Method and device for predicting vehicle path based on intention of driver

Abstract

A method and apparatus for predicting a vehicle path based on a driver's intent are disclosed. The method for predicting the vehicle path comprises the following steps: acquiring road information and driving information of a vehicle; determining a driving intent of the driver based on at least one of a steering angle, a steering angular velocity, or a yaw rate of the vehicle; determining a predicted path generation time based on the driving intention of the driver; and generating a derived path based on the predicted path generation time.

Description

[0001] Cross-reference to related applications

[0002] This application claims priority to Korean Patent Application No. 10-2024-0138535, filed with the Korean Intellectual Property Office on October 11, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to a method and apparatus for predicting vehicle routes based on driver intent. More specifically, it relates to a method and apparatus for improving route prediction accuracy by changing the predicted route generation time according to the changed driver driving intent. Background Technology

[0004] Various advanced driver assistance systems (ADAS) have been developed to assist drivers or enable autonomous driving in complex traffic conditions. A typical ADAS predicts the path of the test vehicle for path planning, collision avoidance decisions, and other purposes. For example, an ADAS can use the predicted path to calculate the probability of the test vehicle colliding with nearby objects and to warn the driver in advance and / or implement control measures to take evasive action.

[0005] Autonomous driving systems predict the path of a test vehicle using physics-based models, which are based on the vehicle's driving information, including speed, acceleration, yaw rate, steering angle, and steering angular velocity. Furthermore, autonomous driving systems can improve path prediction accuracy by using maneuver-based models, which are based on road information, including lane information. To balance the characteristics of both physics-based and maneuver-based models, existing autonomous driving systems use both types of models separately for path prediction, combining predicted paths with physics-based models, and combining predicted paths with maneuver-based models for further path prediction.

[0006] However, the above-mentioned method for generating predicted paths may predict paths that drivers cannot follow, mainly because it does not take the driver's intentions into account, resulting in inaccurate path prediction results. Summary of the Invention

[0007] This disclosure provides a method and apparatus that, by determining the predicted path generation time based on driver intent, can generate a natural predicted path even when driver intent changes. The disclosure aims to provide a path prediction method and apparatus that reflects road conditions and vehicle driving status by predicting paths for autonomous vehicles based on driver intent (hereinafter also referred to as driving intent). The technical objectives to be achieved by this disclosure are not limited to the foregoing, and other technical objectives not mentioned above will be clearly understood by those skilled in the art from the following detailed description.

[0008] According to this disclosure, a method for predicting vehicle paths includes the following steps: acquiring road information and vehicle driving information through at least one processor; determining the driver's driving intention based on at least one of the vehicle's steering angle, steering angular velocity, or yaw rate through at least one processor; determining the predicted path generation time based on the driver's driving intention through at least one processor; and generating a derived path based on the predicted path generation time through at least one processor.

[0009] According to at least one aspect, this disclosure provides a method for predicting vehicle paths, the method comprising: acquiring road information and vehicle driving information; determining a driver's driving intention based on at least one of the vehicle's steering angle, steering angular velocity, or yaw rate; determining a predicted path generation time based on the driver's driving intention; and generating a derived path based on the predicted path generation time.

[0010] According to this disclosure, an apparatus for predicting vehicle paths includes: at least one memory configured to store instructions; and at least one processor, wherein the at least one processor is configured to execute instructions stored in the at least one memory such that the processor: acquires road information and driving information of the vehicle; determines the driver's driving intention based on at least one of the vehicle's steering angle, steering angular velocity, or yaw rate; determines a predicted path generation time based on the driver's driving intention; and generates a derived path based on the predicted path generation time.

[0011] According to another aspect, this disclosure provides an apparatus for predicting vehicle paths, comprising: at least one memory configured to store instructions; and at least one processor, wherein the at least one processor executes instructions to cause the processor to perform the following steps: acquiring road information and driving information of the vehicle; determining the driver's driving intention based on at least one of the vehicle's steering angle, steering angular velocity, or yaw rate; determining a predicted path generation time based on the driver's driving intention; and generating a derived path based on the predicted path generation time.

[0012] According to at least one embodiment, by determining the predicted path generation time based on the driver's driving intention, this disclosure can still predict a smooth and natural path even when the driver's driving intention changes.

[0013] According to another embodiment, by performing path prediction for autonomous vehicles based on the driver's driving intentions, this disclosure can reflect road conditions and vehicle driving status.

[0014] A vehicle may include the above-described device.

[0015] According to this disclosure, a non-transient computer-readable medium includes program instructions executable by a processor. The computer-readable medium includes: program instructions for acquiring road information and driving information of a vehicle; program instructions for determining a driver's driving intention based on at least one of the vehicle's steering angle, steering angular velocity, or yaw rate; program instructions for determining a predicted path generation time based on the driver's driving intention; and program instructions for generating a derived path based on the predicted path generation time.

[0016] The beneficial effects of this disclosure are not limited to those described above; those skilled in the art can clearly understand other beneficial effects of this disclosure not mentioned above from the following description. Attached Figure Description

[0017] Figure 1 is a schematic block diagram of a path prediction device (100) according to at least one embodiment of the present disclosure.

[0018] Figure 2 is an example state flowchart illustrating the path prediction device (100) according to at least one embodiment of the present disclosure for determining driving intention.

[0019] Figure 3 is an example state flowchart illustrating a method for determining the predicted path generation time according to at least one embodiment of the present disclosure.

[0020] Figure 4 is a flowchart of path prediction using a physics-based model according to at least one embodiment of the present disclosure.

[0021] Figures 5A, 5B and 5C are schematic diagrams illustrating derived paths generated by a path prediction apparatus according to at least one embodiment of the present disclosure.

[0022] Figure 6 is a flowchart of a process for calculating vehicle position within a prediction time window length according to at least one embodiment of the present disclosure.

[0023] Figure 7 is a flowchart of generating an export path according to at least one embodiment of the present disclosure.

[0024] Figure 8 is a schematic block diagram illustrating a computing device that can be used to implement the method or apparatus according to the present disclosure. Detailed Implementation

[0025] It should be understood that the terms "vehicle" or "of a vehicle" or other similar terms as used herein include general motor vehicles, such as passenger cars (including sport utility vehicles (SUVs), buses, trucks, various commercial vehicles, watercraft (including various vessels), aircraft, etc.), and include hybrid electric vehicles, electric vehicles, plug-in hybrid electric vehicles, hydrogen-powered vehicles, and other alternative fuel vehicles (e.g., fuels derived from resources other than petroleum). Hybrid electric vehicles, as referred to herein, are vehicles with two or more power sources, such as vehicles that simultaneously utilize gasoline and electric power.

[0026] The terminology used herein is for descriptive purposes only and is not intended to limit this disclosure. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” used herein are also intended to include the plural forms. It should also be understood that when the terms “comprising” and / or “including” are used herein, the presence of the stated feature, integer, step, operation, element, and / or component is explicitly stated, but the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof is not excluded. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. Throughout this specification, unless otherwise explicitly stated, the word “comprising” and variations thereof, such as “including” or “having,” should be understood to include the stated elements but not exclude any other elements. Furthermore, the terms “unit,” “-er,” “-or,” and “module” described in the specification refer to a unit for performing at least one function and operation and can be implemented by hardware components or software components and combinations thereof.

[0027] Furthermore, the control logic of this disclosure may be embodied in a non-transitory computer-readable medium, including executable program instructions that are executed by a processor, controller, etc. Examples of computer-readable media include, but are not limited to, ROM, RAM, optical disc (CD)-ROM, magnetic tape, floppy disk, flash drive, smart card, and optical data storage device. The computer-readable medium may also be distributed across networked computer systems, enabling it to be stored and executed in a distributed architecture via, for example, a telematics server or a controller area network (CAN).

[0028] Here, some exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the following description, the same reference numerals are preferred to denote the same elements, although these elements are shown in different drawings. Furthermore, in the following description of some embodiments, detailed descriptions of known functions and configurations incorporated herein will be omitted for clarity and brevity.

[0029] Furthermore, terms such as first, second, A, B, (a), (b) are used only to distinguish one component from another, and not to imply or suggest the order, sequence or order of components.

[0030] The following detailed description and accompanying drawings are intended to illustrate exemplary embodiments of this disclosure and are not intended to represent the only embodiments that may be practiced with this disclosure.

[0031] As used in this article, path prediction refers to the function of an autonomous driving system in predicting the future path of an autonomous vehicle (the test vehicle).

[0032] In this disclosure, the prediction time window refers to the time interval from the current time to the future time that the autonomous driving system needs to predict. The length of the prediction time window can be expressed in units of time. For example, if the autonomous driving system predicts the path from the current time to a future time four seconds later, then the length of the prediction time window is four seconds.

[0033] Figure 1 is a schematic block diagram of a path prediction device 100 according to at least one embodiment of the present disclosure.

[0034] The path prediction device 100 includes a memory 110 and a processor 120. The path prediction device 100 can be implemented as an embedded device, a server, an electronic device within an autonomous driving system, etc. Not all of the blocks shown in Figure 1 are essential components; some modules included in the path prediction device 100 can be added, modified, or removed. Furthermore, Figure 1 The components shown represent elements categorized by function, and at least one component can be integrated into a formal implementation within a real-world physical environment.

[0035] The memory 110 stores the data and commands required for running the path prediction device 100.

[0036] Memory 110 can store vehicle driving information and road information acquired using at least one sensor included in the vehicle. Vehicle driving information may include vehicle speed, acceleration, steering angle, steering angular velocity, heading angle, yaw rate, accelerator / brake pedal engagement, and / or gear shift position. Road information may include lane information. As used herein, steering angle refers to a measurement of the position and rate of rotation of the vehicle's steering wheel. Steering angular velocity refers to the rate of steering wheel rotation (e.g., the change in steering angle over time). Yaw rate refers to the rate of rotation of the vehicle about its vertical axis, i.e., how quickly the vehicle turns left or right or rotates.

[0037] Memory 110 can store the predicted path from a physics-based model. Path prediction using a physics-based model predicts the vehicle position by applying acquired driving information to a dynamics-based vehicle path curvature estimation. The vehicle's behavior can be represented as constant curvature based on the path prediction from the physics-based model. Furthermore, memory 110 can store the vehicle driving information, reference steering angle, and reference steering angular velocity required to calculate the predicted path.

[0038] Processor 120 controls the overall operation of path prediction device 100. Processor 120 is implemented as one or more processors. Processor 120 can execute instructions stored in memory 110.

[0039] The processor 120 may include a driving intent determination module 122, a predicted path generation timing module 124, an exported path generation module 126, and a configuration file generation module 128.

[0040] The driving intent determination module 122 can determine the driver's driving intent based on vehicle driving information stored in the memory 110. The predicted path generation timing module 124 can determine the predicted path generation time based on the driver's driving intent. The exported path generation module 126 can generate an exported path based on the predicted path generation time. The configuration file generation module 128 can generate a velocity profile and a curvature profile for predicting the vehicle path based on the driver's driving intent.

[0041] As described in this article, the term "predicted path generation time" refers to the appropriate length of time within the prediction time window that reflects the driver's driving intentions.

[0042] The driving intention determination module 122 can determine the driver's driving intention based on the vehicle driving information stored in the memory 110. The driver's driving intention includes the driver's intention to turn the vehicle at a certain angle, drive straight, or turn in the opposite direction. The driver's driving intention can be determined based on the vehicle's steering angle, steering angular velocity, yaw rate, etc.

[0043] Driver intentions include "gentle lane regaining", "gentle lane change", "unknown", "abrupt lane change", and "abrupt lane regaining".

[0044] "Smooth lane change" indicates that the driver intends to smoothly change lanes to a side lane parallel to the current lane. If the vehicle steering angle is greater than or equal to a preset first reference steering angle but less than a preset second reference steering angle, and if the vehicle steering angular velocity is greater than or equal to a preset first reference steering angular velocity but less than a preset second reference steering angular velocity, then the driving intention determination module 122 determines the driver's driving intention as "smooth lane change". The first reference steering angle, second reference steering angle, first reference steering angular velocity, and second reference steering angular velocity are set based on the steering angle and steering angular velocity that occur during a smooth lane change.

[0045] "Smooth lane return" indicates the driver's intention to change lanes to a side lane parallel to the driver's current lane and then smoothly return to the vehicle's original path. If the vehicle steering angle is less than or equal to a preset third reference steering angle, and the vehicle yaw rate is out of phase with the vehicle steering angle, the driving intention determination module 122 determines the driver's driving intention as "smooth lane return." The vehicle yaw rate being out of phase with the vehicle steering angle means that due to the phase delay of the yaw rate output, the yaw rate and steering angle have opposite signs. The third reference steering angle is set based on the steering angle that occurs when the driver attempts to change lanes and then smoothly return to the vehicle's original path.

[0046] "Sudden lane change" means that the driver intends to suddenly change the path to a side lane parallel to the driver's current lane. If the vehicle steering angle is greater than or equal to the preset second reference steering angle and the vehicle steering angular velocity is greater than or equal to the preset second reference steering angular velocity, the driving intention determination module 122 determines the driver's driving intention as "sudden lane change".

[0047] "Sudden lane return" indicates that the driver intends to change lanes to a side lane parallel to the current lane and then suddenly return to the original lane. If the vehicle steering angle exceeds the preset third reference steering angle, and the vehicle steering angle and vehicle steering angular velocity are out of phase, the driving intention determination module 122 determines the driver's driving intention as "sudden lane return". The vehicle steering angle and vehicle steering angular velocity being out of phase means that due to the phase delay of the steering angle output, the steering angle and steering angular velocity have opposite signs.

[0048] "Unknown" indicates a non-lane-related driving scenario or a scenario where the driver's driving intention is difficult to determine. Lane-related driving means that the driver is driving within the lane and is able to perceive it. When it is difficult to determine whether the driver's current driving intention is a smooth lane change, a smooth lane return, a sudden lane change, or a sudden lane return, the driving intention determination module 122 can determine the driving intention as "unknown".

[0049] The driving intent determination module 122 can use a state flowchart to prevent unintentional actions from the driver. In one example, the lane restoration state satisfies the prerequisites for the lane change state. Therefore, a transition from the lane change state to the lane restoration state may occur, but a transition from the unknown state to the lane restoration state may not occur.

[0050] Figure 2 is an example state flowchart illustrating the path prediction device 100 according to at least one embodiment of the present disclosure for determining driving intention.

[0051] When a driver begins to determine their driving intention, that intention is unknown.

[0052] If the vehicle steering angle is greater than or equal to the first reference steering angle but less than the second reference steering angle, and if the vehicle steering angular velocity is greater than or equal to the first reference steering angular velocity but less than the second reference steering angular velocity, then the driving intention determination module 122 switches the driving intention from unknown to smooth lane change.

[0053] Conversely, if the vehicle steering angle is greater than or equal to the first reference steering angle and greater than or equal to the second reference steering angle, or if the vehicle steering angular velocity is greater than or equal to the first reference steering angular velocity and greater than or equal to the second reference steering angular velocity, then the driving intention determination module 122 switches the driving intention from smooth lane change to unknown.

[0054] If the vehicle steering angle is greater than or equal to the second reference steering angle and the vehicle steering angular velocity is greater than or equal to the second reference steering angular velocity, then the driving intention determination module 122 switches the driving intention from unknown to sudden lane change.

[0055] Conversely, if the vehicle steering angle is less than the second reference steering angle, or if the vehicle steering angular velocity is less than the second reference steering angular velocity, the driving intention determination module 122 switches the driving intention from sudden lane change to unknown.

[0056] If the vehicle steering angle is greater than or equal to the second reference steering angle, and if the vehicle steering angular velocity is greater than or equal to the second reference steering angular velocity, then the driving intention determination module 122 switches the driving intention from a smooth lane change to a sudden lane change.

[0057] Conversely, if the vehicle steering angle is greater than or equal to the first reference steering angle but less than the second reference steering angle, and if the vehicle steering angular velocity is greater than or equal to the first reference steering angular velocity but less than the second reference steering angular velocity, then the driving intention determination module 122 switches the driving intention from sudden lane change to gradual lane change.

[0058] If the vehicle steering angle is equal to or less than the preset third reference steering angle, and if the vehicle speed is out of phase with the vehicle steering angle, the driving intention determination module 122 switches the driving intention from smooth lane change to smooth lane restoration.

[0059] Conversely, if the vehicle steering angle is greater than or equal to the first reference steering angle but less than the second reference steering angle, and if the vehicle speed is greater than or equal to the first reference steering angle speed but less than the second reference steering angle speed, then the driving intention determination module 122 switches the driving intention from smooth lane recovery to smooth lane change.

[0060] If the vehicle steering angle exceeds the preset third reference steering angle, and if the vehicle steering angle is out of phase with the vehicle steering angular velocity, the driving intention determination module 122 restores the driving intention from sudden lane change to sudden lane.

[0061] Conversely, if the vehicle steering angle is greater than or equal to the second reference steering angle and the vehicle steering angular velocity is greater than or equal to the second reference steering angular velocity, the driving intention determination module 122 switches the driving intention from sudden lane recovery to sudden lane change.

[0062] If the vehicle steering angle is equal to or less than the preset third reference steering angle, and if the vehicle yaw rate is out of phase with the vehicle steering angle, the driving intention determination module 122 switches the driving intention from smooth lane recovery to sudden lane recovery.

[0063] Conversely, if the vehicle steering angle is equal to or less than the preset third reference steering angle, and if the vehicle yaw rate is out of phase with the vehicle steering angle, the driving intention determination module 122 switches the driving intention from sudden lane recovery to gradual lane recovery.

[0064] Predictive path generation timing module 124 determines the predicted path generation time (T) based on the driver's driving intention. g,t Specifically, the predicted path generation timing module 124 determines the predicted path generation time based on the conversion conditions of driving intention.

[0065] The configuration file generation module 128 generates speed and curvature distributions for predicting vehicle paths based on the driver's driving intentions.

[0066] In this disclosure, speed distribution refers to information representing the change of vehicle speed over time, and curvature distribution refers to information representing the change of vehicle path curvature over time. Speed ​​and curvature distributions can be represented as arrays. For example, if the prediction time window is 4 seconds, and the driving speed or curvature is predicted at 0.1-second intervals, the speed or curvature distribution can consist of 41 elements.

[0067] Predicted path generation time (T) g,t It can be based on the prediction time window length (T) p The driver's current driving intention, the driver's past driving intentions, and the previously determined predicted path generation time (T) g,t-1 It was calculated.

[0068] Figure 3 is an example state flowchart illustrating a method for determining the predicted path generation time according to at least one embodiment of the present disclosure.

[0069] If the driver's driving intention changes to a smooth lane change, the predicted path generation timing module 124 can change the predicted path generation time to, for example, T p .

[0070] If the driver's driving intention changes to a sudden lane change, the predicted path generation timing module 124 can change the predicted path generation time to, for example, T p .

[0071] If the driver's driving intention changes to a smooth lane return state, the predicted path generation timing module 124 can change the predicted path generation time to, for example, T p .

[0072] If the driver's driving intention changes to a sudden lane re-entry state, the predicted path generation timing module 124 can change the predicted path generation time to, for example, T p .

[0073] If the driver's driving intention changes to an unknown state, the predicted path generation timing module 124 can change the predicted path generation time to, for example, T. p .

[0074] When the driver maintains the intention to make a gentle lane change, the predicted path generation timing module 124 can adjust the predicted path generation time from the previously determined predicted path generation time (T). g,t-1 The first value preset in advance.

[0075] When the driver maintains the intention to resume driving smoothly in the lane, the predicted path generation timing module 124 can adjust the predicted path generation time from the previously determined predicted path generation time (T). g,t-1 The second value preset in advance.

[0076] The predicted path generation timing module 124 can reduce the time required to reflect the physics-based model by advancing the predicted path generation time from the smooth lane restoration state or smooth lane change state. This enables the generation of predicted paths that reflect road information in the smooth lane restoration state or smooth lane change state.

[0077] When the driver maintains the intention to suddenly change lanes, the predicted path generation timing module 124 can adjust the predicted path generation time from the determined predicted path generation time (T). g,t-1 The third value of the delay preset.

[0078] When the driver maintains the intention to suddenly return to the lane, the predicted path generation timing module 124 can adjust the predicted path generation time from the determined predicted path generation time (T). g,t-1 The fourth value of the delay preset.

[0079] The predicted path generation timing module 124 can increase the time reflecting the physics-based model by further delaying the predicted path generation time from sudden lane change states or sudden lane resumption states. This enables the generation of predicted paths reflecting driving information in sudden lane change states or smooth lane resumption states.

[0080] Therefore, this disclosure can generate a predicted path reflecting road information in a smooth lane change state or a smooth lane restoration state, and generate a predicted path reflecting driving information in a sudden lane change state or a sudden lane restoration state.

[0081] In at least one embodiment of this disclosure, when the driver's driving intention is initially determined, the driving intention is unknown, and the prediction time window is 4 seconds. If the driving intention changes from an unknown state to a smooth lane change state, the prediction path generation time is changed to... T p Or 1 second. When maintaining a smooth lane change, the predicted path generation time will continuously decrease from 1 second based on a preset first variable.

[0082] For example, if the driving intention changes from a smooth lane change to a smooth lane return, the predicted path generation time is changed to 0.5 seconds or... T p .

[0083] Figure 4 is a flowchart of path prediction using a physics-based model according to at least one embodiment of the present disclosure.

[0084] The path prediction device 100 can acquire vehicle driving information using at least one sensor included inside the vehicle (S400). The vehicle driving information may include the vehicle's speed, acceleration, steering angle, steering angular rate, heading angle, yaw rate, accelerator / brake pedal engagement and / or gear shift position.

[0085] The configuration file generation module 128 can generate a speed distribution and curvature distribution for vehicle path prediction based on the acquired driving information (S402).

[0086] The path prediction device 100 can generate a predicted path based on the generated velocity and curvature distribution using a physics-based model (S404). Path prediction using the physics-based model predicts the vehicle position by applying acquired driving information to a dynamics-based vehicle path curvature estimation. The path prediction based on the physics-based model can represent the vehicle's behavior as a constant curvature.

[0087] Because physics-based path prediction can predict vehicle paths with a single curvature value, its advantage lies in its greater sensitivity to driving information while generating predicted paths, especially when the prediction time window is relatively short. However, in cases of sudden lane changes, physics-based path prediction may produce paths that fail to reflect the driver's intentions.

[0088] Figure 5A , 5B Figures 5 and 5C are schematic diagrams illustrating derived paths generated by a path prediction apparatus according to at least one embodiment of the present disclosure.

[0089] As used herein, the term “derived path” refers to the vehicle path determined by the path prediction device 100, thus reflecting the driver’s driving intention.

[0090] Figure 5A is a schematic diagram illustrating a derived path generated by a path prediction device 100 according to at least one embodiment of the present disclosure. Figure 5B shows an example of a derived path generated by the path prediction device 100 when the driving intention is a smooth lane return. Figure 5C shows an example of a derived path generated by the path prediction device 100 when the driving intention is a sudden lane return.

[0091] The exported path generation module 126 can set a target point based on the driver's driving intention. This target point represents the location to be reached via the generated predicted path [x]. e , y e , φ e ]. x e For the vertical target position, y e For the lateral target position, φe This refers to the vehicle's heading angle.

[0092] In at least one embodiment of this disclosure, the derived path generation module 126 does not set a target location in an unknown state. In a smooth lane change state or a sudden lane change state, the derived path generation module 126 sets the center point of the target lane to be reached as the target point of the predicted path. In a smooth lane restoration state or a sudden lane restoration state, the derived path generation module 126 keeps the center point of the target lane as the target point of the predicted path.

[0093] The exported path generation module 126 can set the position at the prediction path generation time on the prediction path obtained from the physics-based model [x]. T , y T , φ T ]. x T It is located at the vertical position of the prediction path generation time, and it is set on the prediction path of the physics-based model. T It is located at the horizontal position during the prediction path generation time, and is set on the prediction path of the physics-based model. φ T It is the heading angle. For example, in a smooth lane change, it corresponds to a predicted path generation time of 1 second ( T p The vehicle's position can be set to the position at the time the predicted path is generated.

[0094] The exported path generation module 126 can generate a third-order polynomial curve for the exported path, with its tangent passing through the position and target point at the predicted path generation time. The third-order polynomial curve of the exported path is shown in Equation 1.

[0095] [Formula 1]

[0096]

[0097] y represents the lateral position of the vehicle, and x represents the longitudinal position of the vehicle.

[0098] The tangent of the third-order polynomial curve of the derived path satisfies Equation 2 at the position and target point at the time of predicted path generation.

[0099] [Formula 2]

[0100]

[0101] Since the tangent of the third-order polynomial curve of the derived path passes through the position and target point at the time of prediction path generation, the derivative of the third-order polynomial curve at each point should be zero.

[0102] The coefficients of the third-order polynomial curve obtained by using Gaussian elimination are as follows.

[0103] [Formula 3]

[0104]

[0105]

[0106]

[0107]

[0108] The mathematical description of Gaussian elimination is omitted here. The derived path generation module 126 can obtain the third-order polynomial curve of the derived path by substituting the coefficients obtained by Gaussian elimination into the third-order polynomial curve.

[0109] Figure 6 This is a flowchart illustrating the calculation of vehicle position within a prediction time window length according to at least one embodiment of the present disclosure.

[0110] The exported path generation module 126 can calculate the current longitudinal travel distance based on the speed distribution and heading angle at previous time points (S600). In this disclosure, speed distribution refers to information representing the change of vehicle speed over time. Heading angle refers to the angle of the vehicle's direction of travel.

[0111] The exported path generation module 126 can calculate the current heading angle (S602) based on the third-order polynomial curve of the exported path and the longitudinal travel distance.

[0112] The exported path generation module 126 can calculate the vehicle position based on the current heading angle and the current longitudinal travel distance (S604).

[0113] The exported path generation module 126 repeats the above steps within the length of the prediction time window to continuously update the vehicle's position and heading. This improves the accuracy of the predicted path. The exported path generation module 126 can repeat the exported path generation process after the vehicle's updated position.

[0114] Figure 7 This is a flowchart of the process of generating an export path according to at least one embodiment of the present disclosure.

[0115] The path prediction device 100 can acquire vehicle driving information (S700) using at least one sensor included in the vehicle. For example, vehicle driving information may include vehicle speed, acceleration, steering angle, steering angular velocity, heading angle, yaw rate, accelerator / brake pedal depress amount, and / or gear shift position. Furthermore, the path prediction device 100 can acquire road information. For example, road information may include lane information. The vehicle driving information and road information can be stored in the memory 110.

[0116] The path prediction device 100 can determine whether the driver is in a lane-related driving state (S702). Determining whether the driver is in a lane-related driving state means determining whether the driver is in a state where he can perceive the lane.

[0117] The driving intention determination module 122 can determine the driver's driving intention based on stored vehicle driving information (S704). The driver's driving intention indicates the driver's intention to turn the vehicle to a certain degree, drive straight, turn in the opposite direction, etc. The driver's driving intention can be determined based on the vehicle's steering angle, steering angular velocity, yaw rate, etc.

[0118] The predicted route generation timing module 124 can determine the predicted route generation time based on the driver's driving intention (S706). Specifically, the predicted route generation timing module 124 can determine the predicted route generation time based on the transition conditions of the driving intention. The predicted route generation time can be calculated based on the driver's current driving intention, the driver's past driving intention, and the previously determined predicted route generation time.

[0119] The exported path generation module 126 can generate an exported path based on the predicted path generation time (S708). The exported path generation module 126 can set a target point based on the driver's driving intention. The exported path generation module 126 can set the vehicle position at the predicted path generation time on the predicted path obtained from the physics-based model. The exported path generation module 126 can generate a third-order polynomial curve of the exported path, with its tangential direction passing through the vehicle position and target point at the predicted path generation time. The exported path generation module 126 can calculate the current longitudinal distance traveled based on the speed distribution and heading angle at past time points. The exported path generation module 126 can calculate the current heading angle based on the third-order polynomial curve of the exported path and the longitudinal distance traveled. The exported path generation module 126 can calculate the vehicle position based on the current heading angle and the current longitudinal distance traveled.

[0120] Figure 8 is a schematic block diagram of an illustrative configuration of a computing device 800 that can be used to implement the methods or apparatus according to the present disclosure.

[0121] The computing device 800 may include some or all of the following: memory 810, processor 820, storage device 830, input / output interface 840, and communication interface 850. The computing device 800 may be a fixed computing device, such as a desktop computer or server, or a mobile computing device, such as a laptop or smartphone. The computing device 800 may include any dedicated hardware accelerator capable of efficiently processing AI model calculations. For example, the computing device 800 may include a graphics processing unit (GPU), a tensor processing unit (TPU), or a neural processing unit (NPU).

[0122] Memory 810 may store programs that enable processor 820 to perform methods or operations under various embodiments of this disclosure. For example, the program includes a plurality of instructions executable by processor 820, and the plurality of instructions may be executed by processor 820 to perform the methods or operations described above. Memory 810 may be a single memory or multiple memories. In this case, information required to perform the methods or operations according to various embodiments of this disclosure may be stored in a single memory or distributed across multiple memories. When memory 810 consists of multiple memories, they may be physically separated. Memory 810 may include at least one of volatile memory or non-volatile memory. For example, volatile memory may include static random access memory (SRAM) or dynamic random access memory (DRAM), and non-volatile memory may include flash memory.

[0123] Processor 820 may include at least one core capable of executing at least one set of instructions. Processor 820 may execute instructions stored in memory 810. Processor 820 may be a single processor or multiple processors.

[0124] Even if the power supply to the computing device 800 is interrupted, the storage device 830 can retain the stored data. For example, the storage device 830 may include non-volatile memory, or may include storage media such as magnetic tape, optical disc, or magnetic disk. Programs stored in the storage device 830 may be loaded into the memory 810 before being executed by the processor 820. The storage device 830 may store files written in a programming language, and programs generated by a compiler or the like may be loaded from files into the memory 810. The storage device 830 may store data awaiting processing by the processor 820 and / or data already processed by the processor 820.

[0125] The input / output interface 840 provides an interface with input devices such as a keyboard and mouse and / or output devices such as a display device and a printer. Users can trigger the processor 820 to execute programs through the input devices and / or view the processing results of the processor 820 through the output devices.

[0126] Communication interface 850 provides access to external networks. Computing device 800 can communicate with other devices through communication interface 850.

[0127] Each element of the apparatus or method according to this disclosure can be implemented as hardware, software, or a combination of hardware and software. The functionality of each element can be implemented in software, and a microprocessor can be implemented to execute the software functions corresponding to each element.

[0128] Various implementations of the systems and technologies described herein can be achieved through digital electronic circuits, integrated circuits, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. Various implementations may include schemes implemented by one or more computer programs executable by the programmable system. The programmable system includes at least one programmable processor (which may be a dedicated processor or a general-purpose processor), coupled to a storage system to receive and transfer data and instructions thereto, at least one input device, and at least one output device. The computer program (also referred to as a program, software, software application, or code) includes instructions for the programmable processor and is stored in a computer-readable recording medium.

[0129] Computer-readable recording media can include all types of storage devices used for storing computer-readable data. Computer-readable recording media can be non-volatile or non-transitory media, such as read-only memory (ROM), random access memory (RAM), optical disc ROM (CD-ROM), magnetic tape, floppy disk, or optical data storage devices. Furthermore, computer-readable recording media can also include transient media, such as data transmission media. Moreover, computer-readable recording media can be distributed across computer systems connected via a network, and computer-readable program code can be stored and executed in a distributed architecture.

[0130] Although the flowcharts / sequence diagrams in this specification show operations performed sequentially, this is merely an exemplary description of the technical concept of one embodiment of this disclosure. In other words, those skilled in the art to which one embodiment of this disclosure pertains will understand that various modifications and changes can be made without departing from the essential characteristics of the embodiments of this disclosure; that is, the order shown in the flowcharts / sequence diagrams can be changed, and one or more operations can be performed in parallel. Therefore, the flowcharts / sequence diagrams are not limited to a chronological order.

[0131] Although exemplary embodiments of this disclosure have been described for illustrative purposes, those skilled in the art will understand that various modifications, additions, and substitutions can be made without departing from the spirit and scope of this disclosure. Therefore, for the sake of brevity and clarity, exemplary embodiments of this disclosure have been described. The scope of the technical concept of this disclosure is not limited to the illustrations. Accordingly, those skilled in the art will understand that the scope claimed by this disclosure is not limited to the embodiments specifically described above, but is limited by the claims and their equivalents.

Claims

1. A method for predicting vehicle paths, the method comprising the following steps: Obtain road information and vehicle driving information; The driver's driving intention is determined based on at least one of the vehicle's steering angle, steering angular velocity, or yaw rate. The predicted path generation time is determined based on the driver's driving intention; as well as The export path is generated based on the predicted path generation time.

2. The method according to claim 1, wherein, The steps for determining the driver's driving intention include: if the steering angle is greater than or equal to a preset first reference steering angle and less than a preset second reference steering angle, and if the steering angular velocity is greater than or equal to a preset first reference steering angular velocity and less than a preset second reference steering angular velocity, then the driver's driving intention is determined as the first driving intention. The first driving intention refers to the driver's intention to make a smooth change of path.

3. The method according to claim 1, wherein, The steps for determining the driver's driving intention include: if the steering angle is equal to or less than a preset third reference steering angle and the yaw rate has the opposite sign to the steering angle, then the driver's driving intention is determined as the second driving intention. The second driving intention refers to the driver's intention to resume a smooth path.

4. The method according to claim 1, wherein, The steps for determining the driver's driving intention include: if the steering angle is greater than or equal to a preset second reference steering angle and the steering angular velocity is greater than or equal to a preset second reference steering angular velocity, then the driver's driving intention is determined as a third driving intention. The third driving intention refers to the driver's intention to make a sudden change of route.

5. The method according to claim 1, wherein, The steps for determining the driver's driving intention include: if the steering angle is greater than a preset third reference steering angle and the steering angle and steering angular velocity have opposite signs, then the driver's driving intention is determined as a fourth driving intention. The fourth driving intention refers to the driver's intention to suddenly resume the route.

6. The method according to claim 1, wherein, The step of determining the predicted path generation time includes: changing the predicted path generation time in response to a change in the driver's driving intention.

7. The method according to claim 1, wherein, The step of determining the predicted path generation time includes: changing the predicted path generation time in response to the driver's continued driving intention.

8. The method according to claim 1, wherein, The steps to generate the export path include: setting target points based on the driver's driving intentions.

9. The method according to claim 1, wherein, The derived path is a third-order polynomial curve, and the third-order polynomial curve is tangentially oriented through the position coordinates of the target point and the position coordinates at the time of the predicted path generation.

10. An apparatus for predicting vehicle paths, comprising: At least one memory configured to store instructions; as well as At least one processor, Wherein, the at least one processor is configured to execute instructions stored in the at least one memory, such that the processor: Obtain road information and vehicle driving information; The driver's driving intention is determined based on at least one of the vehicle's steering angle, steering angular velocity, or yaw rate. The predicted path generation time is determined based on the driver's driving intention; as well as The export path is generated based on the predicted path generation time.

11. The apparatus according to claim 10, wherein, Determining the driver's driving intention includes: if the steering angle is greater than or equal to a preset first reference steering angle and less than a preset second reference steering angle, and if the steering angular velocity is greater than or equal to a preset first reference steering angular velocity and less than a preset second reference steering angular velocity, then the driver's driving intention is determined as the first driving intention. The first driving intention refers to the driver's intention to make a smooth change of path.

12. The apparatus according to claim 10, wherein, Determining the driver's driving intention includes: if the steering angle is equal to or less than a preset third reference steering angle and the yaw rate has the opposite sign to the steering angle, then the driver's driving intention is determined as the second driving intention. The second driving intention refers to the driver's intention to resume a smooth path.

13. The apparatus according to claim 10, wherein, Determining the driver's driving intention includes: if the steering angle is greater than or equal to a preset second reference steering angle and the steering angular velocity is greater than or equal to a preset second reference steering angular velocity, then the driver's driving intention is determined as a third driving intention. The third driving intention refers to the driver's intention to make a sudden change of route.

14. The apparatus according to claim 10, wherein, Determining the driver's driving intention includes: if the steering angle is greater than a preset third reference steering angle and the steering angle and steering angular velocity have opposite signs, then the driver's driving intention is determined as a fourth driving intention. The fourth driving intention refers to the driver's intention to suddenly resume the route.

15. The apparatus according to claim 10, wherein, Determining the predicted path generation time includes: changing the predicted path generation time in response to a change in the driver's driving intention.

16. The apparatus according to claim 10, wherein, Determining the predicted path generation time includes: changing the predicted path generation time in response to the driver's continued driving intention.

17. The apparatus according to claim 10, wherein, The generated export path includes setting target points based on the driver's driving intentions.

18. The apparatus according to claim 10, wherein, The derived path is a third-order polynomial curve, and the third-order polynomial curve is tangentially oriented through the position coordinates of the target point and the position coordinates at the time of the predicted path generation.

19. A vehicle comprising the device according to claim 10.

20. A non-transitory computer-readable medium, the non-transitory computer-readable medium comprising program instructions executable by a processor, the computer-readable medium comprising: Program instructions used to obtain road and driving information of vehicles; The program instructions that determine the driver’s driving intention based on at least one of the vehicle’s steering angle, steering angular velocity, or yaw rate. Program instructions that determine the predicted path generation time based on the driver's driving intentions; as well as Program instructions that generate export paths based on predicted path generation time.

Images