Vehicle positioning method and device

Abstract

The embodiment of the application provides a vehicle positioning method and device, the method comprises the following steps: determining a self-vehicle positioning track of a target vehicle according to self-vehicle positioning information of the target vehicle determined by a positioning unit of the target vehicle; receiving at least one perceived vehicle track sent by a roadside computing device, wherein the perceived vehicle track is determined by the roadside computing device according to collected roadside information; determining a target vehicle track matched with the self-vehicle positioning track from the at least one perceived vehicle track; and for any first time in a first period, if the self-vehicle positioning information of the target vehicle meets a first preset condition, predicting a vehicle position of the target vehicle at the first time according to the target vehicle track. The technical scheme of the application can effectively improve the accuracy of vehicle positioning in the case that the base station coverage is insufficient or the base station signal cannot be received.

Description

Technical Field

[0001] This application relates to computer technology, and more particularly to a vehicle positioning method and apparatus. Background Technology

[0002] High-precision positioning technology can utilize RTK (Real-time kinematic) positioning, vehicle inertial navigation, and high-precision road networks to achieve high-precision positioning.

[0003] High-precision positioning technology can typically be enhanced by ground base stations, thereby improving the effectiveness of traditional positioning. However, insufficient ground base station coverage can lead to high-precision positioning drift or failure. In such cases, inertial navigation fusion and map matching techniques can be used to correct the positioning in a short period of time. However, under the influence of long-term positioning deviations, the positioning results corrected by inertial navigation fusion and map matching will also accumulate errors.

[0004] Therefore, current high-precision positioning technology may suffer from poor vehicle positioning accuracy when ground base station coverage is insufficient or base station signals cannot be received. Summary of the Invention

[0005] This application provides a vehicle positioning method and apparatus to overcome the problem of poor vehicle positioning accuracy.

[0006] In a first aspect, embodiments of this application provide a vehicle positioning method, including:

[0007] Based on the vehicle positioning information determined by the positioning unit of the target vehicle, the vehicle positioning trajectory of the target vehicle is determined.

[0008] Receive at least one perceived vehicle trajectory sent by the roadside computing device, wherein the perceived vehicle trajectory is determined by the roadside computing device based on the collected roadside information;

[0009] Among the at least one perceived vehicle trajectory, a target vehicle trajectory that matches the self-positioning trajectory is determined;

[0010] For any first moment within the first time period, if the vehicle positioning information of the target vehicle meets the first preset condition, then the vehicle position of the target vehicle at the first moment is predicted based on the trajectory of the target vehicle.

[0011] Secondly, embodiments of this application provide a vehicle positioning device, comprising:

[0012] The determination module is used to determine the vehicle positioning trajectory of the target vehicle based on the vehicle positioning information determined by the positioning unit of the target vehicle.

[0013] A receiving module is used to receive at least one perceived vehicle trajectory sent by a roadside computing device, wherein the perceived vehicle trajectory is determined by the roadside computing device based on collected roadside information;

[0014] The determining module is further configured to determine, among the at least one perceived vehicle trajectory, a target vehicle trajectory that matches the self-positioning trajectory;

[0015] The processing module is used to predict the vehicle position of the target vehicle at any first moment within the first time period if the vehicle positioning information of the target vehicle meets a first preset condition, based on the trajectory of the target vehicle.

[0016] Thirdly, embodiments of this application provide an electronic device, including:

[0017] Memory, used to store programs;

[0018] A processor for executing the program stored in the memory, wherein, when the program is executed, the processor is configured to perform the method described in the first aspect above and any of the various possible designs of the first aspect.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the methods described in the first aspect above and any of the various possible designs of the first aspect.

[0020] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect above and any of the various possible designs of the first aspect.

[0021] This application provides a vehicle positioning method and apparatus. The method includes: determining the vehicle positioning trajectory of a target vehicle based on the vehicle positioning information determined by the positioning unit of the target vehicle; receiving at least one perceived vehicle trajectory sent by a roadside computing device, the perceived vehicle trajectory being determined by the roadside computing device based on collected roadside information; determining a target vehicle trajectory that matches the self-positioning trajectory among the at least one perceived vehicle trajectory; and predicting the vehicle position of the target vehicle at any first moment within a first time period if the self-positioning information of the target vehicle meets a first preset condition based on the target vehicle trajectory. By determining the target vehicle trajectory that matches the self-positioning trajectory of the target vehicle among multiple perceived vehicle trajectories sent by the roadside computing device, the vehicle trajectory determined by the roadside computing device for the target vehicle can be obtained. Then, when the accuracy of the self-positioning information of the target vehicle cannot be guaranteed, the vehicle position of the target vehicle can be predicted based on the target vehicle trajectory. Because the vehicle trajectory determined by the roadside computing device is not affected by base station deployment, it effectively improves the accuracy of vehicle positioning when base station coverage is insufficient or base station signals cannot be received. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 The application scenarios of the vehicle positioning method provided in the embodiments of this application will be described;

[0024] Figure 2 A flowchart of the vehicle positioning method provided in the embodiments of this application;

[0025] Figure 3 The flow chart of the vehicle positioning method provided in the embodiments of this application Figure 2 ;

[0026] Figure 4 A schematic diagram illustrating the implementation of determining the trajectory of a target vehicle according to an embodiment of this application;

[0027] Figure 5 The flow chart of the vehicle positioning method provided in the embodiments of this application Figure 3 ;

[0028] Figure 6 A schematic diagram illustrating the trajectory data acquisition frequency provided in an embodiment of this application;

[0029] Figure 7A schematic diagram illustrating the implementation of trajectory point time alignment provided in an embodiment of this application;

[0030] Figure 8 This is a schematic diagram of the interface for displaying vehicle information provided in an embodiment of this application;

[0031] Figure 9 A schematic diagram illustrating the implementation of smoothing processing for the perceived vehicle trajectory provided in an embodiment of this application;

[0032] Figure 10 This is a system schematic diagram of the vehicle positioning method provided in the embodiments of this application;

[0033] Figure 11 This is a schematic diagram of the vehicle positioning device provided in the embodiments of this application;

[0034] Figure 12 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0036] To better understand the technical solution of this application, the relevant concepts involved in this application will be explained first.

[0037] Lane-level navigation: Utilizes high-precision road networks and high-precision positioning technology to provide vehicles with lane-level positioning and lane-level guidance capabilities.

[0038] High-precision road network: a road network topology structure consisting of lanes, road segments, intersections, and their upstream and downstream relationships.

[0039] High-precision positioning: The ability to achieve centimeter-level high-precision positioning by utilizing RTK positioning, vehicle inertial navigation and high-precision road networks.

[0040] Perception fusion: A method that uses vehicle latitude and longitude data obtained by mapping the vehicles identified by perception devices such as millimeter-wave radar, lidar, and high-definition cameras to a high-precision road network, and then uses the perception data to perform cross-point trajectory fusion to obtain the full-path lane-level trajectory.

[0041] Trajectory prediction: Combining historical trajectory data and using the trajectory information of the vehicle's previous n points, predict the trajectory within the next m time slices.

[0042] Based on the above introduction, the relevant technologies involved in this application will be further described in detail below.

[0043] The purpose of lane-level navigation technology is to provide lane-level positioning and lane-level guidance for vehicles. Compared with traditional navigation technology, lane-level navigation technology can improve yaw analysis from the road level to the lane level and replan the route for the current lane.

[0044] To achieve accurate lane-level navigation, it is crucial to accurately determine the vehicle's location information on the road. Current lane-level navigation technologies typically utilize RTK positioning, inertial navigation systems, and high-precision road networks to achieve high-precision positioning.

[0045] Because RTK technology itself relies on ground base stations, current high-precision positioning technologies can enhance the positioning effect by strengthening ground base stations, thereby improving the traditional high-precision positioning effect and enabling the positioning effect to reach the decimeter or even centimeter level.

[0046] However, when ground base station coverage is insufficient or base station signals are unavailable, high-precision positioning can drift or fail. While inertial navigation fusion and map matching techniques can correct the positioning results quickly, in scenarios such as those with mountainous terrain or tunnels, long-term positioning errors may occur. In such cases, the positioning results corrected using inertial navigation fusion and map matching will accumulate increasingly severe errors. Therefore, current high-precision positioning technologies suffer from poor positioning accuracy when ground base station coverage is insufficient or base station signals are unavailable.

[0047] To address the aforementioned technical problems, this application proposes the following technical concept: Vehicle-road cooperative technology can be used to receive roadside sensing results from sensing devices on the road and fuse them with the vehicle's positioning results to determine the vehicle's location. This can effectively determine the vehicle's location even when ground base station coverage is insufficient or base station signals cannot be received, thereby improving the accuracy of vehicle positioning.

[0048] The following is combined Figure 1 The application scenarios of the vehicle positioning method provided in this application are described. Figure 1 The application scenarios of the vehicle positioning method provided in the embodiments of this application will be described.

[0049] like Figure 1 As shown, there are roadside devices in the road, which may include, for example, a roadside sensing device 101, a roadside computing device 102, and a roadside communication device 103.

[0050] The roadside sensing device 101 is used to collect roadside information. This device can be, for example, a camera, millimeter-wave radar, or lidar, and its specific implementation can be determined based on actual conditions. The roadside information collected by the roadside sensing device can include vehicle images, collected vehicle information, and road images, etc.

[0051] The roadside computing device 102 can be deployed along the road to perform high-performance calculations and decisions based on roadside information and / or vehicle-side information; therefore, the roadside computing device has data processing capabilities. For example, the roadside computing device 102 can receive roadside information sent by the roadside sensing device 101 and determine the driving trajectory of vehicles on the road based on the roadside information. Figure 1 As shown, roadside computing devices can be, for example, MEC (Mobile Edge Computing) devices, or other data processing units.

[0052] The roadside communication device 103 can communicate wirelessly with the vehicle terminal. The roadside device can be, for example, an RSU (Road Side Unit) or a communication base station, etc.

[0053] For example, refer to Figure 1 To understand this, the roadside sensing device 101 can collect roadside information and report it to the roadside computing device 102. The roadside computing device 102 can, for example, determine the driving trajectory of vehicles on the road based on the roadside information. Then, the roadside computing device 102 can, for example, broadcast the vehicle's driving trajectory to all vehicles on the road via the roadside communication device 103.

[0054] It is understandable that the roadside computing device 102 determines the vehicle's trajectory based on the roadside information reported by the roadside sensing device 101. Therefore, the roadside computing device 102 can, for example, calculate the trajectories of multiple vehicles within the collection range of the roadside sensing device 101. Furthermore, when transmitting the vehicle's trajectory through the roadside communication device 103, it is done via broadcast, so vehicles within the communication range of the roadside communication device 103 can receive the trajectory information.

[0055] In roads, roadside sensing devices, roadside computing devices, and roadside communication devices are typically configured in a corresponding manner. They can be multiple independent devices or a single integrated device. Therefore, it can be understood that roadside devices can determine the driving trajectory of vehicles within a certain range and broadcast the determined vehicle driving trajectory to vehicles within that range.

[0056] In one possible implementation, an On-Board Unit (OBU) could be present in the vehicle terminal. Therefore, when the roadside computing device sends vehicle trajectories to the vehicle terminal, this can be done via the MEC-RSU-OBU link. Similarly, when the vehicle terminal needs to report information to the roadside computing device, the vehicle data can be aggregated to the MEC via the OBU-RSU-MEC link.

[0057] Based on the above description, the vehicle positioning method provided in this application will be described below with reference to specific embodiments. The methods provided in the various embodiments of this application are applied to the target vehicle. In one possible implementation, for example, the processor or chip in the target vehicle may execute the various steps to achieve the corresponding effect.

[0058] First, combine Figure 2 To explain, Figure 2 A flowchart of a vehicle positioning method provided in an embodiment of this application.

[0059] like Figure 2 As shown, the method includes:

[0060] S201. Determine the vehicle positioning trajectory of the target vehicle based on the vehicle positioning information determined by the positioning unit of the target vehicle.

[0061] The target vehicle contains a positioning unit, which can determine the target vehicle's own positioning information through methods such as RTK positioning and vehicle inertial navigation as described above. In this embodiment, this is referred to as vehicle positioning information.

[0062] The target vehicle can determine its own positioning trajectory based on the self-positioning information determined by the positioning unit at multiple times. The self-positioning trajectory is the vehicle's own driving trajectory.

[0063] S202. Receive at least one perceived vehicle trajectory sent by the roadside computing device, wherein the perceived vehicle trajectory is determined by the roadside computing device based on the collected roadside information.

[0064] In this embodiment, the target device can also receive at least one perceived vehicle trajectory sent by the roadside computing device. Based on the above description, it can be determined that the roadside computing device can determine the vehicle trajectory of a vehicle on the road based on the roadside information collected by the roadside sensing device. In this embodiment, the vehicle trajectory calculated by the roadside computing device is referred to as the perceived vehicle trajectory. The roadside computing device can then send the vehicle trajectory to the target terminal via a roadside communication device.

[0065] In one possible implementation, roadside computing devices can utilize high-precision road networks and radar-visual fusion technology to detect, track, and locate vehicles on the road. Simultaneously, by using spatiotemporal constraints, as well as features such as lane, speed, vehicle attributes, and front-to-back relationships, cross-point trajectory fusion can be performed to determine the lane-level trajectory reconstruction result of the entire path within the device's coverage area, enabling vehicle tracking relay and effectively determining the perceived vehicle trajectory on the road.

[0066] S203. In at least one perceived vehicle trajectory, determine the target vehicle trajectory that matches the self-positioning trajectory.

[0067] Based on the above description, it can be determined that the perceived vehicle trajectory in this embodiment is a vehicle trajectory determined by the roadside computing device through fusion calculation. There may be multiple trajectories, the specific number depending on the vehicle situation on the road. The self-positioning trajectory, on the other hand, is determined by the target vehicle based on its own collected self-positioning information. Since the target vehicle is also traveling on the road, at least one perceived vehicle trajectory may contain the trajectory corresponding to the target vehicle.

[0068] In one possible implementation, a target vehicle trajectory that matches the self-positioning trajectory can be determined from at least one perceived vehicle trajectory, where the target vehicle trajectory can be considered as the vehicle trajectory of the target vehicle determined by the roadside computing device.

[0069] S204. For any first moment within the first time period, if the vehicle positioning information of the target vehicle meets the first preset condition, then predict the vehicle position of the target vehicle at the first moment based on the trajectory of the target vehicle.

[0070] It is understandable that, since vehicles on the road are moving, when the roadside computing unit sends the perceived vehicle trajectory to the vehicles on the road, for example, by sending the latest perceived vehicle trajectory at regular intervals, the target vehicle will receive the perceived vehicle trajectory sent by the roadside computing unit multiple times at different times.

[0071] The time interval between each time the target vehicle receives a detected vehicle trajectory and the next time it receives a detected vehicle trajectory can be, for example, the first time interval in this embodiment. During the first time interval, the target vehicle performs corresponding positioning processing based on the most recently received detected vehicle trajectory. When a new detected vehicle trajectory is received, a new first time interval is entered, and corresponding positioning processing is performed according to the new detected vehicle trajectory. Alternatively, the first time interval can be any time interval during which the target vehicle's position needs to be determined; it can be selected and set according to actual needs.

[0072] There can be multiple moments within the first time period. For each moment within the first time period, the target vehicle needs to determine its location. The processing method for each moment within the first time period is similar. Therefore, the following explanation focuses on any one moment within the first time period.

[0073] In this embodiment, a first preset condition is set for the vehicle positioning information. This first preset condition could be, for example, that the positioning accuracy of the vehicle positioning information is less than or equal to a first threshold. For instance, the positioning accuracy can be determined based on the matching between the vehicle positioning information and the road; when the vehicle positioning information significantly deviates from the road, the accuracy can be considered poor. Alternatively, the positioning accuracy can be analyzed based on multiple historical vehicle positioning data. For example, if abnormal fluctuations occur in the vehicle positioning information at multiple adjacent times, the accuracy can be considered poor.

[0074] Alternatively, the first preset condition could be that the vehicle's location information is collected when the target vehicle is located on a preset type of road segment. The preset type of road segment could be a road segment with less base station coverage, or a tunnel segment or a mountain road segment, etc.

[0075] Therefore, it can be understood that when the vehicle's location information meets the first preset condition, it indicates that the vehicle's location information is obviously abnormal or lost. Thus, if the location accuracy of the target vehicle's location information meets the first preset condition, it can be determined that the target vehicle's location cannot be accurately determined based on the current location information.

[0076] In one possible implementation, since the vehicle trajectory determined by the roadside computing device is not affected by the base station deployment, the vehicle position of the target vehicle at the first moment can be predicted based on the target vehicle trajectory, thereby determining the vehicle position of the target vehicle at the first moment.

[0077] In another possible implementation, if the self-positioning information of the target vehicle does not meet the first preset condition, it can be considered that the self-positioning information of the target vehicle is relatively accurate. Therefore, in this case, the vehicle position of the target vehicle at the first moment can be determined based on the self-positioning information of the target vehicle at the first moment.

[0078] The vehicle positioning method provided in this application includes: determining the vehicle positioning trajectory of a target vehicle based on the vehicle positioning information determined by the positioning unit of the target vehicle; receiving at least one perceived vehicle trajectory sent by a roadside computing device, the perceived vehicle trajectory being determined by the roadside computing device based on collected roadside information; determining the target vehicle trajectory that matches the self-positioning trajectory among the at least one perceived vehicle trajectory; and predicting the vehicle position of the target vehicle at any first moment within a first time period if the self-positioning information of the target vehicle meets a first preset condition based on the target vehicle trajectory. By determining the target vehicle trajectory that matches the self-positioning trajectory of the target vehicle among multiple perceived vehicle trajectories sent by the roadside computing device, the vehicle trajectory determined by the roadside computing device for the target vehicle can be obtained. Then, when the accuracy of the self-positioning information of the target vehicle cannot be guaranteed, the vehicle position of the target vehicle is predicted based on the target vehicle trajectory. Because the vehicle trajectory determined by the roadside computing device is not affected by base station deployment, the accuracy of vehicle positioning is effectively improved when base station coverage is insufficient or base station signals cannot be received.

[0079] Based on the above description, after predicting the target vehicle's position at the first moment according to its trajectory, sub-trajectories can be determined, for example, based on the vehicle's positions at multiple moments within the first time period. These sub-trajectories are then stitched onto the target vehicle's auto-location trajectory to obtain an updated auto-location trajectory. This ensures that abnormal trajectory points are replaced with normal ones in the determined auto-location trajectory, guaranteeing the accuracy of the auto-location trajectory and providing a correct data foundation for subsequent vehicle positioning data.

[0080] Therefore, the technical solution of this application can, on the one hand, integrate vehicle positioning results and roadside perception results to improve the positioning accuracy of the target vehicle, and at the same time eliminate abnormal results of vehicle positioning and perform position correction. On the other hand, in the event of loss of vehicle positioning, roadside perception results can be used to complete the trajectory, ensuring high-precision positioning results for the vehicle in special road sections such as those obstructed by mountains or in tunnels.

[0081] Based on the above introduction, it can be determined that in this embodiment, it is necessary to determine the target vehicle trajectory that matches the target vehicle's self-positioning trajectory among multiple perceived vehicle trajectories. The following will combine... Figures 3 to 4 The specific implementation method for determining the trajectory of the target vehicle will be described in further detail. Figure 3 The flow chart of the vehicle positioning method provided in the embodiments of this application Figure 2 , Figure 4 This is a schematic diagram illustrating the implementation of determining the trajectory of a target vehicle according to an embodiment of this application.

[0082] like Figure 3As shown, the method includes:

[0083] S301. Obtain the trajectory identifier of each sensing vehicle.

[0084] The roadside sensing device assigns a corresponding trajectory identifier to each determined vehicle trajectory to distinguish multiple different trajectories, and can continuously maintain each trajectory based on the trajectory identifier. Therefore, in this embodiment, the target vehicle can obtain the trajectory identifier corresponding to each of the various vehicle trajectories.

[0085] S302. Determine whether a preset trajectory identifier exists among multiple trajectory identifiers. If yes, execute S303; otherwise, execute S304.

[0086] Based on the above description, it can be confirmed that the roadside computing device will periodically send the perceived vehicle trajectory to the target vehicle multiple times, and the roadside computing device will continuously maintain a perceived vehicle trajectory using the same trajectory identifier. Therefore, upon receiving a perceived vehicle trajectory, it can first determine, for example, whether a previously matched perceived vehicle trajectory exists.

[0087] In one possible implementation, for example, it can be determined whether there is a preset trajectory identifier among multiple trajectory identifiers, where the preset trajectory identifier is the trajectory identifier of the perceived vehicle trajectory that matches the self-positioning trajectory of the target vehicle within a historical period.

[0088] S303, the perceived vehicle trajectory corresponding to the preset trajectory marker is determined as the target vehicle trajectory.

[0089] In one possible implementation, if a preset trajectory identifier exists among multiple trajectory identifiers, the perceived vehicle trajectory corresponding to the preset trajectory identifier that was previously matched can be determined. Therefore, the perceived vehicle trajectory corresponding to the preset trajectory identifier can be directly determined as the target vehicle trajectory that matches the target vehicle's self-positioning trajectory.

[0090] For example, it can be combined Figure 4 To understand, such as Figure 4 As shown, trajectory 401 is assumed to be the target vehicle's self-positioning trajectory, and it is assumed that the target vehicle receives three perceived vehicle trajectories sent by the roadside computing device, namely... Figure 4 The trajectories shown are trajectories 1, 2, and 3.

[0091] Assuming that trajectory 2 is a perceived vehicle trajectory that matches the vehicle positioning trajectory 401 within a historical period, then the trajectory identifier of trajectory 2 is the preset trajectory identifier. Therefore, it can be determined that trajectory 2 is the currently determined target vehicle trajectory.

[0092] In one possible implementation, to ensure that the perceived vehicle trajectory corresponding to the preset trajectory identifier is indeed the trajectory corresponding to the target vehicle trajectory, the similarity between the perceived vehicle trajectory corresponding to the preset trajectory identifier and the vehicle's localization trajectory can be further determined. If the similarity is greater than or equal to a second preset threshold, the perceived vehicle trajectory corresponding to the preset trajectory identifier can be determined as the target vehicle trajectory, thus further improving the accuracy of the determined target vehicle trajectory.

[0093] For example in Figure 4 In the example, the similarity between trajectory 401 and trajectory 2 is determined. If the similarity is greater than or equal to the second preset threshold, then trajectory 2 can be determined to be the target vehicle trajectory matched by trajectory 401.

[0094] S304. Based on the trajectory point information of each trajectory point in the perceived vehicle trajectory and the trajectory point information of each trajectory point in the self-positioning trajectory, determine the similarity between the perceived vehicle trajectory and the self-positioning trajectory.

[0095] In another possible implementation, if there is no preset trajectory identifier among the multiple trajectory identifiers, it means that among the multiple perceived vehicle trajectories sent by the current roadside computing device, there is no vehicle trajectory that the target vehicle has previously matched. Therefore, the similarity between the perceived vehicle trajectory and the self-positioning trajectory can be determined based on the trajectory point information of each trajectory point in the perceived vehicle trajectory and the trajectory point information of each trajectory point in the self-positioning trajectory.

[0096] Alternatively, if the similarity between the perceived vehicle trajectory corresponding to the preset trajectory identifier and the self-positioning trajectory is less than the second preset threshold, it means that the perceived vehicle trajectory corresponding to the current preset trajectory identifier may not be matched with the self-positioning trajectory. In this case, the similarity between the perceived vehicle trajectory and the self-positioning trajectory can be determined based on the trajectory point information of each trajectory point in the perceived vehicle trajectory and the trajectory point information of each trajectory point in the self-positioning trajectory.

[0097] It is understood that in this embodiment, if there are previously matched vehicle trajectories of the target vehicle among multiple vehicle identifiers, the target vehicle trajectory can be determined directly, or the target vehicle trajectory can be determined simply by determining the similarity between a single vehicle trajectory and the vehicle's localization trajectory.

[0098] In cases where there are no previously matched perceived vehicle trajectories for the target vehicle, or when the similarity between previously matched perceived vehicle trajectories and the vehicle's current positioning trajectory is poor, it is necessary to determine the similarity for multiple perceived vehicle trajectories. Therefore, this can effectively save computing resources and improve the efficiency of vehicle positioning.

[0099] The trajectory point information in this embodiment may include, for example, the latitude and longitude of the trajectory point, its altitude, speed, acceleration, and orientation angle. For instance, based on the trajectory point information, the lateral distance, longitudinal distance, altitude difference, speed difference, acceleration difference, and orientation angle difference between two corresponding trajectory points in the perceived vehicle trajectory and the self-positioning trajectory can be determined. Then, the trajectory point similarity between the two corresponding trajectory points can be determined, and the similarity between the two trajectories can be determined based on the similarity of multiple trajectory points. When determining the similarity, for example, the covariance of the multi-dimensional data mentioned above can be determined, and the joint Gaussian probability distribution corresponding to multiple trajectories can be compared. The perceived vehicle trajectory with the highest probability corresponds to the perceived vehicle trajectory with the highest similarity.

[0100] In actual implementation, the specific implementation for determining the similarity between trajectories can be selected and set according to actual needs, and this embodiment does not impose any restrictions on this.

[0101] S305. The perceived vehicle trajectory with the highest similarity and a similarity greater than the first preset threshold is determined as the target vehicle trajectory.

[0102] After determining the similarity between each perceived vehicle trajectory and the vehicle's localization trajectory, for example, the perceived vehicle trajectory with the highest similarity and a similarity greater than a first preset threshold can be identified as the target vehicle trajectory.

[0103] In this embodiment, both the first preset threshold and the second preset threshold can be selected and set according to actual needs. They can be the same or different, and this embodiment does not impose any restrictions on this.

[0104] The vehicle positioning method provided in this application determines whether a preset trajectory identifier exists among the trajectory identifiers of multiple perceived vehicle trajectories. If a preset trajectory identifier exists, the perceived vehicle trajectory corresponding to the preset trajectory identifier is directly identified as the target vehicle trajectory. If no preset trajectory identifier exists, the similarity between each perceived vehicle trajectory and the vehicle's positioning trajectory is determined, thereby effectively reducing data computation and improving vehicle positioning efficiency. Furthermore, after determining the similarity between each perceived vehicle trajectory and the vehicle's positioning trajectory, the perceived vehicle trajectory with the highest similarity and a similarity greater than or equal to a first preset threshold is identified as the target vehicle trajectory, thus effectively determining the target vehicle trajectory corresponding to the target vehicle.

[0105] Based on the above introduction, since the frequency of data collection by the roadside sensing device and the frequency of data collection by the target vehicle may be different, the times of each trajectory point in the sensing vehicle trajectory and the self-positioning trajectory may not correspond. In order to correctly perform subsequent data processing, in this embodiment, the trajectory points in the sensing vehicle trajectory and the trajectory points in the self-positioning trajectory can be time-aligned before data processing based on the sensing vehicle trajectory.

[0106] The following is combined Figures 5 to 7 The specific implementation methods of time alignment will be further detailed. Figure 5 The flow chart of the vehicle positioning method provided in the embodiments of this application Figure 3 , Figure 6 This is a schematic diagram illustrating the trajectory data acquisition frequency provided in an embodiment of this application. Figure 7 This is a schematic diagram illustrating the implementation of trajectory point time alignment in an embodiment of this application.

[0107] like Figure 5 As shown, the method includes:

[0108] S501. Based on the delay duration, perform delay compensation on the acquisition time of each trajectory point in the perceived vehicle trajectory to obtain the delayed-compensated perceived vehicle trajectory.

[0109] For example, we can first combine Figure 6 Understanding the frequency of trajectory points in the perceived vehicle trajectory and the vehicle's localization trajectory. For example... Figure 6 As shown in Figure 601, we expect the collected data to be high-frequency and evenly spaced. However, in actual implementation, it may not be possible to collect data at high frequencies; possible collection frequencies are as follows. Figure 6 As shown in 602 and 603.

[0110] Reference Figure 6 The data acquisition frequency for the target vehicle could be, for example, one frame every 100ms. Figure 6 As shown in 602, the acquisition time interval between two adjacent trajectory points in the vehicle positioning trajectory is 100ms.

[0111] and reference Figure 6 Assuming the roadside sensing device collects data every 160ms, then... Figure 6 As shown in 603, the acquisition time interval between two adjacent trajectory points in the perceived vehicle trajectory is 160ms.

[0112] Therefore, the trajectory points in the perceived vehicle trajectory and the trajectory points in the self-positioning trajectory are not aligned in time. In order to ensure the accuracy of subsequent data processing, the trajectory points in the two trajectories can be aligned in time.

[0113] In one possible implementation, since the roadside computing device sends the perceived vehicle trajectory to the target vehicle through a certain data transmission link, this data transmission link will cause data delay. For example, the acquisition time of each trajectory point in the perceived vehicle trajectory can be compensated for the delay based on the delay duration, so as to obtain the delayed-compensated perceived vehicle trajectory.

[0114] S502. Based on the correspondence between each trajectory point in the perceived vehicle trajectory after delay compensation and each trajectory point in the self-positioning trajectory, determine at least one trajectory point pair.

[0115] After determining the delayed-compensated perceived vehicle trajectory, at least one trajectory point pair can be identified, for example, based on the correspondence between each trajectory point in the delayed-compensated perceived vehicle trajectory and each trajectory point in the vehicle localization trajectory. Each trajectory point pair includes a first trajectory point from the delayed-compensated perceived vehicle trajectory and a second trajectory point from the vehicle localization trajectory. This correspondence can be determined, for example, based on the proximity of the trajectory point acquisition times. For instance, for any trajectory point 'a' in the delayed-compensated perceived vehicle trajectory, among the multiple trajectory points in the vehicle localization trajectory, the trajectory point 'b' with the closest acquisition time is identified, and then trajectory points 'a' and 'b' are designated as corresponding trajectory points.

[0116] For example, it can be combined Figure 7 To understand, such as Figure 7 As shown, assuming the interval between adjacent trajectory points of the vehicle's positioning trajectory is 100ms, Figure 7 The diagram illustrates the vehicle's localization trajectory, including trajectory points 1 through 8. It also assumes that the interval between adjacent trajectory points is 160ms. Figure 7 The diagram illustrates the vehicle's positioning trajectory, including trajectory points a to e.

[0117] For example, determining trajectory point pairs based on the similarity of their acquisition times can be done by referring to... Figure 7 As shown, five trajectory point pairs were identified: trajectory point 2 and trajectory point a, trajectory point 3 and trajectory point b, trajectory point 5 and trajectory point c, trajectory point 6 and trajectory point d, and trajectory point 8 and trajectory point e. It can be understood that the number of trajectory point pairs depends on the number of trajectory points in the trajectory with the lower acquisition frequency.

[0118] S503. For any pair of trajectory points, determine the target time based on the first acquisition time corresponding to the first trajectory point and the second acquisition time corresponding to the second trajectory point.

[0119] In this embodiment, after determining the trajectory point pair, the two trajectory points in the trajectory point pair can be time aligned. To perform time alignment, a reference alignment time needs to be determined. Therefore, for example, based on the first acquisition time corresponding to the first trajectory point and the second acquisition time corresponding to the second trajectory point in the trajectory point pair, the target time is determined, which is the time when the two trajectory points need to be aligned.

[0120] In one possible implementation, the later of the first and second acquisition times can be determined as the target time. Alternatively, the earlier of the first and second acquisition times can be determined as the acquisition time. Another possibility is that the target time can be determined between the first and second acquisition times; for example, the target time could be the midpoint between the first and second acquisition times, or it could be any time between the first and second acquisition times. This embodiment does not limit the specific implementation of the target time, as long as a common, aligned reference time is determined for the first and second trajectory points.

[0121] S504. Collect a third trajectory point in the perceived vehicle trajectory after delay compensation, with the collection time being the target time, and determine a fourth trajectory point in the self-positioning trajectory, with the collection time being the target time.

[0122] After determining the target time as described above, the third trajectory point with the acquisition time as the target time can be determined based on the perceived vehicle trajectory after delay compensation. And the fourth trajectory point with the acquisition time as the target time can be determined based on the vehicle's positioning trajectory.

[0123] The third trajectory point can also be understood as the first trajectory point after time alignment. For example, frame interpolation can be performed at the target time in the perceived vehicle trajectory after delay compensation to determine the third trajectory point. Similarly, the fourth trajectory point can be understood as the second trajectory point after time alignment. For example, frame interpolation can be performed at the target time in the vehicle's localization trajectory to determine the fourth trajectory point.

[0124] For example, it can be combined Figure 7 To understand, Figure 7 The example determines the target time by setting the later of the first and second acquisition times as the target time. For instance, for the trajectory point pair of trajectory point 2 and trajectory point a, if the later acquisition time is 200ms, then the target time can be determined to be 200ms.

[0125] Then, for example, based on the vehicle's positioning trajectory, we can determine trajectory point 2' (which is actually equivalent to trajectory point 2) with a sampling time of 200ms within the vehicle's positioning trajectory. Similarly, based on the perceived vehicle trajectory after delay compensation, we can determine trajectory point a' (which can be predicted through frame interpolation). Therefore, trajectory point 2' can be understood as the fourth trajectory point mentioned above, and trajectory point a' can be understood as the third trajectory point mentioned above.

[0126] against Figure 7 The other trajectory point pairs shown in the diagram can also be processed in a similar way, which will not be elaborated here.

[0127] S505. Determine the time-aligned trajectory point pair between the third and fourth trajectory points.

[0128] After determining the third and fourth trajectory points, the third and fourth trajectory points can be used to determine the time-aligned trajectory point pairs.

[0129] S506. Based on multiple time-aligned trajectory point pairs, determine the time-aligned perceived vehicle trajectory and the time-aligned self-positioning trajectory.

[0130] Then, based on multiple time-aligned trajectory point pairs, multiple third trajectory points can be sequentially connected to form a time-aligned perceived vehicle trajectory, and multiple fourth trajectory points can be sequentially connected to form a time-aligned autonomous vehicle localization trajectory. The acquisition times of each trajectory point in the time-aligned perceived vehicle trajectory and the time-aligned autonomous vehicle localization trajectory are corresponding.

[0131] The vehicle positioning method provided in this application can effectively avoid data errors caused by the different data collection frequencies of roadside sensing devices and target vehicles by aligning each trajectory point in the perceived vehicle trajectory and the self-positioning trajectory to the same target time. By ensuring that the trajectory points of the self-positioning trajectory and the perceived vehicle trajectory are at the same time point, high-quality trajectory data can be provided for subsequent data processing, thereby further improving the accuracy of vehicle positioning.

[0132] Based on the above description, it should also be noted that the vehicle positioning method provided in this application can provide not only the positioning information of the target vehicle, but also the positioning information of other vehicles on the road.

[0133] Understandably, in current technologies, if a vehicle needs to understand information about other vehicles on the road, it generally relies on autonomous driving perception technology, using multi-sensor fusion such as cameras and LiDAR to perceive surrounding vehicles. However, autonomous driving perception technology requires vehicles to install expensive hardware and software perception devices, and many finished vehicles lack these capabilities. Therefore, many current vehicles are unable to obtain information about other vehicles on the road.

[0134] The technical solution of this application, after determining the target vehicle trajectory that matches the self-driving vehicle's positioning trajectory, can determine the vehicle positions of other vehicles on the road, excluding the target vehicle, at multiple times within the first moment based on the trajectories of other perceived vehicles other than the target vehicle trajectory, thereby enabling non-autonomous vehicles to have the ability to perceive surrounding vehicles.

[0135] In one possible implementation, for example, the positions of other vehicles can be rendered in the target vehicle's graphical user interface at various times within the first time period, based on the positions of the other vehicles. Alternatively, the target vehicle's position information can be rendered in the target vehicle's graphical user interface at various times within the first time period, allowing the user to quickly and effectively obtain information about vehicles on the road.

[0136] For example, you can refer to Figure 8 To understand, Figure 8 This is a schematic diagram of the interface for displaying vehicle information provided in an embodiment of this application.

[0137] like Figure 8 As shown, for example, the position information of the target vehicle can be rendered in the graphical user interface based on the target vehicle's position, as illustrated in Figure 801. It can also be used to render the position information of other vehicles in the graphical user interface based on their positions, as illustrated in Figure 801. Figure 8 As shown in 802-805.

[0138] In one possible implementation, the roadside computing device can, for example, utilize video recognition capabilities to detect events on the road and determine the category of the events. These events may include, for example, vehicle collision events, traffic jam events, obstacle events, etc. This embodiment does not limit the specific implementation of the events on the road. The roadside computing device can then send the event information to the target vehicle. The event information may include, for example, event category, event location, event image, etc. This embodiment does not particularly limit the specific implementation of the event information.

[0139] Then, the target vehicle can, for example, render the event identifier corresponding to the event in the graphical user interface based on the event information, to remind the user that there is a certain event at the corresponding location.

[0140] In one possible implementation, when rendering vehicle information of the target vehicle, vehicle information of other vehicles, and event information, the positions of other vehicles and the positions of events can be converted relative to the target vehicle before rendering. Risk warning services can also be provided, such as collision warnings for surrounding vehicles, and early warnings for vehicles beyond visual range.

[0141] In summary, the technical solution of this application relies on roadside perception data vehicle-road cooperative technology. It utilizes roadside perception devices such as cameras or millimeter-wave radar mounted on smart road poles to acquire roadside information, and then uses roadside computing equipment to determine vehicle trajectories and event information. This information is then sent to the target device. The target device can combine its own vehicle positioning information with the roadside perception information to improve its own positioning accuracy, especially in areas with poor signal, such as tunnels. Furthermore, it can acquire information about other vehicles and events on the road, enabling a large number of non-autonomous vehicles to obtain information about surrounding vehicles and events. This allows for early risk warning, beyond-line-of-sight risk perception, and improved vehicle traffic efficiency.

[0142] In one possible implementation, the perceived vehicle trajectories sent by the roadside computing device may contain noise, out-of-order data, or dropped frames. Therefore, upon receiving the perceived vehicle trajectory, a smoothing process can be performed first. For example, this could be combined with... Figure 9 To understand, Figure 9 This is a schematic diagram illustrating the implementation of smoothing processing for the perceived vehicle trajectory provided in an embodiment of this application.

[0143] like Figure 9 As shown, the received vehicle trajectory data may be repeatedly transmitted, for example, referring to... Figure 9 In the first scenario, the received trajectory data contains duplicate trajectory points at times t2 and t3, as well as duplicate trajectory points at times t4 and t5. For these scenarios, we can perform deduplication on the duplicate trajectory points, such as removing duplicate trajectory points and keeping only one.

[0144] and reference Figure 9 The second scenario involves a delay in transmitting the received vehicle trajectory data. For example, a trajectory point that should correspond to time t1 might actually correspond to time t1', or vice versa. Delay compensation can be implemented in such cases.

[0145] and reference Figure 9The third scenario involves missing data in the received vehicle trajectory data. For example, there should be two trajectory points between time t1 and t2, but these points are missing due to data loss. To address this, the missing trajectory points can be supplemented based on the received trajectory points.

[0146] and reference Figure 9 In the fourth scenario, the received vehicle trajectory may have out-of-order trajectory points. To address this, the trajectory points can be correctly sorted based on their acquisition time to achieve smooth trajectory processing.

[0147] Subsequent processing based on the smoothed perceived vehicle trajectory can effectively ensure the accuracy and effectiveness of data processing.

[0148] Based on the various embodiments described above, the following will be combined with Figure 10 The specific implementation of the vehicle positioning method provided in this application will be further described in detail. Figure 10 This is a system schematic diagram of the vehicle positioning method provided in the embodiments of this application.

[0149] like Figure 10 As shown, there are three types of equipment: a cloud server, roadside equipment, and a target vehicle. The cloud server can provide control services to the roadside equipment, such as controlling how the roadside computing unit performs calculations. The cloud server can also provide map services to the target vehicle.

[0150] Among them, roadside computing devices, for example Figure 10 The MEC shown can perform event perception and trajectory fusion to determine event information and perceive vehicle trajectories, and send the relevant information to the target vehicle through the MEC-RSU-OBU link.

[0151] The target vehicle may contain a lane-level navigation map service application. This application can utilize a map SDK (Software Development Kit) to provide map services, such as navigation processing, based on cloud-based map services. It can also perform trajectory fusion based on the vehicle's own location and perceived vehicle trajectory to determine the vehicle's driving trajectory, as well as the location of the vehicle itself and other vehicles. Furthermore, it can identify events on the road and render them within the application to display the corresponding vehicle and event results.

[0152] Based on the above description, it can be determined that the vehicle positioning method provided in this application embodiment receives the perceived vehicle trajectory from the roadside computing device and determines the positioning results of the vehicle itself and other vehicles based on the perceived vehicle trajectory. This provides lane-level navigation services for the vehicle. Furthermore, it can receive event information from the roadside computing device and provide early warnings of vehicle collisions, accidents, and other risks based on the event information, without relying on vehicle-side sensing devices such as LiDAR and cameras. Simultaneously, when determining the vehicle's positioning, it comprehensively determines the vehicle's location based on the perceived vehicle trajectory and the vehicle's positioning trajectory. This allows for accurate and effective determination of the vehicle's position even when base station signals are weak or unavailable, improving positioning accuracy in special road sections such as tunnels or areas obstructed by mountains.

[0153] Figure 11 This is a schematic diagram of the vehicle positioning device provided in an embodiment of this application. Figure 11 As shown, the device 110 includes: a determining module 1101, a receiving module 1102, and a processing module 1103.

[0154] The determining module 1101 is used to determine the self-positioning trajectory of the target vehicle based on the self-positioning information determined by the positioning unit of the target vehicle.

[0155] The receiving module 1102 is used to receive at least one perceived vehicle trajectory sent by the roadside computing device, wherein the perceived vehicle trajectory is determined by the roadside computing device based on the collected roadside information;

[0156] The determining module 1101 is further configured to determine, among the at least one perceived vehicle trajectory, a target vehicle trajectory that matches the self-positioning trajectory;

[0157] The processing module 1103 is used to predict the vehicle position of the target vehicle at any first moment within the first time period if the vehicle positioning information of the target vehicle meets the first preset condition, based on the trajectory of the target vehicle.

[0158] In one possible design, the processing module 1103 is further configured to:

[0159] For any first moment within the first time period, if the vehicle positioning information of the target vehicle does not meet the first preset condition, then the vehicle position of the target vehicle at the first moment is determined based on the vehicle positioning information of the target vehicle at the first moment.

[0160] The first time period is the period between the time when the roadside computing device sends the perceived vehicle trajectory and the time when it sends the perceived vehicle trajectory again.

[0161] In one possible design, the processing module 1103 is further configured to:

[0162] After predicting the vehicle position of the target vehicle at the first moment based on the target vehicle trajectory, a sub-trajectory is determined based on the vehicle positions at multiple moments within the first time period;

[0163] The sub-trajectory is spliced ​​onto the target vehicle's self-positioning trajectory to obtain the updated self-positioning trajectory.

[0164] In one possible design, the determining module 1101 is specifically used for:

[0165] Obtain the trajectory identifier of each of the sensing vehicles;

[0166] If a preset trajectory identifier exists among the plurality of trajectory identifiers, the sensing vehicle trajectory corresponding to the preset trajectory identifier is determined as the target vehicle trajectory, wherein the preset trajectory identifier is the trajectory identifier of the sensing vehicle trajectory that matches the self-positioning trajectory of the target vehicle within a historical time period.

[0167] If the preset trajectory identifier is not present among the plurality of trajectory identifiers, the target vehicle trajectory is determined from the at least one perceived vehicle trajectory based on the trajectory points in the perceived vehicle trajectory and the trajectory points in the self-positioning trajectory.

[0168] In one possible design, the determining module 1101 is specifically used for:

[0169] Based on the trajectory point information of each trajectory point in the perceived vehicle trajectory and the trajectory point information of each trajectory point in the self-positioning trajectory, the similarity between the perceived vehicle trajectory and the self-positioning trajectory is determined.

[0170] The perceived vehicle trajectory with the highest similarity and a similarity greater than a first preset threshold is determined as the target vehicle trajectory.

[0171] In one possible design, the determining module 1101 is specifically used for:

[0172] Determine the similarity between the perceived vehicle trajectory corresponding to the preset trajectory identifier and the autonomous vehicle positioning trajectory;

[0173] If the similarity is greater than or equal to the second preset threshold, then the perceived vehicle trajectory corresponding to the preset trajectory identifier is determined as the target vehicle trajectory.

[0174] In one possible design, the processing module 1103 is further configured to:

[0175] Before determining the target vehicle trajectory that matches the vehicle positioning trajectory in the at least one perceived vehicle trajectory, the acquisition time of each trajectory point in the perceived vehicle trajectory is delayed according to the delay duration to obtain the delayed-compensated perceived vehicle trajectory.

[0176] Based on the correspondence between each trajectory point in the perceived vehicle trajectory after delay compensation and each trajectory point in the self-positioning trajectory, at least one pair of trajectory points is determined;

[0177] For any pair of trajectory points, the two trajectory points in the pair are time-aligned to obtain a time-aligned pair of trajectory points.

[0178] Based on multiple time-aligned trajectory point pairs, the time-aligned perceived vehicle trajectory and the time-aligned self-positioning trajectory are determined.

[0179] In one possible design, the trajectory point pair includes a first trajectory point in the delayed-compensated perceived vehicle trajectory and a second trajectory point in the autonomous vehicle positioning trajectory.

[0180] The processing module 1103 is specifically used for:

[0181] The target time is determined based on the first acquisition time corresponding to the first trajectory point and the second acquisition time corresponding to the second trajectory point;

[0182] The third trajectory point with the target time is collected in the perceived vehicle trajectory after delay compensation, and the fourth trajectory point with the target time is determined in the vehicle positioning trajectory.

[0183] The third trajectory point and the fourth trajectory point are used to determine a time-aligned trajectory point pair.

[0184] In one possible design, the determining module 1101 is further configured to:

[0185] After determining the target vehicle trajectory that matches the vehicle positioning trajectory in the at least one perceived vehicle trajectory, the vehicle positions of the remaining vehicles at multiple times within the first time moment are determined based on the remaining perceived vehicle trajectories other than the target vehicle trajectory. The remaining vehicles are vehicles on the road other than the target vehicle.

[0186] In one possible design, the processing module 1103 is further configured to:

[0187] Based on the positions of the remaining vehicles, at various times within the first time period, the position information of the remaining vehicles is rendered in the graphical user interface of the target vehicle; and,

[0188] Based on the vehicle location of the target vehicle, at each moment within the first time period, the location information of the target vehicle is rendered in the graphical user interface of the target vehicle.

[0189] The apparatus provided in this embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effects are similar, and will not be described again here.

[0190] Figure 12 A schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application, such as... Figure 12 As shown, the electronic device 120 of this embodiment includes: a processor 1201 and a memory 1202; wherein

[0191] Memory 1202 is used to store computer-executed instructions;

[0192] The processor 1201 is used to execute computer execution instructions stored in the memory to implement the various steps performed by the vehicle positioning method in the above embodiments. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0193] Alternatively, the memory 1202 can be either standalone or integrated with the processor 1201.

[0194] When the memory 1202 is set up independently, the electronic device also includes a bus 1203 for connecting the memory 1202 and the processor 1201.

[0195] This application also provides a computer-readable storage medium storing computer-executable instructions. When a processor executes the computer-executable instructions, it implements the vehicle positioning method performed by the above-mentioned electronic device.

[0196] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0197] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0198] The integrated modules implemented as software functional modules described above can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application.

[0199] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0200] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0201] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0202] The aforementioned storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0203] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0204] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A vehicle positioning method, characterized in that, Applied to a target vehicle, the method includes: Based on the vehicle positioning information determined by the positioning unit of the target vehicle, the vehicle positioning trajectory of the target vehicle is determined. Receive at least one perceived vehicle trajectory sent by the roadside computing device, wherein the perceived vehicle trajectory is determined by the roadside computing device based on the collected roadside information; Among the at least one perceived vehicle trajectory, a target vehicle trajectory that matches the self-positioning trajectory is determined; For any first moment within the first time period, if the vehicle positioning information of the target vehicle meets the first preset condition, then the vehicle position of the target vehicle at the first moment is predicted based on the trajectory of the target vehicle. Based on the vehicle positions at multiple times within the first time period, a sub-trajectory is determined; The sub-trajectory is spliced ​​onto the target vehicle's self-positioning trajectory to obtain an updated self-positioning trajectory, thereby replacing abnormal trajectory points in the self-positioning trajectory with normal trajectory points.

2. The method according to claim 1, characterized in that, The method further includes: For any first moment within the first time period, if the vehicle positioning information of the target vehicle does not meet the first preset condition, then the vehicle position of the target vehicle at the first moment is determined based on the vehicle positioning information of the target vehicle at the first moment. The first time period is the period between the time when the roadside computing device sends the perceived vehicle trajectory and the time when it sends the perceived vehicle trajectory again.

3. The method according to claim 1 or 2, characterized in that, Determining a target vehicle trajectory that matches the self-positioning trajectory among the at least one perceived vehicle trajectory includes: Obtain the trajectory identifier of each of the sensing vehicles; If a preset trajectory identifier exists among multiple trajectory identifiers, the sensing vehicle trajectory corresponding to the preset trajectory identifier is determined as the target vehicle trajectory. The preset trajectory identifier is the trajectory identifier of the sensing vehicle trajectory that matches the self-positioning trajectory of the target vehicle within a historical time period. If the preset trajectory identifier is not present among the plurality of trajectory identifiers, the target vehicle trajectory is determined from the at least one perceived vehicle trajectory based on the trajectory points in the perceived vehicle trajectory and the trajectory points in the self-positioning trajectory.

4. The method according to claim 3, characterized in that, Determining the target vehicle trajectory from the at least one perceived vehicle trajectory based on trajectory points in the perceived vehicle trajectory and trajectory points in the self-positioning trajectory includes: Based on the trajectory point information of each trajectory point in the perceived vehicle trajectory and the trajectory point information of each trajectory point in the self-positioning trajectory, the similarity between the perceived vehicle trajectory and the self-positioning trajectory is determined. The perceived vehicle trajectory with the highest similarity and a similarity greater than a first preset threshold is determined as the target vehicle trajectory.

5. The method according to claim 4, characterized in that, The step of determining the perceived vehicle trajectory corresponding to the preset trajectory identifier as the target vehicle trajectory includes: Determine the similarity between the perceived vehicle trajectory corresponding to the preset trajectory identifier and the autonomous vehicle positioning trajectory; If the similarity is greater than or equal to the second preset threshold, then the perceived vehicle trajectory corresponding to the preset trajectory identifier is determined as the target vehicle trajectory.

6. The method according to any one of claims 1-2 and 4-5, characterized in that, Before determining the target vehicle trajectory that matches the self-positioning trajectory in the at least one sensed vehicle trajectory, the method further includes: Based on the delay duration, delay compensation is applied to the acquisition time of each trajectory point in the perceived vehicle trajectory to obtain the delayed-compensated perceived vehicle trajectory. Based on the correspondence between each trajectory point in the perceived vehicle trajectory after delay compensation and each trajectory point in the self-positioning trajectory, at least one pair of trajectory points is determined; For any pair of trajectory points, the two trajectory points in the pair are time-aligned to obtain a time-aligned pair of trajectory points. Based on multiple time-aligned trajectory point pairs, the time-aligned perceived vehicle trajectory and the time-aligned self-positioning trajectory are determined.

7. The method according to claim 6, characterized in that, The trajectory point pair includes a first trajectory point in the perceived vehicle trajectory after delay compensation, and a second trajectory point in the autonomous vehicle positioning trajectory; The step of performing time alignment processing on the two trajectory points in the trajectory point pair to obtain a time-aligned trajectory point pair includes: The target time is determined based on the first acquisition time corresponding to the first trajectory point and the second acquisition time corresponding to the second trajectory point; The third trajectory point with the target time is collected in the perceived vehicle trajectory after delay compensation, and the fourth trajectory point with the target time is determined in the vehicle positioning trajectory. The third trajectory point and the fourth trajectory point are used to determine a time-aligned trajectory point pair.

8. The method according to claim 6, characterized in that, After determining the target vehicle trajectory that matches the self-positioning trajectory in the at least one perceived vehicle trajectory, the method further includes: Based on the trajectories of other perceived vehicles besides the target vehicle trajectory, determine the vehicle positions of the remaining vehicles at multiple times within the first time period, wherein the remaining vehicles are vehicles on the road other than the target vehicle.

9. The method according to claim 8, characterized in that, The method further includes: Based on the positions of the remaining vehicles, at various times within the first time period, the position information of the remaining vehicles is rendered in the graphical user interface of the target vehicle; and, Based on the vehicle location of the target vehicle, at each moment within the first time period, the location information of the target vehicle is rendered in the graphical user interface of the target vehicle.

10. A vehicle positioning device, characterized in that, The device includes: The determination module is used to determine the vehicle positioning trajectory of the target vehicle based on the vehicle positioning information determined by the positioning unit of the target vehicle. A receiving module is used to receive at least one perceived vehicle trajectory sent by a roadside computing device, wherein the perceived vehicle trajectory is determined by the roadside computing device based on collected roadside information; The determining module is further configured to determine, among the at least one perceived vehicle trajectory, a target vehicle trajectory that matches the self-positioning trajectory; The processing module is used to predict the vehicle position of the target vehicle at any first moment within the first time period if the vehicle positioning information of the target vehicle meets the first preset condition, based on the trajectory of the target vehicle. The processing module is further configured to: after predicting the vehicle position of the target vehicle at the first moment based on the target vehicle trajectory, determine a sub-trajectory based on the vehicle position at multiple moments within the first time period; and stitch the sub-trajectory onto the vehicle positioning trajectory of the target vehicle to obtain an updated vehicle positioning trajectory, so as to replace abnormal trajectory points in the vehicle positioning trajectory with normal trajectory points.

11. An electronic device, characterized in that, include: Memory, used to store programs; A processor for executing the program stored in the memory, wherein, when the program is executed, the processor is configured to perform the method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, Includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 9.

Images