Reversing driving assisting method and device

Abstract

The invention provides a backing-up driving assisting method and a backing-up driving assisting device. The driving assistance method and apparatus includes: storing a driving path of a vehicle based on forward driving of the vehicle; in response to the vehicle running in a reverse direction; correcting a position of the vehicle based on at least one of sensor information measured by an internal sensor of the vehicle, global positioning system (GPS) information of the vehicle, or feature information obtained by image information of the vehicle; and assisting the backward driving of the vehicle based on the stored driving path and the corrected position of the vehicle.

Description

Technical Field

[0001] This disclosure relates to methods and apparatus for driving assistance of vehicles, and more specifically, to methods and apparatus for reversing driving assistance based on information obtained during forward driving. Background Technology

[0002] The materials described in this section are only background information for this embodiment and do not constitute related technology.

[0003] When drivers must navigate narrow roads or over obstacles, modern vehicles use sensors to calculate the amount of free space around the vehicle and generate an avoidance route. The vehicle supports autonomous reversing capability. It can store the path the driver has already traveled a certain distance forward. Based on the stored path, the vehicle generates a reversing path and performs autonomous reversing maneuvering along that path.

[0004] However, existing technologies rely on internal vehicle sensors to estimate the vehicle's position, and therefore position estimation errors can accumulate as the vehicle moves. This can make it difficult to reverse along the forward path.

[0005] Accumulated errors can be corrected using GPS or communication information, but this information may be difficult to use in narrow roads or underground parking lots. To compensate for this, rear driving assistance methods based on visual simultaneous localization and mapping (V-SLAM) have been proposed, but further reduction in computational load may be cost-effective. Summary of the Invention

[0006] The purpose of this disclosure is to provide a driving assistance method and apparatus that are improved compared to existing methods and apparatuses.

[0007] A vehicle's reversing assist system assists in reversing based on a map stored during forward driving. To prevent the accumulation of position estimation errors during reversing, a method and apparatus are provided for performing position correction based on map information pre-acquired during forward driving and feature information acquired in real time during reversing.

[0008] A vehicle's reversing assist system stores the vehicle's driving path while moving forward and assists in reversing based on the stored driving path. To store a more accurate driving path, methods and apparatus are provided to compensate for time delays in the vehicle's Global Positioning System (GPS) information by utilizing stored sensor information.

[0009] The objectives achieved in the implementation are not limited to the technical objectives described above, and those skilled in the art will clearly understand from the following description other objectives not stated herein.

[0010] This disclosure provides a driving assistance method and apparatus.

[0011] According to one aspect of this disclosure, a driving assistance method includes: storing a driving path of the vehicle based on forward driving; responding to reverse driving of the vehicle; correcting the position of the vehicle based on at least one of sensor information measured by internal sensors of the vehicle, global positioning system (GPS) information of the vehicle, or feature information obtained through image information of the vehicle; and assisting the reverse driving of the vehicle based on the stored driving path and the corrected position of the vehicle.

[0012] According to another aspect of this disclosure, a driving assistance device includes: at least one processor; and at least one memory operatively connected to the at least one processor and storing instructions that, when executed, cause the at least one processor to perform a specific operation, wherein the specific operation includes storing a driving path of the vehicle based on forward driving of the vehicle, correcting the position of the vehicle based on at least one of sensor information measured by internal sensors of the vehicle, global positioning system (GPS) information of the vehicle, or feature information obtained through image information of the vehicle, and assisting the reverse driving of the vehicle based on the stored driving path and the corrected position of the vehicle.

[0013] According to another aspect of this disclosure, a computer-readable non-volatile storage medium is provided, including at least one computer program that causes at least one processor to perform operations, said operations including: storing a driving path of the vehicle based on forward driving of the vehicle; correcting the position of the vehicle based on at least one of sensor information measured by internal sensors of the vehicle, global positioning system (GPS) information of the vehicle, or feature information obtained through image information of the vehicle when the vehicle is driving in reverse, and assisting the reverse driving of the vehicle based on the stored driving path and the corrected position of the vehicle.

[0014] In this method and apparatus, correcting the position of a vehicle may include: applying a first weight to sensor information, applying a second weight to GPS information, and applying a third weight to feature information based on input state information, and correcting the position of the vehicle based on the first weight, the second weight, and the third weight.

[0015] In this method and apparatus, a first weight can be determined based on the matching degree between sensor information and vehicle location information, a second weight can be determined based on the matching degree between GPS information and vehicle location information, and a third weight can be determined based on the matching degree between feature information and vehicle location information.

[0016] In the method and apparatus, the method may further include: extracting local map information within a specific range from the vehicle's current position from the entire map information stored based on the vehicle's forward movement, wherein correcting the vehicle's position may include: calculating a position correction value for the vehicle based on points of the feature information and points of the local map information; and correcting the vehicle's position based on the position correction value.

[0017] In this method and apparatus, the total map information may include first map information generated based on the vehicle's front camera, second map information generated based on the vehicle's rear camera, third map information generated based on the vehicle's left camera, and fourth map information generated based on the vehicle's right camera.

[0018] In this method and apparatus, local map information can be extracted sequentially from the first map information, the second map information, the third map information, and the fourth map information.

[0019] In this method and apparatus, calculating the position correction value may include: calculating a first position correction value based on points of first feature information obtained from a front camera and points of first local map information extracted from first map information; calculating a second position correction value based on points of second feature information obtained from a rear camera and points of second local map information extracted from the second map information; calculating a third position correction value based on points of third feature information obtained from a left camera and points of third local map information extracted from the third map information; and calculating a fourth position correction value based on points of fourth feature information obtained from a right camera and points of fourth local map information extracted from the fourth map information.

[0020] In this method and apparatus, the overall map information may include information about all trajectory indices stored based on vehicle forward movement and information about all points mapped to all trajectory indices, and the extraction of local map information may include extracting information from the overall map information about trajectory indices that are mapped to a specific range of values ​​having a trajectory index corresponding to the current location.

[0021] In this method and apparatus, a driving path can be generated based on the vehicle's location, which is based on at least one of sensor information during forward driving, measurements taken by the vehicle's internal sensors, or forward GPS information of the vehicle.

[0022] In the method and apparatus, the method may further include calculating the vehicle's position coordinates corresponding to the delay time based on the vehicle's forward travel, and compensating for at least one of forward GPS information or feature information based on the vehicle's position coordinates, wherein the travel path may be generated based on the compensated forward GPS information.

[0023] The aspects disclosed herein are merely some exemplary embodiments of the present disclosure, and those skilled in the art can deduce and understand various embodiments reflecting the technical features of the present disclosure based on the specific embodiments of the present disclosure described below. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating a position correction method related to a driving assistance method according to an embodiment.

[0025] Figure 2 An example of generating the entire map during forward travel is shown.

[0026] Figure 3 The entire map is shown based on the forward driving storage.

[0027] Figure 4 An embodiment of a vehicle that controls reverse movement based on a driving assistance device is shown.

[0028] Figure 5 The principle of correcting the vehicle's position based on the control of driving assistance devices is shown.

[0029] Figure 6 An example of a travel path with compensated delay time is shown.

[0030] Figure 7 A driving assistance method according to an embodiment is shown.

[0031] Figure 8 A driving assistance device according to an embodiment is shown. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0033] However, detailed descriptions of well-known functions or configurations that might obscure the essence of this disclosure are omitted in the following description and accompanying drawings. Furthermore, in all the drawings, the same components are denoted by the same reference numerals.

[0034] The terms or words used in the following description and drawings should not be construed as limited to their common or dictionary meanings, but rather as meanings and concepts consistent with the technical concept of this disclosure, based on the inventors' appropriate definition of the terms to best interpret their own inventions. Therefore, the embodiments described in this specification and the configurations shown in the drawings are merely the most desirable embodiments of this disclosure and do not represent all the technical concepts of this disclosure. Therefore, it should be understood that various equivalents and modified embodiments may exist that can replace them at the time of filing this application.

[0035] 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 this disclosure pertains. Terms as defined in commonly used dictionaries shall be interpreted as having a meaning consistent with their meaning in the context of the relevant field and shall not be interpreted in an idealized or overly formalized sense, unless expressly defined in this application.

[0036] Terms including ordinal numbers such as first and second are used to describe various components and are used only to distinguish one component from another, and are not used to limit the components. For example, a second component may be named as a first component without departing from the scope of this disclosure, and similarly, a first component may be named as a second component.

[0037] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. Unless the context clearly indicates otherwise, singular expressions include plural expressions. It should be understood that terms such as “comprising” or “having” as used in this specification are intended to specify the presence of features, quantities, steps, operations, components, parts, or combinations thereof described in this specification, but do not preclude the possibility of the presence or addition of one or more other features, quantities, steps, operations, components, parts, or combinations thereof.

[0038] Terms such as “unit,” “device,” and “module” described in the specification refer to a unit that performs at least one function or operation, which may be implemented by hardware, software, or a combination of hardware and software. The terms “a” (or “an”), “an,” “the,” and similar related terms may be used in the context of describing this disclosure (especially in the context of the following claims) to include both the singular and plural forms, unless otherwise indicated herein or clearly contradicted by the context.

[0039] In the various embodiments disclosed herein, " / " and "," should be interpreted as indicating "and / or". For example, "A / B" may mean "A and / or B". "A, B" may mean "A and / or B". "A / B / C" may mean "at least one of A, B and / or C". "A, B, C" may mean "at least one of A, B and / or C".

[0040] In various embodiments of this disclosure, "or" should be interpreted as meaning "and / or". For example, "A or B" may include "A only", "B only", and / or "both A and B". In other words, "or" should be interpreted as meaning "additionally or alternatively".

[0041] In addition to the terms mentioned above, specific terms used in the following description are provided to aid in understanding this disclosure, and the use of these specific terms may be changed to other forms without departing from the technical spirit of this disclosure.

[0042] Embodiments within the scope of this disclosure include computer-readable media having or transmitting computer-executable instructions or data structures stored on a computer-readable medium. A computer-readable medium can be any available medium that will be accessed by a general-purpose or special-purpose computer system. For example, a computer-readable medium may include (but is not limited to) physical storage media such as random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), CD-ROM or other optical disc storage devices, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be used to store or carry program code in the form of computer-executable instructions, computer-readable instructions, or data structures and is accessible by a general-purpose or special-purpose computer system.

[0043] Each block may represent a module, segment, or portion of code containing one or more executable instructions for performing a specific logical function. It should be noted that in some alternative implementations, the functions mentioned in the blocks may not occur in a sequential order. For example, two blocks shown consecutively may actually be executed substantially synchronously, or these blocks may sometimes be executed in reverse order, depending on their respective functions.

[0044] In describing the embodiments of this disclosure in detail, the main subject matter claimed in this specification will be directed primarily to embodiments of a particular system; however, it will be apparent to those skilled in the art that this disclosure can be applied to other communication systems and services with similar technical backgrounds without significantly departing from the scope disclosed in this specification.

[0045] In the following, a driving assistance method and apparatus according to embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0046] Figure 1 This is a flowchart illustrating a position correction method related to a driving assistance method according to an embodiment.

[0047] See Figure 1 Position correction can be performed via an extended Kalman filter (EKF). The EKF linearizes the nonlinear system to analyze and predict the vehicle's current position and velocity. More specifically, the EKF interprets and predicts the vehicle's current position coordinates (x, y) and heading angle.

[0048] EKF's predictive operation predicts the vehicle's position based on the vehicle's equation of motion. The correction operation corrects the vehicle's position based on sensor measurements.

[0049] For these operations, the driving assistance device 10 can obtain sensor information based on sensors installed inside the vehicle. For example, the driving assistance device 10 can calculate the vehicle's speed and yaw rate (①) based on wheel pulse sensors and motor drive power steering angle (MDPS) sensors installed in the vehicle. That is, the sensor information may include information about the vehicle's speed or information about the vehicle's yaw rate.

[0050] The driving assistance device 10 can obtain sensor information based on sensors installed inside the vehicle when the vehicle is moving forward, or it can obtain sensor information based on sensors installed inside the vehicle when the vehicle is moving backward. That is, the driving assistance device 10 can calculate the vehicle's position based on sensor information measured when the vehicle is moving forward, or it can calculate the vehicle's position based on sensor information measured when the vehicle is moving backward.

[0051] In this scenario, the driving assistance device 10 can generate and store a driving path for the vehicle based on the vehicle's position information calculated when the vehicle is moving forward, or it can correct the vehicle's current position based on the vehicle's position information calculated when the vehicle is reversing. In other words, the driving assistance device 10 can generate a driving path for the vehicle using sensor information obtained when the vehicle is moving forward, or it can correct the vehicle's position in real time when the vehicle is reversing by using sensor information obtained when the vehicle is reversing.

[0052] The driving assistance device 10 can obtain the vehicle's Global Positioning System (GPS) information. For example, the driving assistance device 10 can obtain information about the vehicle's two-dimensional (2D) coordinates and azimuth angle through a Global Navigation Satellite System (GNSS) module installed in the vehicle. That is, the GPS information can include coordinate information (x, y) and azimuth angle information about the vehicle's position (②).

[0053] When the vehicle is moving forward, the driving assistance device 10 can obtain the vehicle's GPS information (hereinafter, "forward GPS information") through a GNSS module or the like, or when the vehicle is moving backward, it can obtain the vehicle's GPS information through a GNSS module or the like. That is, the driving assistance device 10 can calculate the vehicle's position based on the forward GPS information measured when the vehicle is moving forward, or it can calculate the vehicle's position based on the GPS information measured when the vehicle is moving backward.

[0054] In this scenario, the driving assistance device 10 can generate and store a driving path for the vehicle based on position information calculated while the vehicle is moving forward, or it can correct the vehicle's current position based on position information calculated while the vehicle is reversing. In other words, the driving assistance device 10 can generate a driving path for the vehicle using GPS information obtained while the vehicle is moving forward, or it can correct the vehicle's position in real time while the vehicle is reversing by using GPS information obtained while the vehicle is reversing.

[0055] The driving assistance device 10 can perform delay compensation (②) on information obtained via the GNSS module. More specifically, the driving assistance device 10 can perform delay compensation on information obtained via the GNSS module based on information measured by sensors installed inside the vehicle. This will refer to... Figure 6 Detailed description.

[0056] The driving assistance device 10 can acquire spatial exploration (SD) data through a camera installed in the vehicle. While the vehicle is moving forward, the driving assistance device 10 can generate an SD map based on the acquired SD data.

[0057] Even during assisted reverse driving, the driving assistance device 10 can acquire SD data via a camera. The driving assistance device 10 can perform alignment (③) based on the SD map generated during forward driving and the SD data acquired during reverse driving. As a result of the alignment, the vehicle's position information can be obtained in the form of 2D coordinates including {X, Y} and the vehicle's heading.

[0058] That is, the driving assistance device 10 can correct the vehicle's position when the vehicle is reversing based on sensor information obtained from the vehicle's internal sensors, the vehicle's GPS information, and image information obtained from a camera (hereinafter, feature information). More specifically, the vehicle's position can be corrected based on sensor information, GPS information, and feature information obtained via EKF. In this case, the obtained sensor information, GPS information, and feature information can be reflected by weights applied respectively during the EKF correction.

[0059] A first weighting value can be assigned to the sensor information based on the degree of matching between the vehicle's position measured by the sensor information and the actual vehicle's position. The sensor information can also be given a first weighting based on the presence of GPS information and feature information. A second weighting value can be assigned to the GPS information based on the degree of matching between the vehicle's position measured by the GPS information and the actual vehicle's position. A third weighting value can be assigned to the feature information based on the degree of matching between the vehicle's position measured by the sensor information and the actual vehicle's position. In this case, the first, second, and third weights can have various values ​​depending on the input state information, and can be correlated with each other and have relative values.

[0060] That is, for example, when both the GPS information and feature information available from the vehicle are uncertain, the first weight can have a relatively higher value than the second and third weights. For example, in open areas where the feature information obtained through image information is uncertain, or at night when the accuracy of the image information is low, the third weight can have a relatively lower value than the first and second weights.

[0061] Alternatively, for example, when all sensor information, GPS information, and feature information are available, the third weight, second weight, and first weight can have higher values ​​in that order. That is, the weights can be assigned according to the order of sensor information, GPS information, and feature information closest to the vehicle's current location.

[0062] Therefore, the driving assistance method and apparatus according to the embodiments have the effect of efficiently correcting the vehicle's position according to the surrounding environment when the vehicle is driving in reverse.

[0063] Figure 2 An example of generating the entire map during forward travel is shown.

[0064] See Figure 2 Whenever the vehicle travels a distance greater than or equal to (or exceeding) a certain distance, the vehicle's current position coordinates, along with the trajectory index, are stored in a buffer. Figure 2 In this example, a specific distance is 20cm. The driving assistance device 10 can increment the trajectory index value by 1 each time the vehicle moves a distance exceeding 20cm, map the vehicle's position coordinates to each trajectory index, and store the position coordinates in a buffer.

[0065] See Figure 2 The entire map information can include map data. Map data can contain 2D coordinate information of features mapped to the trajectory index. The 2D coordinates of features mapped to the trajectory index can be called points.

[0066] The entire map data corresponding to the overall map information includes information about the entire trajectory index stored based on vehicle movement, as well as information about the points mapped to the entire trajectory index. For local map extraction, an array corresponding to the trajectory indices is selected from the array of the entire map data; the values ​​of these trajectory indices are within a certain range from the trajectory index value corresponding to the vehicle's current position. Therefore, information about the points mapped to the trajectory indices, whose values ​​are within a specific range of the trajectory index values ​​corresponding to the vehicle's current position, is extracted.

[0067] Figure 2The example shown has a trajectory index value of 30 corresponding to the vehicle's current position, with a trajectory index interval of 20cm, and a range of 5m set for each of the forward and reverse directions. Converting the 5m range into the number of trajectory indices results in 25 in each of the forward and reverse directions. Therefore, the driving assistance device 10 extracts information about the points mapped to the corresponding trajectory indices within the range of trajectory indices 5 to 55.

[0068] Figure 3 The entire map stored based on forward travel is displayed.

[0069] See Figure 3 The entire map information includes front camera map information (first map information) generated based on the vehicle's front camera, rear camera map information (second map information) generated based on the vehicle's rear camera, left camera map information (third map information) generated based on the vehicle's left camera, and right camera map information (fourth map information) generated based on the vehicle's right camera.

[0070] Figure 4 An embodiment of controlling the reverse movement of a vehicle based on the driving assistance device 10 is shown.

[0071] See Figure 4 The driving assistance device 10 controls the reverse driving in the direction of the decrease of the trajectory index mapped to the vehicle's position coordinates.

[0072] When the vehicle is reversing, the driving assistance device 10 extracts local map information within a certain range from the vehicle's current position from the overall map information. Local map extraction processing can be performed sequentially on the first map information, the second map information, the third map information, and the fourth map information. The local map information extracted from the first map information can be referred to as the first local map information, the local map information extracted from the second map information can be referred to as the second local map information, the local map information extracted from the third map information can be referred to as the third local map information, and the map information extracted from the fourth map information can be referred to as the fourth local map information.

[0073] Figure 5 The principle of correcting the vehicle's position based on the control of the driving assistance device 10 is shown.

[0074] After extracting a local map from the entire map, an alignment process can be performed to match the local map with feature information.

[0075] Similar to local map extraction, alignment processing can be performed in four directions. Therefore, when obtaining feature information from image information collected by the cameras during reverse driving, the driving assistance device 10 can obtain feature information from the front camera (first feature information), the rear camera (second feature information), the left camera (third feature information), and the right camera (fourth feature information). The feature information may include, for example, information obtained through… Figure 1 The SD data described.

[0076] Position correction values ​​can also be calculated for four directions. Therefore, the driving assistance device 10 can calculate a first position correction value based on the first feature information and the first local map information, calculate a second position correction value based on the second feature information and the second local map information, calculate a third position correction value based on the third feature information and the third local map information, and calculate a fourth position correction value based on the fourth feature information and the fourth local map information.

[0077] In the alignment process, the driving assistance device 10 matches the points of the acquired feature information with the points of the local map information to generate matching pairs. In this specification, the feature information or the points of the feature information may be referred to as the source, and the local map information or the points of the local map information may be referred to as the destination.

[0078] The driving assistance device 10 matches the points in the local map information with the points closest to each point in the feature information. Then, the driving assistance device 10 rotates and moves the points in the feature information to obtain a matrix value that minimizes the Euclidean distance between the matched pairs.

[0079] The amount of rotation and movement of points in the feature information represents the current positioning error. The driving assistance device 10 can output the final position recognition result by adding the positioning result calculated based on the feature information of the position before rotation and movement to the current positioning result value.

[0080] See Figure 5 The driving assistance device 10 will use local map information (third local map information and fourth local map information) to... Figure 5 The black dots are exported as points, and based on the feature information (third feature information and fourth feature information) they are... Figure 5 The red dots are derived as points. The driving assistance device 10 derives green dots as compensation coordinates for each side. The driving assistance device 10 determines the updated coordinates based on the initial error calculated based on the red dots and the final error calculated based on the green dots. Specifically, in this case, the updated coordinates can utilize, as shown in [see...] Figure 1 The weights of the described applications are used to reflect this.

[0081] Figure 6 An example of a travel path with compensated delay time is shown.

[0082] See Figure 1 and Figure 6 The driving assistance device 10 can compensate for the time delay of GPS information obtained through the Global Navigation Satellite System (GNSS) module installed in the vehicle. In this case, the compensated GPS information corresponds to the forward GPS information obtained when the vehicle is moving forward.

[0083] Typically, due to a combination of factors (such as delays in signal propagation, delays in receiver processing of satellite signals, or delays in data transmission between the receiver and data processing device), time delays can occur in the values ​​measured by the GNSS module. This results in a discrepancy between the actual time the GNSS data is measured and the time the corresponding GNSS data is received. In this situation, due to the time delay in the GNSS data, the actual path traveled by the vehicle differs from the stored path.

[0084] To address this issue, the driving assistance device 10 can generate a driving path stored when the vehicle is moving forward, based on time-delay-compensated GNSS data. That is, the driving assistance device 10 can generate a driving path where errors caused by time delays are corrected, by generating a driving path based on time-delay-compensated GNSS data, and when the vehicle is reversing, the driving assistance device 10 can assist the vehicle in reversing based on the corresponding driving path.

[0085] More specifically, the driving assistance device 10 can calculate the positioning change (Δx) corresponding to the delay time based on data measured by the vehicle's internal sensors. VPE Δy VPE , and Δψ VPE The driving assistance device 10 can use data measured from GPS, cameras, etc., to compensate for the calculated change in positioning.

[0086] First, the change in positioning corresponding to the delay time can be calculated using the following expression 1.

[0087] [Expression 1]

[0088] Δx VPE =(x VPE (t)-x VPE (t-Δt))*cos(ψ GNSS -ψ VPE (t-Δt))-(y VPE (t)-y VPE (t-Δt))*sin(ψ GNSS -ψ VPE (t–Δt))

[0089] Δy VPE =(x VPE (t)-x VPE (t–Δt))*sin(ψ GNSS -ψ VPE (t–Δt))+(y VPE (t)-y VPE (t-Δt))*cos(ψ GNSS -ψ VPE (t–Δt))

[0090] Δψ VPE =ψ GNSS -ψ VPE (t-Δt)

[0091] Here, t represents the current time, and Δt represents the delay time.

[0092] The compensation result data can be calculated using the following expression 2.

[0093] [Expression 2]

[0094] x comp =x GNSS +Δx VPE

[0095] y comp =y GNSS +Δy VPE

[0096] ψ comp =ψ GNSS +Δψ VPE

[0097] Here, x comp y comp , and ψ comp This represents the compensation result data.

[0098] x GNSS y GNSS , and ψ GNSS This represents the result data measured from GPS or a camera, and Δx VPE Δy VPE , and Δψ VPE This represents the change in positioning corresponding to the delay time.

[0099] Therefore, the driving assistance method and apparatus according to the embodiments not only effectively assist the vehicle in reversing by correcting the vehicle's position when the vehicle is reversing, but also have the effect of reducing errors in the driving path stored when the vehicle is moving forward.

[0100] That is, the driving assistance method and apparatus according to the embodiments can reduce the error of the stored driving path and at the same time reduce the error of the vehicle's position when following the driving path, thereby achieving the effect of accurately measuring the vehicle's position.

[0101] Figure 7 A driving assistance method according to an embodiment is shown.

[0102] exist Figure 7 The driving assistance method shown can be configured to perform through Figures 1 to 6 The process described.

[0103] Reference Figure 7 The driving assistance method according to the embodiments may include: storing the vehicle's driving path based on the vehicle's forward driving (S700); correcting the vehicle's position based on at least one of sensor information measured by the vehicle's internal sensors, the vehicle's global positioning system (GPS) information, or feature information obtained through the vehicle's image information when the vehicle is driving in reverse (S701); assisting the vehicle in reversing driving based on the stored driving path and the corrected position of the vehicle (S702); extracting local map information within a certain range from the vehicle's current position from the entire map information stored based on the vehicle's forward driving (S703); calculating the vehicle's position coordinate values ​​corresponding to a delay time based on the vehicle's forward driving (S704); and compensating for at least one of the GPS information or the feature information based on the vehicle's position coordinate values ​​(S705).

[0104] In operation S701, based on the input state information, a first weight can be assigned to the sensor information, a second weight can be assigned to the GPS information, and a third weight can be assigned to the feature information. The vehicle's position can be corrected based on the first, second, and third weights. In this case, the first weight can be determined based on the matching degree between the sensor information and the vehicle's position information, the second weight can be determined based on the matching degree between the GPS information and the vehicle's position information, and the third weight can be determined based on the matching degree between the feature information and the vehicle's position information.

[0105] Therefore, the driving assistance method and apparatus according to the embodiments have the effect of efficiently performing vehicle position correction according to the surrounding environment when the vehicle is driving in reverse.

[0106] Figure 8 A driving assistance device 10 according to an embodiment is shown.

[0107] Reference Figure 8The driving assistance device 10 according to embodiments of the present disclosure may include one or more memories 11 and one or more processors 12.

[0108] Processor 12 can control memory 11 and can be configured to implement the descriptions, functions, processes, suggestions, methods, and / or operation flowcharts disclosed in this specification. Specifically, processor 12 can be configured to execute through Figures 1 to 7 The process described.

[0109] The memory 11 can be connected to the processor 12 and can store various information related to the operation of the processor 12. For example, the memory 11 can store software code including instructions for performing some or all of the processes controlled by the processor 12 or for performing the descriptions, functions, processes, suggestions, methods and / or operation flowcharts disclosed herein. Specifically, according to embodiments of this disclosure, the memory 11 can be used to store driving paths, sensor information, GPS information, overall map information, local map information, and feature information.

[0110] Figure 8 The driving assistance device 10 may be included inside the vehicle or configured as part of the vehicle. Alternatively, the driving assistance device 10 may be configured as a stand-alone device independent of the vehicle and may be connected to the vehicle and operate via a wired / wireless interface.

[0111] According to embodiments of this disclosure, an advantage is that a method and apparatus can be provided that reduces computational load and improves the accuracy of vehicle position estimation by correcting the driving path during reverse driving assistance.

[0112] The effects that can be obtained in this disclosure are not limited to those described above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

[0113] While this specification contains details of many specific implementations, as described above, these should not be construed as limiting the scope of any invention or claim, but rather as descriptions of features that may be unique to a particular embodiment of a particular invention. Certain features described in this specification within the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, different features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments. Furthermore, while features may operate in a particular combination and may initially be described as claimed, in some cases one or more features from the claimed combination may be excluded from that combination, and the claimed combination may be modified into a sub-combination or a variation thereof.

[0114] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or in any other order to achieve the desired result, or requiring the execution of all the shown operations. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of the various system components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated into a single software product or packaged into multiple software products.

[0115] Specific embodiments of the subject matter described herein have been described. Other embodiments are within the scope of the following claims. For example, the operations described in the claims may be performed in a different order and still achieve the desired result. For example, the processes shown in the drawings do not necessarily require a specific illustrated order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0116] This specification sets forth the best mode of this disclosure and provides examples to illustrate it, enabling those skilled in the art to make and use it. This specification is not intended to limit this disclosure to the specific terminology stated. Therefore, although this disclosure has been described in detail with reference to the foregoing examples, it will be apparent to those skilled in the art that modifications, alterations, and variations can be made to the examples without departing from the scope of this disclosure.

[0117] Therefore, the scope of this disclosure should not be determined by the described embodiments, but by the claims.

Claims

1. A driving assistance method, comprising: Based on the vehicle's forward movement, store the vehicle's travel path; In response to the vehicle reversing, the vehicle's position is corrected based on at least one of sensor information measured by the vehicle's internal sensors, the vehicle's GPS information, or feature information obtained through the vehicle's image information; and Based on the stored driving path and the corrected position of the vehicle, the vehicle is assisted in reversing.

2. The driving assistance method according to claim 1, further comprising: Based on the state of at least one of the sensor information, the global positioning system information, and the feature information, a first weight is applied to the sensor information, a second weight is applied to the global positioning system information, and a third weight is applied to the feature information; as well as The vehicle's position is corrected based on the first weight, the second weight, and the third weight.

3. The driving assistance method according to claim 2, wherein, The first weight is determined based on the matching degree between the sensor information and the vehicle's location information, and the second weight is determined based on the matching degree between the Global Positioning System information and the vehicle's location information. The third weight is determined based on the matching degree between the feature information and the vehicle's location information.

4. The driving assistance method according to claim 1, further comprising: Local map information is extracted from the entire map information stored based on the vehicle's forward movement, wherein the local map information is within a certain range from the vehicle's current position. The process of correcting the position of the vehicle includes: Based on the points in the feature information and the points in the local map information, the position correction value of the vehicle is calculated; and The position of the vehicle is corrected based on the position correction value.

5. The driving assistance method according to claim 4, wherein, The entire map information includes: First map information generated based on the vehicle's front camera; Second map information generated based on the vehicle's rear camera; The third map information generated based on the vehicle's left camera; and The fourth map information is generated based on the right camera of the vehicle.

6. The driving assistance method according to claim 5, further comprising: The local map information is extracted sequentially from the first map information, the second map information, the third map information, and the fourth map information.

7. The driving assistance method according to claim 6, wherein, Calculating the position correction value includes: A first position correction value is calculated based on points obtained from the first feature information based on the front camera and points extracted from the first local map information; The second position correction value is calculated based on the points obtained from the second feature information based on the rear camera and the points extracted from the second local map information. A third position correction value is calculated based on points obtained from the third feature information of the left camera and points extracted from the third local map information; and The fourth position correction value is calculated based on the points obtained from the fourth feature information obtained from the right camera and the points extracted from the fourth local map information.

8. The driving assistance method according to claim 4, wherein, The entire map information includes information about all stored trajectory indices based on the vehicle's forward movement, and information about all points mapped to all trajectory indices. The extraction of the local map information includes: extracting information from the entire map information about points mapped to trajectory indices whose values ​​are within a certain range from the trajectory index corresponding to the current position.

9. The driving assistance method according to claim 1, wherein, The driving path is generated based on the vehicle's location, and The vehicle's position is measured based on at least one of sensor information measured by the vehicle's internal sensors during forward travel, or the vehicle's GPS information during forward travel.

10. The driving assistance method according to claim 9, further comprising: Based on the vehicle's forward movement, calculate the vehicle's position coordinates corresponding to the delay time; as well as Compensation is provided based on the vehicle's location coordinates during forward travel, using at least one of the vehicle's GPS information or the feature information. The driving path is generated based on compensated GPS information.

11. A driving assistance device, comprising: At least one processor; as well as At least one memory, operatively connected to the at least one processor, and storing instructions. When executing the instructions, the at least one processor is configured to: Based on the vehicle's forward movement, store the vehicle's travel path; In response to the vehicle reversing; The vehicle's position is corrected based on at least one of sensor information measured by the vehicle's internal sensors, the vehicle's GPS information, or feature information obtained through the vehicle's image information; and Based on the stored driving path and the corrected position of the vehicle, the vehicle is assisted in reversing.

12. The driving assistance device according to claim 11, wherein, The at least one processor is further configured to: Based on the state of at least one of the sensor information, the global positioning system information, and the feature information, a first weight is applied to the sensor information, a second weight is applied to the global positioning system information, and a third weight is applied to the feature information; as well as The vehicle's position is corrected based on the first weight, the second weight, and the third weight.

13. The driving assistance device according to claim 12, wherein, The first weight is determined based on the matching degree between the sensor information and the vehicle's location information. The second weight is determined based on the matching degree between the GPS information and the vehicle's location information. The third weight is determined based on the matching degree between the feature information and the vehicle's location information.

14. The driving assistance device according to claim 11, wherein, The at least one processor is further configured to: The driving path is generated based on the vehicle's location, wherein the vehicle's location is measured based on at least one of sensor information measured by the vehicle's internal sensors during forward travel or the vehicle's GPS information during forward travel.

15. The driving assistance device according to claim 14, wherein, The at least one processor is further configured to: Based on the vehicle's forward movement, calculate the vehicle's position coordinates corresponding to the delay time; and Compensation is provided based on the vehicle's location coordinates during forward travel, using at least one of the vehicle's GPS information or the feature information. The driving path is generated based on compensated GPS information.

16. A computer-readable non-volatile storage medium comprising at least one computer program that causes at least one processor to perform operations, said operations including: Based on the vehicle's forward movement, store the vehicle's travel path; In response to the vehicle reversing, the vehicle's position is corrected based on at least one of sensor information measured by the vehicle's internal sensors, the vehicle's GPS information, or feature information obtained through the vehicle's image information; and Based on the stored driving path and the corrected position of the vehicle, the vehicle is assisted in reversing.

17. The computer-readable non-volatile storage medium according to claim 16, wherein, The operation also includes: Based on the state of at least one of the sensor information, the global positioning system information, and the feature information, a first weight is applied to the sensor information, a second weight is applied to the global positioning system information, and a third weight is applied to the feature information; and The vehicle's position is corrected based on the first weight, the second weight, and the third weight.

18. The computer-readable non-volatile storage medium according to claim 17, wherein, The operation also includes: The first weight is determined based on the matching degree between the sensor information and the vehicle's location information; The second weight is determined based on the matching degree between the global positioning system information and the vehicle's location information; and The third weight is determined based on the matching degree between the feature information and the vehicle's location information.

19. The computer-readable non-volatile storage medium according to claim 16, wherein, The operation also includes: The driving path is generated based on the vehicle's location, wherein the vehicle's location is measured based on at least one of sensor information measured by the vehicle's internal sensors during forward travel or the vehicle's GPS information during forward travel.

20. The computer-readable non-volatile storage medium according to claim 19, wherein, The operation also includes: Based on the vehicle's forward movement, calculate the vehicle's position coordinates corresponding to the delay time; and Compensation is provided based on the vehicle's location coordinates during forward travel, using at least one of the vehicle's GPS information or the feature information. The driving path is generated based on compensated GPS information.

Images