CN116467859B - Data processing method, system, device and computer readable storage medium - Google Patents
Data processing method, system, device and computer readable storage medium Download PDFInfo
- Publication number
- CN116467859B CN116467859B CN202310332659.6A CN202310332659A CN116467859B CN 116467859 B CN116467859 B CN 116467859B CN 202310332659 A CN202310332659 A CN 202310332659A CN 116467859 B CN116467859 B CN 116467859B
- Authority
- CN
- China
- Prior art keywords
- data
- computing platform
- test vehicle
- test
- vehicle model
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 36
- 238000012360 testing method Methods 0.000 claims abstract description 159
- 238000007689 inspection Methods 0.000 claims abstract description 57
- 238000004088 simulation Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 230000008859 change Effects 0.000 claims abstract description 12
- 238000004891 communication Methods 0.000 claims description 31
- 238000012795 verification Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 26
- 230000005540 biological transmission Effects 0.000 claims description 23
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000013101 initial test Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000003068 static effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 description 17
- 238000011161 development Methods 0.000 description 14
- 238000011156 evaluation Methods 0.000 description 11
- 230000033001 locomotion Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 238000009877 rendering Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000009432 framing Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000002347 injection Methods 0.000 description 3
- 239000007924 injection Substances 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a data processing method, a system, equipment and a storage medium, which are applied to a simulation server and comprise the following steps: transmitting initial inspection data to a computing platform, wherein the initial inspection data comprises initial image data rendered under a virtual scene; a test vehicle model is arranged in the virtual scene; receiving an actuator signal which is fed back by an algorithm of the computing platform according to the initial image data and is used for controlling the test vehicle model; adjusting the test vehicle model based on the actuator signal, and sending target inspection data to a computing platform, wherein the target inspection data comprises target image data rendered in the virtual scene after the test vehicle model is adjusted; the computing platform is verified based on the change in the virtual scene. The application can realize the closed loop test of the automatic driving algorithm.
Description
Technical Field
The present invention relates to the field of autopilot technology, and in particular to a data processing method, system, apparatus and computer readable storage medium.
Background
Automatic driving is a technology for realizing automatic control on a vehicle by means of artificial intelligence, computer vision and other methods. In the development phase, extensive data training or verification of the autopilot system (e.g., its computing platform) is often required to ensure the effectiveness of the autopilot system after being brought online.
In the process of training, testing and verifying an automatic driving computing platform, a large number of images are often required, the images are usually real images, the source of outputting the images to the algorithm can be understood as a data source, and further, if the algorithm is to be verified based on the real images, only whether the actuator signals output by the algorithm are identical or similar to the real actuator signals when the real images are acquired or not can be judged, namely whether the actuator signals are correct or not is judged. In the process, the output result of the computing platform is not fed back to the data source further, and is not fed back to the data source, so in the prior art, the inspection of the computing platform is usually an open loop test, and the continuous interactive feedback closed loop test of the image data by the computing platform driven automatically cannot be realized.
Disclosure of Invention
The invention provides a data processing method, a device, equipment and a computer readable storage medium, wherein the method can realize closed loop test of an automatic driving algorithm.
In a first aspect, the present invention provides a data processing method, applied to a simulation server, the method comprising:
transmitting initial inspection data to a computing platform, wherein the initial inspection data comprises initial image data rendered under a virtual scene, and a test vehicle model is arranged in the virtual scene;
Receiving an actuator signal which is fed back by an algorithm of the computing platform according to the initial image data and is used for controlling the test vehicle model;
adjusting the test vehicle model based on the actuator signal, and sending target inspection data to a computing platform, wherein the target inspection data comprises target image data rendered in the virtual scene after the test vehicle model is adjusted;
The computing platform is verified based on the change in the virtual scene.
In one embodiment of the present invention, the initial verification data and the target verification data are sent to the computing platform through a virtual screen.
In an embodiment of the invention, the method further comprises:
Acquiring a communication bus required for constructing the virtual screen, wherein the communication bus is a PCIE bus or PXIE bus;
acquiring a data transmission protocol corresponding to the PCIE bus or the PXIE bus, and obtaining the bus protocol;
after binding the communication bus and the bus protocol through a driver, registering the communication bus and the bus protocol to the virtual screen, so that the virtual screen can communicate with an FPGA interface card in the simulation server without protocol limitation based on the communication bus and the bus protocol.
In one embodiment of the present invention, the sending the initial verification data to the computing platform includes:
based on the communication bus and the bus protocol, sending the initial test data to the FPGA interface card inside the simulation server;
converting the initial test data into serial signals through the FPGA interface card;
and sending the serial signal to a video acquisition interface of the computing platform.
In an embodiment of the present invention, a reference model is further provided in the virtual scene, where the reference model includes a dynamic object reference model and/or a static object reference model;
verifying the computing platform based on the change in the virtual scene, comprising:
If the relative relation between the test vehicle model and the reference model in the virtual scene meets any check trigger condition, detecting event information, wherein the event information is used for representing whether a target event occurs in the test vehicle model or not, and the target event comprises: a first target event that should occur to the test vehicle model under the any test trigger condition, and/or: a second target event that should not occur to the test vehicle model under the any test trigger condition;
Updating the checking reference information of the computing platform according to the event information; the verification reference information is associated with the number or probability of occurrence of the detected target event;
And checking the computing platform according to the checking reference information.
In one embodiment of the invention, the relative relationship comprises at least one of: the relative distance, relative azimuth and relative speed of the test vehicle model and the reference model;
The test triggering condition includes at least one of: the relative distance is in a corresponding preset interval; the relative azimuth is in a corresponding preset interval; the relative speed is in a corresponding preset interval;
The target event includes at least one of: deceleration events, braking events, steering events, lane changing events, acceleration events, steering wheel events;
The virtual scene is also provided with a virtual camera, the virtual camera is arranged on the test vehicle model, and the target image data and the initial image data are framed and rendered based on the visual angle of the virtual camera.
In an embodiment of the invention, the method further comprises:
If the test vehicle model generates a specified abnormal event in the virtual scene, resetting the model state of the test vehicle model in the virtual scene to an initial model state, wherein the model state is used for representing at least one of the following corresponding models: position, attitude, velocity, acceleration.
In a second aspect, the invention also provides a data processing system comprising an emulation server for performing the data processing method as described above, and the computing platform.
In a third aspect, the present invention also provides a data processing apparatus comprising a memory and a processor; the memory stores an application program, and the processor is configured to execute the application program in the memory to perform the operations in the data processing method as described above.
In a fourth aspect, the present invention also provides a computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps in a data processing method as described above.
As can be seen from the above, in the data processing method of the present invention, since the data sent to the computing platform is the image data rendered under the virtual scene, and is not a real image, the execution result of the actuator signal obtained by the computing platform according to the data is fed back to the test vehicle model under the virtual scene, so as to change the virtual scene, so that a closed loop test in the process of testing the computing platform is formed. Furthermore, since there is no need to use a real image, there is no need to collect a large amount of data as test material for a real drive test vehicle drive test, and it is seen that the amount of data used for testing will not be limited by the limitations of a real vehicle drive test (for example, if a real image is used, the drive test vehicle must collect enough data by running as test material).
In a further alternative scheme of the invention, data transmission can be directly carried out based on a communication bus and a bus protocol configured by a virtual screen, so that private bus protocols corresponding to communication bus transmission technologies with high frame rate and no delay transmission effect such as PXIE, PCIE and the like are realized as the virtual screen, thereby realizing the effect of data display by accessing hardware to a screen like HDMI, realizing deep decoupling of developed simulation software (namely software used for constructing and updating virtual scenes in a simulation server) and the transmission technologies of the communication buses, shielding the hardware environment dependence of the simulation software, improving efficiency, reducing development difficulty and development cost of the simulation software, and solving the defects of data transmission delay and frame rate limitation of HDMI and DP interface transmission data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an application scenario of a data processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of an embodiment of a data processing method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a data processing apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram provided in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
The terms "first," "second," and "third," etc. in this disclosure are used for distinguishing between different objects and not for describing a particular sequential order. Meanwhile, the term "includes" and any form of modification thereof are intended to cover non-exclusive inclusion.
The embodiment of the invention provides a data processing method, a data processing device, data processing equipment and a computer readable storage medium. In accordance with embodiments of the data processing method provided by embodiments of the present invention, it should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the illustrated flowcharts, in some cases the steps described or illustrated may be performed in an order of execution that is different from that described herein.
In some embodiments of the present invention, the data processing method may be applied to at least one of a computer device and a terminal device, where the computer device may be an independent server, or may be a server network or a server cluster formed by servers, for example, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server formed by a plurality of servers. Wherein the Cloud server is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing). The terminal equipment comprises, but is not limited to, a smart phone, a tablet personal computer and a PC (personal computer) terminal.
With reference to FIG. 1, as shown in FIG. 1, a data processing system may include a simulation server and a computing platform.
In some embodiments, the simulation server may transmit the image data to the computing platform in a conventional image reinjection manner without constructing a virtual screen, and in other embodiments, the simulation server may construct a virtual screen, where the virtual screen is integrated with a communication bus and a bus protocol of the communication bus.
Wherein the computing platform may receive data (e.g., initial verification data including initial image data, target data including target image data) sent by the simulation server based on a video capture interface; analyzing and processing the received inspection data (e.g., initial inspection data including initial image data, target data including target image data) based on the autopilot computing unit to obtain an actuator signal; based on an actuator output interface, transmitting the actuator signal to the simulation server so that the simulation server updates the test data to obtain updated test data; in some examples, the cycle may be cycled until a preset condition for completion of the autopilot test is met.
The automatic driving calculation unit may include at least one of several algorithms, models, software and hardware, for example, a controller for implementing automatic driving calculation may be used as the automatic driving calculation unit, where the controller may include at least one of a chassis domain controller, an intelligent driving domain controller and the like, and for another example, the automatic driving calculation unit may be a computer, into which the algorithm of automatic driving calculation may be imported to form the automatic driving calculation unit.
It is understood that the computing platform according to the embodiment of the present invention can be understood as long as the actuator signal for controlling the vehicle can be output based on the input inspection data.
In one example, a real vehicle may also be used as a computing platform, such as a suspended real vehicle, a real vehicle in open space, etc.
Reference to test data (e.g., initial test data, target test data) in this specification is to be understood as any data associated with a test vehicle model for testing a computing platform.
The image data (e.g., initial image data, target image data) in the inspection data may be understood as any image data obtained by framing and rendering in a virtual scene, in one example, a virtual camera is further disposed in the virtual scene, and the virtual camera is disposed in the test vehicle model and may be used to simulate a framing manner of the vehicle camera, for example, may include a front view camera, a side view camera, a rear view camera, and the like, and the image data (e.g., target image data, initial image data) is framed and rendered based on a viewing angle of the virtual camera.
The initial test data may be understood as test data for generating the corresponding actuator signal, and the target test data may be understood as test data generated after the corresponding actuator signal is executed, and meanwhile, the target test data generated after the execution of a certain actuator signal may be used as initial test data for generating another set of actuator signals, and the initial test data for generating a certain actuator signal may be the target test data generated after the execution of another set of actuator signals. Therefore, the transmission mode of the initial verification data and any content of the data content are described in the specification, and the method is also applicable to the target verification data.
Further, the inspection data may include, in addition to the image data, any other sensing data of the test vehicle model, which may refer to any data associated with driving control of the vehicle that can be detected by a sensor in the real vehicle, and further, the sensing data may include, for example, at least one of:
the vehicle model is tested for speed, acceleration, steering information (e.g., steering wheel angle), position data (representing the position of the corresponding model in the virtual field), and so forth.
In some embodiments of the present invention, the data processing method may be applied to scenes such as automatic driving, assisted driving, and the like. Referring to fig. 2, fig. 2 is a flowchart of an embodiment of a data processing method according to an embodiment of the present invention, as shown in fig. 2, the method is applied to a simulation server, and may specifically include the following steps 201 to 205:
Step 201, the initial verification data is sent to the computing platform.
The initial inspection data comprise initial image data rendered under a virtual scene, and a test vehicle model is arranged in the virtual scene. In some embodiments, the initial verification data and the target verification data may be sent to the computing platform through a virtual screen.
In some embodiments, the method of the present application may further comprise:
Acquiring a communication bus required for constructing the virtual screen, wherein the communication bus is a PCIE bus or PXIE bus;
acquiring a data transmission protocol corresponding to the PCIE bus or the PXIE bus, and obtaining the bus protocol;
after binding the communication bus and the bus protocol through a driver, registering the communication bus and the bus protocol to the virtual screen, so that the virtual screen can communicate with an FPGA interface card in the simulation server without protocol limitation based on the communication bus and the bus protocol.
The simulation server is used for simulating, rendering and generating test data of automatic driving. In some embodiments, the simulation server may be based on a high-performance computer, and internally includes hardware such as an FPGA interface card, an executor interface card, a display card, and an operating system of simulation software.
In some embodiments, in the case of implementing the virtual screen, the resolution and/or the frame rate may be implemented through setting the virtual screen, so as to remove the limitation that the functions of adjusting the resolution and the frame rate can only be designed in the FPGA in the prior art, and improve the flexibility and efficiency of parameter setting. That is, there is no need to provide a resolution adjustment circuit or a frame rate adjustment circuit in the FPGA interface card. For example, after image data is generated and sent to the virtual screen, the virtual screen processes the image data into a resolution and a frame rate set by the virtual screen.
The communication buses may include PCIE buses and PXIE buses. In some embodiments, after obtaining the PCIE bus and PXIE bus, the bus protocol of data transmission corresponding to the PCIE bus and PXIE bus may be further obtained, and the obtained bus protocol registration is written into the virtual screen through the driver, so that the virtual screen of the present application integrates the above communication bus and the corresponding bus protocol.
Therefore, in the scheme, the data processing method can directly perform data transmission based on the communication bus and the bus protocol configured by the virtual screen, so that the private bus protocol corresponding to the communication bus transmission technology with high frame rate and no delay transmission effect such as PXIE, PCIE and the like is realized as the virtual screen, the effect of data display like HDMI (high definition multimedia interface) can be realized, the DP interface is accessed to hardware to acquire the screen for performing data display, the deep decoupling of the developed simulation software and the transmission technology of the communication bus can be realized, the hardware environment dependence of the simulation software is shielded, the efficiency is improved, the development difficulty and the development cost of the simulation software are reduced, and the defects of data transmission delay and frame rate limitation of HDMI and DP interface transmission data can be overcome.
The initial inspection data comprise initial image data rendered under the virtual scene where the test vehicle model is located. It can be appreciated that in the automatic driving inspection scenario, the system is required to learn a large amount of image data of the scenario and environment related to the running of the test vehicle, so as to execute different control operations of the test vehicle on different environmental scenarios, thereby inspecting the accuracy and rationality of the corresponding functions of the computing platform.
Thus, the initial image data corresponding to the initial inspection data may be a relatively perfect virtual scene simulating the running environment of the vehicle, for example, the virtual scene may be similar to a game map, including a test vehicle model and other reference models, such as reference models of other vehicles, people, buildings, obstacles, etc., wherein the virtual scene may include dynamic object reference models of moving objects, such as reference models of vehicles, people, etc., and static object reference models of moving objects, such as reference models of buildings, obstacles (e.g., roadblocks, flowers and trees, etc.), lane lines, guideboards, signal lamps, etc.
In some embodiments, in addition to the test vehicle model being free to move, the dynamic reference models of other vehicles and people may be configured to move freely, for example, they may be configured to perform movement conforming to a certain specification (e.g., traffic specification) with a certain target, for example, a certain vehicle in the virtual scene is a specification movement from point a to point B, or they may be configured to move randomly in a situation conforming to a certain specification (e.g., traffic specification), for example, to perform movement such as steering, turning around, braking, advancing, accelerating, decelerating, etc. randomly in the virtual scene. The motion characteristics of the dynamic reference model may be pre-constructed according to the type of the dynamic reference model.
Any means in the art for modeling a dynamic model to move can be used as an implementation of the dynamic reference model. In some examples, a means implementation of game modeling operations may also be referenced.
In addition, the motion rule of the dynamic reference model in the virtual scene can be determined according to the requirement, and can also be dynamically changed, for example, the dynamic reference model moves at a specified target in part of time, moves at random in another part of time, and moves at another specified target in another part of time.
In some embodiments, the richness of the overall features in the scene can also be controlled by adjusting the complexity of the motion and occurrence events of the vehicles and people in the virtual scene, for example, the number of the vehicles and the people contained in the virtual scene can be set, so that the capability of the automatic driving control end of the computing platform under different complexities is tested. Some events which do not meet the traffic regulations, such as events of virtual scenes of traffic accidents, vehicle collisions and the like, can be set, so that the capability of the computing platform to cope with the events is tested.
Since virtual scenes are introduced as the basis of the inspection, various possibilities of the inspection can be greatly enriched. Thereby facilitating comprehensive and efficient inspection of the computing platform.
Optionally, in some embodiments, step "send initial verification data to computing platform" includes:
Transmitting the verification data (e.g., initial verification data and target verification data) to an FPGA interface card within the simulation server based on the communication bus and the bus protocol;
converting the verification data (e.g., initial verification data and target verification data) to serial signals by the FPGA interface card;
and sending the serial signal to a video acquisition interface of the computing platform.
The computing platform may be a device that issues a vehicle control signal for executing the vehicle control signal in the automatic driving, such as an ECU, an automatic driving perception model, or the like.
In some embodiments, the virtual screen may transmit the test data to the FPGA interface card in a high frame rate and low latency manner based on the corresponding bus protocol through the PCIE bus or PXIE bus, where the high frame rate is implemented through a window management mechanism of a high-speed low latency and operating system (Windows and linux) of the PCIE or PXIE interface, a driver may control a frame rate of each virtual screen, and each screen may implement high frame rate video injection. Even the time measurement of the simulation software and the calculation software can be adjusted, and the video injection higher than the actual frame rate of the test vehicle is used for improving the speed, so that the defects of one-frame image delay caused by data transmission through HDMI or DP interface and incapability of high-frame rate transmission can be overcome.
It can be appreciated that the virtual screen is integrated with the communication bus and the corresponding bus protocol, so that the protocol does not need to be repeatedly agreed with the FPGA interface card for each data transmission, high-speed and low-delay transmission of test data can be directly realized, and the dependence on all external hardware environments can be shielded.
The serial signal may be a GMSL (Gigabit Multimedia SERIAL LINKS) signal, and the converted GMSL signal is injected to the computing platform through the FPGA interface card.
In some embodiments, the device interface may be an interface of an associated gaming platform or database, and the verification data may be a second video and a second image of a virtual scene in which the test vehicle is located. For example, the simulation server can generate a virtual scene related to vehicle driving through simulation software, or can directly call and acquire the game virtual scene related to vehicle driving from a game platform or a database based on a device interface, for example, the existing driving game can be simply modified or not modified and is connected to an automatic driving computing platform for verification, simulation or rendering.
The virtual scene can comprise virtual road, vehicle, traffic warning board and other reference models, and after framing and rendering, various videos, images and emergency situations of driving the test vehicle model in the virtual environment scene can be simulated, for example, abnormal situations such as overspeed, slipping, rear-end collision and the like of the test vehicle in the virtual scene can be simulated. It can be understood that the video image collected by the road in the real scene of the vehicle driving may not contain the data of the abnormal or accident of the vehicle, so that the comprehensiveness and diversity of the inspection data can be improved by generating the video and the image of the virtual scene, thereby improving the subsequent inspection effect on the automatic driving computing platform.
Step 202, receiving an actuator signal which is fed back by an algorithm of the computing platform according to the initial image data and is used for controlling the test vehicle model.
To facilitate an understanding of the above, in one example, assuming that the virtual scene contains a road, the goal of the test vehicle model is to travel through the road under the control of the computing platform in a state that meets certain specifications (e.g., traffic light specifications for red light stop and green light rows, lane travel specifications, etc.). Or the virtual scene comprises a closed loop road section with any shape, and the test vehicle can continuously and stably run in a state of a certain load standard (such as signal lamp standard of stopping a red light and stopping a green light, lane running standard and the like) on the premise that other vehicles, people and barriers exist on the closed loop road.
Further, in the running process of the test vehicle model, an image in a virtual scene is framed and rendered, for example, the test vehicle is provided with a plurality of virtual cameras with different orientations at the positions of the head and the tail, so that the simulation server can framed and render the front of the test vehicle in the virtual scene through the position angles of the plurality of cameras to obtain two-dimensional image data so as to form a plurality of test data.
After the image data of the test data are sent to the computing platform, the computing platform calculates an actuator signal for controlling the test vehicle to perform standard movement in the virtual scene according to an algorithm stored by the computing platform, the generated actuator signal is sent to the simulation server, the simulation server can control the test vehicle according to the actuator signal, meanwhile, whether the actuator signal meets a preset rule can be verified, if the actuator signal does not meet the preset rule, the event which does not meet the preset rule is recorded for subsequent verification and evaluation of the computing platform algorithm.
In some embodiments, the computing platform may generate a control policy for changing a model state (such as a speed, an acceleration, steering information, etc.) of the test vehicle model according to determining whether the model state of the test vehicle model in the virtual scene satisfies a preset condition, and if so. The preset condition may be any condition that needs to be adjusted to the model state. Taking the above test vehicle running in the virtual scene as an example, assuming that the test vehicle is running in the road of the virtual scene normally, if an obstacle is found to be located at the center of the running road 30m in front, the normal running of the test vehicle can be ensured by adjusting the model state corresponding to the motion data such as the speed, the acceleration, the steering, etc. of the test vehicle model, so that the event that the obstacle is located at the center of the running road 30m in front satisfies the preset condition for adjusting the model state, and a control strategy for changing the model state of the first model is generated.
Step 203, based on the actuator signal, adjusting the test vehicle model, and sending target inspection data to a computing platform.
The target inspection data comprise target image data rendered in the virtual scene after the test vehicle model is adjusted. The target verification data can also be sent to the computing platform through the virtual screen.
In some embodiments, the computing platform may output an actuator signal for controlling the test vehicle, where the actuator signal may include an IO signal, a Can signal, an Eth signal, and other signals for controlling the test vehicle, and after receiving the above actuator signal, the actuator interface card of the simulation server may adjust parameters of the model in the image data by reading and analyzing the above actuator signal.
For example only, for the example of "30 meters ahead with an obstacle in the center of the driving road" in step 203, assuming that the actuator signal is for controlling the steering wheel of the test vehicle to rotate 30 ° to the left, the operating system of the simulation server will read and analyze the actuator signal to obtain an adjustment value corresponding to the calculated parameter of the model, and further analyze the calculated adjustment value to adjust the parameter of the model based on the adjustment. For example, if the model to be adjusted is an obstacle in front of the test vehicle, the position parameter of the model can be adjusted based on the actuator signal that the steering wheel rotates by 30 ° to the left, for example, the model moves by 2 meters, 3 meters, etc. to the right relative to the position of the previous frame in the video, and then the adjusted model is rendered to obtain a corresponding rendered image.
Continuing with this example, taking the signal of the actuator as an example for controlling the vehicle to turn left to avoid the obstacle, after the test vehicle receives the signal to turn to avoid the obstacle, the rendered image of the environmental scene in each direction and view angle of the test vehicle at the current moment can be obtained as updated test data, for example, the video directly in front of the test vehicle at the current moment does not contain the previous obstacle any more to generate new video data.
In some embodiments, the simulation server may simulate a three-dimensional virtual scene through simulation software, similar to a game three-dimensional scene, for example, the three-dimensional scene may include virtual roads, road identifications, vehicles, obstacles, and other virtual models related to driving of the vehicle. Then, the virtual model in the virtual scene can be rendered at different angles, the operation is equivalent to adjusting the position parameters of the model, so as to obtain the rendering pictures of different visual angles in the same virtual scene, and then the rendering pictures of different visual angles are displayed on different virtual screens, so that synchronous injection of the rendering pictures of different visual angles in the same virtual scene is realized. For example, in the virtual scene, there may be one vehicle X (i.e., a test vehicle model), and for the virtual screen a, a picture of a camera view angle in front of the vehicle X in the virtual scene may be taken when the virtual screen a corresponds to the view, and for the virtual screen B, a picture of a camera view angle behind the rear of the vehicle X in the virtual scene may be taken when the virtual screen B corresponds to the view; the actuator signal may effect operation of the vehicle X to start, accelerate, decelerate, turn, etc. In a virtual scenario, vehicle X may perform actions corresponding to the operation of the actuator signal, the controlled course of motion of which is similar to the controlled course of motion of a vehicle in a game scenario. With this change, the screen taken by the virtual screen A, B changes.
In some embodiments, the method of the present application may further comprise:
And if the test vehicle model generates a specified abnormal event in the virtual scene, resetting the model state of the test vehicle model in the virtual scene to an initial model state.
The model state is used to represent at least one of the following of the corresponding model: position, attitude, velocity, acceleration, etc.
In some embodiments, if the test vehicle model collides in the virtual scene, and the test vehicle is in a rear-end collision, the test vehicle model may be repositioned to a position in the virtual scene, for example, the position may be an initial area. For example, when the virtual scene is a road section connected to a closed-loop road section, the test vehicle is separated from the road section after each reset, and enters a rectangular annular road section, for example, the reset position may be a parking lot exit of a building in the virtual scene, and the embodiment is not limited thereto.
The data processing method may further include:
step 204, checking the computing platform based on the change of the virtual scene.
The execution of step 204 may be performed at any time, for example, before, during, or after step 202, before, during, or after step 203, or may be performed in parallel with steps 202 and 203, or may be performed after the test vehicle model stops traveling in the virtual scene. It will be appreciated that the continual looping of steps 202, 203 may form the basis for verification, i.e. the change of the virtual scene, whereas for verification only the change of the virtual scene, i.e. only the control result of the computing platform, may not be concerned with the actuator signal itself.
In one embodiment, with the steps 202, 203 repeated, step 204 may be performed after the test vehicle model has traveled a sufficient amount of time or distance in the virtual scene (e.g., the accumulated travel time or distance reaches the target value), i.e., the verification may be achieved by backtracking all changes in the virtual scene.
Furthermore, in the data processing method, because the data sent to the computing platform is the image data rendered under the virtual scene and is not a real image, the execution result of the actuator signal obtained by the computing platform can be fed back to the test vehicle model under the virtual scene to change the virtual scene, so that the closed loop test in the process of checking the computing platform is formed. Furthermore, since there is no need to use a real image, there is no need to collect a large amount of data as test material for a real drive test vehicle drive test, and it is seen that the amount of data used for testing will not be limited by the limitations of a real vehicle drive test (for example, if a real image is used, the drive test vehicle must collect enough data by running as test material).
In one embodiment, step 204 may include:
if the relative relation between the test vehicle model and the reference model in the virtual scene meets any inspection trigger condition, event information is detected,
Updating the checking reference information of the computing platform according to the event information;
And checking the computing platform according to the checking reference information.
Corresponding to the above steps, if the detection trigger condition is not satisfied, the event information does not need to be detected.
The relative relationship includes at least one of: the relative distance, relative azimuth and relative speed of the test vehicle model and the reference model;
The test triggering condition includes at least one of: the relative distance is in a corresponding preset interval; the relative azimuth is in a corresponding preset interval; the relative speed is in a corresponding preset interval.
The event information is used for representing whether the test vehicle model generates a target event or not;
The target event includes: a first target event that should occur to the test vehicle model under the any test trigger condition, and/or: a second target event that should not occur to the test vehicle model under the any test trigger condition;
Furthermore, the target events (first target event and/or second target event) corresponding to different verification trigger conditions may be different, e.g., completely different, or partially different.
The verification reference information is associated with the number or probability of occurrence of the detected target event; specifically, the checking reference information may be the times and/or the probability itself, or may be a statistical value of the times and/or the probability;
The target event includes at least one of: deceleration events, braking events, steering events, lane changing events, acceleration events, steering wheel events.
In a specific example, the test reference information of the computing platform may differentiate between different test trigger conditions for statistical update, for example, the occurrence number of the first target event and/or the occurrence number of the second target event under each test trigger condition may be statistically updated to be used as the test reference information.
In one example, for each inspection triggering condition, a corresponding first weight value may be preset, then when the computing platform is inspected according to the inspection reference information, the occurrence times of the first target events of all the inspection triggering conditions may be weighted and summed based on the first weight value to obtain a first summation value, and the first summation value is divided by the total mileage (or total duration) of the test vehicle model to obtain a first inspection evaluation value; judging whether the computing platform meets the inspection requirements or not based on the first inspection evaluation value, for example, if the first inspection evaluation value is lower than a preset first threshold value, considering that the computing platform does not meet the inspection requirements;
In one example, for each inspection triggering condition, a corresponding second weight value may be preset, then when the computing platform is inspected according to the inspection reference information, the occurrence times of the second target events of all the inspection triggering conditions may be weighted and summed based on the second weight value to obtain a second summed value, and the second summed value is divided by the total mileage (or total duration) of the test vehicle model to obtain a second inspection evaluation value; judging whether the computing platform meets the inspection requirements or not based on the second inspection evaluation value, for example, if the second inspection evaluation value is higher than a preset second threshold value, considering that the computing platform does not meet the inspection requirements;
In combination with the above example, for example, the inspection requirements may be considered to be satisfied in the case where the first inspection evaluation value is higher than a preset first threshold value and the second inspection evaluation value is lower than a preset second threshold value. The difference value, the ratio and the like of the first checking evaluation value and the second checking evaluation value can be firstly obtained, and whether the checking requirement is met or not can be judged according to the difference value, the ratio and the like.
Through the steps, the method can be used for realizing the security check, compliance check and the like of the computing platform.
For one example of the test trigger condition and the target event, if the relative distance between the test vehicle model and the reference model of the preceding vehicle is smaller than a certain threshold value, it is considered that a corresponding one of the test trigger conditions T1 is achieved, it may be detected whether a corresponding target event occurs in this case, for example, whether a first target event such as a deceleration event, a braking event, etc., occurs, and a second target event such as an acceleration event, etc.
For one example of the test trigger condition and the target event, if the relative distance between the test vehicle model and the reference model of the preceding vehicle is smaller than a certain threshold value and the relative speed is decreasing, then it is considered that the corresponding one test trigger condition T2 is achieved, it may be detected whether the corresponding target event occurs in this case, for example, whether a first target event such as a deceleration event, a braking event, etc. of sufficient intensity occurs, and then a second target event such as an acceleration event, a deceleration event, etc. of insufficient intensity does not occur.
For one example of a test trigger condition, a target event, if a test vehicle model travels between the reference models of two lane lines, if the relative distance between the test vehicle model and the reference model of either lane line L is less than a certain threshold (e.g., a certain threshold close to 0), then a corresponding one of the test trigger conditions T3 is considered to be fulfilled, then it may be detected whether a corresponding target event occurs in this case, e.g., whether a reverse steering wheel has occurred to be away from the first target event of the lane line L.
For one example of a test trigger condition, a target event, if a reference model is within a certain relative distance of a certain relative orientation to the left of the test vehicle model, then a corresponding one of the test trigger conditions T4 is considered to be fulfilled, then it may be detected whether a corresponding target event has occurred in this case, for example, whether a first target event has occurred to turn the steering wheel to the right.
It can be appreciated that by checking the algorithm of the computing platform multiple times, the algorithm of the computing platform can be adjusted appropriately, so that the accuracy of the actuator signal fed back by the computing platform is improved to meet the standard of the online requirement of automatic driving, for example, the control accuracy of the actuator signal on the test vehicle has reached the industry standard, or the requirement specified by the research personnel, the user, etc.
The data processing method simulation server can acquire the actuator signals output by the computing platform, so that corresponding pictures are rendered in real time to update training data, and the updated training data are injected into the computing platform to be repeated, thereby realizing real closed loop test. The virtual screen of the communication bus with high frame rate and no delay transmission effect is adopted in the closed loop test for data transmission, and the training accuracy can be ensured.
In addition, in order to reduce the development difficulty and development cost of the closed-loop simulation test environment, the design of an executor interface card and a virtual screen is introduced into the simulation server, so that the development of the simulation software has the advantage of low development threshold of conventional game development, more research and development personnel can participate in the development of automatic driving training by utilizing the current game development infrastructure, the development difficulty and cost of the simulation software are further reduced, and the development efficiency is improved.
Data processing method in order to better implement the data processing method provided by the embodiment of the present invention, on the basis of the automatic data processing method, a data processing device is provided, as shown in fig. 3, fig. 3 is a schematic structural diagram of an embodiment of a data processing system of the data processing device provided by the embodiment of the present invention, where the data processing system of the data processing device includes:
The simulation server can comprise an operating system, an FPGA interface card, an executor interface card and a display card, and the operating system can comprise simulation software, a virtual screen, an OpenGL interface and a device interface;
The computing platform, which can be understood as the detected object of the simulation server, can be implemented by any automatic driving computing carrier in the field.
The embodiment of the invention also provides equipment, as shown in fig. 4, which shows a schematic structural diagram provided by the embodiment of the invention, in particular:
The autopilot training apparatus may include one or more processing cores 'processing module 401, one or more computer-readable storage medium's storage module 402, power module 403, and input module 404, among other components. It will be appreciated by those skilled in the art that the configuration of the autopilot training apparatus shown in fig. 4 is not limiting of the autopilot training apparatus and may include more or fewer components than shown, or certain components in combination, or a different arrangement of components. Wherein:
The processing module 401 is a control center of the automatic driving training apparatus, connects various parts of the entire automatic driving training apparatus using various interfaces and lines, and performs various functions of the automatic driving training apparatus and processes data by running or executing software programs and/or modules stored in the storage module 402, and calling data stored in the storage module 402. Optionally, the processing module 401 may include one or more processing cores; preferably, the processing module 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program, etc., and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processing module 401.
The storage module 402 may be used to store software programs and modules, and the processing module 401 executes various functional applications and data processing by running the software programs and modules stored in the storage module 402. The storage module 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created from use of the autopilot training device, etc. In addition, the storage module 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory module 402 may also include a memory controller to provide access to the memory module 402 by the processing module 401.
The autopilot training apparatus further includes a power module 403 for powering the various components, and preferably, the power module 403 may be logically connected to the processing module 401 through a power management system, so that functions of managing charging, discharging, and power consumption are implemented through the power management system. The power module 403 may also include one or more of any components, such as a direct current or alternating current power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The autopilot training apparatus may further include an input module 404, the input module 404 being operable to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the automatic driving training apparatus may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processing module 401 in the autopilot training device loads executable files corresponding to the processes of one or more application programs into the storage module 402 according to the following instructions, and the processing module 401 runs the application programs stored in the storage module 402, so as to implement various functions as follows:
transmitting initial inspection data to a computing platform, wherein the initial inspection data comprises initial image data rendered under a virtual scene, and a test vehicle model is arranged in the virtual scene;
Receiving an actuator signal which is fed back by an algorithm of the computing platform according to the initial image data and is used for controlling the test vehicle model;
adjusting the test vehicle model based on the actuator signal, and sending target inspection data to a computing platform, wherein the target inspection data comprises target image data rendered in the virtual scene after the test vehicle model is adjusted;
The computing platform is verified based on the change in the virtual scene.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present invention provides a computer readable storage medium having stored therein a plurality of instructions capable of being loaded by a processor to perform the steps of any of the data processing methods provided by the embodiments of the present invention. For example, the instructions may perform the steps of:
transmitting initial inspection data to a computing platform, wherein the initial inspection data comprises initial image data rendered under a virtual scene, and a test vehicle model is arranged in the virtual scene;
Receiving an actuator signal which is fed back by an algorithm of the computing platform according to the initial image data and is used for controlling the test vehicle model;
adjusting the test vehicle model based on the actuator signal, and sending target inspection data to a computing platform, wherein the target inspection data comprises target image data rendered in the virtual scene after the test vehicle model is adjusted;
The computing platform is verified based on the change in the virtual scene.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
Wherein the computer-readable storage medium may comprise: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
Because the instructions stored in the computer readable storage medium may execute the steps in any data processing method provided by the embodiments of the present invention, the beneficial effects that any data processing method provided by the embodiments of the present invention can be achieved, which are detailed in the previous embodiments and are not described herein.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements and adaptations of the application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within the present disclosure, and therefore, such modifications, improvements, and adaptations are intended to be within the spirit and scope of the exemplary embodiments of the present disclosure.
Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.
Some aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. The processor may be one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital signal processing devices (DAPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or a combination thereof. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media. For example, computer-readable media can include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips … …), optical disks (e.g., compact disk CD, digital versatile disk DVD … …), smart cards, and flash memory devices (e.g., card, stick, key drive … …).
The computer readable medium may comprise a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable medium can be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or the like, or a combination of any of the foregoing.
Similarly, it should be noted that in order to simplify the description of the present disclosure and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure does not imply that the subject application requires more features than are set forth in the claims. Indeed, less than all of the features of a single embodiment disclosed above.
While the application has been described with reference to the specific embodiments presently, it will be appreciated by those skilled in the art that the foregoing embodiments are merely illustrative of the application, and various equivalent changes and substitutions may be made without departing from the spirit of the application, and therefore, all changes and modifications to the embodiments are intended to be within the scope of the appended claims.
Claims (10)
1. A data processing method, applied to a simulation server, the method comprising:
Transmitting initial inspection data to a computing platform, wherein the initial inspection data comprises initial image data rendered under a virtual scene, and a test vehicle model and a reference model are arranged in the virtual scene;
Receiving an actuator signal which is fed back by an algorithm of the computing platform according to the initial image data and is used for controlling the test vehicle model;
adjusting the test vehicle model based on the actuator signal, and sending target inspection data to a computing platform, wherein the target inspection data comprises target image data rendered in the virtual scene after the test vehicle model is adjusted;
Verifying the computing platform based on the change in the virtual scene, comprising: if the relative relation between the test vehicle model and the reference model in the virtual scene meets any check trigger condition, detecting event information, wherein the event information is used for representing whether a target event occurs in the test vehicle model or not, and the target event comprises: a first target event that should occur to the test vehicle model under the any test trigger condition, and/or: a second target event that should not occur to the test vehicle model under the any test trigger condition; updating the checking reference information of the computing platform according to the event information; the verification reference information is associated with the number or probability of occurrence of the detected target event; and checking the computing platform according to the checking reference information.
2. The data processing method of claim 1, wherein the initial verification data and the target verification data are sent to the computing platform via a virtual screen.
3. The method according to claim 2, wherein the method further comprises:
Acquiring a communication bus required for constructing the virtual screen, wherein the communication bus is a PCIE bus or PXIE bus;
Acquiring a data transmission protocol corresponding to the PCIE bus or the PXIE bus to obtain a bus protocol;
after binding the communication bus and the bus protocol through a driver, registering the communication bus and the bus protocol to the virtual screen, so that the virtual screen can communicate with an FPGA interface card in the simulation server without protocol limitation based on the communication bus and the bus protocol.
4. A data processing method according to claim 3, wherein said sending initial verification data to a computing platform comprises:
based on the communication bus and the bus protocol, sending the initial test data to the FPGA interface card inside the simulation server;
converting the initial test data into serial signals through the FPGA interface card;
and sending the serial signal to a video acquisition interface of the computing platform.
5. The data processing method according to claim 1, wherein the reference model comprises a dynamic object reference model and/or a static object reference model.
6. The data processing method of claim 5, wherein the relative relationship comprises at least one of: the relative distance, relative azimuth and relative speed of the test vehicle model and the reference model;
The test triggering condition includes at least one of: the relative distance is in a corresponding preset interval; the relative azimuth is in a corresponding preset interval; the relative speed is in a corresponding preset interval;
The target event includes at least one of: deceleration events, braking events, steering events, lane changing events, acceleration events, steering wheel events;
The virtual scene is also provided with a virtual camera, the virtual camera is arranged on the test vehicle model, and the target image data and the initial image data are framed and rendered based on the visual angle of the virtual camera.
7. The data processing method of claim 1, wherein the method further comprises:
If the test vehicle model generates a specified abnormal event in the virtual scene, resetting the model state of the test vehicle model in the virtual scene to an initial model state, wherein the model state is used for representing at least one of the following corresponding models: position, attitude, velocity, acceleration.
8. A data processing system, characterized in that the system comprises a simulation server for performing the data processing method of any of claims 1 to 7, and the computing platform.
9. A data processing apparatus comprising a memory and a processor; the memory stores an application program, and the processor is configured to execute the application program in the memory to perform the operations in a data processing method according to any one of claims 1 to 7.
10. A computer readable storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor for performing the steps of a data processing method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310332659.6A CN116467859B (en) | 2023-03-30 | 2023-03-30 | Data processing method, system, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310332659.6A CN116467859B (en) | 2023-03-30 | 2023-03-30 | Data processing method, system, device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116467859A CN116467859A (en) | 2023-07-21 |
| CN116467859B true CN116467859B (en) | 2024-05-10 |
Family
ID=87172723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310332659.6A Active CN116467859B (en) | 2023-03-30 | 2023-03-30 | Data processing method, system, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116467859B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114296424A (en) * | 2021-12-06 | 2022-04-08 | 苏州挚途科技有限公司 | Simulation test system and method |
| WO2022141294A1 (en) * | 2020-12-30 | 2022-07-07 | 深圳市大疆创新科技有限公司 | Simulation test method and system, simulator, storage medium, and program product |
| CN115167374A (en) * | 2022-08-09 | 2022-10-11 | 科大国创合肥智能汽车科技有限公司 | Automatic driving sensor recharging virtual simulation test method and system thereof |
| CN115623271A (en) * | 2022-10-10 | 2023-01-17 | 昆易电子科技(上海)有限公司 | Processing method of video to be injected and electronic equipment |
| CN115857685A (en) * | 2022-11-30 | 2023-03-28 | 宁波吉利汽车研究开发有限公司 | Perception algorithm data closed-loop method and related device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10086845B2 (en) * | 2015-10-30 | 2018-10-02 | Mitsubishi Electric Corporation | Vehicle information display control device, and method for displaying automatic driving information |
| US11687165B2 (en) * | 2020-12-30 | 2023-06-27 | Meta Platforms Technologies, Llc | Stabilizing gestures in artificial reality environments |
-
2023
- 2023-03-30 CN CN202310332659.6A patent/CN116467859B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022141294A1 (en) * | 2020-12-30 | 2022-07-07 | 深圳市大疆创新科技有限公司 | Simulation test method and system, simulator, storage medium, and program product |
| CN114296424A (en) * | 2021-12-06 | 2022-04-08 | 苏州挚途科技有限公司 | Simulation test system and method |
| CN115167374A (en) * | 2022-08-09 | 2022-10-11 | 科大国创合肥智能汽车科技有限公司 | Automatic driving sensor recharging virtual simulation test method and system thereof |
| CN115623271A (en) * | 2022-10-10 | 2023-01-17 | 昆易电子科技(上海)有限公司 | Processing method of video to be injected and electronic equipment |
| CN115857685A (en) * | 2022-11-30 | 2023-03-28 | 宁波吉利汽车研究开发有限公司 | Perception algorithm data closed-loop method and related device |
Non-Patent Citations (2)
| Title |
|---|
| 基于增强现实的汽车驾驶仿真实验系统;方艳红;庄永智;王学渊;张红英;;实验技术与管理;20201231(第04期);153-156 * |
| 基于虚拟场景自动构建的四旋翼仿真测试系统;邓顺;杨涛;梅艳莹;;传感器与微系统;20200826(第09期);107-110 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116467859A (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110795818B (en) | Method and device for determining virtual test scene, electronic equipment and storage medium | |
| CN111919225B (en) | Training, testing, and validating autonomous machines using a simulated environment | |
| CN113157578B (en) | Automatic driving simulation test method and device based on scene | |
| CN111813650B (en) | Visual unmanned vehicle decision control simulation test method and system | |
| CN115016474A (en) | Control method, road side equipment, cloud control platform and system for cooperative automatic driving of vehicle and road | |
| CN112819968B (en) | Test method and device for automatic driving vehicle based on mixed reality | |
| CN109345829A (en) | Monitoring method, device, equipment and the storage medium of unmanned vehicle | |
| WO2022078077A1 (en) | Driving risk early warning method and apparatus, and computing device and storage medium | |
| KR102139172B1 (en) | Autonomous vehicle simulation method in virtual environment | |
| CN110032947A (en) | A kind of method and device that monitor event occurs | |
| CN114492022A (en) | Road condition sensing data processing method, device, equipment, program and storage medium | |
| CN116403174A (en) | End-to-end automatic driving method, system, simulation system and storage medium | |
| CN110874610B (en) | Human driving behavior modeling system and method using machine learning | |
| CN114444208A (en) | Method, device, equipment and medium for determining reliability of automatic driving system | |
| Xiong et al. | Design and Implementation of Digital Twin‐Assisted Simulation Method for Autonomous Vehicle in Car‐Following Scenario | |
| CN114722631A (en) | Vehicle test simulation scene generation method and device, electronic equipment and storage medium | |
| CN112849144B (en) | Vehicle control method, device and storage medium | |
| CN116467859B (en) | Data processing method, system, device and computer readable storage medium | |
| CN115830562B (en) | Lane information determination method, computer device and medium | |
| CN111881121A (en) | Automatic driving data filling method and device | |
| CN111816022A (en) | Simulation method and device for simulation scene, storage medium and electronic equipment | |
| Kowol et al. | A-eye: Driving with the eyes of ai for corner case generation | |
| CN113962107A (en) | Method and device for simulating driving road section, electronic equipment and storage medium | |
| CN112769929A (en) | Site-to-site loop test system and method for vehicle-road cooperation technology | |
| CN115903542A (en) | Interactive driving simulation system, method, equipment and storage medium |
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 |