JP2019127207A - Driving support device and method of learning driving characteristics - Google Patents

Abstract

To provide a technology to exclude a driving operation inappropriate for the learning of a driving operation from a learning object in a driving support device that reflects a user's driving characteristics in automatic driving of a vehicle by learning the user's driving operation in manual driving of the vehicle.SOLUTION: A driving support device includes: an information acquisition unit for acquiring information indicating a driving operation and information indicating a driving condition in the driving operation; a driving condition determination unit for determining whether or not the driving condition is appropriate for learning based on the information acquired by the information acquisition unit; and a learning object determination unit for determining that a driving operation in the driving condition determined to be inappropriate by the driving condition determination unit is to be excluded from a learning object.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a driving support device and a learning method of driving characteristics.

  In recent years, in order to reduce the burden of manual driving by a user (mainly a driver (driver)), driving support technology for automatically driving a vehicle has been developed. In such an automatic driving technique, in addition to the acceleration and deceleration timings set as standard in the vehicle, the user's driving operation during manual driving is learned for each driving situation and reflected in the automatic driving.

  Related to the above, Patent Document 1 proposes a technique for identifying a driving environment by a combination of environmental item values detected for environmental items at the time of manual driving control and learning a driver's driving operation in association with the driving environment. ing. Further, in Patent Document 2, a driver-specific driving characteristic is extracted based on traveling when the traveling control is not performed, and a reference line on which the host vehicle should travel is calculated based on the extracted driving characteristic. Techniques have been proposed in which travel control is performed so that the vehicle travels along the reference line.

JP, 2015-89801, A JP 2009-227196 A

  However, the above-described technology targets all the driving operations of the user at the time of manual driving as a learning target, and there is no function to exclude unnecessary driving operations. Therefore, there is a risk of learning a driving operation that should not be originally targeted for learning. For example, driving operations in driving situations that are inappropriate for learning, such as exceeding the legal speed limit (speed limit), sudden stopping, sudden start, staggered driving, driving an unfamiliar road, etc. Undesirable for learning. If a driving operation in a driving situation unsuitable for such learning is learned, it becomes difficult to realize an automatic driving that reproduces a normal driving by the user or an ideal automatic driving by the user. In addition, in order to avoid such a situation, if the user manually operates with an awareness that improper driving operation is not learned, the driving tends to be different from usual, and as a result, the automatic driving is uncomfortable for the user. There is a risk of becoming. Furthermore, although information (data) of inappropriate driving operation is data that is unnecessary for learning, if a large amount of such data is accumulated by learning, there is a problem that memory is compressed with unnecessary data. there were.

  The present invention has been made to solve such a problem, and its object is to reflect the driving characteristics of the user in the automatic driving of the vehicle by learning the driving operation of the user during the manual driving of the vehicle. An object of the present invention is to provide a technology capable of excluding a driving operation inappropriate for learning a driving operation as a target of learning in a driving support device.

A driving support apparatus that reflects driving characteristics of the user in automatic driving of the vehicle by learning driving operations of the user during manual driving of the vehicle,
An information acquisition unit that acquires information indicating the driving operation and information indicating a driving situation at the time of the driving operation;
A driving situation determination unit that determines whether or not the driving situation is inappropriate for learning of the driving operation based on the information acquired by the information acquisition unit;
A learning target determination unit that determines that the driving operation in the driving situation determined to be inappropriate by the driving state determination unit is not subject to learning;
It is a driving assistance device.

  According to the present invention, it is possible to exclude driving operation in a driving situation inappropriate for learning of driving operation as a target of learning. According to this, it is possible to increase the degree of completion of learning of the driving characteristic, and in automatic driving, it is possible to realize automatic driving that reproduces normal driving by the user and automatic driving that the user makes ideal. In addition, since inappropriate driving operations can be excluded from learning, the user does not need to be aware that inappropriate driving operations are not learned during manual driving. Therefore, the user can perform a normal manual operation as usual. As a result, it is possible to realize automatic driving that does not give the user a sense of discomfort. Further, since the degree of completion of learning can be increased, it is possible to eliminate the necessity of resetting the learning result and re-learning the driving characteristics. Furthermore, since unnecessary data need not be accumulated, the data capacity of the memory can be reduced.

  Further, the driving condition determination unit may determine that the driving condition is inappropriate for learning of the driving operation when there is deceleration at a deceleration equal to or higher than a predetermined first reference deceleration. According to this, the sudden braking can be excluded from the learning of the driving characteristic.

  Further, the driving condition determination unit may determine that the driving condition is not suitable for learning the driving operation, when there is acceleration at an acceleration equal to or higher than a predetermined first reference acceleration. According to this, the sudden acceleration can be excluded from the learning target of the driving characteristic.

  The driving situation determination unit may determine that the driving situation is inappropriate for learning the driving operation when the yaw rate is equal to or higher than a predetermined first reference yaw rate. According to this, the sharp steering wheel can be excluded from learning of the driving characteristic.

  The driving condition determination unit is not suitable for learning the driving condition as the driving condition, when there is a sudden stop factor and there is deceleration at a deceleration equal to or higher than a predetermined second reference deceleration. May be determined. According to this, it can be determined more accurately whether or not there has been a sudden brake that the user has to stop, and the sudden brake can be excluded from learning of driving characteristics more reliably.

  Further, the driving condition determination unit determines that the driving condition is inappropriate for learning of the driving operation when there is a sudden start factor and acceleration at an acceleration equal to or higher than a predetermined second reference acceleration occurs. You may According to this, it is possible to more accurately determine whether or not there is a sudden acceleration that the user can not stop, and the sudden acceleration can be more reliably excluded from learning of the driving characteristics.

  In addition, the driving condition determination unit determines that the driving condition is not suitable for learning the driving operation when there is a sudden steering factor and the yaw rate is equal to or higher than a predetermined second reference yaw rate. Good. According to this, it can be determined more accurately whether or not there is an abrupt steering wheel that the user can not stop, and the steering wheel can be more reliably excluded from learning of the driving characteristics.

  Further, the driving situation determination unit may determine that the driving situation is inappropriate for learning the driving operation when the vehicle speed exceeds a legal speed on the travel path. According to this, traveling at a vehicle speed exceeding the legal speed can be excluded from learning of the driving characteristic.

  Further, the driving condition determination unit determines that the driving condition is inappropriate for learning the driving operation, when the vehicle speed is equal to or less than a predetermined reference speed which is a speed below the legal speed on the traveling path. Good. According to this, traveling at a vehicle speed significantly lower than the legal speed can be excluded from learning of the driving characteristics.

  The driving situation determination unit may determine that the driving situation is inappropriate for learning the driving operation when the behavior of the vehicle is unstable. According to this, traveling where the behavior of the vehicle is unstable can be excluded from the learning target of the driving characteristics.

  In addition, the driving situation determination unit may determine that the driving situation is inappropriate for learning the driving operation when the past number of times of traveling on the currently running road is equal to or less than a predetermined reference number of times of driving. Good. According to this, driving on an unfamiliar road can be excluded from learning of driving characteristics.

The present invention can also be specified as a method of learning driving characteristics. That is, the present invention
In order to reflect the user's driving characteristics in the automatic driving of the vehicle, a method for learning the user's driving characteristics during manual driving of the vehicle, information indicating driving operation and information indicating driving status during the driving operation, Information acquisition step to acquire
A driving condition determination step of determining whether the driving condition is inappropriate for learning the driving operation based on the information acquired in the information acquisition step;
A learning object determination step for determining that the driving operation in the driving condition determined to be inappropriate in the driving condition determination step is not subject to learning,
It may be a learning method of driving characteristics.

  According to the present invention, by learning the driving operation of the user at the time of the manual driving of the vehicle, in the driving support device for reflecting the driving characteristic of the user to the automatic driving of the vehicle, learning of the driving operation inappropriate for learning the driving operation Can be excluded.

It is a figure showing the whole driving support system composition concerning a 1st embodiment. It is a figure which shows an example of the hardware constitutions of a driving assistance device. It is a flowchart of the driving characteristic learning process which a driving assistance device performs. It is a flowchart of the learning object determination process which a driving assistance device performs. It is a flowchart of the speed determination process which a driving assistance device performs. It is a flowchart of the rapid deceleration determination processing which a driving assistance device performs. It is a figure for demonstrating a standard deceleration. It is a flowchart of the modification of the rapid deceleration determination processing which a driving assistance device performs. It is a flowchart of the rapid acceleration determination process which a driving assistance device performs. It is a figure for demonstrating a reference acceleration. It is a flowchart of the modification of the rapid acceleration determination process which a driving assistance device performs. It is a flowchart of the sudden steering determination processing which a driving assistance device performs. It is a flowchart of the modification of the sudden-handling determination process which a driving assistance device performs. It is a flowchart of the wobbling driving determination process executed by the driving support device. It is a flowchart of the unfamiliar traveling path determination process which a driving assistance device performs. It is a flowchart of the modification of the learning target determination process which a driving assistance device performs. It is a figure which shows the whole structure of the driving assistance system which concerns on 2nd Embodiment. It is a screen displayed on a display apparatus, Comprising: It is a figure for demonstrating an example of designation operation by the user which a learning object exclusion designation | designated part receives. It is a screen displayed on a display apparatus, Comprising: It is a figure for demonstrating an example of designation operation by the user which a learning object exclusion designation | designated part receives. It is a screen displayed on a display apparatus, Comprising: It is a figure for demonstrating an example of designation operation by the user which a learning object exclusion designation | designated part receives. It is a screen displayed on a display apparatus, Comprising: It is a figure for demonstrating an example of designation operation by the user which a learning object exclusion designation | designated part receives.

  Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. However, the embodiments described below are exemplifications for carrying out the present invention, and the present invention is not limited to the embodiments described below.

First Embodiment
[overall structure]
FIG. 1 is a diagram illustrating an overall configuration of a driving support system 1 according to the first embodiment. As shown in FIG. 1, the driving support system 1 according to the present embodiment includes a driving support device 100, a navigation device 200, a GPS (Global Positioning System) device 300, various detection means 400, 500, 600, A display device 700, an operating device 800, and a control mechanism 900 are provided. The driving support system 1 is mounted on a vehicle and executes automatic driving based on various information acquired in manual driving by a user.

  The display device 700 is disposed at a position at which a user (mainly a driver) can visually recognize the vehicle interior of the vehicle, and various types of display devices such as a map display screen supplied from the navigation device 200 and an operation screen supplied from the driving assistance device 100 A device that displays visual information to a user. The display device 700 is, for example, a liquid crystal display. The display device 700 may be configured integrally with the navigation device 200. The display device 700 may include a sound output device such as a speaker, and may output various sound information such as a guide sound and a warning sound to the user.

  The operation device 800 is a device that is arranged at a position where the user can operate, receives an input operation by the user, and outputs a signal corresponding to the input operation to the driving support device 100 or the navigation device 200. The operation device 800 has a touch panel superimposed on a display provided in the display device 700, physical buttons, and the like. The user operates the driving support device 100 or the navigation device 200 by the touch operation on the touch panel or the press operation on the button. In addition, the controller device 800 may receive the driver's voice by a voice input device such as a microphone and may output a signal corresponding to the voice to the driving support device 100 or the navigation device 200.

  The detection means detects information related to the environment around the vehicle, the traveling state of the vehicle, and the driving operation of the vehicle. The detection means includes an environment information detection means 400 that detects environmental information that is information related to the surrounding environment of the vehicle, a vehicle information detection means 500 that detects vehicle information that is information related to the running state of the vehicle, and a driving operation of the vehicle by the user. And operation information detection means 600 for detecting operation information which is information related to

The environment information detection means 400 includes a camera 401 that captures an image around the vehicle, a microphone 402 that records environmental sounds around the vehicle, and the presence or absence of targets around the vehicle (mainly front vehicles or rear vehicles). It includes a millimeter wave radar 403 for detecting the speed, and a communication device 404 for acquiring various environment information by executing communication with an external server. The millimeter wave radar 403 transmits a millimeter wave (wavelength of about 1 to 10 mm and a frequency of 30 G to 300 GHz) around it, receives a reflected wave from a target, and deviates between the transmitted wave and the reflected wave. Based on the above, the relative distance to the target, the relative speed of the target, and the like are calculated. The communication device 404 executes inter-vehicle communication and road-vehicle communication. Further, the communication device 404 acquires road traffic information and road environment information by executing communication with an external server managed by an information center such as a VICS (Vehicle Information and Communication System: registered trademark) center, for example.

  The vehicle information detection unit 500 includes a vehicle speed sensor 501 that measures the speed of the vehicle, an acceleration sensor 502 that measures acceleration and deceleration acting on the vehicle, and a yaw rate sensor 503 that measures a yaw rate (rotational angular velocity) of the vehicle. including.

  The operation information detection means 600 includes an accelerator sensor 601 that detects an accelerator operation, a throttle sensor 602 that detects the opening of the engine throttle, a brake sensor 603 that detects a brake operation, and a steering wheel that detects a steering operation (steering). Sensor 604.

  The control mechanism 900 is a mechanism that adjusts at least one of acceleration / deceleration, steering, and braking of the vehicle by controlling actuators of various parts of the vehicle in accordance with the control of the driving support device 100. The control mechanism 900 according to this embodiment includes a throttle control mechanism 901, a steering control mechanism 903 and a brake control mechanism 902. The throttle control mechanism 901 adjusts the acceleration of the vehicle by supplying fuel to the engine and supplying power to the motor based on the control of the driving support device 100. The steering control mechanism 903 adjusts the traveling direction of the vehicle by steering based on the control of the drive assist device 100. The brake control mechanism 90232 operates the brake based on the control of the driving support device 100 to decelerate or stop the vehicle.

  The GPS device 300 is a device that detects current position coordinates of a vehicle. The GPS device 300 receives GPS information from a GPS artificial satellite via a GPS antenna, and detects the current position coordinates of the GPS unit (and thus the own vehicle) based on the received signal.

The navigation device 200 is a device that executes setting of a planned travel route (travel planned route) of the host vehicle and route guidance by the user. The navigation device 200 includes a current position calculation unit and a route guidance unit 202. In addition, a map including POI (Point Of Interest) data representing road data used mainly to represent road shapes, names and positions of various facilities, types, telephone numbers, etc. in a predetermined storage area of the navigation device 200. Data is stored. The current position calculation unit calculates the current position of the host vehicle based on the position coordinates of the host vehicle acquired from the GPS device 300 and the map data. When the route guidance unit 202 receives a destination setting by the user via the operation device 800, the route guidance unit 202 sets a planned travel route from the current location to the destination and identifies the road on which the host vehicle is traveling, and the display device 700. Route guidance according to the planned travel route is executed using the display and the speaker. In addition, the route guide unit 202 provides the driving support apparatus 100 with information indicating the set planned travel route. In addition to the map database DB3 configured by the above-described map data, the navigation device 200 also includes a route database DB4 in which information on a route traveled by the vehicle in the past is accumulated.

The driving support device 100 executes automatic driving to drive the vehicle to the destination according to the guide route acquired from the navigation device 200 by controlling the control mechanism 900 according to the situation around the vehicle. The driving support device 100 learns the user's driving characteristics based on the operation information acquired from the detection means during manual driving by the user, and reflects the learned driving characteristics in automatic driving. Here, how the user performs the driving operation differs depending on a situation during driving of the vehicle (hereinafter, driving situation). Furthermore, the degree of change in driving operation according to the driving situation varies depending on the user. That is, the characteristics of how to perform a driving operation for a specific driving situation vary from user to user. This characteristic that differs for each user is referred to herein as a driving characteristic. The driving support device 100 according to the present embodiment performs a special process, which will be described later, at the time of learning of driving characteristics, thereby excluding driving operation in a driving situation inappropriate for learning from being learned, and as a result, driving by the user It is possible to execute an automatic operation that accurately reflects the characteristics. Hereinafter, the driving support apparatus 100 according to the present embodiment will be described in detail.

  The driving method switching unit 101 switches the driving method of the vehicle between manual driving and automatic driving. For example, the driving method switching unit 101 switches the driving method by receiving a designating operation input by the user via the operating device 800.

  The information acquisition unit 102 acquires environment information from the environment information detection unit 400 and the navigation device 200, acquires vehicle information from the vehicle information detection unit 500, and operation information detection unit in the driving operation learning process executed during manual operation. Operation information is acquired from 600.

  As described above, the environmental information refers to information on the surrounding environment of the vehicle. More specifically, the environmental information includes information on legal speed of the traveling road (legal speed information), information on lanes of the traveling road (lane information), information on display information of traffic lights around the vehicle (traffic light information), vehicle surroundings Information on obstacles in the area (obstacle information), information on the presence or absence of nearby vehicles and information on the distance between vehicles ahead (around vehicle information), information on tracks on the road (track information), and information on alarms on alarms around vehicles (Alarm device information), information on the presence / absence of traffic jams and the degree of traffic jams (traffic jam information), and information on travel history of the travel route (running history information).

  Further, as described above, the vehicle information indicates information on the traveling state of the vehicle. More specifically, the vehicle information includes information related to vehicle speed (vehicle speed information), information related to vehicle acceleration and deceleration (acceleration / deceleration information), and information related to vehicle yaw rate (yaw rate information).

  In the present specification, the above-described environment information and vehicle information are collectively referred to as situation information. That is, the situation information is information related to the driving situation.

  As described above, the operation information indicates information related to a predetermined driving operation of the vehicle by the user. The predetermined driving operation is, for example, an accelerator operation, a brake operation, and a steering wheel operation. The operation information includes accelerator operation information, brake operation information, and handle operation information. The accelerator operation information includes information such as an accelerator depression amount, a throttle opening degree, an accelerator operation speed, and an accelerator operation timing. The brake operation information includes information such as the brake depression amount, the brake pressure, the brake operation speed, and the brake timing. The steering wheel operation information includes information such as a steering angle, a steering angular velocity, and steering operation timing.

  The driving condition determination unit 103 determines whether or not the driving condition indicated by the condition information acquired by the information acquiring unit 102 is an inappropriate driving condition for learning of the driving operation in the driving characteristic learning process performed at the time of manual driving. The determination is made based on the situation information. Details of the determination method of the driving situation determination unit 103 will be described later.

  The learning target determination unit 104 determines that the driving operation in the driving condition determined as inappropriate by the driving condition determination unit 103 is out of learning, and determines the driving operation in the driving condition determined as appropriate as the learning target. Details of the learning target determination unit 104 will be described later.

The driving operation learning unit 105 indicates operation information indicating a driving operation determined as a learning target by the learning target determination unit 104 in a driving characteristic learning process executed at the time of manual driving, and indicates a driving situation where the driving operation is performed. It is stored in the storage unit 108 in association with the information. The operation information is accumulated in the driving characteristic database DB1 of the storage unit 108. Thereby, the user's driving operation is learned in association with the driving situation in which the driving operation is executed. The user's driving characteristics are learned by learning driving operations corresponding to various driving situations. As a result, it is possible to execute an automatic operation reflecting the operation characteristics.

  The storage unit 108 stores various types of information according to processing executed by each processing unit of the driving support device 100. In addition to the driving characteristic database DB1 in which the operation information and the status information described above are accumulated, the storage unit 108 accumulates threshold information used for the judgment of the driving operation by the driving situation determination unit 103 in the driving characteristic learning process described later. A threshold database DB2.

  The automatic driving execution unit 106 causes the vehicle to travel to the destination according to the travel route acquired from the navigation device 200 by executing the automatic driving. The automatic driving execution unit 106 executes the automatic driving by controlling the control mechanism 900 based on the situation information acquired from the detecting means and the driving characteristics learned in the driving characteristics learning process.

  Here, the automatic driving process performed by the automatic driving execution unit 106 to execute the automatic driving will be described. First, the automatic driving execution unit 106 specifies the current driving situation by acquiring the situation information from the detection means. Next, the automatic driving execution unit 106 refers to the learning result of the driving operation accumulated in the driving characteristic database DB1. As described above, in the driving characteristic database DB1, the operation information and the situation information are stored in association with each other. Thereby, the automatic driving execution unit 106 specifies the driving operation corresponding to the driving condition. And the automatic driving | operation execution part 106 reproduces the driving | operation similar to the case where the driving operation corresponding to the present driving | running condition is performed by controlling operation | movement of each structure of the control mechanism 900. FIG. As a result, automatic driving in which the driving characteristic of the user is reflected is performed.

  The HMI control unit 107 controls an interface for executing input and output of information between the user and the driving support apparatus 100. More specifically, the HMI control unit 107 controls the operation device 800 and the display device 700.

FIG. 2 is a diagram illustrating an example of a hardware configuration of the driving support device 100. As illustrated in FIG. 2, the driving support apparatus 100 includes a CPU (Central Processing Unit) 10, a memory 20, a communication IF 30, and an input / output IF 40 that are connected to each other via a connection bus 50. CPU
A central processing unit 10 controls the entire driving support apparatus 100. The CPU 10 is also called a processor. However, the CPU 10 is not limited to a single processor, and may have a multiprocessor configuration. Further, a single CPU 10 connected by a single socket may have a multi-core configuration. The driving support device 100 is configured such that when the CPU 10 executes a navigation program, the driving method switching unit 101, the information acquisition unit 102, the driving situation determination unit 103, the learning target determination unit 104, the driving operation learning unit 105, and the automatic operation illustrated in FIG. It functions as each processing unit of the operation execution unit 106 and the HMI control unit 107. However, at least a part of the processing of each processing unit may be provided by a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), or the like. Further, at least a part of each of the processing units may be a dedicated LSI (large scale integration) such as an FPGA (Field-Programmable Gate Array) or other digital circuit. Further, at least part of each processing unit may include an analog circuit.

The memory 20 includes a main storage device and an auxiliary storage device. The main storage device functions as the storage unit 108 shown in FIG. 1 and is also a storage medium in which the CPU 10 caches programs and data, and expands a work area. The main storage device is, for example, a flash memory, RA
It includes M (Random Access Memory) and ROM (Read Only Memory). The auxiliary storage device is a recording medium on which the operation characteristic database DB1 and the threshold database DB2 shown in FIG. 1 are mainly recorded. Auxiliary storage devices include, for example, HDD (Hard-disk Drive), SSD (Solid State Drive), EPROM (Erasable Programmable ROM), flash memory, USB
Memory, including memory card.

  The communication IF 30 is an interface that can be connected to a general-purpose network via a base station through a wireless telephone line. The communication IF 30 can communicate with a wireless LAN access point (AP), and can be connected to a network via an arbitrary communication means.

  The input / output IF 40 is an interface for inputting / outputting data to / from devices such as the driving support device 100, the navigation device 200, the display device 700, the operation device 800, and the ECU. The input / output IF 40 functions as the HMI control unit 107 shown in FIG. A user's input operation on the operation device 800 is input to the driving support device 100 via the input / output IF 40.

[Driving characteristics learning process]
Next, driving characteristic learning processing executed by the driving support device 100 according to the present embodiment will be described. As described above, the driving support apparatus 100 can reflect the driving characteristics of the user in the automatic driving by learning the driving operation of the user in the manual driving. On the other hand, driving operations in driving situations inappropriate for learning driving operations should be excluded from learning. An inappropriate driving situation for learning is a situation where the user can not drive as usual or a situation where the user can not drive according to his / her preference because of irregular or sudden reasons. When the learning result of the irregular driving operation performed in such a situation is reflected in the automatic driving, to realize the automatic driving that reproduces the normal driving by the user or the automatic driving that the user likes as the user's ideal There is a risk that

  As a specific example of the improper driving situation of the driving operation, the situation where the user is forced to carry out a sudden deceleration, sudden acceleration or sudden steering without stopping, or travels significantly below the legal speed. Situations, driving with unstable behavior (steady driving), driving on unfamiliar roads or roads that are difficult to drive, or other driving difficulties. As a case where the user carries out a sudden deceleration without stopping, for example, when the color of the signal changes from blue (may advance) to yellow (stopped) just before passing the signal, a pedestrian etc. When it approachs into the traveling path of a vehicle (jumps out), the case where the forward vehicle has rapidly decelerated etc. may be mentioned. Moreover, as a case where the user inevitably stops sudden acceleration, for example, a case where an alarm starts to sound while passing through a level crossing can be cited. In addition, as a case where the user turns suddenly without stopping, for example, there is a case where a pedestrian or the like jumps out. Moreover, as a case where it travels exceeding legal speed, the case where a user does not notice that it exceeds legal speed, etc. are mentioned, for example. Further, as a case where the vehicle travels significantly below the legal speed, for example, there may be a case where the traveling route is congested due to traffic congestion or the like. In addition, as a case where the driver does not move, for example, there is a case where the steering wheel operation is not blurred due to the user's lack of sleep or the like. When driving an unfamiliar road or a road that is difficult to drive, or when driving is difficult, for example, the user may drive a road that is driving for the first time. On the first driving road, it tends to be difficult for the user to drive as usual.

  FIG. 3 is a flowchart of driving operation learning processing executed by the driving support apparatus 100 according to the present embodiment. The driving support apparatus 100 according to the present embodiment can exclude driving operations inappropriate for learning described above from learning by performing special processing in learning of driving operations. The details will be described below.

  The driving operation learning process according to the present embodiment is performed during a manual operation by the user. First, in step S100, the information acquisition unit 102 acquires operation information and status information (step S100, information acquisition step).

  In step S <b> 100, the information acquisition unit 102 acquires operation information from the operation information detection unit 600. Specifically, the information acquisition unit 102 acquires accelerator operation information from the accelerator sensor 601 and the throttle sensor 602 as operation information, acquires brake operation information from the brake sensor 603, and acquires steering wheel operation information from the steering sensor 604. Do.

  As described above, the situation information includes environment information and vehicle information. The information acquisition unit 102 acquires environment information from the environment information detection unit 400 and the navigation device 200, and acquires vehicle information from the vehicle information detection unit 500.

  The information acquisition unit 102 responds to the current driving situation among the legal speed information, lane information, traffic signal information, obstacle information, surrounding vehicle information, track information, alarm information, traffic jam information and travel history information as environmental information. Acquire information that can be acquired.

  Legal speed information can be acquired by detecting a speed limit sign from an image captured by the camera 401. The legal speed information may be acquired from an external server by the communication device 404, or may be acquired from the map database DB3 of the navigation device 200. Lane information can be acquired by detecting a lane from an image captured by the camera 401. Similarly, the traffic signal information can be acquired when the camera 401 detects the traffic signal from the image. Obstacle information and surrounding vehicle information can be acquired by detecting surrounding vehicles using an image captured by the camera 401 or the millimeter wave radar 403. The track information can be acquired by detecting the track from an image captured by the camera 401. The track information may be acquired from an external server by the communication device 404, or may be acquired from the map database DB3 of the navigation device 200. The alarm information can be acquired by detecting an alarm sound from the environmental sound recorded by the microphone 402. The travel history information can be acquired from the route database DB4.

Further, the information acquisition unit 102 acquires vehicle speed information from the vehicle speed sensor 501, acceleration / deceleration information from the acceleration sensor 502, and yaw rate information from the yaw rate sensor 503 as vehicle information. Note that the information acquisition unit 102 may acquire the vehicle speed based on the interval of vehicle speed pulses acquired by CAN (Controller Area Network) communication.

  Next, in step S200, it is determined whether the driving operation indicated by the acquired operation information is to be learned (step S200). FIG. 4 is a flowchart showing details of the learning target determination process executed in step S200.

  As shown in FIG. 4, in the learning target determination process, the driving condition determination unit 103 determines whether the driving condition is inappropriate for learning in steps S201, S203, S205, S207, S209, and S211 ( Driving condition determination step), the learning object determination unit 104 sets driving operation in the driving condition as a learning object based on the determination result of the driving condition determination unit 103 in steps S202, S204, S206, S208, S210, and S212. (Learning object determination step).

Specifically, in step S201, the driving condition determination unit 103 determines whether or not the vehicle is traveling at an inappropriate vehicle speed for learning (step S201), and in step S203,
It is determined whether or not sudden deceleration has occurred (step S203), and it is determined whether or not rapid acceleration has occurred in step S205 (step S205). In step S207, it is determined whether or not sudden steering has occurred (step S207) In step S209, it is determined whether or not a wobbling operation has been performed (step S209). In step S211, it is determined whether or not the driving is on an unfamiliar road (step S211). The following will be described in order.

FIG. 5 is a diagram illustrating details of the speed determination process executed in step S201. In the speed determination process in step S201, when the vehicle speed exceeds the legal speed or when the vehicle speed is significantly lower than the legal speed, the driving situation is determined to be inappropriate for learning. As shown in FIG. 5, in the speed determination process, first, in step S2011, whether or not the current vehicle speed has exceeded the legal speed based on the vehicle speed information acquired in step S1 by the driving situation determination unit 103. It is determined (step S2011). Here, the vehicle speed acquired by the information acquisition unit 102 in step S1 is V _A , and the legal speed is V _L. The driving state determination unit 103 determines whether or not V _A > V _L in step S2011. If V _A > V _L (step S2011-YES), that is, if the vehicle speed exceeds the legal speed, the process proceeds to step S2013. If V _A > V _L is not satisfied (step S2011-NO), that is, if V _A ≦ V _L , the process proceeds to step S2012.

In step S2012, it is determined whether the vehicle speed is significantly lower than the legal speed (step S2012). Here, the threshold database DB2 of the storage unit 108, the reference speed V _T which vehicle speed is whether criteria had significantly less than the legal speed is stored in step S2012. The reference speed V _T is determined to be a sufficiently small value with respect to the legal speed. That is, V _T <V _L. The reference speed V _T is a vehicle speed that can be regarded as a travel that is significantly slower (the vehicle speed is smaller) than the travel in the normal driving of the user when the vehicle speed is equal to or lower than the reference speed V _T. Reference speed V _T may be different values depending on legal speed V _L, it may be determined based on the average value of the vehicle speed in the previous travel user. In step S2012, a reference speed V _T corresponding to the legal speed on the traveling road is acquired from the threshold value database DB2, and it is determined whether V _A ≦ V _T. If V _A ≦ V _T (step S2012-YES), that is, if the current vehicle speed is significantly lower than the legal speed, the process proceeds to step S2013. If V _A > V _T (step S2012-NO), that is, if the vehicle speed is not significantly lower than the legal speed, it is determined in step S2014 that the driving situation is appropriate for learning (step S2014).

In step S2013, it is determined whether or not the traveling speed has exceeded the legal speed and the time which has been significantly lower than the legal speed is a short time (step S2013). For example, when the vehicle speed exceeds the legal speed for a short time to overtake the car ahead, or when the car speed is significantly lower than the legal speed for a short time because of an appropriate stop at an intersection or a level crossing etc. Should not be excluded from learning. Therefore, by executing the processing in step S2013, a situation in which the legal speed is exceeded for a short time or a situation in which the legal speed is significantly reduced is not determined as an inappropriate driving situation. Here, in the threshold value database DB2 of the storage unit 108, in step S2013, it is determined whether the time when the vehicle speed continuously exceeds the legal speed or the time when the legal speed is continuously significantly lower is a short time. A reference time which is a reference for the purpose is stored. The time when the vehicle speed continuously exceeds the legal speed or the time when the vehicle speed is significantly lower than the legal speed is T, and the reference time is T _T. In step S2013, the reference time _{T T} acquired from the threshold database DB2, determines whether or not T ≦ _{T T.} If T ≦ T _T (step S2013-YES), that is, if the time during which the vehicle speed has continuously exceeded the legal speed or the time when the speed has been significantly lower than the legal speed for a short time, It is determined that the driving situation is appropriate for learning (step S2014). On the other hand, if T ≦ T _T (step S2013-NO), that is, if T> T _T , the process proceeds to step S2015, and the time at which the vehicle speed continuously exceeds the legal speed or the legal speed is continuously It is determined that the driving time is significantly unsuitable for learning on the assumption that the time significantly decreased is a long time (step S2015).

  In step S2015, the driving situation that is finally determined to be an inappropriate driving situation for learning, that is, the vehicle speed continuously exceeds the legal speed for a long time or significantly lower than the legal speed. The situation is

  Returning to FIG. 4, in step S <b> 202, the learning target determination unit 104 determines whether it is determined in step S <b> 201 that the driving situation is inappropriate (step S <b> 202). If it is not determined in step S201 that the driving condition is inappropriate for learning (step S202-NO), that is, if it is determined in step S201 that the driving condition is appropriate for learning, the process proceeds to step S203. If it is determined in step S201 that the driving condition is inappropriate for learning (step S202-YES), the process proceeds to step S214, and it is determined that the driving operation in the driving condition is not to be learned (step S214).

FIG. 6 is a diagram showing details of the rapid deceleration determination process executed in step S203. In the rapid deceleration determination process of step S203, when it is determined that there has been a rapid deceleration, it is determined that the driving situation is inappropriate for learning. As shown in FIG. 6, in the rapid deceleration determination process, first, in step S2032, whether or not the driving condition determination unit 103 has decelerated more than a predetermined threshold based on the situation information acquired in step S1. It judges (Step S2032). Here, the threshold database DB2 of the storage unit 108 stores a reference deceleration that is a criterion for rapid deceleration in step S2032. The reference deceleration is a deceleration that can be regarded as a deceleration that is remarkably abrupt (the deceleration is large) with respect to the deceleration caused by the brake operation that the user normally performs when the vehicle is decelerated at a deceleration greater than that value. The reference deceleration may be determined based on, for example, an average value of deceleration in the user's past travel. Here, the deceleration acquired in step S1 is D, and the reference deceleration acquired from the threshold value database DB2 is a first reference deceleration _DT1 . In step S2032, it is determined whether D ≧ D _T1 . If a D ≧ _{D T1} (step S2032-YES), i.e., if the rapid deceleration has been performed, in step S2035, determines that inappropriate driving condition to the learning (step S2035). Not D ≧ _{D T1,} when a D _{<D T1} (step S2032-NO), i.e., if the rapid deceleration has not been performed, in step S2034, an appropriate driving condition to the learning (step S2034) . FIG. 7 is a diagram for explaining the reference deceleration. The vertical axis in FIG. 7 indicates the vehicle speed V, and the horizontal axis indicates the time t. The time when the vehicle running at the vehicle speed V ₀ starts to decelerate is set to t = 0, and the deceleration when V = 0 at t = t ₁ is set as the reference deceleration D _T1 . At this time, when V = 0 at t = t ₂ (≦ t ₁ ) (region indicated by hatching in the figure), it is determined that the vehicle is decelerating rapidly in step S2032.

FIG. 8 is a diagram illustrating a modification of the rapid deceleration determination process executed in step S203. In a modified example of the rapid deceleration determination process, step S2031 is executed before step S2032. In step S2031, the driving state determination unit 103 determines whether or not there is a sudden stop factor (step S2031). The sudden stop factor is a factor that allows the user to make a sudden stop. Whether or not there is a sudden stop factor is determined based on the situation information acquired in step S1. For example, if it is determined based on the traffic signal information acquired in step S1 that the display of the traffic light has been changed from blue to yellow immediately before passing through the traffic light, the driving status determination unit 103 determines that there is a sudden stop factor. judge. In addition, when it is determined based on the obstacle information and surrounding vehicle information acquired in step S1 that there has been a sudden jump-out or the preceding vehicle has stopped suddenly, the driving situation determination unit 103 indicates that there is a cause of a sudden stop. judge. In step S2031, when there is no sudden stop factor (step S2031-NO), the process proceeds to step S2032. In step S2031, when there is a sudden stop factor (step S2031-YES), the process proceeds to step S2033. In step S2033, the driving situation determination unit 103 determines whether or not deceleration greater than a predetermined threshold has been performed based on the situation information acquired in step S1 (step S2033). In step S2033, it is determined whether D D D _T2 . If a D ≧ _{D T2} (Step S2033-YES), step S2035, determines that the improper operating conditions in the learning (step S2035). If D ≧ D _T2 is not satisfied (step S2033-NO), it is determined in step S2034 that the driving situation is appropriate for learning (step S2034). Here, _DT2 is a second reference deceleration, which is a deceleration threshold stored in the threshold database DB2 of the storage unit 108. In step S2031, since it has been found that there is a cause of a sudden stop, it is highly likely that the user has suddenly decelerated that the driving situation has to be stopped, that is, an inappropriate deceleration for learning. . Therefore, D _T2 <D _T1 is set, and the reference deceleration is set smaller than when there is no sudden stop factor. By doing so, it is possible to determine more accurately whether or not there has been an inappropriate deceleration for learning.

  Returning to FIG. 4, in step S <b> 204, the learning target determination unit 104 determines whether it is determined in step S <b> 203 that the driving situation is inappropriate (step S <b> 204). If it is not determined in step S203 that the driving condition is inappropriate for learning (step S204-NO), that is, if it is determined in step S203 that the driving condition is appropriate for learning, the process proceeds to step S205. If it is determined in step S203 that the driving condition is inappropriate for learning (step S204-YES), the process proceeds to step S214, and the driving operation (mainly the brake operation) in the driving condition is determined to be outside the learning target ( Step S214).

FIG. 9 is a diagram showing details of the rapid acceleration determination process executed in step S205. In the rapid acceleration determination process of step S205, when it is determined that rapid acceleration has occurred, it is determined that the driving situation is inappropriate for learning. As shown in FIG. 9, in the rapid acceleration determination process, first, in step S2052, whether or not the driving state determination unit 103 has accelerated more than a predetermined threshold based on the state information acquired in step S1. It determines (step S2052). Here, in the threshold value database DB2 of the storage unit 108, a reference acceleration that is a determination criterion for rapid acceleration in step S2052 is stored. The reference acceleration is an acceleration that can be regarded as an acceleration that is remarkably abrupt (high acceleration) with respect to the acceleration by the accelerator operation that the user normally performs when accelerating at an acceleration greater than that value. The reference acceleration may be determined based on, for example, an average value of acceleration in the past travel of the user. Here, the acceleration acquired in step S1 is A, and the reference acceleration acquired from the threshold database DB2 is a first reference acceleration _AT1 . In step S2052, it is determined whether A ≧ A _T1 . If A ≧ A _T1 (step S2052-YES), that is, if rapid acceleration has been performed, it is determined in step S2055 that the driving situation is inappropriate for learning (step S2055). If not A ≧ A _T1 but A <A _T1 (step S2052-NO), that is, if rapid acceleration has not been performed, it is determined in step S2054 that the driving state is appropriate for learning (step S2054). . FIG. 10 is a diagram for explaining the reference acceleration. The vertical axis in FIG. 10 indicates the vehicle speed V, and the horizontal axis indicates the time t. The time at which the vehicle is stopped (V = 0) starts the acceleration and t = 0, the acceleration when the V = _{V 0} at t = _{t 1} and reference acceleration _{A T1.} At this time, when t = t ₂ (≦ t ₁ ) and V = V ₀ (the area indicated by hatching in the figure), it is determined in step S2052 that the acceleration is rapid.

FIG. 11 is a diagram illustrating a modification of the rapid acceleration determination process executed in step S205. In a modified example of the rapid acceleration determination process, step S2051 is executed before step S2052. In step S2051, the driving situation determination unit 103 determines whether there is a sudden start factor (step S2051). The sudden start factor is a factor that allows the user to make a sudden start.
Whether there is a sudden start factor is determined based on the situation information acquired in step S1. For example, if it is determined based on the crossing information acquired in step S1 that the alarm has been ringing during passing through the level crossing or the alarm information, the driving state determination unit 103 determines that the sudden start factor is present. . In step S2051, when there is no sudden start factor (step S2051-NO), the process proceeds to step S2052. If there is a sudden start factor in step S2051 (step S2051-YES), the process proceeds to step S2053. In step S2053, the driving situation determination unit 103 determines whether acceleration equal to or greater than a predetermined threshold has been performed based on the situation information acquired in step S1 (step S2053). In step S2053, determines whether the A ≧ _{A T2.} If A ≧ A _T2 (step S2053-YES), it is determined in step S2055 that the driving situation is inappropriate for learning (step S2055). If not A ≧ _{A T2} (Step S2053-NO), step S2054, determines an appropriate driving condition to the learning (step S2054). Here, _AT2 is the second reference acceleration, and is a threshold value of acceleration stored in the threshold value database DB2 of the storage unit 108. In step S2051, since it has been found that there is a sudden start factor, it is highly likely that the driving situation was suddenly accelerated by the user, that is, there was inappropriate acceleration for learning. . Therefore, A _T2 <A _T1 is set, and the reference acceleration is set smaller than when there is no sudden start factor. By doing so, it is possible to more accurately determine whether or not there has been an inappropriate acceleration in learning.

  Returning to FIG. 4, in step S <b> 206, the learning target determination unit 104 determines whether or not it is determined that the driving situation is inappropriate in step S <b> 205 (step S <b> 206). If it is determined in step S205 that the driving situation is not suitable for learning (step S206-NO), that is, if it is determined in step S205 that the driving situation is suitable for learning, the process proceeds to step S207. When it is determined in step S205 that the driving condition is inappropriate for learning (step S206-YES), the process proceeds to step S214, and it is determined that the driving operation (mainly accelerator operation) in the driving condition is not the learning target ( Step S214).

FIG. 12 is a diagram showing details of the sudden handle determination process executed in step S207. In the sudden handle determination process in step S207, if there is a sudden handle, it is determined that the driving situation is inappropriate for learning. As shown in FIG. 12, in the sudden handle determination process, first, in step S2072, the driving condition determination unit 103 determines whether or not the yaw rate is equal to or greater than a predetermined threshold based on the condition information acquired in step S1. (Step S2072). Here, in the threshold value database DB2 of the storage unit 108, a reference yaw rate that is a criterion for determining a sharp handle in step S2072 is stored. The reference yaw rate is a yaw rate that can be regarded as a steering operation that is remarkably abrupt (a yaw rate is large) compared to a steering operation that a user normally performs when the yaw rate is equal to or higher than that value. The reference yaw rate may be determined based on, for example, an average value of yaw rates in the past travel of the user. Here, the yaw rate acquired in step S1 is Y, and the reference yaw rate acquired from the threshold database DB2 is the first reference yaw rate Y _T1 . In step S2072, it is determined whether Y ≧ Y _T1 . If Y ≧ Y _T1 (step S2072-YES), that is, if a sharp steering is being performed, it is determined in step S2075 that the driving situation is inappropriate for learning (step S2075). When Y <Y _T1 (step S2072-NO), that is, when the sudden steering is not performed, it is determined in step S2074 that the driving situation is appropriate for learning (step S2074).

FIG. 13 is a diagram illustrating a modification of the sudden handle determination process executed in step S207. In a modified example of the sudden handle determination process, step S2071 is executed before step S2072. In step S2071, the driving situation determination unit 103 determines whether or not there is a sudden handle factor (step S2071). The sudden steering factor is a factor that allows the user to make a sudden steering. Whether there is a sudden handle factor is determined based on the situation information acquired in step S1. For example, when it is revealed based on the traffic signal information acquired in step S1 that the display of the traffic light has been changed from blue to yellow immediately before passing through the traffic light, the driving situation determination unit 103 has a sudden steering cause. Is determined. Further, if it is determined based on the obstacle information and the surrounding vehicle information acquired in step S1 that there is a sudden jump out or that the preceding vehicle has suddenly stopped, the driving situation determination unit 103 determines that there is a sudden steering factor. judge. If it is determined in step S2071 that a sudden steering factor is not present (step S2071-NO), the flow proceeds to step S2072. In step S2071, if there is a sudden handle factor (step S2071-YES), the process proceeds to step S2073. In step S2073, the driving condition determination unit 103 determines whether the yaw rate is equal to or greater than a predetermined threshold value based on the condition information acquired in step S1 (step S2073). In step S2073, determines whether the Y ≧ _{Y T2.} If Y Y Y _T2 (step S2073-YES), it is determined in step S2075 that the driving situation is inappropriate for learning (step S2075). Not Y ≧ _{Y T2,} if it is Y _{<Y T2} (Step S2073-NO), step S2074, determines an appropriate driving condition to the learning (step S2074). Here, Y _T2 is the second reference yaw rate, and is the threshold of the yaw rate stored in the threshold database DB2 of the storage unit 108. In step S2071, since it is known that there is a sudden steering factor, the driving condition is the sudden steering performed by the user without stopping, that is, a situation in which the steering operation is inappropriate for learning. Probability is high. Therefore, Y _T2 <Y _T1 is set, and the reference yaw rate is set to be smaller than that in the case where there is no sudden handle factor. By doing so, it is possible to more accurately determine whether or not there has been a handle operation inappropriate for learning.

  Returning to FIG. 4, in step S <b> 208, the learning target determination unit 104 determines whether it is determined in step S <b> 207 that the driving situation is inappropriate (step S <b> 208). If it is determined in step S207 that the driving situation is not suitable for learning (step S208-NO), that is, if it is determined in step S207 that the driving situation is suitable for learning, the process proceeds to step S209. If it is determined in step S207 that the driving condition is inappropriate for learning (step S208-YES), the process proceeds to step S214, and the driving operation (mainly the steering wheel operation) in the driving condition is determined to be outside the learning target ( Step S214).

  FIG. 14 is a diagram illustrating details of the wobbling operation determination process executed in step S209. In the wobbling driving determination process in step S209, when it is determined that the driving situation is the wobbling driving, the driving situation is determined to be inappropriate for learning. As shown in FIG. 14, in the wobbling driving determination process, first, in step S2091, the driving state determination unit 103 determines whether or not there is a departure from the lane of the host vehicle based on the lane information acquired in step S1. (Step S2092). As described above, lane information can be acquired by detecting a lane from an image captured by the camera 401. If there is a departure from the lane (step S2091-YES), it is determined in step S2092 that the driving situation is inappropriate for learning because it is determined that the wandering has been performed (step S2092). If there is no departure from the lane (step S2091-NO), it is determined that the driving situation is appropriate for learning, since it is determined in step S2093 that the drivability has not been performed (step S2093).

Returning to FIG. 4, in step S <b> 210, the learning target determination unit 104 determines whether it is determined in step S <b> 209 that the driving situation is inappropriate (step S <b> 210). If it is not determined in step S209 that the driving condition is inappropriate for learning (step S210-NO), that is, if it is determined in step S209 that the driving condition is appropriate for learning, the process proceeds to step S211. When it is determined in step S209 that the driving situation is inappropriate for learning (step S210-YES), the process proceeds to step S214, and the driving operation in the driving state is determined to be out of learning (step S214).

  FIG. 15 is a diagram showing details of the inexperienced traveling road determination processing executed in step S211. In the unfamiliar traveling road determination process of step S211, when it is determined that the driving situation is traveling on an unfamiliar traveling road, it is determined that the driving situation is inappropriate for learning. As shown in FIG. 15, in the unaccustomed traveling road determination process, first, in step S2111, based on the traveling history information acquired by the driving situation determination unit 103 in step S1, the traveling road currently traveling is unfamiliar to the user It is determined whether or not it is a road (step S2111). Here, the threshold database DB2 of the storage unit 108 stores a reference number of times N that is a criterion for determining whether or not the road is unfamiliar in step S2032. The reference traveling number N is the number of travelings that can be regarded as a traveling route unfamiliar to the user when the past traveling number n of the traveling route that is currently traveling is equal to or less than the value. The reference number of times N may be N = 0, for example. In that case, it is possible to regard the traveling path where the user travels for the first time as the unaccustomed traveling path. In step S2111, it is determined whether n ≦ N. If n ≦ N (step S2111-YES), it is determined in step S2112 that the driving condition is unsuitable for learning because it is unfamiliar traveling on the travel path (step S2112). If n ≦ N is not satisfied (step S2111-NO), that is, if n> N, it is determined in step S2113 that the driving condition is not suitable for learning because it is not an unfamiliar traveling road (step S2113).

  Returning to FIG. 4, in step S212, the learning target determination unit 104 determines whether or not it is determined in step S211 that the driving situation is inappropriate (step S212). If it is determined in step S211 that the driving situation is not suitable for learning (step S212-NO), that is, if it is determined in step S211 that the driving situation is suitable for learning, the process proceeds to step S213. If it is determined in step S211 that the driving condition is inappropriate for learning (step S212-YES), the process proceeds to step S214, and it is determined that the driving operation in the driving condition is not to be learned (step S214).

  In step S213, the driving operation indicated by the operation information acquired in step S1 is determined as a learning target (step S213). The driving operation determined to be the learning target in step S213 is, in other words, the driving operation in the driving situation determined to be appropriate for learning in all of steps S201, S203, S205, S207, S209, and S211.

Returning to FIG. 3, in step S300, the driving operation learning unit 105 determines whether or not the driving operation is determined as a learning target in step S200 (step S300). If it is determined that it is a learning target (step S300-YES), the process proceeds to step S400. If it is not determined to be the learning target (step S300-YES), that is, if it is determined to be out of the learning target, the process proceeds to step S500. In step S400, the operation information indicating the driving operation as the learning target is associated with the situation information and stored in the storage unit 108 (step S400). Thereby, the learning result of the said driving operation is accumulate | stored in driving | operation characteristic database DB1. In step S500, the operation information and the situation information that are not subject to learning are discarded (step S500). More specifically, the information acquired from the time when the driving operation that is not subject to learning is started to the time when the driving operation ends is discarded. By repeating the processing from step S100 to step S500 during manual driving by the user, the learning result of driving operation in a driving situation appropriate for learning of driving operation is accumulated in the driving characteristic database DB1. Thus, the learning processing of the driving characteristic is executed. The driving support apparatus 100 according to the present embodiment performs driving characteristic learning with high accuracy by excluding driving operation in an inappropriate driving situation from learning and driving operation in an appropriate driving situation as a learning target. be able to.

[Operation / effect]
As described above, the driving support device 100 according to the first embodiment learns the driving status based on the information acquisition unit 102 that acquires the driving operation information and the driving status information, and the information acquired by the information acquisition unit 102. A driving condition determining unit 103 that determines whether or not the driving condition is appropriate, and a learning target determining unit 104 that determines that the driving operation in the driving condition determined to be inappropriate by the driving condition determining unit 103 is not subject to learning. . According to such a driving support device 100, driving operations in driving situations inappropriate for learning can be excluded from learning. According to this, the completeness of learning of driving characteristics can be enhanced, and in automatic driving, automatic driving that reproduces the normal driving by the user and automatic driving ideal by the user can be realized. In addition, since an inappropriate driving operation can be excluded from the learning target, the user does not have to be conscious of not learning an inappropriate driving operation during manual driving. Therefore, the user may perform the normal manual operation. As a result, it is possible to realize automatic driving without a sense of discomfort to the user. Further, since the degree of completion of learning can be increased, it is possible to eliminate the necessity of resetting the learning result and re-learning the driving characteristics. Furthermore, since unnecessary data need not be accumulated, the data capacity of the memory can be reduced.

Further, in step S201, when the vehicle speed exceeds the legal speed V _L on the traveling path, the driving condition determination unit 103 determines that the driving condition is unsuitable for learning of the driving operation. According to this, traveling at a vehicle speed that exceeds the legal speed can be excluded from learning of driving characteristics. Furthermore, in step S201, the driving situation determination unit 103 determines that the driving situation is inappropriate for learning the driving operation when the vehicle speed is equal to or lower than a predetermined reference speed V _T that is lower than the legal speed on the road. You may judge. According to this, traveling at a vehicle speed that is significantly lower than the legal speed can be excluded from learning of driving characteristics.

Further, the operation state determination section 103 determines in step S203, if there is decelerated at a predetermined first reference deceleration deceleration exceeding D _T1, inappropriate operating conditions for learning driving operation. According to this, the sudden braking can be excluded from the learning of the driving characteristic. Further, the operation state determination section 103 determines in step S205, when there is an acceleration of a predetermined first reference acceleration A _T1 acceleration or more, and unsuitable operating conditions for learning driving operation. According to this, the sudden accelerator can be excluded from the learning target of the driving characteristics. Furthermore, the operation state determination section 103 determines in step S207, when the yaw rate is was first reference yaw rate Y _T1 or more predetermined, inappropriate operating conditions for learning driving operation. According to this, the sudden handle can be excluded from the learning target of the driving characteristics.

In addition, in step S203, the driving situation determination unit 103 determines the driving situation of the driving operation when there is a sudden stop factor and there is a deceleration at a deceleration equal to or higher than a predetermined second reference deceleration _DT2 . You may decide that it is unsuitable for learning. According to this, it can be determined more accurately whether or not there is a sudden brake that the user can not stop, and the sudden brake can be more surely excluded from the learning target of the driving characteristic. In step S205, the driving situation determination unit 103 uses the driving situation to learn driving operation when there is an abrupt start factor and there is acceleration at an acceleration equal to or higher than a predetermined second reference acceleration _AT2. It may be determined as inappropriate. According to this, it can be determined more accurately whether or not there is a sudden accelerator that the user has to stop, and the sudden accelerator can be more reliably excluded from the learning target of the driving characteristics. Further, the operation state determination section 103 in step S207, there are abrupt steering factors, and, when the yaw rate was the second reference yaw rate Y _T2 or more predetermined, inappropriate operating conditions for learning driving operation You may judge. According to this, it can be determined more accurately whether or not there is an abrupt steering wheel that the user can not stop, and the steering wheel can be more reliably excluded from learning of the driving characteristics.

  In addition, in step S209, the driving situation determination unit 103 determines that the driving situation is inappropriate for learning the driving operation when there is a wobbling driving. According to this, traveling where the behavior of the vehicle is unstable can be excluded from the learning target of the driving characteristics.

  Further, in step S211, the driving condition determination unit 103 determines that the driving condition is not suitable for learning the driving operation when the number of times the vehicle has traveled in the past is less than or equal to a predetermined reference number of travelings. Do. According to this, driving on an unfamiliar road can be excluded from learning of driving characteristics.

  Note that the deceleration determination in step S203 may be executed based on operation information such as brake pressure, brake depression amount, and brake pressure acquired from the brake sensor 603. For example, in step S203, when the brake depression amount acquired from the brake sensor 603 is greater than or equal to a predetermined amount, the driving situation may be determined to be inappropriate for learning.

  Further, the acceleration determination in step S205 may be executed based on operation information such as the accelerator depression amount and the throttle opening obtained from the accelerator sensor 601 and the throttle sensor 602. For example, in step S205, when the throttle opening obtained from the throttle sensor 602 is greater than or equal to a predetermined value, the driving situation may be determined to be inappropriate for learning.

  The determination of the yaw rate in step S207 may be performed based on operation information such as a steering angle acquired from the steering sensor 604. For example, in step S207, when the steering angle acquired from the steering sensor 604 is greater than or equal to a predetermined value, it may be determined that the driving situation is inappropriate for learning.

  FIG. 16 is a diagram showing a modification of the learning object determination process. As illustrated in FIG. 16, the learning target determination unit 104 determines that the driving operation in the driving situation determined to be inappropriate in any of steps S201, S203, S205, S207, S209, and S211 in step S215 as a learning target. The user may select whether or not to perform the process (step S215). The learning target determination unit 104 displays, for example, on the screen of the display device 700 to select whether or not the driving operation in the driving situation determined to be inappropriate is to be the learning target. It may be attached in response to the selection operation. When the user selects the learning target (step S215-YES), the learning target determination unit 104 proceeds to step S213 and sets it as the learning target. On the other hand, when the user selects not to be learned (step S215-NO), the process proceeds to step S214, and is excluded from learning.

Second Embodiment
FIG. 17 is a diagram showing a driving support system 1A according to the second embodiment. The driving support apparatus 100A constituting the driving support system 1A according to the second embodiment can exclude the driving operation that matches the condition specified by the user's specified operation as the target of learning.

  As shown in FIG. 17, the driving support system 1A according to the second embodiment is different from the driving support system 1 according to the first embodiment in that the driving support device 100A includes the non-learning object designation unit 109. The other configuration is the same as that of the driving support system 1 according to the first embodiment. Hereinafter, the driving support system 1A according to the second embodiment will be described focusing on differences from the driving support system 1 according to the first embodiment, and the detailed description will be given by attaching the same reference numerals to the same components. I will omit it.

  The driving assistance apparatus 100A according to the second embodiment executes the same process as the driving characteristic learning process executed by the driving assistance apparatus 100 according to the first embodiment. Thereby, the learning result of the driving operation in the manual driving is accumulated in the driving characteristic database DB1. The driving support apparatus 100A according to the second embodiment meets the condition designated by the user from among the driving operations determined as the learning target in the learning target determination processing by receiving the user's designating operation after manual driving. Driving operation can be excluded from learning.

  FIGS. 18 and 19 are screens displayed on the display device 700, and are diagrams for explaining an example of a designation operation by the user that is accepted by the non-learning target designation unit 109. FIG. The learning object exclusion designation unit 109 may exclude driving operation in the position range designated by the user as the learning object. As shown in FIG. 18, the non-learning object designation unit 109 causes the display device 700 to display the traveling route R on which the driving characteristic learning has been performed. Then, the user traces the operating route R1 with the operating finger Z1 by tracing with the operating finger Z1 via the operating device 800 (touch panel) arranged on the display screen so as to overlap the operating route R1 that the user wants to exclude from learning. The driving operation on the travel route R1 may be excluded from learning, and the operation information indicating the driving operation and the situation information associated with the operation information may be discarded. Further, as illustrated in FIG. 19, the non-learning target designating unit 109 displays a travel route for which driving characteristic learning has been performed on the display device 700, and a range including the travel route that the user wants to exclude from the learning target is displayed on the operation device 800 By surrounding with the operation finger Z1 via the touch panel, the driving operation on the route included in the range enclosed by the user is excluded from learning, and the operation information indicating the driving operation and the situation information associated with the operation information May be discarded. As described above, by excluding driving operations in the position range designated by the user, for example, only traveling on an expressway is considered as learning object, and traveling of a traffic jam area or a school zone is excluded from learning object. be able to.

  FIG. 20 is a screen that is displayed on the display device 700 and is a diagram for explaining an example of a designation operation by the user that is accepted by the learning-target non-designating unit 109. The non-learning target designating unit 109 may exclude the driving operation in the section designated by the user from being studied. As illustrated in FIG. 20, the non-learning target designating unit 109 lists and displays the travel sections in which the driving characteristics are learned on the display device 700. Then, when the user selects a traveling section to be excluded from learning through the operation device 800, the driving operation in the section selected by the user is excluded from learning, and operation information indicating the driving operation and the operation information The associated status information may be discarded.

  FIG. 21 is a screen that is displayed on the display device 700 and is a diagram for describing an example of a designation operation by a user that is accepted by the learning-target non-designating unit 109. The learning object exclusion designation unit 109 may exclude driving operation in a time zone designated by the user as the learning object. As shown in the figure, the non-target-to-be-designated designation unit 109 causes the display device 700 to divide and display the time zone in which the driving characteristic learning has been performed by a predetermined length. Then, when the user selects a time zone to be excluded from learning through the operation device 800, the driving operation in the time zone selected by the user is excluded from learning, and operation information indicating the driving operation and the operation information And the status information associated with the may be discarded.

  As described above, according to the driving support apparatus 100 according to the second embodiment, the driving operation that meets the condition designated by the user is excluded from the learning target, and the driving characteristic learning desired by the user is further completed. Can be realized. The acceptance of the user's designation operation by the non-target-of-learning designation unit 109 may be performed before learning of the driving characteristic. That is, the non-learning target specifying unit 109 may accept in advance a manual operation for specifying a condition (position range, section, time zone) to be excluded from the learning target by the user.

  Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. The above embodiments can be combined as long as there is no contradiction. For example, the driving support devices 100 and 100A may include detection means such as an environment information detection means 400, a vehicle information detection means 500, and an operation information detection means 600 as a configuration.

DESCRIPTION OF SYMBOLS 1,1A ... Driving assistance system 100,100A ... Driving assistance apparatus 101 ... Driving method switching part 102 ... Information acquisition part 103 ... Driving condition determination part 104 ... Learning object determination part 105 Driving operation learning unit 106 Automatic driving execution unit 107 HMI control unit 108 Storage unit 109 Non-learning designation unit 200 Navigation device 300 GPS device 400 ... Environmental information detection means 500 ... Vehicle information detection means 600 ... Operation information detection means 700 ... Display device 800 ... Operation device 900 ... Control mechanism

Claims (12)

A driving support device that reflects the user's driving characteristics in the automatic driving of the vehicle by learning the driving operation of the user during manual driving of the vehicle,
An information acquisition unit that acquires information indicating the driving operation and information indicating a driving situation at the time of the driving operation;
A driving condition determination unit that determines whether the driving condition is inappropriate for learning the driving operation based on the information acquired by the information acquisition unit;
A learning target determination unit that determines that the driving operation in the driving situation determined to be inappropriate by the driving state determination unit is not subject to learning;
Driving assistance device. The driving situation determination unit determines that the driving situation is inappropriate for learning the driving operation when there is deceleration at a deceleration equal to or higher than a predetermined first reference deceleration.
The driving support device according to claim 1. The driving situation determination unit determines that the driving situation is inappropriate for learning the driving operation when there is acceleration at an acceleration equal to or higher than a predetermined first reference acceleration.
The driving support device according to claim 1. The driving condition determination unit determines that the driving condition is inappropriate for learning of the driving operation, when the yaw rate is equal to or higher than a predetermined first reference yaw rate.
The driving assistance device according to any one of claims 1 to 3. The driving condition determination unit determines that the driving condition is inappropriate for learning the driving operation when there is a cause of a sudden stop and there is deceleration at a deceleration equal to or higher than a predetermined second reference deceleration. To
The driving assistance device according to any one of claims 1 to 4. The driving situation determination unit determines that the driving situation is inappropriate for learning the driving operation when there is a sudden start factor and there is acceleration at an acceleration equal to or higher than a predetermined second reference acceleration.
The driving assistance device according to any one of claims 1 to 5. The driving situation determination unit determines that the driving situation is inappropriate for learning of the driving operation when a steep steering factor exists and the yaw rate is equal to or higher than a predetermined second reference yaw rate.
The driving assistance device according to any one of claims 1 to 6. The driving situation determination unit determines that the driving situation is inappropriate for learning the driving operation when the vehicle speed exceeds a legal speed on the road.
The driving assistance device according to any one of claims 1 to 7. The driving situation determination unit determines that the driving situation is inappropriate for learning of the driving operation when the vehicle speed is equal to or lower than a predetermined reference speed that is a speed lower than a legal speed on the road.
The driving assistance device according to any one of claims 1 to 8. The driving situation determination unit determines that the driving situation is inappropriate for learning the driving operation when the behavior of the vehicle is unstable.
The driving assistance device according to any one of claims 1 to 9. The driving condition determination unit determines that the driving condition is inappropriate for learning of the driving operation, when the number of past travels of the traveling road currently traveling is equal to or less than a predetermined reference number of traveling times.
The driving assistance device according to any one of claims 1 to 10. In order to reflect the user's driving characteristics in the automatic driving of the vehicle, a method for learning the user's driving characteristics during manual driving of the vehicle, information indicating driving operation and information indicating driving status during the driving operation, Information acquisition step to acquire
A driving situation determination step for determining whether or not the driving situation is inappropriate for learning of the driving operation based on the information acquired by the information acquisition step;
A learning object determination step for determining that the driving operation in the driving condition determined to be inappropriate in the driving condition determination step is not subject to learning,
How to learn driving characteristics.

Images