Vehicles and their map building and positioning methods and devices

Abstract

This application discloses a vehicle and its map construction and positioning method and apparatus. The method includes: acquiring a semantic map from the current parking lot to a target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; constructing a target semantic map in real time based on the vehicle trajectory coordinate information, vehicle heading information, and traffic facility semantic information; determining the vehicle's initial position based on the current positioning result; matching the semantic map from the current parking lot to the target parking lot with the target semantic map based on the initial vehicle position to determine the vehicle's location; and updating the vehicle's location by matching the target semantic map with the semantic map from the current parking lot to the target parking lot when the vehicle's location is not within the range of a high-precision map. This map construction and positioning method supports vehicle startup in the absence of GNSS signals and solves the positioning problem in the absence of a high-precision map.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to a method for vehicle map building and positioning, a device for vehicle map building and positioning, and a vehicle. Background Technology

[0002] In related technologies, when a vehicle is automatically assisted to drive from its current parking space to a target parking space, the current parking lot may be indoors. Without a high-precision map or GNSS signal, the vehicle cannot locate and start. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in related technologies. To this end, the first objective of this application is to propose a vehicle map construction and positioning method. The method includes: acquiring a semantic map from the current parking lot to the target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; constructing a target semantic map in real time based on the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; determining the vehicle's initial position based on the current positioning result; matching the semantic map from the current parking lot to the target parking lot with the target semantic map based on the initial vehicle position to determine the vehicle's location; and updating the vehicle's location by matching the target semantic map with the semantic map from the current parking lot to the target parking lot when the vehicle's location is not within the range of a high-precision map. This map construction and positioning method supports vehicle startup in the absence of GNSS signals and solves the positioning problem in the absence of a high-precision map.

[0004] The second objective of this application is to propose a vehicle map building and positioning device.

[0005] The third objective of this application is to propose a vehicle.

[0006] To achieve the above objectives, the first aspect of this application proposes a method for vehicle map construction and positioning. The method includes: acquiring a semantic map from the current parking lot to the target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; constructing a target semantic map in real time based on the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; determining the initial position of the vehicle based on the current positioning result; matching the semantic map from the current parking lot to the target parking lot with the target semantic map based on the initial position of the vehicle to determine the vehicle's position; and updating the vehicle's position when the vehicle's position is not within the range of the high-precision map by matching the target semantic map with the semantic map from the current parking lot to the target parking lot.

[0007] According to one embodiment of this application, the method further includes: when the vehicle location is within the range of a high-precision map, performing location matching between the target semantic map and the high-precision map to update the vehicle location.

[0008] According to one embodiment of this application, the above method further includes: when a GNSS signal is present when generating the coordinate information of the vehicle trajectory based on dead reckoning, and / or when the vehicle position is within the range of a high-precision map during the construction of the target semantic map, post-processing the target semantic map based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal and / or the semantic information of traffic facilities in the high-precision map, so as to update the semantic map from the current parking lot to the target parking lot.

[0009] According to one embodiment of this application, post-processing of the target semantic map based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal to update the semantic map from the current parking lot to the target parking lot includes: obtaining a first correspondence between the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning, and the precision value of the coordinate information of the vehicle trajectory corresponding to the GNSS signal; fusing the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning according to the first correspondence and the precision value to obtain a first fusion result; and correcting the target semantic map according to the first fusion result to update the semantic map from the current parking lot to the target parking lot.

[0010] According to one embodiment of this application, post-processing of a target semantic map based on the semantic information of traffic facilities in a high-precision map to update the semantic map from the current parking lot to the target parking lot includes: obtaining a second correspondence between the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map; fusing the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map based on the second correspondence to obtain a second fusion result; and correcting the target semantic map based on the second fusion result to update the semantic map from the current parking lot to the target parking lot.

[0011] According to one embodiment of this application, obtaining a first correspondence between the coordinate information of a vehicle trajectory corresponding to a GNSS signal and the coordinate information of a vehicle trajectory generated based on dead reckoning includes: when generating the coordinate information of a vehicle trajectory based on dead reckoning, if a GNSS signal exists, obtaining the coordinate information of the vehicle trajectory corresponding to the GNSS signal; and binding the coordinate information of the vehicle trajectory corresponding to the GNSS signal with the coordinate information of the vehicle trajectory generated based on dead reckoning to determine the first correspondence.

[0012] According to one embodiment of this application, obtaining a second correspondence between the semantic information of traffic facilities in a high-precision map and the semantic information of traffic facilities in a target semantic map includes: during the construction of the target semantic map, when the vehicle location is within the range of the high-precision map, obtaining the semantic information of traffic facilities in the high-precision map; and binding the semantic information of traffic facilities in the high-precision map with the semantic information of traffic facilities in the target semantic map to determine the second correspondence.

[0013] According to one embodiment of this application, a target semantic map is constructed based on the coordinate information of the vehicle trajectory, the heading information of the vehicle, and the semantic information of the traffic facilities, including: unifying the semantic information of the traffic facilities, the heading information of the vehicle, and the coordinate information of the vehicle trajectory into the same coordinate system; determining the vehicle trajectory based on the coordinate information of the vehicle trajectory and the heading information of the vehicle; and mapping the vehicle trajectory and the semantic information of the traffic facilities into a preset map frame to determine the target semantic map.

[0014] To achieve the above objectives, a second aspect of this application proposes a vehicle map building and positioning device. The device includes: an acquisition module, used to acquire a semantic map from the current parking lot to the target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; a mapping module, used to construct a target semantic map in real time based on the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; and a positioning module, used to determine the initial position of the vehicle based on the current positioning result, match the semantic map from the current parking lot to the target parking lot with the target semantic map based on the initial position of the vehicle to determine the vehicle's position, and update the vehicle's position by matching the target semantic map with the semantic map from the current parking lot to the target parking lot when the vehicle's position is not within the range of the high-precision map.

[0015] To achieve the above objectives, a third aspect of this application provides a vehicle, including a memory, a processor, and a vehicle map building and positioning program stored in the memory and executable on the processor. When the processor executes the vehicle map building and positioning program, it implements the aforementioned vehicle map building and positioning method.

[0016] According to the vehicle and its map construction and positioning method and apparatus of the embodiments of this application, the semantic map from the current parking lot to the target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the heading information of the vehicle, and the semantic information of traffic facilities are obtained; the target semantic map is constructed in real time based on the coordinate information of the vehicle trajectory, the heading information of the vehicle, and the semantic information of traffic facilities; the initial position of the vehicle is determined based on the current positioning result; the semantic map from the current parking lot to the target parking lot is matched and positioned with the target semantic map based on the initial position of the vehicle to determine the vehicle position; and when the vehicle position is not within the range of the high-precision map, the vehicle position is updated by matching the target semantic map with the semantic map from the current parking lot to the target parking lot. Attached Figure Description

[0017] Figure 1 This is a flowchart of a vehicle map construction and positioning method according to some embodiments of this application;

[0018] Figure 2 A block diagram of a vehicle map building and positioning device according to some embodiments of this application;

[0019] Figure 3 This is a block diagram of a vehicle according to some embodiments of this application. Detailed Implementation

[0020] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0021] The vehicle and its map construction and positioning method and apparatus according to embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0022] Figure 1 This is a flowchart of a vehicle map construction and positioning method according to some embodiments of this application. (Refer to...) Figure 1 The vehicle map construction and positioning method of this application embodiment may include the following steps:

[0023] S110: Obtain the semantic map from the current parking lot to the target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of the traffic facilities.

[0024] Specifically, when a user needs to control the vehicle to automatically drive from the current parking lot to the target parking lot, the vehicle will obtain the ID of the current parking lot from the map record file after powering on in the current parking lot. After reading this ID, multiple semantic maps containing the current parking lot will be determined. The user can select the semantic map from the multiple semantic maps containing the current parking lot to the target parking lot.

[0025] The vehicle stores the current location result before it enters the current parking lot and is powered off, and the current location result can be read after the vehicle is powered on.

[0026] Before a vehicle enters the current parking lot and is powered off, the dead reckoning system will save the coordinates of the current vehicle trajectory and the vehicle's heading information. When the vehicle is powered on, the system will load the saved coordinates of the vehicle trajectory and the vehicle's heading information, and continue to perform dead reckoning to obtain the coordinates of the vehicle trajectory and the vehicle's heading information.

[0027] When the vehicle is powered on, the vehicle's visual perception system will collect semantic information about traffic facilities, such as lane lines, ground arrows, parking spaces, and speed bumps. This semantic information includes, but is not limited to, the coordinate and directional information of the traffic facilities.

[0028] S120 constructs a target semantic map in real time based on the coordinate information of vehicle trajectory, the heading information of vehicle, and the semantic information of traffic facilities.

[0029] Specifically, after acquiring the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities to construct a target semantic map in real time, the vehicle trajectory is determined based on the semantic map from the current parking lot to the target parking lot, according to the vehicle trajectory coordinate information and the vehicle's heading information. Traffic facilities, such as lane lines, ground arrows, parking spaces, and speed bumps, are determined based on the semantic information of the traffic facilities. After fusing duplicate information, the vehicle trajectory and traffic facilities are mapped onto a preset map frame to construct the target semantic map. Furthermore, during vehicle movement, the vehicle trajectory coordinate information, vehicle heading information, and traffic facility semantic information are acquired in real time, and the target semantic map is constructed in real time based on the acquired information.

[0030] S130: Determine the initial position of the vehicle based on the current positioning result. Based on the initial position of the vehicle, match the semantic map from the current parking lot to the target parking lot with the target semantic map to determine the vehicle's position. If the vehicle's position is not within the range of the high-precision map, match the target semantic map with the semantic map from the current parking lot to the target parking lot to update the vehicle's position.

[0031] Specifically, after the vehicle is powered on, it can read the current positioning result and use it as the vehicle's initial position. It then uses a real-time constructed target semantic map and a semantic map from the current parking lot to the target parking lot for matching and positioning. The initial vehicle position ensures successful positioning initialization, determining the vehicle's location within the semantic map from the current parking lot to the target parking lot. This means that even if the current parking lot cannot receive GNSS signals, the positioning result saved from the vehicle's last power-off can be used for initial positioning to ensure successful vehicle startup. Furthermore, the initial positioning accuracy requirement is not high, and there is no need to upload to a server. During vehicle operation, if the vehicle's position is detected to be outside the high-precision map range, the semantic map from the current parking lot to the target parking lot can be used for positioning. For example, the real-time constructed target semantic map can be matched with the semantic map from the current parking lot to the target parking lot to update the vehicle's position, ensuring that the vehicle can plan and automatically drive to the target parking lot.

[0032] The map construction and positioning method of this application supports vehicle startup in the absence of GNSS signal and solves the positioning problem in the absence of high-precision map.

[0033] In some embodiments, the method further includes: when the vehicle location is within the range of a high-precision map, performing location matching between the target semantic map and the high-precision map to update the vehicle location.

[0034] Specifically, if the vehicle's location is detected to be within the range of a high-precision map during its operation, the high-precision map can be used to locate the vehicle. For example, the real-time constructed target semantic map can be matched with the high-precision map to update the vehicle's location, thereby improving the positioning accuracy.

[0035] In some embodiments, the method further includes: when a GNSS signal is present when generating the coordinate information of the vehicle trajectory based on dead reckoning, and / or when the vehicle position is within the range of a high-precision map during the construction of the target semantic map, post-processing the target semantic map according to the coordinate information of the vehicle trajectory corresponding to the GNSS signal and / or the semantic information of traffic facilities in the high-precision map, so as to update the semantic map from the current parking lot to the target parking lot.

[0036] Specifically, when the vehicle is powered on, a target semantic map is constructed in real time regardless of the scenario. This means that as the vehicle autonomously drives from the current parking lot to the target parking lot, a target semantic map is also constructed in real time. After the vehicle is powered off at the target parking lot, the target semantic map undergoes post-processing. For example, the target semantic map is corrected based on the coordinate information of the vehicle's trajectory corresponding to the GNSS (Global Navigation Satellite System) signal, the semantic information of traffic facilities in the high-precision map, or vice versa, to generate a new semantic map from the current parking lot to the target parking lot. This new semantic map is then merged with the original one, and the merged semantic map is stored in the map record file as the semantic map from the current parking lot to the target parking lot. The processed map is saved in a high-precision map standard format, and the start and end point information of the current map, including the coordinates of the start and end points, the parking lot entrance coordinates, and the semantic map ID from the current parking lot to the target parking lot, are also saved in the map record file. This information is used the next time the user needs to control the vehicle to automatically drive from the current parking lot to the target parking lot.

[0037] In addition, post-processing of the target semantic map includes obtaining the Carrier-to-Noise Ratio (CNO) from the vehicle's GPS receiver, determining whether the target parking lot is an indoor parking lot based on the CNO, for example, if the CNO is less than a CNO threshold, the target parking lot is determined to be an indoor parking lot. If the target parking lot is an indoor parking lot, the indoor parking lot is divided into floors to help users locate their vehicle's position.

[0038] Post-processing of the target semantic map also includes retaining a certain length of map data, such as 1km, for maps not actively constructed by the user before entering the current parking lot, while deleting map data further away. Specifically, when the vehicle is powered on, the target semantic map is constructed in real time regardless of the scenario. However, to obtain a semantic map from the current parking lot to the target parking lot, the user can actively construct and save the semantic map from the current parking lot to the target parking lot by clicking a preset button on the in-vehicle terminal device, while deleting the map not actively constructed by the user before entering the current parking lot.

[0039] Post-processing of the target semantic map also includes performing loop fusion and deleting the trajectory formed during parking if a closed loop is detected in the target semantic map, in order to optimize the target semantic map.

[0040] Post-processing of the target semantic map also includes checking for overlap in the coordinates of trajectories across multiple maps if the user has saved more than one map. If overlap is found and the overlap ratio exceeds a certain threshold, a map fusion operation is performed to merge the two maps into one. This process is repeated until no overlapping maps are found. If the maps contain the same parking lot, the areas of the same parking lot in the two maps are matched. If the matching area exceeds a certain ratio, the maps are merged. After fusion, the map is saved and the two old maps are deleted.

[0041] In some embodiments, post-processing of the target semantic map based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal to update the semantic map from the current parking lot to the target parking lot includes: obtaining a first correspondence between the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning, and the precision value of the coordinate information of the vehicle trajectory corresponding to the GNSS signal; fusing the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning according to the first correspondence and the precision value to obtain a first fusion result; and correcting the target semantic map according to the first fusion result to update the semantic map from the current parking lot to the target parking lot.

[0042] Specifically, when generating vehicle trajectory coordinates using dead reckoning, GNSS signals may be present, and the coordinates of the corresponding vehicle trajectory can also be obtained from these GNSS signals. Therefore, to improve the accuracy of the semantic map from the current parking lot to the target parking lot, when the vehicle arrives at the target parking lot and is powered off, a first correspondence is established between the coordinates of the vehicle trajectory corresponding to the GNSS signal and the coordinates of the vehicle trajectory generated based on dead reckoning. Based on this first correspondence, the coordinates of the vehicle trajectory corresponding to the GNSS signal are fused with those generated based on dead reckoning. However, when the GNSS signal is weak, the accuracy of the coordinates of the vehicle trajectory corresponding to the GNSS signal is low; when the GNSS signal is strong, the accuracy is high. Therefore, when fusing the coordinates of the vehicle trajectory corresponding to the GNSS signal with those generated based on dead reckoning to obtain the first fusion result, the accuracy of the coordinates of the vehicle trajectory corresponding to the GNSS signal also needs to be considered. Then, the target semantic map is corrected based on the first fusion result to update the semantic map from the current parking lot to the target parking lot.

[0043] For example, when the accuracy of the coordinate information of the vehicle trajectory corresponding to the GNSS signal is greater than a preset accuracy threshold, the weight of the coordinate information of the vehicle trajectory corresponding to the GNSS signal is increased and the weight of the coordinate information of the vehicle trajectory generated based on dead reckoning is decreased during fusion. When the accuracy of the coordinate information of the vehicle trajectory corresponding to the GNSS signal is less than or equal to the preset accuracy threshold, the weight of the coordinate information of the vehicle trajectory corresponding to the GNSS signal is decreased and the weight of the coordinate information of the vehicle trajectory generated based on dead reckoning is increased during fusion. The preset accuracy threshold can be determined according to the actual situation and is not specifically limited here.

[0044] Thus, by correcting the target semantic map based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal, the accuracy of the semantic map from the current parking lot to the target parking lot can be improved.

[0045] In some embodiments, post-processing the target semantic map based on the semantic information of traffic facilities in the high-precision map to update the semantic map from the current parking lot to the target parking lot includes: obtaining a second correspondence between the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map; fusing the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map based on the second correspondence to obtain a second fusion result; and correcting the target semantic map based on the second fusion result to update the semantic map from the current parking lot to the target parking lot.

[0046] Specifically, during the real-time construction of the target semantic map, vehicles may enter the area covered by the high-precision map. Based on the high-precision map, semantic information about traffic facilities can be obtained, such as coordinate and directional information. This semantic information is typically superior to that of the traffic facilities in the target semantic map. Therefore, to improve the accuracy of the semantic map from the current parking lot to the target parking lot, when the vehicle arrives at the target parking lot and is powered off, a second correspondence is established between the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map. Based on this second correspondence, the semantic information of traffic facilities in the high-precision map and the target semantic map are fused to obtain a second fusion result. The target semantic map is then corrected based on this second fusion result to update the semantic map from the current parking lot to the target parking lot, and areas covered by the high-precision map are marked on the real-time constructed target semantic map.

[0047] Thus, by correcting the target semantic map based on the semantic information of traffic facilities in the high-precision map, the accuracy of the semantic map from the current parking lot to the target parking lot can be improved, and seamless connection between the high-precision map and the target semantic map can be achieved.

[0048] In some embodiments, obtaining the first correspondence between the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning includes: when generating the coordinate information of the vehicle trajectory based on dead reckoning, if a GNSS signal exists, obtaining the coordinate information of the vehicle trajectory corresponding to the GNSS signal; and binding the coordinate information of the vehicle trajectory corresponding to the GNSS signal with the coordinate information of the vehicle trajectory generated based on dead reckoning to determine the first correspondence.

[0049] Specifically, while the coordinate information of vehicle trajectories obtained by GNSS signals is relatively accurate, there may be signal obstruction and other issues that may lead to missing or inaccurate data in some periods. Although dead reckoning can continuously estimate trajectories to a certain extent, it also has problems such as cumulative errors. Combining the two can complement each other's advantages. The high precision of GNSS can be used to calibrate the results of dead reckoning, and dead reckoning can be used to maintain the continuity of the trajectory when GNSS signals are temporarily unavailable, thereby determining an accurate and reliable first correspondence. For example, vehicle trajectory coordinate information obtained from GNSS signals and dead reckoning at the same or similar times can be correlated and matched. For instance, at a certain time point t1, the coordinates obtained from the GNSS signal are (Xgnss1, Ygnss1), and the coordinates obtained from dead reckoning are (Xdr1, Ydr1). By associating these two sets of coordinate information and organizing multiple such corresponding coordinate sets in chronological order, the first correspondence between the two can be determined. The first correspondence can intuitively reflect the correlation between the coordinate information obtained by the two different methods throughout the entire vehicle driving process, providing a foundation for subsequent trajectory fusion, error correction, and other work.

[0050] In some embodiments, obtaining a second correspondence between the semantic information of traffic facilities in a high-precision map and the semantic information of traffic facilities in a target semantic map includes: during the construction of the target semantic map, when the vehicle location is within the range of the high-precision map, obtaining the semantic information of traffic facilities in the high-precision map; and binding the semantic information of traffic facilities in the high-precision map with the semantic information of traffic facilities in the target semantic map to determine the second correspondence.

[0051] Specifically, binding the semantic information of traffic facilities in high-precision maps with that in target semantic maps enables effective fusion and mutual calibration of map information from different sources. High-precision maps provide relatively authoritative and accurate basic traffic facility information, while target semantic maps depict traffic facilities more from a real-time perception perspective. By binding the two information, high-precision maps can be used to correct potential recognition errors in target semantic maps, while also enriching and perfecting the information in target semantic maps. The resulting second correspondence helps in subsequent more accurate traffic environment analysis and driving decisions. For example, for each identifiable traffic facility, the semantic information of that facility in the high-precision map (such as the precise coordinates, type, and cycle of a traffic light in the high-precision map) is matched one-to-one with the semantic information of the corresponding traffic facility in the target semantic map (the position and status of the traffic light in the vehicle's relative coordinate system as perceived by sensors). The association between the two is then determined according to dimensions such as the category and location of the traffic facility to establish the second correspondence. For example, a right-turn lane guidance sign located at a specific intersection has coordinates (X1, Y1) and is classified as lane guidance in a high-precision map. Its coordinates relative to vehicles in the target semantic map are (X2, Y2). By mapping these two sets of semantic information about the same traffic facility, and summarizing the correspondence of numerous traffic facilities, a second correspondence can be constructed.

[0052] In some embodiments, constructing a target semantic map based on the coordinate information of the vehicle trajectory, the heading information of the vehicle, and the semantic information of the traffic facilities includes: unifying the semantic information of the traffic facilities, the heading information of the vehicle, and the coordinate information of the vehicle trajectory into the same coordinate system; determining the vehicle trajectory based on the coordinate information of the vehicle trajectory and the heading information of the vehicle; and mapping the vehicle trajectory and the semantic information of the traffic facilities into a preset map frame to determine the target semantic map.

[0053] Specifically, the semantic information of traffic facilities, the heading information of vehicles, and the coordinate information of vehicle trajectories are unified under the same coordinate system to facilitate subsequent fusion processing. The coordinate information of the vehicle trajectory records the specific position of the vehicle at different times, while the heading information reflects the direction of travel of the vehicle at each position point. Combining these two allows for a complete depiction of the vehicle's trajectory over a period of time. For example, given that the coordinates of a vehicle at a certain moment are (X1, Y1), and the heading information shows that the vehicle is traveling in a northeast direction, as time progresses, new position points (X2, Y2), etc., are obtained based on the coordinate information at subsequent moments. By sequentially connecting these coordinate points in chronological order and combined with the direction of travel, the actual trajectory of the vehicle on the road, such as how it travels, turns, and changes lanes, can be determined. For example, according to the time sequence, the vehicle trajectory coordinate information and the vehicle heading information corresponding to each moment are read sequentially. The coordinate information determines the position, and the heading information determines the direction of the line connecting that position point to the next position point, gradually constructing a continuous, directional vehicle trajectory line. Appropriate data structures (such as linked lists and arrays) can be used to store these directional coordinate point sequences, facilitating further processing and application of vehicle trajectories. The determined vehicle trajectories and semantic information of traffic facilities are mapped to corresponding layers and locations within a pre-defined map framework according to their positions in a unified coordinate system. Vehicle trajectories can be mapped to the road layer, clearly showing the vehicle's route within the pre-defined area; the semantic information of traffic facilities is accurately placed at their respective layer locations based on their type (e.g., traffic signs to the traffic sign layer, traffic lights to the traffic light layer, etc.). Through this mapping and integration, the pre-defined map framework is filled with specific and meaningful content, ultimately determining the target semantic map.

[0054] In summary, the map construction and positioning method of this application solves the problem of map construction and positioning from the current parking space to the target parking space in the automatic assisted driving system. It supports vehicle startup in the absence of GNSS signal and solves the positioning problem in the absence of high-precision maps.

[0055] Corresponding to the above embodiments, this application also proposes a vehicle map building and positioning device.

[0056] In some embodiments, refer to Figure 2 The vehicle map building and positioning device 200 includes: an acquisition module 210, a mapping module 220, and a positioning module 230.

[0057] The acquisition module 210 acquires the semantic map from the current parking lot to the target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities. The mapping module 220 constructs the target semantic map in real time based on the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities. The positioning module 230 determines the vehicle's initial position based on the current positioning result, matches the semantic map from the current parking lot to the target parking lot with the target semantic map to determine the vehicle's location, and updates the vehicle's location if the vehicle's location is not within the range of the high-precision map.

[0058] According to one embodiment of this application, the positioning module 230 is further configured to update the vehicle position by performing positioning matching between the target semantic map and the high-precision map when the vehicle position is within the range of the high-precision map.

[0059] According to one embodiment of this application, the above method further includes: when a GNSS signal is present when generating the coordinate information of the vehicle trajectory based on dead reckoning, and / or when the vehicle position is within the range of a high-precision map during the construction of the target semantic map, post-processing the target semantic map based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal and / or the semantic information of traffic facilities in the high-precision map, so as to update the semantic map from the current parking lot to the target parking lot.

[0060] According to one embodiment of this application, post-processing of the target semantic map based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal to update the semantic map from the current parking lot to the target parking lot includes: obtaining a first correspondence between the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning, and the precision value of the coordinate information of the vehicle trajectory corresponding to the GNSS signal; fusing the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning according to the first correspondence and the precision value to obtain a first fusion result; and correcting the target semantic map according to the first fusion result to update the semantic map from the current parking lot to the target parking lot.

[0061] According to one embodiment of this application, post-processing of a target semantic map based on the semantic information of traffic facilities in a high-precision map to update the semantic map from the current parking lot to the target parking lot includes: obtaining a second correspondence between the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map; fusing the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map based on the second correspondence to obtain a second fusion result; and correcting the target semantic map based on the second fusion result to update the semantic map from the current parking lot to the target parking lot.

[0062] According to one embodiment of this application, obtaining a first correspondence between the coordinate information of a vehicle trajectory corresponding to a GNSS signal and the coordinate information of a vehicle trajectory generated based on dead reckoning includes: when generating the coordinate information of a vehicle trajectory based on dead reckoning, if a GNSS signal exists, obtaining the coordinate information of the vehicle trajectory corresponding to the GNSS signal; and binding the coordinate information of the vehicle trajectory corresponding to the GNSS signal with the coordinate information of the vehicle trajectory generated based on dead reckoning to determine the first correspondence.

[0063] According to one embodiment of this application, obtaining a second correspondence between the semantic information of traffic facilities in a high-precision map and the semantic information of traffic facilities in a target semantic map includes: during the construction of the target semantic map, when the vehicle location is within the range of the high-precision map, obtaining the semantic information of traffic facilities in the high-precision map; and binding the semantic information of traffic facilities in the high-precision map with the semantic information of traffic facilities in the target semantic map to determine the second correspondence.

[0064] According to one embodiment of this application, the mapping module 220 is specifically used to unify the semantic information of traffic facilities, the heading information of vehicles, and the coordinate information of vehicle trajectories into the same coordinate system; determine the vehicle trajectory based on the coordinate information of the vehicle trajectory and the heading information of the vehicle; and map the vehicle trajectory and the semantic information of traffic facilities into a preset map frame to determine the target semantic map.

[0065] It should be noted that the above explanation of the embodiments and beneficial effects of the vehicle map building and positioning method also applies to the vehicle map building and positioning device of the present application embodiments. To avoid redundancy, it will not be elaborated in detail here.

[0066] Corresponding to the above embodiments, this application also proposes a vehicle.

[0067] See Figure 3As shown, the vehicle 300 of this application includes a memory 310, a processor 320, and a vehicle map building and positioning program stored in the memory 310 and capable of running on the processor 320. When the processor executes the vehicle map building and positioning program, it implements the aforementioned vehicle map building and positioning method.

[0068] It should be noted that the above-described embodiments and explanations of the vehicle map construction and positioning methods are also applicable to the vehicles in the embodiments of this application. To avoid redundancy, they will not be elaborated in detail here.

[0069] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0070] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0071] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0072] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0073] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0074] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for vehicle map construction and positioning, characterized in that, The method includes: Obtain the semantic map from the current parking lot to the target parking lot, the current location result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; A target semantic map is constructed in real time based on the coordinate information of the vehicle trajectory, the heading information of the vehicle, and the semantic information of the traffic facilities. The vehicle's initial position is determined based on the current positioning result. Based on the vehicle's initial position, the semantic map from the current parking lot to the target parking lot is matched with the target semantic map to determine the vehicle's location. If the vehicle's location is not within the range of the high-precision map, the vehicle's location is updated by matching the target semantic map with the semantic map from the current parking lot to the target parking lot.

2. The vehicle map construction and positioning method according to claim 1, characterized in that, The method further includes: If the vehicle's location is within the range of the high-precision map, the vehicle's location is updated by performing a location matching between the target semantic map and the high-precision map.

3. The vehicle map construction and positioning method according to claim 1, characterized in that, The method further includes: When GNSS signals are present when generating vehicle trajectory coordinate information based on dead reckoning, and / or when the vehicle position is within the range of a high-precision map during the construction of the target semantic map, the target semantic map is post-processed based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal and / or the semantic information of traffic facilities in the high-precision map, so as to update the semantic map from the current parking lot to the target parking lot.

4. The vehicle map construction and positioning method according to claim 3, characterized in that, Post-processing is performed on the target semantic map based on the coordinate information of the vehicle trajectory corresponding to the GNSS signal to update the semantic map from the current parking lot to the target parking lot, including: Obtain the first correspondence between the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning, as well as the accuracy value of the coordinate information of the vehicle trajectory corresponding to the GNSS signal. Based on the first correspondence and the accuracy value, the coordinate information of the vehicle trajectory corresponding to the GNSS signal is fused with the coordinate information of the vehicle trajectory generated based on dead reckoning to obtain a first fusion result. Based on the first fusion result, the target semantic map is corrected to update the semantic map from the current parking lot to the target parking lot.

5. The vehicle map construction and positioning method according to claim 3, characterized in that, Post-processing is performed on the target semantic map based on the semantic information of traffic facilities in the high-precision map to update the semantic map from the current parking lot to the target parking lot, including: Obtain a second correspondence between the semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map; The semantic information of traffic facilities in the high-precision map and the semantic information of traffic facilities in the target semantic map are fused according to the second correspondence relationship to obtain the second fusion result. The target semantic map is then corrected based on the second fusion result to update the semantic map from the current parking lot to the target parking lot.

6. The vehicle map construction and positioning method according to claim 4, characterized in that, Obtain the first correspondence between the coordinate information of the vehicle trajectory corresponding to the GNSS signal and the coordinate information of the vehicle trajectory generated based on dead reckoning, including: When generating coordinate information of vehicle trajectories based on dead reckoning, if GNSS signals are present, the coordinate information of the vehicle trajectory corresponding to the GNSS signals is obtained. The coordinate information of the vehicle trajectory corresponding to the GNSS signal is bound to the coordinate information of the vehicle trajectory generated based on dead reckoning to determine the first correspondence.

7. The vehicle map construction and positioning method according to claim 5, characterized in that, Obtaining a second correspondence between the semantic information of traffic facilities in a high-precision map and the semantic information of traffic facilities in a target semantic map, including: During the construction of the target semantic map, when the vehicle's location is within the range of the high-precision map, the semantic information of the traffic facilities in the high-precision map is obtained; The semantic information of traffic facilities in the high-precision map is bound to the semantic information of traffic facilities in the target semantic map to determine the second correspondence.

8. The method for map construction and positioning of vehicles according to any one of claims 1-7, characterized in that, A target semantic map is constructed based on the coordinate information of the vehicle trajectory, the heading information of the vehicle, and the semantic information of the traffic facilities, including: The semantic information of the traffic facilities, the heading information of the vehicles, and the coordinate information of the vehicle trajectories are unified into the same coordinate system; The vehicle trajectory is determined based on the coordinate information of the vehicle trajectory and the heading information of the vehicle. The semantic information of the vehicle trajectory and the traffic facilities is mapped onto a preset map frame to determine the target semantic map.

9. A vehicle map building and positioning device, characterized in that, The device includes: The acquisition module is used to acquire the semantic map from the current parking lot to the target parking lot, the current positioning result, the coordinate information of the vehicle trajectory, the vehicle's heading information, and the semantic information of traffic facilities; The mapping module is used to construct a target semantic map in real time based on the coordinate information of the vehicle trajectory, the heading information of the vehicle, and the semantic information of the traffic facilities. The positioning module is used to determine the initial position of the vehicle based on the current positioning result, match the semantic map from the current parking lot to the target parking lot with the target semantic map based on the initial position of the vehicle to determine the vehicle position, and update the vehicle position by matching the target semantic map with the semantic map from the current parking lot to the target parking lot when the vehicle position is not within the range of the high-precision map.

10. A vehicle, characterized in that, The system includes a memory, a processor, and a vehicle map building and positioning program stored in the memory and executable on the processor. When the processor executes the vehicle map building and positioning program, it implements the vehicle map building and positioning method according to any one of claims 1-8.

Images