Method and apparatus for positioning

Abstract

A positioning method and apparatus are disclosed. The method includes: determining a sensor-based reference position using a vehicle's position sensor; determining an image-based reference position of the vehicle based on image information of the vehicle captured using a camera of the vehicle; setting an acceptable range for the image-based reference position based on the vehicle's driving conditions; and comparing an error level of the image-based reference position with the acceptable range and estimating the current position of the vehicle.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefit of Korean Patent Application No. 10-2020-0155767, filed on November 19, 2020, with the Korean Intellectual Property Office, the entire disclosure of which is incorporated herein by reference for all purposes. Technical Field

[0003] The following description relates to positioning methods and apparatus. Background Technology

[0004] As an example, to assist vehicle navigation and other modes of transportation, there exist navigation systems that provide drivers with various visual information through augmented reality (AR). These systems receive GPS signals from satellites via Global Positioning System (GPS) sensors and estimate the vehicle's current position based on these signals. The absolute position of the vehicle, in latitude and longitude, can be obtained from the GPS signals. Summary of the Invention

[0005] This summary is provided to introduce, in a simplified form, the selection of concepts further described in the detailed embodiments below. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to help determine the scope of the claimed subject matter.

[0006] In one general aspect, a processor-implemented method includes: determining a first reference position based on position information of the vehicle measured using a vehicle's position sensor; determining a second reference position of the vehicle based on image information of the vehicle captured using a camera of the vehicle; setting an acceptable range for the second reference position based on the vehicle's driving conditions; comparing the second reference position with the first reference position and estimating an error level of the second reference position; and comparing the error level of the second reference position with the acceptable range and estimating the current position of the vehicle.

[0007] Determining the second reference position may include: determining the second reference position based on the geometric information of the lane boundary included in the image information.

[0008] The second reference location may include one or both of the following: information about the lane to which the vehicle belongs, and information about the specific location of the vehicle in the lane to which the vehicle belongs.

[0009] Setting an acceptable range for the second reference position based on the vehicle's driving conditions may include: determining the driving conditions from a plurality of driving conditions, wherein the plurality of driving conditions may include at least one of the following: a first driving condition in which the vehicle is driving at an intersection, and a second driving condition in which the vehicle is driving through a turn.

[0010] Setting the acceptable range may include selectively adjusting the width of the acceptable range based on the driving conditions.

[0011] Setting the acceptable range may include setting the acceptable range for a second driving situation where the vehicle is turning wider than the acceptable range set for a first driving situation where the vehicle is traveling at an intersection.

[0012] Estimating the current position may include: excluding the second reference position from consideration when estimating the current position of the vehicle in response to an error level of the second reference position being outside the acceptable range.

[0013] Estimating the current position may include: estimating the first reference position as the current position of the vehicle in response to the error level of the second reference position being outside the acceptable range; and estimating a new position estimated based on a weighted sum of the second reference position and the first reference position as the current position of the vehicle in response to the error level of the second reference position being within the acceptable range.

[0014] Determining the error level may include: determining the error level of the second reference position based on the distance between the second reference position and the first reference position.

[0015] The method may further include: setting another acceptable range for another second reference position in a subsequent time step, including: when the second reference position is outside the acceptable range, setting the width of the other acceptable range to be wider than the width of the acceptable range.

[0016] The method may further include: determining a change in a reference heading angle corresponding to a second reference position based on a plurality of second reference positions corresponding to a plurality of previous time steps, wherein estimating the current position may include: estimating the current position of the vehicle by further considering a comparison between the output of the gyroscope and the determined change in the reference heading angle.

[0017] In one general aspect, one or more examples include a non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to perform any, any combination, or all of the operations, processes, and / or methods described herein.

[0018] In one general aspect, an apparatus includes one or more processors configured to: determine a first reference position based on position information of the vehicle measured using a vehicle's position sensor; determine a second reference position of the vehicle based on image information of the vehicle captured using a camera of the vehicle; set an acceptable range for the second reference position based on the vehicle's driving conditions; compare the second reference position with the first reference position and estimate an error level of the second reference position; and compare the error level of the second reference position with the acceptable range and estimate the current position of the vehicle.

[0019] For estimating the error level of the second reference position, the processor can be configured to determine the error level based on the distance between the second reference position and the first reference position.

[0020] For estimating the current position of the vehicle, the processor can be configured to: estimate the first reference position as the current position of the vehicle in response to an error level of the second reference position being outside the acceptable range; and estimate a new position estimated based on a weighted sum of the second reference position and the first reference position as the current position of the vehicle in response to an error level of the second reference position being within the acceptable range.

[0021] The device may be a vehicle that further includes: the camera; the sensor; and a control system configured to control the vehicle based on the current location.

[0022] In setting the acceptable range, the processor can be configured to set the acceptable range for a second driving situation where the vehicle is turning wider than the acceptable range set for a first driving situation where the vehicle is traveling at an intersection.

[0023] The processor can also be configured to: set another acceptable range for another second reference position in a subsequent time step, including: when the second reference position is outside the acceptable range, setting the width of the other acceptable range to be wider than the width of the acceptable range.

[0024] The apparatus may further include a memory storing instructions that, when executed by the processor, configure the processor to perform the following operations: determining a first reference position, determining a second reference position, setting the acceptable range, comparing the second reference position with the first reference position and estimating the error level, and comparing the error level of the second reference position with the acceptable range and estimating the current position.

[0025] In one general aspect, an apparatus includes a processor configured to: determine a first reference position based on position information of the vehicle measured using a vehicle's position sensor; determine a second reference position of the vehicle based on image information of the vehicle captured using a camera of the vehicle; set an acceptable range for the second reference position based on the vehicle's driving conditions; compare the second reference position with the first reference position and estimate an error level of the second reference position; compare the error level of the second reference position with the acceptable range and estimate the current position of the vehicle; and generate control commands associated with the driving of the vehicle based on the current position of the vehicle; and further includes a control system configured to control the vehicle in response to the control commands.

[0026] The device may be a vehicle and may also include the camera.

[0027] For estimating the error level of the second reference position, the processor can be configured to determine the error level based on the distance between the second reference position and the first reference position.

[0028] For estimating the current position of the vehicle, the processor can be configured to: estimate the first reference position as the current position of the vehicle in response to an error level of the second reference position being outside the acceptable range; and estimate a new position estimated based on a weighted sum of the second reference position and the first reference position as the current position of the vehicle in response to an error level of the second reference position being within the acceptable range.

[0029] In one general aspect, a processor-implemented method includes: determining a first reference position based on position information of the vehicle measured using a vehicle's position sensor; determining a second reference position of the vehicle based on image information of the vehicle captured using a camera of the vehicle; selecting between estimating the current position of the vehicle based on the first reference position and the second reference position, and estimating the current position of the vehicle based on the first reference position, based on a determination that the second reference position is an erroneous position; and estimating the current position based on the result of the selection, wherein the determination of whether the second reference position is an erroneous position is based on an error consideration of the second reference position, the error consideration depending on the current driving conditions of the vehicle.

[0030] The determination of whether the second reference position is an incorrect position can be based on an acceptable range depending on the determination of the current driving situation, and on whether the estimation error of the second reference position is within the acceptable range.

[0031] The acceptable range can be set differently for at least two different driving situations, including setting the acceptable range wider in a turning situation compared to an intersection situation.

[0032] Determining whether the second reference position is an erroneous position may include considering at least one or both of the following: whether the second reference position determined by the previous time step was determined to be erroneous, and a comparison between the determined change in the reference heading angle corresponding to the second reference position and the output of the vehicle's gyroscope.

[0033] Other features and aspects will become clear from the following detailed description, drawings and claims. Attached Figure Description

[0034] Figure 1 An example of a navigation device is shown.

[0035] Figure 2 An example of the location estimation process is shown.

[0036] Figure 3A , Figure 3B and Figure 3C An example of a process for estimating location using an acceptable range of error detection is shown.

[0037] Figure 4A and Figure 4B This shows an example of an error based on an image-based reference location.

[0038] Figure 5 An example is shown comparing the reference location and the acceptable range.

[0039] Figure 6 This shows an example of setting an acceptable range based on driving conditions.

[0040] Figure 7 An example of detecting a turn is shown.

[0041] Figure 8 This shows an example of detecting vehicles driving at an intersection.

[0042] Figure 9 Examples of expanding the acceptable range are shown.

[0043] Figure 10 This example illustrates the process of detecting errors using the heading angle.

[0044] Figure 11 This is a flowchart illustrating an example of a vehicle positioning method.

[0045] Figure 12 An example of the configuration of a navigation device is shown.

[0046] Figure 13 An example of the configuration of an electronic device is shown.

[0047] Throughout the accompanying drawings and detailed embodiments, unless otherwise described or provided, the same and similar reference numerals will be understood to refer to the same elements, features, and structures. The drawings may not be drawn to scale, and for clarity, illustration, and convenience, the relative dimensions, scale, and depiction of elements in the drawings may be enlarged. Detailed Implementation

[0048] The following detailed description is provided to assist the reader in gaining a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, various variations, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding the disclosure of this application. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein; rather, the order of operations described herein may be obviously altered upon understanding the disclosure of this application, except for operations that must occur in a specific order. Furthermore, for clarity and conciseness, descriptions of features well-known after understanding this disclosure may be omitted.

[0049] The features described herein may be implemented in various forms and should not be construed as limited to the examples described herein. Rather, the examples described herein are provided merely to illustrate some of the many feasible ways of implementing the methods, apparatus, and / or systems described herein, which will become apparent upon understanding the disclosure of this application.

[0050] The following structures or other descriptions of the examples disclosed herein are for illustrative purposes only, and the examples may be implemented in various forms. The examples are not intended to be limiting, but rather intended to cover various modifications, equivalents, and alternatives within the scope of the claims.

[0051] As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including” as used in this specification specify the presence of the stated features, integers, operations, elements, components, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, operations, elements, components, and / or combinations thereof. Furthermore, the use of the term “may” (e.g., regarding what an example or embodiment may include or implement) in relation to examples or embodiments herein means that at least one example or embodiment includes or implements such a feature, and that all examples are not limited thereto.

[0052] Unless otherwise defined, all terms used herein (including technical or scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the examples pertain, upon understanding this disclosure. It should also be understood that terms such as those defined in general dictionaries shall be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the disclosure of this application, and not as an ideal or overly superficial meaning, unless so explicitly defined herein.

[0053] Additionally, in the description of the example embodiments, such descriptions may be omitted when it is believed that a detailed description of the structure or function learned after understanding the disclosure of this application may lead to an ambiguous interpretation of the example embodiments.

[0054] Although terms such as “first,” “second,” “A,” “B,” “(a),” and “(b)” are used to describe various components, the components are not limited to these terms. These terms should only be used to distinguish one component from another. For example, within the scope of the conception of this disclosure, a “first” component may be referred to as a “second” component, or similarly, a “second” component may be referred to as a “first” component. It will be understood that when a component is referred to as being “connected to” or “coupled to” another component, the component may be directly connected to or coupled to that other component, or there may be an intermediate component.

[0055] Furthermore, the term "vehicle" can refer to any type of transport equipment and corresponding means used to move people or things, such as cars, buses, motorcycles, and trucks. The term "road" can refer to a path on which such vehicles travel, and can include various types of roads, such as highways, national roads, expressways, and dedicated motor vehicle lanes. The term "lane" refers to the road space separated by lane boundaries marked on the road surface. The term "current lane," referring to the lane currently being traveled by a vehicle among multiple lanes, can refer to the lane space currently occupied and used by the vehicle, and can also be called "this lane." The term "lane boundary" refers to the solid or dashed lines marked on the road surface to distinguish lanes. "Lane boundary" can also be called "lane marking."

[0056] Components included in one example can be described using the same names in various examples. Unless the context explicitly indicates otherwise, a description made about one example can be applied to other examples, and therefore further descriptions can be omitted.

[0057] Figure 1 An example of a navigation device is shown. (Reference) Figure 1 The navigation device 100 can provide navigation parameters based on at least one of the vehicle's image data, sensor data, and map data. For example, the navigation parameters may include information about at least one of the vehicle's attitude, speed, and position.

[0058] The vehicle can generate navigation information based on navigation parameters and provide this information to users (e.g., drivers and / or vehicles (e.g., autonomous vehicles)). The navigation device 100 can also represent the vehicle. As a non-limiting example, the vehicle can provide navigation information using an augmented reality (AR) scheme via its three-dimensional (3D) head-up display (HUD). The navigation device 100 can represent a virtual image to be overlaid on a real background based on navigation parameters. It is desirable to accurately measure the vehicle's state to achieve or seek an error-free AR environment.

[0059] The vehicle may include at least one camera configured to capture at least one of a plurality of directions around the vehicle, including front, side, rear, above, and below. The navigation device 100 may receive image information of the vehicle from the at least one camera. The vehicle may include a position sensor configured to measure the vehicle's position, such as an inertial measurement unit (IMU), a global positioning system (GPS), and on-board diagnostics (OBD). The navigation device 100 may receive position information of the vehicle from the position sensor. Here, by way of non-limiting example, the IMU may include an accelerometer and a gyroscope.

[0060] The navigation device 100 can use or generate high-definition (HD) maps as map data. HD maps can include information about various map elements (e.g., lane boundaries, center lines, and guide markings) generated using various sensors. The various elements of the HD map can be represented as a point cloud, and each point in the point cloud can correspond to a 3D location. For example, the 3D location can be represented using latitude, longitude, and altitude.

[0061] Figure 2 An example of the location estimation process is shown. (Reference) Figure 2 The navigation device can perform sensor-based positioning in operation 210, image-based positioning in operation 220, and determine the vehicle's final position in operation 240 by performing fusion based on the results of operations 210 and 220.

[0062] In operation 210, the navigation device can estimate the vehicle's sensor-based position based on position information measured by the vehicle's position sensors. For example, sensor-based positioning can include sensor fusion. Sensor fusion refers to an estimation scheme that fuses various types of information. For example, sensor fusion can correspond to a Kalman filter. In such an example, the fused information can include values ​​estimated using an estimation model based on Kalman filter theory and values ​​estimated using sensor information. For example, the navigation device can use IMU, GPS, and OBD for sensor fusion in operation 210. Here, the navigation device can use the outputs of GPS and OBD as sensor information and the output of the IMU as input to the estimation model to estimate the vehicle's position, velocity, and attitude.

[0063] In operation 220, the navigation device can perform image-based positioning based on image information of the vehicle. The image information may include geometric information about lane boundaries visible ahead of the vehicle. For example, the geometric information about lane boundaries may include information about at least one of the type, direction, and arrangement of lane boundaries. The navigation device can determine the image-based position by combining image information with sensor information other than the image information. For example, the navigation device can verify the approximate position of the vehicle based on position information measured by a position sensor (e.g., a GPS sensor). The navigation device can verify the lane to which the vehicle belongs and / or the specific position of the vehicle within its lane based on the image information, and estimate the image-based position accordingly. For example, the estimated image-based position can be mapped to an HD map, and information from the HD map can be provided to the user.

[0064] Sensor-based localization is adaptable to fast output intervals and can accurately apply changes. Therefore, relative positions can be verified relatively accurately based on positions estimated from sensors. In one example, image-based localization is suitable for verifying absolute positions. In operation 240, the navigation device can obtain the final position by performing fusion based on the estimated sensor-based position and the estimated image-based position. Here, in one example, the navigation device can perform fusion via sensor fusion. For example, the navigation device can estimate the final position of the vehicle by using the image-based position of the vehicle estimated in operation 220 and the vehicle speed estimated in operation 210 as inputs to a model for estimating the final position.

[0065] Typically, images can contain information suitable for estimating absolute position. However, due to potential occlusion and saturation, some image information may be lost, or changes may occur in the driving environment such as lane additions or reductions, which can significantly reduce the reliability of image-based position estimations. Therefore, obtaining the final position from an image-based estimated position may lead to reduced accuracy of the estimated final position.

[0066] In each example, the navigation device can determine in operation 230 whether the image-based estimated position corresponds to an error, and can obtain the final position in operation 240 by excluding the corresponding erroneous position, and can ultimately obtain a final position with high accuracy.

[0067] In one example, a navigation device can estimate the error level of an image-based position (i.e., the location estimated from an image) by setting an acceptable range based on the vehicle's corresponding driving conditions and comparing the estimated error level of the image-based position with the acceptable range. For example, the navigation device can estimate the error level of the image-based position based on sensor-based location. When the error level is outside the acceptable range, the navigation device can classify the image-based position as incorrect. For example, the navigation device can obtain the final position by excluding consideration of the image-based estimated position.

[0068] In another example, the navigation device may calculate the heading angle using image-based estimated positions over consecutive time steps, and may compare the calculated changes in the heading angle with the outputs of one or more gyroscopes. When the difference based on this comparison exceeds a threshold, the navigation device may, for example, classify the corresponding estimated position (e.g., the estimated position of the last time step) as incorrect.

[0069] The navigation device may consider two operations: whether the estimated error level is outside an acceptable range, and whether the difference between the calculated change in heading angle and the output of one or more gyroscopes exceeds a threshold. In such an example, these two operations can be performed sequentially or in parallel. When both conditions are met, the image-based estimated position can be applied in the process of obtaining the final position. Conversely, when neither condition is met, the image-based estimated position can be considered incorrect and is not used in obtaining the final position.

[0070] Figure 3A , Figure 3B and Figure 3C An example of a process for estimating location using error detection within an acceptable range is shown. (Reference) Figure 3A In operation 310, the navigation device can perform sensor-based localization. For example, the navigation device can estimate the vehicle's position, speed, and attitude based on sensor fusion. In operation 330, the navigation device can perform image-based localization. The navigation device can estimate the lane to which the vehicle belongs and / or the vehicle's specific position within the lane based on image information and sensor information. Here, the navigation device can use the vehicle's position and attitude estimated by sensor fusion in operation 310. The image-based localization result is based on image information and can therefore be referred to as an image-based reference position.

[0071] In operation 320, the navigation device can determine the vehicle's driving status. The vehicle's driving status can be determined based on the type of road and / or the type of direction of travel. For example, driving status may include: the vehicle traveling at an intersection, the vehicle turning, and other driving statuses. Other driving statuses may include: the vehicle traveling straight without turning at a point on the road that is not an intersection.

[0072] In operation 340, the navigation device can perform error detection related to the image-based reference position. For error detection, the navigation device can set an acceptable range in operation 341 and compare the estimated error level of the image-based reference position with the acceptable range in operation 342. The navigation device can estimate the error level of the image-based reference position based on sensor-based positioning results. For example, the navigation device can determine the model-estimated reference position by performing the preliminary estimation in operation 351 based on the sensor-based positioning results. The model-estimated reference position can be used as a criterion for estimating the error level of the image-based reference position. An exemplary preliminary estimation process is further described below. The navigation device can estimate the error level of the image-based reference position based on the difference between the image-based reference position and the model-estimated reference position. When the difference is relatively large or greater than a threshold, the error level of the image-based reference position can be determined to be relatively high.

[0073] Navigation devices can set acceptable ranges based on driving conditions. In one example, the navigation device can set different widths or degrees of acceptable ranges based on driving conditions. Therefore, whether to accept image-based reference positions with the same error level can vary based on driving conditions. In other words, although a particularly large error level may be estimated for each of several image-based reference positions, some image-based reference positions may be identified as incorrect, while others may not be identified as incorrect, depending on the driving conditions of the specific image-based reference position. For example, a smaller acceptable range can be set for driving at intersections, while a larger acceptable range can be set for turning. In the case of driving at intersections, the possibility of including noise in the image information is high due to factors such as lane disappearance, changes in lane boundary patterns, and occlusions leading to and within intersections. Therefore, strict criteria can be applied to image-based reference positions in the case of intersections. In the case of turning, the estimation accuracy in the lateral direction may decrease significantly. Therefore, receiving as much image information as possible can improve the accuracy of position estimation, and thus, the acceptable range for turning can be greater than the acceptable range for intersection situations. (Refer to...) Figures 6 to 9 An example setting for acceptable ranges is further described. The navigation device can classify image-based reference positions within the acceptable range as neither erroneous nor not erroneous, and can classify image-based reference positions outside the acceptable range as erroneous.

[0074] In operation 350, the navigation device can perform fusion based on sensor-based positioning results and image-based positioning results (i.e., image-based reference positions). The fusion in operation 350 may include: a preliminary estimation in operation 351 and a secondary estimation in operation 352. The navigation device can estimate the position at the current time step by performing a preliminary estimation using the final position estimated in the previous time step and the sensor-based positioning results. The preliminary estimation result corresponds to an estimate from a model based on sensor information (e.g., vehicle position data measured using a position sensor (e.g., GPS)) and may be referred to as a model-based estimated reference position to distinguish it from an image-based reference position. The navigation device may also set the model-based estimated reference position based on an acceptable range.

[0075] The navigation device can perform secondary estimation by correcting a model-estimated reference position based on an image-based reference position. Secondary estimation can be performed selectively based on the result of error detection performed in operation 340. When the image-based reference position corresponds to an error, secondary estimation may not be performed, and the model-estimated reference position can be output as the final position. When the image-based reference position does not correspond to an error, secondary estimation can be performed, and the new position based on the position correction result can be output as the final position. The new position can be estimated based on a weighted sum of the image-based reference position and the model-estimated reference position. In the following, as a non-limiting example, the reference... Figure 3B and Figure 3C Further description of the fusion of operation 350.

[0076] Figure 3B An example of sensor fusion is shown. (Reference) Figure 3B Sensor fusion can include: model propagation in operation 361, measurement update in operation 362, and time update in operation 363. Model propagation refers to the following operation: based on the model's information from the previous time step (… or Calculate the information for the current time step. The calculation result can be represented as... k represents the current time step, and + / - indicates whether sensor information was applied. When a measurement update was performed in the previous time step, the information from the previous time step is... If no measurement update was performed in the previous time step, the information from the previous time step is...

[0077] Time updates refer to operations such as performing "model-based estimation" of information about the current time step, based on Kalman filter theory. The estimation result can be represented as... Here, the caret (^) indicates an estimate. Measurement update refers to executing y.k and The weighted sum operation. y k This represents the sensor information input at the current time step. It can be based on y. k and The weights are determined by the precision or covariance. The corresponding result can be expressed as... When responding to y k When performing a measurement update based on the input, the estimate of the current time step is... When the response is no input y k Without performing a measurement update, the estimate of the current time step is... In the next time step, it can be achieved through... or Execution model propagation.

[0078] Figure 3C For example, Figure 3A The preliminary estimate in operation 351 and, for example, with Figure 3A Examples of sensor fusion related to operation 352. In operations 353, 354, and 355, Figure 3C The navigation device can perform model propagation, measurement update, and time update corresponding to operations 361, 362, and 363, respectively. The navigation device can calculate the position at the current time step by applying the velocity estimated at the current time step via sensor-based positioning to the position at the previous time step, as a model propagation operation. For example, P k According to P k =P k-1 +V k *Calculated using Δt. Here, P k P represents the position at the current time step. k-1 V represents the position of the previous time step. k This represents the velocity at the current time step, and Δt represents the time interval between two consecutive time steps. The calculation results are... Correspondingly.

[0079] The navigation device can generate preliminary estimates through time update operations. The preliminary estimates are then compared with... Correspondingly, this can be referred to as the aforementioned model-based estimation reference position. Furthermore, the navigation device can generate a secondary estimation result by performing a weighted sum of sensor information and the preliminary estimation result. The secondary estimation result is then compared with... Correspondingly, sensor information may include: the position estimated at the current time step by sensor-based positioning, and the position estimated at the current time step by image-based positioning. As mentioned above, the position estimated at the current time step by image-based positioning can be referred to as the image-based reference position. The navigation device can generate preliminary and secondary estimation results through operations 353, 354, and 355, and select one of the preliminary and secondary estimation results as the final position based on the error detection result.

[0080] Figure 4A and Figure 4B This shows an example of an error based on an image's reference location. Figure 4A and Figure 4B In the image, thick or dark solid lines represent the actual or real driving path, while dots represent positions estimated based on the image. Figure 4A An example is shown below: The current vehicle is traveling in the direction indicated by the arrow 410, and there is an obstruction in road segment 412. For example, obstruction may occur when another vehicle in front of the current vehicle obstructs the current vehicle's camera. Because of the obstruction in road segment 412, it is difficult to include information suitable for determining the absolute position in the image information captured in road segment 412. Therefore, position 411 may differ from the actual travel path.

[0081] Figure 4B An example is shown below: the current vehicle is traveling in the direction indicated by the arrow 420, and the number of lanes increases at boundary 422. If all lanes appear in the image information, it is relatively easy to identify the lane that is the vehicle's travel lane. However, if not all lanes but only a portion of all lanes appear in the image information, for example, if only two lanes are captured on a four-lane road, it may be difficult to identify the lane corresponding to the current vehicle's travel lane. In this case, the accuracy of the location information may further decrease if the number of lanes increases or decreases. For example, if a left-turn lane boundary appears in the first lane, it may be necessary to change the travel lane, for example, changing the travel lane from the second lane to the third lane. However, this information about the increase or decrease in the number of lanes may not be immediately reflected in the location information through the image information. Therefore, although the vehicle is traveling in the same lane, errors may occur in image-based positioning, and the travel lane may be identified as having changed, as shown at location 421.

[0082] refer to Figure 4A Position 411 and Figure 4BAt position 421, errors caused by image-based localization are likely to involve lane changes that are incorrectly identified as lane changes. Image-based localization results are provided by mapping on an HD map. Here, the HD map includes positional information for each lane boundary, and the localization results can generally be mapped onto the HD map based on these lane boundaries. Furthermore, in cases such as occlusion and lane addition / reduction, the image information may include information for estimating the specific position within the current driving lane; however, the image information may not include information for estimating which lane the current driving lane is. Therefore, the navigation device can detect errors in the position estimated by image-based localization based on such lane changes.

[0083] Figure 5 An example is shown comparing the reference location and the acceptable range. Figure 5 A first acceptable region 511 is shown in relation to a first image-based reference position 510, and a second acceptable region 521 is shown in relation to a second image-based reference position 520. Each acceptable region visually represents a corresponding acceptable range to aid in understanding each acceptable range.

[0084] refer to Figure 5 The first acceptable region 511 corresponds to a circle with a radius equal to a first acceptable range set for a first image-based reference position 510, and the center of the first acceptable region 511 is a first model-estimated reference position 512 corresponding to the first image-based reference position 510. Similarly, the second acceptable region 521 corresponds to a circle with a radius equal to a second acceptable range set for a second image-based reference position 520, and the center of the second acceptable region 521 is a second model-estimated reference position 522 corresponding to the second image-based reference position 520. Therefore, an image-based reference position within the acceptable region can indicate that the difference between the image-based reference position and its corresponding model-estimated reference position is within an acceptable range. Figure 5 In this context, it is assumed that the first acceptable range and the second acceptable range are the same. For example, the width of each acceptable range can be based on the width of each lane.

[0085] The navigation device can determine the distance between a first image-based reference position 510 and a first model-estimated reference position 512 as the error level of the first image-based reference position 510, and can determine the distance between a second image-based reference position 520 and a second model-estimated reference position 522 as the error level of the second image-based reference position 520. Furthermore, the navigation device can compare the error level of the first image-based reference position 510 with a first acceptable range, and compare the error level of the second image-based reference position 520 with a second acceptable range. Here, because the first image-based reference position 510 is within the first acceptable region 511, the navigation device can classify the first image-based reference position 510 as error-free. Because the second image-based reference position 520 is outside the second acceptable region 521, the navigation device can classify the second image-based reference position 520 as error.

[0086] The accuracy in the lateral direction (Y) may be more important than the accuracy in the longitudinal direction (X) of the vehicle's movement. Therefore, a navigation device can determine the error level of each image-based reference position based on the lateral direction (Y). For example, the navigation device can... Figure 5 The coordinate system is used to determine the error level of the first image-based reference position 510 based on the difference between the y coordinate of the first image-based reference position 510 and the y coordinate of the first model-based estimated reference position 512, and an acceptable range corresponding to it can be set and the acceptable range can be compared with the error level.

[0087] Figure 6 This shows an example of setting an acceptable range based on driving conditions. (Reference) Figure 6 The navigation device can determine the current driving situation in operations 611, 621, and 631, and can set an acceptable range based on the current driving situation in operations 612, 622, 632, and 633. In operations 612, 622, 632, and 633, e k e represents the acceptable range of the current time step. L This indicates the first acceptable range, and e S Indicates the second acceptable range. (Similar to e) S In comparison, e L This can correspond to a wider acceptable range. For example, when the current driving situation corresponds to a turn, the navigation device can set the current acceptable range to e. L When the current driving situation corresponds to driving at an intersection, the navigation device can set the current acceptable range to e. S .

[0088] Although the current driving direction does not correspond to turning or driving at an intersection, the navigation device can adjust the width of the acceptable range based on whether the previous image-based reference position was classified as incorrect. For example, if the previous image-based reference position was classified as incorrect, the navigation device can adjust the width of the acceptable range accordingly. k-1 In comparison, navigation devices can enable e k The width is increased by Δe. When the previous image-based reference position is classified as error-free, the navigation device can increase e. k Set to e init Here, e init This represents the initial width, and, for example, can have a value based on lane width. If the error persists and image-based reference positions are continuously excluded from the position estimate, the error may diverge. Therefore, if the error persists, the navigation device can incrementally (e.g., little by little) increase the width by an acceptable range to prevent the error from diverging.

[0089] In operation 640, the navigation device can compare ΔP. y and e i ΔP y This represents the difference between the image-based reference position and the model-estimated reference position. A large difference indicates a high error level for the image-based reference position. For example, ΔP y It can represent the difference in the lateral direction between image-based reference positions and model-estimated reference positions. i This indicates the set acceptable range, and i can correspond to one of L, S, and k, i.e., it depends on the result of operation 611, operation 621, or operation 631. For example, if ΔP y Within an acceptable range, for example, if ΔP y Less than e i Then the navigation device can classify the corresponding image-based reference position as error-free. If ΔP y Outside the acceptable range, for example, if ΔP y Greater than e i If so, the navigation device can classify the corresponding image-based reference position as incorrect.

[0090] Figure 7An example of detecting a turn is shown. Because road-related information is generally distributed in the lateral direction, estimates in the longitudinal direction are often less accurate than those in the lateral direction. If a vehicle is turning in a corner, the inaccuracy in the longitudinal direction can affect the lateral direction estimate for a predetermined (or alternatively, desired) time period before and after the turn. Lateral inaccuracies can have fatal consequences, such as estimating that the vehicle is leaving the road or entering the wrong lane. Therefore, lateral inaccuracies urgently need to be corrected.

[0091] To reduce inaccuracies in the lateral direction, navigation devices can increase the width of the acceptable range based on image information. (Reference) Figure 7 As can be seen, the acceptable range 720 after the vehicle turns is wider than the acceptable range 710 before the turn. Therefore, although the error level of the image-based reference position may be slightly higher after the turn, the image-based reference position is more likely to be used to estimate the final position. For example, the navigation device can accumulate the gyroscope output for a predetermined (or alternatively, desired) time period, and if the accumulated angle exceeds a threshold within that time period, it can determine that the driving situation corresponds to turning. If the accumulated angle falls below the threshold, the navigation device can determine that the turn has ended, and from this point in time, the acceptable range can be expanded so that the lateral position of the vehicle converges to the image-based reference position.

[0092] Figure 8 This shows an example of detecting vehicles driving at an intersection. (Reference) Figure 8 The vehicle's current estimated position 810 is marked on an HD map 800. Each point on the HD map 800 can include information about various map elements (e.g., lane boundaries, center lines, and guide signs). Therefore, map elements present near the current estimated position 810 can be verified using points on the HD map 800. The navigation device can verify whether a lane exists in the surrounding area 820 of the current estimated position 810, and when no lane exists, it can determine that the current estimated position 810 corresponds to an intersection. Image-based localization algorithms that identify the road environment can determine that the probability of error is high in intersection segments where lanes disappear or new lanes appear. The navigation device can reduce the width of an acceptable range over a predetermined (or alternative, desired) time period after passing the intersection to minimize the position estimation error at the intersection.

[0093] Figure 9 Examples of expanding the acceptable range are shown. (Reference) Figure 9In time step t2, the image-based reference position begins to deviate from the acceptable region 910, and this state is maintained until time step t4. Therefore, the image-based reference position from time step t2 to time step t4 may not be applicable when estimating the final position. If the image-based reference position is continuously ignored while the error persists, the error may become divergent, and the estimation accuracy may further decrease compared to using the image-based reference position. Therefore, if the error persists, the navigation device can incrementally (e.g., little by little) increase the width of the acceptable range to prevent the error from diverging. The navigation device can expand the acceptable region 910 from time step t2, when the image-based reference position begins to deviate from the acceptable region 910. In time step t5, the image-based reference position enters the acceptable region 920. Therefore, starting from time step t5, the navigation device can use the image-based reference position to estimate the final position.

[0094] Figure 10 An example of the process for detecting errors using heading angles is shown. Alternatively, or in addition to the aforementioned process using error levels and acceptable ranges, the navigation device may classify image-based reference positions using other processes. Figure 10 An example of a process that uses heading angles as one of these other processes is shown.

[0095] The navigation device can determine the change in reference heading angle corresponding to the image-based reference position at the current time step, based on multiple image-based reference positions corresponding to multiple time steps, including the current time step. The navigation device can compare the change in reference heading angle with the output of a gyroscope and perform error detection related to the image-based reference position at the current time step. If the difference based on the comparison is greater than a threshold, the navigation device can classify the corresponding image-based reference position as erroneous. If the difference is less than the threshold, the navigation device can classify the corresponding image-based reference position as error-free. If the error level is within an acceptable range and the difference in heading angle is less than the threshold—that is, if both valid conditions are met—the navigation device can classify the image-based reference position as error-free and can use it to estimate the current position.

[0096] refer to Figure 10 The image-based reference position p is shown for three consecutive time steps k-2 to k. k-2 to p k Here, for example, the average heading angle can be calculated according to Equation 1 below.

[0097] Equation 1:

[0098]

[0099] In equation 1, L k The latitude representing the current time step, l k L represents the longitude of the current time step. k-1 Indicates the latitude of the previous time step, and l k-1 This indicates the longitude at the previous time step. Latitude and longitude can be obtained from an image-based reference location p. k-2 to p k The coordinates are obtained from the average heading angle ψ between the current time step and the previous time step. k It can be calculated according to Equation 1. When... Figure 10 When at least three time steps are given, the average heading angle for a given time step can be calculated.

[0100] A gyroscope is one or more sensors configured to detect turns based on angular velocity. The gyroscope's output can be stored for each time step, measuring the corresponding image-based reference position, and the average heading change for a given time step can be calculated based on the stored output. The navigation device can compare the average heading change calculated from the image-based reference position with the average heading change calculated from the gyroscope output. If the difference between them is greater than a threshold, the navigation device can classify the corresponding image-based reference position (e.g., the image-based reference position of the most recent time step) as incorrect.

[0101] Figure 11 This is a flowchart illustrating an example of a vehicle positioning method. (Reference) Figure 11 The navigation device can: in operation 1110, determine a first reference position based on vehicle position information measured by the vehicle's position sensor; in operation 1120, determine a second reference position based on image information of the vehicle captured by the vehicle's camera; in operation 1130, set an acceptable range for the second reference position based on the vehicle's driving conditions; in operation 1140, compare the second reference position with the first reference position and estimate the error level of the second reference position; and in operation 1150, compare the error level of the second reference position with the acceptable range and estimate the vehicle's current position. Figures 1 to 10 The description above and the reference below Figure 12 and Figure 13 The description can be applied to the method of vehicle positioning.

[0102] Figure 12 This is a diagram illustrating an example configuration of a navigation device. (Reference) Figure 12The navigation device 1200 may include a processor 1210 and a memory 1220. The navigation device may be a vehicle, a control system, or another electronic device. The memory 1220 may be connected to the processor 1210 and may store instructions executable by the processor 1210, data to be operated by the processor 1210, and / or data processed by the processor 1210. As a non-limiting example, the memory 1220 may include various types of memory, such as non-transitory computer-readable media, for example, high-speed random access memory and / or non-volatile computer-readable storage media (e.g., at least one disk storage device, flash memory device, and other non-volatile solid-state storage devices, etc.).

[0103] Processor 1210 can execute instructions, and when those instructions are executed, cause the processor to implement the concepts discussed in this article in all possible combinations. Figures 1 to 11 and Figure 13 The description includes one or more of the operations, processes, and / or methods. For example, processor 1210 may determine a first reference position based on vehicle position information measured by a vehicle position sensor, determine a second reference position based on image information of the vehicle captured by a vehicle camera, set an acceptable range for the second reference position based on the vehicle's driving conditions, compare the second reference position with the first reference position and estimate the error level of the second reference position, and compare the error level of the second reference position with the acceptable range and estimate the current position of the vehicle. Similarly, reference... Figures 1 to 11 The descriptions and references provided above Figure 13 The description below can be applied to navigation device 1200.

[0104] Figure 13 This is a diagram illustrating an example configuration of an electronic device. (Reference) Figure 13 Electronic device 1300 may include: processor 1310, memory 1320, camera 1330, sensor 1340, control system 1350, storage device 1360, input device 1370, output device 1380, and network interface 1390. The components of electronic device 1300 can communicate with each other via communication bus 1305.

[0105] Furthermore, while the processor 1310, memory 1320, camera 1330, sensor 1340, control system 1350, storage device 1360, input device 1370, output device 1380, network interface 1390, and communication bus 1305 are referred to in the singular, the examples also include various examples in which each of the processor 1310, memory 1320, camera 1330, sensor 1340, control system 1350, storage device 1360, input device 1370, output device 1380, network interface 1390, and communication bus 1305 exists in the plural or singular in all various combinations (e.g., in the example where the electronic device is a vehicle). As another example, the electronic device 1300 may correspond to a vehicle control device, apparatus, or system and may perform various vehicle-related operations, such as driving function control and additional function control. Furthermore, the electronic device 1300 may structurally and / or functionally include... Figure 1 The navigation device 100 can be implemented as a vehicle (e.g., an autonomous vehicle), and all other components of the vehicle or parts of the vehicle are taken as non-limiting examples.

[0106] Electronic device 1300 can estimate the vehicle's position through sensor-based localization and image-based localization, and can perform subsequent operations based on the estimated position, such as driving function control in an autonomous vehicle.

[0107] Processor 1310 can execute functions and instructions that will be executed in electronic device 1300. For example, processor 1310 can process instructions stored in memory 1320 and / or storage device 1360. In one example, processor 1310 and memory 1320 can be coupled with... Figure 12 The processor 1210 and memory 1220 correspond to each other. In one example, the processor 1310 can estimate the vehicle's position through sensor-based localization and / or image-based localization, and can generate control commands associated with the vehicle's movement based on the estimated position. The processor 1310 is configured to execute the above-mentioned reference. Figures 1 to 12 The one or more operations, processes and / or methods described.

[0108] Memory 1320 may store data used for vehicle positioning. Memory 1320 may include computer-readable storage media and / or computer-readable storage devices. Memory 1320 may store instructions to be executed by processor 1310, and may store relevant information during the execution of additional software and / or applications by electronic device 1300.

[0109] Camera 1330 can capture video images and / or still images, such as photographs. For example, camera 1330 may include one or more cameras 1330 of a vehicle and can capture the corresponding surrounding environment of the vehicle in a predetermined direction (e.g., in front of, behind, above, and / or below the vehicle) and can generate corresponding image information related to the surrounding environment of the vehicle. In one example, camera 1330 can provide a 3D image including depth information of an object.

[0110] Sensor 1340 can sense information associated with electronic device 1300, such as visual, auditory, and tactile information. For example, sensor 1340 may include a position sensor, an ultrasonic sensor, a radar sensor, and a LiDAR (Light Detection and Ranging) sensor. Control system 1350 can control the vehicle in response to control commands from processor 1310. For example, control system 1350 can physically control various vehicle-related functions, including: driving functions, such as vehicle acceleration, steering, and actuation; and additional functions, such as opening and closing doors, opening and closing windows, and activating airbags.

[0111] Storage device 1360 may include computer-readable storage media and / or computer-readable storage devices. In one example, storage device 1360 may store a larger amount of information than memory 1320 and may store information for a longer period of time. For example, as a non-limiting example, storage device 1360 may include magnetic hard disks, optical disks, flash memory, floppy disks, or other types of non-volatile memory. One or both of storage device 1360 and memory 1320 may store HD maps.

[0112] Input device 1370 can receive input from a user using typical input schemes such as keyboard and mouse, as well as newer input schemes such as touch input, voice input, and image input. For example, input device 1370 may include other devices capable of detecting input from a keyboard, touchscreen, microphone, user, steering wheel, or other in-vehicle input and transmitting the detected input to electronic device 1300.

[0113] Output device 1380 can provide the output of electronic device 1300 to a user through visual, auditory, or tactile channels. For example, output device 1380 may include, for example, a display, touchscreen, speaker, vibration generator, or other equipment capable of providing output to a user. Network interface 1390 can communicate with external devices over a wired or wireless network. The output device can also provide the user with augmented reality information about the vehicle's progress, such as an overlay with the user's view through the vehicle's windshield, where the progress includes the vehicle's estimated and / or final position.

[0114] The devices, navigation devices, processors, memories, image sensors, cameras, 3D cameras, depth sensors, position sensors, GPS sensors, gyroscopes, other sensors, control systems, storage devices, input devices, output devices, network interfaces, communication buses, modules, equipment, and other components described herein are implemented through hardware components. Examples of hardware components that may be used to perform the operations described herein, where appropriate, include controllers, sensors, generators, drivers, memories, comparators, arithmetic logic units, adders, subtractors, multipliers, dividers, integrators, and any other electronic components configured to perform the operations described herein. In other examples, one or more of the hardware components used to perform the operations described herein are implemented by computing hardware (e.g., by one or more processors or computers). A processor or computer may be implemented by one or more processing elements (e.g., logic gate arrays, controllers and arithmetic logic units, digital signal processors, microcomputers, programmable logic controllers, field-programmable gate arrays, programmable logic arrays, microprocessors, or any other device or combination of devices configured to respond to and execute instructions in a defined manner to achieve a desired result). In one example, the processor or computer includes or is connected to one or more memories storing instructions or software executed by the processor or computer. Hardware components implemented by the processor or computer can execute instructions or software, such as an operating system (OS) and one or more software applications running on the OS, to perform the operations described in this application. Hardware components can also access, manipulate, process, create, and store data in response to the execution of instructions or software. For brevity, the singular terms "processor" or "computer" may be used in the description of the examples described in this application, but in other examples multiple processors or computers may be used, or a processor or computer may include multiple processing elements, or multiple types of processing elements, or both. For example, a single hardware component or two or more hardware components may be implemented by a single processor, or two or more processors, or a processor and a controller. One or more hardware components may be implemented by one or more processors, or a processor and a controller, and one or more other hardware components may be implemented by one or more other processors, or another processor and another controller. One or more processors, or a processor and a controller, may implement a single hardware component, or two or more hardware components. The hardware components can have any one or more different processing configurations, examples of which include single processor, discrete processor, parallel processor, single instruction single data (SISD) multiprocessing, single instruction multiple data (SIMD) multiprocessing, multiple instruction single data (MISD) multiprocessing, and multiple instruction multiple data (MIMD) multiprocessing.

[0115] Perform the operations described in this application Figures 1 to 13 The methods illustrated are performed by computing hardware (e.g., one or more processors or computers implemented as described above, executing instructions or software to perform the operations performed by the methods described in this application). For example, a single operation or two or more operations may be performed by a single processor, or two or more processors, or a processor and a controller. One or more operations may be performed by one or more processors, or a processor and a controller, and one or more other operations may be performed by one or more other processors, or another processor and another controller. One or more processors, or a processor and a controller, may perform a single operation or two or more operations.

[0116] Instructions or software for controlling computing hardware (e.g., one or more processors or computers) to implement hardware components and perform the methods described above can be written as computer programs, code segments, instructions, or any combination thereof, for individually or collectively instructing or configuring one or more processors or computers to operate as machines or special-purpose computers to perform the operations performed by the hardware components and methods described above. In one example, the instructions or software include machine code that is directly executed by one or more processors or computers, such as machine code generated by a compiler. In another example, the instructions or software include higher-level code that is executed by one or more processors or computers using an interpreter. The instructions or software can be written using any programming language based on the block diagrams and flowcharts shown in the accompanying drawings and the corresponding description used herein (which discloses algorithms for performing the operations performed by the hardware components and methods described above).

[0117] Instructions or software for controlling computing hardware (e.g., one or more processors or computers) to implement hardware components and perform the methods described above, along with any associated data, data files, and data structures, may be recorded, stored, or fixed on or in one or more non-transitory computer-readable storage media. Examples of non-transitory computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage devices, hard disk drives (HDDs), solid-state drives (SSDs), flash memory, card-type memory (e.g., multimedia cards or microcards (e.g., Secure Digital (SD) or Extreme Digital (XD))), magnetic tape, floppy disks, magneto-optical data storage devices, optical data storage devices, hard disks, solid-state drives, and any other devices configured to: store instructions or software and any associated data, data files, and data structures in a non-transitory manner, and provide instructions or software and any associated data, data files, and data structures to one or more processors or computers, enabling said one or more processors or computers to execute said instructions. In one example, the instructions or software and any associated data, data files, and data structures are distributed across a networked computer system, causing one or more processors or computers to store, access, and execute said instructions and software and any associated data, data files, and data structures in a distributed manner.

[0118] Although this disclosure includes specific examples, it will be apparent upon understanding the disclosure of this application that various changes in form and detail may be made to these examples without departing from the spirit and scope of the claims and their equivalents. The examples described herein should be considered descriptive only and not for limiting purposes. The description of features or aspects in each example is intended to apply to similar features or aspects in other examples. Suitable results may be achieved if the described techniques are performed in a different order and / or if components in the described system, architecture, device, or circuit are combined in a different manner and / or replaced or supplemented by other components or their equivalents.

Claims

1. A processor-implemented method, the method comprising: A first reference position is determined based on the vehicle's position information measured using the vehicle's position sensors; A second reference position of the vehicle is determined based on image information of the vehicle captured by the vehicle's camera; An acceptable range for the second reference position is set based on the vehicle's driving conditions; The second reference position is compared with the first reference position, and the error level of the second reference position is estimated. as well as The error level of the second reference position is compared with the acceptable range, and the current position of the vehicle is estimated. The acceptable range for the second reference position based on the vehicle's driving conditions includes: determining the driving conditions from multiple driving conditions, including: a first driving condition where the vehicle is driving at an intersection, and a second driving condition where the vehicle is turning. The setting of the acceptable range includes setting the acceptable range for the second driving situation to be wider than the acceptable range set for the first driving situation.

2. The method according to claim 1, wherein, Determining the second reference position includes: determining the second reference position based on the geometric information of the lane boundary included in the image information.

3. The method according to claim 1, wherein, The second reference location includes one or both of the following: information about the lane to which the vehicle belongs, and information about the specific location of the vehicle in the lane to which it belongs.

4. The method according to claim 1, wherein, Setting the acceptable range includes selectively adjusting the width of the acceptable range based on the driving conditions.

5. The method according to claim 1, wherein, Estimating the current position includes: excluding the second reference position from consideration when estimating the current position of the vehicle in response to an error level of the second reference position being outside the acceptable range.

6. The method according to claim 1, wherein, The estimation of the current position includes: In response to the error level of the second reference position being outside the acceptable range, the first reference position is estimated as the current position of the vehicle; and In response to the error level of the second reference position being within the acceptable range, the new position estimated based on the weighted sum of the second reference position and the first reference position is estimated as the current position of the vehicle.

7. The method according to claim 1, wherein, Determining the error level includes: determining the error level of the second reference position based on the distance between the second reference position and the first reference position.

8. The method according to claim 1, further comprising: Setting another acceptable range for another second reference position in a subsequent time step includes: when the second reference position is outside the acceptable range, setting the width of the other acceptable range to be wider than the width of the acceptable range.

9. The method according to claim 1, further comprising: Based on multiple second reference positions corresponding to multiple previous time steps, the change in reference heading angle corresponding to the second reference position is determined. The estimation of the current position includes estimating the current position of the vehicle by further considering the comparison between the output of the gyroscope and the determined change in the reference heading angle.

10. A non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to perform the method according to claim 1.

11. A positioning device, comprising: One or more processors are configured as follows: A first reference position is determined based on the vehicle's position information measured using the vehicle's position sensors; A second reference position of the vehicle is determined based on image information of the vehicle captured by the vehicle's camera; An acceptable range for the second reference position is set based on the vehicle's driving conditions; The second reference position is compared with the first reference position, and the error level of the second reference position is estimated. as well as The error level of the second reference position is compared with the acceptable range, and the current position of the vehicle is estimated. Specifically, regarding setting an acceptable range for the second reference position based on the vehicle's driving conditions, the one or more processors are configured to: determine the driving conditions from a plurality of driving conditions, including: a first driving condition where the vehicle is driving at an intersection, and a second driving condition where the vehicle is turning; and Wherein, in setting the acceptable range, the one or more processors are configured to: set the acceptable range for the second driving situation to be wider than the acceptable range set for the first driving situation.

12. The apparatus according to claim 11, wherein, For estimating the error level of the second reference position, the processor is configured to determine the error level based on the distance between the second reference position and the first reference position.

13. The apparatus according to claim 11, wherein, For estimating the current position of the vehicle, the processor is configured to: In response to the error level of the second reference position being outside the acceptable range, the first reference position is estimated as the current position of the vehicle; as well as In response to the error level of the second reference position being within the acceptable range, the new position estimated based on the weighted sum of the second reference position and the first reference position is estimated as the current position of the vehicle.

14. The apparatus according to claim 11, wherein, The device is a vehicle that further includes: the camera; the position sensor; and a control system configured to control the vehicle based on the current position.

15. The apparatus according to claim 11, wherein, The processor is further configured to: set another acceptable range for another second reference position in a subsequent time step, including: when the second reference position is outside the acceptable range, setting the width of the other acceptable range to be wider than the width of the acceptable range.

16. The apparatus of claim 11, further comprising: A memory storing instructions, when the instructions are executed by the processor, configuring the processor to perform the following operations: determining a first reference position, determining a second reference position, setting the acceptable range, comparing the second reference position with the first reference position and estimating the error level, and comparing the error level of the second reference position with the acceptable range and estimating the current position.

17. A positioning device, comprising: The processor is configured as follows: A first reference position is determined based on the vehicle's position information measured using the vehicle's position sensors; A second reference position of the vehicle is determined based on image information of the vehicle captured by the vehicle's camera; An acceptable range for the second reference position is set based on the vehicle's driving conditions; The second reference position is compared with the first reference position, and the error level of the second reference position is estimated. The error level of the second reference position is compared with the acceptable range, and the current position of the vehicle is estimated. as well as Based on the vehicle's current location, control commands associated with the vehicle's movement are generated. as well as The control system is configured to control the vehicle in response to the control command. Specifically, regarding setting an acceptable range for the second reference position based on the vehicle's driving conditions, the processor is configured to: determine the driving conditions from a plurality of driving conditions, including: a first driving condition where the vehicle is driving at an intersection, and a second driving condition where the vehicle is turning; and Specifically, regarding the setting of the acceptable range, the processor is configured to set the acceptable range for the second driving situation to be wider than the acceptable range set for the first driving situation.

18. The apparatus according to claim 17, wherein, The device is a vehicle and also includes the camera.

19. The apparatus according to claim 17, wherein, For estimating the error level of the second reference position, the processor is configured to determine the error level based on the distance between the second reference position and the first reference position.

20. The apparatus according to claim 17, wherein, For estimating the current position of the vehicle, the processor is configured to: In response to the error level of the second reference position being outside the acceptable range, the first reference position is estimated as the current position of the vehicle; as well as In response to the error level of the second reference position being within the acceptable range, the new position estimated based on the weighted sum of the second reference position and the first reference position is estimated as the current position of the vehicle.

21. A processor-implemented method, the method comprising: A first reference position is determined based on the vehicle's position information measured using the vehicle's position sensors; A second reference position of the vehicle is determined based on image information of the vehicle captured by the vehicle's camera; Based on the determination of whether the second reference position is an erroneous position, a choice is made between estimating the current position of the vehicle based on the first reference position and the second reference position and estimating the current position of the vehicle based on the first reference position; as well as The current position is estimated based on the result of the selection. The determination of whether the second reference position is an erroneous position is based on an acceptable range depending on the current driving conditions of the vehicle. The current driving status of the vehicle includes: a first driving situation where the vehicle is traveling at an intersection, and a second driving situation where the vehicle is turning. The acceptable range for the second driving situation is set to be wider than the acceptable range set for the first driving situation.

22. The method according to claim 21, wherein, The determination of whether the second reference position is an erroneous position is further based on whether the estimation error of the second reference position is within the acceptable range.

23. The method according to claim 22, wherein, The acceptable range is set differently for at least two different driving situations, including setting the acceptable range wider in a turning situation compared to an intersection situation.

24. The method according to claim 21, wherein, Determining whether the second reference position is an erroneous position includes considering at least one or both of the following: whether the second reference position determined by the previous time step was determined to be erroneous, and a comparison between the determined change in the reference heading angle corresponding to the second reference position and the output of the vehicle's gyroscope.

Images