A method, device, equipment and storage medium for determining an autonomous driving scene

Abstract

The embodiment of the present invention discloses a method, device, equipment and storage medium for determining an autonomous driving scene. The method includes: determining at least one target scene label associated with the current driving scene of the vehicle to be tested according to the current driving scene of the vehicle to be tested; selecting a target scene element from the candidate scene elements of the target scene label according to the current driving information of the vehicle to be tested; combining the target scene elements to obtain a target driving scene sequence of the vehicle to be tested. By dividing different scenes into scene labels and dividing specific scene elements under the scene labels, independent selection of each scene element is achieved and combined into a complete scene sequence, accurate determination of the target scene is achieved, repeated selection of autonomous driving scenes is avoided, and scene determination efficiency is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to vehicle testing technology, and more particularly to a method, device, equipment and storage medium for determining an autonomous driving scenario. Background Art

[0002] Autonomous driving is a product of the times that is the result of the deep integration of multiple scientific and technological fields. Autonomous driving vehicles have moved from the laboratory to the stage of field testing and commercial demonstration. Autonomous driving technology is facing the stage of testing and verification before entering the market.

[0003] Autonomous driving scene analysis technology is a key technology in the autonomous driving test process. When dealing with the test scene planning problem of high-level autonomous driving vehicles, the usual practice is to collect typical autonomous driving scene data and select the target scene from the collected data. However, the collection of autonomous driving scene data cannot achieve flexible changes to autonomous driving scenes, and ignores issues such as the coverage of the test scene set and the comprehensiveness of the test, resulting in fuzzy classification of autonomous driving scenes and low efficiency and accuracy in determining autonomous driving scenes. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, equipment and storage medium for determining an autonomous driving scenario to improve the efficiency and accuracy of determining an autonomous driving scenario.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining an autonomous driving scenario, the method comprising:

[0006] Determining, according to a current driving location of the vehicle to be tested, at least one target scene label associated with the current driving location;

[0007] Selecting a target scene element from candidate scene elements of the target scene label according to current driving information of the vehicle to be tested;

[0008] The target scene elements are combined to obtain a target driving scene sequence for the vehicle to be tested.

[0009] In a second aspect, an embodiment of the present invention further provides a device for determining an autonomous driving scenario, the device comprising:

[0010] A label determination module, used to determine at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested;

[0011] An element determination module, configured to select a target scene element from candidate scene elements of the target scene label according to current driving information of the vehicle to be tested;

[0012] The scene determination module is used to combine the target scene elements to obtain a target driving scene sequence of the vehicle to be tested.

[0013] In a third aspect, an embodiment of the present invention further provides a device for determining an autonomous driving scenario, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for determining an autonomous driving scenario as described in any embodiment of the present invention is implemented.

[0014] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a method for determining an autonomous driving scenario as described in any embodiment of the present invention.

[0015] The embodiment of the present invention determines at least one target scene tag from a plurality of pre-set scene tags according to the current driving location of the vehicle to be tested. Each scene tag includes one or more candidate scene elements. According to the driving information, at least one target scene element can be selected. The target scene elements are combined, and the obtained sequence is the target driving scene sequence. This solves the problem in the prior art that the autonomous driving scene is difficult to change arbitrarily according to the vehicle test situation, realizes flexible changes to the autonomous driving scene, and improves the efficiency and accuracy of determining the autonomous driving scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flowchart of a method for determining an autonomous driving scenario in Embodiment 1 of the present invention;

[0017] Figure 2 is a flowchart of a method for determining an autonomous driving scenario in Embodiment 2 of the present invention;

[0018] Figure 3 is a structural block diagram of a device for determining an autonomous driving scenario in Embodiment 3 of the present invention;

[0019] Figure 4 It is a structural diagram of a device for determining an autonomous driving scenario in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0020] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0021] Embodiment 1

[0022] Figure 1This is a flow chart of a method for determining an autonomous driving scenario provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of determining an autonomous driving scenario for a vehicle to be tested. The method can be executed by a device for determining an autonomous driving scenario. Figure 1 As shown, the method specifically comprises the following steps:

[0023] Step 110: Determine at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested.

[0024] The vehicle to be tested is an autonomous driving vehicle, and the driving environment in which the vehicle to be tested is currently located is taken as the current driving location, which is the location of the road where the vehicle to be tested is located. For example, the driving location can be an airport, a mine, a dock, a scenic spot, etc. If the vehicle to be tested is on the runway of an airport, the current driving location is the airport.

[0025] Multiple candidate scene tags are pre-set, and different driving places can be associated with different candidate scene tags. There may be duplication between candidate scene tags associated with different driving places. Scene tags can be set using different division dimensions, and specific driving scenes can be represented by one or more scene tags. For example, scene tags may include road type, lane direction, number of lanes, road section type, whether it intersects with a slide, weather conditions, road surface conditions, time period, and lighting, etc. The association relationship between different driving places and scene tags is set. For example, if the driving place is a scenic spot, the associated scene tags are road type, lane direction, number of lanes, road section type, weather conditions, road surface conditions, time period, and lighting. If the driving place is an airport, the associated scene tags may also include whether it intersects with a slide. After determining the current driving place, at least one target scene tag associated with the current driving place is determined according to the preset association relationship.

[0026] In this embodiment, optionally, before determining at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested, the method further includes: obtaining current position information of the vehicle to be tested, and determining the current driving location of the vehicle to be tested according to the current position information.

[0027] Specifically, a GPS positioning device can be used to determine the current location information of the vehicle to be tested, or a camera can be used to capture the surrounding environment of the vehicle to be tested as the current location information, and the current driving location of the vehicle to be tested can be determined based on the current location information. For example, the camera captures a photo of the surrounding environment, identifies that there is an airport terminal in the surrounding environment, and determines that the current driving location is an airport. The beneficial effect of such a setting is that the current driving location of the vehicle to be tested can be identified in real time, so that the driving scene can be determined according to the current driving location, the vehicle can be tested, the correlation between the vehicle test and the surrounding environment can be improved, and the accuracy of the vehicle test can be improved.

[0028] In this embodiment, optionally, at least one target scene label associated with the current driving location is determined based on the current driving location of the vehicle to be tested, including: selecting at least one target scene label associated with the current driving location from preset candidate scene labels based on the current driving location of the vehicle to be tested.

[0029] Specifically, multiple candidate scene tags are preset, and the candidate scene tags are associated with each driving location and saved. For example, for a mine, the candidate scene tags may include a lane direction tag, a weather condition tag, and a lighting tag. The lane direction tag may specifically indicate the different directions of the lane, the weather tag may specifically indicate different weather conditions, and the lighting tag may indicate whether lighting is to be provided for the current scene. After determining the current driving location, a selection is made from the preset candidate scene tags to obtain one or more target scene tags associated with the current driving location. The beneficial effect of such a setting is that the target scene tag is determined according to the current driving location, the selection range of the scene tag is reduced, the final autonomous driving scene is determined from the target scene tag, the efficiency and accuracy of determining the autonomous driving scene is improved, and data confusion is avoided.

[0030] Step 120 : Select a target scene element from candidate scene elements of the target scene label according to the current driving information of the vehicle to be tested.

[0031] Among them, the current driving information may include dynamic information such as the current vehicle behavior of the vehicle to be tested, and may also include relatively static information such as the surrounding environment of the vehicle to be tested. Static information may refer to information such as lanes and weather that will not change in a short time, and dynamic information refers to behavioral information such as acceleration or deceleration of the vehicle to be tested. The current driving information can be obtained by a preset sensor or camera or other device. Each scene label may include one or more candidate scene elements, and the candidate scene elements are different situation classifications of the scene label. For example, if the scene label is lighting, the candidate scene elements may include "yes" and "no", indicating the presence or absence of lighting; if the scene label is road conditions, the candidate scene elements may include "dry", "slippery", "water accumulation" and "icing". The staff can manually select the required candidate scene elements as the target scene elements according to the test requirements. For example, if the test requirement is to drive the vehicle under lighting conditions, the target scene element of the lighting scene label is "yes". The target scene element can also be determined according to the current driving information of the vehicle to be tested. For example, if the camera on the vehicle captures the current road condition as an icy state, it can be determined that the test is to be carried out under an icy state, and the target scene element of the road condition is "icing".

[0032] In this embodiment, optionally, the target scene elements include static scene elements; accordingly, according to the current driving information of the vehicle to be tested, the target scene elements are selected from the candidate scene elements of the target scene label, including: determining the static information of the target path to be traveled by the vehicle to be tested according to the current driving information of the vehicle to be tested; according to the association relationship between the preset static information and the static scene label, filtering out the static scene label associated with the static information from the target scene label; and selecting the target scene element from the candidate scene elements of the static scene label.

[0033] Specifically, in the target scene label, a static scene label may be included, and the candidate scene elements in the static scene label are static scene elements. A static scene label refers to a scene label in which the information represented by the scene label does not change over a period of time, and the information represented by the static scene label is the specific content of the static scene element. For example, a static scene label may include road type, lane direction, number of lanes, road section type, whether it intersects with a slide, weather conditions, road surface conditions, time period, and lighting, etc. The road type on which the vehicle to be tested is currently located is a straight road, and "road type" is a static scene label. "Straight road" is a static scene element in the static scene label and is also a target scene label. The static information associated with the static scene label is predetermined. For example, if the static information is the current weather, the associated static scene label is "weather conditions."

[0034] The current driving information of the vehicle to be tested is obtained. The current driving information can be collected by a camera or other sensors on the vehicle to be tested. Static information related to the target path is filtered out from the current driving information. The target path can be determined based on the current driving information. The road sign path is the path to be tested of the vehicle to be tested. The current driving information can include the starting point and the end point of the path to be tested. The target path can be determined based on the starting point and the end point. The static information related to the target path is information that will not change within a preset period of time. For example, the static information can include the road type, lane direction, number of lanes, road section type, whether it intersects with the slide, weather conditions, road surface conditions and lighting conditions of the target path. The static scene tags in the candidate scene tags are pre-set. After determining the target scene tags, the static scene tags in the target scene tags are obtained. The association relationship between the static scene tags and the static information is pre-set, that is, the static information corresponding to each static scene tag is determined. The static information in the current driving information is determined, and the static scene tags in the target scene tags involving these static information are determined based on the static information. If the static scene labels in the target scene labels include label one, label two, and label three, and the static scene labels related to the static information of the target path are label one and label two, then label three in the target scene labels is not considered, and there is no need to select the candidate scene elements in label three. After determining the static scene labels related to the static information, the target scene elements can be determined from the candidate scene elements of the static scene labels according to the test requirements of the vehicle or the collected static information. For example, if the static information indicates that the target path is a one-way lane, then the static scene label involved is determined to be "lane direction", and the target scene element of the static scene label is "one-way". The beneficial effect of such a setting is that the required static scene labels can be screened out from the target scene labels, and the static scene labels that are not involved can be eliminated, so as to avoid data confusion caused by too many useless labels, and improve the determination accuracy and efficiency of the target scene elements.

[0035] In this embodiment, optionally, the target scene label also includes a dynamic scene label; accordingly, according to the current driving information of the vehicle to be tested, the target scene element is selected from the candidate scene elements of the target scene label, and it also includes: determining the vehicle behavior of the vehicle to be tested according to the current driving information of the vehicle to be tested; according to the preset association relationship between the vehicle behavior and the dynamic scene label, filtering out the dynamic scene label that meets the vehicle behavior from the target scene label; and selecting the target scene element from the candidate scene elements of the dynamic scene label.

[0036] Specifically, the target scene tag may include a static scene tag and a dynamic scene tag, and the candidate scene elements in the dynamic scene tag are dynamic scene elements. A dynamic scene tag refers to a scene tag in which the information represented by the scene tag of the vehicle to be tested changes from time to time, and the information represented by the dynamic scene tag of the vehicle to be tested is the specific content of the dynamic scene element. For example, a dynamic scene tag may be the driving state of the vehicle, and the candidate scene elements in the dynamic scene tag may include acceleration, deceleration, start and stop, etc.

[0037] The current driving information of the vehicle to be tested is obtained, and the vehicle behavior information of the vehicle to be tested is filtered out from the current driving information. The vehicle behavior information is the dynamic information. For example, the speed change of the vehicle to be tested can be determined by a speed sensor. The dynamic scene labels in all candidate scene labels are pre-divided, and after the target scene label is determined, the dynamic scene label in the target scene label is obtained. The association relationship between the dynamic scene label and the vehicle behavior is pre-set, that is, the vehicle behavior information corresponding to each dynamic scene label is determined. The vehicle behavior information in the current driving information is determined, and the dynamic scene labels in the target scene label involving these vehicle behavior information are determined according to the vehicle behavior information. For example, "wiper" is used as a dynamic scene label. If the vehicle behavior information indicates that the wiper is in use, the scene element "in use" can be selected from the dynamic scene label "wiper". The beneficial effect of such a setting is that the required dynamic scene labels can be filtered out from the target scene label, avoiding data confusion caused by too many useless labels, and the static scene elements and dynamic scene elements are determined separately, thereby improving the determination accuracy and efficiency of the target scene elements.

[0038] Step 130: Combine the target scene elements to obtain a target driving scene sequence for the vehicle to be tested.

[0039] After obtaining each target scene element, the target scene elements are combined in a preset arrangement to obtain a series of target driving scene sequences, thereby determining the target driving scene of the vehicle to be tested. For example, the preset arrangement is to arrange the target scene elements in sequence, and the target scene elements are A, B, C, D and E, then the target driving scene sequence can be ABCDE.

[0040] The technical solution of this embodiment determines at least one target scene tag from a plurality of pre-set scene tags according to the current driving location of the vehicle to be tested, each scene tag includes one or more candidate scene elements, and at least one target scene element can be selected according to the driving information, and the target scene elements are combined to obtain a sequence that is a target driving scene sequence. This solves the problem in the prior art that the autonomous driving scene is difficult to change arbitrarily according to the vehicle test situation, realizes flexible changes to the autonomous driving scene, and improves the efficiency and accuracy of determining the autonomous driving scene.

[0041] Embodiment 2

[0042] Figure 2 This is a flow chart of a method for determining an autonomous driving scene provided by Embodiment 2 of the present invention. This embodiment is further optimized based on the above embodiment. The method can be executed by a device for determining an autonomous driving scene. Figure 2 As shown, the method specifically comprises the following steps:

[0043] Step 210: Determine at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested.

[0044] Step 220: According to the logical relationship between the candidate scene elements and the preset test requirements, at least one necessary scene element is selected from the target scene label to form a necessary scene sequence, and at least one abnormal scene element is selected to form an abnormal scene sequence.

[0045] Among them, there may be a certain logical relationship between the candidate scene elements of each candidate scene label, and the logical relationship may include a mutually exclusive relationship and a combination relationship. A mutually exclusive relationship means that the candidate scene elements under a certain target scene label cannot be selected at the same time, that is, only one of the candidate scene elements in the target scene label can be selected. A combination relationship means that the candidate scene elements under a certain target scene label can be selected at the same time, that is, one or more candidate scene elements in the target scene label can be used as the target scene element. For example, the target scene label is "lane direction", the candidate scene elements of the target scene label are "one-way" and "two-way", and the logical relationship of the candidate scene elements is mutually exclusive. When selecting the target scene element of the target scene label, only "one-way" or "two-way" can be selected. For another example, the target scene label is "road section type", the candidate scene elements of the target scene label are "motor vehicle lane", "pedestrian crossing" and "emergency parking strip", and the logical relationship of the candidate scene elements is a combination. When selecting the target scene element of the target scene label, only one of the candidate scene elements can be selected as the target scene element, or two or three candidate scene elements can be selected as the target scene element. By setting the logical relationship between the candidate scene elements, the combination relationship between the scene elements can be limited, avoiding the selection of conflicting candidate scene elements, improving the determination accuracy of the autonomous driving scene, and facilitating the testing of the vehicle.

[0046] The preset test requirements may be candidate scene elements that must exist or must not exist during the test. For example, lighting is required for airport cargo transportation during the night time period. In this case, the target scene element of the "lighting" scene tag must be the case where lighting is turned on during the night time period. According to the logical relationship between the candidate scene elements and the preset test requirements, the necessary scene sequence that must exist in the target driving scene sequence and the abnormal scene sequence that must not exist can be determined. The scene elements in the necessary scene sequence are necessary scene elements, and the scene elements in the abnormal scene sequence are abnormal scene elements. For example, if there is no one-way four-lane, the abnormal scene element is the "one-way" scene element in the "lane direction" scene tag and the "four lanes" scene element in the "number of lanes" scene tag, and the abnormal scene sequence is "one-way four lanes". For another example, the road in the vehicle test scene must contain a motor vehicle lane, then the necessary scene element is the "motor vehicle lane" scene tag in the "road section type" scene tag, and the necessary scene sequence is "motor vehicle lane". When selecting the target scenario element of "Road Section Type", you can select a single "Motor Vehicle Lane", or you can select a "Motor Vehicle Lane" and a "Pedestrian Crossing", or you can select a "Motor Vehicle Lane" and an "Emergency Stop Lane", or you can select a "Motor Vehicle Lane", a "Pedestrian Crossing" and an "Emergency Stop Lane".

[0047] Step 230: Select a target scene element from the candidate scene elements of the target scene label according to the current driving information of the vehicle to be tested.

[0048] Among them, when selecting the target scene elements, the necessary scene sequence and the abnormal scene sequence can be referred to for selection, and the scene elements in the necessary scene sequence are given priority. If the selected target scene element is a scene element in the abnormal scene sequence, the scene elements other than the selected scene elements in the abnormal scene elements are eliminated to avoid the abnormal scene sequence in the target driving scene sequence.

[0049] Step 240: Combine the target scene elements to obtain a target driving scene sequence for the vehicle to be tested.

[0050] Step 250: Compare the target driving scene sequence with the necessary scene sequence and the abnormal scene sequence to determine whether the target driving scene sequence meets the requirements of the necessary scene sequence and the abnormal scene sequence. If so, determine that the target driving scene sequence is correct.

[0051] After obtaining the target driving scene sequence, the target driving scene sequence is compared with the necessary scene sequence and the abnormal scene sequence to determine whether the target driving scene sequence meets the requirements of the necessary scene sequence and the abnormal scene sequence. It can be determined whether the target driving scene sequence contains the necessary scene sequence and the abnormal scene sequence, thereby determining whether the target driving scene sequence is correct.

[0052] In this embodiment, optionally, after combining the target scene elements to obtain the target driving scene sequence of the vehicle to be tested, it also includes: comparing the target driving scene sequence with the necessary scene sequence to determine whether the target driving scene sequence contains the necessary scene sequence; if not, it is determined that an error occurs in the target driving scene sequence, and the staff is prompted to redetermine the target driving scene sequence; comparing the target driving scene sequence with the abnormal scene sequence to determine whether the target driving scene sequence contains the abnormal scene sequence; if so, it is determined that an error occurs in the target driving scene sequence, and the staff is prompted to redetermine the target driving scene sequence.

[0053] Specifically, the target driving scene sequence can be compared with the necessary scene sequence to determine whether the target driving scene sequence has a necessary scene sequence. For example, if the target driving scene sequence is ABCDE and the necessary scene sequence is AB, it is determined that there is a necessary scene sequence in the target driving scene; if the target driving scene sequence is ACDE and the necessary scene sequence is AB, it is determined that there is no necessary scene sequence in the target driving scene. If there is no necessary scene sequence in the target driving scene, it is determined that there is an error in the target driving scene sequence, and a prompt message can be issued to prompt the staff to re-determine the target driving scene sequence for vehicle testing. Compare the target driving scene sequence with the abnormal scene sequence to determine whether there is an abnormal scene sequence in the target driving scene sequence. For example, if the target driving scene sequence is ABCDE and the abnormal scene sequence is EF, it is determined that there is no abnormal scene sequence in the target driving scene sequence. If there is an abnormal scene sequence in the target driving scene sequence, it is determined that there is an error in the target driving scene sequence, and a prompt message is issued to prompt the staff to re-determine the target driving scene sequence. If there is a necessary scene sequence in the target driving scene sequence, and there is no abnormal scene sequence, it is determined that the target driving scene sequence meets the requirements of the necessary scene sequence and the abnormal scene sequence, and the target driving scene sequence is determined correctly. The beneficial effect of such a setting is that the target driving scene sequence can be checked through the necessary scene sequence and the abnormal scene sequence, thereby avoiding confirmation errors of the target driving scene sequence and improving the determination accuracy of the autonomous driving scene.

[0054] The embodiment of the present invention determines at least one target scene label from a plurality of pre-set scene labels according to the driving location where the vehicle to be tested is currently located, each scene label includes one or more scene elements, and at least one target scene element can be selected according to the driving information, and the target scene elements are combined, and the obtained sequence is the target driving scene. Before determining the target driving scene, the necessary scene sequence and the abnormal scene sequence are first determined, and the target driving scene sequence is checked according to the necessary scene sequence and the abnormal scene sequence. This solves the problem in the prior art that the autonomous driving scene is difficult to change according to the vehicle test situation, realizes flexible changes to the autonomous driving scene, and improves the efficiency and accuracy of determining the autonomous driving scene.

[0055] Embodiment 3

[0056] Figure 3 This is a structural block diagram of an apparatus for determining an autonomous driving scene provided in the third embodiment of the present invention, which can execute an autonomous driving scene determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 3 As shown, the device specifically includes:

[0057] The label determination module 301 is used to determine at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested;

[0058] An element determination module 302 is used to select a target scene element from the candidate scene elements of the target scene label according to the current driving information of the vehicle to be tested;

[0059] The scene determination module 303 is used to combine the target scene elements to obtain a target driving scene sequence of the vehicle to be tested.

[0060] Optionally, the device further comprises:

[0061] The location determination module is used to obtain the current location information of the vehicle to be tested before determining at least one target scene label associated with the current driving location of the vehicle to be tested, and determine the current driving location of the vehicle to be tested according to the current location information.

[0062] Optionally, the tag determination module 301 is specifically configured to:

[0063] According to the current driving location of the vehicle to be tested, at least one target scene label associated with the current driving location is selected from preset candidate scene labels.

[0064] Optionally, the target scene label includes a static scene label;

[0065] Accordingly, the element determination module 302 is specifically configured to:

[0066] Determine static information of a target path that the vehicle to be tested is to travel based on current driving information of the vehicle to be tested;

[0067] According to the preset association relationship between the static information and the static scene tags, the static scene tags associated with the static information are filtered out from the target scene tags;

[0068] A target scene element is selected from the candidate scene elements of the static scene label.

[0069] Optionally, the target scene label also includes a dynamic scene label;

[0070] Accordingly, the element determination module 302 is further specifically configured to:

[0071] Determining the vehicle behavior of the vehicle to be tested according to the current driving information of the vehicle to be tested;

[0072] According to the preset association relationship between the vehicle behavior and the dynamic scene tag, the dynamic scene tag that matches the vehicle behavior is filtered out from the target scene tags;

[0073] A target scene element is selected from the candidate scene elements of the dynamic scene tag.

[0074] Optionally, the device further comprises:

[0075] A sequence screening module is used to screen out at least one necessary scene element from the target scene label to form a necessary scene sequence, and to screen out at least one abnormal scene element to form an abnormal scene sequence, before selecting a target scene element from the candidate scene elements of the target scene label according to the current driving information of the vehicle to be tested, according to the logical relationship between the candidate scene elements and preset test requirements.

[0076] Optionally, the device further comprises:

[0077] A necessary sequence comparison module, used for comparing the target driving scene sequence with the necessary scene sequence to determine whether the target driving scene sequence contains the necessary scene sequence;

[0078] If not, it is determined that an error occurs in the target driving scene sequence, and the staff is prompted to redetermine the target driving scene sequence;

[0079] An abnormal sequence comparison module is used to compare the target driving scene sequence with the abnormal scene sequence to determine whether the target driving scene sequence contains the abnormal scene sequence;

[0080] If so, it is determined that an error occurs in the target driving scene sequence, and the staff is prompted to redetermine the target driving scene sequence.

[0081] The embodiment of the present invention determines at least one target scene tag from a plurality of pre-set scene tags according to the current driving location of the vehicle to be tested. Each scene tag includes one or more candidate scene elements. According to the driving information, at least one target scene element can be selected. The target scene elements are combined, and the obtained sequence is the target driving scene sequence. This solves the problem in the prior art that the autonomous driving scene is difficult to change arbitrarily according to the vehicle test situation, realizes flexible changes to the autonomous driving scene, and improves the efficiency and accuracy of determining the autonomous driving scene.

[0082] Embodiment 4

[0083] Figure 4 1 is a schematic diagram of a structure of a device for determining an autonomous driving scene provided by a fourth embodiment of the present invention. The device for determining an autonomous driving scene may be a computer device. Figure 4 A block diagram of an exemplary computer device 400 suitable for use in implementing embodiments of the present invention is shown. Figure 4The computer device 400 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0084] like Figure 4 As shown, the computer device 400 is in the form of a general computing device. The components of the computer device 400 may include, but are not limited to: one or more processors or processing units 401, a system memory 402, and a bus 403 connecting different system components (including the system memory 402 and the processing unit 401).

[0085] Bus 403 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0086] Computer device 400 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 400, including volatile and non-volatile media, removable and non-removable media.

[0087] System memory 402 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 404 and / or cache memory 405. Computer device 400 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 406 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 403 via one or more data medium interfaces. Memory 402 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0088] A program / utility 408 having a set (at least one) of program modules 407 may be stored, for example, in memory 402, such program modules 407 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 407 generally perform the functions and / or methods of the embodiments described herein.

[0089] The computer device 400 may also communicate with one or more external devices 409 (e.g., keyboard, pointing device, display 410, etc.), may also communicate with one or more devices that enable a user to interact with the computer device 400, and / or communicate with any device that enables the computer device 400 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via input / output (I / O) interface 411. Furthermore, the computer device 400 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) via network adapter 412. As shown, the network adapter 412 communicates with other modules of the computer device 400 via bus 403. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0090] The processing unit 401 executes various functional applications and data processing by running the program stored in the system memory 402, for example, a method for determining an autonomous driving scenario provided by an embodiment of the present invention, including:

[0091] Determining, according to a current driving location of the vehicle to be tested, at least one target scene label associated with the current driving location;

[0092] Selecting a target scene element from candidate scene elements of the target scene label according to current driving information of the vehicle to be tested;

[0093] The target scene elements are combined to obtain a target driving scene sequence for the vehicle to be tested.

[0094] Embodiment 5

[0095] Embodiment 5 of the present invention further provides a storage medium containing computer executable instructions, on which a computer program is stored. When the program is executed by a processor, a method for determining an autonomous driving scenario provided in an embodiment of the present invention is implemented, including:

[0096] Determining, according to a current driving location of the vehicle to be tested, at least one target scene label associated with the current driving location;

[0097] Selecting a target scene element from candidate scene elements of the target scene label according to current driving information of the vehicle to be tested;

[0098] The target scene elements are combined to obtain a target driving scene sequence for the vehicle to be tested.

[0099] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0100] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0101] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0102] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0103] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining an autonomous driving scenario, characterized in that: include: Determining, according to a current driving location of the vehicle to be tested, at least one target scene label associated with the current driving location; Selecting a target scene element from candidate scene elements of the target scene label according to current driving information of the vehicle to be tested; Combining the target scene elements according to a preset arrangement to obtain a target driving scene sequence for the vehicle to be tested; Determining at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested, including: According to the current driving location of the vehicle to be tested, selecting at least one target scene label associated with the current driving location from preset candidate scene labels; Wherein, the target scene label includes a static scene label; Accordingly, according to the current driving information of the vehicle to be tested, a target scene element is selected from the candidate scene elements of the target scene label, including: Determine static information of a target path that the vehicle to be tested is to travel based on current driving information of the vehicle to be tested; According to the preset association relationship between the static information and the static scene tags, the static scene tags associated with the static information are filtered out from the target scene tags; A target scene element is selected from the candidate scene elements of the static scene label.

2. The method according to claim 1, characterized in that Before determining at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested, the method further includes: The current position information of the vehicle to be tested is obtained, and the current driving location of the vehicle to be tested is determined according to the current position information.

3. The method according to claim 1, characterized in that The target scene label also includes a dynamic scene label; Accordingly, according to the current driving information of the vehicle to be tested, the target scene element is selected from the candidate scene elements of the target scene label, and further includes: Determining the vehicle behavior of the vehicle to be tested according to the current driving information of the vehicle to be tested; According to the preset association relationship between the vehicle behavior and the dynamic scene tag, the dynamic scene tag that matches the vehicle behavior is filtered out from the target scene tags; A target scene element is selected from the candidate scene elements of the dynamic scene tag.

4. The method according to claim 1, characterized in that Before selecting a target scene element from the candidate scene elements of the target scene label according to the current driving information of the vehicle to be tested, the method further includes: According to the logical relationship between the candidate scene elements and the preset test requirements, at least one necessary scene element is screened out from the target scene label to form a necessary scene sequence, and at least one abnormal scene element is screened out to form an abnormal scene sequence.

5. The method according to claim 4, characterized in that After combining the target scene elements to obtain the target driving scene sequence of the vehicle to be tested, the method further includes: Comparing the target driving scene sequence with a necessary scene sequence to determine whether the target driving scene sequence contains the necessary scene sequence; If not, it is determined that an error occurs in the target driving scene sequence, and the staff is prompted to redetermine the target driving scene sequence; Comparing the target driving scene sequence with an abnormal scene sequence to determine whether the target driving scene sequence contains the abnormal scene sequence; If so, it is determined that an error occurs in the target driving scene sequence, and the staff is prompted to redetermine the target driving scene sequence.

6. A device for determining an automatic driving scenario, characterized in that: include: A label determination module, used to determine at least one target scene label associated with the current driving location according to the current driving location of the vehicle to be tested; An element determination module, used for selecting a target scene element from the candidate scene elements of the target scene label according to the current driving information of the vehicle to be tested; A scene determination module, used to combine the target scene elements according to a preset arrangement to obtain a target driving scene sequence of the vehicle to be tested; The label determination module is specifically used for: According to the current driving location of the vehicle to be tested, selecting at least one target scene label associated with the current driving location from preset candidate scene labels; Wherein, the target scene label includes a static scene label; Accordingly, the element determination module is specifically used to: Determine static information of a target path that the vehicle to be tested is to travel based on current driving information of the vehicle to be tested; According to the preset association relationship between the static information and the static scene tags, the static scene tags associated with the static information are filtered out from the target scene tags; A target scene element is selected from the candidate scene elements of the static scene label.

7. A device for determining an autonomous driving scenario, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for determining the autonomous driving scenario as described in any one of claims 1-5 is implemented.

8. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the method for determining an autonomous driving scenario as described in any one of claims 1 to 5.

Images