Map data generation method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a map data generation method and device, electronic equipment and storage medium, relates to the technical field of computers, specifically to the technical field of artificial intelligence such as intelligent transportation and automatic driving, comprising: in response to a set event occurring in the driving scene of a first vehicle, determining an occurrence position area corresponding to the set event, obtaining first trajectory information of the first vehicle in the occurrence position area, and generating target map data corresponding to the occurrence position area according to the first trajectory information. Since the target map data corresponding to the occurrence position area is generated according to the first trajectory information of the occurrence position area when the set event occurs in the driving scene of the first vehicle, the period of map updating can be effectively reduced, and the resource waste caused by updating the entire map in the driving scene of the vehicle can be effectively avoided while ensuring the freshness of the map.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the fields of intelligent transportation, autonomous driving and other artificial intelligence technologies, and in particular to a map data generation method, apparatus, electronic device and storage medium. Background Technology

[0002] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0003] In related technologies, vehicle positioning is usually based on offline maps of the vehicle's driving area. However, due to the frequent occurrence of environmental change events in the vehicle driving scenario, the positioning effect based on offline map data is poor. In this case, it is necessary to update the offline map data. However, for the entire driving area of ​​the vehicle, environmental change events may only exist in a certain driving area, resulting in a long overall update cycle for the offline map and a significant waste of resources. Summary of the Invention

[0004] This disclosure provides a map data generation method, a vehicle pose determination method, an apparatus, an electronic device, a storage medium, and a computer program product.

[0005] According to a first aspect of this disclosure, a map data generation method is provided, which is executed by a first vehicle. The method includes: responding to a predetermined event occurring in a driving scenario of the first vehicle, determining a location area corresponding to the predetermined event; acquiring first trajectory information of the first vehicle in the location area; and generating target map data corresponding to the location area based on the first trajectory information.

[0006] According to a second aspect of this disclosure, a method for determining a vehicle pose is provided, which is executed by a second vehicle. The method includes: determining first trajectory information and / or target map data, wherein the first trajectory information describes the trajectory of the first vehicle in a region where a predetermined event has occurred, the predetermined event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information; and determining the target pose of the second vehicle based on the first trajectory information and / or the target map data.

[0007] According to a third aspect of this disclosure, a map data generation apparatus is provided, comprising: a first determining module, configured to determine a location area corresponding to a predetermined event in response to a predetermined event occurring in a driving scenario of a first vehicle; a first acquiring module, configured to acquire first trajectory information of the first vehicle in the location area; and a generating module, configured to generate target map data corresponding to the location area based on the first trajectory information.

[0008] According to a fourth aspect of this disclosure, a vehicle pose determination device is provided, executed by a second vehicle, the method comprising: a second determining module, configured to determine first trajectory information and / or target map data, wherein the first trajectory information describes the trajectory of the first vehicle in a region where a predetermined event has occurred, the predetermined event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information; and a third determining module, configured to determine the target pose of the second vehicle based on the first trajectory information and / or the target map data.

[0009] According to a fifth aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a map data generation method as described in the first aspect of this disclosure, or to perform a vehicle pose determination method as described in the second aspect of this disclosure.

[0010] According to a sixth aspect of this disclosure, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing a computer to perform a map data generation method as described in the first aspect of this disclosure, or a vehicle pose determination method as described in the second aspect of this disclosure.

[0011] According to a seventh aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of a map data generation method as described in the first aspect of this disclosure, or the steps of a vehicle pose determination method as described in the second aspect of this disclosure.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0014] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0015] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;

[0016] Figure 3 A schematic diagram according to the third embodiment of this disclosure.

[0017] Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure;

[0018] Figure 5 This is a schematic diagram according to the fifth embodiment of the present disclosure;

[0019] Figure 6 This is a schematic diagram according to the sixth embodiment of the present disclosure;

[0020] Figure 7 This is a schematic diagram according to the seventh embodiment of the present disclosure;

[0021] Figure 8 This is a schematic diagram according to the eighth embodiment of the present disclosure;

[0022] Figure 9 This is a schematic diagram according to the ninth embodiment of the present disclosure.

[0023] Figure 10 This is a schematic diagram according to the tenth embodiment of the present disclosure;

[0024] Figure 11 This is a schematic diagram according to the eleventh embodiment of the present disclosure;

[0025] Figure 12 A schematic block diagram of an example electronic device for implementing the map data generation method of embodiments of the present disclosure is shown. Detailed Implementation

[0026] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0027] Figure 1 This is a schematic diagram according to the first embodiment of the present disclosure.

[0028] It should be noted that the execution subject of the map data generation method in this embodiment is a map data generation device, which can be implemented by software and / or hardware. The device can be configured in an electronic device, which may include, but is not limited to, a terminal, a server, etc.

[0029] This disclosure relates to the fields of artificial intelligence technology, such as intelligent transportation and autonomous driving.

[0030] Artificial Intelligence (AI) is a new technological science that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence.

[0031] Intelligent transportation refers to the effective integration of advanced information technology, data communication technology, sensor technology, electronic control technology, and computer technology into the entire transportation management system, thereby establishing a comprehensive transportation and management system that functions in a wide range, in real time, accurately, and efficiently.

[0032] Autonomous driving, also known as driverless cars, computer-driven cars, or wheeled mobile robots, is a type of intelligent connected vehicle that achieves driverless operation through a computer system. Autonomous vehicles rely on the collaborative efforts of artificial intelligence, computer vision, radar, monitoring devices, and a global positioning system to enable computers to perform vehicle-to-infrastructure (V2I) communication and automatically and safely operate motor vehicles without human intervention.

[0033] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0034] like Figure 1 As shown, the map data generation method is executed by the first vehicle, and the method includes:

[0035] The map data generation method described in this disclosure can be executed by a first vehicle, which can be any vehicle in a driving scenario, without limitation.

[0036] S101: In response to a set event occurring in the driving scenario of the first vehicle, determine the location area corresponding to the set event.

[0037] The event to be set can be, for example, an environmental change event in a vehicle driving scenario, and the environmental change event can be, for example, an obstacle change event, a lane line change event, a road change event, etc. in a vehicle driving scenario, without any restrictions.

[0038] In the vehicle driving scenario, the area corresponding to the event can be called the occurrence location area. This occurrence location area can be specifically, for example, the obstacle change section area or the lane change section area in the vehicle driving scenario, without any restrictions.

[0039] In other words, in this embodiment of the present disclosure, it may be necessary to determine whether a set event occurs in the driving scenario of the first vehicle, and when the set event occurs in the driving scenario, locate the location of the set event and take the location area corresponding to the set event as the location area of ​​the event, without any limitation.

[0040] S102: Obtain the first trajectory information of the first vehicle in the location area where the incident occurred.

[0041] The first trajectory information can be used to describe the trajectory of the first vehicle in the location area where the incident occurred. Specifically, the first trajectory information can be, for example, the vehicle pose information at different times when the first vehicle is in the location area where the incident occurred, without limitation.

[0042] In this embodiment of the disclosure, after a set event occurs in the driving scenario of the first vehicle and the location area corresponding to the set event is determined, the first trajectory information of the first vehicle in the location area can be obtained. Then, the subsequent map data generation method can be triggered based on the first trajectory information. For details, please refer to the following embodiments, which will not be elaborated here.

[0043] In some embodiments, obtaining the first trajectory information of the first vehicle in the location area of ​​the incident can be based on the Global Positioning System (GPS) carried in the first vehicle, which locates the trajectory of the first vehicle in the location area of ​​the incident when the first vehicle passes through the location area of ​​the incident, so as to obtain the vehicle pose information of the first vehicle in the location area of ​​the incident, and the aforementioned obtained vehicle pose information of the first vehicle in the location area of ​​the incident is used as the first trajectory information, without limitation.

[0044] In other embodiments, obtaining the first trajectory information of the first vehicle in the location area of ​​the incident may also involve collecting sensor data of the scene where the first vehicle is located in real time during the driving process of the first vehicle, and locating the first vehicle based on the sensor data collected at the aforementioned different times to obtain the location information of the first vehicle in the location area of ​​the incident at different times, and using the location information of the first vehicle in the location area of ​​the incident determined at the aforementioned different times as the first trajectory information, without limitation.

[0045] S103: Generate target map data corresponding to the location area based on the first trajectory information.

[0046] The target map data corresponding to the location of the incident can be, for example, a local map of the location of the incident, and there are no restrictions on this.

[0047] After obtaining the first trajectory information of the first vehicle in the location area of ​​the incident, this embodiment of the present disclosure can generate a local map corresponding to the location area of ​​the incident based on the first trajectory information, and use the aforementioned generated local map corresponding to the location area of ​​the incident as the target map data corresponding to the location area of ​​the incident, without limitation.

[0048] It is understood that, in this embodiment of the disclosure, since the set event (e.g., environmental change event) may only exist in a certain driving area, when generating a local map corresponding to the location area based on the first trajectory information of the first vehicle in the location area, the map update cycle can be effectively reduced, and the waste of resources caused by updating the entire map in the vehicle driving scenario can be effectively avoided.

[0049] Optionally, in this embodiment of the present disclosure, after obtaining the first trajectory information of the first vehicle in the location area where the incident occurred, and generating target map data corresponding to the location area based on the first trajectory information, the first trajectory information and / or target map data can also be sent to the second vehicle. Thus, the first vehicle can realize timely synchronization of the real-time updated target map data to the second vehicle, thereby ensuring the freshness of the map data in the second vehicle and effectively assisting in improving the safety of the autonomous driving of the second vehicle.

[0050] There are no restrictions on whether the second vehicle is the same as or different from the first vehicle.

[0051] In this embodiment of the disclosure, in response to a predetermined event occurring in the driving scenario of the first vehicle, the location area corresponding to the predetermined event is determined, and the first trajectory information of the first vehicle in the location area is obtained. Based on the first trajectory information, target map data corresponding to the location area is generated. Since the target map data corresponding to the location area is generated based on the first trajectory information of the location area when the predetermined event occurs in the driving scenario of the first vehicle, the map update cycle can be effectively reduced. Furthermore, while ensuring map freshness, the resource waste caused by updating the entire map in the vehicle driving scenario can be effectively avoided.

[0052] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure.

[0053] like Figure 2 As shown, the map data generation method includes:

[0054] S201: Collect the point cloud data to be processed from the driving scene of the first vehicle.

[0055] Among them, the point cloud collected in advance for the driving scenario of the first vehicle during the driving process can be referred to as the point cloud to be processed.

[0056] In other words, in this embodiment of the present disclosure, the first vehicle may be equipped with a corresponding camera component (e.g., LiDAR, which is not limited to this), and then, based on the LiDAR pre-installed in the first vehicle, the driving scene of the first vehicle is collected as the point cloud to be processed during the driving process of the first vehicle.

[0057] S202: Obtain the reference point cloud corresponding to the driving scenario of the first vehicle.

[0058] The reference point cloud is a point cloud pre-collected from the driving scene. Specifically, the reference point cloud can be, for example, the labeled point cloud data collected for the first vehicle's driving scene before an environmental change event occurs in the vehicle driving scene. That is, the corresponding point cloud can be pre-acquired for the first vehicle's driving scene before the first vehicle passes through the location area, and the pre-acquired point cloud can be used as the reference point cloud. Then, the reference point cloud and the point cloud to be processed can be combined to determine whether an environmental change event has occurred in the first vehicle's driving scene. For details, please refer to the following embodiments, which will not be elaborated here.

[0059] S203: Based on the point cloud to be processed and the reference point cloud, determine whether a set event has occurred in the driving scenario of the first vehicle.

[0060] In this embodiment of the present disclosure, after collecting the point cloud to be processed of the driving scene of the first vehicle and obtaining the reference point cloud corresponding to the driving scene of the first vehicle, it can determine whether a set event has occurred in the driving scene of the first vehicle based on the point cloud to be processed and the reference point cloud.

[0061] Understandably, since the point cloud collected for the driving scenario of the first vehicle can be used to represent the scene information in the driving scenario of the first vehicle, when a set time occurs in the driving scenario of the first vehicle, the point cloud in the first driving scenario will also change accordingly. Therefore, based on the point cloud to be processed and the pre-acquired reference point cloud, it is possible to accurately identify whether a set event has occurred in the driving scenario of the first vehicle, and effectively identify the set event in the driving scenario of the first vehicle.

[0062] In some embodiments, determining whether a predetermined event has occurred in the driving scenario of the first vehicle based on the point cloud to be processed and the reference point cloud can be achieved by comparing the point cloud to be processed and the reference point cloud. For example, corresponding point cloud features to be processed can be extracted from the point cloud to be processed, and corresponding reference point cloud features can be extracted from the reference point cloud. Then, the point cloud features to be processed and the reference point cloud features are compared. If the point cloud features to be processed and the reference point cloud features are different, it can be determined that a predetermined event has occurred in the driving scenario of the first vehicle.

[0063] In other embodiments, determining whether a predetermined event has occurred in the driving scenario of the first vehicle is based on the point cloud to be processed and the reference point cloud. Alternatively, the point cloud to be processed and the reference point cloud can be transformed into the same spatial coordinate system. When no environmental change event occurs in the driving scenario of the first vehicle, the coordinates of the point cloud to be processed and the reference point cloud should be the same in the same spatial coordinate system. Thus, it is possible to determine that a predetermined event has occurred in the driving scenario of the first vehicle when there is a large deviation between the coordinates of the point cloud to be processed and the reference point cloud. There is no limitation on this.

[0064] S204: In response to a set event occurring in the driving scenario of the first vehicle, determine the location area corresponding to the set event.

[0065] S205: Obtain the first trajectory information of the first vehicle in the location area where the incident occurred.

[0066] S206: Based on the first trajectory information, generate target map data corresponding to the location area where the incident occurred.

[0067] For a detailed description of S204-S206, please refer to the above embodiments, which will not be repeated here.

[0068] In this embodiment, a point cloud to be processed of the driving scene of the first vehicle is collected, and a reference point cloud corresponding to the driving scene of the first vehicle is obtained. The reference point cloud is a point cloud pre-collected from the driving scene. Based on the point cloud to be processed and the reference point cloud, it is determined whether a set event has occurred in the driving scene of the first vehicle. Based on the point cloud to be processed and the pre-acquired reference point cloud, it is possible to accurately identify whether a set event has occurred in the driving scene of the first vehicle, effectively identify the set event in the driving scene of the first vehicle, and in response to the occurrence of the set event in the driving scene of the first vehicle, determine the occurrence location area corresponding to the set event, obtain the first trajectory information of the first vehicle in the occurrence location area, and generate target map data corresponding to the occurrence location area based on the first trajectory information. Since the target map data corresponding to the occurrence location area is generated based on the first trajectory information of the occurrence location area when the set event occurs in the driving scene of the first vehicle, the map update cycle can be effectively reduced, and the resource waste caused by updating the entire map of the vehicle driving scene can be effectively avoided while ensuring map freshness.

[0069] Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure.

[0070] like Figure 3 As shown, the map data generation method includes:

[0071] S301: Collect the point cloud data to be processed from the driving scene of the first vehicle.

[0072] S302: Obtain a reference point cloud corresponding to the driving scene of the first vehicle, wherein the reference point cloud is a point cloud pre-collected from the driving scene.

[0073] For a detailed description of S301-S302, please refer to the above embodiments, which will not be repeated here.

[0074] S303: Determine the mapping position of the first vehicle.

[0075] Here, the mapping position represents the relative position of the local point cloud of the first vehicle in the point cloud to be processed.

[0076] In other words, in this embodiment of the present disclosure, since the point cloud to be processed is collected for the driving scene of the first vehicle, the point cloud to be processed includes a local point cloud corresponding to the first vehicle. The relative position of the local point cloud corresponding to the first vehicle in the point cloud to be processed can be referred to as the mapping position of the first vehicle.

[0077] In this embodiment of the disclosure, determining the mapping position of the first vehicle can be achieved by constructing a three-dimensional coordinate system with the center of the first vehicle as the center of the coordinate system, and using the position coordinates of the local point cloud corresponding to the vehicle in the three-dimensional coordinate system as the mapping position of the first vehicle. There are no restrictions on this.

[0078] S304: Rasterize the point cloud to be processed to obtain a rasterized point cloud to be processed, and rasterize the reference point cloud to obtain a reference rasterized point cloud.

[0079] In this embodiment of the present disclosure, after acquiring the point cloud to be processed of the driving scene of the first vehicle and obtaining the reference point cloud corresponding to the driving scene of the first vehicle, the point cloud to be processed can be rasterized to obtain a rasterized point cloud corresponding to the point cloud to be processed. This rasterized point cloud can be referred to as the rasterized point cloud to be processed. The reference point cloud is also rasterized to obtain a rasterized point cloud corresponding to the reference point cloud. This rasterized point cloud can be referred to as the reference rasterized point cloud. There are no limitations on this.

[0080] S305: Determine the depth value to be processed corresponding to the rasterized point cloud to be processed, and determine the reference depth value corresponding to the reference rasterized point cloud.

[0081] The value used to quantize the depth of the rasterized point cloud to be processed can be called the depth value to be processed, and the value used to quantize the depth of the reference rasterized point cloud can be called the reference depth value.

[0082] In this embodiment of the disclosure, since the rasterized point to be processed and the reference rasterized point cloud can be regarded as spatial coordinates in a three-dimensional coordinate system, the depth value to be processed corresponding to the rasterized point cloud to be processed and the reference depth value corresponding to the reference rasterized point cloud are determined. Specifically, for example, the spatial coordinates of the rasterized point cloud to be processed in the z-coordinate direction are determined and used as the depth value to be processed, and the spatial coordinates of the reference rasterized point cloud in the z-coordinate direction are determined and used as the reference depth value. Then, based on the depth value to be processed and the reference depth value, the subsequent map data generation method can be triggered. For details, please refer to the following embodiments, which will not be repeated here.

[0083] S306: Determine whether a set event has occurred in the driving scenario of the first vehicle based on the depth value to be processed, the reference depth value, and the relative position.

[0084] In this embodiment of the present disclosure, after determining the depth value to be processed corresponding to the rasterized point cloud to be processed and the reference depth value corresponding to the reference rasterized point cloud, it can determine whether a set event has occurred in the driving scenario of the first vehicle based on the depth value to be processed, the reference depth value, and the relative position. Thus, it is possible to extract the depth value to be processed and the reference depth value from the rasterized point cloud to be processed and the reference rasterized point cloud, which can be specifically quantified. Therefore, it is possible to determine whether a set event has occurred in the driving scenario of the first vehicle more simply and conveniently based on the depth value to be processed, the reference depth value, and the relative position.

[0085] Optionally, in some embodiments, determining whether a predetermined event has occurred in the driving scenario of the first vehicle based on the depth value to be processed, the reference depth value, and the relative position may involve determining at least one target rasterized point cloud from the rasterized point cloud to be processed based on the depth value to be processed and the reference depth value, performing clustering processing on the at least one target rasterized point cloud to obtain a cluster of point clouds to be processed, and then determining whether a predetermined event has occurred in the driving scenario of the first vehicle based on the relative position of the first vehicle in the point cloud to be processed and the cluster of point clouds to be processed used to describe the predetermined event, thereby effectively improving the accuracy of the predetermined event judgment.

[0086] Among them, the target rasterized point cloud can be used to represent objects or environmental change events corresponding to set events in the first vehicle driving scene.

[0087] In some embodiments, determining at least one target rasterized point cloud from the rasterized point cloud to be processed based on the depth value to be processed and the reference depth value can be achieved by comparing the depth value to be processed and the reference depth value, and if the depth value to be processed and the reference depth value are different, the rasterized point cloud to be processed corresponding to the depth value to be processed is taken as the target rasterized point cloud. There is no limitation on this.

[0088] Optionally, in some embodiments, determining at least one target rasterized point cloud from the rasterized point cloud to be processed based on the depth value to be processed and the reference depth value can be achieved by determining the depth difference between the depth value to be processed and the reference depth value, and if the depth difference is less than the difference threshold, then the rasterized point cloud to be processed corresponding to the depth value to be processed is determined as the target rasterized point cloud. In this way, the target rasterized point cloud used to represent the environment or object change event corresponding to the set event can be accurately determined from multiple rasterized point clouds to be processed, which effectively reduces the amount of point cloud data that needs to be processed in the process of setting time determination while ensuring the effect of subsequent setting time determination.

[0089] In other words, in this embodiment of the disclosure, the difference between the depth value to be processed and the reference depth value can be determined as the depth difference, and the depth difference can be compared with a pre-determined difference threshold (wherein, the difference threshold can be combined with the map data generation requirements in the actual business scenario and can be adaptively configured without restriction). If the depth difference is less than the difference threshold, the rasterized point cloud corresponding to the depth value to be processed is determined as the target rasterized point cloud.

[0090] Understandably, for the set events in the first vehicle driving scenario (e.g., environmental change events, which are not restricted), the environmental change events that affect the subsequent driving of subsequent vehicles may specifically manifest as lane line changes, obstacle changes, etc. in the vehicle driving scenario. However, there may also be other environmental change events in the vehicle driving scenario that do not affect vehicle driving, such as speed bumps, small obstacles, etc. In this case, there may be a significant waste of resources when processing the rasterized point cloud to be processed in the vehicle driving scenario.

[0091] Therefore, in this embodiment of the present disclosure, after determining at least one target rasterized point cloud from the rasterized point cloud to be processed, the at least one target rasterized point cloud can be clustered to obtain a point cloud cluster distributed in a more clustered state. This point cloud cluster can be referred to as the point cloud cluster to be processed, without limitation.

[0092] In this embodiment of the present disclosure, after clustering at least one target rasterized point cloud to obtain a point cloud cluster to be processed, it can determine whether a set event has occurred in the driving scenario of the first vehicle based on the relative position and the point cloud cluster to be processed.

[0093] Optionally, in some embodiments, determining whether a predetermined event has occurred in the driving scenario of the first vehicle based on the relative position and the point cloud cluster to be processed can be achieved by obtaining the point cloud density and cluster size of the point cloud cluster to be processed, and determining the reference position of the point cloud cluster to be processed in the point cloud to be processed, wherein the reference position represents the relative position of the point cloud cluster to be processed in the point cloud to be processed, and then determining the positional distance between the mapped position and the reference position. Then, based on the point cloud density, cluster size, and positional distance, it is determined whether a predetermined event has occurred in the driving scenario of the first vehicle. Thus, based on multi-dimensional data such as point cloud density, cluster size, and positional distance, the predetermined time in the driving scenario of the first vehicle can be accurately captured, effectively avoiding the occurrence of misidentification of the predetermined event.

[0094] Since a point cloud cluster is composed of multiple rasterized point clouds, the value used to quantize the rasterized point clouds in the point cloud cluster can be called the point cloud density. Correspondingly, the value used to quantize the size of the point cloud cluster can be called the cluster size.

[0095] In this embodiment of the disclosure, since the point cloud to be processed is collected for the driving scene of the first vehicle, the point cloud to be processed includes a local point cloud corresponding to the point cloud cluster to be processed. The relative position of the local point cloud corresponding to the point cloud cluster to be processed in the point cloud to be processed can be referred to as the reference position of the point cloud cluster to be processed.

[0096] In this embodiment of the present disclosure, after determining the mapping position of the first vehicle and the reference position of the point cloud cluster to be processed in the point cloud to be processed, the positional distance between the mapping position and the reference position can be determined. Then, based on the point cloud density, cluster size, and positional distance, it can be determined whether a set event has occurred in the driving scenario of the first vehicle.

[0097] Optionally, in some embodiments, determining whether a set event has occurred in the driving scenario of the first vehicle based on point cloud density, cluster size, and location distance can be done by determining that a set event has occurred in the driving scenario of the first vehicle when the point cloud density is less than or equal to a density threshold, the cluster size is greater than a size threshold, and the location distance is less than or equal to a distance threshold, and determining that no set event has occurred in the driving scenario of the first vehicle when the point cloud density is greater than the density threshold, the cluster size is less than or equal to the size threshold, or the location distance is greater than the distance threshold.

[0098] In other words, after determining the point cloud density, cluster size, and location distance, the embodiments of this disclosure can compare the point cloud density, cluster size, and location distance with predetermined density thresholds, size thresholds, and distance thresholds. If the point cloud density is less than or equal to the density threshold, the cluster size is greater than the size threshold, and the location distance is less than or equal to the distance threshold, it is determined that a set event has occurred in the driving scenario of the first vehicle. If the point cloud density is greater than the density threshold, the cluster size is less than or equal to the size threshold, or the location distance is greater than the distance threshold, it is determined that no set event has occurred in the driving scenario of the first vehicle. Thus, based on the specific quantified values ​​such as point cloud density, cluster size, location distance, density threshold, size threshold, and distance threshold, it is possible to accurately determine whether a set event has occurred in the driving scenario of the first vehicle, effectively improving the operability of determining the set time.

[0099] S307: In response to a set event occurring in the driving scenario of the first vehicle, determine the location area corresponding to the set event.

[0100] S308: Obtain the first trajectory information of the first vehicle in the location area where the incident occurred.

[0101] S309: Generate target map data corresponding to the location area based on the first trajectory information.

[0102] For detailed descriptions of S307-S309, please refer to the above embodiments, which will not be repeated here.

[0103] In this embodiment, a point cloud of the driving scene of a first vehicle is collected to be processed, and a reference point cloud corresponding to the driving scene of the first vehicle is obtained. The reference point cloud is a point cloud pre-collected from the driving scene. After determining the depth value to be processed corresponding to the rasterized point cloud and the reference depth value corresponding to the reference rasterized point cloud, it is possible to determine whether a predetermined event has occurred in the driving scene of the first vehicle based on the depth value to be processed, the reference depth value, and the relative position. Thus, specific and quantifiable depth values ​​to be processed and reference depth values ​​are extracted from the rasterized point cloud to be processed and the reference rasterized point cloud. Therefore, based on the depth value to be processed, the reference depth value, and the relative position, more precise and quantifiable depth values ​​can be obtained. To easily and conveniently determine whether a predetermined event has occurred in the driving scenario of the first vehicle, and in response to the occurrence of the predetermined event in the driving scenario of the first vehicle, determine the location area corresponding to the predetermined event, obtain the first trajectory information of the first vehicle in the location area, and generate target map data corresponding to the location area based on the first trajectory information. Since the target map data corresponding to the location area is generated based on the first trajectory information of the location area when the predetermined event occurs in the driving scenario of the first vehicle, the map update cycle can be effectively reduced, and the resource waste caused by updating the entire map in the vehicle driving scenario can be effectively avoided while ensuring map freshness.

[0104] Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure.

[0105] like Figure 4 As shown, the map data generation method includes:

[0106] S401: In response to a set event occurring in the driving scenario of the first vehicle, determine the location area corresponding to the set event.

[0107] S402: Obtain the first trajectory information of the first vehicle in the location area where the incident occurred.

[0108] For a detailed description of S401-S402, please refer to the above embodiments, which will not be repeated here.

[0109] S403: Determine the sensing parameter information of the pose detection sensor.

[0110] In this embodiment of the disclosure, the first vehicle includes a pose detection sensor, which may be, for example, an inertial measurement unit (IMU). The first trajectory information is obtained based on the pose detection sensor, and there is no limitation on this.

[0111] The pose detection sensor may have corresponding parameter information, which can be called sensing parameter information. Specifically, the sensing parameter information may be, for example, the sensor extrinsic parameters of the pose detection sensor, without limitation.

[0112] In other words, in this embodiment of the present disclosure, the sensor extrinsic parameters of the pose detection sensor of the first vehicle can be determined, and the aforementioned determined sensor extrinsic parameters can be used as sensing parameter information. Then, based on the sensor extrinsic parameters, the subsequent map data generation method can be triggered. For details, please refer to the following embodiments, which will not be repeated here.

[0113] S404: Acquire at least one point data in the occurrence location area and / or a region image of the occurrence location area.

[0114] Specifically, point data can be, for example, point cloud data corresponding to the location of the occurrence, while the region image can be, for example, an image corresponding to the location of the occurrence; there are no restrictions on this.

[0115] In this embodiment of the disclosure, the first vehicle further includes a camera component, which may specifically be, for example, a lidar, without limitation, and the at least one point data is obtained based on the camera component.

[0116] In this embodiment of the disclosure, the first vehicle further includes a camera component, which may specifically be, for example, a camera. The regional image is obtained based on the camera component capturing images of the region where the incident occurred, and there are no limitations on this.

[0117] In other words, in this embodiment of the present disclosure, when the first vehicle passes through the area where the incident occurred, the point cloud of the area where the incident occurred can be collected as point data based on the camera component of the first vehicle, and the image of the area where the incident occurred can be collected as a region image based on the camera component of the first vehicle, without any limitation.

[0118] S405: Generate a target point cloud corresponding to the location of the occurrence based on the first trajectory information, sensing parameter information, and at least one point data.

[0119] Among them, the target point cloud can be used to represent the overall point cloud information of the area where the incident occurred. The target point cloud can be understood as the point cloud map of the area where the incident occurred, and there are no restrictions on this.

[0120] In this embodiment of the disclosure, after acquiring at least one point data in the occurrence location area, a target point cloud corresponding to the occurrence location area can be generated based on the first trajectory information, sensing parameter information, and at least one point data.

[0121] Optionally, in some embodiments, generating a target point cloud corresponding to the occurrence location area based on the first trajectory information, sensing parameter information, and at least one point data may involve determining the device parameter information of the point cloud acquisition device and generating a target point cloud corresponding to the occurrence location area based on the first trajectory information, the sensing parameter information, the device parameter information, and the at least one point data. This ensures that the generated target point cloud corresponding to the occurrence location area can accurately represent the set event information of the occurrence location area, and that the generated target point cloud can accurately adapt to the occurrence location area, effectively guaranteeing the generation effect of the target point cloud.

[0122] Among them, the point cloud acquisition device can have corresponding parameter information, which can be called device parameter information. Specifically, the device parameter information can be, for example, the device extrinsic parameters of the point cloud acquisition device (e.g., radar extrinsic parameters), without limitation.

[0123] In other words, in this embodiment of the present disclosure, a target point cloud corresponding to the occurrence location area can be generated based on the first trajectory information, the sensing parameter information, the device parameter information, and the at least one point data. This can be achieved by projecting a distance image onto the vertical and horizontal angles of the point data based on the sensing parameter information and the device parameter information, resulting in an image with length = point cloud acquisition device line bundle and width = 360 degrees / horizontal resolution of the point cloud acquisition device. Then, ground point data with vertical angles below a certain threshold are removed, followed by point cloud segmentation to obtain a segmented point cloud. Feature extraction is then performed on the segmented point cloud, specifically by calculating the curvature between adjacent points to extract line and surface features. The point cloud labels of the perception label are used to filter out occluded areas and noise points. Finally, the extracted point cloud features are projected onto the world coordinate system based on the first trajectory information to obtain the target point cloud. No limitations are imposed on this process.

[0124] S406: Generate a target map corresponding to the location of the incident based on the first trajectory information, sensing parameter information, and regional image.

[0125] The target map can be used to represent the overall visual information of the area where the incident occurred. The target map can be understood as a visual map of the area where the incident occurred, and there are no restrictions on this.

[0126] In this embodiment of the disclosure, after acquiring the regional image of the location where the incident occurred, a target map corresponding to the location where the incident occurred can be generated based on the first trajectory information, sensing parameter information, and the regional image.

[0127] Optionally, in some embodiments, generating a target map corresponding to the occurrence location area based on the first trajectory information, the sensing parameter information, and the area image may involve determining the camera parameter information of the camera component and generating a target map corresponding to the occurrence location area based on the first trajectory information, the sensing parameter information, the camera parameter information, and the area image. This ensures that the generated target map corresponding to the occurrence location area can accurately represent the visual information of the set event in the occurrence location area, and that the generated target map can accurately adapt to the occurrence location area, effectively guaranteeing the generation effect of the target map.

[0128] The camera component may have corresponding parameter information, which can be referred to as camera parameter information. Specifically, the camera parameter information may be, for example, the camera component's extrinsic parameters (e.g., camera extrinsic parameters), without limitation.

[0129] In other words, in this embodiment of the present disclosure, a target map corresponding to the location of the occurrence can be generated based on the first trajectory information, the sensing parameter information, the camera parameter information, and the area image.

[0130] Specifically, the region image and the first trajectory information can be aligned to obtain paired trajectory information and image data. The first trajectory information can be mapped onto the paired region image and the occluded point cloud can be filtered to obtain the target projection image. Then, the target projection image can be input into a pre-trained visual map generation model to obtain the target map output by the pre-trained visual map generation model. There are no restrictions on this.

[0131] S407: Use the target point cloud and / or target map together as target map data.

[0132] In this embodiment of the disclosure, after generating a target point cloud corresponding to the occurrence location area based on the first trajectory information, sensing parameter information, and at least one point data, and generating a target map corresponding to the occurrence location area based on the first trajectory information, sensing parameter information, and regional image, the target point cloud and / or target map can be used together as target map data. Since the target point cloud data is generated by combining the point data of the occurrence location area, and the target map is generated by combining the regional image of the occurrence location area, the generated target point cloud and target map can describe the occurrence location area based on both point cloud dimension and visual dimension. Therefore, when the target point cloud and target map are used together as target map data, the reference value of the target map data can be effectively improved, and the generation effect of the map data can be effectively improved.

[0133] In this embodiment of the disclosure, in response to a predetermined event occurring in the driving scenario of the first vehicle, the location region corresponding to the predetermined event is determined, and the first trajectory information of the first vehicle in the location region is obtained. Then, the sensing parameter information of the pose detection sensor is determined, and at least one point data and / or a regional image of the location region are obtained. Then, a target point cloud corresponding to the location region is generated based on the first trajectory information, the sensing parameter information, and the at least one point data; and / or a target map corresponding to the location region is generated based on the first trajectory information, the sensing parameter information, and the regional image. The target point cloud and / or the target map are used together as the target map data. Since the target point cloud data is generated by combining the point data of the location region, and the target map is generated by combining the regional image of the location region, the generated target point cloud and target map can describe the location region based on both point cloud dimension and visual dimension. Therefore, when the target point cloud and target map are used together as the target map data, the reference value of the target map data can be effectively improved, and the generation effect of the map data can be effectively improved.

[0134] Figure 5 This is a schematic diagram according to the fifth embodiment of the present disclosure.

[0135] like Figure 5 As shown, the method for determining the vehicle's pose is executed by the second vehicle, and the method includes:

[0136] The method for determining the vehicle pose described in this disclosure can be executed by a second vehicle. The first vehicle can be any vehicle in a vehicle driving scenario, without limitation.

[0137] S501: Determine the first trajectory information and / or target map data.

[0138] The meanings and descriptions of the same terms as in the above embodiments can be found in the above embodiments, and will not be repeated here.

[0139] The first trajectory information describes the trajectory of the first vehicle in the area where the set event occurred. The set event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information.

[0140] Optionally, in some embodiments, determining the first trajectory information and / or target map data may involve receiving the first trajectory information and / or target map data sent by the first vehicle. This allows the first trajectory information and / or target map data generated by the first vehicle to be synchronized to the second vehicle in a timely manner, so as to update the map data in the second vehicle in a timely manner and effectively ensure the freshness of the map data in the second vehicle.

[0141] S502: Determine the target pose of the second vehicle based on the first trajectory information and / or target map data.

[0142] In this embodiment of the disclosure, after determining the first trajectory information and / or target map data, the second vehicle can be located based on the first trajectory information and / or target map data to obtain the position and attitude of the second vehicle at the current moment, and the aforementioned determined position and attitude of the second vehicle can be used as the target pose of the second vehicle, without limitation.

[0143] In some embodiments, determining the target pose of the second vehicle based on the first trajectory information and / or target map data may involve jointly determining whether the second vehicle has passed through the location area of ​​the incident with the first trajectory information, and when it is determined that the second vehicle has passed through the location area of ​​the incident, locating the second vehicle by combining the target map data of the location area of ​​the incident to determine the target pose of the second vehicle. There are no limitations on this.

[0144] In this embodiment of the disclosure, by determining first trajectory information and / or target map data, wherein the first trajectory information describes the trajectory of the first vehicle in the area where a set event occurs, and the set event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information, and the target pose of the second vehicle is determined based on the first trajectory information and / or target map data, the second vehicle can be located based on the target map data generated by the first vehicle that is compatible with the current driving scenario of the vehicle, so that the determined target pose of the second vehicle can effectively meet the vehicle positioning requirements in the current driving scenario, and effectively improve the vehicle pose determination effect.

[0145] Figure 6 This is a schematic diagram according to the sixth embodiment of the present disclosure.

[0146] like Figure 6 As shown, the map data generation method includes:

[0147] S601: Determine the first trajectory information and / or target map data.

[0148] For a detailed description of S601, please refer to the above embodiments, which will not be repeated here.

[0149] S602: Obtain the second trajectory information of the second vehicle.

[0150] The second trajectory information can be used to describe the trajectory of the second vehicle in the location area where the incident occurred. Specifically, the second trajectory information can be, for example, the vehicle pose information at different times when the second vehicle is in the location area where the incident occurred, without limitation.

[0151] In this embodiment of the disclosure, after a set event occurs in the driving scenario of the second vehicle and the location area corresponding to the set event is determined, the second trajectory information of the second vehicle in the location area can be obtained. Then, the subsequent map data generation method can be triggered based on the second trajectory information. For details, please refer to the following embodiments, which will not be elaborated here.

[0152] In some embodiments, obtaining the second trajectory information of the second vehicle in the location area of ​​the incident can be based on the Global Positioning System (GPS) carried in the second vehicle, which locates the trajectory of the second vehicle in the location area of ​​the incident as the second vehicle passes through the location area of ​​the incident, so as to obtain the vehicle pose information of the second vehicle in the location area of ​​the incident, and the aforementioned obtained vehicle pose information of the second vehicle in the location area of ​​the incident is used as the second trajectory information, without limitation.

[0153] In other embodiments, obtaining the second trajectory information of the second vehicle in the location area of ​​the incident can also be achieved by collecting sensor data of the scene where the second vehicle is located in real time during the driving of the second vehicle, and locating the second vehicle based on the sensor data collected at different times to obtain the location information of the second vehicle in the location area of ​​the incident at different times, and using the location information of the second vehicle in the location area of ​​the incident determined at different times as the second trajectory information. There are no restrictions on this.

[0154] S603: Based on the first trajectory information and the second trajectory information, determine whether the second vehicle has passed through the area where the incident occurred.

[0155] In this embodiment of the present disclosure, after obtaining the first trajectory information and the second trajectory information of the second vehicle, it is possible to determine whether the second vehicle has passed through the location area of ​​the incident based on the first trajectory information and the second trajectory information.

[0156] In some embodiments, determining whether the second vehicle has passed through the location area based on the first trajectory information and the second trajectory information may involve comparing the first trajectory information and the second trajectory information to determine the deviation value between the first trajectory information and the second trajectory information, comparing the deviation value with a predetermined deviation value threshold, and determining whether the second vehicle has passed through the location area when the deviation value is greater than the deviation value threshold.

[0157] In other embodiments, a pre-trained deep learning model can be used to determine whether the second vehicle has passed through the location area based on the first trajectory information and the second trajectory information. That is, the first trajectory information and the second trajectory information can be input into the pre-trained deep learning model to determine whether the second vehicle has passed through the location area based on the output of the pre-trained deep learning model. There are no restrictions on this.

[0158] S604: If the second vehicle passes through the area where the incident occurred, the second vehicle is located based on the second trajectory information and the target map data to obtain the target pose.

[0159] In this embodiment of the disclosure, if the second vehicle passes through the location area, the second vehicle can be located based on the second trajectory information and the target map data to obtain the target pose.

[0160] In other words, in this embodiment of the present disclosure, when it is determined that the second vehicle has passed through the location area, the target map data of the location area and the second trajectory information of the second vehicle in the location area can be combined to locate the second vehicle in order to determine the target pose of the second vehicle, without any limitation.

[0161] In this embodiment of the present disclosure, by determining the first trajectory information and / or target map data, the second trajectory information of the second vehicle is obtained, and based on the first trajectory information and the second trajectory information, it is determined whether the second vehicle has passed through the occurrence location area. When the second vehicle passes through the occurrence location area, the second vehicle is located based on the second trajectory information and the target map data to obtain the target pose. Thus, it is possible to accurately determine whether the second vehicle has passed through the occurrence location area based on the first trajectory information and the second trajectory information, and when the second vehicle passes through the occurrence location area, the second vehicle is located based on the second trajectory information and the target map data of the occurrence pose area, thereby accurately determining the target pose of the second vehicle in the occurrence location area.

[0162] Figure 7 This is a schematic diagram according to the seventh embodiment of the present disclosure.

[0163] like Figure 7 As shown, the map data generation method includes:

[0164] S701: Determine the first trajectory information and / or target map data.

[0165] S702: Obtain the second trajectory information of the second vehicle.

[0166] S703: Based on the first trajectory information and the second trajectory information, determine whether the second vehicle has passed through the area where the incident occurred.

[0167] For a detailed description of S701-S703, please refer to the above embodiments, which will not be repeated here.

[0168] S704: Locate the second vehicle based on the target point cloud and the second trajectory information to obtain the first pose of the second vehicle.

[0169] In this embodiment of the disclosure, after determining whether the second vehicle has passed through the location area based on the first trajectory information and the second trajectory information, the second vehicle can be located based on the target point cloud and the second trajectory information to obtain the current pose of the second vehicle. The pose of the second vehicle determined based on the target point cloud and the second trajectory information can be referred to as the first pose.

[0170] Optionally, in some embodiments, the second vehicle is located based on the target point cloud and the second trajectory information to obtain the first pose of the second vehicle. This can be achieved by identifying point cloud line features and point cloud surface features from the target point cloud. The point cloud line features are used to describe local line information in the target point cloud, and the point cloud surface features are used to describe local region information in the target point cloud. The first pose is determined based on the position coordinates, the point cloud line features, and the point cloud surface features. Since the corresponding point cloud line features and point cloud surface features are extracted from the target point cloud, the extracted line features and surface features can be used to describe the information in the target point cloud while also reducing the amount of feature data in subsequent processing to a certain extent. This ensures the effectiveness of determining the first pose while reducing the amount of data in subsequent feature processing.

[0171] The point cloud line features are used to describe local line information in the target point cloud, and the point cloud surface features are used to describe local region information in the target point cloud.

[0172] In this embodiment, all line features and surface features (in the world coordinate system) in the target point cloud can be used. If the number of features does not meet the threshold, no output is performed. If the number of features meets the threshold, point cloud segmentation and feature extraction are performed to obtain the corresponding point cloud line features and point cloud surface features. Occlusion areas and noise points are filtered out according to the label of the perceived point cloud to obtain point cloud line features and point cloud surface features. Then, the predicted pose of the vehicle is used to transform the point cloud line features and point cloud surface features to the W coordinate system (in the world coordinate system). There are no restrictions on this.

[0173] In this embodiment of the disclosure, after identifying point cloud line features and point cloud surface features from the target point cloud, the first pose is determined based on the position coordinates, the point cloud line features, and the point cloud surface features.

[0174] Optionally, in some embodiments, determining the first pose based on the position coordinates, the point cloud line features, and the point cloud surface features may involve determining a first distance between the position coordinates and the point cloud line features, and determining a second distance between the position coordinates and the point cloud surface features, and performing least-squares processing on the first distance and the second distance to obtain the first pose. This achieves the combined determination of the first distance between the position coordinates and the point cloud line features, and the determination of the second distance between the position coordinates and the point cloud surface features, thereby accurately determining the first pose of the second vehicle in the location region.

[0175] Specifically, the distance between the position coordinates k and the point cloud line features can be determined as the first distance. That is, based on the position coordinates k, the minimum nearest neighbor point u in the target point cloud is found, and the closest point v to u is found. The distance d between k and the line features of u and v (i.e., the point cloud line features) is then calculated. ek The determination process is as follows:

[0176]

[0177] in, Let k be the coordinate of the position. Let u be the coordinates of the feature point in the target point cloud. Let v be the coordinates of the feature point v in the target point cloud.

[0178] Specifically, the second distance can be determined by the distance between the position coordinates k and the point cloud surface feature. That is, based on the position coordinates k, the smallest nearest neighbor feature point u is found in the target point cloud, and then planar feature points v and w are found among u's neighboring feature points to form a planar feature (i.e., the point cloud surface feature). The distance d from the position coordinates k to the plane is then calculated. pk The determination process is as follows:

[0179]

[0180] in, Let k be the coordinate of the position. Let u be the coordinates of the smallest nearest neighbor planar feature point in the target point cloud. Let v be the coordinates of the feature point v in the target point cloud. Let w be the coordinates of the feature point w in the target point cloud.

[0181] In this embodiment of the disclosure, a first distance is determined between the position coordinates and the point cloud line features, and a second distance is determined between the position coordinates and the point cloud surface features. The first distance and the second distance are then subjected to least-squares processing to obtain the first pose. The determination process is as follows:

[0182]

[0183] in, This represents the sum of distance errors between the current point feature and the corresponding point feature in the target point cloud. This represents the sum of distance errors between the current point feature and the corresponding point feature in the target point cloud.

[0184] S705: Locate the second vehicle based on the target map and the second trajectory information to obtain the second vehicle's second pose.

[0185] In this embodiment of the present disclosure, after determining whether the second vehicle has passed through the location area based on the first trajectory information and the second trajectory information, the second vehicle can be located based on the target map and the second trajectory information to obtain the current pose of the second vehicle. The pose of the second vehicle determined based on the target map and the second trajectory information can be referred to as the second pose.

[0186] Optionally, in some embodiments, locating the second vehicle based on the target map and the second trajectory information to obtain the second pose of the second vehicle can be achieved by inputting the target map and the second trajectory information together into a visual positioning model to obtain the second pose output by the visual positioning model. Since the second vehicle is located based on the target map and the second trajectory information to obtain the second pose of the second vehicle using a joint visual positioning model, the logic for determining the second pose can be effectively simplified, the operability of the second pose determination process can be effectively improved, and the efficiency of the second pose determination can be effectively improved.

[0187] In other words, in this embodiment of the present disclosure, after obtaining the target map and the second trajectory information of the location of the occurrence, the target map and the second trajectory information can be input into the visual positioning model together to obtain the second pose output by the visual positioning model, without limitation.

[0188] S706: Determine the target pose based on the first pose and / or the second pose.

[0189] In this embodiment of the disclosure, after obtaining the first pose and / or the second pose of the second vehicle, the target pose can be determined based on the first pose and / or the second pose.

[0190] Specifically, the first pose and / or the second pose can be fused, and the fused pose can be used as the target pose. That is, the first pose and / or the second pose can be input into the pose fusion filter, and the pose fusion filter can fuse the first pose and / or the second pose and output the corresponding target pose. There are no restrictions on this.

[0191] In this embodiment of the disclosure, by determining the first trajectory information and / or target map data, and obtaining the second trajectory information of the second vehicle, and then determining whether the second vehicle has passed through the occurrence location area based on the first trajectory information and the second trajectory information, it is possible to accurately determine whether the second vehicle has passed through the occurrence location area based on the first trajectory information and the second trajectory information. Then, the second vehicle is located based on the target point cloud and the second trajectory information to obtain the first pose of the second vehicle, and the second vehicle is located based on the target map and the second trajectory information to obtain the second pose of the second vehicle. That is, the second vehicle is located based on the point cloud updated in the occurrence location area to obtain the first pose of the second vehicle, and the second vehicle is located based on the visual map updated in the occurrence location area to obtain the second pose of the vehicle. When the first pose and / or the second pose are combined to determine the target pose, the first pose and the second pose can be effectively fused to generate a more accurate target pose, effectively improving the target pose determination effect.

[0192] Figure 8 This is a schematic diagram according to the eighth embodiment of the present disclosure.

[0193] like Figure 8 As shown, the map data generation device 80 includes:

[0194] The first determining module 801 is used to determine the location area corresponding to the setting event in response to a setting event occurring in the driving scenario of the first vehicle.

[0195] The first acquisition module 802 is configured to acquire first trajectory information of the first vehicle in the location area of ​​the incident; and

[0196] The generation module 803 is used to generate target map data corresponding to the location area of ​​the occurrence based on the first trajectory information.

[0197] In some embodiments of this disclosure, such as Figure 9 As shown, Figure 9 This is a schematic diagram according to the ninth embodiment of the present disclosure. The map data generation device 90 includes: a first determining module 901, a first acquiring module 902, and a generating module 903. The map data generation device 90 further includes:

[0198] The sending module 904 is used to send the first trajectory information and / or the target map data to the second vehicle.

[0199] In some embodiments of this disclosure, the map data generation apparatus 90 further includes:

[0200] The first acquisition module 905 is used to acquire the point cloud of the driving scene of the first vehicle.

[0201] The second acquisition module 906 is used to acquire a reference point cloud corresponding to the driving scene of the first vehicle, wherein the reference point cloud is a point cloud pre-collected from the driving scene;

[0202] The second determining module 907 is used to determine whether the set event has occurred in the driving scenario of the first vehicle based on the point cloud to be processed and the reference point cloud.

[0203] In some embodiments of this disclosure, the second determining module 907 further includes:

[0204] The first determining submodule 9071 is used to determine the mapping position of the first vehicle, wherein the mapping position represents the relative position of the local point cloud of the first vehicle in the point cloud to be processed.

[0205] The processing submodule 9072 is used to perform rasterization processing on the point cloud to be processed to obtain a rasterized point cloud to be processed, and to perform rasterization processing on the reference point cloud to obtain a reference rasterized point cloud.

[0206] The second determining submodule 9073 is used to determine the depth value to be processed corresponding to the rasterized point cloud to be processed, and to determine the reference depth value corresponding to the reference rasterized point cloud; and

[0207] The third determining submodule 9074 is used to determine whether the set event has occurred in the driving scenario of the first vehicle based on the depth value to be processed, the reference depth value, and the relative position.

[0208] In some embodiments of this disclosure, the first determining submodule 9074 is further configured to:

[0209] Based on the depth value to be processed and the reference depth value, at least one target rasterized point cloud is determined from the rasterized point cloud to be processed;

[0210] Clustering is performed on the at least one target rasterized point cloud to obtain a point cloud cluster to be processed;

[0211] Based on the relative position and the point cloud cluster to be processed, determine whether the set event has occurred in the driving scenario of the first vehicle.

[0212] In some embodiments of this disclosure, the first determining submodule 9074 is further configured to:

[0213] Determine the depth difference between the depth value to be processed and the reference depth value;

[0214] If the depth difference is less than the difference threshold, then the rasterized point cloud corresponding to the depth value to be processed is determined as the target rasterized point cloud.

[0215] In some embodiments of this disclosure, the first determining submodule 9074 is further configured to:

[0216] Obtain the point cloud density and cluster size of the point cloud cluster to be processed;

[0217] Determine the reference position of the point cloud cluster to be processed in the point cloud to be processed, wherein the reference position represents the relative position of the point cloud cluster to be processed in the point cloud to be processed;

[0218] Determine the positional distance between the mapped position and the reference position;

[0219] The determination of whether the set event occurs in the driving scenario of the first vehicle is based on the point cloud density, the cluster size, and the location distance.

[0220] In some embodiments of this disclosure, the first determining submodule 9074 is further configured to:

[0221] If the point cloud density is less than or equal to a density threshold, the cluster size is greater than a size threshold, and the location distance is less than or equal to a distance threshold, then it is determined that the set event has occurred in the driving scenario of the first vehicle.

[0222] If the point cloud density is greater than the density threshold, or the cluster size is less than or equal to the size threshold, or the location distance is greater than the distance threshold, then it is determined that the set event has not occurred in the driving scenario of the first vehicle.

[0223] In some embodiments of this disclosure, the first vehicle includes: a pose detection sensor, and the first trajectory information is obtained based on the pose detection sensor;

[0224] The generation module 903 is also used for:

[0225] Determine the sensing parameter information of the pose detection sensor;

[0226] Acquire at least one point data and / or a regional image of the occurrence location area;

[0227] Generate a target point cloud corresponding to the location of the occurrence based on the first trajectory information, the sensing parameter information, and the at least one point data; and / or

[0228] A target map corresponding to the location of the incident is generated based on the first trajectory information, the sensing parameter information, and the regional image.

[0229] The target point cloud and / or the target map are used together as the target map data.

[0230] In some embodiments of this disclosure, the first vehicle further includes: a camera assembly, wherein the at least one point data is acquired based on the camera assembly;

[0231] The generation module 903 is also used for:

[0232] Determine the device parameter information of the camera component;

[0233] Based on the first trajectory information, the sensing parameter information, the device parameter information, and the at least one point data, a target point cloud corresponding to the location of the occurrence is generated.

[0234] In some embodiments of this disclosure, the first vehicle further includes: a camera assembly, wherein the area image is acquired based on the camera assembly;

[0235] The generation module 903 is also used for:

[0236] Determine the camera parameter information of the camera component;

[0237] Based on the first trajectory information, the sensing parameter information, the camera parameter information, and the regional image, a target map corresponding to the location of the occurrence is generated.

[0238] It is understood that this embodiment is accompanied by Figure 9 The map data generation device 90 in the above embodiment is the same as the map data generation device 80 in the above embodiment, the first determining module 901 is the same as the first determining module 801 in the above embodiment, the first acquiring module 902 is the same as the first acquiring module 802 in the above embodiment, and the generation module 903 is the same as the generation module 803 in the above embodiment. They can have the same functions and structures.

[0239] It should be noted that the foregoing explanation of the map data generation method also applies to the map data generation device of this embodiment.

[0240] In this embodiment, by responding to a predetermined event occurring in the driving scenario of the first vehicle, the location area corresponding to the predetermined event is determined, and the first trajectory information of the first vehicle in the location area is obtained. Based on the first trajectory information, target map data corresponding to the location area is generated. Since the target map data corresponding to the location area is generated based on the first trajectory information of the location area when the predetermined event occurs in the driving scenario of the first vehicle, the map update cycle can be effectively reduced. Furthermore, while ensuring map freshness, the resource waste caused by updating the entire map in the vehicle driving scenario can be effectively avoided.

[0241] Figure 10 This is a schematic diagram according to the tenth embodiment of the present disclosure.

[0242] like Figure 10 As shown, the vehicle pose determination device 100 includes:

[0243] The third determining module 1001 is used to determine first trajectory information and / or target map data, wherein the first trajectory information describes the trajectory of the first vehicle in the area where the set event occurs, the set event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information.

[0244] The fourth determining module 1002 is used to determine the target pose of the second vehicle based on the first trajectory information and / or the target map data.

[0245] In some embodiments of this disclosure, such as Figure 11 As shown, Figure 11 According to a schematic diagram of the eleventh embodiment of this disclosure, the vehicle pose determination device 110 includes: a third determination module 1101 and a fourth determination module 1102, wherein the third determination module 1101 is further configured to:

[0246] Receive the first trajectory information and / or the target map data sent by the first vehicle.

[0247] In some embodiments of this disclosure, the fourth determining module 1102 further includes:

[0248] The acquisition submodule 11021 is used to acquire the second trajectory information of the second vehicle;

[0249] The fourth determining submodule 11022 is used to determine whether the second vehicle has passed through the location area based on the first trajectory information and the second trajectory information;

[0250] The positioning submodule 11023 is used to locate the second vehicle based on the second trajectory information and the target map data when the second vehicle passes through the location area where the incident occurred, so as to obtain the target pose.

[0251] In some embodiments of this disclosure, the target map data includes: target point cloud and / or target map;

[0252] The positioning submodule 11023 is further used for:

[0253] The second vehicle is located based on the target point cloud and the second trajectory information to obtain the first pose of the second vehicle; and / or

[0254] The second vehicle is located based on the target map and the second trajectory information to obtain the second vehicle's second pose;

[0255] The target pose is determined based on the first pose and / or the second pose.

[0256] In some embodiments of this disclosure, the second trajectory information includes: at least one position coordinate of the second vehicle in a world coordinate system;

[0257] The positioning submodule 11023 is further used for:

[0258] Point cloud line features and point cloud surface features are identified from the target point cloud, wherein the point cloud line features are used to describe local line information in the target point cloud, and the point cloud surface features are used to describe local region information in the target point cloud;

[0259] The first pose is determined based on the position coordinates, the point cloud line features, and the point cloud surface features.

[0260] In some embodiments of this disclosure, the positioning submodule 11023 is further configured to:

[0261] Determine a first distance between the position coordinates and the point cloud line feature, and determine a second distance between the position coordinates and the point cloud surface feature;

[0262] The first distance and the second distance are subjected to least squares processing to obtain the first pose.

[0263] In some embodiments of this disclosure, the positioning submodule 11023 is further configured to:

[0264] The target map and the second trajectory information are input into the visual positioning model to obtain the second pose output by the visual positioning model.

[0265] It is understood that the map data generation device 110 in the accompanying drawings of this embodiment is the same as the map data generation device 100 in the above embodiment, the third determining module 1101 is the same as the third determining module 1001 in the above embodiment, and the fourth determining module 1102 is the same as the fourth determining module 1002 in the above embodiment, and may have the same function and structure.

[0266] It should be noted that the foregoing explanation of the method for determining the vehicle's pose also applies to the vehicle pose determination device of this embodiment.

[0267] In this embodiment, by determining first trajectory information and / or target map data, wherein the first trajectory information describes the trajectory of the first vehicle in the area where the set event occurs, and the set event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information, and the target pose of the second vehicle is determined based on the first trajectory information and / or target map data, the second vehicle can be located based on the target map data generated by the first vehicle that is compatible with the current driving scenario, so that the determined target pose of the second vehicle can effectively meet the vehicle positioning requirements in the current driving scenario, and effectively improve the vehicle pose determination effect.

[0268] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0269] Figure 12 A schematic block diagram of an example electronic device is shown for implementing a map data generation method or a vehicle pose determination method according to embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0270] like Figure 12 As shown, device 1200 includes a computing unit 1201, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1202 or a computer program loaded from storage unit 1208 into random access memory (RAM) 1203. The RAM 1203 may also store various programs and data required for the operation of device 1200. The computing unit 1201, ROM 1202, and RAM 1203 are interconnected via bus 1204. Input / output (I / O) interface 1205 is also connected to bus 1204.

[0271] Multiple components in device 1200 are connected to I / O interface 1205, including: input unit 1206, such as keyboard, mouse, etc.; output unit 1207, such as various types of monitors, speakers, etc.; storage unit 1208, such as disk, optical disk, etc.; and communication unit 1209, such as network card, modem, wireless transceiver, etc. Communication unit 1209 allows device 1200 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0272] The computing unit 1201 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1201 performs the various methods and processes described above, such as map data generation methods or vehicle pose determination methods. For example, in some embodiments, the map data generation method or vehicle pose determination method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1208. In some embodiments, part or all of the computer program can be loaded and / or installed on device 1200 via ROM 1202 and / or communication unit 1209. When the computer program is loaded into RAM 1203 and executed by the computing unit 1201, one or more steps of the map data generation method or vehicle pose determination method described above can be performed. Alternatively, in other embodiments, the computing unit 1201 may be configured in any other suitable manner (e.g., by means of firmware) to perform a map data generation method or a vehicle pose determination method.

[0273] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0274] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0275] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0276] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0277] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0278] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0279] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0280] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A map data generation method, executed by a first vehicle, the method comprising: In response to a predetermined event occurring in the driving scenario of the first vehicle, the location area corresponding to the predetermined event is determined; Obtain the first trajectory information of the first vehicle in the area where the incident occurred; as well as Based on the first trajectory information, generate target map data corresponding to the location of the occurrence; The first vehicle includes a pose detection sensor, and the first trajectory information is obtained based on the pose detection sensor. The step of generating target map data corresponding to the location area based on the first trajectory information includes: Determine the sensing parameter information of the pose detection sensor; Acquire at least one point data and / or a regional image of the occurrence location area; Generate a target point cloud corresponding to the location of the occurrence based on the first trajectory information, the sensing parameter information, and the at least one point data; and / or A target map corresponding to the location of the incident is generated based on the first trajectory information, the sensing parameter information, and the regional image. The target point cloud and / or the target map are used together as the target map data.

2. The method according to claim 1, further comprising: Send the first trajectory information and / or the target map data to the second vehicle.

3. The method according to claim 1, further comprising: Collect the point cloud of the driving scene of the first vehicle to be processed; Obtain a reference point cloud corresponding to the driving scene of the first vehicle, wherein the reference point cloud is a point cloud pre-collected from the driving scene; Based on the point cloud to be processed and the reference point cloud, determine whether the set event has occurred in the driving scenario of the first vehicle.

4. The method according to claim 3, wherein, The step of determining whether the predetermined event has occurred in the driving scenario of the first vehicle based on the point cloud to be processed and the reference point cloud includes: Determine the mapping position of the first vehicle, wherein the mapping position represents the relative position of the local point cloud of the first vehicle in the point cloud to be processed; The point cloud to be processed is rasterized to obtain a rasterized point cloud to be processed, and the reference point cloud is rasterized to obtain a reference rasterized point cloud. Determine the depth value to be processed corresponding to the rasterized point cloud to be processed, and determine the reference depth value corresponding to the reference rasterized point cloud; and Based on the depth value to be processed, the reference depth value, and the relative position, it is determined whether the set event occurs in the driving scenario of the first vehicle.

5. The method according to claim 4, wherein, Determining whether the predetermined event has occurred in the driving scenario of the first vehicle based on the depth value to be processed, the reference depth value, and the relative position includes: Based on the depth value to be processed and the reference depth value, at least one target rasterized point cloud is determined from the rasterized point cloud to be processed; Clustering is performed on the at least one target rasterized point cloud to obtain a point cloud cluster to be processed; Based on the relative position and the point cloud cluster to be processed, determine whether the set event has occurred in the driving scenario of the first vehicle.

6. The method according to claim 5, wherein, The step of determining at least one target rasterized point cloud from the rasterized point cloud to be processed based on the depth value to be processed and the reference depth value includes: Determine the depth difference between the depth value to be processed and the reference depth value; If the depth difference is less than the difference threshold, then the rasterized point cloud corresponding to the depth value to be processed is determined as the target rasterized point cloud.

7. The method according to claim 5, wherein, Determining whether the predetermined event has occurred in the driving scenario of the first vehicle based on the relative position and the point cloud cluster to be processed includes: Obtain the point cloud density and cluster size of the point cloud cluster to be processed; Determine the reference position of the point cloud cluster to be processed in the point cloud to be processed, wherein the reference position represents the relative position of the point cloud cluster to be processed in the point cloud to be processed; Determine the positional distance between the mapped position and the reference position; The determination of whether the set event occurs in the driving scenario of the first vehicle is based on the point cloud density, the cluster size, and the location distance.

8. The method according to claim 7, wherein, Determining whether the predetermined event occurs in the driving scenario of the first vehicle based on the point cloud density, the cluster size, and the location distance includes: If the point cloud density is less than or equal to a density threshold, the cluster size is greater than a size threshold, and the location distance is less than or equal to a distance threshold, then it is determined that the set event has occurred in the driving scenario of the first vehicle. If the point cloud density is greater than the density threshold, or the cluster size is less than or equal to the size threshold, or the location distance is greater than the distance threshold, then it is determined that the set event has not occurred in the driving scenario of the first vehicle.

9. The method according to claim 1, wherein the first vehicle further comprises: A point cloud acquisition device, wherein the at least one point data is acquired based on the point cloud acquisition device; The step of generating a target point cloud corresponding to the location of occurrence based on the first trajectory information, the sensing parameter information, and the at least one point data includes: Determine the device parameter information of the point cloud acquisition device; Based on the first trajectory information, the sensing parameter information, the device parameter information, and the at least one point data, a target point cloud corresponding to the location of the occurrence is generated.

10. The method according to claim 1, wherein the first vehicle further comprises: A camera component, wherein the area image is acquired based on the camera component; The step of generating a target map corresponding to the location of the occurrence based on the first trajectory information, the sensing parameter information, and the region image includes: Determine the camera parameter information of the camera component; Based on the first trajectory information, the sensing parameter information, the camera parameter information, and the regional image, a target map corresponding to the location of the occurrence is generated.

11. A method for determining the position and orientation of a vehicle, executed by a second vehicle, the method comprising: Determine first trajectory information and / or target map data, wherein the first trajectory information describes the trajectory of the first vehicle in the area where a set event occurs, the set event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information, and the target map data includes: target point cloud and / or target map. Obtain the second trajectory information of the second vehicle; Based on the first trajectory information and the second trajectory information, determine whether the second vehicle has passed through the area where the incident occurred; If the second vehicle passes through the area where the incident occurred, the second vehicle is located based on the target point cloud and the second trajectory information to obtain the first pose of the second vehicle; and / or the second vehicle is located based on the target map and the second trajectory information to obtain the second pose of the second vehicle; and the target pose of the second vehicle is determined based on the first pose and / or the second pose.

12. The method according to claim 11, wherein, The determination of the first trajectory information and / or target map data includes: Receive the first trajectory information and / or the target map data sent by the first vehicle.

13. The method according to claim 11, wherein the second trajectory information includes: The coordinates of at least one position of the second vehicle in the world coordinate system; The step of locating the second vehicle based on the target point cloud and the second trajectory information to obtain the first pose of the second vehicle includes: Point cloud line features and point cloud surface features are identified from the target point cloud, wherein the point cloud line features are used to describe local line information in the target point cloud, and the point cloud surface features are used to describe local region information in the target point cloud; The first pose is determined based on the position coordinates, the point cloud line features, and the point cloud surface features.

14. The method as described in claim 13, characterized in that, Determining the first pose based on the position coordinates, the point cloud line features, and the point cloud surface features includes: Determine a first distance between the position coordinates and the point cloud line feature, and determine a second distance between the position coordinates and the point cloud surface feature; The first distance and the second distance are subjected to least squares processing to obtain the first pose.

15. The method according to claim 11, wherein, The step of locating the second vehicle based on the target map and the second trajectory information to obtain the second vehicle's second pose includes: The target map and the second trajectory information are input into the visual positioning model to obtain the second pose output by the visual positioning model.

16. A map data generation apparatus, executed by a first vehicle, the apparatus comprising: The first determining module is used to determine the location area corresponding to the set event in response to a set event occurring in the driving scenario of the first vehicle. The first acquisition module is used to acquire the first trajectory information of the first vehicle in the location area where the incident occurred. as well as The generation module is used to generate target map data corresponding to the location of the occurrence based on the first trajectory information; The first vehicle includes: a pose detection sensor, wherein the first trajectory information is obtained based on the pose detection sensor; Specifically, the generation module is used for: Determine the sensing parameter information of the pose detection sensor; Acquire at least one point data and / or a regional image of the occurrence location area; Generate a target point cloud corresponding to the location of the occurrence based on the first trajectory information, the sensing parameter information, and the at least one point data; and / or A target map corresponding to the location of the incident is generated based on the first trajectory information, the sensing parameter information, and the regional image. The target point cloud and / or the target map are used together as the target map data.

17. A vehicle pose determination device, executed by a second vehicle, the device comprising: The third determining module is used to determine the first trajectory information and / or target map data, wherein the first trajectory information describes the trajectory of the first vehicle in the area where the set event occurs, the set event has occurred in the driving scenario of the first vehicle, and the target map data is generated by the first vehicle based on the first trajectory information, and the target map data includes: target point cloud and / or target map. The fourth determining module is used to acquire the second trajectory information of the second vehicle; determine whether the second vehicle has passed through the occurrence location area based on the first trajectory information and the second trajectory information; if the second vehicle has passed through the occurrence location area, locate the second vehicle based on the target point cloud and the second trajectory information to obtain the first pose of the second vehicle; and / or locate the second vehicle based on the target map and the second trajectory information to obtain the second pose of the second vehicle; and determine the target pose of the second vehicle based on the first pose and / or the second pose.

18. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-10, or the method of any one of claims 11-15.

19. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-10, or to perform the method according to any one of claims 11-15.

20. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-10, or performs the steps of the method according to any one of claims 11-15.

Images