Methods, devices, storage media and electronic devices for processing sensed data

Abstract

This disclosure provides a method, apparatus, storage medium, and electronic device for processing sensing data. The method includes: acquiring collected sensing data and a plurality of preset driving scenario templates; determining a target driving scenario template corresponding to each dynamic element from the plurality of driving scenario templates based on the constraints of each driving scenario template, wherein the trajectory information of the dynamic element in the sensing data conforms to the constraints corresponding to the target driving scenario template; and generating a target scenario file based on the sensing data and the target driving scenario template corresponding to each dynamic element. This allows for the automated conversion of sensing data into scenario files based on the target scenario templates, improving the efficiency of converting sensing data into scenario files and thus improving the training efficiency of the sensing algorithm.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a method, apparatus, storage medium, and electronic device for processing perception data. Background Technology

[0002] OSC (OpenScenario, an open standard) is a standard format for traffic simulation and vehicle motion data exchange. OSC scenario files, carrying vehicle trajectory data, can be used to support the development and testing of autonomous vehicles in simulated environments. Using OSC scenario files to test autonomous vehicles can improve the efficiency of vehicle development and testing, and promote the maturity of autonomous driving technology.

[0003] Currently, when converting vehicle trajectory data into OSC scene files, it is necessary to manually edit the data according to the vehicle's driving scenario to restore the traffic situation, which results in low efficiency in generating OSC scene files. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, apparatus, storage medium, and electronic device for processing sensing data, which can improve the efficiency of converting sensing data into scene files.

[0005] According to a first aspect of the present disclosure, a method for processing sensing data is provided, the method comprising:

[0006] Acquire the collected perception data and multiple preset driving scenario templates;

[0007] Based on the constraints of each driving scenario template, a target driving scenario template corresponding to each dynamic element is determined from the plurality of driving scenario templates, wherein the trajectory information of the dynamic element in the perception data conforms to the constraints corresponding to the target driving scenario template;

[0008] Based on the target driving scene template corresponding to the dynamic elements in the perception data, a target scene file is generated.

[0009] In one embodiment, determining the target driving scenario template corresponding to each dynamic element from the plurality of driving scenario templates based on the constraints of each driving scenario template includes:

[0010] Determine the category and trajectory information of multiple dynamic elements in the perceived data;

[0011] Based on the categories of the multiple dynamic elements, determine at least one driving scene template of the same category corresponding to each dynamic element;

[0012] The trajectory information of each dynamic element is matched with the constraints of at least one corresponding driving scenario template of the same category to determine the target driving scenario template.

[0013] In one embodiment, matching the trajectory information of each dynamic element with the constraints of at least one corresponding driving scenario template of the same category to determine the target driving scenario template includes:

[0014] The trajectory points in the trajectory information of the dynamic element are matched with the constraints of at least one driving scene template of the same category to determine the matching rate between the dynamic element and each driving scene template of the same category.

[0015] Among the matching rates of the dynamic element and at least one driving scenario template of the same category, the highest matching rate is determined;

[0016] If the highest matching rate reaches a preset threshold, then the driving scenario template of the same category corresponding to the highest matching rate is determined as the target driving scenario template.

[0017] In one embodiment, the constraints include at least start time constraints, end time constraints, and process constraints;

[0018] The step of matching the trajectory points in the trajectory information of the dynamic element with the constraints of at least one driving scene template of the same category, and determining the matching rate between the dynamic element and each driving scene template of the same category, includes:

[0019] If a first trajectory point and a second trajectory point exist in the trajectory information of the dynamic element, a set of trajectory points between the first trajectory point and the second trajectory point is determined. The first trajectory point is a trajectory point in the trajectory information of the dynamic element that meets the start time constraint condition of the same type of driving scenario template, and the second trajectory point is a trajectory point in the trajectory information of the dynamic element that meets the end time constraint condition of the same type of driving scenario template. The timestamp of the first trajectory point is earlier than the timestamp of the second trajectory point.

[0020] Determine the number of qualified trajectory points in the trajectory point set, wherein the qualified trajectory points are the trajectory points in the trajectory point set that meet the process constraint conditions of the same type of driving scenario template;

[0021] Based on the number of qualified trajectory points and the total number in the trajectory point set, the matching rate between the dynamic element and the same type of driving scenario template is determined.

[0022] In one embodiment, the trajectory information of the dynamic element includes at least: the trajectory point of the dynamic element, timestamp information, orientation angle information, coordinate information of the dynamic element relative to the host vehicle, and lane information.

[0023] In one embodiment, generating a target scene file based on the perceived data and the target driving scene template corresponding to each dynamic element includes:

[0024] Based on the timestamps in the perceived data, the time sequence of the target driving scene template corresponding to each dynamic element is determined;

[0025] The arrangement of the target driving scenario templates is determined based on the time sequence of multiple target driving scenario templates;

[0026] Based on the arrangement of driving scenes corresponding to the dynamic elements, an initial scene file is generated;

[0027] High-precision map data is inserted into the initial scene file to generate the target scene file.

[0028] According to a second aspect of the present disclosure, a processing apparatus for sensed data is provided, the apparatus comprising:

[0029] The acquisition unit is used to acquire the collected perception data and multiple preset driving scenario templates;

[0030] The determining unit is used to determine the target driving scene template corresponding to each dynamic element from the plurality of driving scene templates based on the constraints of each driving scene template, wherein the trajectory information of the dynamic element in the perception data conforms to the constraints corresponding to the target driving scene template.

[0031] The generation unit is used to generate a target scene file based on the target driving scene template corresponding to the dynamic elements in the perception data.

[0032] In one embodiment, the determining unit is configured to:

[0033] Determine the category and trajectory information of multiple dynamic elements in the perceived data;

[0034] Based on the categories of the multiple dynamic elements, determine at least one driving scene template of the same category corresponding to each dynamic element;

[0035] The trajectory information of each dynamic element is matched with the constraints of at least one corresponding driving scenario template of the same category to determine the target driving scenario template.

[0036] In one embodiment, the determining unit is configured to:

[0037] The trajectory points in the trajectory information of the dynamic element are matched with the constraints of at least one driving scene template of the same category to determine the matching rate between the dynamic element and each driving scene template of the same category.

[0038] Among the matching rates of the dynamic element and at least one driving scenario template of the same category, the highest matching rate is determined;

[0039] If the highest matching rate reaches a preset threshold, then the driving scenario template of the same category corresponding to the highest matching rate is determined as the target driving scenario template.

[0040] In one embodiment, the determining unit is configured to:

[0041] The step of matching the trajectory points in the trajectory information of the dynamic element with the constraints of at least one driving scene template of the same category, and determining the matching rate between the dynamic element and each driving scene template of the same category, includes:

[0042] If a first trajectory point and a second trajectory point exist in the trajectory information of the dynamic element, a set of trajectory points between the first trajectory point and the second trajectory point is determined. The first trajectory point is a trajectory point in the trajectory information of the dynamic element that meets the start time constraint condition of the same type of driving scenario template, and the second trajectory point is a trajectory point in the trajectory information of the dynamic element that meets the end time constraint condition of the same type of driving scenario template. The timestamp of the first trajectory point is earlier than the timestamp of the second trajectory point.

[0043] Determine the number of qualified trajectory points in the trajectory point set, wherein the qualified trajectory points are the trajectory points in the trajectory point set that meet the process constraint conditions of the same type of driving scenario template;

[0044] Based on the number of qualified trajectory points and the total number in the trajectory point set, the matching rate between the dynamic element and the same type of driving scenario template is determined.

[0045] In one embodiment, the trajectory information of the dynamic element includes at least: the trajectory point of the dynamic element, timestamp information, orientation angle information, coordinate information of the dynamic element relative to the host vehicle, and lane information.

[0046] In one embodiment, the generating unit is configured to:

[0047] Based on the timestamps in the perceived data, the time sequence of the target driving scene template corresponding to each dynamic element is determined;

[0048] The arrangement of the target driving scenario templates is determined based on the time sequence of multiple target driving scenario templates;

[0049] Based on the arrangement of driving scenes corresponding to the dynamic elements, an initial scene file is generated;

[0050] High-precision map data is inserted into the initial scene file to generate the target scene file.

[0051] According to a third aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described in the first aspect.

[0052] According to a fourth aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the methods described in the first aspect above.

[0053] According to a fifth aspect of the present disclosure, a computer program product is provided, on which a computer program is stored, wherein when the computer program product is executed by a processor, it implements the steps of any of the methods described in the first aspect above.

[0054] The technical solutions provided in this disclosure can include the following beneficial effects:

[0055] By matching the perception data of the vehicle's motion trajectory with the preset driving scene template, the target scene template corresponding to the perception data is determined, and scene files are automatically generated based on the target scene template. This improves the efficiency of converting perception data into scene files, thereby improving the training efficiency of the perception algorithm. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating a method for processing perceived data according to an exemplary embodiment of this disclosure;

[0057] Figure 2 This is a flowchart illustrating an exemplary embodiment of the present disclosure for determining a target driving scenario template;

[0058] Figure 3 This is a schematic diagram illustrating dynamic element trajectory information according to an exemplary embodiment of this disclosure;

[0059] Figure 4 This is a flowchart illustrating an exemplary embodiment of the present disclosure of determining a target driving scenario template among driving scenario templates of the same category;

[0060] Figure 5 This is a flowchart illustrating an exemplary embodiment of the present disclosure for generating a target scene file;

[0061] Figure 6This is a block diagram of a sensor data processing apparatus shown in an exemplary embodiment of the present disclosure;

[0062] Figure 7 This is a hardware structure diagram of an electronic device illustrated in an exemplary embodiment of the present disclosure. Detailed Implementation

[0063] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0064] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0065] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0066] OpenScenario provides a standardized way to describe dynamic elements in a simulated environment, such as the behavior of traffic participants and how these participants interact with other participants and the environment. This ensures that different simulation platforms can be tested using the same scenario definitions. By converting perception data collected by vehicles into OpenScenario 2.0 (a version of OpenScenario, hereinafter referred to as OSC2.0) files, complex and realistic traffic scenarios can be generated. These scenarios help perception algorithms be trained under various conditions, thereby improving the robustness and accuracy of the algorithms and ensuring their reliability in the real world, thus promoting the development of autonomous driving technology.

[0067] However, currently, when converting the motion trajectory of dynamic elements in the perception data into OSC2.0 scene files, it is necessary to manually edit the data according to the vehicle's driving scenario to restore the traffic situation. This results in a relatively low efficiency in generating OSC2.0 scene files.

[0068] Based on this, this disclosure provides a method for processing perceived data, which can be applied to electronic devices that simulate vehicle driving scenarios. Please refer to [link to relevant documentation]. Figure 1 The flowchart shown illustrates the following steps in this method:

[0069] S101: Acquire the collected perception data and multiple preset driving scenario templates.

[0070] Perception data can be road data collected by physical sensors on public roads, such as image data, video data, or GPS (Global Positioning System) data. Driving scenario templates are pre-designed templates based on various driving scenarios that a vehicle may encounter during its journey, such as vehicle entry scenario templates, vehicle exit scenario templates, oncoming vehicle driving scenario templates, and pedestrian crossing scenario templates. Driving scenario templates are used to describe the changes in dynamic elements on the road in different scenarios. For example, a vehicle entry scenario involves another vehicle entering the same lane as the primary vehicle from another lane; the primary vehicle is the one collecting perception data.

[0071] S102, based on the constraints of each driving scenario template, determine the target driving scenario template corresponding to each dynamic element from the plurality of driving scenario templates.

[0072] The constraints for each driving scenario template are pre-set. For example, for a vehicle entry scenario, the constraint could be that before the vehicle enters, the target vehicle's lane is different from the main vehicle's lane; after the vehicle enters, the target vehicle's lane becomes the same as the main vehicle's lane. Dynamic elements refer to movable target objects on the road, such as other cars, pedestrians, bicycles, etc., besides the main vehicle. The target driving scenario template refers to a driving scenario template where the trajectory information of the dynamic element in the perception data conforms to its constraints. For example, if another vehicle enters the lane where the main vehicle is located, the trajectory information of that vehicle will conform to the constraints of the vehicle entry scenario.

[0073] For each dynamic element, its trajectory information is matched against the constraints of multiple driving scenario templates. Based on the matching results, a target scenario template corresponding to the trajectory information of the dynamic element is determined from among the multiple driving scenario templates. It should be noted that the trajectory information of the dynamic element in the perception data conforms to the constraints corresponding to the target driving scenario template.

[0074] In one embodiment, the process of determining the target driving scenario template is as follows: Figure 2 As shown, Figure 2 This is a flowchart illustrating an exemplary embodiment of the present disclosure, which includes the following steps:

[0075] S201, determine the category and trajectory information of multiple dynamic elements in the perceived data.

[0076] S202, based on the categories of the multiple dynamic elements, determine at least one driving scene template of the same category corresponding to each dynamic element.

[0077] S203, match the trajectory information of each dynamic element with the constraints of at least one corresponding driving scene template of the same category to determine the target driving scene template.

[0078] When determining the target driving scenario, dynamic elements are first classified, such as vehicles, pedestrians, or bicycles. Then, the trajectory information of the dynamic elements in the host vehicle coordinate system is determined. This trajectory information includes at least: the trajectory point of the dynamic element, timestamp information, orientation angle information, the coordinates of the dynamic element relative to the host vehicle, and lane information. The timestamp information is the timestamp recorded when the vehicle collects perception data, and each timestamp corresponds to a trajectory point in the motion trajectory. Each trajectory point carries one timestamp. The orientation angle information is the angle between the orientation of the dynamic element and the x-axis of the host vehicle coordinate system. The coordinates of the dynamic element relative to the host vehicle can be represented by xyz coordinates. The lane information can be represented by a lane ID. Please refer to [link to relevant documentation]. Figure 3 The lane ID of the main vehicle is 0. The coordinates of the main vehicle and other vehicles can be represented based on the x, y, and z axes of the main vehicle's coordinate system. Other vehicles initially travel in lane ID 1, with an orientation angle of h relative to the main vehicle's x-axis. These vehicles travel according to this orientation angle, and their trajectories are as follows: Figure 3 As shown by the black dot, the vehicle will eventually travel in the same lane as the main vehicle, thus enabling it to cut in.

[0079] Then, based on the category of the dynamic element, determine the corresponding driving scenario template for each dynamic element. For example, if the dynamic element category is vehicle, the driving scenario template for vehicles could include vehicle entry, vehicle exit, and vehicle traveling in opposite directions. Similarly, if the dynamic element category is pedestrian, the driving scenario template for pedestrians could include pedestrian crossing.

[0080] After determining the corresponding driving scenario template for each dynamic element based on its category, the trajectory information of each dynamic element is matched with the driving scenario template for the same category. Based on the matching results, the preferred option is determined from the driving scenario templates for the same category and identified as the target driving scenario template for that dynamic element.

[0081] Based on the category information of dynamic elements, the corresponding driving scene templates of the same category are determined, and the trajectory information of dynamic elements is matched with the driving scene templates of the same category. The target driving scene template is then determined from the driving scene templates of the same category, which improves the efficiency of matching the trajectory information of dynamic elements and driving scene templates.

[0082] In one embodiment, the process of determining the target driving scenario template from driving scenario templates of the same category can be found in [link to relevant documentation]. Figure 4 The flowchart shown includes the following steps:

[0083] S401, the trajectory points in the trajectory information of the dynamic element are matched with the constraints of at least one driving scene template of the same category, and the matching rate between the dynamic element and each driving scene template of the same category is determined.

[0084] The constraints include at least a start time constraint, an end time constraint, and a process constraint. The start time constraint is used to determine the state of the dynamic element at the start time of the driving scenario. The end time constraint is used to determine the state of the dynamic element at the end time of the driving scenario. The process constraint is used to determine the state of the dynamic element between the start time and the end time in the driving scenario.

[0085] Taking the vehicle entry scenario as an example, the dynamic element is other vehicles, and the start time constraint of the vehicle entry scenario template is as shown in formula (1):

[0086]

[0087] in, The initial constraints are represented by x, which represents the lateral coordinates of other vehicles relative to the driver vehicle (i.e., the distance between other vehicles and the driver vehicle), y, which represents the lateral coordinates of other vehicles relative to the driver vehicle (i.e., the distance between other vehicles and the driver vehicle), W, which represents the width of the lane where the driver vehicle is located, and h. npch represents the heading angle of other vehicles. npc LaneID indicates the heading angle of the main vehicle. npc LaneID represents the lane ID of other vehicles. ego This indicates the lane ID of the main vehicle.

[0088] The constraint condition for the end time of the vehicle entering the scene template is shown in formula (2):

[0089]

[0090] in, The constraint at the end time is indicated, and l represents the length of the main vehicle.

[0091] The process constraints for the vehicle entering the scene template are shown in formula (3):

[0092]

[0093] in, This represents the longitudinal coordinates of other vehicles relative to the master vehicle's coordinates at the initial moment.

[0094] After determining the constraints of at least one driving scenario template of the same type, it is determined whether there is a first trajectory point and a second trajectory point in the trajectory information of the dynamic element. The first trajectory point is the trajectory point in the trajectory information of the dynamic element that meets the start time constraint of the driving scenario template of the same type, and the second trajectory point is the trajectory point in the trajectory information of the dynamic element that meets the end time constraint of the driving scenario template of the same type.

[0095] If the trajectory information of a dynamic element contains a first trajectory point and a second trajectory point, it indicates that the dynamic element may meet the driving conditions specified by the driving scenario template. Therefore, the matching rate between the dynamic element and the driving scenario template is calculated based on the set of trajectory points between the first trajectory point corresponding to the start time and the second trajectory point corresponding to the end time. Specifically, this is achieved by matching the trajectory points in the trajectory point set with the process constraints. Trajectory points in the trajectory point set that meet the process constraints of the driving scenario template are identified as qualified trajectory points. Trajectory points in the trajectory point set that do not meet the process constraints of the driving scenario template are identified as unqualified trajectory points. The matching rate is the ratio of the number of qualified trajectory points to the total number of trajectory points in the trajectory point set.

[0096] S402, determine the highest matching rate among the matching rates of the dynamic element and at least one driving scene template of the same category.

[0097] It should be noted that different driving scenario templates may have some identical constraints. For example, the constraint for the start time of vehicle entry may be the same as the constraint for the end time of vehicle exit. Therefore, for the same dynamic element, its trajectory may satisfy the constraints of multiple driving scenario templates of the same category. Thus, it is necessary to determine an optimal option among these multiple templates. In this embodiment, the optimal option can be determined by comparing matching rates. Specifically, a highest matching rate is determined among the matching rates of multiple driving scenario templates of the same category, and it is then determined whether this highest matching rate reaches a preset threshold.

[0098] S403, if the highest matching rate reaches a preset threshold, then the same category driving scenario template corresponding to the highest matching rate is determined as the target driving scenario template.

[0099] If the highest matching rate is greater than or equal to the preset threshold, the driving scenario template of the same category corresponding to the highest matching rate is determined as the target driving scenario template; if the highest matching rate is less than the preset threshold, it means that the dynamic element fails to match the driving scenario template.

[0100] S103, Generate a target scene file based on the target driving scene template corresponding to the dynamic elements in the perception data.

[0101] In some embodiments, the target scene file can be an OSC2.0 scene file. After determining the target driving scene corresponding to each dynamic element, multiple target driving scene templates are sorted and combined according to the timestamp information in the trajectory information of the dynamic element to generate a target scene file. It should be noted that when a vehicle is driving on the road, the driving conditions may be complex and changeable. Therefore, there may be multiple dynamic elements in the perception data, and the driving scene of each dynamic element may be completely different. For example, when a vehicle is driving, it may encounter multiple scenarios such as other vehicles cutting in, other vehicles cutting out, and pedestrians crossing the road within a certain period of time. A complex simulated traffic scene can be generated through a single target scene file (i.e., an OSC2.0 file), so the target scene file can contain driving scenes of multiple dynamic elements in the perception data. To improve the accuracy of generating simulated traffic scenes from the target scene file, multiple target driving scene templates can be sorted according to time order.

[0102] In one embodiment, the process of generating the target scene file is described in [reference needed]. Figure 5 The flowchart shown includes the following steps:

[0103] S501, based on the timestamp information of the dynamic elements in the perception data, determine the time sequence of the target driving scene template corresponding to each dynamic element.

[0104] S502, based on the time sequence of multiple target driving scenario templates, determine the arrangement of the target driving scenario templates.

[0105] S503, Based on the arrangement of driving scenes corresponding to the dynamic elements, generate an initial scene file.

[0106] S504, high-precision map data is inserted into the initial scene file to generate the target scene file.

[0107] First, based on the timestamp information of each dynamic element, the time order of the target driving scenario templates corresponding to each dynamic element can be determined. Specifically, the time order can be determined by sorting the start or end times in the constraints of each target driving scenario template. For example, the first vehicle corresponds to the vehicle entry scenario template, and the second vehicle corresponds to the vehicle exit scenario template. Based on the start time constraint of the vehicle entry scenario template, the start time of the first vehicle's entry can be determined, and based on the start time constraint of the vehicle exit scenario template, the start time of the second vehicle's exit can be determined. Thus, the time order of the vehicle entry and vehicle exit scenario templates is determined.

[0108] After determining the temporal sequence of multiple target driving scenario templates, the arrangement and order of these templates within the scenario file can be determined based on this temporal sequence. For example, if the vehicle entry scenario template and the vehicle exit scenario template are in parallel temporal sequence (meaning the first vehicle's entry and the second vehicle's exit occur simultaneously), then they can be arranged in parallel. Alternatively, if the vehicle entry scenario template and the pedestrian crossing scenario template are in the order of vehicle entry followed by pedestrian crossing, then they can be arranged sequentially, with the vehicle entry scenario template preceding the pedestrian crossing scenario template.

[0109] After arranging all target driving templates, the initial scene file is obtained. To further improve the information in the initial scene file, high-precision map information can be inserted. High-precision maps provide detailed road information, traffic signs, lane structure, and other data, increasing the realism and accuracy of the simulated scene. Additionally, weather and environmental information can be added to the initial scene file to simulate factors affecting vehicle driving safety, such as extreme weather (heavy rain, blizzards, fog, etc.) and different lighting conditions. After generating the target scene file, it can be imported into the simulation platform to generate various data for training the perception algorithm, including images and labeled ground truth data. This improves the accuracy and adaptability of the algorithm, ensuring the safety and reliability of the autonomous driving system in real-world environments.

[0110] In this embodiment of the disclosure, by matching the perception data of the vehicle with the motion trajectory collected with the preset driving scene template, the target scene template corresponding to the perception data is determined, and the scene file is automatically generated according to the target scene template, which improves the efficiency of converting perception data into scene files, thereby improving the training efficiency of the perception algorithm.

[0111] Corresponding to the embodiments of the aforementioned methods for processing sensing data, this disclosure also provides embodiments of a device for processing sensing data.

[0112] Please refer to Figure 6 , Figure 6 This is a block diagram of a sensor data processing apparatus according to an exemplary embodiment of the present disclosure, the apparatus comprising:

[0113] The acquisition unit 601 is used to acquire the collected perception data and multiple preset driving scenario templates;

[0114] The determining unit 602 is used to determine the target driving scene template corresponding to each dynamic element from the plurality of driving scene templates based on the constraints of each driving scene template, wherein the trajectory information of the dynamic element in the perception data conforms to the constraints corresponding to the target driving scene template.

[0115] The generation unit 603 is used to generate a target scene file based on the target driving scene template corresponding to the dynamic elements in the perception data.

[0116] In one embodiment, the determining unit 602 is configured to:

[0117] Determine the category and trajectory information of multiple dynamic elements in the perceived data;

[0118] Based on the categories of the multiple dynamic elements, determine at least one driving scene template of the same category corresponding to each dynamic element;

[0119] The trajectory information of each dynamic element is matched with the constraints of at least one corresponding driving scenario template of the same category to determine the target driving scenario template.

[0120] In one embodiment, the determining unit 602 is configured to:

[0121] The trajectory points in the trajectory information of the dynamic element are matched with the constraints of at least one driving scene template of the same category to determine the matching rate between the dynamic element and each driving scene template of the same category.

[0122] Among the matching rates of the dynamic element and at least one driving scenario template of the same category, the highest matching rate is determined;

[0123] If the highest matching rate reaches a preset threshold, then the driving scenario template of the same category corresponding to the highest matching rate is determined as the target driving scenario template.

[0124] In one embodiment, the determining unit 602 is configured to:

[0125] The step of matching the trajectory points in the trajectory information of the dynamic element with the constraints of at least one driving scene template of the same category, and determining the matching rate between the dynamic element and each driving scene template of the same category, includes:

[0126] If a first trajectory point and a second trajectory point exist in the trajectory information of the dynamic element, a set of trajectory points between the first trajectory point and the second trajectory point is determined. The first trajectory point is a trajectory point in the trajectory information of the dynamic element that meets the start time constraint condition of the same type of driving scenario template, and the second trajectory point is a trajectory point in the trajectory information of the dynamic element that meets the end time constraint condition of the same type of driving scenario template. The timestamp of the first trajectory point is earlier than the timestamp of the second trajectory point.

[0127] Determine the number of qualified trajectory points in the trajectory point set, wherein the qualified trajectory points are the trajectory points in the trajectory point set that meet the process constraint conditions of the same type of driving scenario template;

[0128] Based on the number of qualified trajectory points and the total number in the trajectory point set, the matching rate between the dynamic element and the same type of driving scenario template is determined.

[0129] In one embodiment, the trajectory information of the dynamic element includes at least: the trajectory point of the dynamic element, timestamp information, orientation angle information, coordinate information of the dynamic element relative to the host vehicle, and lane information.

[0130] In one embodiment, the generating unit 603 is configured to:

[0131] Based on the timestamps in the perceived data, the time sequence of the target driving scene template corresponding to each dynamic element is determined;

[0132] The arrangement of the target driving scenario templates is determined based on the time sequence of multiple target driving scenario templates;

[0133] Based on the arrangement of driving scenes corresponding to the dynamic elements, an initial scene file is generated;

[0134] High-precision map data is inserted into the initial scene file to generate the target scene file.

[0135] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0136] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. 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 the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0137] Embodiments of the data processing device disclosed herein can be applied to electronic devices. The device embodiments can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of the electronic device loading corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, such as... Figure 7 The diagram shown is a hardware structure diagram of an electronic device containing the data processing apparatus of this disclosure, except... Figure 7 In addition to the processor, memory, network interface, and non-volatile memory shown, the electronic device in which the device is located in the embodiment may also include other hardware depending on the actual function of the electronic device, which will not be described in detail here.

[0138] Based on the same inventive concept, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method for processing perceived data.

[0139] Based on the same inventive concept, this disclosure also provides a computer program product on which a computer program is stored, and when the computer program product is executed by a processor, it implements the steps of the above-described method for processing the perceived data.

[0140] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0141] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method of processing perception data, the method comprising: The method comprises: acquiring the collected perception data and a plurality of preset driving scene templates; determining, according to a constraint condition of each driving scene template, a target driving scene template corresponding to each dynamic element from the plurality of driving scene templates, wherein a trajectory information of the dynamic element in the perception data meets the constraint condition of the target driving scene template; generating a target scene file according to the target driving scene template corresponding to the dynamic element in the perception data; the determining, according to the constraint condition of each driving scene template, the target driving scene template corresponding to each dynamic element from the plurality of driving scene templates comprises: determining a category and trajectory information of a plurality of dynamic elements in the perception data; determining at least one same-category driving scene template corresponding to each dynamic element according to the category of the plurality of dynamic elements; matching the trajectory information of each dynamic element with the constraint condition of the at least one same-category driving scene template corresponding thereto respectively to determine the target driving scene template.

2. The method of claim 1, wherein, the matching the trajectory information of each dynamic element with the constraint condition of the at least one same-category driving scene template to determine the target driving scene template comprises: matching a trajectory point in the trajectory information of the dynamic element with the constraint condition of the at least one same-category driving scene template respectively to determine a matching rate of the dynamic element with each same-category driving scene template; determining a highest matching rate from the matching rates of the dynamic element with the at least one same-category driving scene template; if the highest matching rate reaches a preset threshold, determining the same-category driving scene template corresponding to the highest matching rate as the target driving scene template.

3. The method of claim 2, wherein, the constraint condition at least comprises a start time constraint condition, an end time constraint condition and a process constraint condition; the matching a trajectory point in the trajectory information of the dynamic element with the constraint condition of the at least one same-category driving scene template to determine the matching rate of the dynamic element with each same-category driving scene template comprises: in a case where there are a first trajectory point and a second trajectory point in the trajectory information of the dynamic element, determining a trajectory point set between the first trajectory point and the second trajectory point, wherein the first trajectory point is a trajectory point in the trajectory information of the dynamic element meeting the start time constraint condition of the same-category driving scene template, the second trajectory point is a trajectory point in the trajectory information of the dynamic element meeting the end time constraint condition of the same-category driving scene template, and a timestamp of the first trajectory point is earlier than a timestamp of the second trajectory point; determining a number of qualified trajectory points in the trajectory point set, wherein the qualified trajectory point is a trajectory point in the trajectory point set meeting the process constraint condition of the same-category driving scene template; determining the matching rate of the dynamic element with the same-category driving scene template according to the number of the qualified trajectory points and a total number in the trajectory point set.

4. The method of claim 1, wherein, the trajectory information of the dynamic element at least comprises a trajectory point of the dynamic element, timestamp information, orientation angle information, coordinate information of the dynamic element relative to a host vehicle and lane information.

5. The method of claim 1, wherein, The target scene file is generated according to the target driving scene template corresponding to the dynamic element in the perception data, and the target scene file includes: According to the timestamp information of the dynamic element in the perception data, the time sequence of the target driving scene template corresponding to each dynamic element is determined; Based on the time sequence of the plurality of target driving scene templates, the arrangement mode of the target driving scene templates is determined; Based on the driving scene arrangement mode corresponding to the dynamic element, an initial scene file is generated; The high-definition map data is inserted into the initial scene file to generate the target scene file.

6. A processing device of perception data, characterized in that, The device includes: An acquisition unit configured to acquire the perception data collected and a plurality of preset driving scene templates; A determination unit configured to determine, according to the constraint condition of each driving scene template, the target driving scene template corresponding to each dynamic element from the plurality of driving scene templates, wherein the trajectory information of the dynamic element in the perception data meets the constraint condition corresponding to the target driving scene template; A generation unit configured to generate a target scene file according to the target driving scene template corresponding to the dynamic element in the perception data; The determination unit is configured to: Determine the category and trajectory information of a plurality of dynamic elements in the perception data; According to the category of the plurality of dynamic elements, determine at least one same-category driving scene template corresponding to each dynamic element; Match the trajectory information of each dynamic element with the constraint condition of the at least one same-category driving scene template corresponding thereto to determine the target driving scene template.

7. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps of the method of any one of claims 1 to 5.

9. A computer program product having stored thereon a computer program, characterized in that, The computer program product is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images