Method and system for integrating high-precision map acquisition and manufacturing

Abstract

According to the high-precision map acquisition and production integrated method and system provided by the invention, data is acquired by using a sensor on a mass production vehicle, and the steps of SLAM technology multi-source fusion mapping, map topological generation and the like are combined, so that high-quality and high-availability map data can be generated; and a solid foundation is provided for subsequent automatic driving and navigation application. According to the invention, the cost is reduced by adopting lightweight hardware equipment; efficient algorithms and models are used for data processing and map generation, so that the manufacturing efficiency is improved; and through the integrated design, seamless exchange and integration of data are realized, and the precision and real-time performance of the map are ensured. The system can integrate a plurality of links of data acquisition, processing, manufacturing and the like, realizes integrated operation, reduces equipment and labor cost, and improves manufacturing efficiency. Meanwhile, the system also has high-precision and high-real-time map making capability so as to meet the requirements of various application scenes on high-precision maps.

Description

Technical Field

[0001] The present invention relates to the field of map making, and in particular to a method and system for integrating high-precision map acquisition and making. Background Art

[0002] With the rapid development of technologies such as autonomous driving and intelligent navigation, high-precision maps have become an important foundation for these technologies. High-precision maps not only provide rich road and terrain information, but also accurately mark subtle features such as traffic signals and road markings, meeting the needs of advanced autonomous driving systems for precise, real-time positioning and environmental perception.

[0003] At present, the acquisition technology of high-precision maps is mainly divided into two categories: laser radar-based and vision-based acquisition methods. Lidar obtains the three-dimensional coordinates of ground objects by emitting laser beams and measuring their reflection time. Although it has high precision and high resolution, the equipment cost is high and the data processing is complex. The vision-based method uses high-definition cameras to capture ground images and uses computer vision technology to extract road and terrain information. The cost is relatively low, but the accuracy and real-time performance are slightly insufficient. In order to improve efficiency and quality, some comprehensive solutions combining multiple sensors have emerged in recent years. Through multi-source data fusion and collaborative processing, high-precision maps can be quickly and accurately acquired. These solutions make up for the shortcomings of a single acquisition method to a certain extent, but they still face challenges such as high equipment costs, complex data processing, and difficulty in system integration.

[0004] The solution that is closest to the present invention on the market is a system that integrates multiple sensors such as laser radar and high-definition cameras. The system collects ground information in real time through sensors mounted on the vehicle, and generates maps by a built-in computer processing unit. Specifically, the system obtains three-dimensional coordinates through laser radar, captures images with a high-definition camera, and then generates road and terrain data through image processing and feature extraction technology. Then, the system integrates and optimizes these data through a multi-source data fusion algorithm to generate a high-precision, high-resolution map. The advantage of this system is that it integrates multiple sensor data to improve the accuracy and real-time performance of the map.

[0005] However, the system still has shortcomings. First, the integration of multiple sensors and complex processing units makes the cost high, limiting its large-scale application. Second, the data processing and map generation process is time-consuming and consumes computing resources, affecting production efficiency. In addition, the system integration and debugging are difficult, requiring professional technicians to operate and maintain. Summary of the invention

[0006] In view of the defects in the prior art, the purpose of the present invention is to provide a method and system for integrating the collection and production of high-precision maps, which can integrate multiple links such as data collection, processing, and production, realize integrated operation, reduce equipment and labor costs, and improve production efficiency. At the same time, the system should also have high-precision and high-real-time map production capabilities to meet the needs of various application scenarios for high-precision maps.

[0007] In order to achieve the above technical effects, the present invention adopts the following technical solutions:

[0008] According to a first aspect of the present invention, a method for integrating high-precision map collection and production is provided, characterized in that it includes the following steps:

[0009] Step S1. Use the sensors on the mass-produced vehicle to collect data, the sensors include a laser radar, a camera, a combined inertial navigation and a wheel speed sensor; the laser radar can obtain three-dimensional environmental information around the vehicle, the camera can capture road information, and the combined inertial navigation and wheel speed sensor provide accurate position and motion status information of the vehicle;

[0010] Step S2. Using the simultaneous localization and mapping (SLAM) technology, the position information detected by the lidar and the semantic information detected by the camera are integrated, the position and posture of the robot or vehicle are estimated by processing the sensor data, and an environmental map is constructed; in addition, the result of the SLAM mapping is aligned and calibrated with the navigation map;

[0011] Step S3. Based on data fusion and SLAM mapping, complex map data is converted into a topological structure;

[0012] Step S4. Manually detect, discover and correct errors and deviations that occur during the above-mentioned automated processing; at the same time, evaluate and optimize the accuracy, resolution and real-time performance of the map to meet the needs of different application scenarios.

[0013] Preferably, the road information captured by the camera includes road signs, traffic signals, and road shape, width and curvature.

[0014] Preferably, in step S2, the navigation map that is aligned and calibrated with the result of SLAM mapping is a lane-level navigation map.

[0015] According to a second aspect of the present invention, a system for integrating high-precision map acquisition and production is provided, which is used to implement the above-mentioned method for integrating high-precision map acquisition and production, and includes the following modules:

[0016] Data acquisition module: This module is used to collect data using sensors built into mass-produced vehicles, including lidar, cameras, combined inertial navigation, wheel speed sensors, etc.

[0017] Multi-source data fusion and SLAM mapping module: This module is used to use SLAM (simultaneous localization and mapping) technology to fuse the position information detected by the lidar and the semantic information detected by the camera;

[0018] Map topology module: This module is used to convert complex map data into a topological structure that is easy to process and understand, and optimize and correct the map data using relevant algorithms and technologies;

[0019] Manual inspection and quality control module: This module is used to manually discover and correct errors and deviations that may occur during automated processing, and to evaluate and optimize the accuracy, resolution and real-time performance of the map.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] 1. The integrated high-precision map acquisition and production method provided by the present invention uses the sensors on mass-produced vehicles to collect data, avoiding the high cost of purchasing special equipment and significantly reducing the overall cost of the system. This is not only beneficial to the cost control of enterprises, but also promotes the popularization and application of high-precision map acquisition and production technology.

[0022] 2. The integrated method for high-precision map acquisition and production provided by the present invention can realize fast and accurate data processing and map generation by adopting advanced SLAM technology and multi-source data fusion algorithm. This greatly shortens the map production cycle, improves production efficiency, and meets the demand for efficient map updates in practical applications.

[0023] 3. The integrated method for collecting and producing high-precision maps provided by the present invention can obtain accurate location information and rich semantic information through the combined use of laser radar and camera. Through the fusion processing of multi-source data, high-quality maps that are both accurate and rich in semantic information can be generated, providing reliable basic data for autonomous driving and navigation applications.

[0024] 4. The present invention transforms complex map data into a concise and clear topological structure through map topological generation technology. This topological map is not only convenient for storage and transmission, but also more suitable for path planning and navigation algorithm processing, thus improving the practicality and efficiency of the map.

[0025] 5. The present invention is based on the sensors that come with mass-produced vehicles, so it has good flexibility and scalability. According to different application requirements and scene changes, the sensor configuration and data processing algorithm can be easily adjusted and optimized to adapt to various complex road and environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0027] Figure 1 A flowchart of the steps of the method for integrating high-precision map acquisition and production described in the first embodiment;

[0028] Figure 2 This is a schematic diagram of the integrated system for collecting and producing high-precision maps described in the second embodiment. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0030] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0031] First Embodiment

[0032] This embodiment provides an integrated method for collecting and producing high-precision maps. By using the sensors on mass-produced vehicles to collect data, combined with SLAM technology, multi-source fusion mapping, and map topology generation, high-quality, highly usable map data can be generated, providing a solid foundation for subsequent autonomous driving and navigation applications. Specifically, the following steps are included:

[0033] Step S1. Sensor data collection

[0034] This solution uses the sensors on mass-produced vehicles, including laser radar, cameras, combined inertial navigation, and wheel speed sensors to collect data to ensure the accuracy and richness of the data. The laser radar can accurately obtain the three-dimensional environmental information around the vehicle, the camera can capture the texture and details of the road, and the combined inertial navigation and wheel speed sensors provide the vehicle's precise position and motion status information. This integration method not only reduces the cost of equipment, but also improves the popularity and practicality of the system. The combined use of laser radar and camera enables the present invention to obtain accurate location information and rich semantic information.

[0035] Step S2. Multi-source data fusion and SLAM mapping

[0036] The collected data will be integrated and processed through multi-source fusion technology. Specifically, the position information detected by the lidar and the semantic information detected by the camera are fused using SLAM (Simultaneous Localization and Mapping) technology. SLAM technology estimates the position and posture of the robot or vehicle and builds an environmental map by processing sensor data. In this solution, the lidar provides accurate spatial position information, while the camera provides rich semantic information, such as road signs, traffic signals, etc. By fusing these two types of information, high-quality maps that are both accurate and rich in semantic information can be generated, providing reliable basic data for autonomous driving and navigation applications.

[0037] In addition, combined with the data of the lane-level navigation map, the results of SLAM mapping can be aligned and calibrated with the lane-level navigation map to further improve the accuracy and usability of the map. This fusion method can overcome the limitations of single sensor data and improve the quality and usability of the map. By adopting advanced SLAM technology and multi-source data fusion algorithms, the present invention can achieve fast and accurate data processing and map generation. This greatly shortens the map production cycle, improves production efficiency, and meets the demand for efficient map updates in practical applications.

[0038] Step S3. Map topology generation

[0039] Based on data fusion and SLAM mapping, this solution further generates the map topology. Topology is a graphical representation method that abstracts map information into nodes and edges, which can simplify the complexity of the map and extract key road network information. Through topological generation, complex map data can be converted into a topological structure that is easy to process and understand, which is convenient for subsequent path planning and navigation applications. In the process of topological generation, it is also necessary to use relevant algorithms and technologies to optimize and correct the map data to improve the accuracy and reliability of the map. This topological map is not only easy to store and transmit, but also more suitable for the processing of path planning and navigation algorithms, which improves the practicality and efficiency of the map.

[0040] Step S4. Manual inspection and quality control

[0041] Finally, in order to ensure the quality and usability of the map, manual inspection and quality control are required. Manual inspection can detect and correct errors and deviations that may occur during the automated processing process to ensure the accuracy and completeness of the map. At the same time, the quality control link can also evaluate and optimize the accuracy, resolution and real-time performance of the map to meet the needs of different application scenarios.

[0042] In summary, this technical solution uses the built-in sensors on mass-produced vehicles to collect data, combines SLAM technology with multi-source fusion mapping and map topology generation, and can generate high-quality, highly usable map data, providing a solid foundation for subsequent autonomous driving and navigation applications.

[0043] Second Embodiment

[0044] This embodiment provides a system for integrating high-precision map collection and production, which is used to implement the method for integrating high-precision map collection and production described in the first embodiment, and specifically includes the following modules:

[0045] Data acquisition module: This module is used to collect data using the built-in sensors on mass-produced vehicles, including lidar, cameras, combined inertial navigation, wheel speed and other sensors.

[0046] Multi-source data fusion and SLAM mapping module: This module is used to use SLAM (simultaneous localization and mapping) technology to fuse the position information detected by the lidar and the semantic information detected by the camera.

[0047] Map topology module: This module is used to convert complex map data into a topological structure that is easy to process and understand. It also uses relevant algorithms and technologies to optimize and correct map data.

[0048] Manual inspection and quality control module: This module is used to manually discover and correct errors and deviations that may occur during automated processing, and to evaluate and optimize the accuracy, resolution and real-time performance of the map.

[0049] The above describes the specific embodiments of the present invention. Based on the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention.

Claims

1. A method for integrating high-precision map collection and production, characterized in that: The following steps are involved: Step S1. Use the sensors on the mass-produced vehicle to collect data, the sensors include a laser radar, a camera, a combined inertial navigation and a wheel speed sensor; the laser radar can obtain three-dimensional environmental information around the vehicle, the camera can capture road information, and the combined inertial navigation and wheel speed sensor provide accurate position and motion status information of the vehicle; Step S2. Using the simultaneous localization and mapping (SLAM) technology, the position information detected by the lidar and the semantic information detected by the camera are integrated, the position and posture of the robot or vehicle are estimated by processing the sensor data, and an environment map is constructed; In addition, the SLAM mapping results are aligned and calibrated with the navigation map; Step S3. Based on data fusion and SLAM mapping, complex map data is converted into a topological structure; Step S4. Manually detect, discover and correct errors and deviations that occur during the above-mentioned automated processing; at the same time, evaluate and optimize the accuracy, resolution and real-time performance of the map to meet the needs of different application scenarios.

2. The method for integrating high-precision map collection and production according to claim 1 is characterized in that: The road information captured by the camera includes road signs, traffic signals, and road shape, width, and curvature.

3. The method for integrating high-precision map collection and production according to claim 1 is characterized in that: In step S2, the navigation map that is aligned and calibrated with the result of SLAM mapping is a lane-level navigation map.

4. A system for integrating high-precision map collection and production, used to implement the method for integrating high-precision map collection and production as described in any one of claims 1 to 3, characterized in that: Includes the following modules: Data acquisition module: This module is used to collect data using sensors built into mass-produced vehicles, including lidar, cameras, combined inertial navigation, wheel speed sensors, etc. Multi-source data fusion and SLAM mapping module: This module is used to use SLAM (simultaneous localization and mapping) technology to fuse the position information detected by the lidar and the semantic information detected by the camera; Map topology module: This module is used to convert complex map data into a topological structure that is easy to process and understand, and optimize and correct the map data using relevant algorithms and technologies; Manual inspection and quality control module: This module is used to manually discover and correct errors and deviations that may occur during automated processing, and to evaluate and optimize the accuracy, resolution and real-time performance of the map.

Images