Autonomous driving simulation system, method, server and medium

Abstract

The present invention discloses an automatic driving simulation system, method, server and medium, wherein the scene construction subsystem in the system is used to process the received data to be processed corresponding to the target area to obtain the simulation scene file corresponding to the target area; the simulation service subsystem communicates with the scene construction subsystem, and is used to obtain the simulation scene file determined by the scene construction subsystem, and processes the simulation scene file to obtain the dynamic scene corresponding to the target area, so as to simulate the automatic driving of the subsystem under test based on the dynamic scene; wherein the subsystem under test is integrated with an automatic driving algorithm. The technical solution of the embodiment of the present invention solves the problem that there are certain safety risks and high labor costs in the prior art when conducting road tests, and realizes that the corresponding road tests can be carried out in a simulation environment, thereby improving the technical effect of road test efficiency and safety.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of autonomous driving technology, and in particular to an autonomous driving simulation system, method, server and medium. Background Art

[0002] At present, driverless cars have become a trend. Before the specific application of driverless cars, road tests can be carried out to determine the control effect of the autonomous driving algorithm, and then adjust the autonomous driving algorithm based on the control effect. This method is also called road testing.

[0003] Road testing mainly involves deploying the autonomous driving algorithm to the autonomous driving vehicle and turning on the autonomous driving in a real road environment to test the autonomous driving algorithm. This testing method is based on a real traffic environment and the test results are authentic and reliable.

[0004] However, the above method has certain problems. The autonomous driving algorithm is not mature. When unmanned vehicles conduct road tests based on this algorithm, there are certain safety risks, high labor costs, and it is difficult to complete high-mileage and multi-scenario coverage tests in a short period of time. Summary of the invention

[0005] The present invention provides an autonomous driving simulation system, method, server and medium to achieve testing in various scenarios in a simulation environment, which not only improves testing efficiency and safety, but also reduces labor costs.

[0006] In a first aspect, an embodiment of the present invention provides an autonomous driving simulation system, the system comprising: a scenario construction subsystem, a simulation service subsystem;

[0007] A scene construction subsystem is used to process the received data to be processed corresponding to the target area to obtain a simulation scene file corresponding to the target area; wherein the target area is an area for unmanned vehicle road testing, and the data to be processed corresponds to traffic element information in the target area;

[0008] A simulation service subsystem communicates with the scenario construction subsystem, and is used to obtain the simulation scenario file determined by the scenario construction subsystem, and process the simulation scenario file to obtain a dynamic scene corresponding to the target area, so as to perform autonomous driving simulation on the subsystem under test in the dynamic scene; wherein the subsystem under test is integrated with an autonomous driving algorithm.

[0009] In a second aspect, an embodiment of the present invention further provides a simulation method using an automatic driving simulation system, wherein the driving simulation system includes a scene construction subsystem and a simulation service subsystem;

[0010] The simulation method includes:

[0011] The scene construction subsystem processes the received data to be processed corresponding to the target area to obtain a simulation scene file corresponding to the target area; wherein the target area is an area for unmanned vehicle road testing, and the data to be processed corresponds to traffic element information in the target area;

[0012] The simulation service subsystem obtains the simulation scenario file determined by the scenario construction subsystem, and processes the simulation scenario file to obtain a dynamic scene corresponding to the target area, so as to perform autonomous driving simulation on the subsystem under test based on the dynamic scene; wherein an autonomous driving algorithm is integrated in the subsystem under test.

[0013] In a third aspect, an embodiment of the present invention further provides a server, the server comprising:

[0014] one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement a simulation method of applying an autonomous driving simulation system as described in any of the embodiments of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a simulation method using an autonomous driving simulation system as described in any one of the embodiments of the present invention.

[0018] The technical solution of the embodiment of the present invention is to process the received data to be processed corresponding to the target area through the scene construction subsystem to obtain a simulation scene file corresponding to the target area. The simulation service subsystem obtains the simulation scene file determined by the scene construction subsystem, and processes the simulation scene file to obtain a dynamic scene corresponding to the target area, so as to simulate the automatic driving of the subsystem under test based on the dynamic scene. At this time, the subsystem under test is integrated with an automatic driving algorithm, which solves the technical problem that in the prior art, when testing the automatic driving algorithm of an unmanned vehicle, road testing is required, which has low safety and high cost. The automatic driving algorithm is tested in a virtual scene, and the virtual scene is constructed based on the road environment information actually collected, thereby improving the technical effect of the authenticity, safety and effectiveness of the simulation test. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a schematic diagram of the structure of an automatic driving simulation system provided by Embodiment 1 of the present invention;

[0021] Figure 2 Another structural schematic diagram of an automatic driving simulation system provided by the first embodiment of the present invention;

[0022] Figure 3 A schematic flow chart of a simulation method using an automatic driving simulation system provided in the second embodiment of the present invention;

[0023] Figure 4 A schematic diagram of a server structure provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Embodiment 1

[0026] Figure 1 This is a structural diagram of an automatic driving simulation system provided in Example 1 of the present invention. This embodiment can be applicable to various simulated vehicles performing simulated driving in various scenarios. The system can be used to execute the simulation method. The system can be implemented in the form of software and / or hardware. The hardware can be an electronic device, such as a mobile terminal or a PC.

[0027] See also Figure 1 The autonomous driving simulation system provided by the embodiment of the present invention includes: a scene construction subsystem 110 and a simulation service subsystem 120.

[0028] Among them, the scene construction subsystem 110 is used to process the received data to be processed corresponding to the target area to obtain a simulation scene file corresponding to the target area; wherein the target area is an area for unmanned vehicle road testing, and the data to be processed corresponds to the traffic element information in the target area; the simulation service subsystem 120 communicates with the scene construction subsystem, and is used to obtain the simulation scene file determined by the scene construction subsystem, and process the simulation scene file to obtain a dynamic scene corresponding to the target area, so as to perform autonomous driving simulation on the subsystem under test based on the dynamic scene; wherein the subsystem under test is integrated with an autonomous driving algorithm.

[0029] Among them, the scene construction subsystem is used to process the scene files under the corresponding scenes to obtain the corresponding simulation scenes. If the user wants to build a simulation scene corresponding to area A, area A can be used as the target area. The simulation scene file can be a scene file corresponding to the target area. The scene file may include element information of each traffic element in the environment. The data to be processed corresponds to the traffic element information in the target area, and the traffic element information includes information such as pedestrians, vehicles, and indicator lights. The target area is an area without road testing. The simulation service subsystem loads the simulation file to obtain the corresponding dynamic scene, that is, the dynamic scene can be subjected to corresponding simulation processing.

[0030] For example, see Figure 2 The autonomous driving simulation system includes a scene construction subsystem and a simulation service subsystem. The scene construction subsystem is used to process the received data to be processed and obtain a simulation scene file corresponding to the target area. The simulation service subsystem is used to process the simulation scene file and obtain a dynamic simulation scene. The subsystem under test is processed based on the dynamic simulation scene to obtain a corresponding test report.

[0031] The subsystem under test is integrated with an autonomous driving algorithm. The subsystem under test can receive traffic element status information from the simulation service subsystem and issue vehicle control instructions for the driving algorithm, that is, control the vehicle to simulate driving based on the autonomous driving algorithm in the simulation test scenario.

[0032] In this embodiment, before the scenario-based construction subsystem processes the received data to be processed, the data acquisition system is required to acquire the corresponding data to be processed.

[0033] Among them, the data acquisition subsystem can be set on the corresponding vehicle, which can be an unmanned vehicle or a manned vehicle. A full set of autonomous driving hardware and software can be installed on the vehicle to support perception data acquisition and autonomous driving functions. The hardware can be a camera device and a laser radar. The vehicle can travel in each area, and during the driving process, based on the camera device and the laser radar, it can collect traffic element information in the corresponding area, that is, collect traffic flow data in real time. After the collection is completed, the collected data can be stored locally, and the data stored locally is stored in a preset format, which can be .record.

[0034] Specifically, during the driving process of the vehicle, the actual traffic flow information can be collected based on the data collection subsystem set on the vehicle, and the actual traffic flow information can be stored locally as the data to be processed in a preset format. In other words, the data collection subsystem is used to collect real traffic element data in the real traffic environment, such as information on each vehicle, pedestrian, indicator light, and road conditions in the real traffic environment.

[0035] In this embodiment, the data acquisition subsystem includes a camera module and a data conversion module. The camera module is used to capture image information in the target area when the unmanned vehicle is controlled to drive or other manned vehicles are driving. The target area can be the area corresponding to the scene to be tested. For example, if the traffic element information in area A is to be collected, area A can be used as the target area. The target image information includes traffic element information, and the traffic element information includes at least one of roads, pedestrians, vehicles and indicator lights in the target area. The data conversion module communicates with the camera module and is used to convert the target image into structured data after the camera module collects the target image information, so as to obtain a lightweight data stream corresponding to the target area, that is, to obtain a lightweight data stream corresponding to the video stream. The lightweight data stream can be used as data to be processed.

[0036] It should be noted that after obtaining the data to be processed, the data to be processed can be stored locally. When storing locally, it can be stored in a preset format. The advantage of this is that it is easy for the simulation service subsystem to identify the corresponding data to be processed.

[0037] In this embodiment, the scenario construction subsystem includes: a data extraction module, which is used to extract traffic element information from the data to be processed; a fitting module, which is used to fit the traffic element information with the map information corresponding to the target area to obtain a running point trace matching the target area; and a scenario construction module, which is used to generate the simulation scenario file based on the running point trace.

[0038] Specifically, the scene construction subsystem is mainly used to construct the corresponding simulation scene. The data extraction module is used to obtain the data to be processed collected by the data acquisition subsystem, and extract the traffic element information from the data to be processed. At the same time, the map information of the corresponding area can also be extracted. Based on the fitting module, the traffic element information can be integrated into the map to obtain a dynamic simulation scene. In other words, the data collected by the data acquisition module is static data. In order to obtain a simulation scene, the static data can be integrated with the map of a certain area to obtain a dynamic scene file. The dynamic scene file can be used as a simulation scene file.

[0039] Exemplarily, the scenario construction subsystem extracts the perception data stored in the .record file, and annotates the status information of the traffic elements, and optionally, the location of the traffic elements in the map, the size of the traffic elements, and the type of the traffic elements in the map, that is, fits the map where the real traffic environment is located, and generates the movement traces of the traffic elements. A simulation scenario compatible with the simulation service subsystem can be constructed based on the running traces. At this time, the format of the simulation scenario file is .json format.

[0040] In this embodiment, the simulation service subsystem is used to parse and process the simulation scene file to convert the simulation scene file into a dynamic scene; wherein the dynamic scene matches the scene corresponding to the unmanned vehicle when it travels in the target area.

[0041] The dynamic scene can be understood as a scene of a simulated real environment. In other words, the dynamic scene matches the scene corresponding to when the unmanned vehicle is driving in the target area.

[0042] In this embodiment, the simulation service subsystem includes: a state update module, which is used to create an information sending sub-thread and send updated traffic element information to the subsystem under test according to pre-set configuration rules; a monitoring module, which is used to monitor the vehicle control instructions fed back by the subsystem under test based on the updated traffic element information; and a control module, which is used to receive the vehicle control instructions and control the simulation to drive in the dynamic scene based on the vehicle control instructions.

[0043] Among them, the status update module mainly creates sub-threads and continuously updates the status of traffic elements, such as the location information of each traffic element in the map. At the same time, the status update module is also used to periodically send the latest status information of traffic elements to the subsystem under test. After receiving the updated traffic element status information, the subsystem under test can send corresponding control instructions to the target vehicle based on the autonomous driving algorithm. At this time, the monitoring module can monitor the vehicle control instructions fed back by the subsystem under test.

[0044] It should be noted that the vehicle control instructions fed back by the subsystem under test are generated by the automatic driving algorithm based on the updated traffic element status information. For example, the updated traffic element status information is: the location information of the traffic participating vehicle A and the location information of the simulated vehicle. When the subsystem under test determines that the distance between the two location information is less than the preset distance threshold, the central control instruction sent may be that the target simulated vehicle stops driving, or the target simulated vehicle slows down. The control module may control the target simulated vehicle to perform the operation corresponding to the central control instruction based on the received central control instruction. At this time, the execution of the corresponding operation may be to control the movement of the target simulated vehicle in the simulation map, and the above work continues during the simulation process until the simulation ends or terminates abnormally.

[0045] The technical solution of the embodiment of the present invention is to process the received data to be processed corresponding to the target area through the scene construction subsystem to obtain a simulation scene file corresponding to the target area. The simulation service subsystem obtains the simulation scene file determined by the scene construction subsystem, and processes the simulation scene file to obtain a dynamic scene corresponding to the target area, so as to simulate the automatic driving of the subsystem under test based on the dynamic scene. At this time, the subsystem under test is integrated with an automatic driving algorithm, which solves the technical problem that in the prior art, when testing the automatic driving algorithm of an unmanned vehicle, road testing is required, which has low safety and high cost. The automatic driving algorithm is tested in a virtual scene, and the virtual scene is constructed based on the road environment information actually collected, thereby improving the technical effect of the authenticity, safety and effectiveness of the simulation test.

[0046] It should be noted that the simulation scene generated by the simulation subsystem of the present invention is based on real traffic flow, which can ensure the authenticity of the simulation scene to the greatest extent; further, the simulation system of the present invention makes full use of the massive perception data collected by the data acquisition vehicle, and uses this system to quickly convert it into a large number of complex scenes, thereby improving the efficiency of scene creation; thirdly, the simulation system of the present invention can convert the problem scenes occurring in the autonomous driving road test into simulation scenes, and continuously reproduce these problem scenes in the simulation environment, which is beneficial to the effectiveness verification of the algorithm optimization iteration; finally, the simulation system of the present invention implements a method for introducing human driving decisions into simulation scenes, and compares the autonomous driving algorithm with the human driving decision in the same scene, which is beneficial to exploring the optimization direction of the autonomous driving algorithm.

[0047] The autonomous driving simulation system provided in the embodiment of the present invention can execute the method of applying the autonomous driving simulation system provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0048] It is worth noting that the various units and modules included in the above system are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0049] Embodiment 2

[0050] Figure 3 This is a flow chart of a method for applying an autonomous driving simulation system provided in the second embodiment of the present invention. The method can be applied in situations where the autonomous driving algorithm needs to be verified. The method can be implemented through an autonomous driving simulation system. The system can be built in hardware or software, and the hardware can be a server. Among them, the technical terms that are the same or corresponding to the above embodiments are not repeated here.

[0051] like Figure 3 As shown, the method includes:

[0052] S310, the scene construction subsystem processes the received data to be processed corresponding to the target area to obtain a simulation scene file corresponding to the target area; wherein the target area is the area for unmanned vehicle road testing, and the data to be processed corresponds to the traffic element information in the target area.

[0053] S320, the simulation service subsystem obtains the simulation scene file determined by the scene construction subsystem, and processes the simulation scene file to obtain a dynamic scene corresponding to the target area, so as to simulate the autonomous driving of the subsystem under test in the dynamic scene; wherein the subsystem under test is integrated with an autonomous driving algorithm.

[0054] The implementation process of the embodiment of the present invention can be referred to the following detailed description:

[0055] Step 1: Build a data acquisition subsystem. The data acquisition subsystem hardware can be installed on an autonomous driving vehicle or a manned vehicle. The hardware installed at this time can be a camera device and a lidar. The data acquisition subsystem is mainly used to support perception data acquisition.

[0056] Step 2: At the same time, the data acquisition subsystem includes a perception data acquisition plug-in. The perception data acquisition plug-in has the function of obtaining the perception data output by the autonomous driving perception algorithm and storing it in a local file. In this example, the local file format is .record.

[0057] Step 3: Integrate the perception data acquisition plug-in in step 2 into the data acquisition subsystem.

[0058] Step 4: Use the data acquisition subsystem to collect perception data in a real traffic environment and generate a .record file. It can be understood that the above integrated data acquisition subsystem can be installed on the vehicle, and the traffic element information of the vehicle can be collected based on the data acquisition subsystem during the vehicle's driving process, and the traffic element information is stored locally to obtain a file in the .record format.

[0059] Step 5: Scenario construction subsystem. The scenario construction subsystem extracts the perception data stored in the .record file, that is, the actual traffic environment information, which includes traffic element information. The state information of the traffic elements (such as the size and location of the traffic elements) is fitted with the map of the real traffic environment (that is, the map of a certain area) to obtain the running points of the traffic elements, and then a simulation scene compatible with the simulation service subsystem is constructed based on the running points. In this example, the format of the simulation scene file is .json.

[0060] Step 6: Use the scenario construction subsystem to convert the .record file generated in step 4 into a simulation scenario file. In other words, the data to be processed is processed based on the scenario construction subsystem to obtain a simulation scenario file.

[0061] Step 7: Simulation service subsystem. The simulation service subsystem reads the traces of all traffic elements in the simulation scene file. At the same time, a subthread can be created, and the status of the traffic element (the position coordinates in the map) can be continuously updated based on the created subthread. Further, the latest status of the traffic element can be sent based on the created subthread cycle. That is, after the status information of the traffic element changes, the traffic element information after the status change can be sent to the subsystem under test based on the subthread cycle. Further, a subthread can be created, and the subthread is used to monitor the vehicle control instructions fed back by the subsystem under test. It can be understood that after the status information of the traffic element is sent to the subsystem under test, the subsystem under test can determine the control instructions sent to the target simulated vehicle according to the changed traffic element status information, and feed the control instructions back to the simulation service subsystem. The simulation service subsystem can control the simulated vehicle under test to move in the map according to the received vehicle control instructions, that is, the control instructions. The above work continues during the simulation process until the simulation ends or terminates abnormally.

[0062] Step 8: Load the simulation scenario file generated in step 6 into the simulation service subsystem and start the simulation.

[0063] Step 9: The simulation service subsystem generates a simulation test report after the simulation is completed. The simulation test includes evaluating the control effect of the algorithm integrated in the subsystem under test on the target simulated vehicle.

[0064] The technical solution of the embodiment of the present invention is to process the received data to be processed corresponding to the target area through the scene construction subsystem to obtain a simulation scene file corresponding to the target area. The simulation service subsystem obtains the simulation scene file determined by the scene construction subsystem, and processes the simulation scene file to obtain a dynamic scene corresponding to the target area, so as to simulate the automatic driving of the subsystem under test based on the dynamic scene. At this time, the subsystem under test is integrated with an automatic driving algorithm, which solves the technical problem that in the prior art, when testing the automatic driving algorithm of an unmanned vehicle, road testing is required, which has low safety and high cost. The automatic driving algorithm is tested in a virtual scene, and the virtual scene is constructed based on the road environment information actually collected, thereby improving the technical effect of the authenticity, safety and effectiveness of the simulation test.

[0065] Embodiment 3

[0066] Figure 4 A schematic diagram of the structure of a server provided in Embodiment 3 of the present invention. Figure 4 A block diagram of an exemplary server 40 suitable for use in implementing exemplary embodiments of the present invention is shown. Figure 4 The server 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0067] like Figure 4 As shown, the server 40 is in the form of a general-purpose computing device. The components of the server 40 may include, but are not limited to: one or more processors or processing units 401, a system memory 402, and a bus 403 connecting different system components (including the system memory 402 and the processing unit 401).

[0068] Bus 403 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0069] The server 40 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the server 40, including volatile and non-volatile media, removable and non-removable media.

[0070] System memory 402 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 404 and / or cache memory 405. Server 40 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 406 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 403 via one or more data medium interfaces. Memory 402 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0071] A program / utility 408 having a set (at least one) of program modules 407 may be stored, for example, in memory 402, such program modules 407 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 407 generally perform the functions and / or methods of the embodiments described herein.

[0072] The server 40 may also communicate with one or more external devices 409 (e.g., keyboards, pointing devices, displays 410, etc.), one or more devices that enable a user to interact with the server 40, and / or any device that enables the server 40 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 411. Furthermore, the server 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 412. As shown, the network adapter 412 communicates with other modules of the server 40 via the bus 403. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with server 40, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0073] The processing unit 401 executes various functional applications and data processing by running the programs stored in the system memory 402, such as implementing the simulation method of applying the automatic driving simulation system provided in the embodiment of the present invention.

[0074] Embodiment 4

[0075] Embodiment 4 of the present invention also provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a simulation method using an autonomous driving simulation system.

[0076] The method includes:

[0077] The scene construction subsystem processes the received data to be processed corresponding to the target area to obtain a simulation scene file corresponding to the target area; wherein the target area is an area for unmanned vehicle road testing, and the data to be processed corresponds to traffic element information in the target area;

[0078] The simulation service subsystem obtains the simulation scenario file determined by the scenario construction subsystem, and processes the simulation scenario file to obtain a dynamic scene corresponding to the target area, so as to perform autonomous driving simulation on the subsystem under test in the dynamic scene; wherein an autonomous driving algorithm is integrated in the subsystem under test.

[0079] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0080] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0081] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0082] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0083] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An automatic driving simulation system, characterized in that: include: Data acquisition subsystem, scenario construction subsystem and simulation service subsystem; The data acquisition subsystem is installed on the unmanned vehicle and includes a camera module and a data conversion module; The camera module is used to capture target image information of a target area when the unmanned vehicle is controlled to travel; wherein the target image information includes traffic element information, and the traffic element information includes at least one of information of roads, pedestrians, vehicles and indicator lights in the target area; The data conversion module is in communication with the camera module, and is used to convert the target image information into structured data, obtain a lightweight data stream corresponding to the target area, and use the lightweight data stream as data to be processed; Wherein, the target area is the area of ​​the unmanned vehicle road test, and the data to be processed is stored in a preset format; The scene construction subsystem includes: a data extraction module, a fitting module and a scene construction module; The data extraction module is used to process the received data to be processed corresponding to the target area, extract the traffic element information in the data to be processed, and extract the map information of the target area at the same time; wherein the data to be processed corresponds to the traffic element information in the target area; The fitting module is used to fit the traffic element information with the map information corresponding to the target area to obtain a running point trace matching the target area; The scenario construction module is used to generate a simulation scenario file corresponding to the target area based on the running point trace; a simulation service subsystem, communicating with the scenario construction subsystem, for obtaining the simulation scenario file determined by the scenario construction subsystem, and processing the simulation scenario file to obtain a dynamic scene corresponding to the target area, so as to perform automatic driving simulation on the subsystem under test in the dynamic scene; wherein the subsystem under test is integrated with an automatic driving algorithm, and after receiving the updated traffic element status information, sends corresponding control instructions to the target vehicle based on the automatic driving algorithm; Wherein, the simulation service subsystem further includes: a status update module, a monitoring module, a control module and a test result generation module; The state updating module is used to create an information sending sub-thread, continuously update the state of the traffic element information, and send the updated traffic element information to the subsystem under test according to a preset configuration rule; The monitoring module is used to monitor the vehicle control instructions fed back by the subsystem under test based on the updated traffic element information; The control module is used to receive the vehicle control command and control the simulation to drive in the dynamic scene based on the vehicle control command; The test result generation module is used to compare the corresponding control instructions sent to the target vehicle based on the automatic driving algorithm monitored by the monitoring module with the decisions made by human drivers in the same scenario, and generate a simulation test report.

2. The system according to claim 1, characterized in that The simulation service subsystem is used to parse and process the simulation scene file to convert the simulation scene file into a dynamic scene; wherein the dynamic scene matches the scene corresponding to the unmanned vehicle when driving in the target area.

3. The system according to claim 1, characterized in that The traffic element information also includes: pedestrian position information and position information of simulated vehicles in the simulation service subsystem.

4. A simulation method using an automatic driving simulation system, characterized in that: include: Data acquisition subsystem, scenario construction subsystem, simulation service subsystem; The simulation method includes: The data acquisition subsystem is arranged on the unmanned vehicle, and when the unmanned vehicle is controlled to travel, it captures target image information of the target area; converts the target image information into structured data, obtains a lightweight data stream corresponding to the target area, and uses the lightweight data stream as data to be processed; wherein the target image information includes traffic element information, and the traffic element information includes at least one of road, pedestrian, vehicle and indicator light information in the target area; the target area is the area of ​​the unmanned vehicle road test; the data to be processed is stored in a preset format; The scenario construction subsystem processes the received data to be processed corresponding to the target area, extracts the traffic element information in the data to be processed, and simultaneously extracts the map information of the target area, fits the traffic element information with the map information corresponding to the target area, obtains the running point traces matching the target area, and generates a simulation scenario file corresponding to the target area based on the running point traces; wherein the data to be processed corresponds to the traffic element information in the target area; The simulation service subsystem obtains the simulation scenario file determined by the scenario construction subsystem, and processes the simulation scenario file to obtain a dynamic scenario corresponding to the target area, so as to perform automatic driving simulation on the subsystem under test in the dynamic scenario; wherein the subsystem under test is integrated with an automatic driving algorithm, and after receiving the updated traffic element status information, sends corresponding control instructions to the target vehicle based on the automatic driving algorithm; The simulation method further comprises: The simulation service subsystem creates an information sending subthread, continuously updates the status of the traffic element information, and sends the updated traffic element information to the subsystem under test according to a preset configuration rule; monitors the vehicle control instructions fed back by the subsystem under test based on the updated traffic element information; receives the vehicle control instructions, and controls the simulation to drive in the dynamic scene based on the vehicle control instructions; compares the corresponding control instructions sent to the target vehicle based on the automatic driving algorithm monitored by the monitoring module with the decisions made by human drivers in the same scene, and generates a simulation test report.

5. A server, characterized in that: The server comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the simulation method of applying the automatic driving simulation system as described in any one of claim 4.

6. A storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute the simulation method using an autonomous driving simulation system as claimed in any one of claims 4.

Images