Map generation method, driving assistance system and vehicle

Abstract

The embodiment of the invention provides a map generation method, a driving assistance system and a vehicle, and relates to the technical field of map generation and auxiliary driving, the method comprises the following steps: obtaining environment perception data of a target road area, the target road area is determined according to the real-time position of a target vehicle, and the environment perception data is acquired according to the real-time position of the target vehicle; the environment perception data is used for representing multi-modal environment characteristics in the target road area; analyzing the environmental perception data to obtain road element information; and carrying out Voronoi diagram modeling by utilizing the road element information, and generating a regional environment map of the target road region. The technical problems of poor timeliness and low accuracy of a map generation method in related technologies are solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of map generation and assisted driving, and in particular, to a map generation method, a driving assistance system, and a vehicle. Background Art

[0002] In application scenarios involving assisted driving, road information is usually collected during vehicle driving to update the map, and the map is used to assist in adjusting the driving behavior of the vehicle. Therefore, the above application scenarios pose higher requirements for the accuracy and timeliness of map updating.

[0003] In the related art, the methods for generating maps based on road information mainly include the following two. First, a map is constructed by generating high-resolution three-dimensional point cloud data. However, in a dynamic driving environment, the generation speed of three-dimensional point cloud data is slow, resulting in a high update delay when using this method to generate a map. That is to say, the timeliness of this map generation method is poor and the accuracy is low. Second, a map is generated by using the road information obtained by identifying vehicle cameras and vision algorithms. However, the data quality of the road information collected by this method is easily affected by environmental factors. For example, in a complex driving environment (such as an environment with bad weather, an environment with blurred road markings, etc.), the accuracy of the identified road information is poor, and thus it is easy to cause low accuracy of this map generation method.

[0004] Therefore, how to enhance the timeliness and accuracy of the map generation method to improve the adaptability of the map generation method to complex environments has become one of the important technical problems in the related technical field. For the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] The embodiments of the present application provide a map generation method, a driving assistance system, and a vehicle, aiming to improve the problems of poor timeliness and low accuracy of the map generation method in the related art.

[0006] According to one aspect of the embodiments of the present application, a map generation method is provided, including: obtaining environmental perception data of a target road area, where the target road area is determined according to the real-time position of a target vehicle, and the environmental perception data is used to characterize multi-modal environmental features within the target road area; analyzing the environmental perception data to obtain road element information; and using the road element information to perform Voronoi diagram modeling to generate a regional environmental map of the target road area.

[0007] The above map generation method provided by the embodiments of the present application achieves the following technical effects: First, according to the real-time position of the target vehicle, the target road area is dynamically adjusted to ensure that the target road area can be updated according to the real-time position of the target vehicle, enhancing the timeliness of the determined target road area. Using the real-time determined target road area, the environmental perception data corresponding to the target road area is obtained, enhancing the timeliness of the environmental perception data and improving the accuracy of the environmental perception data. Second, the environmental perception data is analyzed to obtain road element information from the environmental perception data, and further the Voronoi diagram modeling is performed using the road element information, which can more accurately determine the topological structure of the target road area and improve the timeliness and accuracy of the regional environmental map. Thus, the embodiments of the present application determine the target road area according to the real-time position of the target vehicle, obtain the environmental perception data of the target road area with better timeliness, and perform Voronoi diagram modeling using the road element information obtained by analyzing the environmental perception data, achieving the purpose of generating an environmental map with better timeliness and higher accuracy, thereby realizing the technical effects of enhancing the timeliness of the map generation method and improving the accuracy of the map generation method, and further solving the technical problems of poor timeliness and low accuracy of the map generation method in the related art.

[0008] Optionally, the map generation method further includes: obtaining the real-time position based on a predefined update frequency parameter; and determining the target road area using the real-time position and a predefined sliding window parameter.

[0009] The above optional embodiments of the present application can achieve the following technical effects: Using the predefined update frequency parameter, the current position information of the target vehicle can be determined in real time, and the real-time position of the target vehicle can be obtained. Then, using the real-time position of the target vehicle and the predefined sliding window parameter, the target road area is dynamically adjusted to ensure that the target road area is updated in a timely manner during the vehicle driving process, enhancing the timeliness of the determined target road area and providing a basis for subsequently obtaining the environmental perception data corresponding to the target road area, avoiding the situation where the timeliness of the environmental perception data deteriorates due to the delay in updating the target road area. Thus, the present application obtains the real-time position based on the predefined update frequency parameter, and uses the real-time position and the predefined sliding window parameter to dynamically adjust the target road area, enhancing the timeliness of the target road area and being able to obtain environmental perception data with better timeliness, thereby enhancing the timeliness of the map generation method.

[0010] Optionally, the environmental perception data includes environmental point cloud data and environmental image data. The environmental point cloud data is used to characterize the spatial structure features of road elements in the target road area, and the environmental image data is used to characterize the visual features of road elements. Analyzing the environmental perception data to obtain road element information includes: extracting and labeling elements from the environmental point cloud data and the environmental image data to obtain road element information, where the road element information is used to data-identify road elements according to element types.

[0011] The above optional embodiments of the present application can achieve the following technical effects: By using both environmental point cloud data and environmental image data as environmental perception data, environmental perception data can be provided from multiple dimensions, improving the comprehensiveness and accuracy of environmental perception data, providing a more comprehensive and accurate data basis for subsequent analysis of environmental perception data. Even in a complex and changeable environment, road element information can be accurately obtained. Therefore, by fusing environmental point cloud data and environmental image data for element extraction and labeling, the accuracy and reliability of road element information are improved, and the adaptability of the map generation method is enhanced.

[0012] Optionally, the road element information includes lane line information and other element information. Using the road element information for Voronoi diagram modeling to generate a regional environmental map includes: using the lane line information for Voronoi diagram modeling to obtain a road network model of the target road area; integrating and integrating the other element information and the road network model to generate a regional environmental map.

[0013] The above optional embodiments of the present application can achieve the following technical effects: Using the lane line information for Voronoi diagram modeling, by converting the lane line information into a geometric representation of the road area, converting the complex analog signal form of lane line information into a simpler geometric representation form, the position of each lane can be accurately determined, a more accurate road network can be established, and the accuracy of the road network model of the target road area is improved; furthermore, integrating and integrating the identified and labeled other element information with the road network model to supplement the detailed information of the road network model and generate a more comprehensive regional environmental map. Therefore, by using the lane line information for Voronoi diagram modeling, a road network model with higher accuracy is built, and by integrating the other element information with the road network model, the comprehensiveness of the regional environmental map is enhanced, thereby improving the accuracy of the map generation method.

[0014] Optionally, a Voronoi diagram is modeled using lane line information to obtain a road network model, including: performing coordinate transformation on the lane line information to determine the target point set data in the body coordinate system of the target vehicle; dividing the target road area based on the target point set data and the target area division algorithm to determine multiple Voronoi regions corresponding to multiple lanes in the target road area; constructing a road network model based on the multiple Voronoi regions.

[0015] The above optional embodiment of the present application can achieve the following technical effects: By performing coordinate transformation on the lane line information and transforming the lane line information to the body coordinate system of the target vehicle for calculation, it can not only reduce the complexity of processing data, reduce the demand for computing resources, and improve the efficiency of data processing, but also analyze the lane line information based on the body coordinate system of the target vehicle, and can more accurately determine the position of the lane line relative to the target vehicle. Then, according to the target point set data and the target area division algorithm, the Voronoi region corresponding to each lane in the target road area can be determined, so as to determine multiple Voronoi regions corresponding to multiple lanes in the target road area, distinguish different lanes, and clearly represent multiple lanes in the road network model based on the multiple Voronoi regions, construct a more accurate road network model, and avoid the situation where it is impossible to accurately construct a road network model due to a large number of lanes, thereby improving the accuracy of the map generation method.

[0016] Optionally, performing coordinate transformation on the lane line information to determine the target point set data includes: extracting lane boundary point data from the lane line information; constructing a virtual lane center line based on the boundary point data; performing coordinate transformation on the lane boundary point data and the coordinates of multiple key points on the virtual lane center line to obtain the target point set data.

[0017] The above optional embodiments of the present application can achieve the following technical effects: Extracting lane boundary point data from lane line information can reduce the influence of error point data, avoid the situation of low accuracy of lane position caused by error point data, ensure that the position of the lane can be accurately determined, and then, based on the boundary point data, construct a virtual lane center line, and perform coordinate transformation on the lane boundary point data and the coordinates of multiple key points on the virtual lane center line. This can not only combine the generated virtual lane center line with the perceived lane boundary point data to obtain more accurate target point set data, but also specifically select the lane boundary point data and the coordinates of multiple key points on the virtual lane center line, reduce the point data that needs to be processed by coordinate transformation, and reduce the consumption of computing resources. On the premise of ensuring the accuracy of the target point set data, the efficiency of obtaining the target point set data is improved. Thus, the present application constructs a virtual lane center line based on the boundary point data extracted from the lane line information, combines the perceived lane boundary point data with the coordinates of multiple key points on the virtual lane center line, improves the accuracy of the target point set data, and thus can accurately provide data support for the subsequent construction of the road network model.

[0018] Optionally, constructing a road network model based on multiple Voronoi regions includes: determining the topological relationship between multiple lanes according to the regional boundaries of the multiple Voronoi regions and the adjacent relationship between the multiple Voronoi regions; constructing a road network model based on the topological relationship.

[0019] The above optional embodiments of the present application can achieve the following technical effects: By according to the regional boundaries of the multiple Voronoi regions and the adjacent relationship between the multiple Voronoi regions, the lane boundary of each lane and the adjacent relationship between different lanes can be determined more accurately, so that the topological relationship between the multiple lanes can be determined more accurately. Then, based on the topological relationship, not only can a more accurate road network be determined, improving the accuracy of the road network model of the target road area, but also the construction process of the road network model can be simplified, the efficiency of constructing the road network model is improved, and it is beneficial to update the road network model in real time.

[0020] Optionally, the environmental perception data further includes dynamic perception data, which is used to characterize the dynamic characteristics between the target vehicle and the road elements in the target road area. The map generation method further includes: performing driving decision analysis according to the dynamic perception data and the regional environmental map to generate driving suggestions, where the driving suggestions are used to assist in adjusting the driving operations of the target vehicle in the target road area.

[0021] The above optional embodiments of the present application can achieve the following technical effects: By combining dynamic perception data with the regional environment map for driving decision analysis, it is possible to utilize the dynamic characteristics of the real-time changes in the environment within the target road area to generate more accurate driving suggestions, and then more accurately guide the driving operations of the target vehicle in the target road area, improving the safety of the vehicle during driving and enhancing the overall performance of the vehicle.

[0022] According to another aspect of the embodiments of the present application, there is also provided a driving assistance system, including: an acquisition module, configured to acquire the real-time driving data of a target vehicle within a target road area and the functional indicators corresponding to a target driving assistance function; a processing module, configured to perform driving assistance operations on the target vehicle according to the real-time driving data, the regional environment map, and the functional indicators; wherein, the regional environment map is generated according to the map generation method of any one of the above.

[0023] The above driving assistance system provided by the embodiments of the present application achieves the following technical effects: By using the acquisition module to acquire the real-time driving data of the target vehicle within the target road area and the functional indicators corresponding to the target driving assistance function, it is possible to update the real-time driving data and functional indicators in a timely manner, providing data support with better timeliness and higher accuracy for subsequent driving assistance operations on the target vehicle. Furthermore, by generating an environment map with better timeliness and higher accuracy according to the map generation method of any one of the above, and combining the real-time driving data, the regional environment map, and the functional indicators, the timeliness and accuracy of the driving assistance operations are improved, avoiding the situation where it is impossible to accurately perform driving assistance operations on the target vehicle due to poor timeliness and low accuracy of the regional environment map, and enhancing the intelligence and safety of the driving assistance system.

[0024] According to another aspect of the embodiments of the present application, there is also provided a vehicle, including an in-vehicle processor and an in-vehicle memory, wherein the in-vehicle memory is used to store a computer program; the in-vehicle processor is configured to execute the computer program stored on the memory to implement the map generation method of any one of the above.

[0025] The above vehicle provided by the embodiments of the present application achieves the following technical effects: Storing the computer program corresponding to the map generation method of any one of the above in the in-vehicle memory, and using the in-vehicle processor to execute the computer program stored on the memory. By determining the target road area according to the real-time position of the target vehicle, acquiring the environmental perception data of the target road area with better timeliness, and performing Voronoi diagram modeling using the road element information obtained by analyzing the environmental perception data, it is possible to generate an environment map with better timeliness and higher accuracy, more accurately guide the driving operations of the target vehicle in the target road area, reduce the driving difficulty of the driver, improve the comfort and convenience of the driver, enhance the overall performance of the vehicle, and thus improve the safety of vehicle driving.

[0026] It should be noted that the general description in the above content and the detailed description hereinafter are only for exemplifying and explaining this application, and do not constitute a limitation to this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of this application and form a part of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0028] Figure 1 is a flowchart of a map generation method provided by one embodiment of this application;

[0029] Figure 2 is a schematic diagram of an optional driving assistance method provided by one embodiment of this application;

[0030] Figure 3 is a structural diagram of a driving assistance system provided by one embodiment of this application;

[0031] Figure 4 is a structural diagram of a vehicle provided by one embodiment of this application;

[0032] Figure 5 is a hardware structural block diagram of a computing terminal for implementing the map generation method provided by one embodiment of this application;

[0033] Figure 6 is a structural diagram of a map generation device provided by one embodiment of this application;

[0034] Figure 7 is a structural diagram of an electronic device provided by one embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] In order to make the technical problems, technical solutions and beneficial effects solved by this application clearer, the following further describes this application in detail with reference to embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0036] It should be noted that the terms "first", "second", etc. in the specification, claims and the above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] First, some nouns or terms that appear in the process of describing the embodiments of this application are applicable to the following explanations:

[0038] A Voronoi Diagram is a data structure applied in the computer field. By using the Voronoi Diagram, road element information can be converted into geometric feature information, so that in road environment mapping, the Voronoi Diagram is used to represent the topological structure of the road network.

[0039] A map generation method provided by an embodiment of this application includes: obtaining environmental perception data of a target road area, where the target road area is determined according to the real-time position of a target vehicle, and the environmental perception data is used to characterize multi-modal environmental features within the target road area; analyzing the environmental perception data to obtain road element information; and using the road element information to perform Voronoi diagram modeling to generate a regional environmental map of the target road area.

[0040] The above map generation method provided by the embodiment of this application achieves the following technical effects: By determining the target road area according to the real-time position of the target vehicle, obtaining environmental perception data of the target road area with better timeliness, and using the road element information obtained by analyzing the environmental perception data to perform Voronoi diagram modeling, the purpose of generating an environmental map with better timeliness and higher accuracy is achieved, thereby realizing the technical effects of enhancing the timeliness of the map generation method and improving the accuracy of the map generation method, and further solving the technical problems of poor timeliness and low accuracy in the map generation method in the related art.

[0041] Embodiment 1

[0042] An embodiment of this application provides a map generation method. Please refer to Figure 1 , including the following steps:

[0043] S110: Obtain the environmental perception data of the target road area, where the target road area is determined according to the real-time position of the target vehicle, and the environmental perception data is used to characterize the multi-modal environmental features within the target road area;

[0044] S120: Analyze the environmental perception data to obtain road element information;

[0045] S130: Use the road element information to perform Voronoi diagram modeling to generate the regional environmental map of the target road area.

[0046] The above real-time position can be used to represent the current position of the target vehicle. The above target road area can be dynamically adjusted according to the real-time position of the target vehicle. The target road area can be a local area of the map to be updated. By using the target road area, the target road area for data collection can be updated in a timely manner, ensuring that the map generation system can capture the surrounding environment information of the current position of the target vehicle in real time, ensuring the timeliness of the obtained environmental perception data, and avoiding the situation where the timeliness of the obtained environmental perception data is poor due to the non-real-time update of the target road area for data collection, resulting in the inability to provide effective data support for generating the regional environmental map, thereby leading to poor timeliness of the generated regional environmental map.

[0047] The above environmental perception data can be obtained by collecting the environmental information of the target road area through in-vehicle sensors (such as visual sensors, lidar sensors, radar sensors, thermal sensors, temperature sensors, humidity sensors, light sensors, etc.). The installation parameters of the above in-vehicle sensors (such as installation position, installation angle, installation quantity, etc.) can be set according to the actual situation to cover the key areas around the target vehicle, avoiding the situation where the accuracy of the environmental perception data is low due to the existence of data collection blind spots.

[0048] The above multi-modal environmental features can be the feature information of the environmental state within the target road area in multiple dimensions. The multi-modal environmental features can include: the spatial information of the target road area, the visual information of the target road area, the dynamic information of the target road area, the thermal imaging information of the target road area, the climate information of the target road area (such as light intensity, humidity, etc.), and the cloud network information of the target road area. By using the multi-modal environmental features, the environmental feature information within the target road area can be characterized more accurately, avoiding the limitations of single feature information in a complex and changeable driving environment, and providing an accurate data basis for subsequent generation of the regional environmental map.

[0049] In an exemplary application scenario, the real-time position of a target vehicle is obtained. Based on the real-time position of the target vehicle, the target road area is dynamically adjusted to ensure that the target road area for data collection can be updated in a timely manner. Then, each in-vehicle sensor among multiple in-vehicle sensors of the target vehicle is used to collect environmental features within the target road area, and environmental perception data representing the multi-modal environmental features within the target road area is obtained.

[0050] It is easy to understand that in the embodiments of the present application, the target road area is dynamically updated according to the real-time position of the target vehicle, and the corresponding environmental perception data within the target road area is obtained in real time, which can update the target road area for data collection in a timely manner, thereby enhancing the timeliness of the environmental perception data and improving the accuracy of the environmental perception data. In addition, the environmental perception data can be used to represent the multi-modal environmental features within the target road area. Compared with the solutions in the related art that only use single-modal environmental feature information, the environmental perception data in the embodiments of the present application can better adapt to the complex and changeable driving environment. Even in a high-dynamic environment (such as a driving environment under bad weather), real-time analysis can be performed using environmental feature information in multiple dimensions, improving the accuracy of the environmental perception data. Therefore, the environmental perception data in the embodiments of the present application can provide data support with higher accuracy and better timeliness for generating a regional environmental map, thereby enhancing the timeliness and accuracy of the map generation method.

[0051] The above-mentioned road element information can be extracted from the environmental perception data. The road element information can be used to represent the road characteristics of the target road area, and the road element information can include lane lines, road edges, stop lines, zebra crossings, ground arrows, traffic lights, access ramps, speed bumps, parking spaces, walls, columns, etc.

[0052] The above-mentioned regional environmental map can be used to represent the detailed environmental features within the target road area, and the regional environmental map can be dynamically updated. As the real-time position of the target vehicle changes, the target road area is updated according to the real-time position, thereby updating the regional environmental map to ensure the timeliness of the regional environmental map and avoiding the situation where the current regional environmental map cannot support the driving assistance function due to high latency of the regional environmental map.

[0053] In an exemplary application scenario, key points in the road element information are used as inputs, and a Voronoi diagram modeling is performed using a modeling algorithm to construct a Voronoi diagram topological structure and generate a more accurate regional environmental map of the target road area. The above-mentioned modeling algorithm can include, but is not limited to, algorithms based on scan lines, algorithms based on pseudo-triangulations (such as the Boggs algorithm), and clustering algorithms (such as the Lloyd algorithm).

[0054] It should be noted that the map parameters of the above regional environmental map (such as map resolution, annotation accuracy of road elements, map scaling ratio, map coordinate system setting, etc.) can be adjusted according to the actual situation to generate a regional environmental map with higher accuracy.

[0055] It is easy to understand that in the embodiments of the present application, by analyzing the environmental perception data, obtaining road element information from the environmental perception data, and further using the road element information for Voronoi diagram modeling, the topological structure of the target road area can be determined more accurately, improving the timeliness and accuracy of the regional environmental map.

[0056] The above map generation method provided by the embodiments of the present application achieves the following technical effects: First, according to the real-time position of the target vehicle, the target road area is dynamically adjusted to ensure that the target road area can be updated according to the real-time position of the target vehicle, enhancing the timeliness of the determined target road area. Using the real-time determined target road area to obtain the environmental perception data corresponding to the target road area enhances the timeliness of the environmental perception data and improves the accuracy of the environmental perception data. Second, by analyzing the environmental perception data, obtaining road element information from the environmental perception data, and further using the road element information for Voronoi diagram modeling, the topological structure of the target road area can be determined more accurately, improving the timeliness and accuracy of the regional environmental map. Thus, the embodiments of the present application determine the target road area according to the real-time position of the target vehicle, obtain the environmental perception data of the target road area with better timeliness, and use the road element information obtained by analyzing the environmental perception data for Voronoi diagram modeling, achieving the purpose of generating an environmental map with better timeliness and higher accuracy, thereby realizing the technical effects of enhancing the timeliness of the map generation method and improving the accuracy of the map generation method, and further solving the technical problems of poor timeliness and low accuracy of the map generation method in the related art.

[0057] The map generation method provided by the embodiments of the present application integrates multi-modal environmental perception data and combines Voronoi diagram modeling, and can be widely applied to multiple application scenarios.

[0058] For example, in the application scenario of automatic parking, when looking for and entering a parking space in a parking lot, the present application can generate a detailed environmental map of the parking lot. The vehicle automatic parking system uses the environmental map of the parking lot to identify a suitable parking space, plan a parking path, and monitor the surrounding dynamic environment to avoid collisions with moving obstacles, thus realizing safe and efficient automatic parking.

[0059] For example, in the application scenario of lane departure warning, during the driving process of a vehicle, the lane departure warning system needs to monitor whether the vehicle deviates from the lane line. This application can provide lane line information with higher accuracy for the lane departure warning system, monitor the position of the vehicle relative to the lane line in real time, and issue a warning when the vehicle deviates from the lane line, helping the driver adjust the direction in time and keep driving within the lane, thus improving driving safety.

[0060] For example, in the application scenario of vehicle positioning, this application constructs a high-precision environmental map and updates the local map in real time, and uses the vehicle positioning system to match the features identified in the vehicle sensor data with the features in the environmental map. By identifying consistent feature points, the position of the vehicle on the map can be determined more accurately, providing accurate vehicle positioning information.

[0061] The map generation method provided by the embodiments of this application can be but is not limited to being applied to the above-listed application scenarios. With the continuous evolution of technology, the above method can also be applied to a wider range of scenarios, such as traffic flow prediction and optimization, urban construction planning, remotely driven vehicles, etc. By providing real-time and accurate environmental perception, maps can be generated more accurately and quickly, supporting a variety of advanced functions and applications, and being able to improve driving safety and traffic efficiency.

[0062] Optionally, the above map generation method further includes the following steps:

[0063] S140: Obtain the real-time position based on a predefined update frequency parameter;

[0064] S150: Determine the target road area by using the real-time position and predefined sliding window parameters.

[0065] The above update frequency parameter can be used to determine the update frequency of the target road area.

[0066] It should be noted that the above update frequency parameter can be adjusted according to the speed of the target vehicle. For example, when the target vehicle is in a high-speed driving state, the update frequency parameter can be increased to ensure that the target road area for data collection can be updated in time and ensure the timeliness of the target road area; while when the target vehicle is in a low-speed driving state, the update frequency parameter can be decreased to reduce the consumption of computing resources.

[0067] The above sliding window can be used to determine the dynamic area where the regional environmental map needs to be updated, and this sliding window can also be used to determine the range of the target road area. The above sliding window parameters can include the window range of the sliding window, the update interval of the sliding window, the sliding strategy of the sliding window, etc.

[0068] In an exemplary application scenario, the map generation system regularly obtains the real-time position of the target vehicle by using a predefined update frequency parameter. Further, by using the real-time position and a predefined sliding window parameter, the target road area is dynamically adjusted to ensure that the data acquisition area can be updated in a timely manner, so as to ensure that the map generation system can collect environmental perception data reflecting the current position of the target vehicle.

[0069] In another exemplary application scenario, Figure 2 is a schematic diagram of an optional driving assistance method provided by one embodiment of the present application. As Figure 2 shown, the driving assistance method includes: local map update. The local map update includes: updating the target road area by using the real-time position and a predefined sliding window parameter, obtaining updated environmental perception data by using the updated target road area, and further, updating the current area environmental map based on the updated environmental perception data and a map update algorithm to obtain an updated area environmental map. Thus, in the embodiment of the present application, by using the updated environmental perception data and a map update algorithm to update the current area environmental map, the map data of the current area environmental map is fully utilized, the flexibility of the map data of the current area map is improved, and on the basis of ensuring the timeliness of the updated area environmental map, the consumption of computing resources is reduced, thereby improving the processing efficiency and response speed of the map generation system.

[0070] The above map update algorithm can be used to update the local map data of the area environmental map, and the map update algorithm can include an expired data processing algorithm and a new and old data merging algorithm. The above expired data processing algorithm can include, but is not limited to: an adaptive update algorithm, a differential update algorithm. The above new and old data merging algorithm can include, but is not limited to: a weighted average algorithm, a Kalman filtering algorithm, a Bayesian filtering algorithm, a two-way fusion algorithm.

[0071] The above optional embodiment of the present application can achieve the following beneficial effects: By using a predefined update frequency parameter, the current position information of the target vehicle can be determined in real time, the real-time position of the target vehicle can be obtained, and further, by using the real-time position of the target vehicle and a predefined sliding window parameter, the target road area is dynamically adjusted to ensure that the target road area is updated in a timely manner during the vehicle driving process, enhancing the timeliness of the determined target road area, providing a basis for subsequently obtaining the environmental perception data corresponding to the target road area, and avoiding the situation that the timeliness of the environmental perception data becomes poor due to the delay in updating the target road area. Thus, in the present application, by obtaining the real-time position based on a predefined update frequency parameter and dynamically adjusting the target road area by using the real-time position and a predefined sliding window parameter, the timeliness of the target road area is enhanced, and environmental perception data with better timeliness can be obtained, thereby enhancing the timeliness of the map generation method.

[0072] Optionally, the environmental perception data includes environmental point cloud data and environmental image data. The environmental point cloud data is used to characterize the spatial structure features of road elements in the target road area, and the environmental image data is used to characterize the visual features of road elements. In step S120 above, analyzing the environmental perception data to obtain road element information includes the following steps:

[0073] S121: Extract and label elements from the environmental point cloud data and environmental image data to obtain road element information, where the road element information is used to data-label road elements according to element types.

[0074] The above environmental perception data may include static perception data, which may include the above environmental point cloud data and the above environmental image data.

[0075] The above static perception data can be used to characterize static features and structures in the target road area, and the static perception data may include, but is not limited to: lane line data, road sign data, traffic signal data, roadblock data, parking area data, road shape data.

[0076] It should be noted that the above static perception data generally does not change rapidly over time and can reflect the fixed attributes of the target road area environment.

[0077] The above environmental point cloud data can be obtained by collecting environmental information of the target road area through a laser sensor. The laser sensor emits laser beams and measures the time of the laser return signal, thereby generating high-precision environmental point cloud data. The environmental point cloud data may include spatial structure data of lane lines, spatial structure data of obstacles, spatial structure data of multiple lanes in the target road area, etc.

[0078] The above environmental image data can be obtained by collecting environmental information of the target road area through a vision sensor (such as an in-vehicle camera). The environmental image data may include traffic sign information data, traffic signal data, color data of lane lines, etc.

[0079] It should be noted that the accuracy of the above environmental point cloud data is related to the parameters of the laser sensor (such as the point cloud density of the laser sensor, the distance measurement accuracy of the laser sensor, etc.), and the accuracy of the above environmental image data is related to the parameters of the vision sensor (such as the resolution of the image captured by the camera, the frame rate of the image captured by the camera, etc.).

[0080] The above element types can be used to characterize the categories of different objects in the target road area. The above data identification may include geographic coordinate identification and attribute information identification.

[0081] In an exemplary application scenario, still asFigure 2 As shown, the driving assistance method includes: data acquisition and data processing. Specifically, data acquisition includes: collecting the environmental information of the target road area through a laser sensor to obtain the above environmental point cloud data, and collecting the environmental information of the target road area through an in-vehicle camera to obtain the above environmental image data. Data processing includes: fusing the environmental point cloud data and the environmental image data to obtain fused data, using computer vision algorithms and deep learning models to extract and label the environmental image data in the fused data to obtain element visual features, using point cloud analysis and pattern recognition algorithms to extract and label the environmental point cloud data in the fused data to obtain element spatial features, combining the element visual features and the element spatial features to determine the element type, obtaining road element information, and using the road element information to perform data identification on the recognized road elements according to the element type.

[0082] Still in the above application scenario, taking the case where the road element information is lane line information as an example, using image processing technology to extract and label lane line elements from the environmental image data to determine the visual features of lane line information (such as the boundary of the lane line, the width of the lane line, etc.), using point cloud analysis technology to extract and label lane line elements from the environmental point cloud data to obtain the spatial features of lane line information (such as the position of the lane line, the shape of the lane line, etc.), combining the visual features and the spatial features of lane line information to determine the element type, obtaining lane line information, and ensuring the accuracy and integrity of lane line recognition.

[0083] The above computer vision algorithms may include, but are not limited to: Hough transform algorithm, Canny edge detection algorithm, Sobel operator edge detection algorithm, Prewitt operator edge detection algorithm, Laplacian operator edge detection algorithm.

[0084] The above deep learning models may include, but are not limited to: convolutional neural network, recurrent neural network, attention mechanism network.

[0085] The above point cloud analysis and pattern recognition algorithms may include, but are not limited to: feature extraction algorithm, feature matching algorithm, nearest neighbor search algorithm, clustering algorithm.

[0086] It should be noted that in the process of using the above computer vision algorithms, the above deep learning models, and the above point cloud analysis and pattern recognition algorithms for element extraction and labeling, the parameters of the algorithms and / or models can be optimized to improve the accuracy of road element information.

[0087] In addition, it should be noted that before extracting and annotating elements from the environmental point cloud data and environmental image data, the environmental point cloud data and environmental image data can also be preprocessed (such as data noise filtering, data coordinate conversion, background data removal processing, point cloud data filtering, image feature enhancement, etc.) to improve the accuracy of the environmental perception data.

[0088] The above optional embodiments of the present application can achieve the following beneficial effects: By using the environmental point cloud data and environmental image data as environmental perception data at the same time, environmental perception data can be provided from multiple dimensions, improving the comprehensiveness and accuracy of the environmental perception data, providing a more comprehensive and accurate data basis for subsequent analysis of the environmental perception data. Even in a complex and changeable environment, road element information can be accurately obtained. Therefore, by fusing the environmental point cloud data and environmental image data for element extraction and annotation, the accuracy and reliability of the road element information are improved, and the adaptability of the map generation method is enhanced.

[0089] Optionally, the road element information includes lane line information and other element information. In the above step S130, using the road element information for Voronoi diagram modeling to generate a regional environmental map includes the following steps:

[0090] S131: Use the lane line information for Voronoi diagram modeling to obtain a road network model of the target road area;

[0091] S132: Integrate and integrate the other element information and the road network model to generate a regional environmental map.

[0092] The above lane line information may include, but is not limited to, the position, shape, and type of the lane line (such as solid line type, dashed line type).

[0093] The above other elements may include road edges, stop lines, zebra crossings, traffic signs, traffic lights, parking spaces, walls, columns, speed bumps, access ramps, etc. The above other element information may be other element information in the road element information except for the lane line information, and this other element information may include the position, shape, attributes, functions, etc. of the other elements.

[0094] The above road network model may be a mathematical model representing the lane line information in the target road area in a geometric form. This road network model may include the connection relationship of lanes, intersection information, and the division of the road area. Using this road network model helps the map generation system understand and plan the road network, improve the accuracy of generating the regional environmental map, and thus more safely assist the target vehicle in performing driving operations.

[0095] In an exemplary application scenario, still as Figure 2As shown, the driving assistance method further includes map construction. Map construction includes: taking the lane line information in the road element information as input, using a modeling algorithm to perform Voronoi diagram modeling, establishing a road network, and constructing a road network model of the target road area. Further, integrating other element information in the road element information with the constructed road network model, and more comprehensively integrating the road element information (such as road structure, obstacle information, etc.) into the regional environment map to improve the accuracy of the road element information in the regional environment map and ensure the accuracy of the regional environment map.

[0096] The above optional embodiments of the present application can achieve the following beneficial effects: Using the lane line information for Voronoi diagram modeling, by converting the lane line information into a geometric representation of the road area, converting the complex analog signal form of the lane line information into a simpler geometric representation form, the position of each lane can be accurately determined, a more accurate road network can be established, and the accuracy of the road network model of the target road area is improved; furthermore, integrating the identified and labeled other element information with the road network model, supplementing the detailed information of the road network model, and generating a more comprehensive regional environment map. Thus, the present application builds a road network model with higher accuracy by using the lane line information for Voronoi diagram modeling, integrates other element information with the road network model, improves the comprehensiveness of the regional environment map, and thereby improves the accuracy of the map generation method.

[0097] Optionally, in the above step S131, using the lane line information for Voronoi diagram modeling to obtain a road network model includes the following steps:

[0098] S1311: Perform coordinate transformation on the lane line information to determine the target point set data in the body coordinate system of the target vehicle;

[0099] S1312: According to the target point set data and the target area division algorithm, divide the target road area to determine multiple Voronoi regions corresponding to multiple lanes in the target road area;

[0100] S1313: Based on the multiple Voronoi regions, construct a road network model.

[0101] The above body coordinate system can be a coordinate system with the center point of the target vehicle as the origin, and this body coordinate system can be used to represent the position and direction of targets around the vehicle (such as roadblocks, pedestrians, etc.) relative to the vehicle.

[0102] The above target point set data can be used to represent the information of the lane line information in the body coordinate system. The target point set data can include multiple target point data, and the target point data can be used to characterize the lane line information (such as lane line shape, lane line position, etc.).

[0103] The above-mentioned target area division algorithm can be used to divide the target road area into multiple areas. The target area division algorithm can include, but is not limited to: a scan-line based algorithm (e.g., Fortune algorithm), a grid-based division algorithm, a hierarchical clustering algorithm, and a minimum spanning tree algorithm.

[0104] The above-mentioned Voronoi area can be used to generate a terrain map. The Voronoi area can be a set shape defined by multiple target point data. In this application, the points on each lane correspond to a Voronoi area. By using multiple Voronoi areas, the ranges and boundaries of multiple lanes can be distinguished, avoiding the situation where the relationship between multiple target point data in the target point set data is chaotic due to a large number of lanes, resulting in a low accuracy of the constructed road network model.

[0105] In an exemplary application scenario, since directly processing lane line information has a high computational complexity, the lane line information is transformed to the body coordinate system of the target vehicle for calculation. Still as Figure 2 shown, the map construction further includes: performing coordinate transformation on the lane line information to determine the target point set data in the body coordinate system of the target vehicle, using the target point set data as the input of the target area division algorithm, using the target area division algorithm to identify the lane features and the relative position relationship between different lanes, dividing the multiple target point data corresponding to each lane in the target point set data into a Voronoi area, and determining the multiple Voronoi areas corresponding to multiple lanes in the target road area.

[0106] The above optional embodiments of the present application can achieve the following beneficial effects: By performing coordinate transformation on the lane line information and transforming the lane line information to the body coordinate system of the target vehicle for calculation, it can not only reduce the complexity of processing data, reduce the demand for computing resources, and improve the efficiency of data processing, but also analyze the lane line information based on the body coordinate system of the target vehicle, and can more accurately determine the position of the lane line relative to the target vehicle. Then, according to the target point set data and the target area division algorithm, the Voronoi areas corresponding to each lane in the target road area can be determined, so as to determine the multiple Voronoi areas corresponding to multiple lanes in the target road area, distinguish different lanes, and clearly represent multiple lanes in the road network model based on multiple Voronoi areas, construct a more accurate road network model, and avoid the situation where it is impossible to accurately construct a road network model due to a large number of lanes, thereby improving the accuracy of the map generation method.

[0107] Optionally, in the above step S1311, performing coordinate transformation on the lane line information to determine the target point set data includes the following steps:

[0108] S13111: Extract lane boundary point data from the lane line information;

[0109] S13112: Construct a virtual lane centerline based on boundary point data;

[0110] S13113: Perform coordinate transformation on the lane boundary point data and the coordinates of multiple key points on the virtual lane centerline to obtain target point set data.

[0111] The above-mentioned lane boundary point data can be used to represent the boundary information of the lane. Since the lane boundary point data is usually located at the edge of the lane line, therefore, using this lane boundary point data, the width of the lane line, the type of lane line, the curvature of the lane line, etc. can also be determined.

[0112] The above-mentioned virtual lane centerline can be calculated and generated based on the lane boundary point data, and this virtual lane centerline can be used to characterize the center position of the lane.

[0113] The above-mentioned key points can include but are not limited to the starting point of the lane line, the ending point of the lane line, and the intersection points between multiple lane lines. The above-mentioned key point coordinates can be used to characterize the coordinate information of the key points.

[0114] In an exemplary application scenario, still as Figure 2 shown, map construction further includes: using a boundary point clustering algorithm to cluster the lane boundary points of each lane, extracting the lane boundary point data of each lane from the lane line information, constructing a virtual lane centerline based on the lane boundary point data, and further, selecting multiple key point data from the lane boundary point data and the virtual lane centerline, performing coordinate transformation on the coordinates of the multiple key points corresponding to the multiple key point data, and transforming the coordinates of the multiple key points to the body coordinate system of the target vehicle to obtain target point set data. The above-mentioned boundary point clustering algorithm can include but is not limited to: distance-based clustering algorithms (such as the K-means clustering algorithm), density-based clustering algorithms, region growing algorithms, machine learning-based clustering algorithms (such as support vector machine algorithms, decision tree algorithms, random forest algorithms, etc.).

[0115] Still in the above application scenario, the virtual lane centerline can be constructed by the following method: divide the lane boundary point data corresponding to each lane to obtain multiple left boundary point data corresponding to each lane and multiple right boundary data corresponding to each lane; match the multiple left boundary point data with the multiple right boundary data to obtain multiple boundary pair data; use Equation (1) to calculate each boundary pair data in the multiple boundary pair data to obtain multiple centerline points; construct a virtual lane centerline based on the multiple centerline points.

[0116]

[0117] In Equation (1), C(x,y) represents the point coordinates of the centerline point, (Lx ,L y ) represents the point coordinates of the left boundary point data, (R x ,R y ) represents the point coordinates of the right boundary point data.

[0118] The above optional embodiments of the present application can achieve the following beneficial effects: Extracting lane boundary point data from lane line information can reduce the influence of error point data, avoid the situation of low accuracy of lane position caused by error point data, ensure that the position of the lane can be accurately determined, and further, based on the boundary point data, construct a virtual lane center line, and perform coordinate transformation on the lane boundary point data and multiple key point coordinates on the virtual lane center line. This can not only combine the generated virtual lane center line with the perceived lane boundary point data to obtain more accurate target point set data, but also selectively select the lane boundary point data and multiple key point coordinates on the virtual lane center line, reduce the point data that needs to be processed by coordinate transformation, reduce the consumption of computing resources, and improve the efficiency of obtaining the target point set data on the premise of ensuring the accuracy of the target point set data. Thus, the present application constructs a virtual lane center line based on the boundary point data extracted from the lane line information, combines the perceived lane boundary point data with multiple key point coordinates on the virtual lane center line, improves the accuracy of the target point set data, and thus can accurately provide data support for the subsequent construction of the road network model.

[0119] Optionally, in the above step S1313, constructing a road network model based on multiple Voronoi regions includes the following steps:

[0120] S13131: Determine the topological relationship between multiple lanes according to the regional boundaries of multiple Voronoi regions and the adjacent relationship between multiple Voronoi regions;

[0121] S13132: Construct a road network model based on the topological relationship.

[0122] The above regional boundary can be the dividing line between multiple Voronoi regions, and multiple lanes can be more accurately distinguished according to the regional boundaries of multiple Voronoi regions.

[0123] The above adjacent relationship can be the position adjacency situation between multiple Voronoi regions. Through the adjacent relationship between multiple Voronoi regions, the other Voronoi regions adjacent to each Voronoi region can be determined.

[0124] The above topological relationship can be a mathematical representation of the connection relationship between multiple lanes. This topological relationship can be used to characterize the connection situation between multiple lanes, and the position relationship between multiple lanes (such as, connection, bifurcation, merging, etc.) can be determined according to the topological relationship.

[0125] In an exemplary application scenario, still as Figure 2 shown, the map construction further includes: establishing the connection relationships between multiple lanes according to the adjacent relationships between multiple Voronoi regions, and then determining the topological relationships between multiple lanes according to the regional boundaries of multiple Voronoi regions and the connection relationships between multiple lanes (for example, determining the adjacent relationships between multiple lanes, the intersection positions of some lanes among multiple lanes, the branches of some lanes among multiple lanes, etc.), so as to construct a road network model based on the topological relationships between multiple lanes.

[0126] The above optional embodiments of the present application can achieve the following beneficial effects: By according to the regional boundaries of multiple Voronoi regions and the adjacent relationships between multiple Voronoi regions, it is possible to more accurately determine the lane boundaries of each lane and the adjacent relationships between different lanes, so as to more accurately determine the topological relationships between multiple lanes. Furthermore, based on the topological relationships, not only can a more accurate road network be determined, improving the accuracy of the road network model of the target road area, but also the construction process of the road network model can be simplified, improving the efficiency of constructing the road network model, which is beneficial to real-time updating of the road network model.

[0127] Optionally, the environmental perception data further includes dynamic perception data, and the dynamic perception data is used to characterize the dynamic characteristics between the target vehicle and the road elements in the target road area. The above map generation method further includes the following steps:

[0128] S160: Perform driving decision analysis according to the dynamic perception data and the regional environmental map to generate driving suggestions, where the driving suggestions are used to assist in adjusting the driving operations of the target vehicle in the target road area.

[0129] The above dynamic perception data can be data on the dynamic characteristics in the target road area, and the dynamic perception data can be obtained by collecting the environmental information of the target road area through a radar sensor. The distance and relative speed between the target vehicle and the objects around the target vehicle are measured by the radar sensor. The dynamic perception data can include but is not limited to: the motion parameters of the target vehicle (such as speed, acceleration, etc.), and the dynamic data (such as position, speed, direction, etc.) of the moving obstacles (such as vehicles, pedestrians, etc.) around the target vehicle.

[0130] It should be noted that the above dynamic perception data usually changes in real time and can reflect the dynamic changes of the target vehicle itself and the environment where the target vehicle is located. The accuracy of the above dynamic perception data is related to the parameters of the radar sensor (such as the detection distance of the radar sensor, the angular resolution of the radar sensor, etc.).

[0131] The above driving suggestions can be used to provide operation guidance for an autonomous driving system. These driving suggestions can be generated by analyzing environmental data (such as lane position data, obstacle position data, traffic signal data, etc.) within a target road area. The above driving operations can include, but are not limited to, lane keeping, path planning, collision warning, automatic parking, acceleration, deceleration, steering, etc.

[0132] In an exemplary application scenario, still as Figure 2 shown, data collection also includes: using a radar sensor to collect environmental information of the target road area to obtain the above dynamic perception data, and combining the dynamic perception data with the static road element data in the regional environmental map to provide a data basis with higher real-time performance and accuracy.

[0133] Still in the above application scenario, the driving assistance method further includes: data integration and application. Specifically, data integration and application includes: using a driving decision algorithm to perform driving decision analysis on the dynamic perception data and the regional environmental map, generating driving suggestions, transmitting the driving suggestions to the driving assistance system, and the driving assistance system adjusting the driving operations of the target vehicle in the target road area according to the driving suggestions. The above driving decision algorithm can include, but is not limited to, a path planning optimization algorithm, a collision warning algorithm, and an automatic parking algorithm. The above driving assistance system can include multiple subsystems, and different subsystems can be used to perform different driving operations. The above subsystems can include, but are not limited to, a lane keeping subsystem, a collision warning subsystem, a path planning subsystem, an automatic parking subsystem, a speed and direction control subsystem, etc.

[0134] It should be noted that in the above process of generating driving suggestions, it can also include analyzing the movement trend of dynamic obstacles, predicting changes in traffic flow, and evaluating the impact of the dynamic environment on the target vehicle.

[0135] The above optional embodiments of the present application can achieve the following beneficial effects: By combining dynamic perception data with the regional environmental map for driving decision analysis, it is possible to utilize the dynamic characteristics of the real-time changes in the environment within the target road area to generate driving suggestions with higher accuracy and better safety, thereby more accurately guiding the driving operations of the target vehicle in the target road area, improving the safety of the vehicle during driving, enhancing the overall performance of the vehicle, and improving the driving experience of the driver.

[0136] Embodiment 2

[0137] The embodiment of the present application also provides a driving assistance system 30. Please refer to Figure 3, including: an acquisition module 310, configured to acquire real-time driving data of a target vehicle within a target road area and function indicators corresponding to a target driving assistance function; a processing module 320, configured to perform a driving assistance operation on the target vehicle according to the real-time driving data, a regional environment map, and the function indicators; wherein, the regional environment map is generated according to the map generation method of any embodiment.

[0138] The above driving assistance system provided by the embodiments of the present application achieves the following technical effects: By using the acquisition module to acquire the real-time driving data of the target vehicle within the target road area and the function indicators corresponding to the target driving assistance function, the real-time driving data and function indicators can be updated in a timely manner, providing data support with better timeliness and higher accuracy for the subsequent driving assistance operation of the target vehicle. Furthermore, an environment map with better timeliness and higher accuracy is generated according to the map generation method of any embodiment. Combining the real-time driving data, the regional environment map, and the function indicators can improve the timeliness and accuracy of the driving assistance operation, avoiding the situation where it is impossible to accurately perform the driving assistance operation on the target vehicle due to the poor timeliness and low accuracy of the regional environment map, and improving the intelligence and safety of the driving assistance system.

[0139] Embodiment III

[0140] The embodiments of the present application also provide a vehicle 40. Please refer to Figure 4 , including an in-vehicle memory 410 and an in-vehicle processor 420. Among them, the in-vehicle memory 410 is used to store a computer program; the in-vehicle processor 420 is configured to execute the computer program stored on the memory to implement the map generation method of any embodiment.

[0141] The above vehicle provided by the embodiments of the present application achieves the following technical effects: Storing the computer program corresponding to implementing the map generation method of any embodiment in the in-vehicle memory, and using the in-vehicle processor to execute the computer program stored on the memory. By determining the target road area according to the real-time position of the target vehicle, acquiring environmental perception data of the target road area with better timeliness, and performing Voronoi diagram modeling using the road element information obtained by analyzing the environmental perception data, an environment map with better timeliness and higher accuracy can be generated, more accurately guiding the driving operation of the target vehicle in the target road area, reducing the driving difficulty of the driver, improving the comfort and convenience of the driver, enhancing the overall performance of the vehicle, and thus improving the safety of vehicle driving.

[0142] Those of ordinary skill in the art can understand that, similarly, the above vehicle can also be a computing terminal. Figure 5 is a hardware structure block diagram of a computing terminal for implementing the map generation method in the embodiments of the present application, as Figure 5As shown, the computing terminal 50 (such as, a computer terminal, a mobile intelligent terminal, a vehicle terminal, or a cloud computing virtual terminal, etc.) may include: one or more processors 502 (such as, may include processors 502a, 502b, ……, 502n), a memory 504 for storing data, and a transmission device 506 for implementing communication functions. Among them, the processor 502 may include, but is not limited to, processing components such as a microcontroller unit (MCU) or a field programmable gate array (FPGA).

[0143] The above computing terminal 50 may further include: a display, an input / output interface, a universal serial bus (USB) port (this USB port may be one of the ports of the computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure), and a camera (not shown in the figure).

[0144] It should be noted that one or more of the processors 502 and / or other data processing circuits in the above computing terminal 50 may be embodied in whole or in part as software, hardware, firmware, or any other combination. In addition, the data processing circuit may be a single independent processing module, or may be wholly or partially incorporated into any one of the other elements in the computing terminal 50 (or mobile device).

[0145] The memory 504 may be used to store software programs and modules of application software, such as the program instructions and data storage devices corresponding to the path planning method in the embodiments of the present application. The processor 502 executes various functional applications and data processing by running the software programs and modules stored in the memory 504, that is, implements the above path planning method. The memory 504 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 504 may further include a memory remotely disposed relative to the processor 502, and these remote memories may be connected to the vehicle terminal 50 through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The transmission device 506 is used to receive or send data via a network. Specific examples of the above network may include a wireless network provided by the communication provider of the vehicle terminal 50. In one example, the transmission device 506 includes a Network Interface Controller (NIC) and a network interface. The network adapter can be connected to other network devices through a base station so as to communicate with the Internet. The transmission device 506 can perform data communication in a wired and / or wireless network connection manner. In one example, the transmission device 506 can be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0147] The input / output interface can be connected to the input / output devices corresponding to the computing terminal 50 to implement input / output functions. The input / output devices may include, but are not limited to: cursor control devices, keyboards, displays, etc. The above input / output devices can be built into the computing terminal 50 or external external devices of the computing terminal 50.

[0148] Those of ordinary skill in the art can understand that Figure 5 The structure of the illustrated computing terminal 50 is only schematic and does not strictly limit the structure of the above computing terminal 50. For example, the computing terminal 50 may further include more or fewer components than those shown in Figure 5 or the computing terminal 50 may have different categories of components from those shown in Figure 5 shown.

[0149] Embodiment 4

[0150] The embodiment of the present application also provides a map generation device 60. Please refer to Figure 6 , including: an acquisition module 610, configured to obtain environmental perception data of a target road area, where the target road area is determined according to the real-time position of the target vehicle, and the environmental perception data is used to characterize multi-modal environmental features in the target road area; an analysis module 620, configured to analyze the environmental perception data to obtain road element information; a generation module 630, configured to perform Voronoi diagram modeling using the road element information to generate a regional environmental map of the target road area.

[0151] The above-mentioned map generation device provided by the embodiments of the present application achieves the following technical effects: through the acquisition module, according to the real-time position of the target vehicle, the target road area is dynamically adjusted to ensure that the target road area can be updated according to the real-time position of the target vehicle, enhancing the timeliness of the determined target road area. Using the real-time determined target road area, the environmental perception data corresponding to the target road area is obtained, enhancing the timeliness of the environmental perception data and improving the accuracy of the environmental perception data; through the analysis module, the environmental perception data is analyzed to obtain road element information from the environmental perception data; further through the generation module, using the road element information for Voronoi diagram modeling can more accurately determine the topological structure of the target road area, improving the timeliness and accuracy of the regional environmental map. Thus, the embodiments of the present application determine the target road area according to the real-time position of the target vehicle, obtain the environmental perception data of the target road area with better timeliness, and use the road element information obtained by analyzing the environmental perception data for Voronoi diagram modeling, achieving the purpose of generating an environmental map with better timeliness and higher accuracy, thereby realizing the technical effects of enhancing the timeliness of the map generation method and improving the accuracy of the map generation method, and further solving the technical problems of poor timeliness and low accuracy of the map generation method in the related art.

[0152] It should be noted that the optional implementation manners of this embodiment can refer to the relevant descriptions in Embodiment 1, and will not be elaborated here.

[0153] Embodiment 5

[0154] The embodiments of the present application also provide an electronic device 70. Please refer to Figure 7 , including a memory 710 and a processor 720. Among them, the memory 710 is used to store a computer program; the processor 720 is used to execute the program stored on the memory 710 to implement the map generation method introduced in any embodiment of the present application.

[0155] The above-mentioned electronic device provided by the embodiments of the present application achieves the following technical effects: storing the computer program corresponding to the map generation method for implementing any embodiment in the memory, and using the processor to execute the program stored on the memory. By determining the target road area according to the real-time position of the target vehicle, obtaining the environmental perception data of the target road area with better timeliness, and using the road element information obtained by analyzing the environmental perception data for Voronoi diagram modeling, the timeliness and accuracy of the regional environmental map are improved to provide more accurate map information.

[0156] Those of ordinary skill in the art can understand that Figure 7The structure shown is only schematic, and the electronic device can also be a terminal device such as a smart phone (e.g., Android phone, iOS phone, etc.), a tablet computer, a personal digital assistant, and a Mobile Internet Device (MID). Figure 7 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device 70 may further include more or fewer components (such as a network interface, a display device, etc.) than those shown Figure 7 in the figure, or have a different configuration from that shown Figure 7 in the figure.

[0157] Embodiment Six

[0158] The embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the map generation method introduced in any embodiment of the present application is implemented.

[0159] Optionally, in this embodiment, the above storage medium may include, but is not limited to: various media that can store computer programs such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disc.

[0160] The computer-readable storage medium provided by the embodiment of the present application achieves the following technical effects: storing the computer program corresponding to the map generation method for implementing any embodiment in the computer-readable storage medium, and using the processor to execute the stored computer program, determining the target road area according to the real-time position of the target vehicle, obtaining the environmental perception data of the target road area with better timeliness, and performing Voronoi diagram modeling using the road element information obtained by analyzing the environmental perception data, improving the timeliness and accuracy of the regional environmental map.

[0161] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0162] In the above embodiments of the present application, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0163] In the present application, "a plurality of" means two or more.

[0164] In this application, unless otherwise clearly defined, the terms "install", "connect", and "link" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0165] The terms "first", "second", "third", "fourth", etc. (if any) in this application are used to distinguish similar objects and do not necessarily describe a specific order or sequence.

[0166] The term "and / or" in this application is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this application generally indicates that the related objects before and after are in an "or" relationship.

[0167] If there is no special instruction, all steps of this application can be carried out in sequence or randomly. For example, the method includes steps A and B, indicating that the method may include steps A and B carried out in sequence, or steps B and A carried out in sequence. For example, it is mentioned that the method may further include step C, indicating that step C can be added to the method in any order. For example, the method may include steps A, B, and C, or steps A, C, and B, or steps C, A, and B, etc.

[0168] The above are only the preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims

1. A map generation method, characterized in that: include: Acquire environmental perception data of a target road area, wherein the target road area is determined according to a real-time position of a target vehicle, and the environmental perception data is used to characterize multimodal environmental features in the target road area; Analyzing the environmental perception data to obtain road element information; The road element information is used to perform Voronoi diagram modeling to generate a regional environment map of the target road area.

2. The map generation method according to claim 1, characterized in that: The map generation method further comprises: Based on a predefined update frequency parameter, obtaining the real-time position; The target road area is determined using the real-time position and predefined sliding window parameters.

3. The map generation method according to claim 1, characterized in that: The environmental perception data includes environmental point cloud data and environmental image data, wherein the environmental point cloud data is used to characterize the spatial structural characteristics of the road elements in the target road area, and the environmental image data is used to characterize the visual characteristics of the road elements; Analyzing the environmental perception data to obtain the road element information includes: Element extraction and annotation are performed on the environmental point cloud data and the environmental image data to obtain the road element information, wherein the road element information is used to perform data identification on the road elements according to element types.

4. The map generation method according to claim 1, characterized in that: The road element information includes lane line information and other element information. The Voronoi diagram modeling is performed using the road element information to generate the regional environment map, which includes: Using the lane line information to perform Voronoi diagram modeling to obtain a road network model of the target road area; The other element information and the road network model are integrated to generate the regional environment map.

5. The map generation method according to claim 4, characterized in that: The road network model is obtained by using the lane line information to perform Voronoi diagram modeling, and includes: Performing coordinate transformation on the lane line information to determine target point set data in the body coordinate system of the target vehicle; Divide the target road area into regions according to the target point set data and the target region division algorithm, and determine a plurality of Voronoi regions corresponding to a plurality of lanes in the target road area; Based on the multiple Voronoi areas, the road network model is constructed.

6. The map generation method according to claim 5, characterized in that: Performing coordinate transformation on the lane line information to determine the target point set data includes: Extracting lane boundary point data from the lane line information; Based on the boundary point data, construct a virtual lane centerline; Coordinate transformation is performed on the lane boundary point data and the coordinates of multiple key points on the virtual lane center line to obtain the target point set data.

7. The map generation method according to claim 5, characterized in that: Based on the multiple Voronoi regions, constructing the road network model includes: Determining a topological relationship between the plurality of lanes according to region boundaries of the plurality of Voronoi regions and an adjacency relationship between the plurality of Voronoi regions; Based on the topological relationship, the road network model is constructed.

8. The map generation method according to any one of claims 1 to 7, characterized in that: The environmental perception data further includes dynamic perception data, and the dynamic perception data is used to characterize dynamic features between the target vehicle and the road elements in the target road area. The map generation method further includes: A driving decision analysis is performed based on the dynamic perception data and the regional environment map to generate driving suggestions, wherein the driving suggestions are used to assist in adjusting the driving operation of the target vehicle in the target road area.

9. A driving assistance system, characterized in that: include: An acquisition module, used to acquire real-time driving data of a target vehicle in a target road area and functional indicators corresponding to a target driving assistance function; A processing module, configured to perform a driving assistance operation on the target vehicle according to the real-time driving data, the regional environment map and the functional index; Wherein, the regional environment map is generated according to the map generation method according to any one of claims 1 to 8.

10. A vehicle, characterized in that: It includes an on-board processor and an on-board memory, wherein: The vehicle-mounted memory is used to store computer programs; The vehicle-mounted processor is used to execute the computer program stored in the memory to implement the map generation method according to any one of claims 1 to 8.

Images