Automatic driving simulation method, device, equipment, readable storage medium and product

Abstract

The present disclosure provides an autonomous driving simulation method, device, equipment, readable storage medium and product, which relate to the field of artificial intelligence, and in particular to autonomous driving. The specific implementation scheme is: obtaining a simulation regression test request; according to the simulation regression test request, obtaining the road data to be simulated corresponding to the target autonomous driving scene information in a preset road database, the road database includes multiple groups of test data, the test data includes annotated road data and autonomous driving scene information corresponding to the annotated road data; performing a simulation regression test operation according to the road data to be simulated to obtain the test results. Therefore, when there are new road test problems and new road data are generated, only the data in the road database needs to be managed and updated, and there is no need to manage and operate the data in the road database and the simulation set separately, which simplifies the data management link, saves human resources, and improves the efficiency of simulation testing.

Description

Technical Field

[0001] The present disclosure relates to autonomous driving in artificial intelligence, and in particular to an autonomous driving simulation method, device, equipment, readable storage medium and product. Background Art

[0002] Autonomous driving simulation is an important method of using computers to conduct closed-loop verification of autonomous driving algorithms in the later stages. By performing regression verification on road test problems in the simulation system, it is possible to directly verify whether the road test problems have been effectively fixed, thereby accelerating the iteration speed of autonomous driving algorithms and achieving faster deployment and application.

[0003] Since the simulation scenarios and road test problems required in the simulation process are different, the existing simulation processing methods generally require technical personnel to analyze and process the road data after obtaining the road data and the corresponding road test problems, and establish a simulation database for simulation.

[0004] However, when using the above method for regression verification, on the one hand, the discovery of problems and the organization of problems to the simulation database are carried out in stages, and each stage requires a large number of personnel to maintain. On the other hand, new problems in the road test iteration process require the collection to be updated, and the simulation data in the simulation database needs to be updated synchronously, which is a cumbersome operation. Summary of the invention

[0005] The present disclosure provides an autonomous driving simulation method, apparatus, device, readable storage medium and product for improving regression verification efficiency and reducing the difficulty and cost of simulation data management.

[0006] According to a first aspect of the present disclosure, there is provided an autonomous driving simulation method, comprising:

[0007] Obtaining a simulation regression test request, wherein the simulation regression test request includes target autonomous driving scenario information to be tested;

[0008] According to the simulation regression test request, obtaining the to-be-simulated road data corresponding to the target autonomous driving scene information in a preset road database, wherein the road database includes a plurality of sets of to-be-tested data, and the to-be-tested data includes annotated road data and autonomous driving scene information corresponding to the annotated road data;

[0009] A simulation regression test operation is performed according to the road data to be simulated to obtain a test result.

[0010] According to a second aspect of the present disclosure, there is provided an automatic driving simulation device, comprising:

[0011] An acquisition module, used to acquire a simulation regression test request, wherein the simulation regression test request includes target autonomous driving scenario information to be tested;

[0012] a processing module, configured to obtain, in a preset road database, road data to be simulated corresponding to the target autonomous driving scenario information according to the simulation regression test request, wherein the road database includes a plurality of groups of test data, and the test data includes annotated road data and autonomous driving scenario information corresponding to the annotated road data;

[0013] The test module is used to perform a simulation regression test operation according to the road data to be simulated to obtain a test result.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the first aspect.

[0019] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising: a computer program, wherein the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect.

[0020] The technology disclosed in the present invention solves the technical problem that simulation data management for autonomous driving simulation is difficult, resulting in low efficiency of regression verification operations.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0023] Figure 1 A schematic diagram of the system architecture on which the present disclosure is based;

[0024] Figure 2 A schematic diagram of the process of the autonomous driving simulation method provided in the first embodiment of the present disclosure;

[0025] Figure 3 A schematic diagram of the process of the automatic driving simulation method provided in the second embodiment of the present disclosure;

[0026] Figure 4 A schematic diagram of data acquisition provided in an embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of the process of the autonomous driving simulation method provided in the third embodiment of the present disclosure;

[0028] Figure 6 A schematic diagram of an application scenario provided for an embodiment of the present disclosure;

[0029] Figure 7 A schematic diagram of the structure of an autonomous driving simulation device provided in Embodiment 4 of the present disclosure;

[0030] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present disclosure. DETAILED DESCRIPTION

[0031] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] The present disclosure provides an autonomous driving simulation method, device, equipment, readable storage medium and product, which are applied to autonomous driving in artificial intelligence to simplify the repeated management links from road testing to simulation, save management costs, and improve regression verification efficiency.

[0033] It should be noted that the test method, apparatus, terminal device and readable storage medium provided by the present disclosure can be used in various scenarios of autonomous driving regression verification.

[0034] Autonomous driving simulation is an important method of using computers to verify the closed-loop problems of autonomous driving algorithms in the later stage. By performing regression verification on road test problems in the simulation system, it is possible to directly verify whether the road test problems have been effectively fixed, which can speed up the iteration of autonomous driving algorithms and achieve faster deployment and application. In the process of autonomous driving simulation, it is generally necessary to obtain data corresponding to different autonomous driving scenarios. In the prior art, after obtaining the road test data, it is necessary to further classify the simulation scenarios according to the road test data, classify them into specific simulation sets, and regularly update and maintain the simulation sets. For example, new problems in the iteration process of autonomous driving road testing require updating of the set, and with the iteration of versions, old scenes also need to be removed from the set, which increases the management steps and the possibility of errors.

[0035] In the process of solving the above technical problems, the inventors found through research that in order to simplify the repeated management links from road testing to simulation and save management costs, it is no longer necessary to generate simulation sets based on road test data. Simulation scenes can be directly annotated in the road test data, so that in the subsequent simulation process, the road test data corresponding to the simulation scene can be directly obtained. There is no need to further manage and maintain the simulation data.

[0036] Figure 1 This is a schematic diagram of the system architecture based on which the present disclosure is based. Figure 1 As shown, the system architecture based on the present disclosure includes at least: a terminal device 11, a server 12, a data collection vehicle 13 and a road database 14. Among them, the server 12 is provided with an automatic driving simulation device, which can be written in languages ​​such as C / C++, Java, Shell or Python; the terminal device 1 can be, for example, a desktop computer, a tablet computer, etc. The data collection vehicle 13 is provided with a data collection device, which includes but is not limited to a camera, a radar, etc. A large amount of road data is stored in the road database 14.

[0037] Figure 2 This is a flow chart of the automatic driving simulation method provided in the first embodiment of the present disclosure, such as Figure 2 As shown, the method includes:

[0038] Step 201: Obtain a simulation regression test request, wherein the simulation regression test request includes target autonomous driving scenario information to be tested.

[0039] The execution subject of this embodiment is an automatic driving simulation device, which can be coupled to a server. The server can be respectively connected to the terminal device and the road database for communication, so as to be able to exchange information with the terminal device and the road database.

[0040] In this embodiment, in order to speed up the iteration speed of the autonomous driving algorithm and enable the autonomous driving algorithm to be deployed and applied more quickly, simulation regression testing operations can be performed for different autonomous driving scenarios. The autonomous driving algorithm is adjusted and optimized according to the test results. In practical applications, a simulation regression test request can be initiated through a terminal device according to actual needs, wherein the simulation regression test request may include the target autonomous driving scene information to be tested. The target autonomous driving scene information may include one or more of road structure information, vehicle behavior information, and obstacle behavior information. For example, the target autonomous driving scene information may specifically be that the vehicle is traveling at a speed of 60 miles per hour on a one-way street, and there is an obstacle 30 meters in front of the vehicle. Accordingly, the autonomous driving simulation device can obtain a simulation regression test request.

[0041] Step 202: According to the simulation regression test request, obtain the road data to be simulated corresponding to the target autonomous driving scene information in a preset road database, wherein the road database includes multiple groups of test data, and the test data includes labeled road data and autonomous driving scene information corresponding to the labeled road data.

[0042] In this embodiment, in order to simplify the repeated management links from road testing to simulation and save management costs, it is no longer necessary to generate a simulation set based on the road test data, but to directly annotate the road data and build a road database. The road database includes multiple sets of data to be tested, including annotated road data and autonomous driving scenario information corresponding to the annotated road data.

[0043] Accordingly, since a large amount of road data with labeled autonomous driving scene information is stored in the road database, after obtaining the simulation regression test request, the road data to be simulated corresponding to the target autonomous driving scene information can be obtained in the road database according to the simulation regression test request.

[0044] By annotating the road data in the road database with information about autonomous driving scenarios, there is no need to establish a separate simulation set. When new road test problems or new road data are generated, only the data in the road database needs to be managed and updated, which greatly simplifies the data management process.

[0045] Step 203: Perform a simulation regression test operation according to the road data to be simulated to obtain a test result.

[0046] In this embodiment, a visual simulation engine may be pre-built. After obtaining the road data to be simulated corresponding to the target autonomous driving scene information, the road data to be simulated may be used to perform a simulation regression test operation in the visual simulation engine for the target autonomous driving scene information to obtain a test result.

[0047] The automatic driving simulation method provided in this embodiment constructs a road database by annotating the road data with the automatic driving scene information, so that in the subsequent automatic driving simulation process, the annotated road data can be directly obtained from the road database for simulation regression test operations. In addition, when there are new road test problems and new road data are generated, only the data in the road database needs to be managed and updated, and there is no need to manage and operate the data in the road database and the simulation set separately, which simplifies the data management process, saves human resources, and improves the efficiency of simulation testing.

[0048] Figure 3 This is a flow chart of the automatic driving simulation method provided in the second embodiment of the present disclosure. Based on the first embodiment, before step 202, as shown in FIG. Figure 3 As shown, it also includes:

[0049] Step 301: Obtain the road data to be labeled collected by a data collection device installed on a vehicle.

[0050] Step 302: Send the road data to be labeled to a terminal device of a technician, so that the technician can label the road test problem information and the autonomous driving scenario information corresponding to the road data to be labeled.

[0051] Step 303: Obtain the annotated road data sent by the technician's terminal device.

[0052] In this embodiment, in order to realize the collection operation of road data, the road data can be collected by a data collection vehicle. The data collection vehicle is provided with data collection equipment, wherein the data collection equipment includes but is not limited to devices such as cameras, radars, and vehicle-mounted sensors.

[0053] Optionally, the autonomous driving simulation device can also be connected to a data collection vehicle in communication, so as to obtain the road data to be labeled collected by the data collection device installed on the vehicle. The autonomous driving simulation device can obtain the road data to be labeled according to a preset time period, or according to the user's trigger operation, and the present disclosure does not limit this.

[0054] After obtaining the road data to be annotated, the road data to be annotated can be sent to the terminal device of the technician. After obtaining the road data to be annotated, the technician can annotate the road test problem information and the autonomous driving scene information corresponding to the road data to be annotated, and after completing the annotating, the annotated road data is fed back to the autonomous driving simulation device. Accordingly, the autonomous driving simulation device can obtain the annotated road data.

[0055] By sending the road data to be labeled to the technician's terminal device for labeling, the accuracy of the road test problem information and autonomous driving scenario information corresponding to the labeled road data can be improved, and subsequent simulation tests based on the road data can obtain better test results.

[0056] Further, based on any of the above embodiments, the data to be tested further includes roadside problem information corresponding to the annotated road data, and the multiple groups of data to be tested are classified according to the roadside problem information;

[0057] Step 202 includes:

[0058] For the test data corresponding to various types of roadside problem information, road data corresponding to the target autonomous driving scenario information is obtained.

[0059] The road data corresponding to all target autonomous driving scene information under various types of roadside problem information are determined as the road data to be simulated.

[0060] In this embodiment, each group of data to be tested in the road database also includes roadside problem information corresponding to the annotated road data. In the road database, the data to be tested is classified according to the roadside problem information. Based on the above data structure, after obtaining the simulation regression test request, for the data to be tested corresponding to each type of roadside problem information, the road data corresponding to the target autonomous driving scene information in the simulation regression test request can be obtained, and the target autonomous driving scene information corresponding to the roadside problem information can be obtained. The road data corresponding to all the target autonomous driving scene information under each type of roadside problem information is determined as the road data to be simulated.

[0061] The automatic driving simulation method provided in this embodiment can obtain the road data corresponding to all target automatic driving scene information under the test data corresponding to various types of roadside problem information as the road data to be simulated, so as to realize the acquisition operation of the road data corresponding to the automatic driving scene information in the road database. There is no need to generate a simulation set according to the road test data, which simplifies the data management link and improves the efficiency of simulation testing.

[0062] Further, based on any of the above embodiments, after step 203, the method further includes:

[0063] The road data to be simulated is associated with the automatic driving scenario information and stored in a preset data server.

[0064] In this embodiment, after obtaining the road data to be simulated corresponding to the target autonomous driving scene information, an association relationship between the road data to be simulated and the autonomous driving scene information can be established, and the road data to be simulated and the autonomous driving scene information are associated and stored in a preset data server. Therefore, the acquisition operation of the road data to be simulated can be performed directly based on the association relationship, further simplifying the data acquisition process.

[0065] Further, based on any of the above embodiments, after step 201, the method further includes:

[0066] Detect whether the data server includes the autonomous driving scenario information corresponding to the simulation regression test request.

[0067] If included, the road data to be simulated corresponding to the autonomous driving scenario information is obtained.

[0068] If not included, then according to the simulation regression test request, the road data to be simulated corresponding to the autonomous driving scenario information is obtained from a preset road database.

[0069] In this embodiment, by establishing an association relationship between the road data to be simulated and the automatic driving scene information, after obtaining the simulation regression test request, in order to improve the efficiency of data acquisition, it is first possible to detect whether the data server includes the automatic driving scene information corresponding to the simulation regression test request. If it is included, the road data to be simulated corresponding to the automatic driving scene information can be directly obtained according to the pre-established association relationship. Otherwise, the road data to be simulated corresponding to the automatic driving scene information can be obtained in the preset road database according to the simulation regression test request.

[0070] Figure 4 A schematic diagram of data acquisition provided by an embodiment of the present disclosure, such as Figure 4 As shown, the automatic driving simulation device 41 can obtain the simulation regression test request sent by the terminal device 42. After obtaining the simulation regression test request, it can be detected whether the automatic driving scene information corresponding to the simulation regression test request already exists in the data server 43. If so, the automatic driving scene information corresponding to the simulation regression test request can be directly obtained from the data server 43. Otherwise, the road data to be simulated corresponding to the automatic driving scene information can be obtained from the road database 44.

[0071] The autonomous driving simulation method provided in this embodiment establishes an association relationship between the road data to be simulated and the autonomous driving scene information after acquiring the road data to be simulated, so that the road data to be simulated can be acquired directly based on the association relationship. There is no need to acquire data under the test data corresponding to various types of roadside problem information according to the simulation regression test request, thereby improving the efficiency of data acquisition and further improving the efficiency of autonomous driving simulation.

[0072] Figure 5 This is a flow chart of an autonomous driving simulation method provided in Embodiment 3 of the present disclosure. Based on any of the above embodiments, the road data to be simulated corresponding to the autonomous driving scene information includes road structure information, vehicle behavior information, and obstacle behavior information; Figure 5 As shown, step 203 includes:

[0073] Step 501: input the road data to be simulated into a preset visual simulation engine, so that the simulated vehicle in the visual simulation engine travels according to the road data to be simulated.

[0074] Step 502: Obtain decision information generated by the simulated vehicle, and determine the decision information as the test result.

[0075] In this embodiment, in order to realize the automatic driving simulation operation, a visual simulation engine can be pre-built. The road data to be simulated corresponding to the automatic driving scene information includes road structure information, vehicle behavior information and obstacle behavior information. In the visual simulation engine, the target automatic driving scene information can be reconstructed according to the road structure information, vehicle behavior information and obstacle behavior information corresponding to the target automatic driving scene information, and the test operation can be performed under the target automatic driving scene information.

[0076] Specifically, after obtaining the road data to be simulated, the data to be simulated can be input into the visual simulation engine, so that the simulated vehicle in the visual simulation engine travels according to the road data to be simulated. During the simulation process, when the simulated vehicle travels according to the road data to be simulated, decision information can be generated. For example, if the data to be simulated is a roadblock in front of the vehicle, the simulated vehicle can generate decision information for the roadblock, and the decision information can be deceleration, parking, route switching, etc.

[0077] Figure 6 A schematic diagram of an application scenario provided by an embodiment of the present disclosure, such as Figure 6 As shown, the road data to be simulated corresponding to the target autonomous driving scene information may specifically be that during the driving of the simulated vehicle 61, there is an obstacle roadblock 62 at XXX meters in front, and at XX seconds, an obstacle vehicle 63 enters from the right rear of the simulated vehicle 62.

[0078] By performing simulation tests based on the road data to be simulated in the visualization engine, it is possible to intuitively determine whether the decision information made by the simulated vehicle is safe and reasonable, and whether the road test problems have been effectively fixed. This can speed up the iteration of the autonomous driving algorithm and achieve faster deployment and application.

[0079] Further, based on any of the above embodiments, after step 502, the method further includes:

[0080] Determine a simulation result after the simulated vehicle travels according to the decision information.

[0081] If the simulation result is that the simulated vehicle has an accident, the road data to be simulated and the decision information are sent to a terminal device of a technician so that the technician can correct the decision information.

[0082] In this embodiment, after obtaining the decision information made by the simulated vehicle, the simulation result after the simulated vehicle travels according to the decision information can be determined. It is detected whether the simulation result is an accident of the simulated vehicle. If so, the decision information is sent to the terminal device of the technician so that the technician can correct the decision information.

[0083] Continuing with the above example, if the simulated vehicle chooses to slow down in response to the roadblock ahead, and the simulation result is a collision with the obstacle, it indicates that the current decision information is incorrect. The decision information can be sent to the technician's terminal device so that the technician can correct the decision information. Optionally, the decision information can be corrected to a parking operation.

[0084] The autonomous driving simulation method provided in this embodiment can improve the driving safety of the autonomous driving vehicle by sending the decision information made by the simulated vehicle to the terminal device of the technician so that the technician can correct the decision information when it is detected that the decision information made by the simulated vehicle is not safe.

[0085] Figure 7 This is a schematic diagram of the structure of the autonomous driving simulation device provided in the fourth embodiment of the present disclosure, such as Figure 7As shown, the autonomous driving simulation device includes: an acquisition module 71, a processing module 72 and a testing module 73. The acquisition module 71 is used to obtain a simulation regression test request, wherein the simulation regression test request includes the target autonomous driving scene information to be tested. The processing module 72 is used to obtain the road data to be simulated corresponding to the target autonomous driving scene information in a preset road database according to the simulation regression test request, wherein the road database includes multiple groups of data to be tested, and the data to be tested includes annotated road data and autonomous driving scene information corresponding to the annotated road data. The testing module 73 is used to perform a simulation regression test operation according to the road data to be simulated to obtain a test result.

[0086] Furthermore, based on the fourth embodiment, the device further includes: a road data acquisition module, a sending module and a communication module. The road data acquisition module is used to acquire the road data to be labeled collected by the data acquisition device installed on the vehicle. The sending module is used to send the road data to be labeled to the terminal device of the technician, so that the technician can label the road test problem information and the automatic driving scene information corresponding to the road data to be labeled. The communication module is used to acquire the labeled road data sent by the terminal device of the technician.

[0087] Further, based on any of the above embodiments, the data to be tested also includes roadside problem information corresponding to the annotated road data, and the multiple groups of data to be tested are classified according to the roadside problem information. The processing module includes: an acquisition unit and a determination unit, wherein the acquisition unit is used to acquire the road data corresponding to the target autonomous driving scene information for the data to be tested corresponding to each type of roadside problem information. The determination unit is used to determine the road data corresponding to all target autonomous driving scene information under each type of roadside problem information as the road data to be simulated.

[0088] Furthermore, based on any of the above embodiments, the root device also includes: a storage module, used to associate the road data to be simulated with the automatic driving scene information and store it in a preset data server.

[0089] Further, based on any of the above embodiments, the device further includes: a detection module, a first matching module and a second matching module. The detection module is used to detect whether the data server includes the autonomous driving scene information corresponding to the simulation regression test request. The first matching module is used to obtain the road data to be simulated corresponding to the autonomous driving scene information if it is included. The second matching module is used to obtain the road data to be simulated corresponding to the autonomous driving scene information in a preset road database according to the simulation regression test request if it is not included.

[0090] Further, on the basis of any of the above embodiments, the road data to be simulated corresponding to the autonomous driving scene information includes road structure information, vehicle behavior information and obstacle behavior information; the test module includes: a simulation unit and a decision information acquisition unit, wherein the simulation unit is used to input the road data to be simulated into a preset visual simulation engine so that the simulated vehicle in the visual simulation engine travels according to the road data to be simulated. The decision information acquisition unit is used to obtain the decision information generated by the simulated vehicle and determine the decision information as the test result.

[0091] Furthermore, based on any of the above embodiments, the device further includes: a simulation result determination module and a correction module. The simulation result determination module is used to determine the simulation result after the simulated vehicle travels according to the decision information. The correction module is used to send the road data to be simulated and the decision information to a terminal device of a technician if the simulation result is that the simulated vehicle has an accident, so that the technician can correct the decision information.

[0092] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0093] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0094] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0095] Figure 8 A schematic diagram of the structure of an electronic device provided for Embodiment 5 of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0096] like Figure 8As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0097] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0098] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the autonomous driving simulation method. For example, in some embodiments, the autonomous driving simulation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the autonomous driving simulation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the autonomous driving simulation method in any other appropriate manner (e.g., by means of firmware).

[0099] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0101] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0104] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0105] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0106] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An automatic driving simulation method, comprising: Obtaining a simulation regression test request, wherein the simulation regression test request includes target autonomous driving scenario information to be tested; According to the simulation regression test request, obtaining the to-be-simulated road data corresponding to the target autonomous driving scene information in a preset road database, wherein the road database includes a plurality of groups of to-be-tested data, and the to-be-tested data includes annotated road data and autonomous driving scene information corresponding to the annotated road data; Perform a simulation regression test operation according to the road data to be simulated to obtain a test result; Wherein, the data to be tested also includes roadside problem information corresponding to the annotated road data, and the multiple groups of data to be tested are classified according to the roadside problem information; The step of acquiring, in a preset road database, road data to be simulated corresponding to the target autonomous driving scenario information according to the simulation regression test request includes: For the data to be tested corresponding to various types of roadside problem information, road data corresponding to the target autonomous driving scene information is obtained; and the road data corresponding to all target autonomous driving scene information under various types of roadside problem information are determined as the road data to be simulated.

2. The method according to claim 1, before obtaining the to-be-simulated road data corresponding to the target autonomous driving scenario information in a preset road database according to the simulation regression test request, further comprising: Acquire the road data to be annotated collected by a data collection device installed on the vehicle; Sending the road data to be annotated to a terminal device of a technician, so that the technician can annotate the road test problem information and the autonomous driving scene information corresponding to the road data to be annotated; Obtain the annotated road data sent by the technician's terminal device.

3. The method according to claim 1 or 2, wherein after performing a simulation regression test operation according to the road data to be simulated and obtaining a test result, the method further comprises: The road data to be simulated is associated with the automatic driving scenario information and stored in a preset data server.

4. The method according to claim 3, wherein: After obtaining the simulation regression test request, the method further includes: Detecting whether the data server includes the autonomous driving scenario information corresponding to the simulation regression test request; If included, obtaining the road data to be simulated corresponding to the autonomous driving scenario information; If not included, then according to the simulation regression test request, the road data to be simulated corresponding to the autonomous driving scenario information is obtained from a preset road database.

5. The method according to claim 1 or 2, wherein: The road data to be simulated corresponding to the autonomous driving scenario information includes road structure information, vehicle behavior information, and obstacle behavior information; The performing of a simulation regression test operation according to the road data to be simulated to obtain a test result includes: Inputting the road data to be simulated into a preset visual simulation engine, so that the simulated vehicle in the visual simulation engine travels according to the road data to be simulated; Decision information generated by the simulated vehicle is obtained, and the decision information is determined as the test result.

6. The method according to claim 5, wherein: After acquiring the decision information generated by the simulated vehicle, the method further includes: Determining a simulation result after the simulated vehicle travels according to the decision information; If the simulation result is that the simulated vehicle has an accident, the road data to be simulated and the decision information are sent to a terminal device of a technician so that the technician can correct the decision information.

7. An automatic driving simulation device, comprising: An acquisition module, used to acquire a simulation regression test request, wherein the simulation regression test request includes target autonomous driving scenario information to be tested; a processing module, configured to obtain, in a preset road database, road data to be simulated corresponding to the target autonomous driving scenario information according to the simulation regression test request, wherein the road database includes a plurality of groups of test data, and the test data includes annotated road data and autonomous driving scenario information corresponding to the annotated road data; A testing module, used for performing a simulation regression test operation according to the road data to be simulated to obtain a test result; Wherein, the data to be tested also includes roadside problem information corresponding to the annotated road data, and the multiple groups of data to be tested are classified according to the roadside problem information; The processing module comprises: An acquisition unit, configured to acquire road data corresponding to the target autonomous driving scenario information for the data to be tested corresponding to various types of roadside problem information; The determination unit is used to determine the road data corresponding to all target automatic driving scene information under various types of roadside problem information as the road data to be simulated.

8. The device according to claim 7, further comprising: A road data acquisition module is used to acquire the road data to be annotated collected by a data acquisition device installed on the vehicle; A sending module, used for sending the road data to be annotated to a terminal device of a technician, so that the technician can perform an annotation operation on the road test problem information and the automatic driving scene information corresponding to the road data to be annotated; The communication module is used to obtain the annotated road data sent by the technician's terminal device.

9. The device according to claim 7 or 8, further comprising: A storage module is used to associate the road data to be simulated with the automatic driving scene information and store them in a preset data server.

10. The device according to claim 9, wherein: The device also includes: A detection module, used to detect whether the data server includes the autonomous driving scenario information corresponding to the simulation regression test request; A first matching module, for obtaining the to-be-simulated road data corresponding to the autonomous driving scene information, if included; The second matching module is used to obtain the road data to be simulated corresponding to the automatic driving scenario information in a preset road database according to the simulation regression test request if it is not included.

11. The device according to claim 7 or 8, wherein: The road data to be simulated corresponding to the autonomous driving scenario information includes road structure information, vehicle behavior information, and obstacle behavior information; The test module includes: A simulation unit, used for inputting the road data to be simulated into a preset visual simulation engine, so that the simulated vehicle in the visual simulation engine travels according to the road data to be simulated; The decision information acquisition unit is used to acquire the decision information generated by the simulated vehicle and determine the decision information as the test result.

12. The device according to claim 11, wherein The device also includes: A simulation result determination module, used to determine the simulation result after the simulated vehicle travels according to the decision information; The correction module is used to send the road data to be simulated and the decision information to the terminal device of the technician if the simulation result is that the simulated vehicle has an accident, so that the technician can correct the decision information.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

15. A computer program product, comprising a computer program, which implements the steps of the method according to any one of claims 1 to 6 when executed by a processor.

Images