Positioning information determination method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a method, device, electronic device and storage medium for determining positioning information. The method includes: obtaining the positioning information to be corrected of the target vehicle at the current moment; determining at least two associated lane positioning information associated with the positioning information to be corrected, and determining the confidence to be used between each associated lane positioning information and the positioning information to be corrected; if each confidence to be used is less than a preset confidence threshold, the lane details of each associated lane positioning information are displayed on the target display interface; based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence to be used, the positioning information to be corrected is updated to obtain the target positioning information at the current moment. The problem of poor accuracy of positioning results caused by determining the positioning results based on the positioning device in the prior art is solved, and the accuracy of the positioning result determination is improved to achieve the effect of ensuring safe driving of the vehicle.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer processing technology, and more particularly to a method, device, electronic device and storage medium for determining positioning information. Background Art

[0002] At present, autonomous vehicles usually use positioning systems to output vehicle location information. For example, positioning devices such as satellite positioning or radar sensors are used to output vehicle location information in real time.

[0003] However, the positioning results obtained using positioning equipment are usually affected by the environment. For example, in a long tunnel, the satellite positioning signal will be lost for a long time. At this time, only sensor matching positioning or dead reckoning is relied upon to output the vehicle position. The vehicle position may have a certain position error compared with the actual vehicle position, resulting in poor accuracy of the positioning results, which can easily cause vehicle accidents. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, electronic device and storage medium for determining positioning information, so as to improve the accuracy of determining positioning results and achieve the technical effect of ensuring safe driving of a vehicle.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining positioning information, the method comprising:

[0006] Obtain the target vehicle's positioning information to be corrected at the current moment;

[0007] Determine at least two associated lane positioning information associated with the positioning information to be corrected, and determine a confidence level to be used between each associated lane positioning information and the positioning information to be corrected;

[0008] If all the confidences to be used are less than the preset confidence threshold, the lane details of the positioning information of each associated lane are displayed on the target display interface;

[0009] Based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used, the positioning information to be corrected is updated to obtain the target positioning information at the current moment.

[0010] In a second aspect, an embodiment of the present invention further provides a positioning information determining device, the device comprising:

[0011] The module for obtaining the positioning information to be corrected is used to obtain the positioning information to be corrected of the target vehicle at the current moment;

[0012] A confidence determination module to be used, used to determine at least two associated lane positioning information associated with the positioning information to be corrected, and determine the confidence to be used between each associated lane positioning information and the positioning information to be corrected;

[0013] A lane detail display module, used to display the lane details of each associated lane positioning information on the target display interface if each confidence to be used is less than a preset confidence threshold;

[0014] The target positioning information determination module is used to update the positioning information to be corrected based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence to be used, so as to obtain the target positioning information at the current moment.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, the device comprising:

[0016] one or more processors;

[0017] a storage device for storing one or more programs,

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the positioning information determination method as described in any one of the embodiments of the present invention.

[0019] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for determining positioning information as described in any one of the embodiments of the present invention.

[0020] The technical solution of the embodiment of the present invention obtains the to-be-corrected positioning information of the target vehicle at the current moment, and determines at least two associated lane positioning information and the to-be-corrected confidences between each associated lane positioning information and the to-be-corrected positioning information. If each confidence to be used is less than a preset confidence threshold, the to-be-corrected positioning information is updated based on the lane details triggered on the target display interface and the to-be-applied lane positioning information corresponding to the highest confidence to be used to obtain the target positioning information. This solves the problem of poor positioning result accuracy caused by determining the positioning result based on the positioning device in the prior art. After the to-be-corrected positioning information is obtained based on the positioning device, the associated lane positioning information and the to-be-corrected confidences between each associated lane positioning information and the to-be-corrected positioning information are determined. When the triggered lane details match the to-be-applied lane positioning information corresponding to the highest confidence to be used, the to-be-corrected positioning information is corrected to obtain the target positioning information. A manual confirmation interface is added to improve the positioning accuracy in a human-machine co-driving manner, avoid the problem of unavailability of the automatic driving function due to positioning loss, and avoid the occurrence of the automatic driving function being mistakenly turned on due to positioning errors, thereby achieving the technical effect of ensuring safe driving of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flowchart of a method for determining positioning information provided by Embodiment 1 of the present invention;

[0023] Figure 2 A schematic diagram of a method for determining positioning information provided in Embodiment 1 of the present invention;

[0024] Figure 3 A flowchart of a method for determining positioning information provided by Embodiment 2 of the present invention;

[0025] Figure 4 A schematic diagram of the structure of a positioning information determination device provided in Embodiment 3 of the present invention;

[0026] Figure 5 A schematic diagram of a target display interface provided by Embodiment 3 of the present invention;

[0027] Figure 6 A schematic diagram of a method for determining positioning information provided by Embodiment 3 of the present invention;

[0028] Figure 7 This is a structural block diagram of a positioning information determination device provided by Embodiment 4 of the present invention;

[0029] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0031] Embodiment 1

[0032] Figure 1 This is a flowchart of a method for determining positioning information provided in the first embodiment of the present invention. This embodiment is applicable to the case of vehicle positioning. The method can be executed by a positioning information determining device in the embodiment of the present invention. The device can be implemented in software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server. The device can be configured in a computing device. The positioning information determining method provided in this embodiment specifically includes the following steps:

[0033] S110, obtaining the to-be-corrected positioning information of the target vehicle at the current moment.

[0034] It should be noted that when the target vehicle is traveling based on the navigation route, when it is necessary to obtain the positioning information to be corrected at each moment in the driving process, the positioning information to be corrected at any moment can be processed as the positioning information to be corrected at the current moment, so as to illustrate one of the moments as the current moment. The positioning information to be corrected may include but is not limited to longitude, latitude, altitude, heading angle, angular velocity, acceleration, etc.

[0035] Specifically, when the target vehicle is traveling based on the navigation route, the positioning module deployed on the target vehicle can be used to obtain the positioning information of the target vehicle at the current moment as the positioning information to be corrected. It should be noted that in order to improve the accuracy of the positioning result determination and to deal with the situation where the positioning is biased under special working conditions, when obtaining the positioning information to be corrected of the target vehicle at the current moment, the positioning information can be collected based on multiple types of positioning devices to obtain the positioning result after the fusion of multiple devices.

[0036] Optionally, obtaining the to-be-corrected positioning information of the target vehicle at the current moment includes: collecting the to-be-processed positioning information of the target vehicle at the current moment based on at least one positioning device deployed on the target vehicle; and fusing each to-be-processed positioning information to obtain the to-be-corrected positioning information.

[0037] The positioning device includes a satellite positioning device, a radar sensor device and a visual sensor device, and optionally, also includes an inertial measurement unit (IMU).

[0038] Specifically, at the current moment, the positioning information of the target vehicle can be collected by using satellite positioning equipment, radar sensor equipment and / or visual sensor equipment deployed on the target vehicle, all of which are used as positioning information to be processed. Each piece of positioning information to be processed can be fused and processed to obtain positioning information to be corrected based on device fusion positioning. For example, in an actual scenario, the positioning information to be corrected can be determined by comprehensive fusion based on the satellite positioning data collected by the satellite positioning equipment and the sensor data collected by the sensor equipment. It should be noted that if the signal of a certain positioning device is lost or the performance is impaired in an actual application, positioning can be performed based on the remaining positioning devices deployed on the vehicle. For example, when the target vehicle is driving in a long tunnel, the GPS satellite positioning signal is lost for a long time. At this time, the positioning information to be corrected can be calculated by relying on sensor matching positioning or dead reckoning (DR).

[0039] S120: Determine at least two associated lane positioning information associated with the positioning information to be corrected, and determine a confidence level to be used between each associated lane positioning information and the positioning information to be corrected.

[0040] The confidence to be used can be used to characterize the accuracy of the positioning information to be corrected. For example, the higher the confidence to be used, the more accurate the positioning information to be corrected, that is, the smaller the error between the positioning information to be corrected and the actual positioning information of the vehicle. On the contrary, the lower the confidence to be used, the greater the error between the positioning information to be corrected and the actual positioning information of the vehicle. The value range of the confidence to be used is (0, 100%).

[0041] In practical applications, after the target vehicle's positioning information to be corrected is collected through satellite positioning equipment, vision and radar sensor equipment, inertial measurement units, etc., the positioning information to be corrected can be matched with the lane data in the preset high-precision map to determine the information of each lane on the road where the target vehicle is located, and then the longitude, latitude, altitude, heading angle, angular velocity, acceleration and other information in the positioning information to be corrected are used to calculate the distance with each lane. For example, on the left and right sides of the adjacent lane boundary line are lane 1 and lane 2, respectively, the positioning point at a preset distance from the boundary line on the left side can be used as the positioning point corresponding to lane 1, and the positioning point at a preset distance from the boundary line on the right side can be used as the positioning point corresponding to lane 2. The distance between each positioning point on the same horizontal line as the target vehicle and the positioning information to be corrected can be calculated. Several lanes that are closer to the positioning information to be corrected can be used as associated lanes, and optionally, two lanes. The positioning information of the associated lane can be used as the associated lane positioning information, and then based on the positioning information of each associated lane and the positioning information to be corrected, the probability that the positioning information to be corrected may fall into each lane can be determined as the confidence to be used. Optionally, when determining the confidence to be used between the positioning information of each associated lane and the positioning information to be corrected, it can be determined based on the positioning data collected by multiple positioning devices. The positioning devices include satellite positioning, vision and radar sensors, inertial measurement units, etc. When determining the confidence to be used based on each collected data, a certain weight ratio can be set for each type of device collected data. Each weight ratio can correspond to a function, such as satellite positioning is recorded as f1(x1), vision or radar sensors are recorded as f2(x2), and inertial measurement unit is recorded as f3(x3). The total weight ratio = f1(x1)+f2(x2)+f3(x3). The value range of the total weight ratio is (0,100%], and accordingly, the positioning data of the target vehicle and the positioning data of the associated lane can be determined based on the positioning data processed by each weight ratio, and then the corresponding confidence to be used can be determined based on the two positioning data.

[0042] It should also be noted that, when determining at least two associated lane positioning information associated with the positioning information to be corrected, due to the uncertainty of positioning accuracy, and determining the confidence to be used between each associated lane positioning information and the positioning information to be corrected, it is also possible to determine the probability that the positioning information to be corrected may fall in each associated lane based on the sub-distance between the positioning information to be corrected and each associated lane, and the total distance corresponding to each sub-distance, that is, the confidence to be used.

[0043] Optionally, at least two associated lane positioning information associated with the positioning information to be corrected are determined, and the confidence to be used between each associated lane positioning information and the positioning information to be corrected is determined, including: determining at least two sub-lanes on the road on which the target vehicle is traveling, and determining the lane positioning information to be processed corresponding to each sub-lane; based on the sub-distance information between each lane positioning information to be processed and the positioning information to be corrected, determining at least two associated lane positioning information associated with the target vehicle; based on the sub-distance information corresponding to each associated lane positioning information, determining the total distance information; based on the distance ratio between each sub-distance information and the total distance information, determining the confidence to be used between each associated lane positioning information and the positioning information to be corrected.

[0044] In practical applications, the sub-lanes on the road where the target vehicle is located and the position information corresponding to each sub-lane, i.e., the lane positioning information to be processed, can be found based on the matching of the positioning information to be corrected with the lane data in the preset high-precision map. The sub-distance information between each lane positioning information to be processed and the positioning information to be corrected can be calculated, and the lane positioning information to be processed whose sub-distance information is greater than the preset distance threshold can be used as the associated lane positioning information. The sub-distance information can also be sorted by size, and the lane positioning information to be processed corresponding to the first N sub-distance information can be used as the associated lane positioning information, where N is a normal natural number. The sub-distance information corresponding to each associated lane positioning information can be added to obtain the total distance information. The ratio between each sub-distance information and the total distance information can be calculated as the distance ratio. The larger the distance ratio, the larger the distance between the associated lane positioning information and the positioning information to be corrected, the smaller the probability that the target vehicle falls into the corresponding associated lane, and accordingly, the smaller the confidence to be used. On the contrary, the smaller the distance ratio is, the smaller the difference between the associated lane positioning information and the positioning information to be corrected is, the greater the probability that the target vehicle falls into the corresponding associated lane, and accordingly, the smaller the confidence to be used is. Optionally, the value obtained by subtracting the distance ratio from the preset threshold can be used as the confidence to be used, and the preset threshold can be 1.

[0045] For example, see Figure 2There are four sub-lanes on the road where the vehicle is traveling, namely, main road ①, main road ②, main road ③ and auxiliary road ①. There is a very narrow isolation belt or guardrail between main road ③ and auxiliary road ①. The vehicle is actually traveling at position D in lane ③ of main road, but the possible positioning result will be biased towards one side of the isolation belt. The positioning position is C. The sub-distances between C and the positioning information A on main road ③ and the positioning information B on auxiliary road ① can be calculated. For example, the sub-distance between AC is 30, and the sub-distance between BC is 70. Then the total distance is 100, and the corresponding distance accounts for 30% and 70% respectively. The confidence level to be used of the positioning information C to be corrected may be P1=1-30%=70% in lane ③ of main road, and P2=1-70%=30% in lane ① of auxiliary road.

[0046] S130: If all the confidences to be used are less than the preset confidence threshold, the lane details of each associated lane positioning information are displayed on the target display interface.

[0047] The preset confidence threshold may be 90% or 95%.

[0048] Specifically, each confidence to be used can be compared with a preset confidence threshold. When each confidence to be used is greater than the preset confidence threshold, it can be said that the positioning information to be corrected at this time is uncertain and may deviate from the actual positioning result. The lane details of each associated lane positioning information can be displayed on the target display interface. For example, when each confidence to be used is less than the preset confidence threshold, a request instruction can be sent to the human-computer interaction system, which can be an IVI (In-Vehicle Infotainment) system. The details of each lane are displayed on the target display interface through an information pop-up window, requesting the driver to confirm which lane the vehicle is in, so that the vehicle positioning information is determined based on the lane information confirmed by the driver and the positioning information to be corrected, thereby improving the positioning accuracy.

[0049] S140: Based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used, the positioning information to be corrected is updated to obtain the target positioning information at the current moment.

[0050] In this embodiment, the lane details triggered by the driver on the target display interface are received, and the associated lane positioning information corresponding to the highest confidence level among the confidence levels to be used can be used as the lane positioning information to be applied. The manually triggered lane details can also be compared with the associated lane positioning information corresponding to the highest confidence level to be used. If the two information are information of the same sub-lane, the associated lane positioning information can be used as the lane positioning information to be applied, and then the positioning information to be corrected is corrected based on the highest confidence level to be used and the lane positioning information to be applied, so as to obtain the corrected positioning information as the target positioning information.

[0051] It should be noted that when the driver uses the input device to trigger the lane details on the target display interface, there may be misoperation. At this time, the triggered lane details can be compared with the lane positioning information to be applied corresponding to the highest confidence to be used. If the triggered lane details do not match the lane positioning information to be applied, that is, the two belong to two different sub-lanes, it can be said that the confidence of the positioning information to be corrected in the two sub-lanes is low. At this time, the positioning information to be corrected can continue to be maintained as the positioning result output without correction. If the triggered lane details match the lane positioning information to be applied, that is, the two belong to the same sub-lane, it can be said that the confidence of the positioning information to be corrected in the sub-lane is higher, and the positioning information to be corrected can continue to be corrected.

[0052] Optionally, based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence to be used, the positioning information to be corrected is updated to obtain the target positioning information at the current moment, including: if the lane details triggered on the target display interface match the lane positioning information to be applied corresponding to the highest confidence to be used, the highest confidence to be used is adjusted to a preset value to obtain the target confidence; based on the lane positioning information to be applied and the target confidence, the positioning information to be corrected is updated to obtain the target positioning information at the current moment.

[0053] The preset value may correspond to a preset confidence threshold.

[0054] In this embodiment, if the lane details triggered on the target display interface match the lane positioning information to be applied corresponding to the highest confidence to be used, it means that the manually selected sub-lane is consistent with the sub-lane corresponding to the highest confidence to be used, and the highest confidence to be used can be adjusted to a preset confidence threshold, the preset confidence threshold can be used as a preset value, and the adjusted preset value can be used as the target confidence. The lane positioning information to be applied can be fixed, and the positioning information to be corrected can be corrected so that the confidence between the corrected positioning information to be corrected and the lane positioning information to be applied is the target confidence, and the corrected positioning information to be corrected can be used as the target positioning information at the current moment. If the triggered lane details are the same as the positioning result with a lower confidence to be used, the positioning information to be corrected can be directly output as the target positioning information. For example, continue to refer to Figure 2 If the driver selects "main road ③", since the confidence level P1 (70%) of the lane on the main road ③ is greater than the confidence level P2 (30%) of the lane on the auxiliary road ①, the target vehicle may be on the main road ③, and the confidence level P1 can be adjusted to the preset value of 90%; if the driver selects "auxiliary road ①", since P2 is less than P1, the original positioning information to be corrected is maintained and the positioning information to be corrected is used as the target positioning information.

[0055] It should be noted that, when the positioning information to be corrected is updated to obtain the target positioning information at the current moment, the positioning information to be corrected can also be corrected based on the relative distance between the lane positioning information to be applied and the positioning information to be corrected. For example, the positioning information to be corrected can be moved closer to the lane positioning information to be applied. The corresponding sub-distance between the two will be reduced, the corresponding distance ratio will be reduced, and the confidence will increase until the confidence to be used is adjusted to the preset value, and the corrected target positioning information is obtained.

[0056] Optionally, based on the lane positioning information to be applied and the target confidence, the positioning information to be corrected is updated to obtain the target positioning information, including: determining sub-distance information between the lane positioning information to be applied and the positioning information to be corrected; processing the sub-distance information based on the target confidence to obtain the target distance information; and correcting the positioning information to be corrected based on the target distance information to obtain the target positioning information.

[0057] Specifically, based on the sub-distance information between the lane positioning information to be applied and the positioning information to be corrected, the sub-distance information can be processed using the target confidence to obtain the target distance information. For example, Figure 2, assuming that the confidence level P1 (70%) to be used in lane ③ of the main road is adjusted to the target confidence level 90%, the sub-distance between AC is 30, A is fixed, and the C positioning information is corrected. For example, the sub-distance between AC is adjusted to 10 as the target distance information, then the sub-distance between BC is 90. Correspondingly, the confidence level of lane ③ of the main road is 90% at this time, which is consistent with the target confidence level 90%. The corrected C positioning information can be used as the target positioning information.

[0058] The technical solution of this embodiment obtains the to-be-corrected positioning information of the target vehicle at the current moment, and determines at least two associated lane positioning information and the to-be-corrected confidences between each associated lane positioning information and the to-be-corrected positioning information. If each confidence to be used is less than a preset confidence threshold, the to-be-corrected positioning information is updated based on the lane details triggered on the target display interface and the to-be-applied lane positioning information corresponding to the highest confidence to be used to obtain the target positioning information. This solves the problem of poor positioning result accuracy caused by determining the positioning result based on the positioning device in the prior art. After obtaining the to-be-corrected positioning information based on the positioning device, the associated lane positioning information and the to-be-corrected confidences between each associated lane positioning information and the to-be-corrected positioning information are determined. When the triggered lane details match the to-be-applied lane positioning information corresponding to the highest confidence to be used, the to-be-corrected positioning information is corrected to obtain the target positioning information. A manual confirmation interface is added to improve the positioning accuracy in a human-machine co-driving manner, avoid the problem of unavailability of the automatic driving function due to positioning loss, and avoid the occurrence of the automatic driving function being mistakenly turned on due to positioning errors, thereby achieving the technical effect of ensuring safe driving of the vehicle.

[0059] Embodiment 2

[0060] Figure 3 This is a flowchart of a method for determining positioning information provided by Embodiment 2 of the present invention. Based on the above embodiment, after S140, a positioning correction model to be trained can be trained based on the positioning information to be corrected and the corresponding target positioning information to obtain a trained target positioning correction model. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above embodiment are not repeated here.

[0061] like Figure 3 As shown, the method specifically comprises the following steps:

[0062] S210: Obtain the to-be-corrected positioning information of the target vehicle at the current moment.

[0063] S220: Determine at least two associated lane positioning information associated with the positioning information to be corrected, and determine a confidence level to be used between each associated lane positioning information and the positioning information to be corrected.

[0064] S230: If all the confidences to be used are less than the preset confidence threshold, the lane details of each associated lane positioning information are displayed on the target display interface.

[0065] S240: Based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used, the positioning information to be corrected is updated to obtain the target positioning information at the current moment.

[0066] S250: Use the positioning information to be corrected and the corresponding target positioning information as a training sample pair.

[0067] In order to gradually reduce the number of times the driver needs to confirm, reduce the dependence of positioning correction on the driver, and improve positioning accuracy, the positioning information to be corrected and the corresponding target positioning information can be used as training sample pairs, so that the target positioning correction model can be obtained based on the training sample pairs in the subsequent training.

[0068] S260: Train the positioning correction model to be trained based on the training samples to obtain a trained target positioning correction model.

[0069] Among them, the positioning correction model to be trained can be understood as a positioning correction model that needs to be trained. At this time, the output result of the positioning correction model may not reach the expected result and needs to be trained so that the output result of the trained model is consistent with the expected result.

[0070] In order to improve the accuracy of the model, as many and rich training sample pairs as possible can be obtained, and then the positioning correction model to be trained can be trained based on the training sample pairs until a trained target positioning correction model is obtained. It should be noted that when the positioning correction model to be trained is trained based on the training sample pairs to obtain a trained target positioning correction model, the positioning correction model to be trained can also be trained based on the positioning information to be corrected and the target positioning information in the training sample pairs. The positioning information to be corrected can be used as an input parameter, and the target positioning information can be used as an output result, so that the positioning correction model to be trained can learn. When the positioning information to be corrected of the vehicle at a certain moment is input, the output result of the model is consistent with the expected result.

[0071] Optionally, a positioning correction model to be trained is trained based on the training sample pairs to obtain a trained target positioning correction model, including: taking the positioning information to be corrected of the training sample pairs as the input of the positioning correction model to be trained, and taking the target positioning information as the output of the positioning correction model to be trained, and training the positioning correction model to be trained; taking the convergence of the loss function of the positioning correction model to be trained as the training target to obtain the target positioning correction model.

[0072] Specifically, the positioning information to be corrected of the training sample pair can be input into the positioning correction model to be trained, the model can perform learning processing on the positioning information to be corrected, and can output the corrected positioning result corresponding to the positioning information to be corrected, and then the algorithm can be used to perform loss processing on the output positioning result and the expected output target positioning information to obtain the loss value, so that the model parameters in the positioning correction model to be trained can be corrected based on the loss value, and the positioning correction model to be trained can be trained. The loss function convergence of the positioning correction model to be trained can be used as a training target. For example, the training error of the loss function, that is, the loss parameter, can be used as a condition for detecting whether the loss function has reached convergence at present, such as whether the training error is less than the preset error or whether the error change trend tends to be stable, or whether the current number of iterations is equal to the preset number. If the detection reaches the convergence condition, such as the training error of the loss function reaches less than the preset error or the error change tends to be stable, it indicates that the training of the positioning correction model to be trained is completed, and the iterative training can be stopped at this time. If it is detected that the convergence condition is not reached at present, the training sample pair can be further obtained to continue training the positioning correction model to be trained until the training error of the loss function is within the preset range. When the training error of the loss function reaches convergence, it can be considered that the positioning correction model to be trained is trained, that is, a trained target positioning correction model is obtained. So that when a certain positioning information to be corrected is input, the trained target positioning correction model can output the target positioning information corresponding to the positioning information to be corrected.

[0073] It should be noted that when the positioning information to be corrected that is different from the current moment is obtained again, the positioning information to be corrected can be processed based on the trained target positioning correction model to obtain the corrected target positioning information. The associated lane positioning information and the confidence to be used can also be re-determined based on the positioning information to be corrected, and the positioning information to be corrected can be corrected in combination with information such as the manually selected lane details to obtain the corrected target positioning information.

[0074] Optionally, the positioning information determination method also includes, when the positioning information to be corrected that is different from the current moment is acquired again, determining the target processing method; if the target processing method is the first processing method, re-executing the steps of determining the associated lane positioning information, the confidence to be used, and the lane details displayed on the target display interface until the target positioning information different from the current moment is determined; or, if the target processing method is the second processing method, inputting the positioning information to be corrected into the target positioning correction model to obtain the target positioning information different from the current moment.

[0075] In this embodiment, when the positioning information to be corrected that is different from the current moment is obtained again, the processing method for processing the positioning information to be corrected can be determined, that is, the target processing method, which includes the first processing method and the second processing method. If the target processing method is the first processing method, the steps of determining the associated lane positioning information, the confidence to be used, and the lane details displayed on the target display interface are re-executed until the target positioning information to be corrected at the current moment is determined. The positioning information to be corrected that is different from the current moment and the corresponding target positioning information can also be used as training samples to continue to further train the target positioning correction model, continuously optimize and adjust the model parameters in the target positioning correction model, and improve the accuracy of positioning results under various working conditions. In order to gradually reduce the number of times the driver needs to confirm, reduce dependence on the driver, and improve the efficiency of determining the positioning results, the positioning information to be corrected can also be processed based on the second processing method, such as the positioning information to be corrected can be input into the target positioning correction model, and the model outputs the target positioning information to be corrected at the current moment.

[0076] It should be noted that after determining the target positioning information, in order to improve the accuracy of the positioning results, the target positioning information can be integrated with the lane-level or even road-level map data in the high-precision map to provide the vehicle with more precise positioning information to ensure the safe operation of the vehicle.

[0077] Optionally, after determining the target positioning information based on the present technical solution, it also includes: determining lane type information that matches the target positioning information; determining fused positioning information based on the target positioning information and the lane type information, and sending the fused positioning information to the driving controller, so that the driving controller controls the target vehicle to drive based on the fused positioning information.

[0078] The lane type information may include information about the road and lane where the vehicle is located. For example, the lane type information may be high-precision lane information such as an overpass, a tunnel, and a ramp.

[0079] In this embodiment, after determining the target positioning information, the target positioning information can be matched with the map data in the high-precision map to find the lane type information. For example, the latitude and longitude coordinates can be matched with the high-precision map data to obtain information such as the road and lane where the vehicle is located, that is, the lane type information. The target positioning information and the lane type information can be combined as fused positioning information, and the fused positioning information can be sent to the automatic driving controller, so that the driving controller can control the target vehicle to drive based on the lane-level or even road-level fused positioning information, thereby improving the positioning accuracy and preventing accidents.

[0080] The technical solution of this embodiment is to use the positioning information to be corrected and the corresponding target positioning information as training sample pairs, train the positioning correction model to be trained based on the training sample pairs, and obtain a trained target positioning correction model, so that when the positioning information to be corrected is input into the trained target positioning correction model, the model can directly output the corrected target positioning information, and perform deep learning on the positioning correction model to be trained based on the target positioning information obtained based on the manual confirmation result, gradually optimize the positioning correction model to be trained, and improve the accuracy of the positioning model under extreme working conditions. At the same time, it also reduces the number of times the driver needs to confirm, reduces the dependence on the driver, and improves the positioning accuracy.

[0081] Embodiment 3

[0082] As an optional embodiment of the above embodiment, in order to make those skilled in the art further understand the technical solution of the embodiment of the present invention, a specific application scenario example is given. For details, please refer to the following specific content.

[0083] For example, see Figure 4 , which can be represented as a structural schematic diagram of a positioning information determination device. The technical solution of the present invention is applied to an autonomous driving vehicle, which is equipped with at least an autonomous driving control system, a high-precision map and positioning system, a human-computer interaction system, an Internet access module, and an autonomous driving background. During the driving of the vehicle, the visual sensor or radar sensor in the autonomous driving control system can collect sensor data, and send the sensor data to the positioning system, and fuse it with the satellite positioning data collected by the satellite positioning device in the positioning system to obtain the positioning information to be corrected. The positioning information to be corrected can be matched with the map data in the high-precision map to obtain lane type information such as the road and lane where the vehicle is located. Based on the positioning information to be corrected and the lane type information, the fused positioning information can be obtained. Since the positioning accuracy of the fused positioning information at this time is uncertain, the confidence level (denoted as P) can be set to express the probability that the fused positioning information is correct. The value range of P is (0, 100%). Continue to see Figure 2 , there is a very narrow isolation belt or guardrail between the main and auxiliary roads. The vehicle is actually traveling in the main road ③ sub-lane D, but the possible positioning result C will be biased towards the side of the isolation belt. The possible lane type information is that the vehicle is in the main road ③ sub-lane with a confidence of P1=70%, and the vehicle is in the auxiliary road ① sub-lane with a confidence of P2=30%. Although P1 is higher than P2, accurate positioning cannot be guaranteed. Therefore, the preset confidence threshold P0=90% is set (the calibration amount can be modified). When the positioning confidence P<P0, it is considered that the current positioning result is uncertain, because both P1 and P2 are less than P0. At this time, the high-precision map and positioning system sends a request instruction to the human-computer interaction system, requesting manual confirmation. For example, see Figure 5, which can be represented as a schematic diagram of the target display interface. The lane details of the main road ③ and the auxiliary road ① can be sent to the target display interface of the human-computer interaction system through an information pop-up window to request the driver to confirm. The human-computer interaction system can be IVI (In-Vehicle Infotainment). The details information manually triggered on the target display interface can be received. The manually triggered details information and the positioning information to be corrected can be sent to the Internet access module. The Internet access module can be Tbox (Telematics-BOX). The Internet access module forwards the positioning information to be corrected to the automatic driving background. The automatic driving background corrects the positioning information to be corrected in combination with the manually triggered details information to obtain the target positioning information. The target positioning information can be forwarded to the high-precision map and positioning system, and the target positioning information is matched with the map data in the high-precision map to obtain the vehicle type information. The positioning information to be corrected and the corresponding target positioning information can also be used as a training sample pair, and the positioning correction model to be trained is trained based on the training sample pair to obtain a trained target positioning correction model.

[0084] Based on the above scheme, for example, see Figure 6 , which can be represented as a schematic diagram of the positioning information determination method. After obtaining the positioning information to be corrected, the confidence to be used between the positioning information of each associated lane and the positioning information to be corrected can be determined. If the confidence to be used is not less than the preset confidence threshold (90%), the original positioning information to be corrected is maintained. If the confidence to be used is less than the preset confidence threshold (90%), the details of each lane are displayed to request the driver to confirm. If the lane details triggered by the driver are inconsistent with the lane with the highest confidence, the original positioning information to be corrected is maintained, and the high-precision map and positioning system continue to perform matching calculations based on the positioning information to be corrected, and the positioning result is not directly given. If the lane details triggered by the driver are consistent with the lane with the highest confidence, the triggered lane details are used as fusion positioning parameters, and continue to refer to Figure 2 If the driver selects "main road ③", since the confidence of main road ③ P1 (70%)> the confidence of auxiliary road P2 (30%), the vehicle is determined to be on the main road; if the driver selects "auxiliary road ①", since P2<P1, the original fusion positioning information is maintained, and a unique and reliable positioning value cannot be given. Based on the details of the trigger lane and the highest confidence to be used and the corresponding lane positioning information to be applied, the target positioning information is obtained. The positioning information and the matching lane type information are uploaded to the controller in the automatic driving control system.

[0085] On the basis of the above scheme, the parameters for calculating the confidence to be used include data collected by three types of devices: satellite positioning, vision and radar sensors, and inertial measurement units. The data collected by each type of device can be input into the target positioning correction model, and the model corrects the positioning information to be corrected to obtain the target positioning information. The weight proportion of each type of data input corresponds to a function, satellite positioning is recorded as f1(x1), vision or radar sensors are recorded as f2(x2), and inertial measurement units are recorded as f3(x3). After requesting the driver to trigger the lane details, the data collected by the three types of devices, the positioning information to be corrected, the lane details triggered by the driver, the target positioning information and other data can be uploaded to the autonomous driving background. The background gathers the information uploaded by all vehicles to optimize the training of the positioning correction model to be trained, improve the accuracy of positioning results under various working conditions, and then send the trained target positioning correction model as positioning software to the autonomous driving vehicle, gradually reducing the number of times the driver needs to confirm, reducing the dependence on the driver, and improving the positioning accuracy, so that when a certain positioning information to be corrected is input, the trained target positioning correction model can output the target positioning information corresponding to the positioning information to be corrected. The target positioning information can be matched with the map data in the high-precision map to find the lane type information, and it can be accurately determined whether the vehicle is on or under the bridge, on the main road or the ramp, and whether the vehicle is still in the tunnel, etc. Furthermore, the target positioning information and lane type information can be sent to the controller as fused positioning information, so that the controller can control the target vehicle to drive based on the lane-level or even road-level fused positioning information, improve positioning accuracy, and prevent accidents. This technical solution adds a manual confirmation interface under special working conditions, and improves positioning accuracy in a human-machine co-driving manner, avoiding the loss of positioning that causes the automatic driving function to be unavailable, and also avoiding positioning errors that cause the automatic driving function to be mistakenly turned on and cause danger. Deep learning is performed based on the results of manual confirmation, and the positioning algorithm is gradually optimized to improve the accuracy of the positioning algorithm under extreme working conditions.

[0086] The technical solution of this embodiment obtains the positioning information to be corrected based on the positioning device, and determines the associated lane positioning information, as well as the confidence to be used between each associated lane positioning information and the positioning information to be corrected. When the triggered lane details match the lane positioning information to be applied corresponding to the highest confidence to be used, the positioning information to be corrected is corrected to obtain the target positioning information, thereby increasing the manual confirmation interface, improving the positioning accuracy in a human-machine co-driving manner, avoiding the problem of unavailability of the automatic driving function due to positioning loss, and avoiding the occurrence of the automatic driving function being mistakenly activated due to positioning errors, thereby achieving the technical effect of ensuring safe driving of the vehicle.

[0087] Embodiment 4

[0088] Figure 7This is a structural block diagram of a positioning information determination device provided by Embodiment 4 of the present invention. The device comprises: a positioning information acquisition module 710 to be corrected, a confidence determination module 720 to be used, a lane detail display module 730 and a target positioning information determination module 740.

[0089] Among them, the module 710 for obtaining the positioning information to be corrected is used to obtain the positioning information to be corrected of the target vehicle at the current moment; the module 720 for determining the confidence to be used is used to determine at least two associated lane positioning information associated with the positioning information to be corrected, and determine the confidence to be used between each associated lane positioning information and the positioning information to be corrected; the lane details display module 730 is used to display the lane details of each associated lane positioning information on the target display interface if each confidence to be used is less than a preset confidence threshold; the target positioning information determination module 740 is used to update the positioning information to be corrected based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence to be used, so as to obtain the target positioning information at the current moment.

[0090] The technical solution of this embodiment determines the to-be-corrected positioning information, associated lane positioning information and each confidence to be used of the target vehicle at the current moment. If each confidence to be used is less than a preset confidence threshold, the to-be-corrected positioning information is updated based on the triggered lane details and the to-be-applied lane positioning information corresponding to the highest confidence to be used, so as to obtain the target positioning information at the current moment. This solves the problem of poor positioning result accuracy caused by determining the positioning result based on the positioning device in the prior art. After obtaining the to-be-corrected positioning information based on the positioning device, the associated lane positioning information and the to-be-corrected confidence between the associated lane positioning information and the to-be-corrected positioning information are determined. When the triggered lane details match the to-be-applied lane positioning information corresponding to the highest confidence to be used, the to-be-corrected positioning information is corrected to obtain the target positioning information. A manual confirmation interface is added to improve the positioning accuracy in a human-machine co-driving manner, thereby avoiding the problem of unavailability of the automatic driving function due to positioning loss and the occurrence of the automatic driving function being mistakenly turned on due to positioning errors, thereby achieving the technical effect of ensuring safe driving of the vehicle.

[0091] On the basis of the above device, optionally, the module for acquiring positioning information to be corrected 710 includes a unit for determining positioning information to be processed and a unit for determining positioning information to be corrected.

[0092] A unit for determining positioning information to be processed, used to collect positioning information to be processed of the target vehicle at the current moment based on at least one positioning device deployed on the target vehicle; wherein the positioning device includes a satellite positioning device, a radar sensor device, and a visual sensor device;

[0093] The unit for determining the positioning information to be corrected is used to perform fusion processing on each piece of positioning information to be processed to obtain the positioning information to be corrected.

[0094] On the basis of the above device, optionally, the confidence determination module 720 to be used includes a lane positioning information to be processed determination unit, an associated lane positioning information determination unit, a total distance information determination unit and a confidence determination unit to be used.

[0095] A lane positioning information determination unit to be processed, used to determine at least two sub-lanes on the road on which the target vehicle is traveling, and determine the lane positioning information to be processed corresponding to each sub-lane;

[0096] An associated lane positioning information determining unit, configured to determine at least two associated lane positioning information associated with the target vehicle based on sub-distance information between each lane positioning information to be processed and the positioning information to be corrected;

[0097] A total distance information determination unit, configured to determine the total distance information based on the sub-distance information corresponding to each associated lane positioning information;

[0098] The confidence level to be used determining unit is used to determine the confidence level to be used between each associated lane positioning information and the positioning information to be corrected based on the distance ratio between each sub-distance information and the total distance information.

[0099] Based on the above device, optionally, the target positioning information determination module 740 includes a target confidence determination unit and a target positioning information determination unit.

[0100] a target confidence determination unit, configured to adjust the highest confidence to be used to a preset value to obtain a target confidence if the lane details triggered on the target display interface match the lane positioning information to be applied corresponding to the highest confidence to be used;

[0101] The target positioning information determination unit is used to update the positioning information to be corrected based on the lane positioning information to be applied and the target confidence level to obtain the target positioning information at the current moment.

[0102] On the basis of the above device, optionally, the target positioning information determination unit includes a sub-distance information determination sub-unit, a target distance information determination sub-unit and a target positioning information determination sub-unit.

[0103] a sub-distance information determination sub-unit, used to determine the sub-distance information between the lane positioning information to be applied and the positioning information to be corrected;

[0104] a target distance information determination subunit, configured to process the sub-distance information based on the target confidence level to obtain target distance information;

[0105] The target positioning information determination subunit is used to correct the positioning information to be corrected based on the target distance information to obtain the target positioning information.

[0106] On the basis of the above-mentioned device, optionally, the device further includes a target positioning correction model determination model, wherein the target positioning correction model determination model includes a training sample pair determination unit and a target positioning correction model determination unit.

[0107] A training sample pair determination unit, configured to use the positioning information to be corrected and the corresponding target positioning information as a training sample pair;

[0108] The target positioning correction model determination unit is used to train the positioning correction model to be trained based on the training samples to obtain a trained target positioning correction model.

[0109] On the basis of the above-mentioned device, optionally, the target positioning correction model determination unit includes a positioning correction model training subunit to be trained and a target positioning correction model determination subunit.

[0110] A training subunit for the positioning correction model to be trained, used to use the positioning information to be corrected of the training sample pair as input of the positioning correction model to be trained, and use the target positioning information as output of the positioning correction model to be trained, so as to train the positioning correction model to be trained;

[0111] The target positioning correction model determination subunit is used to take the convergence of the loss function of the positioning correction model to be trained as the training target to obtain the target positioning correction model.

[0112] On the basis of the above device, optionally, the device further includes a target processing mode determination module, wherein the target processing mode determination module includes a target processing mode determination unit and a target positioning information determination unit. The target processing mode determination unit is used to determine the target processing mode when the positioning information to be corrected that is different from the current moment is obtained again; the target positioning information determination unit is used to, if the target processing mode is the first processing mode, re-execute the steps of determining the associated lane positioning information, the confidence to be used, and the lane details displayed on the target display interface until the target positioning information that is different from the current moment is determined; or, if the target processing mode is the second processing mode, input the positioning information to be corrected into the target positioning correction model to obtain the target positioning information that is different from the current moment.

[0113] On the basis of the above device, optionally, the device further includes a fused positioning information determination module, wherein the fused positioning information determination module includes a lane type information determination unit and a fused positioning information determination unit.

[0114] A lane type information determination unit is used to determine lane type information that matches the target positioning information; a fused positioning information determination unit is used to determine fused positioning information based on the target positioning information and the lane type information, and send the fused positioning information to the driving controller, so that the driving controller controls the target vehicle to drive based on the fused positioning information.

[0115] The positioning information determination device provided in the embodiment of the present invention can execute the positioning information determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0116] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0117] Embodiment 5

[0118] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. Figure 8 A block diagram of an exemplary electronic device 80 suitable for implementing exemplary embodiments of the present invention is shown. Figure 8 The electronic device 80 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0119] like Figure 8 As shown, the electronic device 80 is in the form of a general computing device. The components of the electronic device 80 may include but are not limited to: one or more processors or processing units 801, a system memory 602, and a bus 803 connecting different system components (including the system memory 802 and the processing unit 801).

[0120] Bus 803 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0121] The electronic device 80 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 80, including volatile and non-volatile media, removable and non-removable media.

[0122] The system memory 802 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 804 and / or cache memory 805. The electronic device 80 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 806 may be used to read and write non-removable, non-volatile magnetic media ( Figure 8 not shown, usually called a "hard drive"). Although Figure 8 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 803 via one or more data medium interfaces. The memory 802 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0123] A program / utility 808 having a set (at least one) of program modules 807 may be stored, for example, in the memory 802, such program modules 807 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 807 generally perform the functions and / or methods of the embodiments described herein.

[0124] The electronic device 80 may also communicate with one or more external devices 809 (e.g., keyboards, pointing devices, displays 810, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 80, and / or may communicate with any device that enables the electronic device 80 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 811. Furthermore, the electronic device 80 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 812. As shown, the network adapter 812 communicates with other modules of the electronic device 80 via the bus 803. It should be understood that although Figure 8Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 80, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] The processing unit 801 executes various functional applications and data processing by running the programs stored in the system memory 802, such as implementing the positioning information determination method provided in the embodiment of the present invention.

[0126] Embodiment 6

[0127] Embodiment 6 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a method for determining positioning information when executed by a computer processor. The method includes:

[0128] Obtain the target vehicle's positioning information to be corrected at the current moment;

[0129] Determine at least two associated lane positioning information associated with the positioning information to be corrected, and determine a confidence level to be used between each associated lane positioning information and the positioning information to be corrected;

[0130] If all the confidences to be used are less than the preset confidence threshold, the lane details of the positioning information of each associated lane are displayed on the target display interface;

[0131] Based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used, the positioning information to be corrected is updated to obtain the target positioning information at the current moment.

[0132] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can 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 (non-exhaustive list) of computer-readable storage media include: 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 this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0133] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media 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.

[0134] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0135] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0136] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining positioning information, characterized in that: include: Obtain the target vehicle's positioning information to be corrected at the current moment; Determine at least two associated lane positioning information associated with the positioning information to be corrected, and determine a confidence level to be used between each associated lane positioning information and the positioning information to be corrected; If all the confidences to be used are less than the preset confidence threshold, the lane details of the positioning information of each associated lane are displayed on the target display interface; Based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used, the positioning information to be corrected is updated to obtain the target positioning information at the current moment; The confidence level to be used is used to indicate the accuracy of the positioning information to be corrected; The step of obtaining the to-be-corrected positioning information of the target vehicle at the current moment includes: Based on at least one positioning device deployed on the target vehicle, the positioning information to be processed of the target vehicle at the current moment is collected; wherein the positioning device includes a satellite positioning device, a radar sensor device and a visual sensor device; Performing fusion processing on each piece of positioning information to be processed to obtain positioning information to be corrected; The updating of the positioning information to be corrected based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used to obtain the target positioning information at the current moment includes: If the lane details triggered on the target display interface match the lane positioning information to be applied corresponding to the highest confidence to be used, the highest confidence to be used is adjusted to a preset value to obtain a target confidence; Based on the lane positioning information to be applied and the target confidence, the positioning information to be corrected is updated to obtain the target positioning information at the current moment.

2. The method according to claim 1, characterized in that The determining of at least two associated lane positioning information associated with the positioning information to be corrected, and determining a confidence level to be used between each associated lane positioning information and the positioning information to be corrected, includes: Determine at least two sub-lanes on the road on which the target vehicle is traveling, and determine lane positioning information to be processed corresponding to each sub-lane; Determine at least two associated lane positioning information associated with the target vehicle based on sub-distance information between each lane positioning information to be processed and the positioning information to be corrected; Determine total distance information based on sub-distance information corresponding to each associated lane positioning information; Based on the distance ratio between each sub-distance information and the total distance information, the confidence to be used between each associated lane positioning information and the positioning information to be corrected is determined.

3. The method according to claim 1, characterized in that The updating of the positioning information to be corrected based on the lane positioning information to be applied and the target confidence to obtain the target positioning information at the current moment includes: Determining sub-distance information between the lane positioning information to be applied and the positioning information to be corrected; Processing the sub-distance information based on the target confidence to obtain target distance information; The to-be-corrected positioning information is corrected based on the target distance information to obtain the target positioning information.

4. The method according to claim 1, characterized in that After the positioning information to be corrected is updated based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used to obtain the target positioning information at the current moment, the method further includes: Using the positioning information to be corrected and the corresponding target positioning information as a training sample pair; The positioning correction model to be trained is trained based on the training samples to obtain a trained target positioning correction model.

5. The method according to claim 4, characterized in that The training of the positioning correction model to be trained based on the training samples to obtain a trained target positioning correction model includes: Taking the positioning information to be corrected of the training sample pair as input of the positioning correction model to be trained, taking the target positioning information as output of the positioning correction model to be trained, and training the positioning correction model to be trained; The convergence of the loss function of the positioning correction model to be trained is taken as a training goal to obtain the target positioning correction model.

6. The method according to claim 4, further comprising: When the positioning information to be corrected that is different from the current moment is obtained again, a target processing method is determined; If the target processing method is the first processing method, re-execute the steps of determining the associated lane positioning information, the confidence to be used, and the lane details displayed on the target display interface until the target positioning information different from the current moment is determined; or, If the target processing method is the second processing method, the positioning information to be corrected is input into the target positioning correction model to obtain the target positioning information different from the current moment.

7. The method according to claim 1 or 6, characterized in that: After the positioning information to be corrected is updated based on the lane details triggered on the target display interface and the lane positioning information to be applied corresponding to the highest confidence level to be used to obtain the target positioning information at the current moment, the method further includes: Determining lane type information matching the target positioning information; Based on the target positioning information and the lane type information, fused positioning information is determined, and the fused positioning information is sent to a driving controller, so that the driving controller controls the target vehicle to travel based on the fused positioning information.

8. An electronic device, characterized in that: The 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 positioning information determination method as described in any one of claims 1-7.

Images