Automatic driving simulation method, automatic driving simulation device and equipment

Abstract

The invention discloses an automatic driving simulation method, an automatic driving simulation device and equipment. The method comprises the steps of obtaining a map file, and generating a test map based on the map file; acquiring a navigation simulation configuration file, and generating a navigation path in the test map based on the navigation simulation configuration file; acquiring a scene simulation file, and generating a path simulation scene matched with the navigation path based on the scene simulation file; and based on the path simulation scene and the to-be-tested automatic driving algorithm, simulating that the vehicle runs along the navigation path. According to the automatic driving simulation method provided by the embodiment of the invention, the navigation path can be simulated, the simulation test of automatic driving along the navigation path is realized, and the test cost is reduced.

Description

Technical Field

[0001] The present application belongs to the field of simulation technology, and in particular relates to an autonomous driving simulation method, an autonomous driving simulation device and equipment. Background Art

[0002] In related technologies, it is necessary to test the situation where the autonomous driving vehicle drives to the target scene. In the field test scenario, the map box and the domain controller are started to plan the navigation path, locate the vehicle, and control the vehicle to drive along the navigation path. Only after a complete actual test process is carried out in the autonomous driving mode can a set of test data be obtained. The above test process needs to be repeated in both the R&D stage and the testing stage to correct the algorithm based on the multiple sets of test data obtained, which brings huge consumption of manpower and material resources and increases the development cost of autonomous driving vehicles. Summary of the invention

[0003] The embodiments of the present application provide an autonomous driving simulation method, an autonomous driving simulation device and equipment, which can solve the technical problem of high testing and development costs of autonomous driving vehicles in related technologies.

[0004] In a first aspect, an embodiment of the present application provides an autonomous driving simulation method, the method comprising:

[0005] Obtain a map file, and generate a test map based on the map file;

[0006] Obtaining a navigation simulation configuration file, and generating a navigation path in a test map based on the navigation simulation configuration file;

[0007] Obtaining a scene simulation file, and generating a path simulation scene adapted to the navigation path based on the scene simulation file;

[0008] Based on the path simulation scenario and the autonomous driving algorithm to be tested, the simulated vehicle travels along the navigation path.

[0009] In some embodiments, obtaining a map file and generating a test map based on the map file includes:

[0010] Get the target map identification code;

[0011] Selecting a target map file that matches the target map identification code from among multiple map files, wherein the multiple map files are files respectively constructed by parsing map data stored using different standard protocols, wherein the map files store road information of multiple map roads, slice information of a road slice corresponding to each map road, and lane information of a slice lane corresponding to each road slice;

[0012] The test map is obtained by simulating the target map file.

[0013] In some embodiments, obtaining a map file and before generating a test map based on the map file includes:

[0014] Acquire map data, parse the map data, and obtain map roads in the map data;

[0015] Slicing the map roads according to the road features of each map road to obtain at least one road slice corresponding to each map road information;

[0016] Performing lane division processing on the road slices corresponding to each map road to obtain at least one slice lane corresponding to each road slice;

[0017] Based on the map data, determining road information corresponding to each map road, slice information corresponding to each road slice, and lane information corresponding to each slice lane;

[0018] The road information corresponding to each map road, the slice information corresponding to each road slice, and the lane information corresponding to each slice lane are stored in a hierarchical manner to obtain a map file stored in a hierarchical database.

[0019] In some embodiments, the road information corresponding to each map road, the slice information corresponding to each road slice, and the lane information corresponding to each slice lane are stored hierarchically to obtain a map file stored in a hierarchical database, including:

[0020] Create a first-level database table, and store the road information corresponding to each map road in the first-level database table;

[0021] Creating a second-level database table corresponding to each map road, and storing the slice information corresponding to the road slice corresponding to each map road in the matching second-level database table;

[0022] Create a third-level database table corresponding to each road slice, and store lane information of the slice lane corresponding to each road slice in the matching third-level database table;

[0023] The first-level database table, the second-level database table and the third-level database table are stored hierarchically to obtain a map file stored in a hierarchical database.

[0024] In some embodiments, obtaining a navigation simulation configuration file, and generating a navigation path in a test map based on the navigation simulation configuration file includes at least one of the following:

[0025] In the case where the navigation simulation configuration file includes a starting point, a waypoint and an end point, a navigation path from the starting point to the end point and passing through the waypoint is generated according to the map file;

[0026] In the case where the navigation simulation configuration file includes a starting point, an avoidance scenario, and an end point, a navigation path from the starting point to the end point and avoiding the avoidance scenario is generated according to the map file.

[0027] In some embodiments, obtaining a navigation simulation configuration file includes at least one of the following:

[0028] In response to a first configuration parameter input by a user in the visualization interface, generating a navigation simulation configuration file according to the first configuration parameter;

[0029] In response to a second configuration parameter input by a user in the visual interface, a preset test script is updated according to the second configuration parameter to generate a navigation simulation configuration file.

[0030] In some embodiments, obtaining a scene simulation file, and generating a path simulation scene adapted to the navigation path based on the scene simulation file includes:

[0031] Based on the test map, determine the real-time positioning information of the simulated vehicle;

[0032] Obtain a scenario simulation file, and explore and obtain a path simulation scenario corresponding to the real-time positioning information based on the vehicle positioning information and the scenario simulation file;

[0033] Encapsulate the broadcast data of the path simulation scenario and send it to the autonomous driving domain controller;

[0034] Based on the path simulation scenario and the autonomous driving algorithm to be tested, the simulated vehicle drives along the navigation path, including:

[0035] The autonomous driving algorithm to be tested in the autonomous driving domain controller simulates the vehicle driving along the navigation path and adapts the path simulation scenario.

[0036] In some embodiments, a scenario simulation file is obtained, and a path simulation scenario corresponding to the real-time positioning information is explored based on the positioning information of the vehicle and the scenario simulation file, including:

[0037] Obtain a scene simulation file, perform path exploration along the navigation path in the test map based on the positioning information and the scene simulation file, and obtain a path simulation scene at a preset distance before and after the positioning information;

[0038] A path simulation scenario adapted to the path simulation scenario is generated according to the scenario simulation file.

[0039] In some embodiments, the preset distance is greater than or equal to the required distance of the control algorithm integrated in the autonomous driving domain controller.

[0040] In a second aspect, an embodiment of the present application provides an autonomous driving simulation device, the device comprising:

[0041] A map simulation module is used to obtain a map file and generate a test map based on the map file;

[0042] A navigation simulation module, used to obtain a navigation simulation configuration file, and generate a navigation path in a test map based on the navigation simulation configuration file;

[0043] A scene simulation module, used to obtain a scene simulation file, and generate a path simulation scene adapted to the navigation path based on the scene simulation file;

[0044] The autonomous driving domain controller is used to simulate the vehicle driving along the navigation path based on the path simulation scenario and the autonomous driving algorithm to be tested.

[0045] On the third aspect, an embodiment of the present application provides an autonomous driving simulation device, which includes: a processor and a memory storing computer program instructions, and the processor implements the above-mentioned autonomous driving simulation method when executing the computer program instructions.

[0046] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above-mentioned autonomous driving simulation method is implemented.

[0047] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the above-mentioned autonomous driving simulation method is implemented.

[0048] In the autonomous driving simulation method, autonomous driving simulation device and equipment provided in the present application, a map file is obtained and a test map is generated based on the map file; a navigation simulation configuration file is obtained and a navigation path in the test map is generated based on the navigation simulation configuration file to realize the simulation of the navigation path in different scenarios; a scene simulation file is obtained and a path simulation scene adapted to the navigation path is generated based on the scene simulation file; based on the path simulation scene and the autonomous driving algorithm to be tested, a vehicle is simulated traveling along the navigation path, thereby realizing the autonomous driving simulation along the navigation path, so as to test the output of the autonomous driving algorithm to be tested in the face of different navigation paths, thereby eliminating or reducing the autonomous driving test of a real vehicle in a real environment, reducing the development cost of the autonomous driving algorithm to be tested and improving the development efficiency of the autonomous driving algorithm to be tested. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 is a flowchart of an automatic driving simulation method provided by an embodiment of the present application,

[0051] Figure 2 is a schematic diagram of a hierarchical database of an autonomous driving simulation method provided in an embodiment of the present application,

[0052] Figure 3 is a module schematic diagram of an automatic driving simulation device provided by an embodiment of the present application,

[0053] Figure 4 It is a structural diagram of an autonomous driving simulation device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0054] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0055] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0056] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The embodiments will be described in detail below in conjunction with the accompanying drawings.

[0057] In order to solve the problems of the prior art, the embodiment of the present application provides an automatic driving simulation method. The automatic driving simulation method provided by the embodiment of the present application is first introduced below.

[0058] Figure 1A schematic diagram of a process flow of an autonomous driving simulation method provided by an embodiment of the present application is shown. The method comprises the following steps:

[0059] S110, obtaining a map file, and generating a test map based on the map file;

[0060] The map file is a file constructed by pre-parsing the map data according to the storage format used by the map data. Multiple map files can be pre-selected and parsed to be selected during simulation testing. The map data can be the original map file provided by the map vendor.

[0061] S120, obtaining a navigation simulation configuration file, and generating a navigation path in a test map based on the navigation simulation configuration file;

[0062] The navigation simulation configuration file can be a file input by the user according to the required test target, or a file input by the user according to the test case set by the required test target. The navigation simulation configuration file can include a starting point and an end point. The preset navigation algorithm maps the coordinates of the starting point and the end point to the test map through the triple positioning logic, and then at least one driving path can be calculated based on the optimal path planning algorithm. One of the at least one driving paths can be selected as the navigation path according to the user input, or a driving path that matches the test rule can be selected as the navigation path from at least one driving path according to the test rule. The test rule can be the shortest travel path, the fastest travel path, the path with the least toll, etc.

[0063] The navigation simulation profile may also include lane-level features, which are parameters accurate to the lane level. For example: priority driving lane, priority auxiliary lane, priority variable lane, avoidance bus lane, etc. Therefore, the navigation path generated based on the navigation simulation profile may be a lane-level navigation path.

[0064] S130, obtaining a scene simulation file, and generating a path simulation scene adapted to the navigation path based on the scene simulation file;

[0065] In the process of autonomous driving of a real vehicle, the vehicle uses sensors such as lidar, ultrasonic radar, millimeter-wave radar, and cameras to achieve beyond-visual-range environmental perception and high-precision fusion positioning, and then directly or indirectly provides the information to the autonomous driving domain controller to achieve autonomous driving. In this application, a path simulation scene adapted to the navigation path is generated based on the scene simulation file, that is, the path scene collected by the sensor at the location of the vehicle on the test map can be simulated.

[0066] The scene simulation files include but are not limited to intersection description files, lane line description files, line proximal geometry parameters, line distal geometry parameters, traffic sign description files, traffic light description files, road type description files, traffic scene information, etc.

[0067] S140, based on the path simulation scenario and the autonomous driving algorithm to be tested, simulating the vehicle to travel along the navigation path.

[0068] The autonomous driving domain controller can be used to simulate the vehicle driving along the navigation path. The autonomous driving domain controller stores the autonomous driving algorithm to be tested. In real scenarios, the autonomous driving algorithm can control the vehicle to drive along the navigation path according to the path scenario, so as to achieve passing intersections, lane switching, avoiding obstacles, etc. in compliance with traffic lights. Therefore, the autonomous driving algorithm to be tested stored in the driving domain controller can also simulate vehicle driving when the navigation path and path simulation scenario are obtained. In the process of simulating vehicle driving, the output of the autonomous driving algorithm to be tested facing different navigation paths can be collected to debug the autonomous driving algorithm to be tested based on the output.

[0069] In the present application, a map file is obtained and a test map is generated based on the map file; a navigation simulation configuration file is obtained and a navigation path in the test map is generated based on the navigation simulation configuration file to realize the simulation of the navigation path in different scenarios; a scene simulation file is obtained and a path simulation scene adapted to the navigation path is generated based on the scene simulation file; based on the path simulation scene and the autonomous driving algorithm to be tested, the vehicle is simulated traveling along the navigation path, thereby realizing the autonomous driving simulation along the navigation path, so as to test the output of the autonomous driving algorithm to be tested in the face of different navigation paths, thereby eliminating or reducing the autonomous driving test of a real vehicle in a real environment, reducing the development cost of the autonomous driving algorithm to be tested, and improving the development efficiency of the autonomous driving algorithm to be tested.

[0070] In some embodiments, S110 includes:

[0071] S210, obtaining a target map identification code;

[0072] S220, selecting a target map file that matches the target map identification code from among multiple map files, wherein the multiple map files are files respectively constructed by parsing map data stored using different standard protocols, wherein the map files store road information of multiple map roads, slice information of a road slice corresponding to each map road, and lane information of a slice lane corresponding to each road slice;

[0073] S230, simulating and obtaining a test map according to the target map file.

[0074] The multiple map files stored in the target database all have corresponding map identification codes. Different map files can be distinguished by map identification codes. Different map files can correspond to different administrative districts, or they can be files parsed from map data of the same administrative district but in different storage formats. Map data stored using different standard protocols can be original map files stored using different standard protocols provided by different map vendors. Different standard protocols include but are not limited to OpenDRIVE, NDS, etc.

[0075] By pre-parsing the map data stored in different standard protocols to construct a map file, when performing autonomous driving simulation, a target map identification code can be given as needed, and a target map file matching the target map identification code can be obtained for test map simulation, thereby avoiding the problem of test map generation failure due to map file format change.

[0076] In some embodiments, before S110, the steps include:

[0077] S310, acquiring map data, parsing the map data, and obtaining map roads in the map data;

[0078] S320, slicing the map roads according to the road features of each map road to obtain at least one road slice corresponding to each map road information;

[0079] S330, performing lane division processing on the road slices corresponding to each map road to obtain at least one slice lane corresponding to each road slice;

[0080] S340, determining, based on the map data, road information corresponding to each map road, slice information corresponding to each road slice, and lane information corresponding to each slice lane;

[0081] S350, hierarchically storing the road information corresponding to each map road, the slice information corresponding to each road slice, and the lane information corresponding to each slice lane, to obtain a map file stored in a hierarchical database.

[0082] The various map data to be deployed can be parsed in advance through a pre-configured parsing program to construct a database file corresponding to each map data, that is, a map file corresponding to each map data. The database file corresponding to each map data is used to store the road information of all map roads in the map data, the slice information of each road slice corresponding to each map road, and the lane information of each slice lane corresponding to each road slice. The road information of the map road may include data such as the road topology relationship of the road and the road boundary coordinates. The slice information of the road slice may include data such as the boundary coordinates of the slice. The lane information of the slice lane includes the lane topology relationship, lane type, lane line type, and coordinate data of the lane. The coordinate data may include data such as the coordinates of discrete points of the lane line and the coordinates of discrete points of the lane center line.

[0083] The road features of the map road may include the length of the map road, the change in the number of lanes, the change in the virtual and real lines of the lanes, etc. Slicing the map road according to the road features of each map road may be slicing the map road based on the length of the map road. For example: slicing the map road A every 1000m. Slicing the map road according to the road features of each map road may be slicing the map road based on the change in the number of lanes. For example: slicing the merge point in map road A.

[0084] For example, the map road includes a first section, a second section, and a third section, the lane line of the first section is a solid line, the lane line of the second section is a dotted line, and the lane line of the third section is a solid line. The map road is sliced, and the first section of the map road is divided into a slice A (lane section A), the second section is divided into a slice B (lane section B), and the third section is divided into a slice C (lane section C).

[0085] The map road may include multiple lanes. Taking the lane as the smallest unit, each road slice is further refined to obtain at least one slice lane corresponding to each road slice.

[0086] The various data attributes to be stored can be preset, and the corresponding road information, slice information and lane information can be obtained from the map data according to the predetermined data attributes.

[0087] A new database file can be created to store road information, slice information, and lane information in the form of a hierarchical database. The database file can use a SQLite lightweight database. When using a map file to generate a test map and locate a simulated vehicle, the corresponding information at each level in the hierarchical database can be loaded step by step, reducing the size of data that needs to be loaded in the cache during autonomous driving simulation and speeding up the operation.

[0088] In some embodiments, S350 includes:

[0089] S410, creating a first-level database table, and storing road information corresponding to each map road in the first-level database table;

[0090] S420, creating a second-level database table corresponding to each map road, and storing slice information corresponding to the road slice corresponding to each map road in the matching second-level database table;

[0091] S430, creating a third-level database table corresponding to each road slice, and storing lane information of a slice lane corresponding to each road slice in a matching third-level database table;

[0092] S440, storing the first-level database table, the second-level database table and the third-level database table in a hierarchical manner to obtain a map file stored in a hierarchical database.

[0093] The first-level database table stores the road information corresponding to the map roads, the second-level database table stores the slice information corresponding to the road slices, and the third-level database table stores the lane information of the slice lanes. The map roads, road slices, and slice lanes all have corresponding identification codes, so that different map roads, road slices, and slice lanes can be distinguished by the identification codes.

[0094] For example, see Figure 2 , according to the identification code Road ID of the map road, the road information corresponding to the identification code Road ID1 in the more macro first-level database table Level1 can be preferentially loaded; then, according to the corresponding index of the identification code Road ID1 stored in the first-level database table Level1, the slice information corresponding to the identification code Section ID in the second-level database table Level2 is queried, and the slice information corresponding to the identification code Section ID1 is loaded; then, according to the corresponding index of the identification code Section ID1 stored in the second-level database table Level2, the slice lane corresponding to the identification code LaneID in the third-level database table Level3 is queried, and the lane information corresponding to the identification code LaneID1 is loaded, so as to obtain the detailed information of the area with the identification code Road ID1-Section ID1-LaneID1, reduce the size of data to be loaded in the cache area during autonomous driving simulation, speed up the running speed, and help improve the work efficiency of testing work and the convenience of carrying out testing work.

[0095] In some embodiments, S120 includes at least one of the following:

[0096] S510, in the case where the navigation simulation configuration file includes a starting point, a waypoint and an ending point, generating a navigation path from the starting point to the ending point and passing through the waypoint according to the map file;

[0097] S520: In a case where the navigation simulation configuration file includes a starting point, an avoidance scenario, and an end point, a navigation path from the starting point to the end point and avoiding the avoidance scenario is generated according to the map file.

[0098] When generating a navigation path by a preset navigation algorithm, only a starting point and an end point may be given to generate a navigation path starting from the starting point and ending at the end point. The user may also set a waypoint according to test needs so that the navigation path passes through the waypoint.

[0099] Users can also set avoidance scenarios according to test needs and generate navigation paths that avoid avoidance scenarios. Avoidance scenarios can include avoiding construction sections, avoiding sections with missing lane lines, avoiding toll sections, avoiding congested sections, avoiding school sections, avoiding highly polluted sections, etc. The generated navigation path will bypass the set avoidance scenarios.

[0100] Those skilled in the art will appreciate that the navigation simulation profile may also include a starting point, waypoints, avoidance scenarios and an end point, thereby generating a navigation path from the starting point to the end point, passing through waypoints and avoiding avoidance scenarios according to a map file.

[0101] By setting the starting point, waypoints, avoidance scenarios, and end points, multiple navigation paths are generated through a preset navigation algorithm to detect the computing power of the autonomous driving domain controller based on the autonomous driving algorithm to be tested along the navigation path.

[0102] In some embodiments, in S120, obtaining a navigation simulation configuration file includes at least one of the following:

[0103] S610, in response to a first configuration parameter input by a user in a visual interface, generating a navigation simulation configuration file according to the first configuration parameter;

[0104] S620, in response to a second configuration parameter input by the user in the visual interface, updating a preset test script according to the second configuration parameter to generate a navigation simulation configuration file.

[0105] A visual interface can be provided for users to input the first configuration parameters. When performing autonomous driving simulation, static scene information, dynamic scene information, simulated vehicle position and posture information, navigation path output by the navigation algorithm, autonomous driving domain controller receiving end information, autonomous driving domain controller output information, etc. can also be read, and then the real-time path simulation scene, test map, broadcast data sending end, and sending data receiving end can be compared and displayed in the visual interface, which can effectively assist simulation development and debugging work.

[0106] The autonomous driving simulation method provided in this application supports two simulation test methods: single debugging test and continuous automated test of test case set. When performing a single debugging test, the user can enter the first configuration parameter in the visual interface, and generate a navigation simulation configuration file based on the first configuration parameter. The navigation algorithm calculates n driving paths for the user to choose, and the user selects one of the multiple driving paths as the navigation path, thereby realizing the function and coverage test of autonomous driving for the navigation paths generated for different road conditions.

[0107] When performing continuous automated testing of a test case set, the test case set includes multiple test cases, and each test case is run in sequence to automatically generate a navigation path that matches each test case. A user can input second configuration parameters required for the test case in the visual interface, such as a starting point and an end point.

[0108] In some embodiments, S130 includes:

[0109] S710, determining real-time positioning information of a simulated vehicle based on a test map;

[0110] S720, obtaining a scene simulation file, and exploring a path simulation scene corresponding to the real-time positioning information according to the real-time positioning information of the vehicle and the scene simulation file;

[0111] S730, encapsulating broadcast data of the path simulation scenario and sending it to the autonomous driving domain controller;

[0112] S140 includes:

[0113] S740, simulating the vehicle to travel along the navigation path and adapting to the path simulation scenario through the autonomous driving algorithm to be tested in the autonomous driving domain controller.

[0114] Determine the real-time positioning information of the simulated vehicle, that is, determine the position of the simulated vehicle in the test map, and obtain the coordinate data of the map road, road slice, and slice lane corresponding to the real-time positioning information of the vehicle.

[0115] After determining the real-time positioning information of the vehicle, the environment information collected by the sensing device in the real environment of the real vehicle can be simulated according to the scene simulation file to generate a path simulation scene. In some embodiments, S720 includes:

[0116] S810, obtaining a scene simulation file, performing path exploration along the navigation path in the test map based on the positioning information and the scene simulation file, and obtaining a path simulation scene located at a preset distance before and after the real-time positioning information of the vehicle;

[0117] S820: Generate a path simulation scenario adapted to the path simulation scenario according to the scenario simulation file.

[0118] During the autonomous driving simulation process, path exploration is performed on the test map within a preset distance in front of and behind the position along the navigation path to obtain coordinate data such as map roads, road slices, slice lanes, etc. corresponding to the positioning information, as well as the required test scenarios.

[0119] In some embodiments, the preset distance is greater than or equal to the required distance of the control algorithm integrated in the autonomous driving domain controller to ensure the normal operation of the control algorithm integrated in the autonomous driving domain controller.

[0120] In some embodiments, the generated navigation path can store information of different levels in the navigation path through log levels to facilitate tracing and reproducing problems that occur during the autonomous driving simulation process.

[0121] In the method provided in the embodiment of the present invention, data transmission can be achieved through a predetermined communication method, including but not limited to inter-process communication (UDP, TCP, SOMEIP, DDS, etc.), shared memory, etc. The path simulation scene is sent to the autonomous driving domain controller, and the autonomous driving domain controller can further send it to the ADAS application that uses the high-precision map data.

[0122] Based on the automatic driving simulation method provided in the above embodiment, the present application also provides a specific implementation method of the automatic driving simulation device. Please refer to the following embodiment.

[0123] See first Figure 3 The automatic driving simulation device 300 provided in the embodiment of the present application includes the following modules:

[0124] A map simulation module 301 is used to obtain a map file and generate a test map based on the map file;

[0125] A navigation simulation module 302 is used to obtain a navigation simulation configuration file and generate a navigation path in a test map based on the navigation simulation configuration file;

[0126] A scene simulation module 303 is used to obtain a scene simulation file and generate a path simulation scene adapted to the navigation path based on the scene simulation file;

[0127] The autonomous driving domain controller 304 is used to simulate the vehicle driving along the navigation path based on the path simulation scenario and the autonomous driving algorithm to be tested.

[0128] The autonomous driving simulation device 300 may be a hardware in loop (HIL). The map simulation module 301, the navigation simulation module 302, the scene simulation module 303, and the automatic test module 305 in the autonomous driving simulation device 300 may be deployed on a real-time simulator, and connected to the autonomous driving domain controller 304 through hardware to verify the autonomous driving algorithm. The map simulation module 301 and the navigation simulation module 302 in the autonomous driving simulation device 300 may also be deployed on a cloud server, and data may be exchanged with the scene simulation module 303 through network communication. The automatic test module 305 may output a navigation simulation configuration file to the navigation simulation module 302.

[0129] As an implementation of the present application, the map simulation module 301 includes:

[0130] A first acquisition unit, used to acquire a target map identification code;

[0131] a first selection unit, configured to select a target map file matching the target map identification code from among a plurality of map files, wherein the plurality of map files are files respectively constructed by parsing map data stored using different standard protocols, wherein the map files store road information of a plurality of map roads, slice information of a road slice corresponding to each map road, and lane information of a slice lane corresponding to each road slice;

[0132] The map simulation unit is used to simulate a test map according to a target map file.

[0133] As an implementation of the present application, the autonomous driving simulation device 300 includes:

[0134] A map parsing module is used to obtain map data, parse the map data, and obtain map roads in the map data;

[0135] A first slicing module, configured to slice the map roads according to the road features of each map road, and obtain at least one road slice corresponding to each map road information;

[0136] A second slicing module is used to perform lane division processing on the road slices corresponding to each map road to obtain at least one slice lane corresponding to each road slice;

[0137] An information determination module, for determining, based on the map data, road information corresponding to each map road, slice information corresponding to each road slice, and lane information corresponding to each slice lane;

[0138] The hierarchical storage module is used to hierarchically store the road information corresponding to each map road, the slice information corresponding to each road slice, and the lane information corresponding to each slice lane, so as to obtain a map file stored in a hierarchical database.

[0139] As an implementation of the present application, the hierarchical storage module includes:

[0140] A first creation unit, used to create a first-level database table, and store the road information corresponding to each map road in the first-level database table;

[0141] A second creation unit is used to create a second-level database table corresponding to each map road, and store the slice information corresponding to the road slice corresponding to each map road in the matching second-level database table;

[0142] A third creation unit, used to create a third-level database table corresponding to each road slice, and store lane information of a slice lane corresponding to each road slice into a matching third-level database table;

[0143] The storage unit is used to store the first-level database table, the second-level database table and the third-level database table in a hierarchical manner to obtain a map file stored in a hierarchical database.

[0144] As an implementation of the present application, the navigation simulation module 302 includes at least one of the following:

[0145] A first path generating unit, configured to generate a navigation path from the starting point to the ending point and passing through the waypoints according to a map file when the navigation simulation configuration file includes a starting point, a waypoint and an ending point;

[0146] The second path generating unit is used to generate a navigation path from the starting point to the ending point and avoiding the avoidance scenario according to the map file when the navigation simulation configuration file includes the starting point, the avoidance scenario and the ending point.

[0147] As an implementation of the present application, the navigation simulation module 302 includes at least one of the following:

[0148] A first configuration unit, configured to generate a navigation simulation configuration file according to a first configuration parameter input by a user on a visual interface;

[0149] The second configuration unit is used to respond to the second configuration parameter input by the user in the visual interface, update the preset test script according to the second configuration parameter, and generate a navigation simulation configuration file.

[0150] As an implementation of the present application, the scene simulation module 303 includes:

[0151] A first positioning unit, used to determine real-time positioning information of a simulated vehicle based on a test map;

[0152] A path exploration unit is used to obtain a scene simulation file, and explore a path simulation scene corresponding to the real-time positioning information according to the vehicle positioning information and the scene simulation file;

[0153] A broadcast data encapsulation unit, used to encapsulate the broadcast data of the path simulation scenario and send it to the autonomous driving domain controller;

[0154] The autonomous driving domain controller 304 is also used to simulate the vehicle driving along the navigation path and adapt the path simulation scenario through the autonomous driving algorithm to be tested.

[0155] As an implementation method of the present application, the broadcast data encapsulation unit is further used to obtain a scene simulation file, perform path exploration along the navigation path in the test map based on the positioning information and the scene simulation file, and obtain a path simulation scene located at a preset distance before and after the positioning information;

[0156] A path simulation scenario adapted to the path simulation scenario is generated according to the scenario simulation file.

[0157] As an implementation method of the present application, the preset distance is greater than or equal to the required distance of the control algorithm integrated in the autonomous driving domain controller.

[0158] Figure 4 A schematic diagram of the hardware structure of the autonomous driving simulation device provided in an embodiment of the present application is shown.

[0159] The autonomous driving simulation device may include a processor 401 and a memory 402 storing computer program instructions.

[0160] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0161] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.

[0162] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0163] The processor 401 implements any one of the autonomous driving simulation methods in the above embodiments by reading and executing computer program instructions stored in the memory 402.

[0164] In one example, the autonomous driving simulation device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0165] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0166] Bus 410 includes hardware, software or both, and couples the components of the autonomous driving simulation device to each other. For example, but not limitation, the bus may include an accelerated graphics port (AGP) or other graphics bus, an enhanced industrial standard architecture (EISA) bus, a front-end bus (FSB), a hypertransport (HT) interconnection, an industrial standard architecture (ISA) bus, an infinite bandwidth interconnection, a low pin count (LPC) bus, a memory bus, a microchannel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus or other suitable bus or a combination of two or more of these. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0167] The autonomous driving simulation device can be based on the above-mentioned embodiment, thereby realizing the autonomous driving simulation method combined with the above-mentioned embodiment.

[0168] In addition, in combination with the autonomous driving simulation method in the above-mentioned embodiment, the embodiment of the present application may provide a computer storage medium to implement it. The computer storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, any one of the autonomous driving simulation methods in the above-mentioned embodiments is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here. Among them, the above-mentioned computer-readable storage medium may include a non-transitory computer-readable storage medium, such as a read-only memory (Read-Only Memory, referred to as ROM), a random access memory (Random Access Memory, referred to as RAM), a disk or an optical disk, etc., which are not limited here.

[0169] In addition, an embodiment of the present application also provides a computer program product, including computer program instructions, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0170] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0171] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0172] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0173] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0174] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. An automatic driving simulation method, characterized in that: The method comprises: Obtaining a map file, and generating a test map based on the map file; Obtaining a navigation simulation configuration file, and generating a navigation path in the test map based on the navigation simulation configuration file; Acquire a scene simulation file, and generate a path simulation scene adapted to the navigation path based on the scene simulation file; Based on the path simulation scenario and the autonomous driving algorithm to be tested, the simulated vehicle travels along the navigation path.

2. The automatic driving simulation method according to claim 1, characterized in that: The obtaining of the map file and generating the test map based on the map file includes: Get the target map identification code; Selecting a target map file that matches the target map identification code from among multiple map files, wherein the multiple map files are files respectively constructed by parsing map data stored using different standard protocols, wherein the map files store road information of multiple map roads, slice information of a road slice corresponding to each of the map roads, and lane information of a slice lane corresponding to each of the road slices; The test map is obtained by simulating the target map file.

3. The automatic driving simulation method according to claim 2, characterized in that: The obtaining of the map file, before generating the test map based on the map file, includes: Acquire map data, parse the map data, and obtain map roads in the map data; Slicing the map roads according to the road features of each of the map roads to obtain at least one road slice corresponding to each of the map roads; Performing lane division processing on the road slices corresponding to each of the map roads to obtain at least one slice lane corresponding to each of the road slices; Based on the map data, determining road information corresponding to each of the map roads, slice information corresponding to each of the road slices, and lane information corresponding to each of the slice lanes; The road information corresponding to each of the map roads, the slice information corresponding to each of the road slices, and the lane information corresponding to each of the slice lanes are stored in a hierarchical manner to obtain the map file stored in a hierarchical database.

4. The automatic driving simulation method according to claim 3, characterized in that: The road information corresponding to each of the map roads, the slice information corresponding to each of the road slices, and the lane information corresponding to each of the slice lanes are stored in a hierarchical manner to obtain the map file stored in a hierarchical database, including: Creating a first-level database table, and storing the road information corresponding to each of the map roads in the first-level database table; Creating a second-level database table corresponding to each of the map roads, and storing slice information corresponding to the road slice corresponding to each of the map roads in the matching second-level database table; Creating a third-level database table corresponding to each of the road slices, and storing lane information of the slice lane corresponding to each of the road slices into the matching third-level database table; The first-level database table, the second-level database table and the third-level database table are stored hierarchically to obtain the map file stored in a hierarchical database.

5. The automatic driving simulation method according to claim 1, characterized in that: The obtaining of the navigation simulation configuration file and generating the navigation path in the test map based on the navigation simulation configuration file comprises at least one of the following: In the case where the navigation simulation configuration file includes a starting point, a waypoint and an end point, generating a navigation path from the starting point to the end point and passing through the waypoint according to the map file; In the case where the navigation simulation configuration file includes a starting point, an avoidance scenario and an end point, a navigation path from the starting point to the end point and avoiding the avoidance scenario is generated according to the map file.

6. The automatic driving simulation method according to claim 1, characterized in that: The obtaining of the navigation simulation configuration file includes at least one of the following: In response to a first configuration parameter input by a user in a visual interface, generating the navigation simulation configuration file according to the first configuration parameter; In response to a second configuration parameter input by a user in the visual interface, a preset test script is updated according to the second configuration parameter to generate the navigation simulation configuration file.

7. The automatic driving simulation method according to claim 1, characterized in that: The acquiring of the scene simulation file and generating a path simulation scene adapted to the navigation path based on the scene simulation file comprises: Based on the test map, determining the real-time positioning information of the simulated vehicle; Obtaining a scenario simulation file, and exploring and obtaining a path simulation scenario corresponding to the real-time positioning information according to the positioning information of the vehicle and the scenario simulation file; Encapsulating broadcast data of the path simulation scenario and sending it to an autonomous driving domain controller; The simulating vehicle driving along the navigation path based on the path simulation scenario and the automatic driving algorithm to be tested includes: The autonomous driving algorithm to be tested in the autonomous driving domain controller simulates the vehicle traveling along the navigation path and adapts to the path simulation scenario.

8. The automatic driving simulation method according to claim 7, characterized in that: The acquiring of the scenario simulation file, exploring and obtaining a path simulation scenario corresponding to the real-time positioning information according to the positioning information of the vehicle and the scenario simulation file, comprises: Acquire a scenario simulation file, perform path exploration along the navigation path in the test map based on the positioning information and the scenario simulation file, and obtain a path simulation scene located at a preset distance before and after the real-time positioning information, wherein the preset distance is greater than or equal to a required distance of a control algorithm integrated in the autonomous driving domain controller; A path simulation scenario adapted to the path simulation scenario is generated according to the scenario simulation file.

9. An automatic driving simulation device, characterized in that: The device comprises: A map simulation module, used for acquiring a map file and generating a test map based on the map file; A navigation simulation module, used for obtaining a navigation simulation configuration file, and generating a navigation path in the test map based on the navigation simulation configuration file; A scene simulation module, used to obtain a scene simulation file, and generate a path simulation scene adapted to the navigation path based on the scene simulation file; The autonomous driving domain controller is used to simulate the vehicle traveling along the navigation path based on the path simulation scenario and the autonomous driving algorithm to be tested.

10. An automatic driving simulation device, characterized in that: The device comprises: a processor and a memory storing computer program instructions, and when the processor executes the computer program instructions, the automatic driving simulation method as described in any one of claims 1 to 8 is implemented.

Images