Vehicle positioning method, electronic equipment and storage medium

Abstract

The invention relates to a vehicle positioning method, electronic equipment and a storage medium. The method comprises the following steps: acquiring current measurement information of each positioning measurement source arranged on a target vehicle; according to the difference between the current measurement information of the target positioning measurement source and the current measurement information of each non-target positioning measurement source, determining a node chain between nodes in the webpage ranking algorithm model; determining a final weight of the target positioning measurement source through a webpage ranking algorithm according to a node chain between a node corresponding to the target positioning measurement source and a node corresponding to each non-target positioning measurement source; and determining a positioning result of the target vehicle according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source. And the precision of the final positioning result is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a vehicle positioning method, electronic equipment, and storage medium. Background Art

[0002] With the rapid improvement of driverless technology, driverless cars have been put into use in more and more scenarios. Positioning accuracy has always been one of the core issues in the field of driverless cars. A good and stable positioning system is the basis for the normal operation of driverless cars.

[0003] As the technology becomes more mature, more and more positioning measurement sources are installed on an unmanned vehicle (used to measure the positioning parameters of the unmanned vehicle). The final positioning of the unmanned vehicle is determined by fusing the measurement results of different positioning measurement sources to achieve the purpose of improving the final positioning accuracy.

[0004] However, as the number of positioning measurement sources increases, how to determine the importance of each positioning measurement source in fusion positioning and how to determine its contribution to the final positioning result of the vehicle are important issues related to the final positioning accuracy. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a vehicle positioning method, an electronic device and a storage medium, which improve the accuracy of the final positioning result by reasonably determining the weights of different positioning measurement sources during fusion positioning.

[0006] In a first aspect, an embodiment of the present disclosure provides a vehicle positioning method, the method comprising:

[0007] Obtaining current measurement information of each positioning measurement source set on the target vehicle;

[0008] Determine a node chain between nodes in a web page ranking algorithm model according to a difference between current measurement information of a target positioning measurement source and each non-target positioning measurement source, wherein the target positioning measurement source is any one of the positioning measurement sources, and the non-target positioning measurement source is other positioning measurement sources among the positioning measurement sources except the target positioning measurement source; one of the nodes corresponds to one of the positioning measurement sources;

[0009] Determine the final weight of the target positioning measurement source according to the node chain between the node corresponding to the target positioning measurement source and the nodes corresponding to each non-target positioning measurement source by using a web page ranking algorithm;

[0010] The positioning result of the target vehicle is determined according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source.

[0011] In a second aspect, an embodiment of the present disclosure further provides a vehicle positioning device, the device comprising:

[0012] An acquisition module is used to acquire current measurement information of each positioning measurement source set on the target vehicle;

[0013] A first determination module is used to determine a node chain between nodes in a web page ranking algorithm model according to a difference between current measurement information of a target positioning measurement source and each non-target positioning measurement source, wherein the target positioning measurement source is any one of the positioning measurement sources, and the non-target positioning measurement source is other positioning measurement sources among the positioning measurement sources except the target positioning measurement source; one of the nodes corresponds to one of the positioning measurement sources;

[0014] A second determination module is used to determine the final weight of the target positioning measurement source according to the node chain between the node corresponding to the target positioning measurement source and the nodes corresponding to each non-target positioning measurement source through a web page ranking algorithm;

[0015] The third determination module is used to determine the positioning result of the target vehicle according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source.

[0016] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle positioning method as described above.

[0017] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle positioning method as described above.

[0018] A vehicle positioning method provided by an embodiment of the present disclosure considers that the deviation between different positioning measurement sources is an important factor in determining the importance of the positioning measurement source, and therefore cleverly utilizes the self-learning characteristics of the pagerank model of the web page ranking algorithm, and utilizes the relationship between model nodes to determine the importance of each node in the entire model. By timely adjusting the weight of the positioning measurement source according to the measurement deviation between different positioning measurement sources, the positioning measurement source with better performance plays a greater role in the fusion positioning, and conversely, the weight of the positioning measurement source with poor performance is reduced, thereby effectively improving the positioning accuracy. Specifically, current measurement information of each positioning measurement source set on the target vehicle is obtained; according to the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source, a node chain between each node in the web page ranking algorithm model is determined, wherein the target positioning measurement source is any one of the positioning measurement sources, and the non-target positioning measurement source is other positioning measurement sources among the positioning measurement sources except the target positioning measurement source; one node corresponds to one positioning measurement source; through the web page ranking algorithm, according to the node chain between the node corresponding to the target positioning measurement source and the node corresponding to each non-target positioning measurement source, a final weight of the target positioning measurement source is determined; according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source, a positioning result of the target vehicle is determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 is a flow chart of a vehicle positioning method in an embodiment of the present disclosure;

[0021] Figure 2 is a schematic diagram of a web page ranking algorithm model in an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of each node and a node chain between nodes in a web page ranking algorithm model determined according to a difference between current measurement information of a target positioning measurement source and each non-target positioning measurement source in an embodiment of the present disclosure;

[0023] Figure 4 is a structural schematic diagram of a vehicle positioning device in an embodiment of the present disclosure;

[0024] Figure 5 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0028] Figure 1 FIG. 1 is a flow chart of a vehicle positioning method in an embodiment of the present disclosure. The method can be executed by a vehicle positioning device, which can be implemented in software and / or hardware, and can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps:

[0029] S110: Acquire current measurement information of each positioning measurement source arranged on the target vehicle.

[0030] Among them, the current measurement information of each positioning measurement source set on the target vehicle can be obtained through the vehicle-mounted CAN bus.

[0031] Exemplarily, the various positioning measurement sources arranged on the target vehicle include an inertial measurement unit, a global satellite navigation system, a camera-based positioning measurement unit, a lidar-based positioning measurement unit, a high-precision map-based positioning measurement unit, and a vehicle network-based positioning measurement unit, etc.

[0032] The current measurement information of each positioning measurement source may specifically include the east coordinate, the north coordinate and the azimuth.

[0033] It can be understood that for the positioning measurement sources that work abnormally on the target vehicle, they are eliminated and their importance is not calculated, or their final weight in the fusion positioning is set to 0.

[0034] S120. Determine a node chain between nodes in a web page ranking algorithm model according to a difference between current measurement information of a target positioning measurement source and each non-target positioning measurement source, wherein the target positioning measurement source is any one of the positioning measurement sources, and the non-target positioning measurement source is other positioning measurement sources among the positioning measurement sources except the target positioning measurement source; and one node corresponds to one positioning measurement source.

[0035] It is understandable that there is a certain stickiness between different positioning measurement sources, and the positioning deviation between them reflects this stickiness. The positioning of a positioning measurement source with relatively high positioning quality is relatively accurate, and the positioning deviation between it and other positioning measurement sources with relatively high positioning quality is relatively small, so a certain aggregation effect will be formed; on the contrary, if the positioning quality of the positioning measurement source is poor, then the positioning deviation with most other positioning measurement sources will be relatively large. Positioning measurement sources with relatively good positioning quality should play a greater role in fusion positioning to improve the final positioning accuracy. Based on this, the positioning deviation relationship between different positioning measurement sources can reflect the importance of the positioning measurement source.

[0036] This embodiment takes into account that the deviation between different positioning measurement sources is an important factor in determining the importance of the positioning measurement source. Therefore, the self-learning characteristics of the pagerank model of the web page ranking algorithm are cleverly used to determine the importance of each node in the entire model by using the relationship between model nodes. By timely adjusting the weight of the positioning measurement source according to the measurement deviation between different positioning measurement sources, the positioning measurement source with better performance can play a greater role in fusion positioning.

[0037] In some implementations, determining the node chain between nodes in the web page ranking algorithm model according to the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source includes:

[0038] One-to-one corresponding nodes are respectively set for the target positioning measurement source and each non-target positioning measurement source; that is, the target positioning measurement source and each non-target positioning measurement source are respectively regarded as nodes in the web page ranking algorithm model.

[0039] In response to the difference between the current measurement information of the target positioning measurement source and a non-target positioning measurement source being less than a set value, a first node chain is established from a node corresponding to the target positioning measurement source to a node corresponding to the non-target positioning measurement source, and a second node chain is established from a node corresponding to the non-target positioning measurement source to a node corresponding to the target positioning measurement source;

[0040] Wherein, the node chain includes the first node chain and the second node chain. For example, if the difference between the current measurement information of the target positioning measurement source a and a non-target positioning measurement source b is less than the set value, a first node chain pointing from node a to node b is established, and a second node chain pointing from node b to node a is established. On the contrary, if the difference between the current measurement information of the target positioning measurement source a and a non-target positioning measurement source b is greater than the set value, the first node chain pointing from node a to node b and the second node chain pointing from node b to node a are not established. Only under the premise that the difference between the current measurement information of the target positioning measurement source a and a non-target positioning measurement source b is less than the set value, the node chain between node a and node b is established, so as to further analyze the correlation between node a and node b based on the node chain, so that the current measurement information of the positioning measurement source corresponding to node a and the current measurement information of the positioning measurement source corresponding to node b are mutually constrained, thereby determining the importance of the corresponding node.

[0041] The current measurement information may specifically include east coordinates, north coordinates and azimuth. Correspondingly, the difference between the current measurement information of the target positioning measurement source and a non-target positioning measurement source is less than a set value, including: the difference between the east coordinates in the current measurement information of the target positioning measurement source and a non-target positioning measurement source is less than a first set value, the difference between the north coordinates in the current measurement information of the target positioning measurement source and a non-target positioning measurement source is less than a second set value, and the difference between the azimuths in the current measurement information of the target positioning measurement source and a non-target positioning measurement source is less than a third set value. Or the sum of the difference in the east coordinates, the difference in the north coordinates and the difference in the azimuth is less than a set value.

[0042] Furthermore, the set value may be a preset value used to limit the positioning deviation between different positioning measurement sources.

[0043] The set value may also be determined based on the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source. For example, the average value of the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source is determined as the set value. By determining the set value based on the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source, the rationality of the set value can be improved, so that different positioning measurement sources are mutually constrained.

[0044] Alternatively, the set value is determined based on the difference in historical measurement information between the target positioning measurement source and the non-target positioning measurement source. For example, the average value of the difference in historical measurement information between the target positioning measurement source and the non-target positioning measurement source in a period of time closest to the current time is determined as the set value. By determining the set value based on the difference in historical measurement information between the target positioning measurement source and the non-target positioning measurement source, the set value can be made more suitable for the target positioning measurement source and the non-target positioning measurement source, thereby improving the pertinence of the set value.

[0045] S130 , determining a final weight of the target positioning measurement source according to a node chain between a node corresponding to the target positioning measurement source and nodes corresponding to each non-target positioning measurement source through a web page ranking algorithm.

[0046] For example, see Figure 2 The schematic diagram of a web page ranking algorithm model shown in the figure includes 4 nodes. First, the initial weight PR of each node in the model is defined as 1 / 4. It is assumed that the node corresponding to the target positioning measurement source is A, and node A has two incoming nodes, namely nodes C and D. The outgoing nodes of node C are A and D, so the corresponding weight of A is 1 / 4×1 / 2=1 / 8; the outgoing node of node D is A, so the corresponding weight of A is 1 / 4×1=1 / 4. Therefore, the comprehensive weight PR of node A is 1 / 8+1 / 4=3 / 8. The calculation process of the comprehensive weight PR of other nodes is similar to that of node A. Iterate continuously in the above manner until the comprehensive weight PR value of the node no longer changes, and obtain the final weight of the node.

[0047] S140: Determine the positioning result of the target vehicle according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source.

[0048] Optionally, the final weight of each positioning measurement source is multiplied by the current measurement information of the corresponding positioning measurement source to obtain the product of the corresponding positioning measurement source, and then the products of different positioning measurement sources are added to obtain the positioning result of the target vehicle.

[0049] The vehicle positioning method provided in this embodiment takes into account that the deviation between different positioning measurement sources is an important factor in determining the importance of the positioning measurement source. Therefore, the self-learning characteristics of the pagerank model of the web page ranking algorithm are cleverly used, and the relationship between model nodes is used to determine the importance of each node in the entire model. By timely adjusting the weight of the positioning measurement source according to the measurement deviation between different positioning measurement sources, the positioning measurement source with better performance plays a greater role in the fusion positioning. Conversely, for the positioning measurement source with poor performance, its weight is reduced, thereby effectively improving the positioning accuracy.

[0050] Based on the above embodiment, in some implementation manners, determining the final weight of the target positioning measurement source according to the node chain between the node corresponding to the target positioning measurement source and the nodes corresponding to each non-target positioning measurement source through a web page ranking algorithm includes:

[0051] Determine the first nodes corresponding to each non-target positioning measurement source that has a node chain between the node corresponding to the target positioning measurement source, the reference weight of each first node, the number of second nodes of each first node, and the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to each first node is respectively a reference, wherein the second node is a node that has a node chain with the first node. Exemplarily, refer to Figure 3 The schematic diagram of each node and the node chain between nodes in the web page ranking algorithm model determined according to the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source is shown, including 5 nodes of the positioning measurement source, namely A, B, C, D and E. Assuming that A is the node corresponding to the target positioning measurement source, the first node includes B, C and D. Since there are 5 nodes in total, the initial reference weight of each node is 1 / 5. The second node of the first node B includes A, C and D; the second node of the first node C includes A, B, D and E; the second node of the first node D includes A, B and C.

[0052] Exemplarily, the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to each of the first nodes is used as a reference is calculated in the following manner:

[0053] Determine each target difference between the current measurement information of the target positioning measurement source and the current measurement information of the non-target positioning measurement source corresponding to each first node. For the current first node, determine the averaged processing value corresponding to the current first node according to the difference between the current measurement information of the target positioning measurement source and the current measurement information of the non-target positioning measurement source corresponding to the current first node, and the target differences; specifically, determine the averaged processing value corresponding to the current first node by the following second calculation formula:

[0054]

[0055] Among them, v represents the averaged value corresponding to the current first node, y d represents the difference between the current measurement information of the target positioning measurement source and the current measurement information of the non-target positioning measurement source corresponding to the current first node, y nrepresents the difference between the current measurement information of the target positioning measurement source and the current measurement information of the non-target positioning measurement source corresponding to the nth first node, y d ∈[y 1 ,y n ].

[0056] For example, the deviations of the east coordinates between the target positioning measurement source A and the non-target positioning measurement sources B, C and D are 0.2, 0.4 and 0.6 respectively. Since the smaller the deviation, the more important the corresponding positioning measurement source is, a certain processing is performed to obtain the averaged processing value, so that the averaged processing value conforms to the rule that the smaller the deviation, the larger the averaged processing value. For example, the averaged processing value v corresponding to the current first node B is: 1-0.2 / (0.2+0.4+0.6)=0.83; the averaged processing value v corresponding to the current first node C is: 1-0.4 / (0.2+0.4+0.6)=0.67; the averaged processing value v corresponding to the current first node D is: 1-0.6 / (0.2+0.4+0.6)=0.5.

[0057] For the current first node, the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the current first node is used as a reference is determined according to the averaged processing value of the current first node and the averaged processing values ​​corresponding to each of the first nodes. Specifically, the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the current first node is used as a reference is determined by the following third calculation formula:

[0058]

[0059] Wherein, z is the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the current first node is used as a reference, z n represents the averaged value of the nth first node, z d represents the averaged value of the current first node, z d ∈[z 1 ,z n ].

[0060] Continuing with the above example, the eastward coordinate deviation weight of the current measurement information of the target positioning measurement source A when taking the current measurement information of the non-target positioning measurement source corresponding to the current first node B as the benchmark is 0.83 / (0.5+0.83+0.67)=0.415; the eastward coordinate deviation weight of the current measurement information of the target positioning measurement source A when taking the current measurement information of the non-target positioning measurement source corresponding to the current first node C as the benchmark is 0.67 / (0.5+0.83+0.67)=0.335; the eastward coordinate deviation weight of the current measurement information of the target positioning measurement source A when taking the current measurement information of the non-target positioning measurement source corresponding to the current first node D as the benchmark is 0.5 / (0.5+0.83+0.67)=0.25.

[0061] The sub-weight of each first node is determined according to the reference weight of each first node, the number of second nodes of each first node, and the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to each first node is used as a benchmark. Exemplarily, the deviation weight includes the deviation weight of the east coordinate, the deviation weight of the north coordinate, and the deviation weight of the azimuth; correspondingly, the sub-weight of the first node is determined by the following first calculation formula:

[0062]

[0063] Wherein, w represents the sub-weight of the first node, x 1 represents a reference weight of the first node, n represents the number of second nodes of the first node, w 1 represents the deviation weight of the east coordinate of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the first node is used as the reference, w 2 represents the deviation weight of the north coordinate of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the first node is used as the reference, w 3 The deviation weight of the azimuth angle of the current measurement information of the target positioning measurement source is represented by the current measurement information of the non-target positioning measurement source corresponding to the first node as the reference. The sum of the sub-weights of each first node is determined as the reference weight of the target positioning measurement source.

[0064] For example, in Figure 3In the example, the node A corresponding to the target positioning measurement source has three incoming nodes (i.e., the first node), namely B, C, and D. The initial reference weights of B, C, and D are all 1 / 5 (because there are 5 nodes in this model, the initial reference weights of each node are all 1 / 5). For the first node B, it has 3 outgoing nodes, so the corresponding n is 3. Assume that the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node B. The deviation weight w of the east coordinate is 1 is 0.8; the deviation weight w of the north coordinate when the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node B 2 is 0.5; the deviation weight w of the azimuth angle when the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node B 3 is 0.5, then the sub-weight w of the first node B is: w=1 / 5×1 / 3×(0.8+0.5+0.5)=0.12.

[0065] For the first node C, it has 4 outbound nodes, so the corresponding n is 4. Assume that the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node C. The deviation weight w of the east coordinate 1 is 0.5; the deviation weight w of the north coordinate when the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node C 2 is 0.8; the deviation weight w of the azimuth angle when the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node C 3 is 0.5, then the sub-weight w of the first node C is: w=1 / 5×1 / 4×(0.5+0.8+0.5)=0.09.

[0066] For the first node D, it has 3 outbound nodes, so the corresponding n is 3. Assuming that the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node D, the deviation weight w of the east coordinate is 1 is 0.4; the deviation weight w of the north coordinate when the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node D 2 is 0.7; the deviation weight w of the azimuth angle when the current measurement information of the target positioning measurement source is based on the current measurement information of the non-target positioning measurement source corresponding to the first node D 3 is 0.5, then the sub-weight w of the first node D is: w=1 / 5×1 / 3×(0.4+0.7+0.5)=0.11.

[0067] Therefore, the sum of the sub-weights of each first node is determined as the reference weight of the target positioning measurement source, which is 0.12+0.09+0.11=0.32. That is, the reference weight of node A is updated from the initial 1 / 5 to 0.32. The reference weights of other nodes are updated in a similar manner to that of node A. When the reference weights of each of the first nodes are updated, the reference weight of the target positioning measurement source is recalculated until the change in the reference weight of the target positioning measurement source is less than the threshold, and the reference weight of the target positioning measurement source obtained by the last calculation is determined as the final weight of the target positioning measurement source. This embodiment takes into account that the deviation between positioning measurement sources is an important factor in determining the importance of positioning measurement sources, and uses the deviation between positioning measurement sources as an important judgment indicator. It also cleverly utilizes the advantages of the pagerank algorithm, and based on the relationship between node chains, allows each positioning measurement source to learn and continuously iterate and update the weight in the entire node model.

[0068] When the node network is constructed, this embodiment extends the single directed chain to 0 to 6 directed chains based on the single directed chain of the original algorithm by the deviations of the east coordinate (east), north coordinate (north) and azimuth (theta) of the positioning measurement source, which is more specific and accurate. At the same time, when the node network is constructed, for different outgoing chains of each node, the original algorithm gives each chain the same chain weight equally without distinction, while this embodiment pre-processes the data from the east coordinate (east), north coordinate (north) and azimuth (theta) based on the deviation between the current positioning measurement source and other positioning measurement sources, and after removing the abnormal values, calculates the averaged processing value based on 1-(deviation ratio), and then calculates the deviation weight. The calculated deviation weight is used as part of the chain weight, which not only ensures that the sum is 1, but also gives each chain an accurate weight, improves the accuracy of the model, and finally determines the importance and contribution of each positioning measurement source in the fusion positioning based on the final weight, thereby improving the accuracy of the final positioning result.

[0069] In the field of unmanned driving, based on the positioning data of different positioning measurement sources, a pagerank learning model is constructed to judge the weights of each positioning measurement source of the unmanned vehicle and adjust its importance in fusion positioning. From the perspective of daily vehicle operation, good and stable vehicle positioning performance is a prerequisite for normal operation. The quality of positioning of the positioning measurement source is not static and may change at any time according to changes in the environment. Through this embodiment, based on the performance of the positioning measurement source and the deviation between different positioning measurement sources, the weight of the positioning measurement source is adjusted in time, so that the positioning measurement source with better performance can play a greater role in fusion positioning. On the contrary, for the positioning measurement source with poor positioning quality, its weight is reduced, thereby effectively improving the positioning quality and avoiding operational risks.

[0070] Figure 4 FIG. 1 is a schematic diagram of the structure of a vehicle positioning device in an embodiment of the present disclosure. Figure 4 As shown: the device includes: an acquisition module 410, which is used to acquire current measurement information of each positioning measurement source set on the target vehicle; a first determination module 420, which is used to determine the node chain between each node in the web page ranking algorithm model according to the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source, wherein the target positioning measurement source is any one of the positioning measurement sources, and the non-target positioning measurement source is other positioning measurement sources among the positioning measurement sources except the target positioning measurement source; one node corresponds to one positioning measurement source; a second determination module 430, which is used to determine the final weight of the target positioning measurement source according to the node chain between the node corresponding to the target positioning measurement source and the node corresponding to the non-target positioning measurement source through the web page ranking algorithm; a third determination module 440, which is used to determine the positioning result of the target vehicle according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source.

[0071] The vehicle positioning device provided in the embodiment of the present disclosure can execute the steps in the vehicle positioning method provided in the method embodiment of the present disclosure, and the execution steps and beneficial effects are no longer repeated here.

[0072] Figure 5 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 5 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0073] like Figure 5As shown, the electronic device 500 may include a processing device 501, a ROM 502, a RAM 503, a bus 504, an input / output (I / O) interface 505, an input device 506, an output device 507, a storage device 508, and a communication device 509. The processing device (e.g., a central processing unit, a graphics processor, etc.) 501 can perform various appropriate actions and processes to implement the method of the embodiment described in the present disclosure according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0074] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the vehicle positioning method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0075] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0076] The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the current measurement information of each positioning measurement source set on the target vehicle; determines the node chain between each node in the web page ranking algorithm model according to the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source, wherein the target positioning measurement source is any one of the positioning measurement sources, and the non-target positioning measurement source is other positioning measurement sources among the positioning measurement sources except the target positioning measurement source; one of the nodes corresponds to one of the positioning measurement sources; through the web page ranking algorithm, according to the node chain between the node corresponding to the target positioning measurement source and the node corresponding to each non-target positioning measurement source, the final weight of the target positioning measurement source is determined; according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source, the positioning result of the target vehicle is determined.

[0077] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0078] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection according to one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0079] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A vehicle positioning method, characterized in that: The method comprises: Obtaining current measurement information of each positioning measurement source set on the target vehicle; Determine a node chain between nodes in a web page ranking algorithm model according to a difference between current measurement information of a target positioning measurement source and each non-target positioning measurement source, wherein the target positioning measurement source is any one of the positioning measurement sources, and the non-target positioning measurement source is other positioning measurement sources among the positioning measurement sources except the target positioning measurement source; one of the nodes corresponds to one of the positioning measurement sources; Determine the final weight of the target positioning measurement source according to the node chain between the node corresponding to the target positioning measurement source and the nodes corresponding to each non-target positioning measurement source by using a web page ranking algorithm; The positioning result of the target vehicle is determined according to the final weight of each positioning measurement source and the current measurement information of each positioning measurement source.

2. The method according to claim 1, characterized in that Determining the node chain between nodes in the web page ranking algorithm model according to the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source includes: Setting one-to-one corresponding nodes for the target positioning measurement source and each non-target positioning measurement source respectively; In response to the difference between the current measurement information of the target positioning measurement source and a non-target positioning measurement source being less than a set value, a first node chain is established from a node corresponding to the target positioning measurement source to a node corresponding to the non-target positioning measurement source, and a second node chain is established from a node corresponding to the non-target positioning measurement source to a node corresponding to the target positioning measurement source; The node chain includes the first node chain and the second node chain.

3. The method according to claim 2, characterized in that The set value is determined according to the difference between the current measurement information of the target positioning measurement source and each non-target positioning measurement source; Alternatively, the setting value is determined according to the difference between historical measurement information of the target positioning measurement source and the non-target positioning measurement source.

4. The method according to claim 1, characterized in that The method of determining the final weight of the target positioning measurement source according to the node chain between the node corresponding to the target positioning measurement source and the nodes corresponding to each non-target positioning measurement source by using a web page ranking algorithm includes: Determine the first nodes corresponding to each non-target positioning measurement source having a node chain between the node corresponding to the target positioning measurement source, the reference weight of each of the first nodes, the number of second nodes of each of the first nodes, and the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to each of the first nodes is respectively a benchmark, wherein the second node is a node having a node chain with the first node; Determine the sub-weight of each first node according to the reference weight of each first node, the number of second nodes of each first node, and the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to each first node is used as a benchmark; Determine the sum of the sub-weights of each first node as the reference weight of the target positioning measurement source; When the reference weight of each first node is updated, the reference weight of the target positioning measurement source is recalculated until the change in the reference weight of the target positioning measurement source is less than a threshold value, and the reference weight of the target positioning measurement source obtained by the last calculation is determined as the final weight of the target positioning measurement source.

5. The method according to claim 4, characterized in that The deviation weights include the deviation weights of the easting coordinates, the deviation weights of the northing coordinates, and the deviation weights of the azimuth angles; The determining the sub-weight of each first node according to the reference weight of each first node, the number of second nodes of each first node, and the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to each first node is respectively used as a benchmark, includes: The sub-weight of the first node is determined by the following first calculation formula: Among them, w represents a sub-weight of the first node, x1 represents a reference weight of the first node, n represents the number of second nodes of the first node, w1 represents the deviation weight of the east coordinate of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the first node is used as a reference, w2 represents the deviation weight of the north coordinate of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the first node is used as a reference, and w3 represents the deviation weight of the azimuth of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the first node is used as a reference.

6. The method according to claim 4, characterized in that Determining the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement sources corresponding to each of the first nodes is used as a reference, includes: Determine target differences between current measurement information of the target positioning measurement source and current measurement information of non-target positioning measurement sources corresponding to each of the first nodes; For the current first node, determine the averaged processing value corresponding to the current first node according to the difference between the current measurement information of the target positioning measurement source and the current measurement information of the non-target positioning measurement source corresponding to the current first node, and the target differences; For the current first node, the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the current first node is used as a reference is determined according to the averaged processing value of the current first node and the averaged processing values ​​corresponding to each of the first nodes.

7. The method according to claim 6, characterized in that The determining, for the current first node, a mean value processing value corresponding to the current first node according to a difference between current measurement information of the target positioning measurement source and current measurement information of a non-target positioning measurement source corresponding to the current first node, and each target difference, includes: The averaged processing value corresponding to the current first node is determined by the following second calculation formula: Among them, v represents the averaged value corresponding to the current first node, y d represents the difference between the current measurement information of the target positioning measurement source and the current measurement information of the non-target positioning measurement source corresponding to the current first node, y n represents the difference between the current measurement information of the target positioning measurement source and the current measurement information of the non-target positioning measurement source corresponding to the nth first node, y d ∈[y1,y n ].

8. The method according to claim 6, characterized in that The determining, for the current first node, according to the averaged processing value of the current first node and the averaged processing values ​​corresponding to each of the first nodes, a deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the current first node is used as a reference, includes: The deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the current first node is used as a reference is determined by the following third calculation formula: Wherein, z is the deviation weight of the current measurement information of the target positioning measurement source when the current measurement information of the non-target positioning measurement source corresponding to the current first node is used as a reference, z n represents the averaged value of the nth first node, z d represents the averaged value of the current first node, z d ∈[z1,z n ].

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images