herein.
S104: and obtaining simulation data according to the sensor data corresponding to each unit detection range, and simulating the simulated vehicle according to the simulation data.
After the terminal device determines the sensor data corresponding to each unit detection range, the sensor data can be used as simulation data, and the simulation vehicle is simulated based on the simulation data.
According to the method, the terminal device can determine which point cloud data and image data are acquired by the simulated vehicle in the actual environment according to the detection range of the simulated vehicle sensor through the pre-stored sensor data sets acquired by the actual vehicle in different states, and then the determined data are used as the simulated data to simulate the simulated vehicle. Compared with the prior art, the unmanned simulation method provided by the application does not need three-dimensional modeling, and when the simulation vehicle is simulated, the state of the simulation vehicle is consistent with that of the actual vehicle when the simulation is not required, so that the flexibility of simulation is effectively improved.
Meanwhile, under the condition of giving the detection range of the simulated vehicle sensor, which sensor data sets are collected by the actual vehicle corresponding to the detection range can be determined. That is to say, when the unmanned simulation method provided by the application is used for simulating a simulated vehicle, the simulation data set selected based on the detection range of the simulated vehicle sensor is the real data collected by the actual vehicle, so that the data collection by the simulated vehicle is not needed, the simulation efficiency is greatly improved, and the simulation authenticity is effectively ensured.
Based on the same idea, the present application also provides a corresponding unmanned simulation apparatus, as shown in fig. 5.
Fig. 5 is a schematic diagram of an unmanned simulation apparatus provided in the present application, which specifically includes:
the reading module 501 is configured to read pre-stored sensor data sets corresponding to the same simulation environment, where sensor data in different sensor data sets are collected by actual vehicles in different states in the simulation environment;
a selecting module 502, configured to select a simulation data set from each sensor data set according to a detection range of a simulation vehicle sensor and a recorded detection range of an actual vehicle sensor corresponding to each sensor data set;
a determining module 503, configured to determine, for each unit detection range of the simulated vehicle sensor, sensor data corresponding to the unit detection range from among the sensor data included in the simulated data set;
and the simulation module 504 is configured to obtain simulation data according to the sensor data corresponding to each unit detection range, and simulate the simulated vehicle according to the simulation data.
Optionally, for each sensor dataset, the sensor dataset comprises point cloud data and image data.
Optionally, the apparatus further comprises:
a storage module 505, configured to acquire, for different states of an actual vehicle, point cloud data and image data acquired when the actual vehicle runs in the simulation environment in the state; determining the spatial coordinates of the image data according to the spatial coordinates of the point cloud data, the detection range of a radar for collecting the point cloud data and the detection range of a camera for collecting the image data; storing the point cloud data, the image data, the spatial coordinates of the point cloud data, and the spatial coordinates of the image data.
Optionally, the storage module 505 is specifically configured to, for each pixel in the image data, determine a spatial ray corresponding to the pixel according to a detection range of the camera; judging whether an intersection point exists between the space ray corresponding to the pixel and the detection range of the radar; if yes, determining the space coordinate of the point cloud data corresponding to the intersection point as the space coordinate of the pixel; otherwise, determining the space coordinate of the pixel according to the state parameter of the actual vehicle in the state and the image data.
Optionally, the selecting module 502 is specifically configured to determine the coincidence degree between the detection range of the simulated vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set; and selecting a simulation data set in each sensor data set according to the contact ratio of the detection range of the simulation vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set.
Optionally, the determining module 503 is specifically configured to determine a detection range of a radar corresponding to the point cloud data included in the simulation data set; aiming at each unit detection range of the camera of the simulated vehicle, determining the intersection point of the space ray corresponding to the unit detection range and the determined detection range of the radar; determining the space coordinates of the point cloud data corresponding to the intersection points; and determining pixels corresponding to the space coordinates in the image data contained in the simulation data set as sensor data detected by a camera of the simulation vehicle in the unit detection range.
Optionally, the determining module 503 is specifically configured to determine a detection range of a radar corresponding to the point cloud data included in the simulation data set; aiming at each unit detection range of the radar of the simulated vehicle, determining the intersection point of the space ray corresponding to the unit detection range and the detection range of the radar corresponding to the point cloud data contained in the simulated data set; and taking the point cloud data corresponding to the intersection points as sensor data detected by the radar of the simulated vehicle in the unit detection range.
An embodiment of the present application further provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program can be used to execute the above-mentioned unmanned simulation method provided in fig. 1.
The embodiment of the present application further provides a schematic structural diagram of the electronic device shown in fig. 6. As shown in fig. 6, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, but may also include hardware required for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the unmanned simulation method described in fig. 1 above. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardsradware (Hardware Description Language), vhjhd (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (9)

1. A method for simulating unmanned driving, the method comprising:
reading pre-stored sensor data sets corresponding to the same simulation environment, wherein the sensor data in different sensor data sets are acquired by actual vehicles in different states in the simulation environment;
determining the contact ratio of the detection range of the simulated vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set, selecting the simulated data set in each sensor data set according to the contact ratio of the detection range of the simulated vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set, wherein the detection range of the actual vehicle sensor corresponding to the selected sensor data set can not completely coincide with the detection range of the simulated vehicle sensor;
for each unit detection range of the simulated vehicle sensor, determining sensor data corresponding to the unit detection range in the sensor data contained in the simulated data set;
and obtaining simulation data according to the sensor data corresponding to each unit detection range, and simulating the simulated vehicle according to the simulation data.
2. The method of claim 1, wherein for each sensor dataset, the sensor dataset comprises point cloud data and image data.
3. The method of claim 2, wherein pre-storing respective sensor data sets corresponding to a same simulation environment, comprises:
aiming at different states of an actual vehicle, point cloud data and image data which are acquired when the actual vehicle runs in the simulation environment in the state are acquired;
determining the spatial coordinates of the image data according to the spatial coordinates of the point cloud data, the detection range of a radar for collecting the point cloud data and the detection range of a camera for collecting the image data;
storing the point cloud data, the image data, the spatial coordinates of the point cloud data, and the spatial coordinates of the image data.
4. The method of claim 3, wherein determining the spatial coordinates of the image data based on the spatial coordinates of the point cloud data, a detection range of a radar that acquired the point cloud data, and a detection range of a camera that acquired the image data comprises:
for each pixel in the image data, determining a spatial ray corresponding to the pixel according to the detection range of the camera;
judging whether an intersection point exists between the space ray corresponding to the pixel and the detection range of the radar;
if yes, determining the space coordinate of the point cloud data corresponding to the intersection point as the space coordinate of the pixel;
otherwise, determining the space coordinate of the pixel according to the state parameter of the actual vehicle in the state and the image data.
5. The method according to claim 3, wherein for each unit detection range of the simulated vehicle sensors, determining sensor data corresponding to the unit detection range from among the sensor data included in the simulated data set, specifically comprises:
determining a detection range of a radar corresponding to point cloud data contained in the simulation data set;
aiming at each unit detection range of the camera of the simulated vehicle, determining the intersection point of the space ray corresponding to the unit detection range and the determined detection range of the radar;
determining the space coordinates of the point cloud data corresponding to the intersection points;
and determining pixels corresponding to the space coordinates in the image data contained in the simulation data set as sensor data detected by a camera of the simulation vehicle in the unit detection range.
6. The method according to claim 3, wherein for each unit detection range of the simulated vehicle sensors, determining sensor data corresponding to the unit detection range from among the sensor data included in the simulated data set, specifically comprises:
determining a detection range of a radar corresponding to point cloud data contained in the simulation data set;
aiming at each unit detection range of the radar of the simulated vehicle, determining the intersection point of the space ray corresponding to the unit detection range and the detection range of the radar corresponding to the point cloud data contained in the simulated data set;
and taking the point cloud data corresponding to the intersection points as sensor data detected by the radar of the simulated vehicle in the unit detection range.
7. An unmanned simulation apparatus, the apparatus comprising:
the simulation system comprises a reading module, a simulation module and a control module, wherein the reading module is used for reading pre-stored sensor data sets corresponding to the same simulation environment, and the sensor data in different sensor data sets are acquired by actual vehicles in different states in the simulation environment;
the selection module is used for determining the contact ratio of the detection range of the simulated vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set, selecting the simulated data set in each sensor data set according to the contact ratio of the detection range of the simulated vehicle sensor and the detection range of the actual vehicle sensor corresponding to each sensor data set, wherein the detection range of the actual vehicle sensor corresponding to the selected sensor data set can not completely coincide with the detection range of the simulated vehicle sensor;
a determination module, configured to determine, for each unit detection range of the simulated vehicle sensor, sensor data corresponding to the unit detection range from among the sensor data included in the simulated data set;
and the simulation module is used for obtaining simulation data according to the sensor data corresponding to each unit detection range and simulating the simulated vehicle according to the simulation data.
8. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-6.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-6 when executing the program.
CN201910462332.4A 2019-05-30 2019-05-30 Unmanned driving simulation method and device Active CN110162089B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910462332.4A CN110162089B (en) 2019-05-30 2019-05-30 Unmanned driving simulation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910462332.4A CN110162089B (en) 2019-05-30 2019-05-30 Unmanned driving simulation method and device

Publications (2)

Publication Number Publication Date
CN110162089A CN110162089A (en) 2019-08-23
CN110162089B true CN110162089B (en) 2020-11-03

Family

ID=67630094

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910462332.4A Active CN110162089B (en) 2019-05-30 2019-05-30 Unmanned driving simulation method and device

Country Status (1)

Country Link
CN (1) CN110162089B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110908387A (en) * 2019-12-13 2020-03-24 齐鲁工业大学 Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment
CN111324945B (en) 2020-01-20 2023-09-26 阿波罗智能技术(北京)有限公司 Sensor scheme determining method, device, equipment and storage medium
CN111339649B (en) * 2020-02-20 2022-02-08 西南交通大学 Simulation method, system and equipment for collecting vehicle track data
CN111563185A (en) * 2020-03-19 2020-08-21 平安城市建设科技(深圳)有限公司 Video picture display method, device, terminal and storage medium based on GIS system
CN112061131B (en) * 2020-11-13 2021-01-15 奥特酷智能科技(南京)有限公司 Road data-based method for driving simulated vehicle to avoid obstacles
CN113650616B (en) * 2021-07-20 2022-11-25 武汉光庭信息技术股份有限公司 Vehicle behavior prediction method and system based on collected data

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101825442A (en) * 2010-04-30 2010-09-08 北京理工大学 Mobile platform-based color laser point cloud imaging system
US8718858B2 (en) * 2011-03-28 2014-05-06 Khaled Abdullah M. Al-Mahnna GPS navigation system
CN103049912B (en) * 2012-12-21 2015-03-11 浙江大学 Random trihedron-based radar-camera system external parameter calibration method
CN103226833B (en) * 2013-05-08 2015-08-05 清华大学 A kind of point cloud data segmentation method based on three-dimensional laser radar
CN109211575B (en) * 2017-07-05 2020-11-20 百度在线网络技术（北京）有限公司 Unmanned vehicle and site testing method, device and readable medium thereof
CN108509918B (en) * 2018-04-03 2021-01-08 中国人民解放军国防科技大学 Target detection and tracking method fusing laser point cloud and image

Also Published As

Publication number Publication date
CN110162089A (en) 2019-08-23

Similar Documents

Publication Publication Date Title
CN110162089B (en) Unmanned driving simulation method and device
CN110414098B (en) Generation method and device of simulation test environment
CN112001456B (en) Vehicle positioning method and device, storage medium and electronic equipment
CN111238450B (en) Visual positioning method and device
CN111311709A (en) Method and device for generating high-precision map
CN111522026A (en) Data fusion method and device
CN112734810B (en) Obstacle tracking method and device
CN111797698A (en) Target object identification method and identification device
CN112327864A (en) Control method and control device of unmanned equipment
CN113674424B (en) Method and device for drawing electronic map
CN116012483A (en) Image rendering method and device, storage medium and electronic equipment
CN115880685A (en) Three-dimensional target detection method and system based on votenet model
CN111192303A (en) Point cloud data processing method and device
CN111242106A (en) Facial image acquisition method, device and equipment and facial recognition equipment
US11495021B2 (en) Picture annotation method, apparatus, processing device, and system
CN117197781B (en) Traffic sign recognition method and device, storage medium and electronic equipment
CN114494381A (en) Model training and depth estimation method and device, storage medium and electronic equipment
CN111426299B (en) Method and device for ranging based on depth of field of target object
CN112489522A (en) Method, device, medium and electronic device for playing simulation scene data
CN112362084A (en) Data calibration method, device and system
CN111798489A (en) Feature point tracking method, device, medium and unmanned device
CN112734851B (en) Pose determination method and device
CN113643321A (en) Sensor data acquisition method and device for unmanned equipment
CN112712561A (en) Picture construction method and device, storage medium and electronic equipment
CN110550025A (en) Automatic parking method and device

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