Vehicle positioning methods, devices, electronic equipment, storage media, and computer program products

Abstract

This application discloses a vehicle positioning method, device, electronic device, storage medium, and computer program product. The method includes: determining whether the vehicle is located within a lane at the start of a first time period, wherein the first time period represents the time during which the vehicle is in an obstructed environment; if the vehicle is located within a lane at the start of the first time period: based on first information, performing forward-order smoothing on the vehicle's RTK positioning in a second time period to obtain a predicted positioning; based on second information, performing reverse-order smoothing on the vehicle's RTK positioning in a third time period to obtain a corrected positioning; and then processing the predicted positioning based on the corrected positioning to obtain the vehicle's positioning result in the first time period. This scheme fully integrates lane marking location information with the vehicle's positioning information in an unobstructed environment. The calculation of the positioning result does not rely on data interaction with other devices. Therefore, even if communication is limited, it does not affect the acquisition of the positioning result, thus improving the accuracy of positioning.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to a vehicle positioning method, device, electronic device, storage medium, and computer program product. Background Technology

[0002] In related technologies, positioning technology based on the Global Navigation Satellite System (GNSS) is used to locate objects. However, it is highly dependent on the interaction with cloud data. Therefore, it cannot work effectively in environments with limited communication and low positioning accuracy. Summary of the Invention

[0003] To address the related technical issues, embodiments of this application provide a vehicle positioning method, device, electronic device, storage medium, and computer program product.

[0004] The technical solution of this application embodiment is implemented as follows:

[0005] This application provides a vehicle positioning method, the method comprising:

[0006] Determine whether the vehicle is within the lane at the start of the first time period, and obtain the determination result; the first time period represents the period during which the vehicle is in an obstructed environment;

[0007] If the determination result indicates that the vehicle was within the lane at the start of the first time period:

[0008] Based on the first information, the real-time kinematic (RTK) positioning of the vehicle in the second time period is smoothed in ascending order to obtain the predicted positioning of the vehicle in the first time period; the first information represents the position information of the lane markings corresponding to the vehicle in the second time period; the second time period represents the time period adjacent to the first time period;

[0009] Based on the second information, the RTK positioning of the vehicle in the third time period is smoothed in reverse order to obtain the corrected positioning of the vehicle in the first time period; the second information represents the position information of the lane markings corresponding to the vehicle in the third time period; the third time period represents the time period adjacent to the first time period.

[0010] Based on the corrected positioning, the predicted positioning is processed to obtain the positioning result of the vehicle in the first time period.

[0011] In the above scheme, the step of performing forward-order smoothing processing on the RTK positioning of the vehicle in the second time period based on the first information to obtain the predicted positioning of the vehicle in the first time period includes:

[0012] Calculate the first distance for each RTK location of the vehicle in the second time period; the first distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0013] Based on the calculated first distance and the set weights corresponding to each first distance, the moving average method is used to calculate the second distance, which represents the shortest distance between the predicted location of the vehicle and the lane markings in the first time period.

[0014] Based on the first information and the second distance, the predicted location of the vehicle in the first time period is calculated.

[0015] In the above scheme, the step of performing reverse smoothing processing on the RTK positioning of the vehicle in the third time period based on the first information to obtain the corrected positioning of the vehicle in the first time period includes:

[0016] Calculate the third distance for each RTK location of the vehicle in the third time period, where the third distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0017] Based on the calculated third distance, the moving average method is used in reverse to calculate the fourth distance, which represents the shortest distance between the corrected positioning of the vehicle and the lane markings in the third time period.

[0018] Based on the second information and the fourth distance, the corrected positioning of the vehicle in the third time period is calculated.

[0019] In the above scheme, the step of processing the predicted positioning based on the corrected positioning to obtain the positioning result of the vehicle in the first time period includes:

[0020] Calculate the average deviation between the corrected positioning and the predicted positioning;

[0021] If the average deviation is less than a set threshold, the predicted positioning is output as the positioning result of the vehicle in the first time period.

[0022] The method in the above scheme further includes:

[0023] The system detects whether a designated marker exists within a first region of the map, and obtains the detection result; the first region represents a designated region containing the RTK positioning of the vehicle; the designated marker represents an occlusion marker marked on the map.

[0024] If the detection result indicates that the set marker exists in the first area of ​​the map, it is determined that the vehicle is in an obstructed environment.

[0025] In the above scheme, determining whether a vehicle is within the lane at the start of the first time period includes:

[0026] Based on the RTK positioning of the vehicle in the second time period, a fifth distance is calculated, which represents the distance between the projection of the front wheel of the vehicle on the lane marking and the projection of the rear wheel on the same side on the lane marking.

[0027] Based on the fifth distance, a first included angle is calculated, which represents the angle between the vehicle's centerline and the lane markings.

[0028] Based on the first included angle, the vehicle body direction is determined;

[0029] If the vehicle's body direction matches the extension direction of the lane markings, the vehicle is determined to be within the lane at the start of the first time period.

[0030] In the above scheme, the method further includes: if the judgment result indicates that the vehicle is not located in the lane at the start of the first time period, outputting the last RTK positioning of the vehicle in the second time period as the positioning result of the vehicle in the first time period.

[0031] This application also provides a vehicle positioning device, including:

[0032] The judgment unit is used to determine whether the vehicle is located in the lane at the start of the first time period and obtain a judgment result; the first time period represents the time period during which the vehicle is in an obstructed environment;

[0033] The first positioning unit is configured to, based on first information, perform forward-order smoothing processing on the RTK positioning of the vehicle in the second time period when the judgment result indicates that the vehicle is located in the lane at the start of the first time period, to obtain the predicted positioning of the vehicle in the first time period; the first information indicates the position information of the lane markings corresponding to the vehicle in the second time period; the second time period indicates the time period adjacent to the first time period.

[0034] The second positioning unit is used to perform reverse smoothing processing on the RTK positioning of the vehicle in the third time period based on the second information to obtain the corrected positioning of the vehicle in the first time period; the second information represents the position information of the lane markings corresponding to the vehicle in the third time period; the third time period represents the time period adjacent to the first time period.

[0035] The third positioning unit is used to process the predicted positioning based on the corrected positioning to obtain the positioning result of the vehicle in the first time period.

[0036] This application also provides an electronic device, including: a first processor and a first memory for storing a computer program capable of running on the processor.

[0037] Wherein, when the first processor is used to run the computer program, it executes the steps of any of the above methods.

[0038] This application also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of any of the above methods.

[0039] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above methods.

[0040] In this embodiment, it is first determined whether the vehicle is located within the lane at the start of the first time period, where the first time period represents the time period during which the vehicle is in an obstructed environment. If the determination result indicates that the vehicle is located within the lane at the start of the first time period, then, based on the first information representing the lane marking position information corresponding to the vehicle in the second time period, the RTK positioning of the vehicle in the second time period is subjected to forward smoothing to obtain predicted positioning. Furthermore, based on the second information representing the lane marking position information corresponding to the vehicle in the third time period, the RTK positioning of the vehicle in the third time period is subjected to reverse smoothing to obtain corrected positioning. Then, based on the corrected positioning, the predicted positioning is processed to obtain the positioning result of the vehicle in the first time period, where the third time period represents the time period following the first time period, and the second time period represents the time period preceding the first time period, both representing the time period during which the vehicle is in an unobstructed environment. In other words, this application smooths the RTK positioning of a vehicle in an unobstructed environment based on lane marking location information to obtain the predicted and corrected positioning of the vehicle in an obstructed environment, thereby obtaining the positioning result in the obstructed environment. Compared with related technologies, it fully integrates lane marking location information and vehicle positioning information in an unobstructed environment to calculate the positioning result of the vehicle in the obstructed environment. The calculation process does not rely on data interaction with other devices. Therefore, even if communication is limited, it will not affect the acquisition of positioning results, thus improving the accuracy of positioning. Attached Figure Description

[0041] Figure 1 A schematic diagram illustrating the implementation process of a vehicle positioning method provided in this application embodiment;

[0042] Figure 2 A flowchart illustrating a vehicle positioning method provided for an application embodiment of this application;

[0043] Figure 3 This is a schematic diagram of the structure of a vehicle positioning device provided in an embodiment of this application;

[0044] Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0045] In related technologies, GNSS-based positioning technology is used to locate objects, but it is highly dependent on the interaction with cloud data. Therefore, it cannot work effectively in environments with limited communication and low positioning accuracy.

[0046] Based on this, this application uses lane marking location information to smooth the RTK positioning of the vehicle in an unobstructed environment, obtaining the predicted positioning and corrected positioning of the vehicle in an obstructed environment, and thus obtaining the positioning result in the obstructed environment. Compared with related technologies, this application fully integrates lane marking location information and vehicle positioning information in an unobstructed environment to calculate the positioning result of the vehicle in the obstructed environment. The calculation process does not rely on data interaction with other devices. Therefore, even if communication is limited, it will not affect the acquisition of positioning results, thus improving the accuracy of positioning.

[0047] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0048] This application provides a vehicle positioning method, the method comprising:

[0049] Step 101: Determine whether the vehicle is within the lane at the start of the first time period and obtain the determination result.

[0050] The first time period represents the period during which the vehicle is in an obstructed environment. This obstructed environment can be an environment containing objects that can block wireless signals, such as overpasses, tunnels, or tall buildings. Due to the obstruction of wireless signals by the obstructed environment, the positioning system in related technologies cannot output accurate positioning if the vehicle is in an obstructed environment. For example, the vehicle's communication signal with satellite may be blocked, resulting in a non-fixed RTK positioning solution that cannot be used as a positioning result. On the other hand, an unobstructed environment is an environment without objects that can block wireless signals. Therefore, if the vehicle is in an unobstructed environment, the positioning system in related technologies can interact with other devices and output accurate positioning. For example, the vehicle can communicate normally with satellites, outputting a fixed RTK positioning solution as the positioning result.

[0051] In practical applications, since the vehicle's driving trajectory is continuous, the lane in which the vehicle is located at the beginning of the first time period can be determined based on the lane in which the vehicle is located in the previous time period. Then, by combining the RTK positioning of the vehicle in the previous time period, it can be determined whether the vehicle is in the lane at the beginning of the first time period.

[0052] Lane-related information, such as the location of lane markings, can be obtained based on lane markings on the map. In practical applications, the map can be stored in a local data storage module and does not need to be obtained through interaction with the cloud.

[0053] Here, if the determination result indicates that the vehicle was in the lane at the start of the first time period, subsequent steps 102, 103, and 104 are executed.

[0054] Step 102: Based on the first information, perform forward smoothing processing on the RTK positioning of the vehicle in the second time period to obtain the predicted positioning of the vehicle in the first time period.

[0055] Wherein, the first information represents the position information of the lane markings corresponding to the vehicle in the second time period; the second time period represents the time period preceding the first time period.

[0056] Here, the lane markings corresponding to the vehicle in the second time period are the lane markings of the lane the vehicle is in during that time period. In practical applications, lane markings are drawn on the lanes. For example, they can be the lane centerline, or dashed lines, solid lines, double solid lines, herringbone lines, deceleration lines, etc., used to divide different lanes. When lane markings are used as auxiliary information in vehicle positioning methods, they can be represented as a set of points. Based on the map's labeling of the lanes, the positional information of each point in the lane markings can be obtained. The positional information of these points together constitutes the positional information of the lane markings.

[0057] Here, if the judgment result indicates that the vehicle is in the lane at the start of the first time period, the position information of the lane markings of the lane where the vehicle is located in the first time period is obtained based on the map, and the RTK positioning of the vehicle in the second time period is obtained; wherein, the second time period represents the time period adjacent to the previous time period of the first time period, that is, the time period when the vehicle is in an unobstructed environment. Therefore, the vehicle is in an unobstructed environment in the second time period, and communication is not restricted. It can obtain a fixed solution of real-time dynamic differential calculation, that is, RTK positioning, through satellite communication.

[0058] Then, based on the position information of the lane markings corresponding to the vehicle in the second time period, the RTK positioning of the vehicle in the second time period is smoothed in ascending order to predict one or more positioning of the vehicle in the first time period, and these positioning are used as predicted positioning.

[0059] Step 103: Based on the second information, perform reverse smoothing on the RTK positioning of the vehicle in the third time period to obtain the corrected positioning of the vehicle in the first time period.

[0060] The second information represents the position information of the lane markings corresponding to the vehicle in the third time period, and the third time period represents the time period adjacent to the first time period.

[0061] Here, the lane markings corresponding to the vehicle in the third time period are the lane markings of the lane the vehicle is in during the third time period. Given that the judgment result indicates the vehicle is within the lane at the start of the first time period, the location information of the lane markings of the lane the vehicle is in during the third time period is obtained based on the map, and the RTK positioning of the vehicle in the third time period is acquired. The third time period represents the period immediately following the first time period, i.e., the period when the vehicle is in an unobstructed environment. Therefore, the vehicle is in an unobstructed environment during the third time period, and communication is unrestricted, enabling the acquisition of a fixed solution through real-time dynamic differential calculation via satellite communication, i.e., RTK positioning.

[0062] Then, based on the position information of the lane markings corresponding to the vehicle in the third time period, the RTK positioning of the vehicle in the third time period is smoothed in reverse order, and one or more positioning of the vehicle in the first time period is calculated in reverse, and these positioning are used as correction positioning.

[0063] Step 104: Based on the corrected positioning, process the predicted positioning to obtain the positioning result of the vehicle in the first time period.

[0064] Here, instead of directly outputting the predicted positioning as the vehicle's positioning result in the first time period, the predicted positioning is processed by corrective positioning before the positioning result is output, which improves the accuracy of the vehicle's positioning result in the first time period.

[0065] In this embodiment, based on lane marking location information, the RTK positioning of the vehicle in an unobstructed environment is smoothed in both forward and reverse order to obtain the predicted positioning and corrected positioning of the vehicle in an obstructed environment, thereby obtaining the positioning result in the obstructed environment. Compared with related technologies, this method fully integrates lane marking location information and vehicle positioning information in an unobstructed environment to calculate the positioning result of the vehicle in the obstructed environment. The calculation process does not rely on data interaction with other devices. Therefore, even if communication is limited, it does not affect the acquisition of positioning results, thus improving the accuracy of positioning.

[0066] In one embodiment, the step of performing forward-order smoothing processing on the RTK positioning of the vehicle in the second time period based on the first information to obtain the predicted positioning of the vehicle in the first time period includes:

[0067] Calculate the first distance for each RTK location of the vehicle in the second time period; the first distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0068] Based on the calculated first distance and the set weights corresponding to each first distance, the moving average method is used to calculate the second distance, which represents the shortest distance between the predicted location of the vehicle and the lane markings in the first time period.

[0069] Based on the first information and the second distance, the predicted location of the vehicle in the first time period is calculated.

[0070] Here, the shortest distance between each RTK location of the vehicle and the lane marking is first calculated in the second time period. For example, the lane marking used for vehicle positioning processing can be the leftmost edge of the lane.

[0071] Then, based on the shortest distance corresponding to the RTK positioning in the second time period and the set weight, the second distance is calculated using the moving average method. The set weight is determined based on historical positioning data and manual adjustment.

[0072] As is understandable, a vehicle's RTK positioning is the vehicle's RTK positioning at a certain moment. Therefore, each RTK positioning has a corresponding moment, and thus, the first distance and the second distance of each RTK positioning also have a corresponding moment.

[0073] Here, the moving average method is used to calculate the second distance of the vehicle's RTK positioning in the first time period. The time corresponding to the second distance calculated earlier is earlier than the time corresponding to the second distance calculated later.

[0074] Specifically, the formula for calculating the moving average method is as follows:

[0075] d n+1 =ω1d1+ω2d2+…w n d n ,

[0076] Where, d i The shortest distance between the vehicle's RTK positioning at time i and the lane markings, where i = 1, 2, ..., n, is earlier than time i+1 and is the closest time to time i+1 among all times earlier than time i+1; w i Characterization and d i The corresponding weights are set.

[0077] When i = n+1, d i =d n+1 d n+1Describes a second distance that needs to be solved in this iteration, when i≤n, d i This represents the shortest distance between the vehicle's RTK positioning and the lane markings at the n nearest times before time n+1. At this point, d i It can be the first distance or the second distance that has already been solved.

[0078] It should be noted that the time mentioned above refers only to the time corresponding to the vehicle's RTK positioning, not any arbitrary time. After obtaining the second distance, the positioning of each vehicle corresponding to the second distance is used as the predicted positioning. Here, the second distance represents the shortest distance between the vehicle's predicted positioning in the first time period and the lane markings. Similar to the first distance, both represent the shortest distance between the vehicle's positioning and the lane markings. The only difference between the first and second distances is:

[0079] The vehicle location corresponding to the first distance is the known RTK location. Based on the known RTK location and the calculation method of the shortest distance, the first distance corresponding to the known RTK location can be obtained. The vehicle location corresponding to the second distance is the predicted location to be solved. After obtaining the second distance, based on the location of the lane marking position point corresponding to each second distance, the shortest distance calculation method is used in reverse to calculate the predicted location of the vehicle to be solved.

[0080] Here, it can be understood that the shortest distance between the vehicle's location and the lane marking is the distance between the vehicle's location and a certain point in the lane marking. That is to say, there is a corresponding lane marking location point for each shortest distance. In an unobstructed environment, the location of the lane marking point corresponding to the shortest distance is known. For example, the location of the lane marking point corresponding to the shortest distance of the vehicle in the second time period can be determined based on the first information. Then, combined with the vehicle's driving speed and driving time, the location of the lane marking point corresponding to the shortest distance between the vehicle and the lane marking in the obstructed environment can be determined. Therefore, the location of the lane marking point corresponding to the second distance can be determined.

[0081] To further illustrate how predictive positioning is calculated, the following explanation includes examples.

[0082] If the RTK location of a vehicle in the second time period is known to be location 1, location 2, and location 3, corresponding to times 1, 2, and 3 respectively; and the predicted location of the vehicle in the first time period is to be calculated as location 4 and location 5, corresponding to times 4 and 5 respectively, then the steps for calculating location 4 and location 5 are as follows:

[0083] 1. Calculate the shortest distances between positioning 1, positioning 2 and positioning 3 and the leftmost edge of the lane, respectively, to obtain the first distances D1, D2 and D3 of these three positioning locations.

[0084] 2. Solve for the second distances D4 and D5 at positions 4 and 5 respectively;

[0085] Specifically, if we set n=3 in the formula for calculating the moving average, then...

[0086] (1) Since time 1, time 2 and time 3 are the three nearest times before time 4, D4 is taken as the object to be solved and substituted into the left side of the calculation formula. The known first distances D1, D2 and D3 are substituted into the right side of the equation in the moving average method calculation formula. Thus, D4 = w1D1 + ω2D2 + ω3D3.

[0087] (2) Since time 4, time 3 and time 4 are the three nearest times before time 5, D5 is taken as the object to be solved and substituted into the left side of the calculation formula. The known first distance D2 and D3, and the solved second distance D4 are substituted into the right side of the moving average method calculation formula. Thus, D5 = w1D2 + ω2D3 + ω3D4.

[0088] 3. Based on the first information and the second distance D4, the shortest distance calculation method is used in reverse to calculate the predicted location of the vehicle at time 4, i.e., location 4; based on the second distance D5, the shortest distance calculation method is used in reverse to calculate the predicted location of the vehicle at time 5, i.e., location 5.

[0089] In this embodiment, the moving average method is used to perform forward smoothing on the RTK positioning of the vehicle in the second time period. This fully integrates the lane marking position information and the vehicle's driving trajectory in an unobstructed environment, and calculates the predicted positioning of the vehicle in the first time period. This provides intermediate data for the accurate calculation of the positioning result of the vehicle in an obstructed environment. Moreover, it does not require training an artificial intelligence model. Compared with the positioning methods based on artificial intelligence models in related technologies, it has lower computational overhead, more flexible adjustment, and ensures the stability of the output positioning result.

[0090] In one embodiment, the step of performing reverse smoothing processing on the RTK positioning of the vehicle in the third time period based on the second information to obtain the corrected positioning of the vehicle in the first time period includes:

[0091] Calculate the third distance for each RTK location of the vehicle in the third time period, where the third distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0092] Based on the calculated third distance, the moving average method is used in reverse to calculate the fourth distance, which represents the shortest distance between the corrected positioning of the vehicle and the lane markings in the third time period.

[0093] Based on the second information and the fourth distance, the corrected positioning of the vehicle in the third time period is calculated.

[0094] Here, we first calculate the shortest distance between each RTK location of the vehicle and the lane markings during the third time period.

[0095] Then, based on the shortest distance corresponding to the RTK positioning in the third time period and the set weight, the calculation formula of the one or more moving average methods is used in reverse to obtain the fourth distance of the vehicle's RTK positioning in the first time period. The time corresponding to the fourth distance calculated earlier is later than the time corresponding to the fourth distance calculated later.

[0096] Specifically, as mentioned above, the formula for calculating the moving average method is:

[0097] d n+1 =ω1d1+ω2d2+…w n d n ,

[0098] Where, d i The shortest distance between the vehicle's RTK positioning at time i and the lane markings, where i = 1, 2, ..., n, is earlier than time i+1 and is the closest time to time i+1 among all times earlier than time i+1; w i Characterization and d i The corresponding weights are determined through historical data and manual adjustments.

[0099] So, if we use the moving average method in reverse, when i = 1, d i =d1, where d1 represents a fourth distance that needs to be solved in this iteration.

[0100] To further illustrate how predictive positioning is calculated, the following explanation includes examples.

[0101] If the RTK positioning of the vehicle in the third time period is known to be Position 3, Position 4, and Position 5, corresponding to times 3, 4, and 5 respectively; and the corrected positioning of the vehicle in the first time period is to be calculated as Position 1 and Position 2, corresponding to times 1 and 2 respectively, then the steps for calculating Position 1 and Position 2 are as follows:

[0102] 1. Calculate the shortest distances between positioning 3, positioning 4 and positioning 5 and the leftmost edge of the lane, respectively, to obtain the first distances D3, D4 and D5 of these three positioning points.

[0103] 2. Solve for the second distances D2 and D1 between position 2 and position 1 respectively;

[0104] Specifically, if we set n=3 in the formula for calculating the moving average, then...

[0105] (1) Since time 2, time 3 and time 4 are the three nearest times before time 5, the known first distance D5 is substituted into the left side of the calculation formula, and the second distance D2 to be solved, as well as the known first distances D3 and D4, are substituted into the right side of the moving average method calculation formula. Thus, the equation D5=w1D2+ω2D3+ω3D4 is obtained, where D2 is the object to be solved by the equation. Solving the equation yields the second distance D2.

[0106] (2) Since time 1, time 2 and time 3 are the three nearest times before time 4, the known first distance D4 is substituted into the left side of the calculation formula, and the second distance D1 to be solved, the solved second distance D2 and the known first distance D3 are substituted into the right side of the moving average method calculation formula. Thus, the equation D4 = w1D1 + ω2D2 + ω3D3 is obtained, where D1 is the object to be solved in this equation. Solving this equation yields the second distance D1.

[0107] 3. Based on the second information and the second distance D1, the shortest distance calculation method is used in reverse to calculate the predicted location of the vehicle at time 1, i.e., location 1; based on the second distance D2, the shortest distance calculation method is used in reverse to calculate the predicted location of the vehicle at time 2, i.e., location 2.

[0108] In this embodiment, the moving average method is used in reverse to smooth the RTK positioning of the vehicle in the third time period. This fully integrates the lane marking position information and the vehicle's driving trajectory in the unobstructed environment, and calculates the corrected positioning of the vehicle in the first time period. This provides intermediate data for the accurate calculation of the positioning result of the vehicle in the obstructed environment. Moreover, it does not require training an artificial intelligence model. Compared with the positioning methods based on artificial intelligence models in related technologies, it has lower computational overhead, more flexible adjustment, and ensures the stability of the output positioning result.

[0109] After obtaining the predicted distance and corrected location of the vehicle in the first time period, further processing of the predicted location based on the corrected location is needed to obtain the vehicle's location result for the first time period. Specifically,

[0110] In one embodiment, processing the predicted positioning based on the corrected positioning to obtain the positioning result of the vehicle in the first time period includes:

[0111] Calculate the average deviation between the corrected positioning and the predicted positioning;

[0112] If the average deviation is less than a set threshold, the predicted positioning will be output as the vehicle's positioning result in the first time period.

[0113] The threshold is set manually. If the average deviation is less than the threshold, the predicted positioning is considered relatively accurate and a reliable positioning result. Therefore, the predicted positioning is output as the vehicle's positioning result for the first time period.

[0114] Specifically, the average deviation between the corrected positioning and the predicted positioning can be calculated by calculating the deviation between the second distance of each predicted positioning and the fourth distance of the corrected positioning of the vehicle at the same time, to obtain one or more deviation values. For example, if the second distance of the predicted positioning of the vehicle at time 1 in the first time period is D1, and the fourth distance of the corrected positioning of the vehicle at time 1 is D2, then the deviation between the predicted positioning and the corrected positioning of the vehicle at the first time is |(D1-D2) / D1|.

[0115] Then, the average of one or more calculated deviation values ​​is used as the average deviation between the corrected positioning and the predicted positioning. If the average deviation is less than a set threshold, the predicted positioning is output as the vehicle's positioning result for the first time period. For example, the set threshold is 10%.

[0116] Instead of directly outputting the predicted location, the output location result is determined based on the degree of deviation between the corrected location and the predicted location. This is equivalent to using the corrected location to calibrate the calculated predicted location, thereby improving the accuracy of the output location result.

[0117] If the average deviation is greater than a set threshold, in one embodiment...

[0118] The system continues to determine whether the duration of the first time period exceeds the set duration. If the determination result indicates that the duration of the first time period does not exceed the set duration, it is considered that the vehicle was in the occluded environment for a relatively short time, and the corrected positioning is output as the vehicle's positioning result for the first time period. If the determination result indicates that the duration of the first time period exceeds the set duration, it is considered that the vehicle was in the occluded environment for too long, and both the predicted positioning and the corrected positioning deviate significantly from the vehicle's actual positioning in the first time period, thus having no reference value. Therefore, the vehicle's positioning result for the first time period is output as empty.

[0119] In this embodiment, when the vehicle is in an obstructed environment for too long, such as when the vehicle breaks down in an obstructed environment, the output positioning result of the vehicle in the obstructed environment is empty, so as to avoid making incorrect positioning instructions and misleading the vehicle.

[0120] In one embodiment, the method further includes:

[0121] The system detects whether a designated marker exists within a first region of the map, and obtains the detection result; the first region represents a designated region containing the RTK positioning of the vehicle; the designated marker represents an occlusion marker marked on the map.

[0122] If the detection result indicates that the set marker exists in the first area of ​​the map, it is determined that the vehicle is in an obstructed environment.

[0123] In practical applications, a map can be a map that marks roads and objects around the roads, such as a high-precision map; obstructing environmental markers can be objects that can block wireless signals, such as overpasses, tunnels, or tall buildings.

[0124] Here, the first area is set manually according to positioning requirements, representing a set area containing the vehicle's RTK positioning. For example, the first area can be an area radiating outward from the vehicle's RTK positioning at a set distance, where the set distance can be 1 kilometer, which can be changed manually according to positioning requirements.

[0125] If a designated marker exists in the first area of ​​the detection result representation map, it is assumed that there are occlusion markers near the vehicle, thus determining that the vehicle is in an occlusion environment. The vehicle positioning calculation method in this embodiment needs to be executed to obtain the calculation result. If no designated marker exists in the first area of ​​the detection result representation map, it is determined that the vehicle is not in an occlusion environment, and the RTK positioning is directly output as the positioning result.

[0126] During vehicle localization, it is possible to determine multiple times whether the vehicle is in an occluded environment. For example, the detection method described in this embodiment can be executed every set time interval, and the vehicle's occlusion status can be determined based on the detection results. By periodically determining whether the vehicle is in an occluded environment, accurate identification of the first, second, and third time periods can be achieved, which helps improve the accuracy of localization. For example, if the detection result at time t1 indicates that the vehicle is in an occluded environment, and the detection result before time t1 indicates that the vehicle is not in an occluded environment, then time t1 is determined as the starting point of the first time period. If the detection result at time t2 indicates that the vehicle is not in an occluded environment, and the detection result before time t2 indicates that the vehicle is in an occluded environment, and time t2 is later than time t1, and the detection results from time t1 to time t2 all indicate that the vehicle is in an occluded environment, then time t2 is determined as the ending point of the first time period, and the time period between time t1 and time t2 is determined as the first time period.

[0127] In practical applications, the presence of a vehicle in an obstructed environment can also be determined by changes in the number of detected satellites. For example, if the number of satellites decreases to less than four, the vehicle is determined to be in an obstructed environment. Alternatively, the presence of a fixed solution in the vehicle's RTK positioning can also be used to determine if the vehicle is in an obstructed environment. If no fixed solution exists, the vehicle is determined to be in an obstructed environment. It should be noted that the determination of whether a vehicle is in an obstructed environment can be based on one of the above methods, or a combination of multiple methods.

[0128] In one embodiment, determining whether a vehicle is within the lane at the start of the first time period includes:

[0129] Based on the RTK positioning of the vehicle in the second time period, a fifth distance is calculated, which represents the distance between the projection of the front wheel of the vehicle on the lane marking and the projection of the rear wheel on the same side on the lane marking.

[0130] Based on the fifth distance, a first included angle is calculated, which represents the angle between the vehicle's centerline and the lane markings.

[0131] Based on the first included angle, the vehicle body direction is determined;

[0132] If the vehicle's body direction matches the extension direction of the lane markings, the vehicle is determined to be within the lane at the start of the first time period.

[0133] Here, the fifth distance represents the distance between the projection of the front wheel of the vehicle onto the lane marking and the projection of the rear wheel on the same side onto the lane marking, which is the length of the projection line segment of the line connecting the front wheel of the vehicle and the rear wheel on the same side onto the lane marking.

[0134] It is understandable that the line connecting the front wheel and the rear wheel on the same side, the projection of this line onto the lane marking, and the angle between this line and the lane marking are mathematically related by trigonometric functions. Therefore, the angle between this line and the lane marking can be calculated based on the length of the projection of this line onto the lane marking, i.e., based on the fifth distance. Furthermore, since the line connecting the front wheel and the rear wheel on the same side is parallel to the vehicle's centerline, the angle between this line and the lane marking is the same as the angle between the vehicle's centerline and the lane marking; that is, the angle between this line and the lane marking is the same as the first angle. Therefore, the first angle can be calculated based on the fifth distance. For ease of explanation, the sixth distance will be used below to represent the distance between the line connecting the front wheel and the rear wheel on the same side.

[0135] Specifically, the first included angle is calculated as follows: Based on an RTK positioning of the vehicle, the fifth and sixth distances corresponding to that RTK positioning are obtained. A trigonometric function is then performed based on the ratio between the fifth and sixth distances to obtain the first included angle. This calculation method is used to process each RTK positioning of the vehicle in the second time period to obtain one or more first included angles corresponding to each RTK positioning.

[0136] After obtaining one or more first included angles, the vehicle body direction at the starting position of the first time period is calculated based on these one or more first included angles. For example, the vehicle body direction can be the first included angle at the starting position of the first time period.

[0137] If the vehicle's direction matches the direction of the lane markings, the vehicle is considered to be within the lane, and the vehicle's position in the first time period can be calculated further using the positioning method provided in this application embodiment.

[0138] If the vehicle's direction does not match the lane marking extension direction, the vehicle is considered to have deviated from the route and is not within the lane. This does not fall under the supported scenario of accurate positioning output by the vehicle positioning method in this application embodiment. Therefore, in one embodiment, when the judgment result indicates that the vehicle is not within the lane at the start of the first time period, the last RTK positioning of the vehicle in the second time period is output as the positioning result of the vehicle in the first time period. Specifically, the last RTK positioning of the vehicle in the second time period is output as the positioning result of the first positioning point of the vehicle in the first time period. The positioning results of other positioning points in the first time period are considered to be undeterminable. For example, the positioning results of other positioning points in the first time period are output as empty to avoid making incorrect positioning instructions to mislead the vehicle and to avoid using invalid smoothing calculation methods, thereby reducing computational overhead.

[0139] Here, when determining whether the vehicle direction matches the lane marking extension direction, it can be determined whether the deviation between the vehicle direction and the lane marking extension direction is less than a set direction threshold. For example, the deviation between the vehicle centerline and the lane marking extension direction can be that the first angle at the starting position of the vehicle in the first time period is less than the set direction threshold.

[0140] In this embodiment, the vehicle is determined to be within the lane at the start of the first time period based on whether the vehicle's body direction matches the extension direction of the lane markings. This determines whether the vehicle has deviated from the route and selects the calculation method for the vehicle's positioning result in the first time period. This reduces computational overhead, fully considers the vehicle's state in an obstructed environment, and improves positioning accuracy.

[0141] Based on the above embodiments, Figure 2A flowchart illustrating a vehicle positioning method provided in an application embodiment of this application is given, as follows: Figure 2 As shown, the main steps include:

[0142] Step 201: Determine whether the vehicle is in an obstructed environment.

[0143] Step 202: Obtain one or more RTK positioning and lane marking location information of the vehicle in the second time period.

[0144] Here, if the judgment result indicates that the vehicle is in an obstructed environment at time t1 and was in an unobstructed environment before time t1, this step is executed; the second time period is 5 minutes before time t1.

[0145] Step 203: Calculate the vehicle's orientation at the initial position at the first moment.

[0146] Step 204: Determine whether the vehicle's orientation at the initial position at the first moment matches the direction of the lane markings.

[0147] If the judgment result indicates that the vehicle's body direction at the initial position at the first moment matches the extension direction of the lane marking, proceed to step 205.

[0148] If the judgment result indicates that the vehicle's body direction at the starting position at the first moment does not match the extension direction of the lane marking, proceed to step 212.

[0149] Step 205: Calculate one or more predicted locations for the vehicle in the first time period.

[0150] Specifically, based on the vehicle's lane marking position information, the RTK positioning in the second time period is smoothed in ascending order to obtain one or more predicted positioning of the vehicle in the first time period.

[0151] Step 206: Obtain one or more RTK positioning and lane marking location information of the vehicle in the third time period.

[0152] Here, the judgment result in step 201 indicates that the vehicle is in an unobstructed environment at time t2. If the vehicle is in an obstructed environment between times t1 and t2, this step is executed, and the third time period is the last 5 minutes of time t2.

[0153] Step 207: Calculate one or more corrected positions of the vehicle in the first time period.

[0154] Specifically, based on the vehicle's lane marking position information, the RTK positioning in the third time period is smoothed in reverse order to obtain one or more corrected positioning of the vehicle in the first time period.

[0155] Step 208: Determine whether the average deviation between the predicted positioning and the corrected positioning is less than 10%.

[0156] If the judgment result indicates that the average deviation between the predicted positioning and the corrected positioning is less than 10%, proceed to 213;

[0157] If the judgment result indicates that the average deviation between the predicted positioning and the corrected positioning is greater than 10%, proceed to step 209.

[0158] Step 209: Determine whether the duration of the first time period exceeds the set duration.

[0159] If the judgment result indicates that the duration of the first time period exceeds the set duration, proceed to step 210.

[0160] If the judgment result indicates that the duration of the first time period does not exceed the set duration, proceed to step 211;

[0161] Step 210: Output null values.

[0162] After completing this step, the method flow ends.

[0163] Step 211: Output one or more corrected positions of the vehicle in the first time period.

[0164] After completing this step, the method flow ends.

[0165] Step 212: Output the vehicle's last RTK location in the second time period.

[0166] After completing this step, the method flow ends.

[0167] Step 213; Output one or more predicted locations of the vehicle in the first time period.

[0168] In this embodiment, after determining that the vehicle is in an obstructed environment, the RTK positioning of the vehicle in an unobstructed environment is smoothed based on the position information of the lane markings to obtain the predicted positioning and corrected positioning of the vehicle in the obstructed environment, thereby obtaining the positioning result in the obstructed environment. Compared with related technologies, this fully integrates the lane marking position information and the vehicle's positioning information in an unobstructed environment to calculate the positioning result of the vehicle in the obstructed environment. The calculation process does not rely on data interaction with other devices. Therefore, even if communication is limited, it does not affect the acquisition of positioning results, thus improving the accuracy of positioning.

[0169] Based on the embodiments of the vehicle positioning method described above, this application also provides a vehicle positioning device, such as... Figure 3 As shown, the vehicle positioning device includes:

[0170] The judgment unit 31 is used to determine whether the vehicle is located in the lane at the start of the first time period and obtain a judgment result; the first time period represents the time period during which the vehicle is in an obstructed environment;

[0171] The first positioning unit 32 is configured to, based on first information, perform forward-order smoothing processing on the RTK positioning of the vehicle in the second time period when the judgment result indicates that the vehicle is located in the lane at the start of the first time period, to obtain the predicted positioning of the vehicle in the first time period; the first information indicates the position information of the lane markings corresponding to the vehicle in the second time period; the second time period indicates the time period adjacent to the first time period.

[0172] The second positioning unit 33 is used to perform reverse smoothing processing on the RTK positioning of the vehicle in the third time period based on the second information to obtain the corrected positioning of the vehicle in the first time period; the second information represents the position information of the lane markings corresponding to the vehicle in the third time period; the third time period represents the time period adjacent to the first time period.

[0173] The third positioning unit 34 is used to process the predicted positioning based on the corrected positioning to obtain the positioning result of the vehicle in the first time period.

[0174] In one embodiment, the first positioning unit 32 is further configured to:

[0175] Calculate the first distance for each RTK location of the vehicle in the second time period; the first distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0176] Based on the calculated first distance and the set weights corresponding to each first distance, the moving average method is used to calculate the second distance, which represents the shortest distance between the predicted location of the vehicle and the lane markings in the first time period.

[0177] Based on the first information and the second distance, the predicted location of the vehicle in the first time period is calculated.

[0178] In one embodiment, the second positioning unit 33 is further configured to:

[0179] Calculate the third distance for each RTK location of the vehicle in the third time period, where the third distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0180] Based on the calculated third distance, the moving average method is used in reverse to calculate the fourth distance, which represents the shortest distance between the corrected positioning of the vehicle and the lane markings in the third time period.

[0181] Based on the second information and the fourth distance, the corrected positioning of the vehicle in the third time period is calculated.

[0182] In one embodiment, the third positioning unit 34 is further configured to:

[0183] Calculate the average deviation between the corrected positioning and the predicted positioning;

[0184] If the average deviation is less than a set threshold, the predicted positioning is output as the positioning result of the vehicle in the first time period.

[0185] In one embodiment, the vehicle positioning device further includes a detection unit, the detection unit being used for:

[0186] The system detects whether a designated marker exists within a first region of the map, and obtains the detection result; the first region represents a designated region containing the RTK positioning of the vehicle; the designated marker represents an occlusion marker marked on the map.

[0187] If the detection result indicates that the set marker exists in the first area of ​​the map, it is determined that the vehicle is in an obstructed environment.

[0188] In one embodiment, the determining unit 31 is further configured to:

[0189] Based on the RTK positioning of the vehicle in the second time period, a fifth distance is calculated, which represents the distance between the projection of the front wheel of the vehicle on the lane marking and the projection of the rear wheel on the same side on the lane marking.

[0190] Based on the fifth distance, a first included angle is calculated, which represents the angle between the vehicle's centerline and the lane markings.

[0191] Based on the first included angle, the vehicle body direction is determined;

[0192] If the vehicle's body direction matches the extension direction of the lane markings, it is determined that the vehicle is within the lane at the start of the first time period.

[0193] In one embodiment, the third positioning unit 34 is further configured to output the last RTK positioning of the vehicle in the second time period as the positioning result of the vehicle in the first time period if the judgment result indicates that the vehicle is not located in the lane at the start time of the first time period.

[0194] In practical applications, the judgment unit 31, the first positioning unit 32, the second positioning unit 33, the third positioning unit 34, and the detection unit can all be implemented by the processor in the vehicle positioning device.

[0195] It should be noted that the vehicle positioning device provided in the above embodiments is only illustrated by the division of the above-described program modules when performing vehicle positioning. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the vehicle positioning device and the vehicle positioning method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0196] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, this application also provides an electronic device, such as... Figure 4 As shown, the electronic device includes:

[0197] The first communication interface 1 is capable of exchanging information with other devices;

[0198] The first processor 2 is connected to the first communication interface 1 to enable information interaction with other devices and to execute the methods provided by one or more of the above-mentioned technical solutions when running a computer program. The computer program is stored in the first memory 3.

[0199] Specifically, the first processor 2 is used to determine whether the vehicle is within the lane at the start of the first time period, and obtain a determination result; the first time period represents the period during which the vehicle is in an obstructed environment; and,

[0200] If the determination result indicates that the vehicle was within the lane at the start of the first time period:

[0201] Based on the first information, the real-time dynamic differential RTK positioning of the vehicle in the second time period is smoothed in ascending order to obtain the predicted positioning of the vehicle in the first time period; the first information represents the position information of the lane markings corresponding to the vehicle in the second time period; the second time period represents the time period adjacent to the first time period.

[0202] Based on the second information, the RTK positioning of the vehicle in the third time period is smoothed in reverse order to obtain the corrected positioning of the vehicle in the first time period; the second information represents the position information of the lane markings corresponding to the vehicle in the third time period; the third time period represents the time period adjacent to the first time period; and,

[0203] Based on the corrected positioning, the predicted positioning is processed to obtain the positioning result of the vehicle in the first time period.

[0204] In one embodiment, the first processor 2 performs forward-order smoothing processing on the RTK positioning of the vehicle in the second time period based on the first information to obtain the predicted positioning of the vehicle in the first time period, including:

[0205] Calculate the first distance for each RTK location of the vehicle in the second time period; the first distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0206] Based on the calculated first distance and the set weights corresponding to each first distance, the moving average method is used to calculate the second distance, which represents the shortest distance between the predicted location of the vehicle and the lane markings in the first time period.

[0207] Based on the first information and the second distance, the predicted location of the vehicle in the first time period is calculated.

[0208] In one embodiment, the first processor 2 performs reverse smoothing processing on the RTK positioning of the vehicle in the third time period based on the second information to obtain the corrected positioning of the vehicle in the first time period, including:

[0209] Calculate the third distance for each RTK location of the vehicle in the third time period, where the third distance represents the shortest distance between the corresponding RTK location and the lane markings;

[0210] Based on the calculated third distance, the moving average method is used in reverse to calculate the fourth distance, which represents the shortest distance between the corrected positioning of the vehicle and the lane markings in the third time period.

[0211] Based on the second information and the fourth distance, the corrected positioning of the vehicle in the third time period is calculated.

[0212] In one embodiment, the first processor 2 processes the predicted positioning based on the corrected positioning to obtain the positioning result of the vehicle in the first time period, including:

[0213] Calculate the average deviation between the corrected positioning and the predicted positioning;

[0214] If the average deviation is less than a set threshold, the predicted positioning is output as the positioning result of the vehicle in the first time period.

[0215] In one embodiment, the first processor 2 is further configured to detect whether a designated marker exists in a first region of the map, and obtain a detection result; the first region represents a designated region containing the RTK positioning of the vehicle; the designated marker represents an occlusion marker marked in the map;

[0216] If the detection result indicates that the set marker exists in the first area of ​​the map, it is determined that the vehicle is in an obstructed environment.

[0217] In one embodiment, the first processor 2 determines whether the vehicle is within the lane at the start of the first time period, including:

[0218] Based on the RTK positioning of the vehicle in the second time period, a fifth distance is calculated, which represents the distance between the projection of the front wheel of the vehicle on the lane marking and the projection of the rear wheel on the same side on the lane marking.

[0219] Based on the fifth distance, a first included angle is calculated, which represents the angle between the vehicle's centerline and the lane markings.

[0220] Based on the first included angle, the vehicle body direction is determined;

[0221] If the vehicle's body direction matches the extension direction of the lane markings, the vehicle is determined to be within the lane at the start of the first time period.

[0222] In one embodiment, the first processor 2 is further configured to output the last RTK positioning of the vehicle in the second time period as the positioning result of the vehicle in the first time period if the determination result indicates that the vehicle is not located in the lane at the start time of the first time period.

[0223] It should be noted that the specific processing procedure of the first communication interface 1 can be understood by referring to the above method.

[0224] Of course, in practical applications, the various components in an electronic device are coupled together through bus system 4. It can be understood that bus system 4 is used to achieve communication and connection between these components. In addition to the data bus, bus system 4 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 4 The general will label all buses as Bus System 4.

[0225] The first memory 3 in this embodiment is used to store various types of data to support operation in the electronic device. Examples of such data include any computer program used to operate on the electronic device.

[0226] The methods disclosed in the embodiments of this application can be applied to the first processor 2, or implemented by the first processor 2. The first processor 2 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware or by instructions in the form of software in the first processor 2. The first processor 2 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 2 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the first memory 3. The first processor 2 reads the information in the first memory 3 and completes the steps of the aforementioned method in combination with its hardware.

[0227] In an exemplary embodiment, the electronic device may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.

[0228] It is understood that the first memory 3 in the embodiments of this application can be volatile memory or non-volatile memory, or both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); the magnetic surface memory can be disk storage or magnetic tape storage. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0229] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as an electronic device including a computer program. The computer program can be executed by a first processor 2 of the electronic device to complete the steps described in the aforementioned method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0230] In an exemplary embodiment, this application also provides a computer program product, including a computer program that can be executed by a first processor 2 of an electronic device to perform the steps described in any of the foregoing methods.

[0231] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0232] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the term "one or more" in this document refers to any combination of at least two of any one or more elements from a set of A, B, and C. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set of A, B, and C.

[0233] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0234] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. A vehicle positioning method, characterized in that, include: Determine whether the vehicle is within the lane at the start of the first time period, and obtain the determination result; The first time period represents the period during which the vehicle is in an obstructed environment; If the determination result indicates that the vehicle was within the lane at the start of the first time period: Based on the first information, the real-time dynamic differential RTK positioning of the vehicle in the second time period is smoothed in ascending order to obtain the predicted positioning of the vehicle in the first time period; the first information represents the position information of the lane markings corresponding to the vehicle in the second time period; the second time period represents the time period adjacent to the first time period. Based on the second information, the RTK positioning of the vehicle in the third time period is smoothed in reverse order to obtain the corrected positioning of the vehicle in the first time period. The second information represents the position information of the lane markings corresponding to the vehicle in the third time period; the third time period represents the time period adjacent to the first time period. Based on the corrected positioning, the predicted positioning is processed to obtain the positioning result of the vehicle in the first time period.

2. The method according to claim 1, characterized in that, The step of performing forward-order smoothing processing on the RTK positioning of the vehicle in the second time period based on the first information to obtain the predicted positioning of the vehicle in the first time period includes: Calculate the first distance for each RTK location of the vehicle in the second time period; the first distance represents the shortest distance between the corresponding RTK location and the lane markings; Based on the calculated first distance and the set weights corresponding to each first distance, the moving average method is used to calculate the second distance, which represents the shortest distance between the predicted location of the vehicle and the lane markings in the first time period. Based on the first information and the second distance, the predicted location of the vehicle in the first time period is calculated.

3. The method according to claim 1, characterized in that, The step of performing reverse smoothing processing on the RTK positioning of the vehicle in the third time period based on the second information to obtain the corrected positioning of the vehicle in the first time period includes: Calculate the third distance for each RTK location of the vehicle in the third time period, where the third distance represents the shortest distance between the corresponding RTK location and the lane markings; Based on the calculated third distance, the moving average method is used in reverse to calculate the fourth distance, which represents the shortest distance between the corrected positioning of the vehicle and the lane markings in the third time period. Based on the second information and the fourth distance, the corrected positioning of the vehicle in the third time period is calculated.

4. The method according to claim 1, characterized in that, The step of processing the predicted positioning based on the corrected positioning to obtain the positioning result of the vehicle in the first time period includes: Calculate the average deviation between the corrected positioning and the predicted positioning; If the average deviation is less than a set threshold, the predicted positioning is output as the positioning result of the vehicle in the first time period.

5. The method according to claim 1, characterized in that, The method further includes: The system detects whether a designated marker exists within a first region of the map, and obtains the detection result; the first region represents a designated region containing the RTK positioning of the vehicle; the designated marker represents an occlusion marker marked on the map. If the detection result indicates that the set marker exists in the first area of ​​the map, it is determined that the vehicle is in an obstructed environment.

6. The method according to claim 1, characterized in that, The determination of whether a vehicle is within the lane at the start of the first time period includes: Based on the RTK positioning of the vehicle in the second time period, a fifth distance is calculated, which represents the distance between the projection of the front wheel of the vehicle on the lane marking and the projection of the rear wheel on the same side on the lane marking. Based on the fifth distance, a first included angle is calculated, which represents the angle between the vehicle's centerline and the lane markings. Based on the first included angle, the vehicle body direction is determined; If the vehicle's body direction matches the extension direction of the lane markings, it is determined that the vehicle was located within the lane at the start of the first time period.

7. The method according to claim 1, characterized in that, The method further includes: if the judgment result indicates that the vehicle is not located in the lane at the start of the first time period, outputting the last RTK positioning of the vehicle in the second time period as the positioning result of the vehicle in the first time period.

8. A vehicle positioning device, characterized in that, include: The judgment unit is used to determine whether the vehicle is within the lane at the start of the first time period and obtain the judgment result. The first time period represents the period during which the vehicle is in an obstructed environment; The first positioning unit is configured to, based on first information, perform forward-order smoothing processing on the RTK positioning of the vehicle in the second time period when the judgment result indicates that the vehicle is located in the lane at the start of the first time period, to obtain the predicted positioning of the vehicle in the first time period; the first information indicates the position information of the lane markings corresponding to the vehicle in the second time period; the second time period indicates the time period adjacent to the first time period. The second positioning unit is used to perform reverse smoothing processing on the RTK positioning of the vehicle in the third time period based on the second information to obtain the corrected positioning of the vehicle in the first time period. The second information represents the position information of the lane markings corresponding to the vehicle in the third time period; the third time period represents the time period adjacent to the first time period. The third positioning unit is used to process the predicted positioning based on the corrected positioning to obtain the positioning result of the vehicle in the first time period.

9. An electronic device, characterized in that, include: A first processor and a first memory for storing computer programs capable of running on the processor. Wherein, when the first processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images