Vehicle driving control device and vehicle driving control program

Abstract

To improve convenience in lane keeping control or lane keeping assist control by further enhancing the effect of reducing discomfort felt by occupants such as a driver of a vehicle. [Solution] A vehicle driving control device (3) that controls the lateral position of a host vehicle within a lane while the host vehicle is traveling includes an estimated value calculation unit (318) and a determination unit (319). The estimated value calculation unit calculates an estimated value related to the host vehicle's future proximity to a lane boundary line. Specifically, the estimated value calculation unit calculates a nonlinear estimated value that is an estimated value based on the assumption that the host vehicle will approach the boundary line on a nonlinear trajectory. The determination unit determines to start executing vehicle driving control to reduce discomfort felt by occupants of the host vehicle when the estimated value is less than a threshold value.

Description

[Technical Field]

[0001] The present invention relates to a vehicle driving control device and a vehicle driving control program for controlling the lateral position of a vehicle within a lane while the vehicle is traveling. [Background technology]

[0002] A known technology for effectively preventing lane departure while reducing driver discomfort is a lane keeping assist device, such as that described in Patent Document 1. This lane keeping assist device performs feedback control based on the angular deviation of the host vehicle's direction of travel relative to the lane it is traveling in, so as to reduce the deviation. In this process, the control gain is corrected based on the distance of the host vehicle from a lateral edge reference position, which is located on the side of the left or right lane edge in the host vehicle's direction of travel, and the control gain is corrected so that the shorter the distance of the host vehicle from the lateral edge reference position, the larger the control gain. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-208602 Summary of the Invention [Problem to be solved by the invention]

[0004] In this type of technology, convenience can be improved by further enhancing the effect of reducing discomfort felt by occupants such as the driver of the vehicle. [Means for solving the problem]

[0005] The vehicle travel control device (3) is configured to control the lateral position of the host vehicle (C) within the lane (Lm) while the host vehicle (C) is traveling. The vehicle driving control device according to claim 1 comprises: an estimated value calculation unit (318) that calculates an estimated value related to the degree of approach of the host vehicle to the lane boundary line (Lb) at a future time point; a determination unit (319) that determines to start execution of vehicle driving control for reducing discomfort felt by an occupant of the host vehicle when the estimated value is less than a threshold value; Equipped with The estimated value calculation unit calculates a nonlinear estimated value, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2). The vehicle driving control device according to claim 3 comprises: an estimated value calculation unit (318) that calculates an estimated value related to the degree of approach of the host vehicle to the lane boundary line (Lb) at a future time point; a determination unit (319) that determines, when the estimated value is less than a threshold value, to start execution of steering control or deceleration control, which is vehicle travel control of the host vehicle; Equipped with The estimated value calculation unit calculates a nonlinear estimated value, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2).

[0006] The vehicle driving control program is a computer program executed by a vehicle driving control device (3) that controls the lateral position of the host vehicle (C) within the lane (Lm) while the host vehicle (C) is traveling. The vehicle driving control program according to claim 10 includes the steps of: A process of calculating an estimated value corresponding to a future approaching degree of the host vehicle to the lane boundary line (Lb); a process of determining, when the estimated value is less than a threshold value, to start execution of vehicle driving control for reducing discomfort felt by an occupant of the host vehicle; Including, In the process of calculating the estimated value, a nonlinear estimated value is calculated, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2). The vehicle driving control program according to claim 11 includes the steps of: A process of calculating an estimated value corresponding to a future approaching degree of the host vehicle to the lane boundary line (Lb); a process of determining whether to start executing steering control or deceleration control of the host vehicle when the estimated value is less than a threshold value; Including, In the process of calculating the estimated value, a nonlinear estimated value is calculated, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2).

[0007] In addition, in each section of the application documents, each element may be assigned a reference symbol in parentheses. However, such reference symbol merely indicates an example of the correspondence between the element and the specific means described in the embodiment described below. Therefore, the present invention is not limited in any way by the above-mentioned reference symbols. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a schematic diagram showing an overview of lane keeping-related control in a host vehicle equipped with an in-vehicle system that implements a vehicle driving control device and a vehicle driving control program according to an embodiment of the present invention; [Figure 2] FIG. 2 is a block diagram showing a schematic configuration of the in-vehicle system shown in FIG. [Figure 3] 3 is a block diagram showing a schematic functional configuration of the vehicle driving control device shown in FIG. 2. FIG. [Figure 4] FIG. 4 is a conceptual diagram showing an outline of the operation of the vehicle driving control device shown in FIG. [Figure 5] FIG. 4 is a conceptual diagram showing an outline of the operation of the vehicle driving control device shown in FIG. [Figure 6] 4 is a flowchart showing an outline of an example of operation of the vehicle driving control device shown in FIG. 3. [Figure 7] 7 is a flowchart showing an outline of an example of LK vehicle control shown in FIG. 6. [Figure 8] 7 is a flowchart showing an outline of another example of the LK vehicle control shown in FIG. 6. [Figure 9]4 is a flowchart showing an outline of another example of the operation of the vehicle driving control device shown in FIG. 3. [Figure 10] 10 is a flowchart showing an outline of still another example of operation of the vehicle driving control device shown in FIG. 3. DETAILED DESCRIPTION OF THE INVENTION

[0009] (Embodiment) Hereinafter, exemplary embodiments or specific examples of the present invention will be described with reference to the drawings as appropriate. Note that the following embodiments and their modifications, as well as the descriptions in the drawings, are schematic or simplified for the purpose of concisely explaining the contents of the present invention, and are not intended to limit the contents of the present invention in any way. Therefore, it goes without saying that the descriptions in the drawings do not necessarily coincide with the specific device configurations that are actually manufactured and sold. In other words, unless expressly limited by the applicant in the prosecution history of this application, it goes without saying that the present invention should not be interpreted as being limited by the descriptions in the drawings and the device configurations, functions, or operations described below corresponding thereto.

[0010] (In-vehicle system configuration) Referring to FIG. 1, an in-vehicle system 1 is mounted on a host vehicle C, which is an automobile traveling on a road. "Host vehicle C" refers to a vehicle equipped with the in-vehicle system 1. The in-vehicle system 1 is an advanced safety driving system, and is configured as a driving automation system that performs at least part of the driving operations of occupants including a driver, i.e., at least one of steering, acceleration / deceleration, starting, and stopping. Here, the definition of "driving automation" in a driving automation system is clarified as follows.

[0011] Driving automation includes Level 1 "driver assistance," Level 2 "highly automated driving," Level 3 "conditional automation," Level 4 "highly automated driving," and Level 5 "fully automated driving" in SAE J3016. SAE J3016 is a standard published by SAE International, where SAE stands for Society of Automotive Engineers. When referring to levels 1 to 2 collectively without specifying that it is Level 1, it is sometimes simply referred to as "driver assistance." Furthermore, levels 3 to 5 are sometimes collectively referred to simply as "autonomous driving."

[0012] Note that driving automation levels equivalent to levels 1 and 2 in SAE J3016 are sometimes referred to as "automated driving with a periphery monitoring obligation." According to this definition, levels 3 to 5 in SAE J3016 can be referred to as "automated driving without a periphery monitoring obligation."

[0013] The in-vehicle system 1 is configured to be able to perform lane keeping control as a driving assistance function or an automatic driving function. Lane keeping control refers to controlling the lateral position of the host vehicle C within the host lane Lm, which is the lane L in which the host vehicle C is traveling, to be within a range inside the boundary lines Lb on both the left and right sides of the host lane Lm. Lane keeping control may also be referred to as lane departure suppression control.

[0014] In this embodiment, the boundary line Lb is a virtual line that passes through the center in the width direction of the lane markings Lp on both the left and right sides of the vehicle's lane Lm. The lane markings Lp are road markings on the road surface that form road markings, including an outer lane marking that is the boundary between the lane L and the shoulder, and a lane marking that separates adjacent lanes L. The boundary line Lb is straight on straight roads and curved on curved roads.

[0015] In this embodiment, the in-vehicle system 1 is configured to control the lateral distance D between a reference point Pc of the host vehicle C and a boundary line Lb during lane keeping control. The reference point Pc may be provided at the left front end and the right front end of the host vehicle C. Specifically, the reference point Pc may be provided at, for example, one of the left and right front ends of the vehicle body, the left and right front ends of a circumscribing rectangle of the vehicle body, an outer position on the contact patch of the front wheels, etc.

[0016] 2, the in-vehicle system 1 includes a sensor unit 2, a vehicle driving control device 3, and an output unit 4. The sensor unit 2, the vehicle driving control device 3, and the output unit 4 are connected to each other via an in-vehicle network line 5 so as to be able to communicate information with each other.

[0017] The in-vehicle network line 5 is configured to comply with a predetermined communication standard such as CAN (international registered trademark: international registration number 1048262A). CAN (international registered trademark) is an abbreviation for Controller Area Network. Note that the in-vehicle network line 5 may have, in addition to a main network conforming to CAN (international registered trademark), another main network or sub-network conforming to LIN, FlexRay, or the like. LIN is an abbreviation for Local Interconnect Network.

[0018] The sensor unit 2 is a collective term for various in-vehicle sensors for detecting or sensing the driving state and driving environment of the host vehicle C. Specifically, in this embodiment, the in-vehicle system 1 includes, as the sensor unit 2, a vehicle speed sensor 21, an acceleration sensor 22, a yaw rate sensor 23, a steering angle sensor 24, a brake pedal sensor 25, an accelerator pedal sensor 26, a GNSS sensor 27, a driver status monitor 28, and a camera 29.

[0019] The vehicle speed sensor 21 is provided to detect the vehicle speed of the host vehicle C. The acceleration sensor 22 is provided to detect the acceleration acting on the host vehicle C. The yaw rate sensor 23 is provided to detect the yaw rate of the host vehicle C.

[0020] The steering angle sensor 24 is provided to detect the steering angle of the host vehicle C. The brake pedal sensor 25 is provided to detect the amount of brake pedal operation by the occupant of the host vehicle C. The accelerator pedal sensor 26 is provided to detect the amount of accelerator pedal operation by the occupant of the host vehicle C.

[0021] The GNSS sensor 27 is provided to detect the current position of the vehicle C. The driver status monitor 28 is provided to detect the line of sight and wakefulness of the driver based on a captured image of the face of an occupant of the vehicle C, i.e., the driver. The configurations and functions of these various sensors included in the sensor unit 2 are well known technologies at the time of filing of the present application, and therefore further detailed description will be omitted.

[0022] The camera 29 is provided to capture images of the surroundings of the host vehicle C in order to detect targets around the host vehicle C. "Targets" include not only three-dimensional objects such as other vehicles, pedestrians, and guardrails, but also two-dimensional objects such as road markings drawn on the road surface. In this embodiment, a side camera as the camera 29 is mounted on the host vehicle C in order to detect the lateral distance D shown in FIG. 1. The side camera is provided to capture images of the sides, i.e., the left and right sides, of the host vehicle C.

[0023] The vehicle driving control device 3 is a so-called ADAS ECU configured to be able to perform ADAS operations including lane keeping control, and is configured as an on-board computer equipped with a processor 31 and one or more storage media 32. ADAS stands for Advanced Driver-Assistance Systems. ADAS operations include automated driving operations. ECU stands for Electronic Control Unit.

[0024] The processor 31 includes one or more arithmetic units having the functions or configuration of a CPU or MPU, and their peripheral circuits (e.g., timer circuits, etc.). CPU stands for Central Processing Unit. MPU stands for Micro Processing Unit.

[0025] The storage medium 32 includes at least a ROM or a nonvolatile rewritable memory among various non-transient physical storage media such as a ROM or a nonvolatile rewritable memory. ROM is an abbreviation for Read Only Memory. The term "storage medium" can also be referred to as "recording medium." A nonvolatile rewritable memory is a storage device that allows information to be rewritten while the power is on but retains information in an unrewritable manner while the power is off, such as a flash memory.

[0026] The vehicle driving control device 3 is configured so that the processor 31 reads out and executes a computer program including a vehicle driving control program according to the present invention from a storage medium 32, thereby realizing predetermined functions related to driving the host vehicle C. The storage medium 32 stores the computer program as well as various data such as initial values, maps, and look-up tables required to execute the computer program. The vehicle driving control device 3 according to this embodiment and the vehicle driving control program executed thereby will be described in detail below.

[0027] The in-vehicle system 1 includes a display 41, a speaker 42, a steering device 43, a braking device 44, and a powertrain device 45 as an output unit 4 that uses the results of arithmetic processing by the vehicle driving control device 3. The display 41 is provided to visually display various information corresponding to the results of arithmetic processing by the vehicle driving control device 3. The speaker 42 is provided to audibly output various information corresponding to the results of arithmetic processing by the vehicle driving control device 3. In other words, the display 41 and the speaker 42 are configured to provide various pieces of information related to ADAS operations, including lane keeping control, to the occupants audiovisually.

[0028] The steering device 43 includes a steering ECU and a steering mechanism (not shown), and is configured to operate the steering mechanism under the control of the steering ECU to adjust the traveling direction of the host vehicle C. The braking device 44 includes a brake ECU and a brake mechanism (not shown), and is configured to decelerate or stop the host vehicle C by operating the brake mechanism under the control of the brake ECU.

[0029] The powertrain device 45 includes a powertrain ECU and a powertrain mechanism (not shown), and is configured to generate driving force for the host vehicle C by operating the powertrain mechanism under the control of the powertrain ECU. The powertrain mechanism includes an engine and / or a traction motor as a power source, and a power transmission mechanism that transmits the driving force generated by the power source to the wheels.

[0030] The above-mentioned ECUs and mechanisms included in the steering device 43, the brake device 44, and the powertrain device 45 are well-known technologies at the time of filing of this application, and therefore further detailed description thereof will be omitted.

[0031] (Vehicle driving control device) 3 shows functional components related to lane keeping control according to this embodiment that are implemented on the ECU by executing a vehicle driving control program in the vehicle driving control device 3. The functional components of the vehicle driving control device 3 include a sensor information acquisition unit 311, a switch state detection unit 312, a boundary recognition unit 313, a forward gaze time acquisition unit 314, a reference time acquisition unit 315, a positional relationship acquisition unit 316, a trajectory calculation unit 317, a characteristic value calculation unit 318, and a determination unit 319.

[0032] The sensor information acquisition unit 311 is configured to acquire information corresponding to the detection results or sensing results of the sensor unit 2, i.e., the vehicle speed sensor 21 to the camera 29. That is, the sensor information acquisition unit 311 is configured to hold the detection results or sensing results of the vehicle speed sensor 21 etc. in chronological order for a predetermined period of time. The switch state detection unit 312 is configured to detect the setting state of the ADAS function, enabled / disabled, by a switch operation by an occupant of the host vehicle C.

[0033] The boundary line recognition unit 313 recognizes the boundary line Lb shown in FIG. 1 based on images of the left and right sides of the vehicle C captured by the camera 29. That is, the boundary line recognition unit 313 recognizes the lane marking paint Lp based on the image information and generates the boundary line Lb, which is a virtual straight line or curve, based on the results of this recognition. The recognition of the lane marking paint Lp based on image information and the generation of the boundary line Lb based on the results of this recognition were well known techniques at the time of filing this application. Therefore, further detailed description of these techniques will be omitted.

[0034] The gaze-forward time acquisition unit 314 acquires, i.e., calculates, the gaze-forward time of the driver of the host vehicle C based on the detection results of the vehicle speed sensor 21 and the driver status monitor 28. Specifically, the gaze-forward time acquisition unit 314 calculates the gaze-forward time by dividing the driver's gaze-forward distance based on the detection results of the driver status monitor 28 by the detection result of the vehicle speed of the host vehicle C by the vehicle speed sensor 21. The gaze-forward time corresponds to the reference time related to the gaze-forward distance according to the present invention.

[0035] The reference time acquisition unit 315 is configured to acquire a reference time used when calculating a travel trajectory of the host vehicle C approaching the boundary line Lb from the current position. The reference time corresponds to a retroactive time from the present time when referring to the past lateral position of the host vehicle C to calculate the travel trajectory. The reference time and its acquisition will be described in detail later.

[0036] The positional relationship acquisition unit 316 acquires the positional relationship between the reference point Pc and the boundary line Lb in the lateral direction, i.e., the road width direction, based on the current lateral position of the host vehicle C in the host lane Lm. In other words, the positional relationship acquisition unit 316 calculates the lateral distance D between the boundary line Lb on the left and right, which the host vehicle C is closest to, and the reference point Pc that is closest to that boundary line.

[0037] The trajectory calculation unit 317 calculates the above-mentioned traveling trajectory based on the change in the lateral position of the host vehicle C up to the present time. Specifically, in this embodiment, the trajectory calculation unit 317 calculates the linear trajectory M1 shown in Fig. 4 and the non-linear trajectory M2 shown in Fig. 5.

[0038] Specifically, as shown in Fig. 4, the trajectory calculation unit 317 calculates a linear trajectory M1 based on the lateral position of the reference point Pc of the host vehicle C at the current time tc and the lateral position of the reference point Pc at a time tc-td that is a time td before the current time tc. The linear trajectory M1 is a traveling trajectory that assumes that the host vehicle C will approach the boundary line Lb in a straight line without changing its traveling direction or vehicle speed, based on the traveling direction and vehicle speed of the host vehicle C at the current time tc.

[0039] Furthermore, the trajectory calculation unit 317 is configured to calculate a nonlinear trajectory M2 based on changes in the lateral position of the host vehicle C at predetermined time intervals. The nonlinear trajectory M2 is a traveling trajectory that assumes that the host vehicle C approaches the boundary line Lb nonlinearly, i.e., in a curved manner, without changing its vehicle speed, based on the vehicle speed of the host vehicle C at the current time tc. In this embodiment, the "predetermined time interval" referred to here corresponds to the reference time acquired by the reference time acquisition unit 315.

[0040] Specifically, as shown in Figure 5, the trajectory calculation unit 317 calculates the nonlinear trajectory M2 by nonlinear regression based on the lateral position of the reference point Pc of the vehicle C at the current time tc, the lateral position of the reference point Pc at a time tc-td that is a time td before the current time tc, and the lateral position of the reference point Pc at a time tc-te that is a time te before the current time tc.

[0041] Specifically, the function representing the nonlinear trajectory M2 may be, for example, a well-known nonlinear function such as an exponential function, a logarithmic function, an n-th order function, or an n-th order polynomial. In calculating the nonlinear trajectory M2, the times td and te correspond to the above-mentioned reference times. The reference times may be set based on the time interval required for the driver of the host vehicle C to make a situation assessment. Specifically, for example, the time td is about 1 second, and the time te is about 0.5 seconds, i.e., te = td / 2.

[0042] The times td and td as reference times can be obtained by optimization through experiments or computer simulations. That is, the reference time acquisition unit 315 has a function of reading default values ​​of the times td and t e from the storage medium 32. The reference time acquisition unit 315 can also have a function of learning and correcting the times td and t e using the default values ​​as initial values. As the learning and correction, for example, normal feedback correction or correction by machine learning can be used.

[0043] The characteristic value calculation unit 318 as an estimated value calculation unit according to the present invention is configured to calculate a characteristic value as an estimated value related to the degree of proximity of the vehicle C to the boundary line Lb at a future point in time based on the lateral distance D between the vehicle C and the boundary line Lb and the driving trajectory calculated by the trajectory calculation unit 317.

[0044] For example, the so-called TTLC, i.e., boundary line crossing time, can be used as the characteristic value calculated by the characteristic value calculation unit 318. TTLC is an abbreviation for Time To Line Crossing, and corresponds to the estimated time until departure from the lane.

[0045] As shown in Fig. 4, the TTLC assuming that the host vehicle C approaches the boundary line Lb on the linear trajectory M1 is referred to as the linear intersection time TTLC1. The linear intersection time TTLC1 corresponds to a linear estimation value according to the present invention. In other words, the linear intersection time TTLC1 is the time estimated to elapse until the reference point Pc reaches the linear trajectory intersection point P1, which is the intersection point between the linear trajectory M1 and the boundary line Lb.

[0046] 5, the TTLC assuming that the host vehicle C approaches the boundary line Lb on the nonlinear trajectory M2 is referred to as the nonlinear crossing time TTLC2. The nonlinear crossing time TTLC2 corresponds to the nonlinear estimated value according to the present invention. In other words, the nonlinear crossing time TTLC2 is the time estimated to elapse until the reference point Pc reaches the nonlinear trajectory crossing point P2, which is the intersection point between the nonlinear trajectory M2 and the boundary line Lb.

[0047] Alternatively, the characteristic value calculated by the characteristic value calculation unit 318 can be, for example, the lateral distance D of the host vehicle C, i.e., the reference point Pc, at a future point in time after the predicted time of the driver of the host vehicle C has elapsed from the current time tc. The predicted time can be a default value calculated based on the forward gaze distance of an average driver, for example, about 2 seconds. Alternatively, the predicted time can be corrected by learning based on detection data of the actual forward gaze distance and vehicle speed of the driver of the host vehicle C. For example, normal feedback correction or correction by machine learning can be used as the learning correction.

[0048] In this case, the lateral distance D as a characteristic value indicates the distance in the road width direction from the reference point Pc to the boundary line Lb, with a positive or negative sign. That is, a positive value of the lateral distance D corresponds to a state in which the entire vehicle C is within the host lane Lm and the reference point Pc has not yet reached the boundary line Lb, a value of 0 corresponds to a state in which the reference point Pc overlaps the boundary line Lb, and a negative value corresponds to a state in which the reference point Pc has crossed the boundary line Lb and reached the adjacent lane L. The lateral distance D calculated assuming a linear trajectory M1 corresponds to a linear estimated value, and the lateral distance D calculated assuming a nonlinear trajectory M2 corresponds to a nonlinear estimated value.

[0049] When the characteristic value calculated by the characteristic value calculation unit 318 is less than a threshold value, the determination unit 319 determines to start the execution of steering control and / or deceleration control, which are vehicle driving controls for maintaining the lateral position of the host vehicle C within the host lane Lm. Specifically, the determination unit 319 determines to start the execution of such vehicle driving control when the smaller of the nonlinear estimated value and the linear estimated value is less than a threshold value.

[0050] More specifically, for example, when TTLC is used, the determination unit 319 selects the smaller of the linear intersection time TTLC1 and the non-linear intersection time TTLC2. If the selected value is less than the forward gaze time threshold, the determination unit 319 determines to start the execution of steering control and / or deceleration control, which are vehicle driving controls for maintaining the lateral position of the host vehicle C within the host lane Lm.

[0051] Alternatively, for example, when the lateral distance D is used, the determination unit 319 selects the smaller of the lateral distance D calculated on the assumption of the linear trajectory M1 and the lateral distance D calculated on the assumption of the nonlinear trajectory M2. Then, when the selected value is less than 0 as a threshold value, the determination unit 319 determines to start the execution of the vehicle driving control.

[0052] (Operation overview) Below, an overview of the lane keeping control operation by the vehicle driving control device 3 according to this embodiment will be described along with the effects of this configuration. Note that the vehicle driving control device 3 according to this embodiment, the vehicle driving control method and vehicle driving control program executed thereby, and the storage medium 32 on which this program is recorded may hereinafter be collectively referred to as "this embodiment."

[0053] As is well known, in recent years, there has been a surge in the number of automobiles equipped with driving assistance functions or automatic driving functions. The installation of driving assistance functions or automatic driving functions improves the convenience of the host vehicle C.

[0054] An example of a driving assistance function or an autonomous driving function is lane keeping control. Lane keeping control is a driving control that detects the lateral position of the host vehicle C within the host lane Lm from an image of the lane marking paint Lp captured by the camera 29, and maintains the lateral position of the host vehicle C within the host lane Lm. Lane keeping control is performed at levels 1 to 5 of SAE J3016.

[0055] Here, the driver of the host vehicle C may feel uneasy during lane keeping control. This feeling of uneasiness is mainly caused by a discrepancy between the timing when the driver expects vehicle control such as steering to start and the actual timing when control starts. That is, even if the host vehicle C is correctly being controlled to keep lane by the in-vehicle system 1, depending on the behavior of the host vehicle C, the driver may feel that the host vehicle C is about to deviate from the host lane Lm. The driver who feels uneasy may take an override action such as steering intervention.

[0056] It is known that such a sense of discomfort can occur even when the vehicle C is traveling in approximately the center of the lane Lm and the steering torque applied by the system is minute. In this regard, the inventors have found the following facts as a result of extensive research.

[0057] During lane keeping control, the driver of the vehicle C monitors the surroundings of the vehicle C by moving his or her eyes not only within a narrow range in the traveling direction but also to the left and right of the vehicle C. In this case, if the timing of the steering control in the direction opposite to the boundary line Lb that the vehicle C is currently approaching is delayed compared to the timing expected by the driver of the vehicle C, this will lead to a sense of discomfort.

[0058] Therefore, the inventors have focused on the relationship between the look-at-the-front time and the TTLC and found that it is possible to determine that a sense of discomfort will occur when the TTLC is shorter than the look-at-the-front time. In other words, it is possible to predict or estimate the sense of discomfort felt by the driver of vehicle C based on the relationship between the look-at-the-front time and the TTLC.

[0059] Furthermore, the inventors have found that in predicting or determining such discomfort, using the nonlinear crossing time TTLC2 as a reference rather than the linear crossing time TTLC1 often makes it possible to reduce the discomfort. In other words, in the nonlinear regression of the lateral distance D, it has been found that the timing at which the host vehicle C is predicted to cross the boundary line Lb within the forward gaze time often coincides with the timing at which the driver of the host vehicle C feels discomfort.

[0060] The inventors have also found that it is possible to properly evaluate the sense of discomfort when using the predicted distance, i.e., the lateral distance D at a future point in time after the predicted time has elapsed, instead of the TTLC. Specifically, it has been found that the timing when the predicted distance is predicted to be less than 0 and the timing when the driver of the host vehicle C feels discomfort often coincide with each other.

[0061] From the above, in this embodiment, when a characteristic value related to the future proximity of the host vehicle C to the boundary line Lb becomes less than a threshold value, the determination unit 319 determines to start execution of vehicle driving control to reduce discomfort felt by occupants of the host vehicle C. This makes it possible to effectively reduce discomfort felt by occupants such as the driver of the host vehicle C, thereby improving the convenience of the host vehicle C.

[0062] (Operation example: first embodiment) A specific example of operation corresponding to this embodiment will be described below. Fig. 6 is a flowchart showing such an example of operation. In the flowchart shown in Fig. 6, "S" is an abbreviation for "Step." Also, "LK" is an abbreviation for Lane Keeping. The same applies to the flowcharts shown in Fig. 7 and subsequent figures.

[0063] In step 101, processor 31 acquires the setting state of the driving automation mode, i.e., the state of whether or not lane keeping control is currently on. Next, in step 102, processor 31 determines whether or not lane keeping control is on.

[0064] If the lane keeping control is turned off (i.e., step 102=NO), processor 31 skips all processing from step 103 onwards. On the other hand, if the lane keeping control is turned on (i.e., step 102=YES), processor 31 causes the processing to proceed to step 103.

[0065] In step 103, processor 31 determines whether or not there has been a steering intervention equivalent to an override by the driver of host vehicle C. If there has been a steering intervention (i.e., step 103=YES), processor 31 causes the process to proceed to step 104. In step 104, processor 31 cancels the lane keeping control (i.e., sets it to OFF).

[0066] On the other hand, if there is no steering intervention (i.e., step 103=NO), processor 31 proceeds to step 105. In step 105, processor 31 executes vehicle control for keeping the vehicle in the lane.

[0067] Fig. 7 shows details of the processing content of step 105 shown in Fig. 6. Referring to Fig. 7, first, processor 31 executes the processing of steps 201 to 208 in order.

[0068] In step 201, processor 31 acquires the forward gaze time. In step 202, processor 31 acquires the current lateral position of host vehicle C.

[0069] In step 203, processor 31 calculates a linear trajectory M1 based on the lateral position acquired in step 202. In step 204, processor 31 calculates a linear intersection time TTLC1. The calculation of the linear trajectory M1 and the linear intersection time TTLC1 is outlined in FIG. 4.

[0070] In step 205, processor 31 calculates a nonlinear trajectory M2 based on the lateral position acquired in step 202. In step 206, processor 31 calculates a nonlinear crossing time TTLC2. An overview of the calculation of the nonlinear trajectory M2 and the nonlinear crossing time TTLC2 is as shown in FIG.

[0071] In step 207, processor 31 selects the smaller of linear intersection time TTLC1 and non-linear intersection time TTLC2 as the TTLC for determining the start of movement. In step 208, processor 31 determines whether the TTLC for determining the start of movement selected in step 207 is less than the gaze-ahead time acquired in step 201.

[0072] If the TTLC for determining the start of operation is less than the look-ahead time (i.e., step 208=YES), processor 31 proceeds to step 209. In step 209, processor 31 determines to start corrective steering control or deceleration control in a direction to move host vehicle C away from boundary line Lb on the approaching side, in order to reduce discomfort felt by occupants such as the driver. In contrast, if the TTLC for determining the start of operation is equal to or greater than the look-ahead time (i.e., step 208=NO), processor 31 skips the processing of step 209 and temporarily terminates vehicle control for lane keeping.

[0073] As described above, according to this embodiment, the nonlinear intersection time TTLC2 and the look-ahead time calculated based on the nonlinear trajectory M2 are used to determine whether to start corrective steering control or deceleration control in a direction to move the host vehicle C away from the approaching lane marking Lp. This increases the sensitivity of predicting discomfort in the vehicle behavior, and effectively reduces discomfort felt by occupants such as the driver.

[0074] Furthermore, in this embodiment, the characteristic value is calculated based on the lateral distance D between the host vehicle C and the boundary line Lb. This lateral distance D can be calculated using information on the sides of the host vehicle C obtained by a side camera. In other words, this embodiment can perform good lane keeping control without using information in front of the host vehicle C obtained by a front camera or the like. Therefore, this embodiment can perform good lane keeping control while suppressing increases in processing load and device costs.

[0075] (Operation example: second embodiment) A second embodiment of the present invention will be described below. Note that in the following description of the second embodiment, differences from the first embodiment will be mainly described. In addition, identical or equivalent parts in the first and second embodiments are assigned the same reference numerals. Therefore, in the following description of the second embodiment, for components having the same reference numerals as those in the first embodiment, the description of the first embodiment can be appropriately cited unless there is a technical contradiction or a special additional explanation. The same applies to the third and subsequent embodiments described below.

[0076] This embodiment shows a specific example of operation using a predicted distance instead of TTLC. Fig. 8 is a flowchart showing such an example of operation. In this embodiment, the processing shown in the flowchart of Fig. 6 is the same as that of the first embodiment, but the content of step 105 is different from that of the first embodiment. In other words, Fig. 8 corresponds to a modified example in which a part of Fig. 7 is changed.

[0077] In this embodiment, in lane keeping vehicle control, first, the processes of steps 301 to 308 are executed in order. In step 301, the processor 31 acquires a predicted time. In step 302, the processor 31 acquires the current lateral position of the host vehicle C.

[0078] At step 303, processor 31 calculates a linear trajectory M1 based on the lateral position acquired at step 302. At step 304, processor 31 calculates a linear prediction distance D1. At step 305, processor 31 calculates a non-linear trajectory M2 based on the lateral position acquired at step 302. At step 306, processor 31 calculates a non-linear prediction distance D2.

[0079] In step 307, processor 31 selects the smaller of linear prediction distance D1 and non-linear prediction distance D2 as the predicted distance for determining whether or not a movement has started. In step 308, processor 31 determines whether or not the predicted distance for determining whether or not a movement has started selected in step 307 is less than a threshold value. The threshold value is, for example, 0.

[0080] If the predicted distance for determining the start of operation is less than the threshold value (i.e., step 308=YES), processor 31 proceeds to step 309. In step 309, processor 31 determines to start corrective steering control or deceleration control in a direction to move host vehicle C away from boundary line Lb on the approaching side, in order to reduce discomfort felt by occupants such as the driver. On the other hand, if the predicted distance for determining the start of operation is equal to or greater than the threshold value (i.e., step 308=NO), processor 31 skips the processing of step 309 and temporarily ends vehicle control for keeping the vehicle in the lane.

[0081] As described above, according to this embodiment, the nonlinear predicted distance D2 calculated based on the nonlinear trajectory M2 is used to determine whether to start corrective steering control or deceleration control in a direction to move the host vehicle C away from the approaching lane marking Lp, thereby achieving the same effects as those of the first embodiment.

[0082] (Operation example: third embodiment) This embodiment shows an example in which the predicted time used to calculate the lateral distance D of the host vehicle C, i.e., the reference point Pc, at a future point in time is adjusted, i.e., corrected, by machine learning. That is, in this embodiment, a default value stored in advance in the storage medium 32 is used as the initial value for the predicted time, and learning correction is performed based on detection data of the actual forward gaze distance and vehicle speed of the driver of the host vehicle C. Therefore, this embodiment corresponds to a modified example in which a part of the second embodiment is changed.

[0083] 9 is a flowchart showing an outline of the machine learning-related processing according to this embodiment. Referring to FIG. 9, in the machine learning-related processing, the processor 31 first executes the processing of steps 401 to 404 in order.

[0084] In step 401, processor 31 acquires the driving behavior including the vehicle speed of host vehicle C. In step 402, processor 31 acquires the driving operation state of the driver of host vehicle C. In step 403, processor 31 acquires the look-ahead distance.

[0085] In step 404, processor 31 determines whether a learning condition is met. The learning condition includes, for example, a significant change in the look-ahead distance from the previous measurement value. The learning condition also includes, for example, a situation in which the driver of vehicle C performs some kind of override operation due to a sense of discomfort.

[0086] If the learning condition is met (i.e., step 404=YES), processor 31 executes the processing of step 405 and then temporarily terminates the machine learning-related processing. In step 405, processor 31 executes machine learning for the predicted time. On the other hand, if the learning condition is not met (i.e., step 404=NO), processor 31 skips the processing of step 405 and temporarily terminates the machine learning-related processing.

[0087] In this manner, in this embodiment, the predicted time used to calculate the lateral distance D of the host vehicle C, i.e., the reference point Pc, at a future time point is adjusted, i.e., corrected, by machine learning. This makes it possible to further reduce the discomfort felt by occupants such as the driver of the host vehicle C.

[0088] (Operation example: fourth embodiment) This embodiment shows an example in which the reference times in the above embodiments, i.e., the times td and te for calculating the nonlinear trajectory M2, are adjusted or corrected by machine learning. That is, in this embodiment, a default value stored in advance in the storage medium 32 is used as the initial value for the reference time, and learning correction is performed based on detection data of the actual driving operation state by the driver of the vehicle C.

[0089] 10 is a flowchart showing an outline of the machine learning-related processing according to this embodiment. Referring to FIG. 10, in the machine learning-related processing, the processor 31 first executes the processing of steps 501 to 503 in order.

[0090] In step 501, processor 31 acquires the driving behavior of host vehicle C, including the vehicle speed. In step 502, processor 31 acquires the driving operation state of the driver of host vehicle C. In step 503, processor 31 determines whether or not a learning condition is met. The learning condition includes, for example, the driver of host vehicle C performing some kind of override operation due to a sense of discomfort. The learning condition also includes, for example, the occurrence of a predetermined change in the reaction time of the driver's steering or pedal operation.

[0091] If the learning condition is met (i.e., step 503=YES), processor 31 executes the processing of step 504 and then temporarily terminates the machine learning-related processing. In step 504, processor 31 executes machine learning of the reference time. On the other hand, if the learning condition is not met (i.e., step 503=NO), processor 31 skips the processing of step 504 and temporarily terminates the machine learning-related processing.

[0092] In this manner, in this embodiment, the reference times, i.e., the times td and te for calculating the nonlinear trajectory M2, are adjusted or corrected by machine learning, thereby making it possible to more effectively reduce the discomfort felt by occupants such as the driver of the host vehicle C.

[0093] (Variation) The present invention is not limited to the above-described embodiments and specific examples. Therefore, the above-described embodiments and the like can be modified as appropriate. Representative modifications will be described below. In the following description of the modifications, differences from the above-described embodiments and the like will be mainly described. Furthermore, the same reference numerals are used for parts that are identical or equivalent to each other in the above-described embodiments and the following modifications. Therefore, in the following description of the modifications, the explanations in the above-described embodiments and the like can be used as appropriate for components that have the same reference numerals as the above-described embodiments and the like, unless there is a technical contradiction or special additional explanation.

[0094] The present invention is not limited to the specific applications and device configurations shown in the above-described embodiments. That is, for example, there is no particular limitation on the type of the host vehicle C, and the host vehicle C may be, for example, a so-called standard automobile or a so-called large automobile. Furthermore, the host vehicle C may be a conventional vehicle equipped with only an internal combustion engine as a power source, an electric vehicle equipped with a traction motor, or a hybrid vehicle equipped with an internal combustion engine and a traction motor. Electric vehicles include fuel cell vehicles in addition to those that use only a battery as a power source.

[0095] The present invention is not limited to the system configuration shown in Fig. 2. That is, for example, the host vehicle C may naturally be equipped with sensors other than the sensors shown in the figure as the sensor unit 2.

[0096] A computer program according to the present invention, which enables the execution of the various operations, procedures, or processes described in the above embodiments, can be downloaded or upgraded via V2X communication using a communication device. V2X stands for Vehicle to X. Alternatively, such a computer program can be downloaded or upgraded via a terminal device installed in a manufacturing plant, a repair shop, a dealer, or the like of the vehicle C. Such a computer program can be stored on any non-transitory tangible storage medium, such as a memory card, an optical disk, or a magnetic disk.

[0097] All or part of the vehicle driving control device 3 may be configured to include a digital circuit, such as an ASIC or FPGA, configured to be able to realize the above-described functions or operations. ASIC stands for Application Specific Integrated Circuit. FPGA stands for Field Programmable Gate Array. In other words, the vehicle driving control device 3 may include both an on-board microcomputer and a digital circuit.

[0098] In this way, each of the above functional configurations and processes may be realized by a special-purpose computer provided by configuring a processor and memory programmed to execute one or more functions embodied in a computer program. Alternatively, each of the above functional configurations and processes may be realized by a special-purpose computer provided by configuring a processor with one or more dedicated hardware logic circuits. Alternatively, each of the above functional configurations and processes may be realized by one or more special-purpose computers configured by combining one or more processors programmed to execute one or more functions, one or more memories, and one or more other processors configured with one or more hardware logic circuits. Furthermore, the computer program may be stored in a computer-readable, non-transitory storage medium as instructions to be executed by a computer. In other words, each of the above functional configurations and processes may be expressed as a computer program including procedures for implementing the same, or as a non-transitory storage medium storing the computer program.

[0099] The present invention is not limited to the specific functions and operational aspects shown in the above embodiment. Specifically, for example, in the above embodiment, it has been described that good lane keeping control can be performed without using information ahead of the host vehicle C from a front camera or the like, but the present invention is not limited to such an aspect. In other words, the present invention can also be suitably applied to a configuration in which the lane marking paint Lp and the boundary line Lb are recognized using information ahead of the host vehicle C from a front camera or the like.

[0100] 1, the boundary line Lb may be recognized as the inner edge of the lane marking paint Lp, i.e., the edge on the vehicle's own lane Lm side. Alternatively, the boundary line Lb may be recognized at a position offset from the edge by a predetermined margin. The lane marking paint Lp is also illustrated in FIG. 1 as a dashed lane marking, but is not limited to this.

[0101] In the above embodiment, a characteristic value is calculated on the assumption that the linear trajectory M1 approaches the boundary line Lb, and a characteristic value is calculated on the assumption that the nonlinear trajectory M2 approaches the boundary line Lb, and then the smaller of the two is selected. However, the present invention is not limited to this embodiment.

[0102] In other words, the present invention may, for example, first determine which of the linear trajectory M1 and the nonlinear trajectory M2 is expected to be closer to the actual behavior of the vehicle C based on the driving state of the vehicle C, and based on the result of such determination, calculate only one of the characteristic values ​​assuming that the vehicle will approach the boundary line Lb on the linear trajectory M1 or the characteristic values ​​assuming that the vehicle will approach the boundary line Lb on the nonlinear trajectory M2.

[0103] It goes without saying that the elements constituting the above-described embodiments are not necessarily essential unless they are particularly clearly stated as essential or are considered to be clearly essential in principle. Furthermore, when numerical values ​​such as the number, value, amount, range, etc. of components are mentioned, the present invention is not limited to those specific numbers unless they are particularly clearly stated as essential or are clearly limited to specific numbers in principle. Similarly, when the shape, direction, positional relationship, etc. of components are mentioned, the present invention is not limited to those shapes, directions, positional relationship, etc. unless they are particularly clearly stated as essential or are clearly limited to specific shapes, directions, positional relationship, etc. in principle.

[0104] Similar expressions such as "acquire," "calculate," "estimate," "detect," and "sensing" may be substituted for each other as appropriate within the scope of technical inconsistency. Furthermore, "exceeding the threshold" and "above the threshold" may be substituted for each other as appropriate within the scope of technical inconsistency. The same applies to "below the threshold" and "below the threshold."

[0105] The modified examples are not limited to the above examples. For example, all or part of one of the multiple modified examples may be combined with all or part of another of the multiple modified examples, provided that there is no technical contradiction. [Explanation of symbols]

[0106] 3 Vehicle driving control device 317 Trajectory calculation section 318 Characteristic value calculation unit (estimated value calculation unit) 319 Judgment Department C. Vehicle D lateral distance L lane Lb border Lm own lane M2 nonlinear orbit

Claims

1. A vehicle driving control device (3) that controls the lateral position of a vehicle (C) within a lane (Lm) while the vehicle is traveling, an estimated value calculation unit (318) that calculates an estimated value related to the degree of approach of the host vehicle to the lane boundary line (Lb) at a future time point; a determination unit (319) that determines to start execution of vehicle driving control for reducing discomfort felt by an occupant of the host vehicle when the estimated value is less than a threshold value; Equipped with the estimated value calculation unit calculates a nonlinear estimated value, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2). Vehicle driving control device.

2. the determination unit determines to start execution of steering control or deceleration control as the vehicle driving control when the estimated value is less than the threshold value. The vehicle driving control device according to claim 1 .

3. A vehicle driving control device (3) that controls the lateral position of a vehicle (C) within a lane (Lm) while the vehicle is traveling, an estimated value calculation unit (318) that calculates an estimated value related to the degree of approach of the host vehicle to the lane boundary line (Lb) at a future time point; a determination unit (319) that determines, when the estimated value is less than a threshold value, to start execution of steering control or deceleration control, which is vehicle travel control of the host vehicle; Equipped with the estimated value calculation unit calculates a nonlinear estimated value, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2). Vehicle driving control device.

4. the estimated value calculation unit calculates the nonlinear estimated value and a linear estimated value that is the estimated value based on the assumption that the host vehicle approaches the boundary line on a linear trajectory (M1); the determination unit determines to start execution of the vehicle driving control when a smaller one of the nonlinear estimated value and the linear estimated value is less than the threshold value. The vehicle driving control device according to claim 2 or 3.

5. the determination unit determines to start execution of the vehicle driving control when a boundary line crossing time, which is the time it takes for a reference point (Pc) of the host vehicle to reach the boundary line based on the nonlinear trajectory as the estimated value, is less than a reference time related to a forward gaze distance of an occupant of the host vehicle as the threshold value. The vehicle driving control device according to claim 2 or 3.

6. the determination unit determines to start execution of the vehicle driving control when the estimated value of the lateral distance of the reference point (Pc) of the host vehicle from the boundary line at the future time point after the predicted time has elapsed from the present time point is less than the threshold value. The vehicle driving control device according to claim 2 or 3.

7. adjusting the predicted time by machine learning; The vehicle driving control device according to claim 6.

8. a trajectory calculation unit (317) that calculates the nonlinear trajectory based on a change in the lateral position at each predetermined time interval; the trajectory calculation unit adjusts the time interval by machine learning. The vehicle driving control device according to claim 1 or 3.

9. the estimated value calculation unit calculates the estimated value based on a lateral distance between the host vehicle and the boundary line. The vehicle driving control device according to claim 1 or 3.

10. A vehicle driving control program executed by a vehicle driving control device (3) that controls the lateral position of a host vehicle (C) within a lane (Lm) while the host vehicle (C) is traveling, The process executed by the vehicle driving control device is a process of calculating an estimated value corresponding to a future approaching degree of the host vehicle to the lane boundary line (Lb); a process of determining, when the estimated value is less than a threshold value, to start execution of vehicle driving control for reducing discomfort felt by an occupant of the host vehicle; Including, In the process of calculating the estimated value, a nonlinear estimated value is calculated, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2). Vehicle driving control program.

11. A vehicle driving control program executed by a vehicle driving control device (3) that controls the lateral position of a host vehicle (C) within a lane (Lm) while the host vehicle (C) is traveling, The process executed by the vehicle driving control device is a process of calculating an estimated value corresponding to a future approaching degree of the host vehicle to the lane boundary line (Lb); a process of determining whether to start executing steering control or deceleration control of the host vehicle when the estimated value is less than a threshold value; Including, In the process of calculating the estimated value, a nonlinear estimated value is calculated, which is the estimated value on the assumption that the host vehicle approaches the boundary line on a nonlinear trajectory (M2). Vehicle driving control program.

Images