JP6756402B2 - Driving control method and driving control device - Google Patents

Description

The present invention is a driving control method and driving that learns a driving operation during a driver's manual driving and applies the learning result to the driving control of the automatic driving in a vehicle capable of switching between manual driving and automatic driving by the driver. Regarding the control device.

Conventionally, Patent Document 1 is disclosed as a travel control system that executes vehicle travel control by automatic driving or driving support. In the driving control system disclosed in Patent Document 1, the degree of anxiety is measured by brain waves or the like in order to prevent anxiety of the occupant during driving control by automatic driving or driving support, and when the anxiety is felt, the anxiety is measured. Adjust the vehicle speed and inter-vehicle distance to eliminate anxiety. Therefore, in situations where the occupants feel uneasy, automatic driving is performed so as to match the vehicle speed and the inter-vehicle distance during manual driving.

Japanese Unexamined Patent Publication No. 2016-52881

Here, if the driving control of the automatic driving is controlled so as to match that of the manual driving as in the conventional driving control system described above, it is difficult for the occupant to know whether the automatic driving is operating normally. You always have to worry about the operating state of the system. As a result, there is a problem that the burden on the occupant for system monitoring increases.

Therefore, the present invention has been proposed in view of the above-mentioned actual situation, and it is possible to easily grasp that the automatic driving is operating normally, and to reduce the burden on the occupant for system monitoring. It is an object of the present invention to provide a driving control method and a driving control device capable of driving.

In order to solve the above-mentioned problems, the traveling control method and the driving control device according to one aspect of the present invention make the jerk during automatic driving of the vehicle different from the jerk during manual driving obtained as a learning result. Driving control.

According to the present invention, the occupant can easily grasp that the automatic operation is operating normally, and the occupant's feeling of burden on the system monitoring can be reduced.

FIG. 1 is a block diagram showing a configuration of an operation control system including an operation control device according to an embodiment of the present invention. FIG. 2 is a diagram showing temporal changes in speed, acceleration, and jerk during deceleration in manual operation. FIG. 3 is a diagram showing temporal changes in speed, acceleration, and jerk during deceleration in the automatic operation of the operation control device according to the embodiment of the present invention. FIG. 4 is a flowchart showing a processing procedure of the driving operation learning process by the driving control device according to the embodiment of the present invention. FIG. 5 is a diagram showing an example of the learning result of the acceleration generation time from the brake on to the generation of 0.1 G. FIG. 6 is a diagram showing an example of the learning result of the acceleration generation time from the accelerator off to the generation of 0.1 G. FIG. 7 is a flowchart showing a processing procedure of automatic operation control processing by the operation control device according to the embodiment of the present invention. FIG. 8 is a diagram for explaining a method of setting acceleration / deceleration parameters in the automatic operation control process according to the embodiment of the present invention. FIG. 9 is a diagram for explaining a method of setting acceleration / deceleration parameters in the automatic operation control process according to the embodiment of the present invention. FIG. 10 is a diagram for explaining a method of setting acceleration / deceleration parameters in the automatic operation control process according to the embodiment of the present invention. FIG. 11 is a diagram for explaining a method of setting acceleration / deceleration parameters in the automatic operation control process according to the embodiment of the present invention. FIG. 12 is a diagram showing an example of a speed change during deceleration of manual operation. FIG. 13 is a diagram showing an example of a speed change during deceleration of automatic driving whose traveling is controlled by the automatic driving control process according to the embodiment of the present invention. FIG. 14 is a diagram showing an example of a speed change during acceleration of manual operation. FIG. 15 is a diagram showing an example of a speed change at the time of acceleration of automatic driving whose running is controlled by the automatic driving control process according to the embodiment of the present invention.

Hereinafter, an embodiment to which the present invention is applied will be described with reference to the drawings.

[Operation control system configuration]
FIG. 1 is a block diagram showing a configuration of an operation control system including an operation control device according to the present embodiment. As shown in FIG. 1, the operation control system 100 according to the present embodiment includes an operation control device 1, a driving state detection unit 3, a driving environment detection unit 5, an operation changeover switch 7, an occupant monitoring unit 8, and the like. A control state presenting unit 9 is provided. Further, the driving control system 100 is connected to the actuator 11 mounted on the vehicle.

The driving control device 1 learns the driving operation during the manual driving of the driver in the vehicle capable of switching between the manual driving and the automatic driving by the driver, and executes a process of applying the learning result to the driving control of the automatic driving. It is a controller to do. In particular, the driving control device 1 executes the traveling control process so that the jerk during automatic driving of the vehicle is different from the jerk during manual driving obtained as a learning result. That is, in this travel control process, travel control may be performed so that the absolute value of the jerk during automatic driving of the vehicle becomes larger than the absolute value of the jerk during manual driving obtained as a learning result. Travel control may be performed so as to be smaller. The jerk is the rate of change of the acceleration, and the jerk learned in the manual driving may be the jerk in the front-rear direction of the vehicle or the jerk in the width direction of the vehicle.

Further, the operation control device 1 includes an operation operation learning unit 21, a situation determination unit 23, a parameter setting unit 25, and an automatic operation control execution unit 27. In the present embodiment, the case where the driving control device 1 is mounted on the vehicle will be described, but the driving control device 1 may be installed on the external server by installing the communication device on the vehicle.

The traveling state detection unit 3 includes vehicle speed, acceleration, acceleration, acceleration / deceleration operation, steering angle, presence / absence of a preceding vehicle, inter-vehicle distance and relative speed with the preceding vehicle, current position, display state of a direction indicator, and headlights. Detects driving data indicating the driving state of the vehicle such as the lighting state and the operating state of the wiper. For example, the traveling state detection unit 3 is an in-vehicle network such as CAN (Controller Area Network), a navigation device, a laser radar, a camera, or the like. Parameters such as vehicle speed, acceleration, and jerk may be detected from the behavior of the vehicle, or may be obtained from the amount of operation by the occupant.

The driving environment detection unit 5 includes the current position of the vehicle, the speed limit of the road on which the vehicle travels, the display state of the traffic light in front of the vehicle, the distance to the intersection in front of the vehicle, the distance to pedestrians and bicycles, and the number of vehicles in front of the vehicle. , Detects environmental information that represents the environment around the vehicle, such as the presence or absence of a toll booth. In addition to this, it also detects the horn activation state of railroad crossings, TTC (time to collision) with vehicles in front, road regulation information, traffic congestion information, and the like. For example, the traveling environment detection unit 5 is a camera, a laser radar, a navigation device, or the like mounted on a vehicle. The display state of the traffic light in front of the vehicle may be detected by using road-to-vehicle communication. Further, the number of vehicles in front of the vehicle may be detected by using inter-vehicle communication or a cloud service linked with a smartphone. Furthermore, the planned course of the intersection in front of the vehicle is acquired from the display state of the navigation device and the direction indicator. In addition, the road surface condition and weather condition around the vehicle are acquired from the illuminance sensor, the outside air temperature sensor, the wiper switch, and the like. However, the illuminance may be obtained from the switch of the headlight.

The operation changeover switch 7 is a switch mounted on a vehicle and operated by an occupant of the vehicle to switch between automatic operation and manual operation. For example, the operation changeover switch 7 is installed on the steering wheel of the vehicle.

The occupant monitoring unit 8 is a vehicle interior camera or the like installed in the vehicle, and detects the occupant's line-of-sight direction from an image captured by the vehicle interior camera to detect the occupant's forward monitoring state. Further, a device for detecting a biological signal may be provided so that the arousal degree and the tension degree of the occupant can be detected.

The control state presenting unit 9 displays on the meter display unit, the display screen of the navigation device, the head-up display, or the like whether the current control state is manual operation or automatic operation. In addition, a notification sound for informing the start and end of automatic driving is also output, and whether or not the learning of driving operation is completed is also indicated.

The actuator 11 receives an execution command from the operation control device 1 and drives various parts such as the accelerator, the brake, and the steering of the vehicle.

Next, each part constituting the operation control device 1 will be described. The driving operation learning unit 21 acquires driving data on the driving state of the vehicle and environmental information on the driving environment around the vehicle from the driving state detection unit 3 and the driving environment detection unit 5, and learns the driving operation during manual driving by the driver. To do. The driving operations to be learned are acceleration / deceleration operations and steering operations, and learn driving operations in situations where acceleration, deceleration, and jerk occur during traveling. For example, the acceleration, deceleration, and jerk from the start (including start) to the end of the acceleration operation are learned, and the acceleration, deceleration, and jerk from the start to end (including stop) of the deceleration operation are learned. Furthermore, the acceleration, deceleration, and jerk in the vehicle width direction from the start to the end of the steering operation are learned. Then, the driving operation learning unit 21 learns by associating the speed and acceleration during the acceleration / deceleration operation in the manual operation, the jerk and the traveling environment.

Specifically, the driving operation learning unit 21 learns the relationship between the speed and the jerk at the start of the acceleration / deceleration operation in the manual operation. In addition, the relationship between the speed at the start of the acceleration / deceleration operation in the manual operation and the acceleration generation time from the start of the acceleration / deceleration operation to the generation of a predetermined acceleration is also learned. Further, the jerk may be learned from the start of the acceleration / deceleration operation in the manual operation to the occurrence of a predetermined acceleration.

The situation determination unit 23 acquires driving data related to the running state of the vehicle and environmental information related to the running environment around the vehicle from the running state detection unit 3 and the running environment detection unit 5, and determines the running condition and automatic driving of the vehicle. Judge the usage status being used. The driving conditions to be judged include turning left and right or stopping at an intersection, avoiding objects such as parked vehicles and pedestrians, passing railroad crossings, road restrictions, merging and overtaking. There are situations where the road is congested or congested, and the weather conditions, visibility, and road surface conditions are poor. In addition to this, the situation determination unit 23 determines the front monitoring state of the occupants of the vehicle, and determines whether the driving environment around the vehicle is a specific preset environment such as a school zone or a living road. To do. In addition, the usage status to be determined is whether or not it is a predetermined period after shifting from manual driving to automatic driving, whether or not it is a predetermined period after the vehicle starts automatic driving, and whether or not it is a predetermined period after the vehicle starts automatic driving, and whether it is from automatic driving to manual driving. There is whether or not it is a predetermined period before shifting to.

When the parameter setting unit 25 shifts to automatic driving, the parameter setting unit 25 executes automatic driving based on the learning result learned by the driving operation learning unit 21 and the driving situation and usage situation determined by the situation determination unit 23. Set the parameters for. The parameters to be set include jerk, acceleration, deceleration, acceleration generation time, and the like. In particular, the parameter setting unit 25 sets the parameters so that the jerk during automatic driving of the vehicle is different from the jerk during manual driving obtained as a learning result. That is, the parameter may be set so that the absolute value of the jerk during automatic driving of the vehicle is larger than the absolute value of the jerk during manual driving obtained as a learning result, or the parameter is set so as to be smaller. May be set.

For example, a case where the vehicle decelerates from 50 km / h will be described with reference to FIGS. FIG. 2 is a diagram showing temporal changes in speed, acceleration, and jerk when decelerating from 50 km / h during manual operation. In FIG. 2, the accelerator is turned off at time t1, and the acceleration drops by 0.1 G at time t2. The acceleration generation time T1 is the time from when the accelerator is turned off to when the accelerator is lowered by 0.1 G. The driving operation learning unit 21 learns such a driving operation and stores it as a learning result.

On the other hand, as shown in FIG. 3, the parameter setting unit 25 sets the jerk during automatic operation to be different from the jerk during manual operation obtained as a learning result. In particular, the parameter setting unit 25 sets the absolute value of the jerk during automatic operation to be larger than the absolute value of the jerk during manual operation obtained as a learning result when starting acceleration / deceleration. In FIG. 3, the accelerator is released at time t3, the acceleration is reduced by 0.1 G at time t4, and the acceleration generation time is T2. Comparing FIGS. 2 and 3, the acceleration generation time T2 during automatic operation is shorter than the acceleration generation time T1 during manual operation. This is because the parameter setting unit 25 sets the absolute value of the jerk during automatic operation to be larger than the absolute value of the jerk during manual operation. Comparing the jerk in the period of T1 in FIG. 2 and the jerk in the period of T2 in FIG. 3, the absolute value of the jerk during automatic operation shown in FIG. 3 is the absolute value of the jerk during manual operation shown in FIG. It is larger than the value.

By setting the jerk during automatic driving to be different from the jerk during manual driving obtained as a learning result in this way, the difference between automatic driving and manual driving becomes clear, so that the occupants can drive automatically. It can be easily grasped that it is operating normally. As a result, the burden on the occupant for system monitoring can be significantly reduced. In particular, when the vehicle speed or acceleration changes during acceleration / deceleration or when turning left or right, the anxiety of the occupants regarding automatic driving increases. However, when the acceleration / deceleration is started (T1 in FIG. 2 and T2 in FIG. 3), if the jerk during automatic operation is set to be different from the jerk during manual operation obtained as a learning result, the occupant Can easily grasp that the automatic operation is operating normally. Therefore, the occupant can obtain a sense of security and reliability for autonomous driving. Although FIGS. 2 and 3 have described a case where the absolute value of the jerk during automatic operation is larger than the absolute value of the jerk during manual operation, it may be set to be smaller.

The automatic driving control execution unit 27 executes automatic driving control when the automatic driving section is reached or when the driver selects automatic driving by the operation changeover switch 7. At this time, the automatic driving control execution unit 27 applies the learning result learned by the driving operation learning unit 21 to the driving control of automatic driving, and automatically controls the automatic driving by the acceleration, deceleration, and jerk set by the parameter setting unit 25. To execute.

The operation control device 1 is composed of a general-purpose electronic circuit including a microcomputer, a microprocessor, and a CPU, and peripheral devices such as a memory. Then, by executing a specific program, it operates as the above-mentioned driving operation learning unit 21, situation determination unit 23, parameter setting unit 25, and automatic driving control execution unit 27. Each function of such an operation control device 1 can be implemented by one or a plurality of processing circuits. The processing circuit includes a programmed processing device such as a processing device including an electric circuit, and is an application specific integrated circuit (ASIC) or a conventional circuit arranged to perform the functions described in the embodiments. It also includes devices such as parts.

[Procedure for driving operation learning process]
Next, the procedure of the driving operation learning process by the driving control device 1 according to the present embodiment will be described with reference to the flowchart of FIG. The driving operation learning process shown in FIG. 4 starts when the ignition of the vehicle is turned on.

As shown in FIG. 4, first, in step S101, the driving operation learning unit 21 determines whether or not the vehicle is manually driven depending on the state of the driving changeover switch 7. If the vehicle is manually driven, the process proceeds to step S103, and if the vehicle is automatically driven, the driving operation learning process is terminated and automatic driving control is executed.

In step S103, the driving operation learning unit 21 detects the driving data regarding the driving state of the vehicle and the environmental information regarding the driving environment around the vehicle from the traveling state detecting unit 3 and the traveling environment detecting unit 5. The detected driving data includes vehicle speed, steering angle, acceleration, deceleration, jerk, inter-vehicle distance to the preceding vehicle, relative speed to the preceding vehicle, current position, planned course at the front intersection, brake pedal and accelerator pedal. Detects the amount of operation, the lighting state of the headlight, the operating state of the wiper, etc. In addition, as environmental information, the speed limit of the road on which the vehicle is traveling, the toll booth, the presence or absence of suspension restrictions or the display state of the traffic light in front of the vehicle, the distance from the vehicle to the intersection ahead, the number of vehicles in front of the vehicle, and walking from the vehicle Detects the distance to a person or a bicycle, the road surface condition, the weather condition around the vehicle, etc. In addition to this, it also detects the horn activation state of railroad crossings, TTC (time to collision) with vehicles in front, road regulation information, traffic congestion information, and the like. Further, the driving operation learning unit 21 detects the occupant's forward monitoring state, alertness, tension, etc. from the occupant monitoring unit 8.

In step S105, the driving operation learning unit 21 determines whether or not the vehicle is decelerating or accelerating. As a determination method, when the deceleration or acceleration of the vehicle acquired in step S103 is equal to or greater than a predetermined value, it is determined that the vehicle is decelerating or accelerating. Then, if it is determined that the vehicle is decelerating or accelerating, the process proceeds to step S107, and if it is determined that the vehicle is not decelerating or accelerating, the process returns to step S103.

In step S107, the driving operation learning unit 21 uses the driving data and environmental information detected in step S103 for learning data, which is determined to be decelerating or accelerating in the process of step S105. Remember as. In the present embodiment, the case where the data is stored after being sorted in advance has been described, but the data during the manual operation may be stored once and then the above-mentioned process of step S105 may be performed for sorting.

In step S109, the driving operation learning unit 21 determines whether or not a predetermined amount of learning data can be stored, returns to step S103 if the amount is less than the predetermined amount, and steps if the predetermined amount or more can be accumulated. Proceed to S111.

In step S111, the driving operation learning unit 21 learns the driving operation during the manual operation of the driver. In particular, learn the driver's acceleration / deceleration operation. For example, the relationship between the speed at the start of the acceleration / deceleration operation in manual operation and the jerk is learned, and a linear function is obtained as the learning result. Similarly, the linear function may be obtained by learning the relationship between the speed at the start of the acceleration / deceleration operation and the acceleration generation time in the manual operation. The acceleration generation time is the time from the start of the acceleration / deceleration operation to the generation of a predetermined acceleration. For example, in the case of a deceleration operation, the time until a predetermined deceleration (for example, 0.1 G) occurs when the accelerator is turned off or the brake is turned on as the start time of the deceleration operation is defined as the acceleration generation time.

Further, only the acceleration generation time may be learned. For example, as shown in FIG. 5, the acceleration generation time from when the brake is turned on until the deceleration of 0.1 G occurs is learned for each driver A to G, and the average value and standard deviation of each are obtained. You may. Similarly, as shown in FIG. 6, the acceleration generation time from when the accelerator is turned off until the deceleration of 0.1 G occurs is learned for each driver A to G, and the average value and standard deviation of each are obtained. You may ask. In addition to the average value and standard deviation, the maximum value may be obtained. Further, instead of learning the acceleration generation time, the jerk from the start of the acceleration / deceleration operation in the manual operation to the generation of a predetermined acceleration may be learned. In this case, the section where the jerk occurs, such as before the intersection, is specified in advance, and the jerk in that section is learned.

Further, the jerk during the acceleration / deceleration operation in the manual driving may be associated with the traveling environment of the vehicle for learning. Among the traveling environments, as an environmental factor that affects the jerk and acceleration during the deceleration operation, for example, the vehicle may approach an object such as another vehicle or a pedestrian. In this case, the jerk at the time of deceleration operation is learned in relation to the distance between the vehicle and the object, the relative speed, or TTC (Time to collision). In this way, the jerk during deceleration operation is learned in relation to situations such as interruption and sudden deceleration of preceding vehicles, appearance of traffic jams, appearance of parked vehicles, approach of crossing vehicles and merging vehicles, crossing of pedestrians and bicycles, etc. be able to.

In addition, when the traffic light is switched, the jerk at the time of deceleration operation is learned in relation to the distance or time (distance / speed) to the stop line when switching from yellow to red. When the horn is activated at a railroad crossing, the jerk during deceleration operation is learned in relation to the distance or time (distance / speed) to the stop line when the horn is activated. Furthermore, if there is road regulation, the jerk during deceleration operation is learned in relation to the distance or time (distance / speed) to the road regulation point. As a result, it is possible to learn the jerk at the time of deceleration operation in relation to the situation such as lane regulation due to road construction, approach to the tollgate, and reduction of the speed limit. Further, the jerk at the time of deceleration operation may be learned in relation to the visibility, the weather condition, and the road surface condition. This makes it possible to learn the jerk during deceleration operation in relation to situations such as rain, snow, and freezing of the road surface.

Next, as environmental factors that affect jerk and acceleration during acceleration operation, for example, there are cases of merging and overtaking. In this case, the jerk at the time of acceleration operation is learned in relation to the length of the merging or overtaking section and the speed of the merging destination. Further, when traveling on an intersection or a narrow road, the jerk at the time of acceleration operation is learned in relation to whether or not the vehicle is turning left or right, whether or not the vehicle is starting from a stop intersection, and whether or not the vehicle is traveling on a narrow road. Further, when the vehicle is congested or congested, the jerk during the acceleration operation is learned in relation to whether or not the own lane or the adjacent lane is congested or congested. Further, the jerk at the time of acceleration operation may be learned in relation to the visibility, the weather condition, and the road surface condition. This makes it possible to learn the jerk at the time of acceleration operation in relation to situations such as rain, snow, and freezing of the road surface. Further, the jerk at the time of acceleration operation may be learned in relation to whether or not the vehicle is traveling in a specific environment such as a school zone or a living road.

In step S113, the driving operation learning unit 21 stores the learning result calculated in step S111 and ends the driving operation learning process according to the present embodiment.

[Procedure for automatic operation control processing]
Next, the procedure of the automatic operation control process by the operation control device 1 according to the present embodiment will be described with reference to the flowchart of FIG.

As shown in FIG. 7, in step S201, the automatic driving control execution unit 27 determines whether or not the learning of the driving operation is completed by the driving operation learning process shown in FIG. If the learning is completed, the process proceeds to step S203, and if the learning is not completed, the process proceeds to step S211.

First, the case where the learning of the driving operation is completed will be described. In step S203, the situation determination unit 23 acquires the traveling data regarding the traveling state of the vehicle and the environmental information regarding the traveling environment around the vehicle from the traveling state detecting unit 3 and the traveling environment detecting unit 5, and the traveling condition in which the vehicle is traveling. And the usage status in which automatic driving is used. The detected driving conditions include turning left and right or stopping at an intersection, avoiding objects such as parked vehicles and pedestrians, passing railroad crossings, road restrictions, merging and overtaking. There are situations where the road is congested or congested, and the weather conditions, visibility, and road surface conditions are poor. In addition to this, the situation determination unit 23 detects the front monitoring state of the occupant of the vehicle and detects whether the driving environment around the vehicle is a specific preset environment such as a school zone or a living road. To do. In addition, the detected usage status includes whether or not it is a predetermined period after shifting from manual driving to automatic driving, whether or not it is a predetermined period after the vehicle starts automatic driving, and whether or not it is a predetermined period after the vehicle starts automatic driving. There is whether or not it is a predetermined period before shifting to.

In step S205, the parameter setting unit 25 sets acceleration / deceleration parameters for executing automatic driving based on the learning result learned in the driving operation learning process and the driving conditions and usage conditions detected in step S203. .. The parameters to be set include jerk, acceleration, deceleration, acceleration generation time, and the like. In particular, the parameter setting unit 25 sets the jerk during automatic driving of the vehicle to be different from the jerk during manual driving obtained as a learning result. That is, the absolute value of the jerk during automatic driving of the vehicle may be set to be larger than the absolute value of the jerk during manual driving obtained as a learning result, or it may be set to be smaller. May be good.

For example, in FIG. 8, the relationship between the speed at the start of the acceleration / deceleration operation in manual operation and the jerk is learned, and the learning result is shown by the dotted line X. By adding a predetermined value to the learning result X, the relationship between the speed at the start of the acceleration / deceleration operation in the automatic operation and the jerk is obtained and shown by the solid line Y. As a result, the parameter setting unit 25 sets the absolute value of the jerk during automatic operation to be larger than the absolute value of the jerk during manual operation obtained as a learning result.

Further, in FIG. 9, the relationship between the speed at the start of the acceleration / deceleration operation in the automatic operation and the jerk is obtained by subtracting a predetermined value from the learning result X shown by the dotted line, and is shown by the solid line Y. As a result, the absolute value of the jerk during automatic operation is set to be smaller than the absolute value of the jerk during manual operation obtained as a learning result. When the jerk during manual operation is large, that is, in the case of a driver who has a lot of sudden acceleration and deceleration, it is better to make the jerk during automatic operation smaller than the jerk during manual operation to make the difference between automatic operation and manual operation. Sometimes it can be clarified. Therefore, the jerk during automatic operation may not only be larger than the jerk during manual operation, but may be smaller. However, it is not necessary to limit the driver to a driver who frequently accelerates or decelerates suddenly, and even in the case of a normal driver, the jerk during automatic operation may be smaller than the jerk during manual operation.

Further, the acceleration generation time may be set instead of the jerk. In FIG. 10, the relationship between the speed at the start of the acceleration / deceleration operation in the manual operation and the acceleration generation time is learned, and the learning result is shown by the dotted line X. By subtracting a predetermined value from this learning result X, the relationship between the speed at the start of the acceleration / deceleration operation in the automatic operation and the acceleration generation time is obtained and is shown by the solid line Y. As a result, the acceleration generation time during automatic operation is set to be smaller than the acceleration generation time during manual operation obtained as a learning result. Since the acceleration generation time is the time from the start of the acceleration / deceleration operation to the arrival at a predetermined acceleration, the jerk increases as the acceleration generation time decreases. Therefore, the parameter setting unit 25 sets the absolute value of the jerk during automatic operation to be larger than the absolute value of the jerk during manual operation obtained as a learning result.

Further, in FIG. 11, by adding a predetermined value to the learning result X shown by the dotted line, the relationship between the speed at the start of the acceleration / deceleration operation in the automatic operation and the acceleration generation time is obtained, and is shown by the solid line Y. As a result, the acceleration generation time during automatic operation is set to be longer than the acceleration generation time during manual operation obtained as a learning result. The jerk decreases as the acceleration generation time increases. Therefore, the parameter setting unit 25 sets the absolute value of the jerk during automatic operation to be smaller than the absolute value of the jerk during manual operation obtained as a learning result.

Further, the parameter setting unit 25 may adjust the jerk during automatic driving according to the usage situation in which automatic driving of the vehicle is used. For example, when the vehicle shifts from manual driving to automatic driving, the parameters are set so that the difference between the jerk during automatic driving and the jerk during manual driving becomes larger than the predetermined value for the predetermined period after the shift. And control the driving. As for the predetermined value, a value may be set in advance so that the occupant can clearly recognize the difference between the jerk during automatic operation and the jerk during manual operation.

Further, when the vehicle starts automatic driving, the parameter setting unit 25 parameters so that the difference between the jerk during automatic driving and the jerk during manual driving becomes larger than a predetermined value for a predetermined period after the start. Is set to control driving. Here, the start of automatic driving means a case where the automatic driving starts from an unused state such as immediately after purchasing a vehicle.

Further, in the parameter setting unit 25, when the vehicle shifts from automatic driving to manual driving, the difference between the jerk during automatic driving and the jerk during manual driving is larger than a predetermined value for a predetermined period before the shift. The driving control is performed by setting the parameters so as to be.

Further, the parameter setting unit 25 may adjust the jerk during automatic driving according to the front monitoring state of the occupant of the vehicle. For example, when it is determined that the occupant's arousal level is reduced, the jerk is increased according to the decrease level to increase the occupant's arousal level. When it is detected that the occupant is not looking ahead, the jerk is increased to promote the occupant's forward monitoring.

Further, the parameter setting unit 25 learns by associating the jerk during the acceleration / deceleration operation in the manual driving of the vehicle with the traveling environment of the vehicle, and sets parameters based on the learning result to control the traveling. For example, when a vehicle is close to an object such as another vehicle or a pedestrian, the jerk or deceleration is increased as the distance decreases. Further, the jerk or deceleration may be increased as the relative speed with the object increases or as the TTC (Time to collision) decreases. As a result, appropriate parameters can be set in the case of interruption or sudden deceleration of the preceding vehicle, appearance of traffic jam, appearance of parked vehicle, entry of crossing vehicle or merging vehicle, crossing of pedestrian or bicycle, and the like.

Further, when the traffic light is switched, the parameter setting unit 25 increases the jerk or deceleration as the distance or time (distance / speed) to the stop line when switching from yellow to red becomes shorter. Furthermore, when the horn is activated at a railroad crossing, the jerk or deceleration is increased as the distance or time (distance / speed) to the stop line when the horn is activated becomes shorter. If there are road restrictions, the jerk or deceleration will be increased as the distance or time (distance / speed) to the road regulation point or tollgate becomes shorter.

Further, when the vehicles merge or overtake, the parameter setting unit 25 increases the jerk or acceleration as the merging or overtaking section becomes shorter. Further, the jerk or acceleration may be increased as the speed of the merging destination increases. Further, when traveling on an intersection or a narrow road, the jerk or acceleration is made smaller than the learning result when turning left or right, starting from a stop intersection, or traveling on a narrow road. In addition, when the road in front of the vehicle is congested or congested, the jerk or acceleration is made smaller than the learning result.

Further, the parameter setting unit 25 makes the jerk or acceleration smaller than the learning result in a situation where the weather condition, the visibility, and the road surface condition are bad (rain, snow, road surface freezing). In addition, when the vehicle is traveling in a specific preset environment such as a school zone or a living road, the jerk or acceleration is made smaller than the learning result.

In step S207, the automatic operation control execution unit 27 executes automatic operation control using the acceleration / deceleration parameters set in step S205. For example, it is assumed that the speed change during deceleration of manual operation is a change as shown in FIG. In FIG. 12, the acceleration generation time at the start of deceleration is Ts, and the acceleration generation time at the end of deceleration is Tf. Here, when automatic operation is performed using the acceleration / deceleration parameters set in step S205, that is, when the absolute value of the jerk during automatic operation is set to be larger than the absolute value of the jerk during manual operation. , The speed changes as shown in FIG. In FIG. 13, since the absolute value of the jerk during automatic operation is set to be larger than the absolute value of the jerk during manual operation, the acceleration generation time Ts'Tf'is the acceleration generation shown in FIG. It is shorter than the time Ts and Tf.

Further, the speed change during acceleration will be described with reference to FIGS. 14 and 15. In FIG. 14, the acceleration generation time at the time when acceleration starts in manual operation is Ts, and the acceleration generation time at the time when acceleration ends is Tf. Here, when automatic operation is performed using the acceleration / deceleration parameters set in step S205, that is, when the absolute value of the jerk during automatic operation is set to be larger than the absolute value of the jerk during manual operation. , The speed changes as shown in FIG. In FIG. 15, since the absolute value of the jerk during automatic operation is set to be larger than the absolute value of the jerk during manual operation, the acceleration generation time Ts'Tf'is the acceleration generation shown in FIG. It is shorter than the time Ts and Tf.

The automatic driving control execution unit 27 transmits a control execution command to the actuator 11 so that such automatic driving is executed, and executes operations such as accelerator, brake, and steering necessary for automatic driving.

In step S209, the automatic operation control execution unit 27 determines whether or not the automatic operation has been completed, and if not, returns to step S203 to continue the automatic operation. On the other hand, when the automatic operation is switched to the manual operation and the automatic operation is completed, the automatic operation control process according to the present embodiment is terminated.

Next, the case where the learning of the driving operation is not completed will be described. In step S211, the situation determination unit 23 acquires the traveling data regarding the traveling state of the vehicle and the environmental information regarding the traveling environment around the vehicle from the traveling state detecting unit 3 and the traveling environment detecting unit 5, and the traveling condition in which the vehicle is traveling. And the usage status in which automatic driving is used. The detected driving conditions include turning left and right or stopping at an intersection, avoiding objects such as parked vehicles and pedestrians, passing railroad crossings, road restrictions, merging and overtaking. There are situations where the road is congested or congested, and the weather conditions, visibility, and road surface conditions are poor. In addition to this, the situation determination unit 23 detects the front monitoring state of the occupant of the vehicle and detects whether the driving environment around the vehicle is a specific preset environment such as a school zone or a living road. To do. In addition, the detected usage status includes whether or not it is a predetermined period after shifting from manual driving to automatic driving, whether or not it is a predetermined period after the vehicle starts automatic driving, and whether or not it is a predetermined period after the vehicle starts automatic driving. There is whether or not it is a predetermined period before shifting to.

In step S213, the parameter setting unit 25 sets a predetermined value preset as an acceleration / deceleration parameter. As this predetermined value, a general acceleration / deceleration value or an average value may be used.

In step S215, the automatic operation control execution unit 27 executes automatic operation control using the set acceleration / deceleration parameters. Specifically, the automatic driving control execution unit 27 transmits a control execution command to the actuator 11 to execute operations such as accelerator, brake, and steering necessary for automatic driving.

In step S217, the automatic operation control execution unit 27 determines whether or not the automatic operation has been completed, and if not, returns to step S211 to continue the automatic operation. On the other hand, when the automatic operation is switched to the manual operation and the automatic operation is completed, the automatic operation control process according to the present embodiment is terminated.

[Effect of Embodiment]
As described in detail above, in the driving control method and the driving control device according to the present embodiment, the driving control is performed so that the jerk during automatic driving of the vehicle is different from the jerk during manual driving obtained as a learning result. To do. As a result, the occupant can easily grasp that the automatic operation is operating normally, and the occupant's feeling of burden on the system monitoring can be reduced.

Further, in the traveling control method according to the present embodiment, traveling control is performed so that the absolute value of the jerk during automatic driving of the vehicle becomes larger than the absolute value of the jerk during manual driving obtained as a learning result. As a result, the occupant can easily grasp the behavior such as acceleration / deceleration and stop of the vehicle. By not only increasing the jerk, but also using the jerk of the occupant obtained as a learning result as a reference, it is possible to reflect the individual driving characteristics and set the jerk so that it does not become larger than necessary. .. In addition, by using the jerk of the occupant obtained as a learning result as a reference, the required acceleration can be estimated accurately, so that the occupant can be informed that the jerk is different from the manual operation. become. In addition, since the occupant can easily grasp that the automatic driving system is operating normally from the behavior of the vehicle, a sense of security and reliability for automatic driving can be obtained. In addition, in order to control the traveling so as to be different from the jerk during manual operation obtained as a learning result, the jerk during automatic driving may be increased by not reflecting the learning result.

Further, in the traveling control method according to the present embodiment, the jerk during automatic driving is adjusted according to the situation in which automatic driving of the vehicle is used. As a result, the jerk pattern (size, time, number of times, etc.) can be adjusted according to the situation in which automatic driving is used. Therefore, when necessary, the jerk is increased to inform the occupants of the operating state of the automatic driving system. However, it can give the occupants a sense of security and reliability. Further, when it is not needed, the jerk can be reduced to provide a comfortable ride.

Further, in the traveling control method according to the present embodiment, when the vehicle shifts from manual driving to automatic driving, the difference between the jerk during automatic driving and the jerk during manual driving is a predetermined value for a predetermined period after the shift. The driving is controlled so as to be larger than this. As a result, immediately after the shift to automatic driving, it is possible to positively inform the occupant that the automatic driving system is operating normally, and the occupant can get a sense of security.

Further, in the traveling control method according to the present embodiment, when the vehicle starts automatic driving, the difference between the jerk during automatic driving and the jerk during manual driving becomes larger than a predetermined value for a predetermined period after the start. The driving is controlled so as to. As a result, it is possible to positively inform the occupants that the automatic driving system is operating normally at the time when the automatic driving of the vehicle is started, and the occupants can get a sense of security.

Further, in the traveling control method according to the present embodiment, when the vehicle shifts from automatic driving to manual driving, the difference between the jerk during automatic driving and the jerk during manual driving is a predetermined value during the predetermined period before the shift. The driving is controlled so as to be larger than this. As a result, the occupant can understand that the return to the manual operation is approaching due to the change in the jerk immediately before returning from the automatic operation to the manual operation. Therefore, the forward monitoring of the occupant is promoted to the manual operation. Can be prepared for.

Further, in the traveling control method according to the present embodiment, the front monitoring state of the occupant of the vehicle is detected, and the jerk during automatic driving is adjusted according to the detected front monitoring state. As a result, when the occupant neglects to monitor forward, the jerk can be increased to encourage the occupant to monitor forward.

Further, in the traveling control method according to the present embodiment, the relationship between the speed at the start of the acceleration / deceleration operation in the manual driving of the vehicle and the jerk is learned, and the traveling control of the automatic driving is performed based on the learning result. As a result, the learning result can be reflected in the acceleration / deceleration operation of the automatic driving, so that the driving control that reflects the driving characteristics of each driver becomes possible.

Further, in the traveling control method according to the present embodiment, the relationship between the speed at the start of the acceleration / deceleration operation in the manual operation of the vehicle and the acceleration generation time from the start of the acceleration / deceleration operation to the occurrence of a predetermined acceleration is learned. Then, based on this learning result, the running control of automatic driving is performed. As a result, the learning result can be reflected in the acceleration / deceleration operation of the automatic driving, so that the driving control that reflects the driving characteristics of each driver becomes possible.

Further, in the traveling control method according to the present embodiment, the jerk from the start of the acceleration / deceleration operation in the manual driving of the vehicle to the occurrence of a predetermined acceleration is learned, and the traveling control of the automatic driving is performed based on the learning result. .. As a result, the learning result can be reflected in the acceleration / deceleration operation of the automatic driving, so that the driving control that reflects the driving characteristics of each driver becomes possible.

Further, in the traveling control method according to the present embodiment, the jerk during the acceleration / deceleration operation in the manual driving of the vehicle is learned in association with the traveling environment of the vehicle, and the traveling control of the automatic driving is performed based on the learning result. As a result, it is possible to adjust the driving characteristics of each driver according to various driving environments and perform driving control.

Further, in the traveling control method according to the present embodiment, when the traveling environment around the vehicle is a preset specific environment, the jerk during automatic driving is adjusted. This makes it possible for the occupants to understand that the environment is at high risk and that the driver needs to intervene in autonomous driving, and encourages the occupants to actively monitor the surrounding environment. it can.

Further, in the traveling control method according to the present embodiment, the jerk learned in the manual driving of the vehicle is the jerk in the front-rear direction of the vehicle. This makes it possible to learn the driving characteristics of the driver when the vehicle stops at an intersection or when the vehicle approaches an object such as another vehicle.

Further, in the traveling control method according to the present embodiment, the jerk learned in the manual driving of the vehicle is the jerk in the vehicle width direction of the vehicle. This makes it possible to learn the driving characteristics of the driver when turning left or right at an intersection.

The above-described embodiment is an example of the present invention. Therefore, the present invention is not limited to the above-described embodiment, and even if it is an embodiment other than this embodiment, as long as it does not deviate from the technical idea of the present invention, it depends on the design and the like. Of course, various changes are possible.

1 Driving control device 3 Driving condition detection unit 5 Driving environment detection unit 7 Operation changeover switch 8 Crew monitoring unit 9 Control status presentation unit 11 Actuator 21 Driving operation learning unit 23 Situation judgment unit 25 Parameter setting unit 27 Automatic operation control execution unit 100 Operation Control system

Claims (13)

It is a driving control method of a driving control device that learns the driving operation during manual driving by the driver and applies the learning result to the driving control of automatic driving in a vehicle that can switch between manual driving and automatic driving by the driver. hand,
By learning the jerk from the start of the acceleration / deceleration operation in the manual driving of the vehicle to the occurrence of a predetermined acceleration,
A traveling control method characterized in that the jerk during automatic driving of the vehicle is controlled to be different from the jerk during manual driving obtained as the learning result. The traveling according to claim 1, wherein the traveling is controlled so that the absolute value of the jerk during automatic driving of the vehicle is larger than the absolute value of the jerk during manual driving obtained as the learning result. Control method. When the vehicle shifts from manual driving to automatic driving, running control is performed so that the difference between the jerk during automatic driving and the jerk during manual driving becomes larger than a predetermined value for a predetermined period after the shift. The traveling control method according to claim 1 or 2. When the automatic driving of the vehicle is started from an unused state, the difference between the jerk during the automatic driving and the jerk during the manual driving becomes larger than a predetermined value for a predetermined period after the start. The traveling control method according to any one of claims 1 to 3, wherein the traveling is controlled. When the vehicle shifts from automatic driving to manual driving, driving control is performed so that the difference between the jerk during automatic driving and the jerk during manual driving becomes larger than a predetermined value during a predetermined period before the shift. The traveling control method according to any one of claims 1 to 4, wherein the traveling control method is characterized. The traveling according to any one of claims 1 to 5, wherein the front monitoring state of the occupant of the vehicle is detected, and the jerk during the automatic driving is adjusted according to the detected front monitoring state. Control method. Any of claims 1 to 6, wherein the relationship between the speed at the start of the acceleration / deceleration operation in the manual operation of the vehicle and the acceleration / acceleration is learned, and the traveling control of the automatic driving is performed based on the learning result. The traveling control method according to item 1. The relationship between the speed at the start of the acceleration / deceleration operation in the manual operation of the vehicle and the acceleration generation time from the start of the acceleration / deceleration operation to the occurrence of a predetermined acceleration is learned, and automatic driving is performed based on the learning result. The traveling control method according to any one of claims 1 to 6, wherein the traveling control is performed. The first to eighth aspects of claim 1, wherein the jerk during the acceleration / deceleration operation in the manual driving of the vehicle is learned in association with the traveling environment of the vehicle, and the traveling control of the automatic driving is performed based on the learning result. The traveling control method according to any one item. The travel control according to any one of claims 1 to 9, wherein when the traveling environment around the vehicle is a specific environment set in advance, the jerk during the automatic driving is adjusted. Method. The traveling control method according to any one of claims 1 to 10, wherein the jerk learned in the manual driving of the vehicle is the jerk in the front-rear direction of the vehicle. The travel control method according to any one of claims 1 to 11, wherein the jerk learned in the manual driving of the vehicle is the jerk in the vehicle width direction of the vehicle. A driving control device that learns the driving operation during manual driving by the driver and applies the learning result to the driving control of automatic driving in a vehicle that can switch between manual driving and automatic driving by the driver.
By learning the jerk from the start of the acceleration / deceleration operation in the manual driving of the vehicle to the occurrence of a predetermined acceleration,
A driving control device characterized in that the jerk during automatic driving of the vehicle is controlled to be different from the jerk during manual driving obtained as a result of the learning.

Images