Apparatus and method for controlling travel

Abstract

The invention relates to an apparatus and a method for controlling travel. The apparatus includes a sensor, a memory, and a controller. For example, the apparatus may obtain, via a sensor (e.g., LIDAR), a lane line recognition result associated with a road on which a vehicle travels, determine whether information including at least one of a curvature of the road or a curvature change rate of the road satisfies a specified condition based on the lane line recognition result, and determine whether the vehicle travels based on the determined condition based on the information satisfying the specified condition. The calibrated lane line information is generated using a predicted curvature change rate, which is determined based on the curvature change rate and at least one of a predicted heading angle of the vehicle at a target point on the road, a predicted curvature at the target point, or a predicted lateral deviation at the target point.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority from Korean Patent Application No. 10-2023-0099888 filed in the Korean Intellectual Property Office on July 31, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present invention relates to an apparatus and method for controlling vehicle movement, and more particularly, to compensating for unstable performance of lane line recognition. Background Art

[0004] The driving control device can execute the vehicle control algorithm according to the autonomous driving control level, and the autonomous driving control level can be divided into partial autonomous driving, conditional autonomous driving, highly autonomous driving and / or fully autonomous driving.

[0005] For example, the driving control device (also referred to as the automatic driving control device) may recognize information of the road on which the vehicle is traveling (e.g., traffic lines) by using sensors. For example, the driving control device may recognize lane line recognition results using a sensor component (e.g., a front camera) provided in one area of ​​the vehicle, and perform driving control (or automatic driving control) of the vehicle based on the results.

[0006] For example, the driving control device can identify a polynomial of a specified degree (e.g., a cubic polynomial) corresponding to a lane line (e.g., a traffic line) based on information about a road identified by a sensor or driving information of the vehicle, or any combination thereof.

[0007] However, when the driving control device obtains the result corresponding to the lane line based on the lane line recognition algorithm, the accuracy may be reduced momentarily. For example, when at least some of the coefficients of the polynomial corresponding to the lane line increase or decrease momentarily, a peak phenomenon may occur.

[0008] In addition, since the driving environment of the vehicle may not be fixed, there may be problems such as inaccurate recognition results due to changes in the driving environment or when the vehicle is driving in a specific driving environment, such as shaking lane lines.

[0009] In addition, due to the effective measurement range of the sensor, lane line recognition may be inaccurate or unable to be recognized. Summary of the invention

[0010] The present invention is directed to solving the above-mentioned problems arising in some embodiments, while the advantages achieved by these embodiments remain unchanged.

[0011] One aspect of the present invention may selectively provide a compensation algorithm according to whether information on at least one of the curvature or the curvature change rate or any combination thereof of a road recognized using a sensor satisfies a specified condition.

[0012] Another aspect of the present invention may provide a travel control device that determines that a peak phenomenon occurs when a change amount of the curvature change rate and a change amount of the curvature have opposite signs and when it is recognized that the change amount of the curvature is equal to or greater than a critical value.

[0013] Another aspect of the present invention may provide a travel control device that performs travel control by compensating a lane line recognition result during a specified duration (eg, 2 seconds) and continues to use the lane line recognition result recognized by a sensor after the specified duration has elapsed.

[0014] Another aspect of the present invention can provide a driving control device that selects such a target point as a target point of a compensation algorithm from at least one target point candidate, wherein the target point generates corrected lane line information such that the difference between the corrected curvature and the reference curvature has a smaller value.

[0015] Another aspect of the present invention can provide a travel control device that effectively sets at least one value of a coefficient corresponding to a lane line using at least one weight.

[0016] The technical problems solved by the present invention are not limited to the aforementioned problems. According to the following description, those skilled in the art to which the present invention belongs will clearly understand any other technical problems not mentioned herein.

[0017] According to one or more example embodiments of the present invention, a device may include: a sensor, a memory, and a controller; the memory stores instructions; the controller is operably connected to the sensor and the memory. When the instructions are executed by the controller, the device may: obtain a lane line recognition result associated with a road on which a vehicle is traveling via a sensor; determine whether information including at least one of the curvature of the road or the curvature change rate of the road meets a specified condition based on the lane line recognition result; based on the information meeting the specified condition, generate calibrated lane line information using the expected curvature change rate. The expected curvature change rate may be determined based on at least one of an expected heading angle of a target point of the vehicle on the road, an expected curvature at the target point, or an expected lateral deviation at the target point, and the curvature change rate.

[0018] The specified condition may include: a first condition and a second condition, wherein the first condition includes one of an increase in the curvature change rate and a decrease in the curvature, or a decrease in the curvature change rate and an increase in the curvature; and the second condition includes a curvature change exceeding a threshold.

[0019] When the instructions are executed by the controller, the device may further control the movement of the vehicle based on the lane line recognition result and the calibrated lane line information during a duration after the time associated with the information.

[0020] When the instructions are executed by the controller, the device may further: determine at least one target point candidate that the vehicle is expected to reach within a duration after the time associated with the information; determine an expected curvature change rate at the target point. The target point may be one of the at least one target point candidate.

[0021] When the instruction is executed by the controller, the device can further: determine a reference curvature associated with a second time among the curvatures included in the lane line recognition result, and the second time is before the time associated with the information; and determine a target point among at least one target point candidate that minimizes the difference between the calibrated curvature at the time point when a specified condition is met and the reference curvature.

[0022] When the instruction is executed by the controller, it can further cause the device to: determine a first curvature change rate at a time point associated with the information based on the curvature change rate included in the lane line recognition result; determine a second curvature change rate representing the overall curvature change rate of the road based on the curvature change rate included in the lane line recognition result; and determine an expected curvature change rate within a duration starting from the time associated with the information based on the first curvature change rate, the second curvature change rate, or at least one of the weights of each of the first curvature change rate and the second curvature change rate.

[0023] The weight of each of the first rate of change of curvature and the second rate of change of curvature may include a first weight of the first rate of change of curvature. The first weight may decrease during the duration.

[0024] When the instructions are executed by the controller, the device may further: determine the driving speed of the vehicle through a sensor; and determine the target point based on at least one of the driving speed or a predetermined duration.

[0025] According to one or more exemplary embodiments of the present invention, a method may include: obtaining, by a controller, a lane line recognition result associated with a road on which a vehicle is traveling via a sensor; determining, by the controller, whether information including at least one of the curvature of the road or the curvature change rate of the road satisfies a specified condition based on the lane line recognition result; and generating calibrated lane line information using an estimated curvature change rate based on the information satisfying the specified condition. The estimated curvature change rate may be determined based on at least one of an estimated heading angle of a target point of the vehicle on the road, an estimated curvature at the target point, or an estimated lateral deviation at the target point, and the curvature change rate.

[0026] The specified condition may include: a first condition and a second condition, wherein the first condition includes one of an increase in the curvature change rate and a decrease in the curvature, or a decrease in the curvature change rate and an increase in the curvature; and the second condition includes a curvature change exceeding a threshold.

[0027] The method may further include controlling, by the controller, movement of the vehicle based on the lane line recognition result and the calibrated lane line information during a duration after the time associated with the information.

[0028] The method may further include: determining, by a controller, at least one target point candidate that the vehicle is expected to reach within a duration after the time associated with the information; and determining, by the controller, an expected curvature change rate at the target point. The target point may be one of the at least one target point candidate.

[0029] The method may further include: among the curvatures included in the lane line recognition result, determining by the controller a reference curvature associated with a second time, the second time being before the time associated with the information; and among the at least one target point candidate, determining by the controller a target point that minimizes the difference between the calibrated curvature at the time point when a specified condition is met and the reference curvature.

[0030] The method may further include: determining, by a controller, a first curvature change rate at a time point associated with the information based on the curvature change rate included in the lane line recognition result; determining, by a controller, a second curvature change rate representing the overall curvature change rate of the road based on the curvature change rate included in the lane line recognition result; and determining, by the controller, an expected curvature change rate within a duration starting from the time associated with the information based on the first curvature change rate, the second curvature change rate, or at least one of the weights of each of the first curvature change rate and the second curvature change rate.

[0031] The weight of each of the first rate of change of curvature and the second rate of change of curvature may include a first weight of the first rate of change of curvature. The first weight may decrease during the duration.

[0032] According to one or more exemplary embodiments of the present invention, a computer-readable medium stores instructions, which, when executed, can cause: a controller to obtain a lane line recognition result associated with a road on which a vehicle is traveling via a sensor; the controller to determine whether information including at least one of the curvature of the road or the curvature change rate of the road meets a specified condition based on the lane line recognition result; based on the information meeting the specified condition, the controller generates calibrated lane line information using the expected curvature change rate. The expected curvature change rate can be determined based on at least one of an expected heading angle of a target point of the vehicle on the road, an expected curvature at the target point, or an expected lateral deviation at the target point, and the curvature change rate.

[0033] The specified condition may include: a first condition and a second condition, wherein the first condition includes one of an increase in the curvature change rate and a decrease in the curvature, or a decrease in the curvature change rate and an increase in the curvature; and the second condition includes a curvature change exceeding a threshold.

[0034] When the instructions are executed, it can further cause: the controller to control the movement of the vehicle based on the lane line recognition result and the calibrated lane line information during a duration after the time associated with the information.

[0035] When the instructions are executed, the controller may further determine at least one target point candidate that the vehicle is expected to reach within a duration after the time associated with the information; and the controller may determine an expected curvature change rate at the target point. The target point may be one of the at least one target point candidate.

[0036] When the instruction is executed, it can further make: among the curvatures included in the lane line recognition results, the controller determines a reference curvature associated with a second time, and the second time is before the time associated with the information; among at least one target point candidate, the controller determines a target point that minimizes the difference between the calibrated curvature at the time point when the specified condition is met and the reference curvature. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description presented in conjunction with the accompanying drawings, in which:

[0038] Figure 1 is a block diagram showing components of a travel control device;

[0039] Figure 2 is a conceptual diagram showing the result of lane line recognition performed by the travel control device;

[0040] Figure 3 is a conceptual diagram showing the result of lane line recognition performed by the travel control device;

[0041] Figure 4 is a conceptual diagram showing the result of lane line recognition performed by the travel control device;

[0042] Figure 5 is a conceptual diagram showing the result of lane line recognition performed by the travel control device;

[0043] Figure 6 is a conceptual diagram of the operation of the travel control device;

[0044] Figure 7 is a graph showing the time-dependent changes in parameters utilized by the travel control device;

[0045] Figure 8 is a conceptual diagram of the operation of the travel control device;

[0046] Fig. 9 is a conceptual diagram of the operation of the travel control device;

[0047] Fig.10 is a conceptual diagram of the operation of the travel control device;

[0048] Fig.11 is a flow chart of a driving control method; and

[0049] Fig.12 A computing system related to a driving control method is shown.

[0050] Regarding the description of the drawings, the same or similar reference numerals may be used for the same or similar components. DETAILED DESCRIPTION

[0051] Hereinafter, one or more example embodiments of the present invention will be described in detail with reference to the exemplary drawings. When adding reference numerals to the components of each figure, it should be noted that the same or equivalent components are indicated by the same numerals even if they are shown in other figures. In addition, when describing one or more example embodiments of the present invention, when it is determined that the detailed description of the related known configuration or function will interfere with the understanding of the example embodiments of the present invention, it will be omitted.

[0052] When describing components according to one or more example embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only used to distinguish components from other components, and these terms do not limit the nature, order or sequence of the components. Unless otherwise defined, all terms (including technical and scientific terms) used in this article have the same meaning as those generally understood by ordinary technicians in the field to which the present invention belongs. It should be further understood that terms (such as those defined in commonly used dictionaries) should be interpreted as having a meaning consistent with the meaning in the context of the relevant technology and should not be interpreted as an ideal or overly formal meaning unless expressly provided herein.

[0053] In the following, reference will be made to Figures 1 to 12 One or more exemplary embodiments of the invention are described in detail.

[0054] Figure 1 is a block diagram showing components of a travel control device.

[0055] The travel control device 100 may include at least one of a sensor 110 , a memory 120 , or a controller 130 , or any combination thereof. Figure 1The configuration of the travel control device 100 shown is illustrative, and the present invention is not limited thereto. For example, the travel control device 100 may further include Figure 1 Components not shown (eg, at least one of an interface, a communication device, a display, or a notification device, or any combination thereof).

[0056] The sensor 110 may acquire (or sense) various information related to the travel of a vehicle (eg, the host vehicle).

[0057] For example, the sensor 110 may include at least one sensor including at least one of a camera, a radar, or a LiDAR, or any combination thereof. As an example, the sensor 110 may include a front camera for identifying information about the area in front of the vehicle.

[0058] For example, the sensor 110 may identify information about at least one of a driving state of the host vehicle, a driving mode, a road, or an area adjacent to the host vehicle, or any combination thereof.

[0059] As an example, the sensor 110 may identify information about the driving state of the vehicle, the information including at least one of the vehicle's actual (or real-time) driving speed, driving direction, acceleration and / or deceleration, or any combination thereof.

[0060] As an example, the sensor 110 may identify information about a road on which the host vehicle is traveling. For example, the controller 130 may identify a lane line recognition result related to the road based on at least some of the information acquired using the sensor 110. The lane line recognition result may include, for example, information (e.g., a polynomial) about a virtual lane line corresponding to the road.

[0061] At least some of the above operations performed by the sensor 110 may be understood to be performed by the controller 130 using information acquired by the sensor 110 .

[0062] The memory 120 may store instructions or data. For example, the memory 120 may store one or more instructions that enable the travel control device 100 to perform various operations when the one or more instructions are executed by the controller 130.

[0063] For example, the memory 120 may be implemented as one chipset together with the controller 130. The controller 130 may include at least one of a communication processor or a modem.

[0064] For example, the memory 120 may store various information related to the travel control device 100. As an example, the memory 120 may store information about the operation history of the controller 130. As an example, the memory 120 may store information related to the state and / or operation of a component of the host vehicle (e.g., at least one of the engine control unit (ECU), the sensor 110 or the controller 130, or any combination thereof).

[0065] The controller 130 may be operably connected to the sensor 110 and / or the memory 120. For example, the controller 130 may control the operation of the sensor 110 and / or the memory 120.

[0066] For example, the controller 130 may use the sensor 110 to identify a lane line recognition result related to the road on which the host vehicle is traveling. For example, the controller 130 may use at least some of the information acquired by the sensor 110 to identify a lane line recognition result including a formula representing the road.

[0067] As an example, the lane line recognition result may include information about the following Formula 1 corresponding to the lane line of the road.

[0068] Formula 1

[0069] y=ax 3 +bx 2 +cx+d

[0070] For example, the y-value may be an identified lateral deviation between the host vehicle and a lane line of the road based on the x-value corresponding to the real-time position of the host vehicle.

[0071] For example, the controller 130 may identify information about a driving condition based on a real-time position of the host vehicle based on Formula 2 below.

[0072] Formula 2

[0073] y 0 (x) = a 0 x 3 +b 0 x 2 +c 0 x+d 0

[0074]

[0075]

[0076]

[0077] For example, 0 (x), It can be a formula that respectively represents the lateral deviation, heading deviation, curvature of the road (or lane line) and curvature change rate of the road between the vehicle and the lane line of the road, which are identified based on the x value corresponding to the real-time position of the vehicle.

[0078] For example, the controller 130 may identify the heading angle of the host vehicle, the curvature of the road, and / or the curvature change rate as coefficients of Formula 2 based on a case where the x value is 0.

[0079] As an example, when the x value is 0, the curvature change rate of the road is It can be 6a.

[0080] As an example, when the x value is 0, the curvature ρ of the road may be 2b.

[0081] As an example, when the x value is 0, the heading deviation θ of the vehicle is H It can be c.

[0082] As an example, when the x value is 0, the lateral deviation e of the vehicle is D It can be d.

[0083] For example, the controller 130 may identify a target point corresponding to the control target point, and perform travel control in a scheme that reduces the lateral deviation and / or heading deviation of the host vehicle at the identified target point.

[0084] As an example, the controller 130 may use the sensor 110 to identify the real-time driving speed of the host vehicle, and use at least one of the real-time driving speed or the preset time (or the look ahead time (look ahead time) (e.g., 0.6 seconds)) or any combination thereof to identify the target point. The preset time may be, for example, a setting value that can be changed by the user. The controller 130 may use the real-time driving speed v of the host vehicle to identify the target point. x With the preset time t ah The product of tp .

[0085] The controller 130 can tp Substitute into the above formula 2 to identify a formula based on the following formula 3, and identify new lane line information based on the identified formula to replace at least part of the road section of the existing lane line recognition result.

[0086] Formula 3

[0087]

[0088]

[0089]

[0090]

[0091] For example, the controller 130 may determine whether information on at least one of the curvature or the curvature change rate or any combination thereof of the road included in the lane line recognition result satisfies a specified condition.

[0092] As an example, the specified condition may include a first condition that the curvature change rate increases and the curvature decreases, or the curvature change rate decreases and the curvature increases. In other words, when there is a road section where the curvature change rate increases and the curvature decreases, or the curvature change rate decreases and the curvature increases in the result data on the road information acquired using the sensor 110, the controller 130 may determine that the first condition is satisfied. That is, when there is a road section where the change amount of the curvature change rate and the change amount of the curvature have opposite signs, the controller 130 may determine that the first condition is satisfied.

[0093] As an example, the specified condition may include a second condition that the value of the curvature change is equal to or greater than a critical value. In other words, when there is a road section in which the value of the instantaneous curvature change is equal to or greater than a predefined critical value in the result data about the road information acquired using the sensor 110, the controller 130 may determine that the second condition is satisfied.

[0094] For example, when both the first condition and the second condition described above are satisfied, the controller 130 may determine that the information on at least one of the curvature or the curvature change rate or any combination thereof of the road included in the lane line recognition result satisfies the specified condition.

[0095] For example, when the information satisfies specified conditions (e.g., the first condition and / or the second condition), the controller 130 can use the target information to generate calibrated (e.g., corrected) lane line information, wherein the target information includes an expected curvature change rate identified using at least one of the expected heading angle, expected curvature, or expected lateral deviation, or any combination thereof, and the curvature change rate of a target point of the vehicle on the road.

[0096] As an example, calibrated (e.g., corrected) lane line information may include information that corrects at least some of the initially identified lane line recognition results within a specified duration to generate new lane line recognition results that are compensated for the initially identified lane line recognition results, and replaces a portion of the initially identified lane line recognition results with the new lane line recognition results.

[0097] As an example, the controller 130 can control the driving of the vehicle based on the lane line recognition result after compensation based on the lane line information calibrated (e.g., corrected) within a specified duration (e.g., 2 seconds) from the time point when the information meets the specified conditions.

[0098] As an example, the controller 130 may identify at least one target point candidate that the vehicle is expected to reach within a specified duration range (e.g., from 0.4 seconds after the time point when the information satisfies the specified condition to 0.8 seconds after the time point when the information satisfies the specified condition) after a preset duration (e.g., 0.4 seconds) from the time point when the information satisfies the specified condition. For example, the controller 130 may identify at least one target point candidate that includes at least one of a target point corresponding to a time point after 0.4 seconds from the time point when the information satisfies the specified condition, a target point corresponding to a time point after 0.6 seconds from the time point when the information satisfies the specified condition, or a target point corresponding to a time point after 0.8 seconds from the time point when the information satisfies the specified condition, or any combination thereof.

[0099] As an example, the controller 130 may identify target information of a target point among the at least one target point candidate. For example, the controller 130 may identify a reference curvature of a second time point (or a first time point) among the curvatures included in the lane line recognition result, and then select a target point among the at least one target candidate that generates calibrated (e.g., corrected) lane line information that minimizes the difference between the corrected curvature at the time point at which a specified condition is satisfied and the reference curvature, wherein the second time point is a time point immediately before the first time point at which the information satisfies the specified condition. In other words, the controller 130 may select a target point that generates calibrated lane line information that connects the curvatures immediately before and after the peak phenomenon occurs to each other in a continuous manner.

[0100] The controller 130 can identify the vehicle at the target point x based on the above formula 3. tp The lateral deviation and heading deviation, curvature and curvature change rate.

[0101] For example, the polynomial coefficients of Formula 3 may be different from the polynomial coefficients of Formula 2. The controller 130 may acquire new lane line information by identifying the polynomial coefficients of Formula 3 through simultaneous equation operations, and identify new lane line segments that replace at least part of the lane line segments included in the existing lane line recognition results based on the new lane line information.

[0102] Formula 4

[0103] a 1 (k) = a 0 (k-1)

[0104] Referring to Formula 4, if the peak phenomenon occurs at time point "k", the controller 130 may use the value a used to generate new lane line information1 (k) is set to value a 0 (k-1), and then perform simultaneous equation operation based on the polynomial of Formula 3. The above value set by the controller 130 can be defined as a HOLD .

[0105] Formula 5

[0106] a 1 =a Hold

[0107]

[0108]

[0109]

[0110] Referring to Formula 5, the controller 130 can identify b 1 、c 1 and d 1 For example, according to Formula 5, the controller 130 can identify three unknowns b based on four equations: 1 、c 1 and d 1 .

[0111] Formula 6

[0112]

[0113] Referring to Formula 6, the controller 130 may identify the first curvature change rate coefficient a at the time point when the information satisfies the specified condition. HOLD and the second curvature change rate coefficient a included in the curvature change rate included in the lane line recognition result 0 (k) The first curvature change rate and the second curvature change rate to be described below may be coefficients of a polynomial corresponding to the curvature change rate.

[0114] As an example, the first curvature change rate may correspond to the curvature change rate coefficient at the time point when the peak phenomenon occurs. In other words, the first curvature change rate may be the curvature change rate identified by the sensor 110 immediately before the peak phenomenon occurs (or at the time point when the peak phenomenon occurs).

[0115] For example, the second curvature change rate may be a curvature change rate coefficient identified by the sensor 110 for the entire road including the first curvature change rate. In other words, the first curvature change rate may be a fixed value (or constant), and the second curvature change rate may be a variable that changes over time.

[0116] For example, the controller 130 can use at least one of the first curvature change rate, the second curvature change rate, or the weight of each of the first curvature change rate and the second curvature change rate, or any combination thereof to identify the expected curvature change rate during a specified duration (e.g., 2 seconds) from the time point when the information satisfies the specified condition.

[0117] As an example, the controller 130 may identify a first weight "α" corresponding to the first curvature change rate and a second weight (1-α) corresponding to the second curvature change rate. For example, the controller 130 may set the first weight "α" corresponding to the first curvature change rate to gradually decrease within a specified duration (e.g., 2 seconds) from the time point when the information satisfies the specified condition.

[0118] As an example, the controller 130 may identify the first weight “α” using the following Formula 7.

[0119] Formula 7

[0120]

[0121] For example, t Act It can be the time point when the existing lane line information is replaced based on the new lane line information (or the time point when the lane line correction logic is enabled). Deact It may be the time point at which the operation of replacing the existing lane line information with the new lane line information ends (or the time point at which the lane line correction logic is enabled). k It can be time point "k". For example, from t Act to Deact The duration of may be 2 seconds in total, but this is an example and the present invention is not limited thereto.

[0122] You can use the following Figure 7 An example in which the controller 130 identifies α(k) is described in detail in the description of .

[0123] For example, the controller 130 may use the value of the following formula 8 to select a target point from the at least one target point candidate to be used when a new lane line result is identified.

[0124] Formula 8

[0125]

[0126] Referring to Formula 8, the controller 130 may identify a target point among the at least one target point candidate that generates calibrated (e.g., corrected) lane line information that minimizes the difference between the calibration curvature and the reference curvature at a time point when a specified condition is satisfied, and identify a target time point t corresponding to the identified target point.tp .

[0127] For example, the controller 130 may identify such a target point as a target point for generating the calibrated lane line information, the target point making the lane line information consistent with the target time point t tp The curvature of the target point calibration corresponds to the first calibration curvature coefficient b 1,tp (k) and a reference curvature coefficient b corresponding to the curvature initially acquired using the sensor 110 0 The difference between (k-1) tp Minimum.

[0128] For example, the controller 130 may use the following formula 9 to determine whether at least some of the information of the lane recognition result obtained by the sensor 110 (eg, at least one of the curvature or the curvature change rate or any combination thereof) satisfies a specified condition.

[0129] Formula 9

[0130] [b 0 (k)-b 0 (k-1)|>b Th

[0131] [a 0 (k)-a 0 (k-1)]×[b 0 (k)-b 0 (k-1)]<0

[0132] Referring to Formula 9, the controller 130 may identify the coefficient b related to the curvature from the information of the lane line recognition result initially acquired by the sensor 110: 0 and the coefficient a related to the rate of change of curvature 0 .

[0133] For example, the sign of the following value can be identified by calculating the coefficient a related to the rate of change of curvature at time point "k": 0 (k) and the coefficient a related to the rate of change of curvature at time point k-1 0 The difference between (k-1) is multiplied by the coefficient b associated with the curvature at time point "k" 0 (k) and the coefficient b related to the curvature at time point k-1 0 For example, when the value obtained by multiplying the difference is a negative number, the controller 130 can determine that the first condition (in the first condition, the curvature change rate needs to increase and the curvature needs to decrease, or the curvature change rate needs to decrease and the curvature needs to increase) is satisfied.

[0134] For example, when the coefficient b associated with the curvature at time point "k" is 0(k) and the coefficient b associated with the curvature at time point k-1 (i.e., the time point immediately before time point "k") 0 The difference between (k-1) exceeds the critical coefficient b TH , the controller 130 can determine that the second condition (in the second condition, the value of the curvature change needs to be equal to or greater than the critical value) is met.

[0135] Figure 1 The components of the travel control device 100 shown are illustrative, and the present invention is not limited thereto. For example, the travel control device 100 may further include a display (not shown) and / or a notification device (not shown).

[0136] The display may visually provide the user with a user interface including the driving path of the host vehicle (eg, the offset driving path).

[0137] For example, the display can provide a user interface in real time that includes information about lane line information generated by the controller 130 via information initially acquired using the sensor 110, or lane line information newly generated for at least a portion of the lane line based on a correction algorithm, or at least one of any of this information.

[0138] The notification device may include at least one output device. For example, the notification device may include an output device (eg, a speaker) included in at least a portion of the interior of the vehicle.

[0139] For example, the notification device may output various types of sounds to the outside. As an example, the notification device may provide a guidance message to the user indicating that at least a portion of the lane line displayed in real time under the control of the controller 130 is displayed via a correction algorithm.

[0140] Figure 2 is a conceptual diagram showing the result of lane line recognition performed by the travel control device.

[0141] Travel control devices (e.g. Figure 1 The driving control device 100 can be based on the use of sensors (for example, Figure 1 The system uses at least some of the information acquired by the sensor 110 to generate a result (e.g., a cubic polynomial) representing the road on which the vehicle is traveling.

[0142] Referring to reference numeral 210, the travel control device may identify a cubic polynomial corresponding to a road (or a lane line). The cubic polynomial may be a formula corresponding to Formula 1 above.

[0143] Referring to reference numeral 250, the travel control device may tgInput into the domain of a cubic polynomial to identify the target point x tg The lateral deviation between the vehicle and the lane line is y(x tg ).

[0144] Figure 3 and Figure 4 is a conceptual diagram showing the result of lane line recognition performed by the travel control device.

[0145] Travel control devices (e.g. Figure 1 The travel control device 100 may utilize sensors (e.g., Figure 1 The sensor 110) is used to identify the curvature change rate, curvature, heading angle (or heading deviation) and / or lateral deviation of the road on which the vehicle is traveling.

[0146] In the graphs of reference numerals 310 , 320 , 410 , and 420 , peak sections appearing during the process of lane line recognition performed by the driving control device are shown.

[0147] refer to Figure 3 Referring to the reference numeral 310 , the driving control device can identify the curvature change rate of the road in real time.

[0148] For example, it can be seen that in the time period from 2100 ms to 2110 ms, a first peak section 315 appears, in which the curvature change rate acquired by the travel control device using the sensor decreases instantaneously.

[0149] refer to Figure 3 Referring to the reference numeral 320 , the driving control device can identify the curvature change rate of the road in real time.

[0150] For example, it can be seen that in the time period from 2100 ms to 2110 ms, a second peak section 325 appears, in which the curvature acquired by the travel control device using the sensor increases instantaneously.

[0151] refer to Figure 4 Referring to the reference numeral 410 , the driving control device can identify the heading angle (or heading deviation) of the vehicle on the road in real time.

[0152] For example, it can be seen that in the time period from 2100 ms to 2110 ms, a third peak section 415 appears, in which the heading angle acquired by the driving control device using the sensor decreases instantaneously.

[0153] refer to Figure 4 Referring to the reference numeral 420 , the driving control device can identify the heading angle (or heading deviation) of the vehicle on the road in real time.

[0154] For example, it can be seen that in the time period from 2100 ms to 2110 m, a fourth peak section 425 appears, in which the lateral deviation acquired by the travel control device using the sensor decreases instantaneously.

[0155] There is a problem that the lane line recognition accuracy of the driving control device is reduced due to at least some of the above-mentioned peak sections.

[0156] Figure 5 is a conceptual diagram showing the result of lane line recognition performed by the travel control device.

[0157] Travel control devices (e.g. Figure 1 The driving control device 100) can identify the change of the value "a" corresponding to the curvature change rate (or curvature change rate coefficient) that changes with time and the change of the value "b" corresponding to the curvature (or curvature coefficient) that changes with time.

[0158] Referring to reference numeral 510, the travel control device may Figure 1 The value "a" of the first time point 512 at which the information acquired by the sensor 110 satisfies the specified condition is set to value a HOLD Alternatively, the travel control device may set the value "a" at the time point immediately before the first time point 512 to the value a. HOLD At this point, when the value "a" is fixed to value a HOLD When generating new lane line information, it may be difficult to generate appropriate lane line information because there is a relatively large deviation between the final value "a" 514 at the end time point 516 when the correction algorithm ends when a specified duration (for example, 2 seconds) has passed since the first time point 512 and the existing value "a" of the lane line information obtained by the sensor.

[0159] To avoid this gap, the driving control device can identify the curvature change rate (or curvature change rate coefficient) used to generate new lane line information based on the above formula 6. Accordingly, the driving control device can ensure the continuity between the existing lane line information and the new lane line information in the process of generating new lane line information.

[0160] Referring to figure mark 520, the driving control device can identify the target point candidate that the vehicle is expected to reach within a specified duration range (for example, a time period from a time point 0.4 seconds after the first time point 522 to a time point 0.8 seconds after the first time point 522) after a preset duration (for example, 0.4 seconds) from the first time point 522 at which information obtained using the sensor satisfies the specified conditions.

[0161] For example, the travel control device may identify a first target time point t corresponding to the first target point tp1 (e.g., a time point 0.4 seconds after the first time point 522), a second target time point t corresponding to the second target point tp2 (e.g., a time point 0.6 seconds after the first time point 522), or a third target time point t corresponding to the third target point tp3 (e.g., at a time point 0.8 seconds after the first time point 522) or at least one of any combination thereof.

[0162] For example, the travel control device may identify a difference between a curvature calibrated at the first time point 522 based on each of the at least one target point candidate and a reference curvature pre-acquired using a sensor at the first time point 522. As an example, during a period from the first time point 522 to a third time point 524 (e.g., a time point at which the correction algorithm ends), the travel control device may respectively identify first curvature information 532 newly generated based on the first target point, second curvature information 534 newly generated based on the second target point, and third curvature information 536 newly generated based on the third target point.

[0163] For example, based on the graph according to reference numeral 520, the travel control device can identify the time corresponding to the second target time point t tp2 The calibrated curvature of the second target point has the smallest difference with the reference curvature, and it is determined that calibrated lane line information will be generated based on the second target point.

[0164] Figure 6 This is a conceptual diagram of the operation of the travel control device.

[0165] Referring to reference numeral 610, a travel control device (eg, Figure 1 The travel control device 100 may utilize sensors (e.g., Figure 1 The sensor 110 of the present invention can be used to identify raw data related to the road. For example, the raw data can include at least one of the curvature change rate or curvature of the road or any combination thereof.

[0166] According to reference numeral 650 , when at least some of the original data satisfy a specified condition, the driving control device may generate new lane line information corresponding to a certain section of the road through a correction algorithm.

[0167] For example, according to reference numeral 652, the travel control device may sense an event in which raw data satisfies a specified condition.

[0168] As an example, the specified conditions may include a first condition (in the first condition, the curvature change rate increases and the curvature decreases, or the curvature change rate decreases and the curvature increases) and a second condition (in the second condition, the value of the curvature change is equal to or greater than a critical value).

[0169] For example, the travel control device may identify values ​​of at least some of the coefficients of the polynomial corresponding to the road, according to reference numeral 654. As an example, the travel control device may identify a coefficient corresponding to at least one of the rate of change of curvature, curvature, heading deviation, or lateral deviation of the host vehicle, or any combination thereof.

[0170] For example, according to reference numeral 656, the travel control device can select a target point. The description related to the travel control device for selecting a target point can be used as above. Figure 1 description instead.

[0171] For example, the travel control device may execute a master compensation (eg, calibration) logic according to reference numeral 658. As an example, the travel control device may correct at least a portion of a lane line generated based on existing raw data based on at least one newly identified coefficient and target point.

[0172] According to reference numeral 620, the driving control device may compensate at least a portion of the lane line generated based on the original data based on at least some of the new lane line information (generated based on the correction algorithm according to reference numeral 650). The driving control device may recognize at least a portion of the lane line based on the compensated lane line recognition result.

[0173] Figure 7 It is a graph showing the temporal changes of parameters used by the travel control device.

[0174] refer to Figure 7 , travel control devices (e.g. Figure 1 The driving control device 100 can be based on the use of sensors (for example, Figure 1 The predicted curvature change rate of at least a portion of the road on which the vehicle is traveling is identified by using at least some of the lane line recognition results obtained by the sensor 110).

[0175] For example, the driving control device may identify the first time point t at which the curvature change rate included in the lane line recognition result satisfies the specified condition when the information obtained by the sensor is used. Act The first curvature change rate (for example, the time point at which the peak phenomenon occurs) and the curvature change rate of the entire road included in the lane line recognition result.

[0176] As an example, based on the first curvature change rate and the curvature change rate of the entire road, the travel control device may identify a first coefficient (eg, aHOLD ) and the coefficient corresponding to the rate of change of curvature of the entire road (e.g., a 0 (k)).

[0177] The first coefficient may be, for example, a value corresponding to the first time point t at which the peak phenomenon is expected to occur in the vehicle. Act The coefficient corresponding to the rate of change of curvature of a point on the road reached (or at the time point immediately before the peak phenomenon occurs).

[0178] The coefficient corresponding to the curvature change rate of the entire road may be, for example, a coefficient corresponding to the curvature change rate of a point on the road that the host vehicle is expected to reach at time point "k". Time point "k" may be, for example, the first time point t Act and the third time point t Deact A point in time between.

[0179] For example, the driving control device may use at least one of the first curvature change rate, the second curvature change rate, or the weight of each of the first curvature change rate and the second curvature change rate, or any combination thereof to identify the first time point t at which the peak phenomenon occurs. Act A third time point t after a specified duration (e.g., 2 seconds) from Deact The expected rate of change of curvature.

[0180] As an example, the driving control device may be based on Figure 7 The first weight α(k) corresponding to the first curvature change rate is set based on the graph shown in FIG.

[0181] As an example, at the first time point t Act (or "k" for t Act time point), the first weight α(k) can be 1.

[0182] As an example, the travel control device may set the first weight α(k) to be the value of the first weight α(k) from the first time point t Act The specified duration from the beginning (for example, to the third time point t Deact duration) period.

[0183] As an example, at the third time point t Deact (or "k" for t Deact time point), the first weight α(k) can be 0.

[0184] The driving control device may run a compensation (eg, calibration) algorithm so that by changing the first time point t Act The first weight α(k) is set to a as a fixed value HOLDTo achieve a relatively large amount of compensation (eg calibration) for the peak phenomenon, at the first time point t Act , as the peaking phenomenon begins to occur, the accuracy decreases by a relatively large amount.

[0185] The travel control device may utilize information related to the curvature change rate that reflects the change in curvature from the first time point t where the peak phenomenon occurs. Act Begin to gradually increase a corresponding to the information initially recognized by the sensor 0 (k), and the curvature change rate is identified as the third time point t at which the compensation algorithm is finally deactivated. Deact Naturally converges to the value a 0 (k) instead of using the value a in lane line recognition HOLD Accordingly, the driving control device can ensure the continuity of the driving control lane line recognition result.

[0186] Figure 8 This is a conceptual diagram of the operation of the travel control device.

[0187] Travel control devices (e.g. Figure 1 The travel control device 100 may utilize sensors (e.g., Figure 1 The driving control device may determine whether at least some of the acquired information (e.g., curvature and curvature change rate) meets specified conditions, and when the specified conditions are met, generate new lane line information for a portion of the lane line through a compensation algorithm.

[0188] Referring to reference numeral 810 , the travel control device may obtain information related to the curvature according to reference numeral 812 using a sensor.

[0189] For example, it can be seen that in the section from 2100ms to 2110ms, the first peak section appears (e.g., Figure 3 The first peak section 315) is a first peak section in which the curvature acquired by the driving control device using the sensor increases instantaneously.

[0190] For example, the driving control device may identify at least one target candidate to apply a compensation algorithm for the peak phenomenon. As the at least one target candidate, at least one target point candidate may be identified at which the vehicle is expected to reach within a specified duration range (e.g., a duration range from a time point 0.4 seconds after the first time point to a time point 0.8 seconds after the first time point) after a preset duration (e.g., 0.4 seconds) from a first time point at which the peak phenomenon occurs.

[0191] For example, the driving control device can generate new lane line information related to the curvature according to the figure mark 814 based on information identified based on the first target point, which is identified based on the first target time point (for example, a time point 0.4 seconds after the first time point).

[0192] For example, the driving control device can generate new lane line information related to the curvature according to the reference numeral 816 based on information identified based on the second target point, which is identified based on the second target time point (for example, a time point 0.6 seconds after the first time point).

[0193] For example, the driving control device can generate new lane line information related to the curvature according to the reference numeral 818 based on information identified based on a third target point, which is identified based on a third target time point (for example, a time point 0.8 seconds after the first time point).

[0194] The driving control device may identify a reference curvature (e.g., approximately -1.4) at a second time point (or a first time point) in the identified lane line information, and identify lane line information having a minimum difference from the reference curvature, wherein the second time point is a time point immediately before the first time point. Figure 8 , the lane line information according to reference numeral 816 can be said to have the minimum difference. The driving control device can use the lane line information according to reference numeral 816 to generate new lane line information.

[0195] Referring to reference numeral 820 , the travel control device may obtain information on a curvature change rate according to reference numeral 822 using a sensor.

[0196] For example, the driving control device may recognize that a second peak segment (eg, Figure 3 The curvature change rate obtained by the driving control device using the sensor increases instantaneously in the second peak section 325 .

[0197] For example, the driving control device may identify at least one target candidate to apply a compensation algorithm for the peak phenomenon. As the at least one target candidate, at least one target point candidate may be identified at which the vehicle is expected to reach within a specified duration range (e.g., a duration range from a time point 0.4 seconds after the first time point to a time point 0.8 seconds after the first time point) after a preset duration (e.g., 0.4 seconds) from a first time point at which the peak phenomenon occurs.

[0198] For example, the driving control device can generate new lane line information related to the curvature according to the reference numeral 824 based on information identified based on the first target point, which is identified based on the first target time point (for example, a time point 0.4 seconds after the first time point).

[0199] For example, the driving control device can generate new lane line information related to the curvature according to the reference numeral 826 based on information identified based on the second target point, which is identified based on the second target time point (for example, a time point 0.6 seconds after the first time point).

[0200] For example, the driving control device can generate new lane line information related to the curvature according to the reference numeral 828 based on information identified based on a third target point, which is identified based on a third target time point (for example, a time point 0.8 seconds after the first time point).

[0201] The driving control device may identify a reference curvature change rate (e.g., approximately 0.5) at a second time point (or a first time point) in the identified lane line information, and identify lane line information having a minimum difference from the reference curvature change rate, wherein the second time point is a time point immediately before the first time point. Figure 8 , the lane line information according to reference numeral 828 can be said to have the minimum difference. The driving control device can use the lane line information according to reference numeral 828 to generate new lane line information.

[0202] If at least one target candidate according to reference numerals 810 and 820 is identified, the driving control device may preferentially generate calibrated lane line information based on the target point (e.g., the second target point) identified by the logic of reference numeral 810. Accordingly, the driving control device may generate new lane line information for a portion of the lane line.

[0203] Fig. 9 This is a conceptual diagram of the operation of the travel control device.

[0204] Travel control devices (e.g. Figure 1 The driving control device 100) can generate new lane line information for a partial section of the lane line through a compensation algorithm.

[0205] Referring to reference numerals 910 to 940, the driving control device may identify a lane line recognition result including information acquired using a sensor (e.g., according to the graph of reference numeral 991). For example, the driving control device may identify at least one of the curvature change rate according to reference numeral 991 in the graph of reference numeral 910, the curvature according to reference numeral 991 in the graph of reference numeral 920, the heading deviation according to reference numeral 991 in the graph of reference numeral 930, or the lateral deviation according to reference numeral 991 in the graph of reference numeral 940, or any combination thereof.

[0206] For example, when at least some of the acquired information (eg, curvature and curvature change rate) meets specified conditions, the travel control device may correct portions of the information through a compensation algorithm.

[0207] For example, the driving control device may enable a compensation algorithm to identify information corresponding to the curve diagram according to reference numeral 992, and generate new lane line information for a portion of the lane line based on the identified information. The driving control device may perform driving control of the vehicle based on the new lane line information.

[0208] Fig.10 This is a conceptual diagram of the operation of the travel control device.

[0209] Travel control devices (e.g. Figure 1 The driving control device 100) can generate new lane line information for a partial section of the lane line through a compensation algorithm.

[0210] For example, the travel control device may identify the time point 1091 at which the maximum peak phenomenon occurs.

[0211] For example, the travel control device may identify the time point 1091 at which the peak phenomenon occurs based on changes in at least some of the information acquired using the sensor.

[0212] For example, the travel control device may identify information of a target point for generating new lane line information.

[0213] For example, the driving control device may identify a first point 1011 and a second point 1012 corresponding to a target point of a lane line. For example, the first point 1011 and the second point 1012 may be points corresponding to a left lane line and a right lane line of a road at the target point, respectively.

[0214] For example, the travel control device may generate new lane line information using at least some of the information about the road at the target point, and control the host vehicle 1001 based on the generated lane line information.

[0215] Fig.11is a flow chart of the driving control method.

[0216] According to one embodiment, a travel control device (e.g., Figure 1 The driving control device) can perform Fig.11 For example, at least some of the components included in the travel control device (e.g., Figure 1 The sensor 110, memory 120 and / or controller 130) may be configured to perform Fig.11 Steps in .

[0217] Steps S1110 to S1130 may be performed in sequence, but are not necessarily performed in sequence. For example, the order of each step may be changed, and at least two steps may be performed in parallel with each other. In addition, the above description of the steps may be briefly described or omitted. Fig.11 The content described corresponds to or is redundant with the content.

[0218] The driving control device may utilize sensors to identify lane line recognition results related to the road on which the vehicle is traveling (step S1110 ).

[0219] The travel control device may determine whether the information on the curvature or the curvature change rate of the road, or any combination thereof, satisfies a specified condition (step S1120).

[0220] For example, the driving control device can determine whether the information acquired in step S1110 satisfies a first condition (in the first condition, the curvature change rate increases and the curvature decreases, or the curvature change rate decreases and the curvature increases) and a second condition (in the second condition, the value of the curvature change is equal to or greater than the critical value).

[0221] For example, when it is identified that information about the curvature or curvature change rate of the road or any combination thereof satisfies a specified condition (eg, yes in step S1120 ), the travel control device may execute step S1130 .

[0222] For example, when it is identified that the information about the curvature or curvature change rate of the road or any combination thereof does not satisfy the specified condition (eg, No in step S1120 ), the travel control device may repeat step S1110 .

[0223] The driving control device may generate calibrated lane line information using at least one of the predicted heading angle, predicted curvature, predicted curvature change rate, or predicted lateral deviation, or any combination thereof, of the target point of the vehicle on the road (step S1130).

[0224] For example, the driving control device may perform driving control of the host vehicle using at least some of the calibrated lane line information.

[0225] Fig.12 A computing system related to a driving control method is shown.

[0226] refer to Fig.12 The computing system 1000 related to the driving control method may include at least one processor 1100 , a memory 1300 , a user interface input device 1400 , a user interface output device 1500 , a storage device 1600 , and a network interface 1700 connected via a bus 1200 .

[0227] The processor 1100 may be a central processing unit (CPU) or a semiconductor device that performs processing based on instructions stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various types of volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) and a random access memory (RAM).

[0228] Therefore, the operations of the methods or algorithms described herein may be implemented directly in hardware or software modules executed by the processor 1100, or in a combination thereof. The software module may exist in a storage medium (i.e., the memory 1300 and / or the storage device 1600), such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, mobile hard disk, and CD-ROM.

[0229] An exemplary storage medium is connected to the processor 1100, and the processor 1100 can read information from the storage medium and can write information to the storage medium. In another method, the storage medium can be integrated with the processor 1100. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). The ASIC can be located in a user terminal. In another method, the processor and the storage medium can exist as separate components in a user terminal.

[0230] The above description merely illustrates the technical idea of ​​the present invention, and those skilled in the art may make various modifications and changes without departing from the basic features of the present invention.

[0231] Therefore, one or more embodiments disclosed in the present invention are not intended to limit the technical concept of the present invention, but are intended to illustrate the present invention, and the scope of the technical concept of the present invention is not limited by the exemplary embodiments. The scope of the present invention should be interpreted as being covered by the scope of the attached claims, and all technical concepts within the scope of the claims should be interpreted as being included in the scope of the present invention.

[0232] The effects of the device and method for controlling driving according to the present invention are as follows.

[0233] One or more example embodiments of the present invention may provide a more adaptive and useful driving experience to a user by ensuring continuity before and after a peak phenomenon occurs and performing a compensation algorithm in a polynomial curve corresponding to a lane line.

[0234] Furthermore, according to the present invention, a driving control apparatus for recognizing a lane line with a polynomial for driving control can provide a lane line recognition result with high accuracy by recognizing a peak phenomenon occurring in some coefficients of the polynomial and appropriately compensating for it.

[0235] In addition, according to the present invention, when a problem such as reduced accuracy of lane line recognition results occurs, at least some of the lane line recognition results are calibrated by a correction algorithm without releasing the driving control to reduce the frequency of control release, thereby providing a driving control function with improved marketability.

[0236] Furthermore, various effects directly or indirectly recognized by this document can be provided.

[0237] As described above, although the present invention has been described with reference to exemplary embodiments and the accompanying drawings, the present invention is not limited thereto, but various modifications and changes may be made by those skilled in the art without departing from the spirit and scope of the invention as claimed in the appended claims.

Claims

1. A device comprising: sensor; a memory storing instructions; as well as Controller; which is operatively connected to the sensor and the memory; Wherein, when the instruction is executed by the controller, the device: Obtaining a lane line recognition result associated with a road on which the vehicle is traveling via a sensor; Based on the lane line recognition result, determining whether information including at least one of the curvature of the road or the curvature change rate of the road satisfies a specified condition; Based on the information satisfying the specified condition, the calibrated lane line information is generated using the expected curvature change rate; wherein the expected curvature change rate is determined based on the following items: The rate of change of curvature, and At least one of an estimated heading angle of the vehicle at a target point on the road, an estimated curvature at the target point, or an estimated lateral deviation at the target point.

2. The device according to claim 1, wherein: The specified conditions include: The first condition includes one of the following: The rate of change of curvature increases and the curvature decreases, or The rate of change of curvature decreases and the curvature increases; and A second condition, the second condition comprising a curvature change exceeding a threshold.

3. The device according to claim 1, wherein: When the instructions are executed by the controller, the device is further caused to: During a duration after the time associated with the information, movement of the vehicle is controlled based on the lane line recognition result and the calibrated lane line information.

4. The device according to claim 1, wherein: When the instructions are executed by the controller, the device is further caused to: determining at least one destination point candidate that the vehicle is expected to arrive at within a duration after a time associated with the information; An expected rate of change of curvature at a target point is determined, wherein the target point is one of the at least one target point candidate.

5. The device according to claim 4, wherein: When the instructions are executed by the controller, the device is further caused to: Determining, among the curvatures included in the lane recognition result, a reference curvature associated with a second time, the second time being before the time associated with the information; Among the at least one target point candidate, a target point is determined that minimizes the difference between the calibrated curvature and the reference curvature at a time point when a specified condition is satisfied.

6. The device according to claim 1, wherein: When the instructions are executed by the controller, the device is further caused to: Determine, based on the curvature change rate included in the lane line recognition result, a first curvature change rate at a time point associated with the information; Determining a second curvature change rate representing an overall curvature change rate of the road based on the curvature change rate included in the lane line recognition result; Based on at least one of the first rate of curvature change, the second rate of curvature change, or a weight of each of the first rate of curvature change and the second rate of curvature change, a predicted rate of curvature change over a duration from a time associated with the information is determined.

7. The device according to claim 6, wherein: The weight of each of the first and second rates of change of curvature includes a first weight of the first rate of change of curvature, wherein the first weight decreases during the duration.

8. The device according to claim 1, wherein: When the instructions are executed by the controller, the device is further caused to: Determine the vehicle's speed through sensors; The target point is determined based on at least one of a travel speed or a predetermined duration.

9. A method comprising: The controller obtains a lane line recognition result associated with the road on which the vehicle is traveling via the sensor; Determining, by the controller based on the lane line recognition result, whether information including at least one of the curvature of the road or the curvature change rate of the road satisfies a specified condition; Based on the information satisfying a specified condition, the controller generates calibrated lane line information using an estimated curvature change rate, wherein the estimated curvature change rate is determined based on the following items: The rate of change of curvature, and At least one of an estimated heading angle of the vehicle at a target point on the road, an estimated curvature at the target point, or an estimated lateral deviation at the target point.

10. The method according to claim 9, wherein: The specified conditions include: The first condition includes one of the following: The rate of change of curvature increases and the curvature decreases, or The rate of change of curvature decreases and the curvature increases; and A second condition, the second condition comprising a curvature change exceeding a threshold.

11. The method according to claim 9, further comprising: The movement of the vehicle is controlled by the controller based on the lane line recognition result and the calibrated lane line information during a duration after the time associated with the information.

12. The method according to claim 9, further comprising: determining, by the controller, at least one destination point candidate that the vehicle is expected to reach within a duration after a time associated with the information; An expected rate of change of curvature at a target point is determined by a controller, wherein the target point is one of the at least one target point candidate.

13. The method according to claim 12, further comprising: Determining, by the controller, a reference curvature associated with a second time among the curvatures included in the lane recognition result, the second time being before the time associated with the information; Among the at least one target point candidate, a target point that minimizes the difference between the calibrated curvature and the reference curvature at a time point when a specified condition is satisfied is determined by the controller.

14. The method according to claim 9, further comprising: Based on the curvature change rate included in the lane line recognition result, determining, by the controller, a first curvature change rate at a time point associated with the information; Determine a second curvature change rate representing an overall curvature change rate of the road based on the curvature change rate included in the lane line recognition result; A predicted rate of curvature over a duration from a time associated with the information is determined by the controller based on at least one of the first rate of curvature, the second rate of curvature, or a weight of each of the first rate of curvature and the second rate of curvature.

15. The method according to claim 14, wherein: The weight of each of the first and second rates of change of curvature includes a first weight of the first rate of change of curvature, wherein the first weight decreases during the duration.

16. A computer readable medium storing instructions which, when executed, cause: The controller obtains a lane line recognition result associated with the road on which the vehicle is traveling via the sensor; Determining, by the controller based on the lane line recognition result, whether information including at least one of the curvature of the road or the curvature change rate of the road satisfies a specified condition; Based on the information satisfying a specified condition, the controller generates calibrated lane line information using an estimated curvature change rate, wherein the estimated curvature change rate is determined based on the following items: The rate of change of curvature, and At least one of an estimated heading angle of the vehicle at a target point on the road, an estimated curvature at the target point, or an estimated lateral deviation at the target point.

17. The computer-readable medium of claim 16, wherein: The specified conditions include: The first condition includes one of the following: The rate of change of curvature increases and the curvature decreases, or The rate of change of curvature decreases and the curvature increases; and A second condition, the second condition comprising a curvature change exceeding a threshold.

18. The computer-readable medium of claim 16, wherein: When the instructions are executed, the following is further achieved: The movement of the vehicle is controlled by the controller based on the lane line recognition result and the calibrated lane line information during a duration after the time associated with the information.

19. The computer-readable medium of claim 16, wherein: When the instructions are executed, the following is further achieved: determining, by the controller, at least one destination point candidate that the vehicle is expected to reach within a duration after a time associated with the information; An expected rate of change of curvature at a target point is determined by a controller, wherein the target point is one of the at least one target point candidate.

20. The computer-readable medium of claim 19, wherein: When the instructions are executed, the following is further achieved: Determining, by the controller, a reference curvature associated with a second time among the curvatures included in the lane recognition result, the second time being before the time associated with the information; Among the at least one target point candidate, a target point that minimizes the difference between the calibrated curvature and the reference curvature at a time point when a specified condition is satisfied is determined by the controller.

Images