Vehicle navigation positioning system and method

Abstract

The embodiment of the invention provides a vehicle navigation positioning system and method, and relates to the technical field of vehicle positioning. According to the vehicle navigation positioning system comprising a cloud end, a plurality of road side units and a plurality of vehicle ends, the cloud end receives a position data packet sent by the vehicle ends, and determines whether the vehicle ends arrive at a GNSS denial area or not based on data in the position data packet. And extracting a plurality of auxiliary position data packets uploaded when other vehicle ends pass through in the GNSS denial area from the database, and sending the auxiliary position data packets to the vehicle end through a road side unit communicating with the vehicle end or directly sending the auxiliary position data packets to the corresponding vehicle end, so that the vehicle end can realize accurate positioning and navigation in the GNSS denial area.

Description

Technical Field

[0001] This invention relates to the field of vehicle positioning technology, and more specifically, to a vehicle navigation and positioning system and method. Background Technology

[0002] In the fields of autonomous driving and high-precision positioning, GNSS (Global Navigation Satellite System) is the primary means for vehicles to obtain their absolute position. However, in GNSS-denied environments such as tunnels, urban canyons, and underground parking lots, signal loss can prevent vehicles from positioning themselves, posing a safety risk.

[0003] Currently, relevant technologies often employ location re-identification techniques based on LiDAR point clouds as a solution. However, in practical applications, this technology is mostly limited to the scope of single-vehicle intelligence and lacks an effective mechanism to improve the overall robustness of the system by utilizing wide-area information and collaborative computing.

[0004] Therefore, how to achieve stable, accurate and efficient vehicle positioning and navigation in GNSS-denied environments remains a technical challenge that urgently needs to be solved in this field. Summary of the Invention

[0005] The present invention aims to, for example, provide a vehicle navigation and positioning system and method that can at least partially solve the above-mentioned technical problems.

[0006] The embodiments of the present invention can be implemented as follows: In a first aspect, embodiments of the present invention provide a vehicle navigation and positioning system, the vehicle navigation and positioning system including a cloud, multiple roadside units and multiple vehicle terminals, the cloud being communicatively connected to each of the roadside units and each of the vehicle terminals, each of the roadside units being set at different preset locations on the roadside, each of the roadside units being communicatively connected to a vehicle terminal within the signal search range of the roadside unit, each of the vehicle terminals including a lidar, a GNSS receiver and an inertial measurement unit; Each of the aforementioned vehicle terminals is configured to obtain a location data packet of the vehicle terminal's location based on the lidar, the inertial measurement unit, and the GNSS receiver, respectively, and send the location data packet to the cloud and / or the roadside unit communicatively connected to the vehicle terminal; wherein, the location data packet includes lidar feature descriptors, location information, vehicle status information, and timestamps; The cloud platform is used to receive each of the location data packets; based on the vehicle status information, timestamp, and location information in the location data packets, it determines whether the corresponding vehicle has reached the GNSS denied area; if so, it extracts multiple auxiliary location data packets for different locations within the GNSS denied area from the database, each auxiliary location data packet including a lidar feature descriptor and location information within the GNSS denied area; it packages and sends each of the auxiliary location data packets to the vehicle and / or a roadside unit communicating with the vehicle to provide navigation and positioning for the vehicle in the GNSS denied area; Each of the roadside units is configured to receive location data packets sent by vehicles within the signal search range and send the location data packets to the cloud; and to receive packaged auxiliary location data packets sent by the cloud and send the packaged auxiliary location data packets to the vehicle connected in communication.

[0007] Optionally, each of the roadside units is further configured to: The location data packet is parsed, and the target historical feature descriptor with the highest similarity to the lidar feature descriptor is retrieved from multiple historical feature descriptors stored in the roadside unit buffer. If the similarity between the target historical feature descriptor and the lidar feature descriptor exceeds a preset threshold, the target location information corresponding to the target historical feature descriptor is sent to the vehicle terminal. The vehicle terminal is also used to correct its own position information based on the target position information.

[0008] Optionally, the vehicle end is also used for: Within the GNSS denied area, location data packets are acquired in real time, and the lidar feature descriptors in the location data packets are matched with the lidar feature descriptors in each of the auxiliary location data packets; The location information corresponding to the lidar feature descriptor in the successfully matched auxiliary location data packet is used as the current location information of the vehicle.

[0009] Optionally, obtaining the location data packet of the vehicle's location based on the lidar, the inertial measurement unit, and the GNSS receiver respectively includes: Time synchronization is performed on the lidar, the inertial measurement unit, and the GNSS receiver; Based on the lidar, obtain the lidar feature descriptor; The vehicle status information at the vehicle end is obtained based on the inertial measurement unit; The location information of the vehicle is obtained based on the GNSS receiver; The location data packet is obtained by packaging the lidar feature descriptor, the vehicle status information, and the location information, and marking them with timestamps.

[0010] Optionally, obtaining the lidar feature descriptor based on the lidar includes: Acquire lidar point cloud based on the lidar; The lidar point cloud is preprocessed and converted into a two-dimensional depth map. The two-dimensional depth map is input into a preset feature extraction network to obtain a feature map; The feature map is divided into multiple regions, and the residual between each region and the cluster center is calculated. The residuals are then weighted and aggregated to obtain the lidar feature descriptor.

[0011] Optionally, the step of preprocessing the lidar point cloud and converting the preprocessed lidar point cloud into a two-dimensional depth map includes: Based on the vehicle status information, motion distortion compensation is performed on the lidar point cloud using interpolation. A clustering algorithm based on Euclidean distance is used to filter invalid points and remove dynamic objects from the LiDAR point cloud after motion distortion compensation, thus completing the preprocessing of the LiDAR point cloud. Using a cylindrical projection model, the preprocessed lidar point cloud is converted into the two-dimensional depth map according to the projection formula; The projection formula is:

[0012] Where W is the width of the two-dimensional depth map, H is the height of the two-dimensional depth map, and f is the vertical field of view of the lidar. up Let |p|| be the maximum elevation angle of the lidar, ||p|| be the distance from the lidar point cloud to the lidar origin, and (u, v) be the pixel value of the two-dimensional depth map.

[0013] Optionally, the step of inputting the two-dimensional depth map into a preset feature extraction network to obtain a feature map includes: Perform a circular convolution operation on the two-dimensional depth map to obtain an initial feature map; The initial feature map is processed using spatial attention mechanism and channel attention mechanism respectively to obtain spatial weight map and channel weight vector; The spatial weight map is concatenated with the channel weight vector to obtain the feature map.

[0014] Optionally, the vehicle status information includes acceleration and angular velocity, and the step of determining whether the corresponding vehicle has reached the GNSS denied zone based on the vehicle status information, timestamp, and location information in the location data packet includes: The current location of the vehicle when it sends the location data packet is determined based on the timestamp and the location information. Determine whether the straight-line distance from the current location to the entrance of the GNSS denied zone is less than a preset distance; The velocity direction of the vehicle end is determined based on the acceleration and the angular velocity. Determine whether the angle between the velocity direction and the inlet direction is less than a preset angle, wherein the inlet direction is the direction perpendicular to the plane where the GNSS denial zone inlet is located; If the straight-line distance from the current location to the entrance of the GNSS denied zone is less than the preset distance, and the angle between the velocity direction and the entrance direction is less than the preset angle, then it is determined that the vehicle has reached the GNSS denied zone.

[0015] Optionally, the vehicle navigation and positioning system further includes positioning satellites, which are respectively connected to the GNSS receiver at the vehicle end and the cloud. The positioning satellite is used to continuously send satellite positioning signals to the GNSS receiver so that the vehicle can obtain the location information; In addition, the packaged auxiliary location data packet is sent to the vehicle via a satellite link.

[0016] Secondly, embodiments of the present invention provide a vehicle navigation and positioning method applied to a vehicle navigation and positioning system. The vehicle navigation and positioning system includes a cloud platform, multiple roadside units, and multiple vehicle terminals. The cloud platform is communicatively connected to each of the roadside units and each of the vehicle terminals. Each roadside unit is located at a different preset position along the roadside. Each roadside unit is communicatively connected to a vehicle terminal within its signal search range. Each vehicle terminal includes a lidar, a GNSS receiver, and an inertial measurement unit. The method includes: Each of the vehicle terminals obtains a location data packet based on the lidar, the inertial measurement unit, and the GNSS receiver, and sends the location data packet to the cloud and / or the roadside unit that is connected to the vehicle terminal; wherein, the location data packet includes lidar feature descriptors, location information, vehicle status information, and timestamps; The cloud receives each of the location data packets; based on the vehicle status information, timestamp, and location information in the location data packets, it determines whether the corresponding vehicle has reached the GNSS denied area; if so, it extracts multiple auxiliary location data packets for different locations within the GNSS denied area from the database, each auxiliary location data packet including a lidar feature descriptor and location information within the GNSS denied area; it packages and sends each of the auxiliary location data packets to the vehicle and / or a roadside unit connected to the vehicle to provide navigation and positioning for the vehicle in the GNSS denied area; Each roadside unit receives a location data packet sent by a vehicle within the signal search range and sends the location data packet to the cloud; and receives a packaged auxiliary location data packet sent by the cloud and sends the packaged auxiliary location data packet to the vehicle connected in communication.

[0017] The beneficial effects of the embodiments of the present invention include, for example: By providing a vehicle navigation and positioning system that includes a cloud, multiple roadside units, and multiple vehicle terminals, the cloud receives location data packets sent by the vehicle terminals. Based on the data in the location data packets, it determines when the vehicle terminal has reached a GNSS denied area. It then extracts multiple auxiliary location data packets uploaded by other vehicle terminals passing through the GNSS denied area from the database and sends them to the vehicle terminal through the roadside units that communicate with the vehicle terminal or directly to the corresponding vehicle terminal, so that the vehicle terminal can achieve accurate positioning and navigation in the GNSS denied area. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is one of the architecture diagrams of a vehicle navigation and positioning system provided in an embodiment of the present invention; Figure 2 An architecture diagram of a vehicle end provided for an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the connection between a roadside unit and a vehicle end, provided as an embodiment of the present invention. Figure 4 This is a second architectural diagram of a vehicle navigation and positioning system provided in an embodiment of the present invention; Figure 5 This is a flowchart illustrating the steps of a vehicle navigation and positioning method provided in an embodiment of the present invention.

[0020] Icons: 01-Vehicle navigation and positioning system; 10-Cloud; 20-Roadside unit; 30-Vehicle terminal; 31-LiDAR; 32-GNSS receiver; 33-Inertial measurement unit; 40-Positioning satellite. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0022] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0024] Furthermore, the terms "first" and "second" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0025] It should be noted that, where there is no conflict, the features in the embodiments of the present invention can be combined with each other.

[0026] This invention provides a vehicle navigation and positioning system 01, which includes a cloud platform 10, multiple roadside units 20, and multiple vehicle terminals 30. The cloud platform 10 is communicatively connected to each roadside unit 20 and each vehicle terminal 30. Each roadside unit 20 is set at a different preset location on the roadside. Each roadside unit 20 is communicatively connected to a vehicle terminal 30 within the signal search range of the roadside unit 20. Each vehicle terminal 30 includes a lidar 31, a GNSS receiver 32, and an inertial measurement unit 33.

[0027] Each vehicle terminal 30 is used to obtain a location data packet of the vehicle terminal 30's location based on the lidar 31, the inertial measurement unit 33, and the GNSS receiver 32, respectively, and send the location data packet to the cloud 10 and / or the roadside unit 20 that is connected to the vehicle terminal 30; wherein, the location data packet includes the lidar 31 feature descriptor, location information, vehicle status information, and timestamp.

[0028] The cloud 10 is used to receive data packets from various locations; based on the vehicle status information, timestamp, and location information in the location data packets, it determines whether the corresponding vehicle terminal 30 has reached the GNSS denied area; if so, it extracts multiple auxiliary location data packets for different locations within the GNSS denied area from the database. Each auxiliary location data packet includes the feature descriptor of the lidar 31 within the GNSS denied area and the location information; it packages and sends each auxiliary location data packet to the vehicle terminal 30 and / or the roadside unit 20 that is connected to the vehicle terminal 30 for navigation and positioning of the vehicle terminal 30 in the GNSS denied area.

[0029] Each roadside unit 20 is used to receive location data packets sent by vehicle terminals 30 within the signal search range and send the location data packets to the cloud 10; and to receive packaged auxiliary location data packets sent by the cloud 10 and send the packaged auxiliary location data packets to the vehicle terminals 30 with communication connection.

[0030] Please see Figure 1 The cloud platform 10 is connected to each roadside unit 20 and each vehicle terminal 30 via communication links. The roadside unit 20 can be an RSU (Road Side Unit), and each roadside unit 20 is deployed at a predetermined location beside the road, such as tunnel entrances / exits, or urban canyon entrances / exits. Figure 1 The dashed lines in the diagram represent that not every vehicle terminal 30 necessarily communicates with a roadside unit 20. Communication is established only when a vehicle terminal 30 enters the signal search range of a roadside unit 20, such as... Figure 2 As shown.

[0031] Each vehicle terminal 30 can be considered as one vehicle, such as Figure 3 As shown, each vehicle terminal 30 is equipped with a lidar 31, a GNSS receiver 32, and an inertial measurement unit 33. The vehicle terminal 30 can use the lidar 31, GNSS receiver 32, and inertial measurement unit 33 to collect location data packets containing lidar 31 feature descriptors, location information, vehicle status information, and timestamps, and send the location data packets to the cloud 10 or the roadside unit 20 with which it communicates.

[0032] After receiving location data packets from each vehicle terminal 30, the cloud 10 determines whether the vehicle terminal 30 is about to enter a GNSS denied zone (i.e., an area where various GNSS systems cannot provide positioning) based on the vehicle status information, timestamp, and location information in the location data packets. If the determination is yes, multiple auxiliary location data packets located at different positions within the GNSS denied zone are extracted from a pre-built database. Each auxiliary location data packet contains the feature descriptor of the lidar 31 in that area and its corresponding location information. These auxiliary location data packets were previously collected and uploaded to the cloud 10 by the vehicle terminal 30 while it was driving through the GNSS denied zone.

[0033] The cloud 10 packages these data packets and sends them to the vehicle terminal 30 or the relevant roadside unit 20, thereby supporting the vehicle terminal 30 in navigation and positioning within the GNSS denied area.

[0034] The roadside unit 20 is responsible for receiving the location data packets sent by the vehicle terminal 30 within its signal range and forwarding them to the cloud 10. At the same time, it receives the packaged auxiliary location data packets sent by the cloud 10 and distributes them to the vehicle terminal 30 connected to it, ensuring that there are no errors or losses in data transmission.

[0035] This system architecture achieves continuous vehicle positioning in scenarios where GNSS signals are missing through the collaboration of the vehicle terminal 30, roadside unit 20, and cloud terminal 10. For example, when a vehicle approaches a tunnel, the cloud terminal 10 predicts its entry into the tunnel by analyzing the vehicle's status and location information, and sends out auxiliary positioning data inside the tunnel in advance to ensure that the vehicle can still maintain high-precision positioning through feature matching of the lidar 31 inside the tunnel.

[0036] Optionally, each roadside unit 20 is also used for: Parse the location data packet and retrieve the target historical feature descriptor with the highest similarity to the feature descriptor of LiDAR 31 from multiple historical feature descriptors stored in the buffer of roadside unit 20.

[0037] If the similarity between the target's historical feature descriptor and the feature descriptor of the lidar 31 exceeds a preset threshold, the target location information corresponding to the historical feature descriptor is sent to the vehicle terminal 30. The vehicle terminal 30 is also used to correct its own location information based on the target location information.

[0038] In addition to ensuring the integrity and accuracy of data transmission, after receiving the location data packet sent by the vehicle terminal 30, the roadside unit 20 parses the data packet to obtain the lidar 31 feature descriptor, and retrieves the target historical feature descriptor with the highest similarity to the current descriptor from multiple historical feature descriptors stored in its local cache. For example, the cache of a roadside unit 20 continuously stores all lidar 31 feature descriptors (i.e., historical feature descriptors) sent by vehicles 30 that have communicated with it within the last 5 minutes. When a new lidar 31 feature descriptor is received, it is matched with each historical feature descriptor stored in the last 5 minutes, and the one with the highest similarity is taken as the target historical feature descriptor.

[0039] If the similarity between the target's historical feature descriptor and the current descriptor exceeds a preset threshold, the roadside unit 20 sends the target location information corresponding to the historical feature descriptor back to the vehicle terminal 30. The vehicle terminal 30 then corrects its own position based on this target location information. For example, it can fuse the target location information with its own GNSS / IMU positioning results. When the GNSS signal begins to attenuate, this can significantly improve positioning accuracy and reliability. This mechanism enhances local area positioning coordination. For instance, when multiple vehicles pass through the same intersection, the roadside unit 20 provides the vehicle with accurate location references from other vehicles by quickly matching vehicle feature descriptors, thereby improving positioning robustness in dynamic environments.

[0040] Optionally, the vehicle end 30 is also used for: Within the GNSS denied area, location data packets are acquired in real time, and the lidar 31 feature descriptors in the location data packets are matched with the lidar 31 feature descriptors in each auxiliary location data packet.

[0041] The location information corresponding to the feature descriptor of the lidar 31 in the successfully matched auxiliary location data packet is used as the current location information of the vehicle 30.

[0042] When the vehicle terminal 30 is within a GNSS denied area, it can acquire location data packets in real time and match the lidar 31 feature descriptors in the data packets with the lidar 31 feature descriptors in the auxiliary location data packets sent by the cloud 10. Once a match is successful, the vehicle terminal 30 uses the location information corresponding to the lidar 31 feature descriptor in the successfully matched auxiliary location data packet as its own current location information. This ensures that the vehicle can achieve absolute positioning through feature comparison in environments without GNSS signals. For example, when driving in a tunnel, the vehicle determines its specific location in the tunnel by matching the real-time lidar 31 scan with a pre-loaded tunnel interior feature set.

[0043] Optionally, the location data packet of the vehicle terminal 30 is obtained based on the lidar 31, the inertial measurement unit 33, and the GNSS receiver 32, respectively, including: Time synchronization is performed on the lidar 31, the inertial measurement unit 33, and the GNSS receiver 32.

[0044] The feature descriptor of lidar 31 is obtained based on lidar 31. The vehicle status information of vehicle terminal 30 is obtained based on inertial measurement unit 33. The position information of vehicle terminal 30 is obtained based on GNSS receiver 32.

[0045] The location data packet is obtained by packaging the lidar feature descriptor 31, vehicle status information, and location information, and marking the timestamp.

[0046] As an optional implementation, the vehicle terminal 30 can first perform microsecond-level time synchronization of the lidar 31, inertial measurement unit 33, and GNSS receiver 32 using methods such as PTP (Precision Time Protocol) to ensure data time consistency. Then, it acquires the lidar 31 feature descriptor, the vehicle status information from the inertial measurement unit 33, and the position information from the GNSS receiver 32, respectively. Finally, it packages this information and timestamps it to form a position data packet. Through multi-source data synchronization and integration, a unified and reliable data input is provided for the vehicle navigation and positioning system 01.

[0047] Optionally, a feature descriptor for lidar 31 is obtained based on lidar 31, including: The lidar point cloud is acquired based on lidar 31. The lidar point cloud is preprocessed and converted into a two-dimensional depth map.

[0048] The 2D depth map is input into a preset feature extraction network to obtain a feature map. The feature map is divided into multiple regions, and the residual between each region and the cluster center is calculated. The residuals are then weighted and aggregated to obtain the 31 feature descriptors of the LiDAR.

[0049] In one optional implementation, the feature descriptor of the LiDAR 31 can be obtained as follows: The vehicle end 30 acquires a LiDAR point cloud through the LiDAR 31, preprocesses the LiDAR point cloud, and converts the preprocessed LiDAR point cloud into a two-dimensional depth map. The two-dimensional depth map is input into a preset feature extraction network to obtain a feature map. The feature map is divided into multiple regions, the residual between each region and the cluster center is calculated, and these residuals are weighted and aggregated to obtain the feature descriptor of the LiDAR 31.

[0050] Optionally, the lidar point cloud is preprocessed to convert the preprocessed lidar point cloud into a two-dimensional depth map, including: Based on vehicle status information, motion distortion compensation is performed on the lidar point cloud using interpolation.

[0051] A clustering algorithm based on Euclidean distance is used to filter invalid points and remove dynamic objects from the LiDAR point cloud after motion distortion compensation, thus completing the preprocessing of the LiDAR point cloud.

[0052] Using a cylindrical projection model, the preprocessed lidar point cloud is converted into a two-dimensional depth map according to the projection formula.

[0053] The projection formula is:

[0054] Where W is the width of the two-dimensional depth map, H is the height of the two-dimensional depth map, and f is the vertical field of view of the LiDAR 31. up is the maximum elevation angle of lidar 31, ||p|| is the distance from the lidar point cloud to the lidar origin, and (u, v) are the pixel values ​​of the two-dimensional depth map.

[0055] In one optional implementation, the preprocessing of the LiDAR point cloud and the depth map conversion steps can be as follows: Based on the vehicle state information, interpolation is used to recover the motion trajectory of the LiDAR 31 during a single-frame scan, and reverse motion compensation is performed on each point in the LiDAR point cloud to eliminate point cloud stretching or compression caused by vehicle movement, thus completing motion distortion compensation for the LiDAR point cloud. A clustering algorithm based on Euclidean distance (such as the DBSCAN algorithm) is used to filter invalid points and remove dynamic objects (such as vehicles and pedestrians) from the compensated point cloud.

[0056] After preprocessing, a cylindrical projection model is used to convert the LiDAR point cloud into a two-dimensional depth map according to the projection formula mentioned above. The parameters in the projection formula include the width and height of the two-dimensional depth map, the vertical field of view of the LiDAR 31, the maximum elevation angle, and the distance from the point cloud to the LiDAR origin. The final output is the pixel values ​​(u, v) of the depth image. During vehicle movement, motion distortion compensation eliminates the point cloud deformation caused by vehicle movement, making the generated two-dimensional depth map more accurately represent the environmental structure.

[0057] Optionally, the two-dimensional depth map is input into a preset feature extraction network to obtain a feature map, including: Perform a circular convolution operation on the 2D depth map to obtain the initial feature map.

[0058] The initial feature map is processed using spatial attention and channel attention mechanisms respectively, resulting in a spatial weight map and channel weight vectors. The spatial weight map and channel weight vectors are then concatenated to obtain the feature map.

[0059] The pre-defined feature extraction network's processing flow can be as follows: An initial feature map is obtained by performing a circular convolution operation on the 2D depth map. Then, spatial attention and channel attention mechanisms are used to process the initial feature map: The initial feature map is input into the spatial attention mechanism, where global average pooling and max pooling are performed. The two pooling results are then concatenated and convolved to generate a spatial weight map. The initial feature map is input into the channel attention mechanism, where the SE (Squeeze-and-Excitation) module generates channel weight vectors.

[0060] After obtaining the spatial weight map and channel weight vectors, the spatial weight map and channel weight vectors are concatenated to form the final feature map. By introducing an attention mechanism, the representation ability of key regions in the feature map is enhanced.

[0061] Optionally, the vehicle status information includes acceleration and angular velocity. Based on the vehicle status information, timestamp, and location information in the location data packet, it is determined whether the corresponding vehicle terminal 30 has reached the GNSS denied area, including: The current location of the vehicle when it sends the location data packet is determined based on the timestamp and location information.

[0062] Determine whether the straight-line distance from the current location to the entrance of the GNSS denied zone is less than the preset distance.

[0063] The velocity direction of vehicle end 30 is determined based on acceleration and angular velocity.

[0064] Determine whether the angle between the velocity direction and the inlet direction is less than a preset angle. The inlet direction is the direction perpendicular to the plane where the GNSS denial zone inlet is located.

[0065] If the straight-line distance from the current location to the entrance of the GNSS denied zone is less than the preset distance, and the angle between the velocity direction and the entrance direction is less than the preset angle, then it is determined that vehicle 30 has reached the GNSS denied zone.

[0066] As an optional implementation, it can be determined whether the vehicle terminal 30 has reached the entrance of the GNSS denied zone in the following way: The cloud 10 determines the current location of the vehicle terminal 30 when it sends the location data packet based on the timestamp and location information in the location data packet, and determines whether the straight-line distance from the current location to the entrance of the GNSS denied zone is less than a preset distance (e.g., 150 meters). At the same time, the velocity direction of the vehicle terminal 30 is determined based on the acceleration and angular velocity in the vehicle status information, and it is determined whether the angle between the velocity direction and the direction perpendicular to the plane where the GNSS denied zone entrance is located (i.e., the entrance direction) is less than a preset angle (e.g., 15°).

[0067] If the straight-line distance is less than the preset distance and the included angle is less than the preset angle, then the vehicle end 30 is determined to have reached the GNSS rejection zone to ensure the accuracy of the prediction.

[0068] Optionally, the vehicle navigation and positioning system 01 also includes a positioning satellite 40, which is communicatively connected to the GNSS receiver 32 of the vehicle terminal 30 and the cloud 10.

[0069] Positioning satellite 40 is used to continuously send satellite positioning signals to GNSS receiver 32 so that vehicle terminal 30 can obtain location information.

[0070] Additionally, the packaged auxiliary location data packets are sent to the vehicle terminal 30 via a satellite link.

[0071] like Figure 4 As shown, the positioning satellite 40 is communicatively connected to both the GNSS receiver 32 on the vehicle terminal 30 and the cloud terminal 10, continuously sending satellite positioning signals to the GNSS receiver 32 to enable the vehicle terminal 30 to obtain location information. Simultaneously, the positioning satellite 40 also sends packaged auxiliary location data packets to the vehicle terminal 30 via a satellite link. This feature enhances the communication redundancy and reliability of the vehicle navigation and positioning system 01; in remote areas or when terrestrial network coverage is poor, the satellite link ensures the effective transmission of auxiliary positioning data.

[0072] Based on the same inventive concept, this specification provides a vehicle navigation and positioning method applied to a vehicle navigation and positioning system. The vehicle navigation and positioning system includes a cloud platform, multiple roadside units, and multiple vehicle terminals. The cloud platform is communicatively connected to each roadside unit and each vehicle terminal. Each roadside unit is located at a different preset position along the roadside. Each roadside unit is communicatively connected to a vehicle terminal within its signal search range. Each vehicle terminal includes a lidar, a GNSS receiver, and an inertial measurement unit. The method includes, as follows: Figure 5 The following steps are shown: Step S110: Each vehicle terminal obtains a location data packet of its location based on the lidar, inertial measurement unit and GNSS receiver, and sends the location data packet to the cloud and / or the roadside unit that is connected to the vehicle terminal. The location data packet includes lidar feature descriptor, location information, vehicle status information and timestamp.

[0073] Step S120: The cloud receives data packets from each location. Based on the vehicle status information, timestamp, and location information in the location data packets, it determines whether the corresponding vehicle has reached the GNSS denied area. If so, it extracts multiple auxiliary location data packets for different locations within the GNSS denied area from the database. Each auxiliary location data packet includes a lidar feature descriptor and location information within the GNSS denied area. The auxiliary location data packets are packaged and sent to the vehicle and / or the roadside unit connected to the vehicle 30 for navigation and positioning of the vehicle in the GNSS denied area.

[0074] Step S130: Each roadside unit receives the location data packets sent by the vehicle terminal within the signal search range, sends the location data packets to the cloud, and receives the packaged auxiliary location data packets sent by the cloud, and sends the packaged auxiliary location data packets to the vehicle terminal with the communication connection.

[0075] The specific implementation methods of each step in the above vehicle navigation and positioning method have been described in detail in the embodiments of the vehicle navigation and positioning system provided in this specification, and will not be elaborated here.

[0076] The present invention has at least the following beneficial effects: By providing a vehicle navigation and positioning system that includes a cloud, multiple roadside units, and multiple vehicle terminals, the cloud receives location data packets sent by the vehicle terminals. Based on the data in the location data packets, it determines when the vehicle terminal has reached a GNSS denied area. It then extracts multiple auxiliary location data packets uploaded by other vehicle terminals passing through the GNSS denied area from the database and sends them to the vehicle terminal through the roadside units that communicate with the vehicle terminal or directly to the corresponding vehicle terminal, so that the vehicle terminal can achieve accurate positioning and navigation in the GNSS denied area.

[0077] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and system can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, systems, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0078] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0079] If the functionality is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the system of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A vehicle navigation and positioning system, characterized in that, The vehicle navigation and positioning system includes a cloud platform, multiple roadside units, and multiple vehicle terminals. The cloud platform is communicatively connected to each of the roadside units and each of the vehicle terminals. Each roadside unit is set at a different preset location on the roadside. Each roadside unit is communicatively connected to a vehicle terminal within the signal search range of the roadside unit. Each vehicle terminal includes a lidar, a GNSS receiver, and an inertial measurement unit. Each of the aforementioned vehicle terminals is configured to obtain a location data packet of the vehicle terminal's location based on the lidar, the inertial measurement unit, and the GNSS receiver, respectively, and send the location data packet to the cloud and / or the roadside unit communicatively connected to the vehicle terminal; wherein, the location data packet includes lidar feature descriptors, location information, vehicle status information, and timestamps; The cloud platform is used to receive each of the location data packets; based on the vehicle status information, timestamp, and location information in the location data packets, it determines whether the corresponding vehicle has reached the GNSS denied area; if so, it extracts multiple auxiliary location data packets for different locations within the GNSS denied area from the database, each auxiliary location data packet including a lidar feature descriptor and location information within the GNSS denied area; it packages and sends each of the auxiliary location data packets to the vehicle and / or a roadside unit communicating with the vehicle to provide navigation and positioning for the vehicle in the GNSS denied area; Each of the roadside units is configured to receive location data packets sent by vehicles within the signal search range and send the location data packets to the cloud; and to receive packaged auxiliary location data packets sent by the cloud and send the packaged auxiliary location data packets to the vehicle connected in communication.

2. The vehicle navigation and positioning system as described in claim 1, characterized in that, Each of the roadside units is also used for: The location data packet is parsed, and the target historical feature descriptor with the highest similarity to the lidar feature descriptor is retrieved from multiple historical feature descriptors stored in the roadside unit buffer. If the similarity between the target historical feature descriptor and the lidar feature descriptor exceeds a preset threshold, the target location information corresponding to the target historical feature descriptor is sent to the vehicle terminal. The vehicle terminal is also used to correct its own position information based on the target position information.

3. The vehicle navigation and positioning system as described in claim 1, characterized in that, The vehicle terminal is also used for: Within the GNSS denied area, location data packets are acquired in real time, and the lidar feature descriptors in the location data packets are matched with the lidar feature descriptors in each of the auxiliary location data packets; The location information corresponding to the lidar feature descriptor in the successfully matched auxiliary location data packet is used as the current location information of the vehicle.

4. The vehicle navigation and positioning system as described in claim 1, characterized in that, The location data packets obtained based on the lidar, the inertial measurement unit, and the GNSS receiver to determine the vehicle's location include: Time synchronization is performed on the lidar, the inertial measurement unit, and the GNSS receiver; Based on the lidar, obtain the lidar feature descriptor; The vehicle status information at the vehicle end is obtained based on the inertial measurement unit; The location information of the vehicle is obtained based on the GNSS receiver; The location data packet is obtained by packaging the lidar feature descriptor, the vehicle status information, and the location information, and marking them with timestamps.

5. The vehicle navigation and positioning system as described in claim 4, characterized in that, The step of obtaining the lidar feature descriptor based on the lidar includes: Acquire lidar point cloud based on the lidar; The lidar point cloud is preprocessed and converted into a two-dimensional depth map. The two-dimensional depth map is input into a preset feature extraction network to obtain a feature map; The feature map is divided into multiple regions, and the residual between each region and the cluster center is calculated. The residuals are then weighted and aggregated to obtain the lidar feature descriptor.

6. The vehicle navigation and positioning system as described in claim 5, characterized in that, The preprocessing of the lidar point cloud, converting the preprocessed lidar point cloud into a two-dimensional depth map, includes: Based on the vehicle status information, motion distortion compensation is performed on the lidar point cloud using interpolation. A clustering algorithm based on Euclidean distance is used to filter invalid points and remove dynamic objects from the LiDAR point cloud after motion distortion compensation, thus completing the preprocessing of the LiDAR point cloud. Using a cylindrical projection model, the preprocessed lidar point cloud is converted into the two-dimensional depth map according to the projection formula; The projection formula is: Where W is the width of the two-dimensional depth map, H is the height of the two-dimensional depth map, and f is the vertical field of view of the lidar. up Let |p|| be the maximum elevation angle of the lidar, ||p|| be the distance from the lidar point cloud to the lidar origin, and (u, v) be the pixel value of the two-dimensional depth map.

7. The vehicle navigation and positioning system as described in claim 5, characterized in that, The step of inputting the two-dimensional depth map into a preset feature extraction network to obtain a feature map includes: Perform a circular convolution operation on the two-dimensional depth map to obtain an initial feature map; The initial feature map is processed using spatial attention mechanism and channel attention mechanism respectively to obtain spatial weight map and channel weight vector; The spatial weight map is concatenated with the channel weight vector to obtain the feature map.

8. The vehicle navigation and positioning system as described in claim 1, characterized in that, The vehicle status information includes acceleration and angular velocity. The step of determining whether the corresponding vehicle has reached the GNSS denied zone based on the vehicle status information, timestamp, and location information in the location data packet includes: The current location of the vehicle when it sends the location data packet is determined based on the timestamp and the location information. Determine whether the straight-line distance from the current location to the entrance of the GNSS denied zone is less than a preset distance; The velocity direction of the vehicle end is determined based on the acceleration and the angular velocity. Determine whether the angle between the velocity direction and the inlet direction is less than a preset angle, wherein the inlet direction is the direction perpendicular to the plane where the GNSS denial zone inlet is located; If the straight-line distance from the current location to the entrance of the GNSS denied zone is less than the preset distance, and the angle between the velocity direction and the entrance direction is less than the preset angle, then it is determined that the vehicle has reached the GNSS denied zone.

9. The vehicle navigation and positioning system as described in claim 1, characterized in that, The vehicle navigation and positioning system also includes positioning satellites, which are connected to the GNSS receiver at the vehicle end and the cloud platform respectively. The positioning satellite is used to continuously send satellite positioning signals to the GNSS receiver so that the vehicle can obtain the location information; Additionally, the packaged auxiliary location data packet is sent to the vehicle via a satellite link.

10. A vehicle navigation and positioning method, characterized in that, An application is made in a vehicle navigation and positioning system, the system comprising a cloud platform, multiple roadside units, and multiple vehicle terminals. The cloud platform is communicatively connected to each of the roadside units and each vehicle terminal. Each roadside unit is located at a different preset position along the roadside. Each roadside unit is communicatively connected to a vehicle terminal within its signal search range. Each vehicle terminal includes a lidar, a GNSS receiver, and an inertial measurement unit. The method includes: Each of the vehicle terminals obtains a location data packet based on the lidar, the inertial measurement unit, and the GNSS receiver, and sends the location data packet to the cloud and / or the roadside unit that is connected to the vehicle terminal; wherein, the location data packet includes lidar feature descriptors, location information, vehicle status information, and timestamps; The cloud receives each of the location data packets; based on the vehicle status information, timestamp, and location information in the location data packets, it determines whether the corresponding vehicle has reached the GNSS denied area; if so, it extracts multiple auxiliary location data packets for different locations within the GNSS denied area from the database, each auxiliary location data packet including a lidar feature descriptor and location information within the GNSS denied area; it packages and sends each of the auxiliary location data packets to the vehicle and / or a roadside unit connected to the vehicle to provide navigation and positioning for the vehicle in the GNSS denied area; Each roadside unit receives a location data packet sent by a vehicle within the signal search range and sends the location data packet to the cloud; and receives a packaged auxiliary location data packet sent by the cloud and sends the packaged auxiliary location data packet to the vehicle connected in communication.

Images