A data processing method and device

Abstract

The embodiment of the present invention provides a method and device for data processing, the method comprising: obtaining preset first map data; obtaining second map data collected in real time; obtaining a first positioning matrix and first residual information for the first positioning matrix; generating a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data; updating the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix; and using the updated first positioning matrix to perform positioning correction. Through the embodiment of the present invention, the updated first matrix is ​​used for positioning correction, and the updated first positioning matrix fully considers the first residual information and the second residual information, which can reduce the influence of errors and improve the robustness of positioning information.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a data processing method and device. Background Art

[0002] With the development of smart cars, more and more vehicles are equipped with positioning systems. The vehicle's positioning system can provide drivers with route guidance, allowing drivers to quickly determine their current location and provide convenient services for public travel.

[0003] When a smart car enters a parking lot, it can build a trajectory map of the current driving trajectory online, match the trajectory map with the previously built scene semantic map online, and obtain the current vehicle's location on the scene semantic map. This positioning information can serve autonomous parking and navigation in the parking lot.

[0004] However, in the current matching positioning algorithm, since it completely relies on the transformation matrix in the prior positioning information for matching positioning, when the error of the prior positioning information is large, drift error is likely to occur, which will cause the error of the obtained vehicle positioning information to be large and the robustness to be low. Summary of the invention

[0005] In view of the above problems, a data processing method and device are proposed to overcome the above problems or at least partially solve the above problems, including:

[0006] A method for data processing, the method comprising:

[0007] Acquire preset first map data;

[0008] Acquire second map data collected in real time;

[0009] Acquire a first positioning matrix and first residual information for the first positioning matrix;

[0010] generating a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data;

[0011] updating the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix;

[0012] The updated first positioning matrix is ​​used to perform positioning correction.

[0013] Optionally, it also includes:

[0014] The first residual information is updated according to the second residual information.

[0015] Optionally, generating a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data includes:

[0016] Obtain target trajectory information collected in real time;

[0017] When the target trajectory information collected in real time meets a first preset condition, generating a second positioning matrix and second residual information for the second positioning matrix according to the first map data, the second map data, and the first positioning matrix;

[0018] When the real-time trajectory information satisfies a second preset condition, a second positioning matrix and second residual information for the second positioning matrix are generated according to the first map data and the second map data.

[0019] Optionally, when the real-time trajectory information satisfies a first preset condition, generating a second positioning matrix according to the first map data, the second map data, and the first positioning matrix includes:

[0020] Using the first positioning matrix, converting the second map data;

[0021] generating an intermediate positioning matrix according to the converted second map data and the first map data;

[0022] The intermediate positioning matrix and the first positioning matrix are combined to obtain a second positioning matrix.

[0023] Optionally, when the target trajectory information collected in real time meets a second preset condition, generating a second positioning matrix according to the first map data and the second map data includes:

[0024] converting the second map data according to the first map data;

[0025] A second positioning matrix is ​​generated according to the converted second map data and the first map data.

[0026] Optionally, the first preset condition is that the track distance in the target track information collected in real time is greater than a first preset distance, and the second preset condition is that the track distance in the real-time track information is greater than a second preset distance;

[0027] Wherein, the second preset distance is greater than the first preset distance;

[0028] And / or, the first preset condition is that the number of semantic elements in the target trajectory information collected in real time is greater than a first preset number, and the second preset condition is that the number of semantic elements in the target trajectory information collected in real time is greater than a second preset number;

[0029] The second preset number is greater than the first preset number.

[0030] Optionally, before acquiring the latest first positioning matrix and first residual information for the first positioning matrix, the method further includes:

[0031] Initial matching is performed on the first map data to obtain an initial first positioning matrix and first residual information for the initial first positioning matrix.

[0032] A data processing device, comprising:

[0033] A first acquisition module, used to acquire preset first map data;

[0034] A second acquisition module, used to acquire second map data collected in real time;

[0035] A third acquisition module, used to acquire a first positioning matrix and first residual information for the first positioning matrix;

[0036] A generating module, configured to generate a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data;

[0037] A first positioning matrix updating module, configured to update the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix;

[0038] The positioning correction module is used to perform positioning correction using the updated first positioning matrix.

[0039] A vehicle comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the data processing method as described above when executed by the processor.

[0040] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the data processing method described above is implemented.

[0041] The embodiments of the present invention have the following advantages:

[0042] The embodiment of the present invention obtains preset first map data, obtains second map data collected in real time, obtains a first positioning matrix and first residual information for the first positioning matrix, generates a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data, updates the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix, and uses the updated first positioning matrix to perform positioning correction, thereby realizing positioning correction using the updated first matrix. Compared with correction using the first positioning matrix or the second positioning matrix before updating, on the one hand, the positioning correction speed can be improved, and on the other hand, the updated first positioning matrix fully considers the first residual information and the second residual information, which can reduce the influence of errors and improve the robustness of positioning information. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0044] Figure 1 is a flowchart of a data processing method provided by an embodiment of the present invention;

[0045] Figure 2 is a flowchart of another data processing method provided by an embodiment of the present invention;

[0046] Figure 3 is a flowchart of the steps of another data processing method provided by an embodiment of the present invention;

[0047] Figure 4 A flow chart of front-end and back-end matching positioning and updating provided by an embodiment of the present invention;

[0048] Figure 5 It is a structural diagram of a data processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Reference Figure 1, shows a flowchart of a data processing method provided by an embodiment of the present invention, which may specifically include the following steps:

[0051] Step 101, obtaining preset first map data;

[0052] When a vehicle enters a parking lot for parking, data collection can be started from the time when the vehicle enters the parking lot, and a real-time trajectory map can be constructed through the collected data.

[0053] The vehicle can obtain the current positioning position of the vehicle through the positioning system. In order to obtain higher-precision map positioning information, a constructed parking lot scene map can be preset in the system, so that the first map data can be obtained.

[0054] In one example, the first map data may include positioning information, posture information, etc. of various semantic landmark information associated with road path points, such as parking lot entrances, speed bumps, exit points, entry points, exit points, entry points, road nodes, parking space information, etc. in the scene map.

[0055] Step 102, obtaining second map data collected in real time;

[0056] After obtaining the first map data, the second map data can be obtained in the latest constructed real-time trajectory map. The second map data may include the location information, posture information, etc. of various semantic landmark information associated with parking lot entrances, speed bumps, exit points, entry points, exit points, entry points, road nodes, parking space information, and road path points in the real-time trajectory map.

[0057] Step 103: Obtain a first positioning matrix and first residual information for the first positioning matrix;

[0058] After the second map data is acquired, the first positioning matrix and first residual information for the first positioning matrix may be acquired.

[0059] The first positioning matrix and the first residual information may be the positioning matrix information used in the most recent positioning update process, and the real-time map data may be transformed by rotation and translation through the positioning matrix information. Since there may be a deviation between the converted map data and the first map data, the greater the deviation, the lower the accuracy of the positioning information obtained by the positioning matrix transformation. Therefore, the residual information corresponding to the positioning matrix information may be obtained by performing residual calculation on the converted map data and the first map data.

[0060] In an embodiment of the present invention, before acquiring the latest first positioning matrix and the first residual information for the first positioning matrix, the method further includes:

[0061] Initial matching is performed on the first map data to obtain an initial first positioning matrix and first residual information for the initial first positioning matrix.

[0062] In practical applications, data collection can be started from the parking lot entrance, and the collected data can be initially matched with the first map data to obtain semantic landmark information that can be matched. Cloud computing can be performed based on the positioning coordinates of the semantic landmark information to obtain the first positioning matrix and the first residual information after conversion according to the first positioning matrix.

[0063] In one example, a trajectory map window that grows with the trajectory starting from the starting point can be selected, and the semantic landmark information in the window can be initially matched with the semantic landmark information in the first map data according to the position and mutual correlation, and the number of matched semantic landmarks and the positioning coordinates of the semantic landmarks can be determined based on the initial matching results. When the number of semantic landmarks is greater than a preset number, it can be determined that the initialization match is successful, and the real-time trajectory map and the scene map can be matched, so that the first positioning matrix and the first residual information can be calculated based on the positioning coordinates of the matched semantic landmarks.

[0064] Step 104: Generate a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data;

[0065] After the first positioning matrix and the first residual information are obtained, the second positioning matrix and the second residual information for the second positioning matrix may be generated in combination with the second map data.

[0066] Step 105: updating the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix;

[0067] After the second positioning matrix and the second residual information, the first positioning matrix can be updated according to the first residual information, the second residual information, and the second positioning matrix.

[0068] In an example, updating the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix includes:

[0069] Determine first weight information corresponding to the first residual information and second weight information corresponding to the second residual information; and update the first positioning matrix according to the first weight information, the second weight information, and the second positioning matrix.

[0070] In practical applications, the first residual information and the second residual information can be used to calculate the corresponding first weight information and second weight information. Since the first residual information and the second residual information can represent the deviation between the second map data and the first map data after the second map data is transformed according to the corresponding positioning matrix through rotation, translation, etc., the larger the deviation is, the lower the accuracy of the positioning information obtained by the positioning matrix conversion is. Therefore, when calculating the weight, the residual value is inversely proportional to the weight, that is, the larger the residual value is, the smaller the corresponding weight is.

[0071] After determining the first weight information and the second weight information, the first positioning matrix and the second positioning matrix can be weightedly fused using the first weight information and the second weight information. The first positioning matrix is ​​updated based on the new positioning matrix value obtained through the weighted fusion calculation. The updated first positioning matrix is ​​the positioning matrix required for this positioning correction.

[0072] By performing weighted fusion based on the residual value, the drift error caused by the error in the previous positioning correction can be reduced, and the positioning information calculated thereby improves robustness.

[0073] For example: Based on the second residual information in the latest positioning matching process of the trajectory map and the historical (last updated) residual value C k-1 (first residual information), calculate its corresponding weight (second weight information) and w(C k-1 )(first weight information), where the weight is inversely proportional to the residual.

[0074] Then, the second positioning matrix can be The corresponding rotation angle and translation and the historical positioning matrix T k-1 (First positioning matrix) corresponding to ΔP k-1 and Δθ k-1 Taking the weighted average, we can get the current rotation angle ΔP k and the translation Δθ k , as shown in the following formula:

[0075]

[0076]

[0077] Thus, the final positioning matrix T of the current position can be obtained k (updated first positioning matrix), as shown in the following formula:

[0078]

[0079] Step 106: Use the updated first positioning matrix to perform positioning correction.

[0080] After the first positioning matrix is ​​updated, the updated first positioning matrix may be used to perform positioning correction on the latest track point or semantic landmark information in the second map data.

[0081] In one example, real-time trajectory information can be obtained in a trajectory map constructed in real time, and the trajectory pose information of the current position in the trajectory map can be determined, so that the first pose matrix can be determined, and then the updated first positioning matrix and the pose matrix can be used to determine the second pose matrix converted to the scene map, so that the corrected pose information can be obtained according to the second pose matrix.

[0082] For example: The trajectory pose of the current position in the trajectory map is P tMap,i and θ tMap,i , from which we can get the current pose matrix T tMap,i , through the latest updated positioning matrix T k (updated first positioning matrix), the pose matrix T converted to the scene map can be calculated vMap,i , and its corresponding position P vMap,i and posture θ vMap,i . As shown in the following formula.

[0083]

[0084] T vMap,i =T k ·T tMap,i

[0085]

[0086] In one embodiment of the present invention, it also includes:

[0087] The first residual information is updated according to the second residual information.

[0088] After obtaining the second residual information, the second residual information in the latest positioning matching process of the trajectory map can be used and the historical (last updated) residual value C k-1 (first residual information) and calculate the current residual value C k (updated first residual information), as shown in the following formula:

[0089]

[0090] The embodiment of the present invention obtains preset first map data, obtains second map data collected in real time, obtains a first positioning matrix and first residual information for the first positioning matrix, generates a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data, updates the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix, and uses the updated first positioning matrix to perform positioning correction, thereby realizing positioning correction using the updated first matrix. Compared with correction using the first positioning matrix or the second positioning matrix before updating, on the one hand, the positioning correction speed can be improved, and on the other hand, the updated first positioning matrix fully considers the first residual information and the second residual information, which can reduce the influence of errors and improve the robustness of positioning information.

[0091] Reference Figure 2 , shows a flowchart of another data processing method provided by an embodiment of the present invention, which may specifically include the following steps:

[0092] Step 201, obtaining preset first map data;

[0093] Step 202, obtaining second map data collected in real time;

[0094] Step 203: Acquire a first positioning matrix and first residual information for the first positioning matrix;

[0095] Step 204, obtaining target trajectory information collected in real time;

[0096] In one example, the target trajectory point may be the trajectory information from the initial trajectory information at the starting point of data collection to the first trajectory information, or may be the trajectory information from the second trajectory information to the first trajectory information in the trajectory map at the time of the previous correction of the vehicle's position.

[0097] After acquiring the first positioning matrix and the first residual information, the first trajectory information of the current position may be determined in the second map data collected in real time, so that the target trajectory information including the first trajectory information may be acquired.

[0098] Step 205: When the target trajectory information collected in real time meets a first preset condition, a second positioning matrix and second residual information for the second positioning matrix are generated according to the first map data, the second map data, and the first positioning matrix;

[0099] In one example, the first preset condition is that the trajectory distance in the target trajectory information collected in real time is greater than a first preset distance; and / or the first preset condition is that the number of semantic elements in the target trajectory information collected in real time is greater than a first preset number.

[0100] After acquiring the target trajectory information, when the target trajectory information satisfies the first preset condition, a second positioning matrix and second residual information for the second positioning matrix may be generated according to the first map data, the second map data, and the first positioning matrix.

[0101] In an embodiment of the present invention, when the trajectory information collected in real time meets a first preset condition, generating a second positioning matrix according to the first map data, the second map data, and the first positioning matrix includes:

[0102] The second map data is converted using the first positioning matrix; an intermediate positioning matrix is ​​generated according to the converted second map data and the first map data; and a second positioning matrix is ​​obtained by combining the intermediate positioning matrix and the first positioning matrix.

[0103] In one example, it also includes:

[0104] Second residual information for the intermediate positioning matrix is ​​generated according to the converted second map data and the first map data.

[0105] After the second positioning matrix is ​​generated, since there may be a deviation between the first map data and the second map data and they cannot be completely overlapped, second residual information for the second positioning matrix may also be generated.

[0106] In practical applications, when the real-time trajectory information meets the first preset condition, trajectory data of a fixed distance or a fixed number of semantic landmarks including the first trajectory information can be determined in the second map data, and the first positioning matrix can be collected to convert the second map data. By matching the converted trajectory data with the semantic landmark information in the first map data, an intermediate positioning matrix can be generated based on the trajectory data corresponding to the matched semantic landmark information and the first map data, and then the intermediate positioning matrix can be combined with the first positioning matrix to obtain the second positioning matrix.

[0107] For example: front-end window matching: select a short distance sliding window on the current real-time trajectory map with a certain trajectory distance or semantic quantity. When the window meets the sliding condition (the first preset condition), the front-end matching can be triggered.

[0108] The front-end matching is mainly achieved by using the positioning transformation matrix T calculated previously k-1(first positioning matrix), convert all semantic landmark information in the latest short-distance map window of the real-time constructed trajectory map (second map data) into data in the constructed scene map coordinate system, and then use the location similarity of the semantic landmark information to find the semantic landmark information in the window selected by the trajectory map and the semantic landmark information matching the first map data. The front-end conversion matrix ΔT can be obtained based on the matching semantic landmark information F,k (intermediate matrix) and the transformed matching residual C F,k . (Second residual information) Calculate the current estimated positioning matrix (second positioning matrix), and the current estimated residual (Second residual information).

[0109] Since matching positioning does not rely on prior positioning information, the amount of calculation is large and time-consuming. Therefore, the positioning correction of the map is too slow to meet user needs. The front-end matching has a smaller amount of calculation and can increase the correction speed.

[0110] Step 206: Update the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix;

[0111] In an example, updating the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix includes:

[0112] Determine first weight information corresponding to the first residual information and second weight information corresponding to the second residual information; and update the first positioning matrix according to the first weight information, the second weight information, and the second positioning matrix.

[0113] In practical applications, the first residual information and the second residual information can be used to calculate the corresponding first weight information and second weight information. Since the first residual information and the second residual information can represent the deviation between the second map data and the first map data after the second map data is transformed according to the corresponding positioning matrix through rotation, translation, etc., the larger the deviation is, the lower the accuracy of the positioning information obtained by the positioning matrix conversion is. Therefore, when calculating the weight, the residual value is inversely proportional to the weight, that is, the larger the residual value is, the smaller the corresponding weight is.

[0114] After determining the first weight information and the second weight information, the first positioning matrix and the second positioning matrix can be weightedly fused using the first weight information and the second weight information. The first positioning matrix is ​​updated based on the new positioning matrix value obtained through the weighted fusion calculation. The updated first positioning matrix is ​​the positioning matrix required for this positioning correction.

[0115] By performing weighted fusion based on the residual value, the drift error caused by the error in the previous positioning correction can be reduced, and the positioning information calculated thereby improves robustness.

[0116] For example: Based on the second residual information in the latest positioning matching process of the trajectory map and the historical (last updated) residual value C k-1 (first residual information), calculate its corresponding weight (second weight information) and w(C k-1 )(first weight information), where the weight is inversely proportional to the residual.

[0117] Then, the second positioning matrix can be The corresponding rotation angle and translation and the historical positioning matrix T k-1 (First positioning matrix) corresponding to ΔP k-1 and Δθ k-1 Taking the weighted average, we can get the current rotation angle ΔP k Translation Δθ k , as shown in the following formula:

[0118]

[0119]

[0120] Thus, the final positioning matrix T of the current position can be obtained k (updated first positioning matrix), as shown in the following formula:

[0121]

[0122] Step 207: Use the updated first positioning matrix to perform positioning correction.

[0123] In one example, real-time trajectory information can be obtained in a trajectory map constructed in real time, and the trajectory pose information of the current position in the trajectory map can be determined and planned, so that the first pose matrix can be determined, and then the updated first positioning matrix and the pose matrix can be used to determine the second pose matrix converted to the scene map, so that the corrected pose information can be obtained according to the second pose matrix.

[0124] For example: The trajectory pose of the current position in the trajectory map is P tMap,i and θ tMap,i , from which we can get the current pose matrix T tMap,i , through the latest updated positioning matrix T k (updated first positioning matrix), the pose matrix T converted to the scene map can be calculatedvMap,i , and its corresponding position P vMap,i and posture θ vMap,i . As shown in the following formula.

[0125]

[0126] T vMap,i =T k ·T tMap,i

[0127]

[0128] In one embodiment of the present invention, it also includes:

[0129] The first residual information is updated according to the second residual information.

[0130] After obtaining the second residual information, the second residual information in the latest positioning matching process of the trajectory map can be used and the historical (last updated) residual value C k-1 (first residual information) and calculate the current residual value C k (updated first residual information), as shown in the following formula:

[0131]

[0132] The embodiment of the present invention obtains preset first map data, obtains second map data collected in real time, obtains a first positioning matrix and first residual information for the first positioning matrix, and obtains target trajectory information collected in real time. When the target trajectory information collected in real time meets a first preset condition, a second positioning matrix and second residual information for the second positioning matrix are generated according to the first map data, the second map data, and the first positioning matrix. The first positioning matrix is ​​updated according to the first residual information, the second residual information, and the second positioning matrix. Positioning correction is performed using the updated first positioning matrix, thereby realizing positioning correction using the updated first matrix. Compared with correction based only on the second positioning matrix, on the one hand, the positioning correction speed can be improved. On the other hand, the updated first positioning matrix fully considers the first residual information and the second residual information, thereby reducing the influence of errors and improving the robustness of positioning information.

[0133] Reference Figure 3 , shows a flowchart of another data processing method provided by an embodiment of the present invention, which may specifically include the following steps:

[0134] Step 301, obtaining preset first map data;

[0135] Step 302, obtaining second map data collected in real time;

[0136] Step 303: Obtain a first positioning matrix and first residual information for the first positioning matrix;

[0137] Step 304, obtaining target trajectory information collected in real time;

[0138] In one example, the target trajectory point may be trajectory information from the initial trajectory information at the starting point of data collection to the first trajectory information, or may be trajectory information from the second trajectory information at the vehicle position at the last correction to the first trajectory information.

[0139] After acquiring the first positioning matrix and the first residual information, the first trajectory information of the current position may be determined in the second map data collected in real time, so that the target trajectory information including the first trajectory information may be acquired.

[0140] Step 305: When the real-time trajectory information satisfies a second preset condition, a second positioning matrix and second residual information for the second positioning matrix are generated according to the first map data and the second map data;

[0141] In one example, the second preset condition is that the trajectory distance in the real-time trajectory information is greater than a second preset distance; wherein the second preset distance is greater than the first preset distance; the second preset condition is that the number of semantic landmarks in the real-time collected target trajectory information is greater than a second preset number; wherein the second preset number is greater than the first preset number.

[0142] After acquiring the target trajectory information, when the target trajectory information meets the second preset condition, the backend matching can be triggered, so that the second positioning matrix and the second residual information for the second positioning matrix can be generated according to the first map data, the second map data, and the first positioning matrix.

[0143] In an implementation of the present invention, when the target trajectory information collected in real time meets a second preset condition, generating a second positioning matrix according to the first map data and the second map data includes:

[0144] The second map data are converted according to the first map data; and a second positioning matrix is ​​generated according to the converted second map data and the first map data.

[0145] When the real-time trajectory information meets the first preset condition, trajectory data of a fixed distance or a fixed semantic quantity including the first trajectory information can be determined in the second map data. The probability of successful key semantic matching between the trajectory data and the first map data is high. Therefore, matching key semantic landmark information can be determined in the trajectory data and the first map data, for example, semantic landmark information such as entrance, off-slope point, on-slope point, road node, etc. The second map data is converted through the key semantic landmark information, and the converted trajectory data can be matched with the first map data for semantic landmark information, and then the second matrix can be generated through the matching semantic landmark information.

[0146] Backend window matching: A long-distance sliding window is selected on the current real-time trajectory map with a certain trajectory distance or number of semantic landmarks. When the window meets the sliding condition (the second preset condition), the backend matching can be triggered.

[0147] In the back-end matching, the matching of several key semantic landmark information (such as entrances, entry and exit slopes, and road nodes) can be determined in the trajectory map and scene map through the mutual correlation between all semantics. After temporary conversion according to the matching results, the latest long-distance window is selected, and the matching semantic landmark information in the window is determined by the position similarity of the semantic landmark information. The conversion matrix ΔT is determined based on the matching semantic landmark information. B,k and the transformed matching residual C B,k . That is, the current estimated positioning matrix (second positioning matrix), and the current estimated residual (Second residual information).

[0148] Since the back-end matching does not rely on the first positioning matrix for matching and positioning, it is not easily affected by drift errors.

[0149] Step 306: Update the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix;

[0150] In an example, updating the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix includes:

[0151] Determine first weight information corresponding to the first residual information and second weight information corresponding to the second residual information; and update the first positioning matrix according to the first weight information, the second weight information, and the second positioning matrix.

[0152] In practical applications, the first residual information and the second residual information can be used to calculate the corresponding first weight information and second weight information. Since the first residual information and the second residual information can represent the deviation between the second map data and the first map data after the second map data is transformed according to the corresponding positioning matrix through rotation, translation, etc., the larger the deviation is, the lower the accuracy of the positioning information obtained by the positioning matrix conversion is. Therefore, when calculating the weight, the residual value is inversely proportional to the weight, that is, the larger the residual value is, the smaller the corresponding weight is.

[0153] After determining the first weight information and the second weight information, the first positioning matrix and the second positioning matrix can be weightedly fused using the first weight information and the second weight information. The first positioning matrix is ​​updated based on the new positioning matrix value obtained through the weighted fusion calculation. The updated first positioning matrix is ​​the positioning matrix required for this positioning correction.

[0154] By performing weighted fusion based on the residual value, the drift error caused by the error in the previous positioning correction can be reduced, and the positioning information calculated thereby improves robustness.

[0155] For example: Based on the second residual information in the latest positioning matching process of the trajectory map and the historical (last updated) residual value C k-1 (first residual information), calculate its corresponding weight (second weight information) and w(C k-1 )(first weight information), wherein the weight value is inversely proportional to the residual value.

[0156] Then, the second positioning matrix can be The corresponding rotation angle and translation and the historical positioning matrix T k-1 (First positioning matrix) corresponding to ΔP k-1 and Δθ k-1 Taking the weighted average, we can get the current rotation angle ΔP k Translation Δθ k , as shown in the following formula:

[0157]

[0158]

[0159] Thus, the final positioning matrix T of the current position can be obtained k (updated first positioning matrix), as shown in the following formula:

[0160]

[0161] Step 307: Use the updated first positioning matrix to perform positioning correction.

[0162] In one example, real-time trajectory information can be obtained in a trajectory map constructed in real time, and the trajectory pose information of the current position in the trajectory map can be determined and planned, so that the first pose matrix can be determined, and then the updated first positioning matrix and the pose matrix can be used to determine the second pose matrix converted to the scene map, so that the corrected pose information can be obtained according to the second pose matrix.

[0163] For example: The trajectory pose of the current position in the trajectory map is P tMap,i and θ tMap,i , from which we can get the current pose matrix T tMap,i , through the latest updated positioning matrix T k (updated first positioning matrix), the pose matrix T converted to the scene map can be calculated vMap,i , and its corresponding position P vMap,i and posture θ vMap,i . As shown in the following formula.

[0164]

[0165] T vMap,i =T k ·T tMap,i

[0166]

[0167] In one embodiment of the present invention, it also includes:

[0168] The first residual information is updated according to the second residual information.

[0169] After obtaining the second residual information, the second residual information in the latest positioning matching process of the trajectory map can be used and the historical (last updated) residual value C k-1 (first residual information) and calculate the current residual value C k (updated first residual information), as shown in the following formula:

[0170]

[0171] The embodiment of the present invention obtains preset first map data, obtains second map data collected in real time, obtains a first positioning matrix and first residual information for the first positioning matrix, and obtains target trajectory information collected in real time. When the target trajectory information collected in real time meets a second preset condition, a second positioning matrix and second residual information for the second positioning matrix are generated according to the first map data, the second map data, and the first positioning matrix. The first positioning matrix is ​​updated according to the first residual information, the second residual information, and the second positioning matrix. Positioning correction is performed using the updated first positioning matrix, thereby realizing positioning correction using the updated first matrix. The updated first positioning matrix fully considers the first residual information and the second residual information, can reduce the influence of errors, and improves the robustness of positioning information.

[0172] The following combination Figure 4 The present invention is exemplified as follows:

[0173] a. Initialize map matching and positioning of the online trajectory map and the constructed scene map.

[0174] Initial matching is performed on the first map data to obtain an initial first positioning matrix and first residual information for the initial first positioning matrix.

[0175] In practical applications, data collection can be started from the parking lot entrance, and the collected data can be initially matched with the first map data to obtain semantic landmark information that can be matched. Cloud computing can be performed based on the positioning coordinates of the semantic landmark information to obtain the first positioning matrix and the first residual information after conversion according to the first positioning matrix.

[0176] b. During the real-time update of the track map, determine whether the front-end match and / or the back-end match are triggered? If the front-end match and / or the back-end match are triggered, proceed to step c. If neither the front-end match nor the back-end match is triggered, proceed to step e.

[0177] c. When the target trajectory information meets the first preset condition, the front-end matching is triggered, and the front-end map matching can be performed to obtain the second positioning matrix and the second residual information. (such as step 204-step 205)

[0178] When the target trajectory information meets the second preset condition, the backend matching is triggered, and the backend map matching can be performed to obtain the second positioning matrix and the second residual information. (such as steps 304-305)

[0179] When no frontend or backend matches are triggered,

[0180] d. Positioning matrix update: After front-end map matching or back-end map matching, the latest first positioning matrix is ​​updated by using the second positioning matrix, the second residual information, and the first residual information. (eg, step 206, step 306)

[0181] e. Positioning update in the scene map: Use the latest first positioning matrix to perform positioning update and obtain the pose matrix in the scene map coordinate system. (such as step 207, step 3087)

[0182] f. Posture update in the scene map: Get the position and posture of the vehicle’s current position based on the posture matrix.

[0183] When both front-end matching and back-end matching are triggered, the second positioning matrix obtained by the front-end matching can be used to update the first positioning matrix, and then the second positioning matrix obtained by the back-end matching can be used to update the first positioning matrix updated by the front-end matching.

[0184] Alternatively, when both front-end matching and back-end matching are triggered, the second positioning matrix obtained by back-end matching can be used to update the first positioning matrix first, and then the second positioning matrix obtained by front-end matching can be used to update the first positioning matrix updated by back-end matching.

[0185] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0186] Reference Figure 5 , shows a schematic diagram of the structure of a device for generating game voices provided by an embodiment of the present invention, which may specifically include the following modules:

[0187] A first acquisition module 501 is used to acquire preset first map data;

[0188] The second acquisition module 502 is used to acquire the second map data collected in real time;

[0189] A third acquisition module 503 is used to acquire a first positioning matrix and first residual information for the first positioning matrix;

[0190] A generating module 504, configured to generate a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data;

[0191] A first positioning matrix updating module 505, configured to update the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix;

[0192] The positioning correction module 506 is used to perform positioning correction using the updated first positioning matrix.

[0193] In one embodiment of the present invention, the device may further include:

[0194] The first residual information updating module is used to update the first residual information according to the second residual information.

[0195] In one embodiment of the present invention, the device may further include:

[0196] The initial matching module is used to perform initial matching on the first map data to obtain an initial first positioning matrix and first residual information for the initial first positioning matrix.

[0197] In one embodiment of the present invention, the generating module 504 may include:

[0198] The target trajectory information acquisition submodule is used to obtain the target trajectory information collected in real time;

[0199] A first preset condition submodule, configured to generate a second positioning matrix and second residual information for the second positioning matrix according to the first map data, the second map data, and the first positioning matrix when the target trajectory information collected in real time meets a first preset condition;

[0200] The second preset condition submodule is used to generate a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data when the real-time trajectory information meets a second preset condition.

[0201] In one embodiment of the present invention, the first preset condition is that the trajectory distance in the target trajectory information collected in real time is greater than the first preset distance, and the second preset condition is that the trajectory distance in the real-time trajectory information is greater than the second preset distance; wherein the second preset distance is greater than the first preset distance; and / or, the first preset condition is that the number of semantic elements in the target trajectory information collected in real time is greater than the first preset number, and the second preset condition is that the number of semantic elements in the target trajectory information collected in real time is greater than the second preset number; wherein the second preset number is greater than the first preset number.

[0202] In one embodiment of the present invention, the first preset condition submodule may include:

[0203] A first conversion unit, configured to convert the second map data using the first positioning matrix;

[0204] an intermediate positioning matrix generating unit, configured to generate an intermediate positioning matrix according to the converted second map data and the first map data;

[0205] The first generating unit is configured to combine the intermediate positioning matrix and the first positioning matrix to obtain a second positioning matrix.

[0206] In one embodiment of the present invention, the second preset condition submodule may include:

[0207] a second conversion unit, configured to convert the second map data according to the first map data;

[0208] The second generating unit is used to generate a second positioning matrix according to the converted second map data and the first map data.

[0209] The embodiment of the present invention obtains preset first map data, obtains second map data collected in real time, obtains a first positioning matrix and first residual information for the first positioning matrix, generates a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data, updates the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix, and uses the updated first positioning matrix to perform positioning correction, thereby realizing positioning correction using the updated first matrix. The updated first positioning matrix fully considers the first residual information and the second residual information, can reduce the influence of errors, and improves the robustness of positioning information.

[0210] An embodiment of the present invention further provides a vehicle, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and the computer program implements the above data processing method when executed by the processor.

[0211] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above data processing method is implemented.

[0212] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0213] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0214] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0215] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0216] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0217] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0218] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0219] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0220] The above is a detailed introduction to a data processing method and device provided. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for data processing, characterized in that: The method comprises: Acquire preset first map data; Acquire second map data collected in real time; Acquire a first positioning matrix used in a most recent positioning update process and first residual information for the first positioning matrix; generating a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data; updating the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix; Using the updated first positioning matrix to perform positioning correction; The updating of the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix includes: Determine first weight information corresponding to the first residual information and second weight information corresponding to the second residual information; and update the first positioning matrix according to the first weight information, the second weight information, and the second positioning matrix.

2. The method according to claim 1, characterized in that Also includes: The first residual information is updated according to the second residual information.

3. The method according to claim 2, characterized in that The generating a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data includes: Obtain target trajectory information collected in real time; When the target trajectory information collected in real time meets a first preset condition, generating a second positioning matrix and second residual information for the second positioning matrix according to the first map data, the second map data, and the first positioning matrix; When the target trajectory information collected in real time meets a second preset condition, a second positioning matrix and second residual information for the second positioning matrix are generated according to the first map data and the second map data.

4. The method according to claim 3, characterized in that: When the target trajectory information collected in real time meets a first preset condition, generating a second positioning matrix according to the first map data, the second map data, and the first positioning matrix includes: Using the first positioning matrix, converting the second map data; generating an intermediate positioning matrix according to the converted second map data and the first map data; The intermediate positioning matrix and the first positioning matrix are combined to obtain a second positioning matrix.

5. The method according to claim 3 or 4, characterized in that: When the target trajectory information collected in real time meets a second preset condition, generating a second positioning matrix according to the first map data and the second map data includes: converting the second map data according to the first map data; A second positioning matrix is ​​generated according to the converted second map data and the first map data.

6. The method according to claim 3, characterized in that The first preset condition is that the track distance in the target track information collected in real time is greater than the first preset distance, and the second preset condition is that the track distance in the target track information collected in real time is greater than the second preset distance; Wherein, the second preset distance is greater than the first preset distance; And / or, the first preset condition is that the number of semantic elements in the target trajectory information collected in real time is greater than a first preset number, and the second preset condition is that the number of semantic elements in the target trajectory information collected in real time is greater than a second preset number; The second preset number is greater than the first preset number.

7. The method according to claim 1, characterized in that Before obtaining the first positioning matrix used in the most recent positioning update process and the first residual information for the first positioning matrix, the method further includes: Initial matching is performed on the first map data to obtain an initial first positioning matrix and first residual information for the initial first positioning matrix.

8. A data processing device, characterized in that: The device comprises: A first acquisition module, used to acquire preset first map data; A second acquisition module, used to acquire second map data collected in real time; A third acquisition module, used to acquire a first positioning matrix used in a most recent positioning update process and first residual information for the first positioning matrix; A generating module, configured to generate a second positioning matrix and second residual information for the second positioning matrix according to the first map data and the second map data; A first positioning matrix updating module, configured to update the first positioning matrix according to the first residual information, the second residual information, and the second positioning matrix; A positioning correction module, used to perform positioning correction using the updated first positioning matrix; The first positioning matrix updating module is used to determine first weight information corresponding to the first residual information and second weight information corresponding to the second residual information; and update the first positioning matrix according to the first weight information, the second weight information, and the second positioning matrix.

9. A vehicle, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the method for data processing according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for data processing according to any one of claims 1 to 7 is implemented.

Images