Data processing method and related apparatus

Abstract

A data processing method and a related apparatus, which are applied to the technical field of connected vehicles. The method comprises: acquiring information of a static element in a target driving scenario; on the basis of the information of the static element, determining danger information present in the target driving scenario, the danger information being used for indicating collisions of a moving object in the target driving scenario; and on the basis of the danger information present in the target driving scenario, determining the degree of complexity of the target driving scenario, the degree of complexity of the target driving scenario reflecting the degree of impact of the target driving scenario on driving safety. For static scenarios, the present application provides a complexity degree classification solution of static scenarios, and achieves decoupling of static scenarios and dynamic scenarios, thus helping to improve the flexibility of classifying danger levels of scenarios.

Description

Data processing method and related device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on January 17, 2024, with application number 202410070924.2 and application name “Data Processing Method and Related Devices”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of connected vehicle technology, and in particular to a data processing method and related devices. Background Art

[0003] Scenario-based autonomous driving simulation testing is an essential component of intelligent vehicle testing and evaluation, offering the advantages of low cost and high efficiency. In scenario-based autonomous driving simulation testing, test scenarios are divided into static and dynamic scenarios. Static scenarios include road conditions, traffic facilities, and weather, while dynamic scenarios include traffic participants, dynamic signage, and communication environments. Currently, the scenario hazard level for autonomous driving is determined by both static and dynamic scenarios. Generally speaking, the scenario hazard level reflects the degree to which different driving environments affect autonomous driving safety. However, this method of determining the scenario hazard level based on both static and dynamic scenarios is inflexible. Summary of the Invention

[0004] The embodiments of the present application provide a data processing method and related devices, which can improve the flexibility of dividing scene danger levels.

[0005] The present application is introduced below from different aspects. It should be understood that the implementation methods and beneficial effects of the following different aspects can be referenced to each other.

[0006] In a first aspect, an embodiment of the present application provides a data processing method, which is executed by a terminal. The terminal may be the terminal itself, or a unit, circuit, or module (such as a chip) in the terminal with corresponding functions. This application does not limit this. The method includes:

[0007] Obtain information about static elements in the target driving scene;

[0008] determining, based on the information of the static elements, danger information present in the target driving scene, the danger information being used to indicate a collision situation of a moving object in the target driving scene;

[0009] The complexity of the target driving scene is determined based on the danger information present in the target driving scene. The complexity of the target driving scene reflects the degree of influence of the target driving scene on driving safety.

[0010] The embodiment of the present application provides a complexity division scheme for static scenes, which can improve the flexibility of the division of scene danger levels. Specifically, the danger information present in the target driving scene can be determined based on the information of the static elements in the target driving scene, and then the complexity of the target driving scene can be determined based on the danger information present in the target driving scene. Generally speaking, the higher the scene complexity of the vehicle driving scene, the greater the impact of the vehicle driving scene on driving safety. Optionally, by executing the complexity division scheme for static scenes of the present application, it is also beneficial to the subsequent rapid identification and screening of scenes of different complexities for autonomous driving testing, etc., thereby improving the efficiency of scene screening.

[0011] In a possible implementation manner, the danger information present in the target driving scene includes information of a collision point in the target driving scene;

[0012] The determining of the danger information present in the target driving scene according to the information of the static element includes:

[0013] Determining a physical collision point in the target driving scene based on information of the static element, where the physical collision point is a merging point of lanes or an intersection of driving paths;

[0014] Information about the collision point in the target driving scene is determined according to the physical collision point in the target driving scene.

[0015] In this implementation, the danger information present in the target driving scene may refer to the information of the collision points in the target driving scene, such as the number of collision points or the density of collision points. Specifically, the physical collision points in the target driving scene may be determined first, and then the information of the collision points in the target driving scene may be determined based on the physical collision points in the target driving scene. Among them, the physical collision points in a certain scene may refer to points where vehicles may collide due to the morphology or topological expression of the road in a static road environment (without considering dynamic factors, traffic control factors, etc.). For example, the physical collision point may be the confluence point of the lane or the intersection of the driving path.

[0016] In a possible implementation, the information of the collision points includes the number of collision points;

[0017] The determining of information of the collision point in the target driving scene according to the physical collision point in the target driving scene includes:

[0018] determining the number of physical collision points in the target driving scene as the number of collision points in the target driving scene; or,

[0019] Rasterizing the collision area where the physical collision point is located to obtain logical collision points in the target driving scene; wherein one logical collision point is associated with at least one physical collision point, and the logical collision point is a collision risk point in an adjacent area of ​​the collision area;

[0020] The number of the logical collision points is determined as the number of collision points in the target driving scene.

[0021] In this implementation, if the target driving scenario is a ramp scenario, the number of physical collision points can generally be directly determined as the number of collision points in the target driving scenario. If the target driving scenario is an intersection scenario, it is generally necessary to first rasterize the collision area where the physical collision points are located to obtain the logical collision points in the target driving scenario, and then determine the number of logical collision points as the number of collision points in the target driving scenario. It should be understood that the logical collision point is generally the location with the greatest collision risk in the vicinity of the physical collision point.

[0022] In one possible implementation, the complexity of the target driving scenario is indicated by a complexity level;

[0023] The determining the complexity of the target driving scene according to the danger information present in the target driving scene includes:

[0024] The complexity level of the target driving scene is determined according to the number of collision points and a plurality of preset collision point number ranges, wherein one collision point number range corresponds to one complexity level.

[0025] This implementation method determines the target driving scenario's complexity level based on the number of collision points and multiple preset collision point ranges, offering high operability and applicability. Specifically, the complexity level corresponding to the collision point range to which the number of collision points in the target driving scenario falls can be determined as the target driving scenario's complexity level.

[0026] In a possible implementation, determining the complexity level of the target driving scenario based on the number of collision points and a plurality of preset collision point number ranges includes:

[0027] A first collision point number range to which the collision point number belongs is determined, and a complexity level corresponding to the first collision point number range is determined as the complexity level of the target driving scene, wherein the first collision point number range is one of the multiple collision point number ranges.

[0028] In a possible implementation manner, the plurality of collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs; or,

[0029] The multiple collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs and the region where the target driving scene is located.

[0030] Regarding the setting of collision point number ranges, 1. Multiple collision point number ranges can be set regardless of region and scene type, which is a universal setting; 2. Multiple collision point number ranges can also be set based on scene type, which means the collision point number range is related to the scene type; 3. Multiple collision point number ranges can also be set based on region and scene type, which means the collision point number range is related to the region and scene type. These collision point number range setting methods are highly flexible and help enhance the applicability of the solution.

[0031] In a possible implementation, obtaining information about static elements in the target driving scene includes:

[0032] The information of static elements in the target driving scene is obtained from the high-precision map.

[0033] In this implementation, preferably, the present application can obtain information about static elements in the target driving scene from a high-precision map. Alternatively, information about static elements in the target driving scene can also be obtained from a vector map and a satellite cloud map.

[0034] In a possible implementation, the target driving scenario includes an ordinary road scenario, an intersection scenario, a ramp scenario, a roundabout scenario, a toll station scenario, a tunnel scenario, an overpass scenario, an elevated road scenario, or a continuous overpass scenario.

[0035] It should be understood that the target driving scene may be other driving scenes in addition to the nine scenes listed above, such as a mining area.

[0036] In a possible implementation, the static elements include one or more of an intersection surface, a road, an obstacle, a road surface marking, a virtual lane, or a traffic facility.

[0037] In a possible implementation, the virtual lane is determined based on lane turning information and angle information between an entrance and an exit.

[0038] In a possible implementation, the information of the static element includes one or more of element border, element position, or element size.

[0039] In one possible implementation, the method further includes:

[0040] Obtain autonomous driving test requirements;

[0041] Determine whether to use the target driving scenario as a test scenario based on the complexity of the target driving scenario and the autonomous driving test requirements.

[0042] In this implementation, after determining the complexity of the target driving scene, it can also be determined whether to use the target driving scene as a test scene based on the autonomous driving test requirements. For example, the tester can input / select the autonomous driving test requirements on the user interface / visual interface. For example, the autonomous driving test requirement may be to use a scene with a complexity level of complexity 1 as the test scene. If the complexity of the target driving scene is complexity level 1, then the target driving scene can be used as an autonomous driving test scene; if the complexity of the target driving scene is not complexity level 1, then the target driving scene cannot be used as an autonomous driving test scene.

[0043] In a second aspect, an embodiment of the present application provides a data processing device, the device comprising:

[0044] An acquisition unit, used to acquire information of static elements in a target driving scene;

[0045] a processing unit, configured to determine, based on information about the static elements, hazard information present in the target driving scene, wherein the hazard information is used to indicate a collision condition of a moving object in the target driving scene;

[0046] The processing unit is used to determine the complexity of the target driving scene based on the danger information existing in the target driving scene. The complexity of the target driving scene reflects the impact of the target driving scene on driving safety.

[0047] In a possible implementation, the hazard information present in the target driving scene includes information about collision points in the target driving scene; and when determining the hazard information present in the target driving scene based on the information of the static element, the processing unit is specifically configured to:

[0048] Determining a physical collision point in the target driving scene based on information of the static element, where the physical collision point is a merging point of lanes or an intersection of driving paths;

[0049] Information about the collision point in the target driving scene is determined according to the physical collision point in the target driving scene.

[0050] In a possible implementation, the collision point information includes the number of collision points; and when determining the collision point information in the target driving scene based on the physical collision points in the target driving scene, the processing unit is specifically configured to:

[0051] determining the number of physical collision points in the target driving scene as the number of collision points in the target driving scene; or,

[0052] Rasterizing the collision area where the physical collision point is located to obtain logical collision points in the target driving scene; wherein one logical collision point is associated with at least one physical collision point, and the logical collision point is a collision risk point in an adjacent area of ​​the collision area;

[0053] The number of the logical collision points is determined as the number of collision points in the target driving scene.

[0054] In one possible implementation, the complexity of the target driving scene is indicated by a complexity level; when determining the complexity of the target driving scene based on the hazard information present in the target driving scene, the processing unit is specifically configured to:

[0055] The complexity level of the target driving scene is determined according to the number of collision points and a plurality of preset collision point number ranges, wherein one collision point number range corresponds to one complexity level.

[0056] In a possible implementation manner, when determining the complexity level of the target driving scenario according to the number of collision points and a plurality of preset collision point number ranges, the processing unit is specifically configured to:

[0057] A first collision point number range to which the collision point number belongs is determined, and a complexity level corresponding to the first collision point number range is determined as the complexity level of the target driving scene, wherein the first collision point number range is one of the multiple collision point number ranges.

[0058] In a possible implementation manner, the plurality of collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs; or,

[0059] The multiple collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs and the region where the target driving scene is located.

[0060] In a possible implementation, when acquiring information of static elements in the target driving scene, the acquiring unit is specifically configured to:

[0061] The information of static elements in the target driving scene is obtained from the high-precision map.

[0062] In a possible implementation, the target driving scenario includes an ordinary road scenario, an intersection scenario, a ramp scenario, a roundabout scenario, a toll station scenario, a tunnel scenario, an overpass scenario, an elevated road scenario, or a continuous overpass scenario.

[0063] In a possible implementation, the static elements include one or more of an intersection surface, a road, an obstacle, a road surface marking, a virtual lane, or a traffic facility.

[0064] In a possible implementation, the virtual lane is determined based on lane turning information and angle information between an entrance and an exit.

[0065] In a possible implementation, the information of the static element includes one or more of element border, element position, or element size.

[0066] In a possible implementation, the processing unit is further configured to:

[0067] Obtain autonomous driving test requirements;

[0068] Determine whether to use the target driving scenario as a test scenario based on the complexity of the target driving scenario and the autonomous driving test requirements.

[0069] In a third aspect, embodiments of the present application provide a data processing device comprising a processor. The processor is coupled to a memory and can be configured to execute instructions in the memory to implement the method of the first aspect and any possible implementation method described above. Optionally, the data processing device further comprises a memory. Optionally, the data processing device further comprises a communication interface, the processor being coupled to the communication interface.

[0070] In a fourth aspect, embodiments of the present application provide a data processing device, comprising: a logic circuit and a communication interface. The communication interface is configured to receive or send information; the logic circuit is configured to receive or send information via the communication interface, so that the data processing device executes the method of the first aspect and any possible implementation method described above.

[0071] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which is used to store a computer program (also referred to as code, or instructions); when the computer program is run on a computer, the method of the above-mentioned first aspect and any possible implementation method is implemented.

[0072] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes: a computer program (also referred to as code, or instructions); when the computer program is run, it enables the computer to execute the method of the above-mentioned first aspect and any possible implementation method.

[0073] In a seventh aspect, an embodiment of the present application provides a chip, comprising a processor configured to execute instructions. When the processor executes the instructions, the chip performs the method of the first aspect and any possible implementation method described above. Optionally, the chip further comprises a communication interface configured to receive or send signals.

[0074] In an eighth aspect, an embodiment of the present application provides a vehicle side, which includes at least one data processing device as described in the second aspect, or the data processing device as described in the third aspect, or the data processing device as described in the fourth aspect, or the chip as described in the seventh aspect.

[0075] In a ninth aspect, an embodiment of the present application provides a server, which is used to execute the method of the above-mentioned first aspect and any possible implementation method.

[0076] In addition, in the process of executing the method described in the first aspect and any possible embodiment, the process of sending information and / or receiving information in the above method can be understood as the process of the processor outputting information and / or the process of the processor receiving input information. When outputting information, the processor can output the information to the transceiver (or communication interface, or sending module) so that it can be transmitted by the transceiver. After the information is output by the processor, it may also need to undergo other processing before it reaches the transceiver. Similarly, when the processor receives input information, the transceiver (or communication interface, or sending module) receives the information and inputs it into the processor. Furthermore, after the transceiver receives the information, the information may need to undergo other processing before it is input into the processor.

[0077] Based on the above principles, for example, the sending of information mentioned in the above method can be understood as the processor outputting information. For another example, the receiving of information can be understood as the processor receiving input information.

[0078] Optionally, for the operations such as transmission, sending and receiving involved in the processor, if there is no special explanation, or if they do not conflict with their actual functions or internal logic in the relevant description, they can be more generally understood as processor output, reception, input and other operations.

[0079] Optionally, in the process of executing the method described in the first aspect and any possible embodiment, the processor may be a processor specifically used to execute these methods, or a processor that executes these methods by executing computer instructions in a memory, such as a general-purpose processor. The memory may be a non-transitory memory, such as a read-only memory (ROM), which may be integrated with the processor on the same chip or may be separately provided on different chips. The embodiment of the present application does not limit the type of memory and the configuration of the memory and the processor.

[0080] In a possible implementation, the at least one memory is located outside the device.

[0081] In yet another possible implementation, the at least one memory is located within the device.

[0082] In another possible implementation, part of the at least one memory is located inside the device, and another part of the memory is located outside the device.

[0083] In this application, the processor and the memory may also be integrated into one device, that is, the processor and the memory may also be integrated together. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] FIG1 is a schematic diagram of lane turning judgment provided by an embodiment of the present application;

[0085] FIG2 is a flow chart of a data processing method according to an embodiment of the present application;

[0086] FIG3 is a schematic diagram of a high-speed ramp scenario provided by an embodiment of the present application;

[0087] FIG4 is a schematic diagram of a lane merging point and an intersection of a driving path provided in an embodiment of the present application;

[0088] FIG5 is a schematic diagram of an intersection scene provided in an embodiment of the present application;

[0089] FIG6 is a schematic diagram of logical collision points and physical collision points provided by an embodiment of the present application;

[0090] FIG7 is a schematic diagram of dividing the number of collision points into different ranges regardless of region and scene type according to an embodiment of the present application;

[0091] FIG8 is a schematic diagram of dividing the number of collision points by scene type according to an embodiment of the present application;

[0092] FIG9 is a schematic diagram of dividing the number of collision points by region and scene type according to an embodiment of the present application;

[0093] FIG10 is a schematic structural diagram of a data processing device provided in an embodiment of the present application;

[0094] FIG11 is a schematic structural diagram of a data processing device provided in an embodiment of the present application;

[0095] FIG12 is a schematic diagram of the structure of a chip provided in an embodiment of the present application. DETAILED DESCRIPTION

[0096] The embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0097] The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and drawings of this application are used to distinguish between different objects, not to describe a particular order. In addition, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0098] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0099] As used in this specification, the terms "component," "module," "system," and the like are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and a computing device can be a component. One or more components can reside in a process and / or an execution thread, and a component can be located on a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures stored thereon. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0100] First, the application scenarios of this application are introduced. This application provides a data processing method, through which the complexity of static scenes is divided, so that in the subsequent autonomous driving simulation test, scenes of different complexities can be quickly identified and screened as needed for test applications. In addition, the complexity of the static scenes involved in this application can also be used to judge the ODD. For example, a scene with a higher complexity at an intersection can be set as not within the ODD range, but as a boundary scene of the ODD. Optionally, the complexity of the static scenes involved in this application can also provide a reference for the overall complexity classification modeling of autonomous driving scenes.

[0101] The data processing method provided in this application can be executed by a data processing device, which can be a network-side device or a terminal device, or a chip inside a network-side device or a chip inside a terminal device. The network-side device includes a computing platform or a server, etc. The specific deployment form of the computing platform and the server is not limited in this application. For example, it can be a cloud deployment (such as a cloud platform), or it can be an independent computer device or chip, etc. The terminal device includes a hardware device that supports scientific computing, such as a vehicle, a personal computer, a server, a mobile terminal, an embedded device, etc.

[0102] In order to facilitate understanding of the contents of this solution, some of the terms in this application are explained below to facilitate understanding by those skilled in the art. This part is only for ease of understanding and cannot be regarded as a specific limitation of this application.

[0103] 1. High-definition map (HD MAP)

[0104] High-definition maps, also known as high-definition or high-precision maps, are a key capability for autonomous driving. They will effectively complement existing sensors and enhance the safety of autonomous driving decisions. Compared to traditional navigation maps, high-definition maps for autonomous driving have higher requirements in various aspects and can be integrated with sensors and algorithms to support decision-making. High-definition maps consist of static and dynamic layers. The static layer primarily refers to objects or targets that remain static within the HD map. These can include map elements such as road geometry, road markings, traffic signs, and obstacles. The dynamic layer contains dynamic information that is or may change during the autonomous driving process. This refers to dynamically changing event information, such as changing traffic flow, real-time road conditions, road repairs or road closures, and other data that requires real-time push or updates.

[0105] 2. Operational design domain (ODD)

[0106] The ODD, also known as the Design Operating Range (ODR) or Design Operating Conditions (DOC), refers to the external environmental conditions for the functional operation of a driving automation system when it is designed. In layman's terms, this refers to the operating conditions for a specific automated driving function. For example, the DOD may include, but is not limited to, road conditions, traffic conditions, weather conditions, and lighting conditions.

[0107] 3. Operational design conditions (ODC)

[0108] A general term for the various conditions applicable to the functional operation of a driving automation system that are determined during its design, including the designed operating range, vehicle status, driver and passenger status, and other necessary conditions.

[0109] 4. Scene

[0110] Currently, scenes (or scene types) mainly include ordinary road scenes, intersection scenes, ramp scenes, roundabout scenes, toll booth scenes, tunnel scenes, overpass scenes, elevated road scenes, or continuous overpass scenes, etc. Among them, different classification labels can exist under each scene type, and each classification label can have multiple value ranges. For example, taking ordinary roads as an example, ordinary roads can have four classification labels, such as road shape, road grade, whether there is an auxiliary road, and whether there is a gap. The value range of road shape can include straight roads, curves, ramps, etc.; the value range of road grade can include highways, open roads, etc.; the value range of whether there is an auxiliary road can include yes (i.e., there is an auxiliary road) and no (i.e., there is no auxiliary road); the value range of whether there is a gap can include yes (i.e., there is a gap) and no (i.e., there is no gap).

[0111] Table 1

[0112] 5. Virtual Lanes

[0113] Lane markings, as road elements, guide the path planning of autonomous vehicles, ensuring safety, comfort, and intelligence during autonomous driving. At intersections, due to the complex road structure and the lack of clear physical lane markings, vehicle behavior varies significantly, making it more difficult to accurately predict the future trajectories of other vehicles. The HD map in the autonomous driving system adds virtual lanes (or virtual lane markings) at the intersection, constraining vehicles to follow these virtual lane markings when passing through the intersection. Accordingly, the autonomous driving system uses the virtual lane markings in the HD map as the future trajectories of other vehicles at the intersection.

[0114] Currently, virtual lanes include one or more of the following: left-turn virtual lanes, right-turn virtual lanes, straight-ahead virtual lanes, and U-turn virtual lanes. Generally speaking, virtual lane lines within an intersection can be calculated based on lane turning information and the angle between entering and exiting the intersection. The specific direction judgment principle of lane connection is shown in (a) of Figure 1. Taking clockwise as the positive direction, when the angle θ between the entrance and exit is in [315°, 360°) or [0°, 45°), it indicates straight ahead; when the angle θ between the entrance and exit is in [45°, 135°), it indicates a right turn; when the angle θ between the entrance and exit is in [135°, 180°), it indicates a right turn; when the angle θ between the entrance and exit is in [180°, 225°), it indicates a U-turn; when the angle θ between the entrance and exit is in [225°, 315°), it indicates a left turn. Generally speaking, the road for a left turn includes a left-turn exit lane and / or a left-turn virtual lane, the road for a right turn includes a right-turn exit lane and / or a right-turn virtual lane, the road for going straight includes a straight-through exit lane and / or a straight-through virtual lane, and the road for a U-turn includes a U-turn exit lane and / or a U-turn virtual lane. For example, in the left-turn scenario shown in Figure 1(b), the angle between the entrance and exit is 300°.

[0115] Automobile safety has always been a focus of widespread attention from automobile companies and scientific research institutions. The development of autonomous driving technology has created a demand for research related to automobile safety, which has led to autonomous driving testing and evaluation research becoming a hot topic. Establishing and improving testing and evaluation methods is crucial to improving the efficiency of autonomous vehicle R&D and ensuring traffic safety.

[0116] Scenario-based autonomous driving simulation testing is an indispensable part of smart car testing and evaluation. Simulation testing has the advantages of low cost and high efficiency. During the autonomous driving process testing, the test scenarios are divided into static scenarios and dynamic scenarios. Static scenarios include road environment, traffic facilities, weather, etc., and dynamic scenarios include traffic participants, dynamic indication facilities, communication environment, etc.

[0117] It should be understood that the danger level of the traffic environment is related to the complexity of the vehicle's driving environment, and also includes various factors such as the road, weather, lighting, and surrounding pedestrians and vehicles. Currently, the scene danger level of autonomous driving is determined by both static and dynamic scenarios. Generally speaking, the scene danger level reflects the degree to which different driving environments affect autonomous driving safety. However, this current method of determining the scene danger level based on both static and dynamic scenarios is not flexible enough.

[0118] Based on this, the present application proposes a data processing method, which decouples static scenes and dynamic scenes, and can construct a complexity level for static scenes alone, thereby improving the flexibility of scene hazard level classification.

[0119] The data processing method and related devices provided by this application are described in detail below:

[0120] Please refer to Figure 2, which is a flow chart of the data processing method provided by an embodiment of the present application. As shown in Figure 2, the data processing method includes the following steps S201 to S203. The method schematically illustrates the cloud platform as the execution subject. It should be noted that Figure 2 is a schematic flow chart of an embodiment of the method of the present application, showing the detailed communication steps or operations of the method, but these steps or operations are only examples. The embodiment of the present application can also perform other operations or variations of the various operations in Figure 2. In addition, the various steps in Figure 2 can be executed in a different order from that presented in Figure 2, and it may not be necessary to execute all the operations in Figure 2. Among them:

[0121] S201. The cloud platform obtains information about static elements in a target driving scene.

[0122] Exemplarily, the target driving scene involved in the embodiments of the present application can be any one of ordinary road scenes, intersection scenes, ramp scenes, roundabout scenes, toll booth scenes, tunnel scenes, overpass scenes, elevated road scenes, or continuous overpass scenes, or the target driving scene can also be a combination of two or more of the above scenes, etc., and the present application does not limit this. For the understanding of various types of scenes, please refer to the relevant descriptions in the aforementioned term explanations, which will not be repeated here. It should be understood that in addition to the 9 scenes listed above, the target driving scene can also be other driving scenes, such as scenes in mining areas, etc., which are not limited to this.

[0123] It should be understood that the static elements in the embodiments of the present application include one or more of an intersection surface, a road, an obstacle, a road marking, a virtual lane, or a traffic facility. The information of the static elements includes one or more of the element boundary, the element position, or the element size. For example, taking the static element as an obstacle, the information of the obstacle may include information such as the boundary of the obstacle, the location of the obstacle, and the size of the obstacle. For another example, taking the intersection surface as an example, the information of the intersection surface includes information such as the boundary of the intersection surface and the area of ​​the intersection surface.

[0124] For example, taking the target driving scenario as an intersection scene, the intersection scene may include the intersection surface, lane turning information, traffic signs, traffic lights, the relationship between the intersection surface and the road / lane, the relationship between the intersection surface and the stop line, crosswalk, obstacles, virtual lanes and other elements / static elements.

[0125] For example, taking a ramp as the target driving scenario, a ramp scenario can include elements / static elements such as exit ramps, entry ramps, and connecting ramps. Generally speaking, a ramp entrance refers to a situation where there is no preceding road or the preceding road is a regular road and the following road is a highway; a ramp exit refers to a situation where there is no following road or the following road is a regular road and the preceding road is a highway; and a connecting ramp refers to a highway junction where both the preceding and following roads are highways. For example, see Figure 3 (a) and (b).

[0126] In one possible implementation, information about static elements in the target driving scene can be obtained from a high-precision map. Generally speaking, a high-precision map includes road-level information and lane-level information. Among them, road-level information can provide navigation information for users to meet the navigation needs of driving routes. For example, road-level information can include: the number of lanes on the current road, the speed limit information of the current road, turn information, etc. Lane-level information is used to indicate lane information in a road network environment, such as lane curvature, lane heading, lane center axis, lane width, lane markings, lane speed limit, lane splitting, and lane merging. In addition, the lane line conditions between lanes (dashed line, solid line, single line and double line), lane line color (white, yellow), road median, median material, road arrows, text content and location, etc. can also be included in the lane-level information.

[0127] Specifically, high-precision map segments (here, high-precision map segments can also be understood as high-precision map segment files) of the target driving scene can be extracted from existing high-precision maps and processed. Here, existing high-precision maps can refer to existing high-precision maps obtained based on data collected from real / actual roads. For example, data acquisition equipment such as lidar, cameras, global navigation satellite systems (GNSS) / inertial measurement units (IMUs), data storage, and computer equipment can be deployed on a collection vehicle to collect and store all information about the surrounding environment while the collection vehicle is driving. The collected data is automatically semantically recognized, including lane lines, traffic signs, vehicle types, etc., and vectorized and annotated according to certain data specifications to establish topological relationships and generate virtual lane lines at intersections, thereby achieving high-precision map construction. Optionally, the constructed high-precision map can be stored in cloud storage. When the complexity of the target driving scene needs to be divided, the cloud platform can obtain high-precision map data from the cloud storage and process the obtained high-precision map data.

[0128] It should be understood that the high-precision map referred to in this application can be a high-precision map within a specific geographical area, such as a high-precision map of a country, a high-precision map of a city, or a high-precision map of a district or county, etc., and this application does not impose any restrictions on this. Optionally, the user can enter / select a specific geographical area on the user interface / visualization interface, and then extract the target driving scene for the specific geographical area selected by the user and perform scene complexity classification.

[0129] It should be noted that the user interface / visualization interface involved in the embodiments of the present application can be the user interface / visualization interface of the client. The client described here can be other devices or software and hardware independent of the cloud platform, which interacts with the cloud platform through a communication port. Optionally, the user interface / visualization interface involved in the embodiments of the present application can also be the user interface / visualization interface that comes with the cloud platform, that is, the client is integrated with the cloud platform. Therefore, the interaction between the user interface / visualization interface and the cloud platform is internally implemented, which is determined according to the actual scenario and is not limited here.

[0130] For example, assuming that the target driving scene is an "intersection", the existing high-precision map can be detected, and the high-precision map segment including the "intersection" can be extracted as a data source. Then, the extracted high-precision map segment is processed to obtain the information of the static elements contained in the high-precision map segment. Generally speaking, when extracting the high-precision map segment corresponding to the intersection scene, the intersection surface, the roads and lanes associated with the intersection surface, and the surrounding traffic facilities in the high-precision map can be extracted as the high-precision map segment corresponding to the intersection scene. For example, the extraction principle of the high-precision map segment corresponding to the intersection scene is: 1. Intersection scene range: 100 meters from the extension line of the entrance and exit roads; 2. Full element coverage: obtain roads, lanes, lane lines, lights, poles, signs, obstacles, road signs, stop lines, virtual lanes and other elements through the intersection association relationship; 3. The dedicated lanes around the intersection are complete, including left and right turn lanes, non-motorized vehicle lanes, etc.

[0131] For another example, assuming the target driving scenario is a "highway ramp," existing high-precision maps can be inspected, and high-precision map segments containing "highway ramps" can be extracted as the data source. These extracted high-precision map segments can then be processed to obtain information about the static elements contained within them. Generally speaking, when extracting high-precision map segments corresponding to ramp scenarios, ramp exits, ramp entrances, connecting ramps, and so on can all be extracted from the high-precision map as high-precision map segments corresponding to the ramp scenario.

[0132] In another possible implementation, information about static elements in the target driving scene can be obtained from existing vector maps and satellite cloud images. Vector maps, such as open-source vector maps, include road-level information such as the number of lanes, speed limits, and turn information. Satellite cloud images, which can be understood as satellite maps, can be used to identify lane-level information such as lane width, number of lanes, lane direction, and lane usage.

[0133] Specifically, vector map segments of the target driving scenario can be extracted from an existing vector map. High-precision map information corresponding to the vector map segments is obtained by performing image detection on the satellite cloud image corresponding to the vector map segments. The high-precision map information is then used to convert the vector map segments into high-precision map segments, which are then processed.

[0134] For ease of understanding, the following text mainly uses high-precision maps as an example for schematic explanation.

[0135] S202: The cloud platform determines the danger information in the target driving scene based on the information of the static elements.

[0136] The hazard information indicates the potential collision of moving objects within the target driving scene. For example, the hazard information within the target driving scene includes information about collision points within the target driving scene. The collision point information includes the number of collision points or the density of collision points. For ease of understanding, the following description primarily uses the number of collision points as an example.

[0137] In some feasible implementations, determining the hazard information present in the target driving scene based on the information of the static elements includes: determining the physical collision point in the target driving scene based on the information of the static elements, and then determining the information of the collision point in the target driving scene based on the physical collision point in the target driving scene. Generally speaking, the physical collision point is the location where the vehicle may collide due to the morphology or topological expression of the road. For example, the physical collision point can be the confluence point of the lane or the intersection / junction point of the driving path (or virtual lane), as shown in (a) and (b) of Figure 4, respectively, which are schematic diagrams of the confluence point of the lane and the intersection point of the driving path.

[0138] For example, taking the intersection scene as an example, the intersection scene can be divided into three areas: outside the intersection, at the intersection boundary, and inside the intersection. For the outside and intersection boundaries, since there are actual physical lane boundaries in these two areas, the confluence of the lanes can be used as the physical collision point. For the inside of the intersection, since there are no actual physical lane boundaries, it is necessary to construct a virtual lane topology and cluster the virtual lanes into driving paths according to the driving direction. The intersection point of the driving paths is then used as the physical collision point. Optionally, for the inside of the intersection, the intersection of the virtual lanes can also be directly used as the physical collision point, as shown in Figure 5.

[0139] In one possible implementation, determining information about collision points in the target driving scene based on physical collision points in the target driving scene includes determining the number of physical collision points in the target driving scene as the number of collision points in the target driving scene. In other words, the number of collision points is equal to the number of physical collision points. For example, in a ramp scenario, the number of physical collision points can be determined as the number of collision points.

[0140] For example, assuming the target driving scenario is a ramp, information about static elements such as the exit ramp, entrance ramp, and connecting ramp can be extracted from the high-definition map fragment corresponding to the ramp. The physical collision point of the ramp can be the merging point of the lanes merging into the ramp. Assuming the number of physical collision points in the ramp scenario is 12, the number of collision points can be determined to be 12.

[0141] In another possible implementation, information about collision points in the target driving scene is determined based on the physical collision points in the target driving scene, including: rasterizing the collision area where the physical collision points are located to obtain logical collision points in the target driving scene, and then determining the number of logical collision points as the number of collision points in the target driving scene. One logical collision point is associated with at least one physical collision point. Generally speaking, a logical collision point is a collision risk point in an area adjacent to the collision area. FIG6 shows a schematic diagram of logical collision points and physical collision points. For example, in a road intersection scenario, the number of logical collision points can be determined as the number of collision points.

[0142] For example, assuming the target driving scenario is an intersection, information on static elements such as exit intersections, entry intersections, and connecting intersections can be extracted from the high-precision map fragment corresponding to the intersection scenario. The physical collision point at the intersection can refer to the confluence point of lanes or the intersection of driving paths (or virtual lanes). Assuming the number of physical collision points in the intersection scenario is 26, as shown in Figure 6, by rasterizing all physical collision points, we can obtain 6 logical collision points as shown in Figure 6, so the number of collision points can be determined to be 6.

[0143] In another possible implementation, information about collision points in the target driving scene is determined based on the physical collision points in the target driving scene, including: clustering each physical collision point, and using the number of cluster points obtained through the clustering process as the number of collision points in the target driving scene.

[0144] S203: The cloud platform determines the complexity of the target driving scene based on the danger information in the target driving scene.

[0145] The complexity of the target driving scene can be indicated by the complexity level. It should be understood that the complexity of the target driving scene reflects the degree of influence of the target driving scene on driving safety. Generally speaking, the higher the complexity of the target driving scene, the greater the degree of influence of the target driving scene on driving safety. In one possible implementation, the scene complexity can be positively correlated with the complexity level, that is, the higher the complexity level, the higher the scene complexity; in another possible implementation, the scene complexity can also be negatively correlated with the complexity level, that is, the higher the complexity level, the lower the scene complexity. For ease of understanding, this application mainly uses the example of a higher complexity level indicating a higher scene complexity for schematic explanation.

[0146] In some feasible implementations, determining the complexity of the target driving scene based on hazard information present in the target driving scene includes determining a complexity level of the target driving scene based on the number of collision points and a plurality of preset collision point number ranges, wherein each collision point number range corresponds to a complexity level. Specifically, a first collision point number range to which the number of collision points belongs can be first determined, and then the complexity level corresponding to the first collision point number range is determined as the complexity level of the target driving scene, where the first collision point number range is one of the plurality of collision point number ranges.

[0147] For example, assume that the multiple collision point number ranges include collision point number range 1, collision point number range 2, and collision point number range 3. Collision point number range 1 corresponds to complexity level 1, collision point number range 2 corresponds to complexity level 2, and collision point number range 3 corresponds to complexity level 3. Assuming that the number of collision points in the target driving scene is included in collision point number range 1, the complexity level of the target driving scene can be determined to be complexity level 1.

[0148] It should be noted that the present application can set multiple collision point number ranges regardless of region and scene type, and then classify the scene complexity level based on the preset multiple collision point number ranges. In other words, the multiple collision point number ranges involved in the embodiments of the present application do not distinguish between regions and scene types, and the set number ranges, or the multiple collision point number ranges involved in the embodiments of the present application, can be applied to all scenes in all regions.

[0149] For example, as shown in FIG7 , it is assumed that the plurality of collision point number ranges include collision point number range 1 , collision point number range 2 , and collision point number range 3 . Among them, the range of the number of collision points 1 is (0, 20], the range of the number of collision points 2 is (20, 40], and the range of the number of collision points 3 is (40, +∞). Among them, the range of the number of collision points 1 corresponds to complexity level 1, the range of the number of collision points 2 corresponds to complexity level 2, and the range of the number of collision points 3 corresponds to complexity level 3. For any scene in any area, its scene complexity can be determined based on these three ranges of the number of collision points. For example, for any ordinary road scene in city A (such as ordinary road 1), if the number of collision points contained in ordinary road 1 is 28, since the number of collision points 28 is contained in (20, 40], the scene complexity of ordinary road 1 in city A can be determined to be complexity level 2. For another example, for any intersection scene in city B (such as intersection 1), if the number of collision points contained in intersection 1 is 18, since the number of collision points 18 is contained in (0, 20], the scene complexity of intersection 1 in city B can be determined to be complexity level 1.

[0150] Alternatively, multiple collision point number ranges may be set for each scene type, and the scene complexity levels may be divided based on the multiple collision point number ranges corresponding to the scene types.

[0151] For example, as shown in Figure 8, for ordinary road scenes, the corresponding collision point number range is 1 to collision point number range 3, where the collision point number range 1 is (0,5], the collision point number range 2 is (5,10], and the collision point number range 3 is (10,+∞). The collision point number range 1 corresponds to complexity level 1, the collision point number range 2 corresponds to complexity level 2, and the collision point number range 3 corresponds to complexity level 3.

[0152] For intersection scenarios, the corresponding collision point number range is 4 to 6, where the collision point number range 4 is (0, 30], the collision point number range 5 is (30, 60], and the collision point number range 6 is (60, +∞). The collision point number range 4 corresponds to complexity level 1, the collision point number range 5 corresponds to complexity level 2, and the collision point number range 6 corresponds to complexity level 3.

[0153] For the ramp scenario, the corresponding collision point number range is 7 to 9, where the collision point number range 7 is (0, 4], the collision point number range 8 is (4, 8], and the collision point number range 9 is (8, +∞). The collision point number range 7 corresponds to complexity level 1, the collision point number range 8 corresponds to complexity level 2, and the collision point number range 9 corresponds to complexity level 3.

[0154] Specifically, for the same scene type, the range of the number of collision points used is the same. For example, for any ordinary road scene in city A (such as ordinary road 1), the range of collision points used is 1 to 3. If the number of collision points contained in ordinary road 1 is 6, since the number of collision points 6 is included in (5,10], it can be determined that the scene complexity of ordinary road 1 in city A is complexity level 2. For another example, for any intersection scene in city B (such as intersection 1), the range of collision points used is 4 to 6. If the number of collision points contained in intersection 1 is The number of collision points is 18. Since the number of collision points 18 is included in (0, 30], the scene complexity of intersection 1 in city B can be determined to be complexity level 1. For another example, for any ramp scene in city B (for example, ramp 1), the collision point number range is 7 to the collision point number range 9. If the number of collision points included in ramp 1 is 4, since the number of collision points 4 is included in (0, 4], the scene complexity of ramp 1 in city B can be determined to be complexity level 1.

[0155] Optionally, multiple collision point ranges can be set based on region and scenario type, allowing for a classification of scene complexity based on the ranges corresponding to specific regions and scenario types. In other words, collision point ranges can be set for different scenario types within different regions. For example, separate collision point ranges can be set for different scenario types within each city.

[0156] For example, as shown in Figure 9, for ordinary road scenes in City A, the corresponding number of collision points ranges from 1 to 3, where collision point range 1 corresponds to complexity level 1, collision point range 2 corresponds to complexity level 2, and collision point range 3 corresponds to complexity level 3. For intersection scenes in City A, the corresponding number of collision points ranges from 4 to 6, where collision point range 4 corresponds to complexity level 1, collision point range 5 corresponds to complexity level 2, and collision point range 6 corresponds to complexity level 3.

[0157] For ordinary road scenarios in City B, the corresponding number of collision points ranges from 7 to 9, with 7 corresponding to complexity level 1, 8 corresponding to complexity level 2, and 9 corresponding to complexity level 3. For intersection scenarios in City B, the corresponding number of collision points ranges from 10 to 12, with 10 corresponding to complexity level 1, 11 corresponding to complexity level 2, and 12 corresponding to complexity level 3.

[0158] Specifically, for the same scene type within the same area, the same range of collision point numbers is used. For example, for any ordinary road scene in City A (e.g., Ordinary Road 1), the collision point number range used is 1 to 3. If the number of collision points contained in Ordinary Road 1 is within the collision point number range 2, then the scene complexity of Ordinary Road 1 in City A can be determined to be Complexity Level 2. For another example, for any ordinary road scene in City B (e.g., Ordinary Road 2), the collision point number range used is 7 to 9. If the number of collision points contained in Ordinary Road 2 is within the collision point number range 8, then the scene complexity of Ordinary Road 2 in City B can be determined to be Complexity Level 2.

[0159] It should be noted that the specific numerical value setting for each collision point number range can be determined based on the actual scenario and is not limited in this application. For example, when separately setting the collision point number range corresponding to different scenario types in each city, the number of scenarios corresponding to each collision point number range can be close to the same. For example, for the three collision point number ranges corresponding to the intersection scene in city A, the numerical settings of the three collision point number ranges are preferably such that the number of intersections in city A belonging to each of the three collision point number ranges is close to the same. For example, assuming that there are a total of 72,202 different intersections in city A, if the three collision point number ranges are set to (0, 29], (29, 59], and (59, +∞), respectively, the number of intersections corresponding to (0, 29] can be 24,052, the number of intersections corresponding to (29, 59] can be 25,000, and the number of intersections corresponding to (59, +∞) can be 23,150. In this case, the numerical settings of (0, 29], (29, 59], and (59, +∞) can be considered as an optimal range setting.

[0160] Optionally, the number of divisions of the collision point number ranges corresponding to different scene types can be the same or different, and there is no limitation on this. For the convenience of description, Figures 7 to 9 above mainly use the example of the same number of divisions of the collision point number ranges corresponding to different scene types, which is 3, as an example.

[0161] Optionally, when the information of the collision point is the density of the collision point, the complexity level of the target driving scene can be determined based on the density of the collision point and a plurality of preset collision point density ranges, where one collision point density range corresponds to one complexity level. For details, please refer to the aforementioned implementation of determining the complexity level of the target driving scene based on the number of collision points and a plurality of preset collision point number ranges when the information of the collision point is the number of collision points, which will not be repeated here.

[0162] Optionally, after determining the complexity of the target driving scene, the cloud platform may also obtain the user's (e.g., tester's) autonomous driving test requirements and determine whether to use the target driving scene as an autonomous driving test scene based on the complexity of the target driving scene and the autonomous driving test requirements. In one possible implementation, the tester may input / select the autonomous driving test requirements on the user interface / visualization interface. For example, the autonomous driving test requirement may be to use a scene with a complexity level of complexity 1 as an autonomous driving test scene (or the autonomous driving test requirement may be to conduct an autonomous driving test under a scene with a complexity level of complexity 1). If the complexity of the target driving scene is complexity level 1, then the target driving scene may be used as a test scene; if the complexity of the target driving scene is not complexity level 1, then the target driving scene may not be used as a test scene. For another example, the autonomous driving test requirement may be to use a scene with a complexity not lower than complexity level 2 as the test scene (or the autonomous driving test requirement is to conduct autonomous driving tests in scenes with complexity level 2 and above). If the complexity of the target driving scene is complexity level 2, then the target driving scene can be used as the test scene. If the complexity of the target driving scene is complexity level 1, then the target driving scene cannot be used as the test scene.

[0163] Optionally, when the high-precision map corresponding to the target driving scene is updated, the cloud platform can obtain the updated high-precision map again and process the updated high-precision map to redetermine the complexity of the target driving scene. For the specific implementation, please refer to the relevant descriptions in the aforementioned steps S201 to S203 and will not be repeated here.

[0164] The embodiments of the present application provide a complexity classification scheme for static scenes, which can improve the flexibility of scene hazard level classification. Specifically, the hazard information present in the target driving scene can be determined based on the information of the static elements in the target driving scene, and then the complexity of the target driving scene can be determined based on the hazard information present in the target driving scene. Generally speaking, the higher the scene complexity of a vehicle driving scene, the greater the impact of the vehicle driving scene on driving safety.

[0165] The above describes in detail the method of the embodiment of the present application. The following provides an apparatus for implementing the method in the embodiment of the present application. For example, an apparatus is provided including units (or means) for implementing each step performed by the device in the above method.

[0166] Please refer to Figure 10, which is a structural diagram of a data processing device provided in an embodiment of the present application.

[0167] As shown in Figure 10, the data processing device 100 may include a transceiver unit 1001 and a processing unit 1002. The transceiver unit 1001 and the processing unit 1002 may be software, hardware, or a combination of software and hardware.

[0168] The transceiver unit 1001 can implement a sending function and / or a receiving function, and can also be described as a transceiver unit. The transceiver unit 1001 can also be a unit that integrates an acquisition unit (or receiving unit) and a sending unit, wherein the acquisition unit is used to implement the receiving function and the sending unit is used to implement the sending function. Optionally, the transceiver unit 1001 can be used to receive information sent by other devices, and can also be used to send information to other devices.

[0169] In one possible design, the data processing device 100 may correspond to the cloud platform in the method embodiment shown in FIG2 . The data processing device 100 may include units for executing the operations performed by the cloud platform in the method embodiment shown in FIG2 , and each unit in the data processing device 100 is respectively for implementing the operations performed by the cloud platform in the method embodiment shown in FIG2 . The description of each unit is as follows:

[0170] The transceiver unit 1001 is used to obtain information about static elements in the target driving scene;

[0171] A processing unit 1002 is configured to determine, based on information about the static elements, hazard information present in the target driving scene, where the hazard information indicates a collision condition of a moving object in the target driving scene;

[0172] The processing unit 1002 is used to determine the complexity of the target driving scene based on the danger information existing in the target driving scene. The complexity of the target driving scene reflects the impact of the target driving scene on driving safety.

[0173] In a possible implementation, the hazard information present in the target driving scene includes information about collision points in the target driving scene; when determining the hazard information present in the target driving scene based on the information of the static element, the processing unit 1002 is specifically configured to:

[0174] Determining a physical collision point in the target driving scene based on information of the static element, where the physical collision point is a merging point of lanes or an intersection of driving paths;

[0175] Information about the collision point in the target driving scene is determined according to the physical collision point in the target driving scene.

[0176] In a possible implementation, the collision point information includes the number of collision points; when determining the collision point information in the target driving scene based on the physical collision points in the target driving scene, the processing unit 1002 is specifically configured to:

[0177] determining the number of physical collision points in the target driving scene as the number of collision points in the target driving scene; or,

[0178] Rasterizing the collision area where the physical collision point is located to obtain logical collision points in the target driving scene; wherein one logical collision point is associated with at least one physical collision point, and the logical collision point is a collision risk point in an adjacent area of ​​the collision area;

[0179] The number of the logical collision points is determined as the number of collision points in the target driving scene.

[0180] In one possible implementation, the complexity of the target driving scene is indicated by a complexity level; when determining the complexity of the target driving scene based on the hazard information present in the target driving scene, the processing unit 1002 is specifically configured to:

[0181] The complexity level of the target driving scene is determined according to the number of collision points and a plurality of preset collision point number ranges, wherein one collision point number range corresponds to one complexity level.

[0182] In a possible implementation, when determining the complexity level of the target driving scenario according to the number of collision points and a plurality of preset collision point number ranges, the processing unit 1002 is specifically configured to:

[0183] A first collision point number range to which the collision point number belongs is determined, and a complexity level corresponding to the first collision point number range is determined as the complexity level of the target driving scene, wherein the first collision point number range is one of the multiple collision point number ranges.

[0184] In a possible implementation manner, the plurality of collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs; or,

[0185] The multiple collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs and the region where the target driving scene is located.

[0186] In a possible implementation, when acquiring information about static elements in the target driving scene, the transceiver unit 1001 is specifically configured to:

[0187] The information of static elements in the target driving scene is obtained from the high-precision map.

[0188] In a possible implementation, the target driving scenario includes an ordinary road scenario, an intersection scenario, a ramp scenario, a roundabout scenario, a toll station scenario, a tunnel scenario, an overpass scenario, an elevated road scenario, or a continuous overpass scenario.

[0189] In a possible implementation, the static elements include one or more of an intersection surface, a road, an obstacle, a road surface marking, a virtual lane, or a traffic facility.

[0190] In a possible implementation, the virtual lane is determined based on lane turning information and angle information between an entrance and an exit.

[0191] In a possible implementation, the information of the static element includes one or more of element border, element position, or element size.

[0192] In a possible implementation, the processing unit 1002 is further configured to:

[0193] Obtain autonomous driving test requirements;

[0194] Determine whether to use the target driving scenario as a test scenario based on the complexity of the target driving scenario and the autonomous driving test requirements.

[0195] Regarding the technical effects brought about by this design and any possible implementation method, please refer to the introduction of the technical effects corresponding to Figure 2 and the corresponding implementation method.

[0196] Optionally, in any possible design of the data processing device 100 shown in FIG10 :

[0197] In one implementation, the data processing apparatus is a communications device. When the data processing apparatus is a communications device, the transceiver unit may be a transceiver or an input / output interface; and the processing unit may be at least one processor. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0198] In another implementation, the data processing device is a chip (system) or circuit used in a communication device. When the data processing device is a chip (system) or circuit used in a communication device, the transceiver unit can be a communication interface (input / output interface), interface circuit, output circuit, input circuit, pin, or related circuit on the chip (system) or circuit; the processing unit can be at least one processor, processing circuit, or logic circuit.

[0199] According to an embodiment of the present application, each unit in the device shown in Figure 10 can be separately or all merged into one or several other units to constitute, or a certain (some) unit therein can also be split into multiple smaller units to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the function of a unit can also be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of the present application, other units can also be included based on electronic equipment. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by collaboration of multiple units.

[0200] It should be noted that the implementation of each unit may also refer to the corresponding description of the method embodiment shown in FIG. 2 .

[0201] Please refer to Figure 11, which is a structural diagram of a data processing device provided in an embodiment of the present application.

[0202] It should be understood that the data processing device 110 shown in Figure 11 is only an example. The data processing device of the embodiment of the present application may also include other components, or include components with functions similar to the various components in Figure 11, or not necessarily include all the components in Figure 11.

[0203] The data processing device 110 includes a communication interface 1101 and at least one processor 1102 .

[0204] The data processing device 110 may correspond to an in-vehicle device or server deployed with a cloud platform, etc. The communication interface 1101 is used to send and receive signals, and at least one processor 1102 executes program instructions, so that the data processing device 110 implements the corresponding process of the method executed by the corresponding device in the above method embodiment.

[0205] In one possible design, the data processing device 110 may correspond to the vehicle-mounted device or chip that deploys the cloud platform in the method embodiment shown in FIG11 . The data processing device 110 may include components for executing the operations performed by the cloud platform in the method embodiment described above, and each component in the data processing device 110 is respectively configured to implement the operations performed by the cloud platform in the method embodiment described above. Specifically, the data processing device 110 may be as follows:

[0206] Obtain information about static elements in the target driving scene;

[0207] determining, based on the information of the static elements, danger information present in the target driving scene, the danger information being used to indicate a collision situation of a moving object in the target driving scene;

[0208] The complexity of the target driving scene is determined based on the danger information present in the target driving scene. The complexity of the target driving scene reflects the degree of influence of the target driving scene on driving safety.

[0209] In a possible implementation manner, the danger information present in the target driving scene includes information of a collision point in the target driving scene;

[0210] The determining of the danger information present in the target driving scene according to the information of the static element includes:

[0211] Determining a physical collision point in the target driving scene based on information of the static element, where the physical collision point is a merging point of lanes or an intersection of driving paths;

[0212] Information about the collision point in the target driving scene is determined according to the physical collision point in the target driving scene.

[0213] In a possible implementation, the information of the collision points includes the number of collision points;

[0214] The determining of information of the collision point in the target driving scene according to the physical collision point in the target driving scene includes:

[0215] determining the number of physical collision points in the target driving scene as the number of collision points in the target driving scene; or,

[0216] Rasterizing the collision area where the physical collision point is located to obtain logical collision points in the target driving scene; wherein one logical collision point is associated with at least one physical collision point, and the logical collision point is a collision risk point in an adjacent area of ​​the collision area;

[0217] The number of the logical collision points is determined as the number of collision points in the target driving scene.

[0218] In one possible implementation, the complexity of the target driving scenario is indicated by a complexity level;

[0219] The determining the complexity of the target driving scene according to the danger information present in the target driving scene includes:

[0220] The complexity level of the target driving scene is determined according to the number of collision points and a plurality of preset collision point number ranges, wherein one collision point number range corresponds to one complexity level.

[0221] In a possible implementation, determining the complexity level of the target driving scenario based on the number of collision points and a plurality of preset collision point number ranges includes:

[0222] A first collision point number range to which the collision point number belongs is determined, and a complexity level corresponding to the first collision point number range is determined as the complexity level of the target driving scene, wherein the first collision point number range is one of the multiple collision point number ranges.

[0223] In a possible implementation manner, the plurality of collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs; or,

[0224] The multiple collision point quantity ranges are collision point quantity ranges corresponding to the scene type to which the target driving scene belongs and the region where the target driving scene is located.

[0225] In a possible implementation, obtaining information about static elements in the target driving scene includes:

[0226] The information of static elements in the target driving scene is obtained from the high-precision map.

[0227] In a possible implementation, the target driving scenario includes an ordinary road scenario, an intersection scenario, a ramp scenario, a roundabout scenario, a toll station scenario, a tunnel scenario, an overpass scenario, an elevated road scenario, or a continuous overpass scenario.

[0228] In a possible implementation, the static elements include one or more of an intersection surface, a road, an obstacle, a road surface marking, a virtual lane, or a traffic facility.

[0229] In a possible implementation, the virtual lane is determined based on lane turning information and angle information between an entrance and an exit.

[0230] In a possible implementation, the information of the static element includes one or more of element border, element position, or element size.

[0231] In one possible implementation, the method further includes:

[0232] Obtain autonomous driving test requirements;

[0233] Determine whether to use the target driving scenario as a test scenario based on the complexity of the target driving scenario and the autonomous driving test requirements.

[0234] Regarding the technical effects brought about by this design and any possible implementation method, please refer to the introduction of the technical effects corresponding to Figure 2 and the corresponding implementation method.

[0235] In the case where the data processing device may be a chip or a chip system, reference may be made to the schematic structural diagram of the chip shown in FIG12 .

[0236] As shown in Figure 12 , chip 120 includes a processor 1201 and an interface 1202. There may be one or more processors 1201, and there may be multiple interfaces 1202. It should be noted that the functions of processor 1201 and interface 1202 may be implemented through hardware design, software design, or a combination of hardware and software, without limitation.

[0237] Optionally, the chip 120 may further include a memory 1203 , which is used to store necessary program instructions and data.

[0238] In this application, processor 1201 may be used to call from memory 1203 a program for implementing the data processing method provided in one or more embodiments of this application on one or more devices in a vehicle-mounted device or server deployed with a cloud platform, and execute the instructions contained in the program. Interface 1202 may be used to output the execution results of processor 1201. In this application, interface 1202 may be specifically used to output various messages or information from processor 1201.

[0239] For the data processing method provided by one or more embodiments of the present application, reference may be made to the various embodiments shown in FIG2 above, which will not be described in detail here.

[0240] The processor in the embodiments of the present application may be a central processing unit (CPU), and may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0241] The memory in the embodiments of the present application is used to provide storage space, in which data such as an operating system and computer programs can be stored. The memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0242] According to the method provided in the embodiment of the present application, the embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program runs on one or more processors, the method shown in Figure 2 can be implemented.

[0243] According to the method provided in the embodiment of the present application, the embodiment of the present application also provides a computer program product, which includes a computer program. When the computer program runs on a processor, it can implement the method shown in Figure 2 above.

[0244] An embodiment of the present application further provides a system, which includes at least one data processing device 100 or data processing device 110 or chip 120 as described above, and is used to execute the steps executed by the corresponding device in any of the embodiments of FIG. 2 .

[0245] The present application also provides a system comprising an in-vehicle device or server deployed with a cloud platform, the in-vehicle device or server deployed with the cloud platform being configured to execute the steps performed by the cloud platform in the embodiment shown in FIG2 . Optionally, the system may further comprise a human-machine interaction (HMI) display screen, the HMI display screen being configured to obtain user input, such as user input of autonomous driving test requirements.

[0246] An embodiment of the present application further provides a processing device, including a processor and an interface; the processor is used to execute the method in any of the above method embodiments.

[0247] It should be understood that the above-mentioned processing device can be a chip. For example, the processing device can be a field programmable gate array (FPGA), a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, a system on chip (SoC), a central processing unit (CPU), a network processor (NP), a digital signal processing circuit (DSP), a microcontroller unit (MCU), a programmable logic device (PLD) or other integrated chip. The various methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0248] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0249] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disc (SSD)).

[0250] The units in the above-mentioned various apparatus embodiments completely correspond to the electronic devices in the method embodiments, and the corresponding modules or units perform the corresponding steps. For example, the transceiver unit (transceiver) performs the receiving or sending steps in the method embodiments, and other steps except sending and receiving can be performed by the processing unit (processor). The functions of the specific units can be referred to the corresponding method embodiments. Among them, there can be one or more processors.

[0251] It is understood that in the embodiments of the present application, the electronic device can perform some or all of the steps in the embodiments of the present application. These steps or operations are merely examples, and the embodiments of the present application can also perform other operations or variations of various operations. In addition, the various steps can be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be performed.

[0252] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0253] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0254] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0255] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0256] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0257] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0258] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A data processing method, characterized in that, Including: Obtaining information of static elements in a target driving scenario; Determining dangerous information existing in the target driving scenario according to the information of the static elements, where the dangerous information is used to indicate the collision situation of a moving object in the target driving scenario; Determining the complexity of the target driving scenario according to the dangerous information existing in the target driving scenario, where the complexity of the target driving scenario reflects the degree of influence of the target driving scenario on driving safety.

2. The method according to claim 1, characterized in that, The dangerous information existing in the target driving scenario includes information of collision points in the target driving scenario; The determining the dangerous information existing in the target driving scenario according to the information of the static elements includes: Determining physical collision points in the target driving scenario according to the information of the static elements, where the physical collision points are merging points of lanes or intersection points of driving paths; Determining the information of collision points in the target driving scenario according to the physical collision points in the target driving scenario.

3. The method according to claim 2, wherein The information of the collision points includes the number of collision points; The determining the information of collision points in the target driving scenario according to the physical collision points in the target driving scenario includes: Determining the number of physical collision points in the target driving scenario as the number of collision points in the target driving scenario; or Performing grid processing on a collision area where the physical collision points are located to obtain logical collision points in the target driving scenario; where at least one physical collision point is associated with one logical collision point, and the logical collision point is a collision risk point in a neighboring area of the collision area; Determining the number of the logical collision points as the number of collision points in the target driving scenario.

4. The method according to claim 3, characterized in that, The complexity of the target driving scenario is indicated by a complexity level; The determining the complexity of the target driving scenario according to the dangerous information existing in the target driving scenario includes: Determining the complexity level of the target driving scenario according to the number of collision points and a plurality of preset ranges of the number of collision points, where one range of the number of collision points corresponds to one complexity level.

5. The method according to claim 4, wherein The determining the complexity level of the target driving scenario according to the number of collision points and a plurality of preset ranges of the number of collision points includes: Determining a first range of the number of collision points to which the number of collision points belongs, and determining the complexity level corresponding to the first range of the number of collision points as the complexity level of the target driving scenario, where the first range of the number of collision points is one of the plurality of ranges of the number of collision points.

6. The method according to claim 4 or 5, wherein The plurality of ranges of the number of collision points are ranges of the number of collision points corresponding to the scenario type to which the target driving scenario belongs; or The plurality of ranges of the number of collision points are ranges of the number of collision points corresponding to the scenario type to which the target driving scenario belongs and the region where the target driving scenario is located.

7. The method according to any one of claims 1-6, characterized in that The obtaining the information of static elements in the target driving scenario includes: Obtaining the information of static elements in the target driving scenario from a high-precision map.

8. The method according to any one of claims 1 to 7, characterized in that, The target driving scenarios include ordinary road scenarios, intersection scenarios, ramp scenarios, roundabout scenarios, toll station scenarios, tunnel scenarios, overpass scenarios, elevated road scenarios, or continuous overpass scenarios.

9. The method according to any one of claims 1 to 8, characterized in that, The static elements include one or more of intersection surfaces, roads, obstacles, road markings, virtual lanes, or traffic facilities.

10. The method according to any one of claims 1-9, characterized in that, The information of the static elements includes one or more of element boundaries, element positions, or element sizes.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Obtaining autonomous driving test requirements; Determining whether to use the target driving scenario as a test scenario according to the complexity of the target driving scenario and the autonomous driving test requirements.

12. A data processing device, characterized in that, Including a unit or module for executing the method according to any one of claims 1-11.

13. A data processing device, characterized in that, Including: A processor, when the processor calls a computer program or instruction in a memory, causing the method according to any one of claims 1-11 to be executed.

14. A data processing device, characterized in that, Including a logic circuit and an interface, the logic circuit and the interface being coupled; The interface is used to input data to be processed, the logic circuit processes the data to be processed according to the method according to any one of claims 1-11 to obtain processed data, and the interface is used to output the processed data.

15. A computer-readable storage medium, characterized in that, Including: The computer-readable storage medium is used to store instructions or a computer program; when the instructions or the computer program are executed, the method according to any one of claims 1-11 is implemented.

16. A computer program product, characterized in that, Including: Instructions or a computer program; When the instructions or the computer program are executed, the method according to any one of claims 1-11 is executed.

Images