Device for controlling vehicle attention alert

Abstract

To make it possible to more accurately estimate an intention of a driver to reduce speed and issue a less awkward attention alert.SOLUTION: A vehicle attention alert controlling device comprises: a preparation specifying unit 110 for specifying whether a driver of a vehicle is in a preparation state capable of performing a speed reduction operation for a target that should be noted while the vehicle is traveling, by using a trend of change in an amount of operation of the accelerator pedal of the vehicle before the operation of the accelerator pedal of the vehicle is turned off, which is employed in the vehicle; and a presentation control unit 111 that does not issue an attention alert about the target when the driver of the vehicle identifies the vehicle as being in the preparation state using the preparation specifying unit 110, and, on the other hand, that issues an attention alert for the target when the driver of the vehicle specifies that the vehicle as not being in the preparation state using the preparation specifying unit 110.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to an attention warning control device for a vehicle. [Background technology]

[0002] Patent Document 1 discloses a technique for estimating the driver's intention to decelerate based on the speed at which the accelerator pedal is released. The technique disclosed in Patent Document 1 estimates that the driver's intention to decelerate is stronger the faster the accelerator pedal is released. On the other hand, the driver's intention to decelerate is weaker the slower the accelerator pedal is released. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-116000 Summary of the Invention [Problem to be solved by the invention]

[0004] In order to reduce annoyance when approaching an object that requires the driver's attention, it is conceivable to switch between the presence and absence of a warning depending on the driver's intention to decelerate. However, with the technology disclosed in Patent Document 1, it is difficult to accurately estimate the driver's intention to decelerate. The details are as follows. For example, the driver may increase the accelerator pedal return speed not only when decelerating but also when accelerating. Therefore, it is difficult to accurately estimate the driver's intention to decelerate based only on the magnitude of the accelerator pedal return speed.

[0005] One object of the present disclosure is to provide a vehicle attention warning control device that can estimate the driver's intention to decelerate with higher accuracy and issue an attention warning that causes less discomfort. [Means for solving the problem]

[0006] The above object is achieved by the combination of features recited in the independent claims, and the subclaims define further advantageous embodiments of the disclosure. The reference characters in parentheses in the claims indicate a correspondence with specific means described in the following embodiment as one aspect, and do not limit the technical scope of the present disclosure.

[0007] In order to achieve the above object, the vehicle attention warning control device disclosed herein is used in a vehicle and includes a readiness determination unit (110, 110a) that uses the tendency of change in the amount of accelerator pedal operation before the accelerator pedal operation of the vehicle is released to determine whether the driver of the vehicle is in a ready state to decelerate the vehicle for an object that requires attention while the vehicle is traveling, and a presentation control unit (111) that does not issue an attention warning for the object when the readiness determination unit determines that the object is in a ready state, but issues an attention warning for the object when the readiness determination unit determines that the object is not in a ready state.

[0008] When the driver intends to decelerate, the accelerator pedal may not be released in a monotonous manner. In contrast, in the above configuration, the tendency of the change in the accelerator pedal operation amount before the accelerator pedal operation is released is used to determine whether the driver is in a preparation state for deceleration. Therefore, compared to the case where the magnitude of the accelerator pedal operation amount is used, it is possible to more accurately estimate whether the driver is in this preparation state. In other words, it is possible to more accurately estimate whether the driver intends to decelerate. Furthermore, when the driver is in the preparation state, no attention is given to the target. Therefore, it is possible to suppress the driver's discomfort caused by the attention being given despite the driver's intention to decelerate. As a result, it is possible to more accurately estimate the driver's intention to decelerate and to give an attention call that causes less discomfort. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of a schematic configuration of a vehicle system. [Diagram 2]5 is a diagram showing an example of a change in accelerator pedal depression amount when deceleration is performed. FIG. [Diagram 3] 5 is a diagram showing an example of a change in accelerator pedal depression amount when deceleration is performed. FIG. [Figure 4] FIG. 2 is a diagram illustrating an example of a schematic configuration of an HCU according to the first embodiment. [Diagram 5] 13 is a flowchart showing an example of the flow of attention drawing control-related processing in an HCU. [Figure 6] FIG. 11 is a diagram illustrating an example of a schematic configuration of an HCU according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] A number of embodiments for disclosure will be described with reference to the drawings. For convenience of description, in a number of embodiments, parts having the same functions as parts shown in the drawings used in the previous description may be given the same reference numerals and their description may be omitted. For parts given the same reference numerals, the description in other embodiments may be referred to.

[0011] (Embodiment 1) <Overall configuration of vehicle system 1> Hereinafter, a first embodiment of the present disclosure will be described with reference to the drawings. A vehicle system 1 shown in FIG. 1 can be used in a vehicle. As shown in FIG. 1, the vehicle system 1 includes a human machine interface control unit (HCU) 10, a locator 11, a map database (hereinafter, map DB) 12, an external sensor 13, a vehicle state sensor 14, a communication module 15, a presentation device 16, and a user input device 17. For example, the HCU 10, the locator 11, the map DB 12, the external sensor 13, the vehicle state sensor 14, and the communication module 15 may be configured to be connected to an in-vehicle LAN (see the LAN in FIG. 1). A vehicle using the vehicle system 1 is not necessarily limited to an automobile, but the following description will be given taking an example of use in an automobile.

[0012] The locator 11 includes a GNSS (Global Navigation Satellite System) receiver and an inertial sensor. The GNSS receiver receives positioning signals from a plurality of positioning satellites. The inertial sensor includes, for example, a gyro sensor and an acceleration sensor. The locator 11 sequentially determines the vehicle position of the vehicle (hereinafter, the vehicle position) by combining the positioning signals received by the GNSS receiver with the measurement results of the inertial sensor. The vehicle position may be expressed, for example, in latitude and longitude coordinates. Note that the vehicle position may be determined using a travel distance calculated from a signal sequentially output from a vehicle speed sensor described later.

[0013] The map DB 12 is a non-volatile memory and stores high-precision map data. The high-precision map data is map data with higher accuracy than map data used for route guidance in the navigation function. The map DB 12 may also store map data used for route guidance. The high-precision map data includes information that can be used for driving assistance, such as three-dimensional shape information of roads, information on the number of lanes, and information indicating the travel direction permitted for each lane. In addition, the high-precision map data may include information on node points indicating the positions of both ends of road markings such as dividing lines. Note that the locator 11 may be configured not to use a GNSS receiver by using the three-dimensional shape information of the road. The three-dimensional shape information of the road may be generated based on a captured image by REM (Road Experience Management).

[0014] The external sensor 13 monitors the environment around the vehicle. As an example, the external sensor 13 detects obstacles around the vehicle. Examples of obstacles include moving objects and stationary objects. Examples of moving objects include pedestrians and other vehicles. Examples of stationary objects include objects that have fallen on the road. In addition, the external sensor 13 detects road markings such as lane markings around the vehicle. The external sensor 13 is a sensor such as a perimeter monitoring camera that captures an image of a predetermined range around the vehicle, a millimeter wave radar that transmits a search wave to a predetermined range around the vehicle, a sonar, or a LIDAR. The predetermined range may be a range that at least partially includes the front, rear, left, and right of the vehicle. The perimeter monitoring camera sequentially outputs the captured images as sensing information. A sensor that transmits a search wave, such as a sonar, a millimeter wave radar, or a LIDAR, is hereinafter referred to as a search wave sensor. The search wave sensor sequentially outputs a scan result based on a received signal obtained when receiving a reflected wave reflected by an obstacle as sensing information. For example, sensing information detected by the external sensor 13 is output to the HCU 10 via an in-vehicle LAN.

[0015] The vehicle state sensor 14 is a group of sensors for detecting various states of the vehicle. The vehicle state sensor 14 includes a vehicle speed sensor, an accelerator sensor, a brake sensor, and the like. The vehicle speed sensor detects the speed. The accelerator sensor detects the displacement amount of the accelerator pedal. This displacement amount can be rephrased as the operation amount or the depression amount. The accelerator sensor can be rephrased as an accelerator position sensor or an accelerator stroke sensor. The brake sensor detects the displacement amount of the brake pedal. This displacement amount can be rephrased as the operation amount or the depression amount. The brake sensor can be rephrased as a brake position sensor or a brake stroke sensor. The vehicle state sensor 14 outputs the detected sensing information to an in-vehicle LAN. The sensing information detected by the vehicle state sensor 14 is output to the HCU 10 via the in-vehicle LAN, for example. The sensing information detected by the vehicle state sensor 14 may be configured to be output to the in-vehicle LAN via an ECU mounted in the vehicle.

[0016] The communication module 15 transmits and receives information to and from a center outside the vehicle via wireless communication. In other words, wide-area communication is performed. The communication module 15 may upload probe data sequentially obtained by the vehicle to the center. The probe data may include information linking the sensing information detected by the external sensor 13 and the sensing information detected by the vehicle state sensor 14 to the vehicle position. The center that collects this probe data from multiple vehicles links the tendency of changes in the amount of accelerator pedal operation to the intention of deceleration based on this probe data. The information linking the tendency of changes in the amount of accelerator pedal operation to the intention of deceleration is hereinafter referred to as a case DB. The center where the case DB is provided is referred to as a case center.

[0017] The case DB may be created as follows. First, from the data group of changes in the operation amount of the accelerator sensor, time series data before the accelerator pedal operation is released is extracted. Here, before the accelerator pedal operation is released may be a predetermined time before the accelerator pedal operation is released. The predetermined time may be a short time that is estimated to have a causal relationship with the release of the accelerator pedal operation, and may be set arbitrarily. Before the accelerator pedal operation is released is referred to as before the operation is released hereinafter. Also, the time series data before the accelerator pedal operation is released is referred to as before-off time series data hereinafter. Two or more different types of time windows may be used to extract the before-off time series data. This is to make it possible to estimate the intention to decelerate more accurately from the tendency of changes in the accelerator pedal operation amount. Details will be described with reference to FIG. 2 and FIG. 3. FIG. 2 and FIG. 3 show an example of changes in the accelerator pedal operation amount when deceleration is performed. When deceleration is performed, as shown by A in FIG. 2, there is a case where the accelerator pedal operation amount continues to decrease linearly. On the other hand, when deceleration is performed, as shown in B of FIG. 3, the accelerator pedal operation amount may not change monotonically but may show a complex change such as a multi-stage reduction in the operation amount. It is difficult to include such a tendency of complex changes unless two or more types of time windows are used. Therefore, by using two or more different types of time windows, it becomes possible to estimate the intention to decelerate even for such a tendency of complex changes, and the estimation accuracy of the intention to decelerate can be improved.

[0018] The different time windows may be time windows with different lengths of time to be extracted. In the following, an example will be described in which two types of time windows are used: a short time window with a shorter extraction time than the other, and a long time window with a longer extraction time than the other. The short time window and the long time window may be such that a section extracted by the long time window includes a section extracted by the short time window. When only the short time window is used, it becomes difficult to target the above-mentioned complex changes. On the other hand, when only the long time window is used, characteristic changes in the operation amount are smoothed when calculating statistics to be described later, making it difficult to distinguish the change trends of different operation amounts. In contrast, by using a short time window and a long time window, these problems can be solved and the estimation accuracy of the deceleration intention can be improved.

[0019] The average, standard deviation, and root mean square are calculated for the pre-off time series data cut out by the short-time window and the long-time window. That is, six-dimensional data is obtained. Although only some of the average, standard deviation, and root mean square may be calculated, in this embodiment, the case where all of them are calculated is described as an example. By using more multidimensional data, it becomes easier to distinguish according to the trend of change in the operation amount. Next, the six-dimensional data is subjected to dimensional compression, for example, by PCA (Principal Component Analysis). By performing dimensional compression, it is possible to reduce the subsequent processing load. Next, the dimensionally compressed data is clustered to classify the data into a plurality of case groups according to the trend of change in the accelerator pedal operation amount.

[0020] Then, the classified groups of cases are labeled with the presence or absence of an intention to decelerate. The labeling of the presence or absence of an intention to decelerate may be performed based on the driving situation. In this case, the labeling may be performed based on the driving situation in the group of cases and the presence or absence of actual deceleration. The driving situation may be recognized from the sensing information detected by the external sensor 13. The presence or absence of actual deceleration may be identified from the displacement amount of the brake pedal among the sensing information detected by the vehicle state sensor 14. Note that a third party may observe the data of the driving situation and label the presence or absence of an intention to decelerate. Alternatively, the labeling may be performed based on the subjective opinion of the driver. In this case, the probe data may be configured to include a selection result of the presence or absence of an intention to decelerate received from the driver by the user input device 17.

[0021] The presentation device 16 is provided in the vehicle and presents information to the interior of the vehicle. That is, the presentation device 16 presents information to the driver of the vehicle. The information presentation also includes a warning about an object that should be taken into consideration when driving the vehicle. The presentation device 16 presents information according to an instruction from the HCU 10. The presentation device 16 includes, for example, a display device and a speaker.

[0022] The display device presents information by displaying information. For example, a meter MID (Multi Information Display), a CID (Center Information Display), a HUD (Head-Up Display), etc. can be used as the display device. The meter MID is a display device provided in front of the driver's seat inside the vehicle. As an example, the meter MID may be configured to be provided in a meter panel. The CID is a display device arranged in the center of the instrument panel of the vehicle. The HUD is provided in, for example, the instrument panel inside the vehicle. The HUD projects a display image formed by a projector onto a projection area that is predefined on the front windshield as a projection member. The HUD may be configured to project a display image onto a combiner provided in front of the driver's seat instead of the front windshield. Examples of attention-calling by display include icons and texts that call attention. The speaker presents information by outputting sound. The sound output from the speaker may include voice. Examples of attention-calling by sound include a buzzer sound that calls attention, voice output, etc.

[0023] The user input device 17 accepts input from the driver of the vehicle. The user input device 17 may be an operation device that accepts operation input from the driver. The operation device may be a mechanical switch or a touch switch integrated with a display device. Note that the user input device 17 is not limited to an operation device that accepts operation input, so long as it is a device that accepts input from the driver. For example, the user input device 17 may be a voice input device that accepts voice command input from the driver.

[0024] The HCU10 is mainly composed of a computer including, for example, a processor, a volatile memory, a non-volatile memory, I / O, and a bus connecting these components. By executing a control program stored in the non-volatile memory, the HCU10 performs various processes related to the communication between the driver and the vehicle system. The HCU10 acquires the input information received from the driver by the user input device 17. The HCU10 causes the presentation device 16 to present information. This HCU10 corresponds to the vehicle attention awakening control device. The configuration of the HCU10 will be described in detail below.

[0025] <Schematic Configuration of HCU10> Subsequently, the schematic configuration of the HCU10 will be described with reference to FIG. 4. As shown in FIG. 4, the HCU10 includes, as functional blocks, an external information acquisition unit 101, an object recognition unit 102, a vehicle information acquisition unit 103, an information storage unit 104, a margin time specification unit 105, an accelerator-off determination unit 106, a time-series data specification unit 107, a classification unit 108, an accelerator operation amount determination unit 109, a readiness determination unit 110, and a presentation control unit 111. Note that part or all of the functions executed by the HCU10 may be configured by one or a plurality of ICs or the like in hardware. Also, part or all of the functional blocks included in the HCU10 may be realized by a combination of software execution by a processor and hardware components.

[0026] The external information acquisition unit 101 acquires the sensing information sequentially output from the external sensor 13. The sensing information output from the external sensor 13 is hereinafter referred to as external sensing information. The object recognition unit 102 recognizes an object that should be noted in the driving of the host vehicle from the external sensing information acquired by the external information acquisition unit 101. This object is hereinafter referred to as a target of attention. The target of attention is preferably an area where attention should be paid to the jumping out of an object. The area where attention should be paid to the jumping out of an object is hereinafter referred to as an attention area. The object recognition unit 102 may also recognize the positional relationship such as the distance between the host vehicle and the target of attention. Note that the object recognition unit 102 may be configured to recognize moving objects such as pedestrians and other vehicles as targets of attention.

[0027] The target recognition unit 102 preferably sets an area blocked by a parked vehicle on the road as the attention area. The area blocked by a parked vehicle on the road is hereinafter referred to as a road parking blocked area. For example, the target recognition unit 102 may recognize an area that cannot be recognized by a parked vehicle within a predetermined range ahead of the vehicle position as the road parking blocked area. The target recognition unit 102 may acquire the vehicle position from the locator 11. The target recognition unit 102 may identify the area that cannot be recognized by a parked vehicle by comparing the surrounding environment that can be recognized from the external sensing information with the high-precision map. The target recognition unit 102 may acquire the high-precision map from the map DB 12. The target recognition unit 102 may recognize the surrounding environment including the parked vehicle from the external sensing information.

[0028] The target recognition unit 102 preferably sets an obstructed area at the intersection for the vehicle, which is caused by an obstruction, as the attention area. The obstructed area at the intersection for the vehicle, which is caused by an obstruction, will be referred to as an intersection obstructed area hereinafter. For example, the target recognition unit 102 may recognize an area in the nearest intersection in the travel direction of the vehicle, which cannot be recognized due to an obstruction, as the intersection obstructed area. Examples of the obstruction in this case include a wall, a signboard, and a roadside tree. The target recognition unit 102 may identify the travel direction of the vehicle from a group of vehicle positions obtained sequentially. The target recognition unit 102 may identify the inside of the intersection from a high-precision map. The target recognition unit 102 may identify the area that cannot be recognized due to an obstruction by comparing the surrounding environment that can be recognized from external sensing information with the high-precision map.

[0029] It is preferable that the target recognition unit 102 sets a crosswalk where it is estimated that a pedestrian may cross as the attention area. A crosswalk where it is estimated that a pedestrian may cross is hereinafter referred to as a caution crosswalk. For example, the target recognition unit 102 may recognize a crosswalk where a pedestrian can be recognized within a predetermined range as a caution crosswalk. The target recognition unit 102 may recognize pedestrians and crosswalks from external sensing information. The target recognition unit 102 may add a condition for recognizing a crosswalk as a caution crosswalk that a pedestrian is facing the crosswalk. The target recognition unit 102 may add a condition for recognizing a crosswalk as a caution crosswalk that the light color of the pedestrian crossing signal is green.

[0030] The vehicle information acquisition unit 103 acquires sensing information sequentially output from the vehicle state sensor 14. The sensing information output from the vehicle state sensor 14 is hereinafter referred to as vehicle sensing information. The vehicle sensing information also includes the operation amount of the accelerator pedal. Therefore, the vehicle information acquisition unit 103 corresponds to an operation amount acquisition unit.

[0031] The vehicle information acquisition unit 103 stores the vehicle sensing information acquired sequentially in the information storage unit 104. For example, a volatile memory of the HCU 10 may be used as the information storage unit 104. The vehicle speed, the accelerator pedal operation amount, and the brake pedal operation amount are sequentially stored in the information storage unit 104 as the vehicle sensing information. The information storage unit 104 may store sensing information within a certain period of time by sequentially deleting sensing information that has been stored for a certain period of time.

[0032] The margin time specification unit 105 specifies the margin time until approaching the attention object. The margin time specification unit 105 may specify a value obtained by dividing the distance to the attention object by the speed of the vehicle as the margin time. The margin time specification unit 105 may use the recognition result of the attention object by the object recognition unit 102 as the distance to the attention object. The margin time specification unit 105 may use the most recent vehicle speed stored in the information storage unit 104 as the vehicle speed. The margin time specification unit 105 may use the most recent vehicle speed acquired by the vehicle information acquisition unit 103 as the vehicle speed. In addition, when the attention object is an attention area, the distance between the attention area and the vehicle may be the distance to the point in the attention area that is closest to the vehicle. In the case where a plurality of attention objects are recognized, the margin time specification unit 105 may specify the margin time of the attention object that is closest in distance among the attention objects in a predetermined range ahead of the vehicle's path. Hereinafter, this closest attention object is simply called the attention object. The predetermined range here may be arbitrarily settable.

[0033] The accelerator off determination unit 106 determines whether or not the operation of the accelerator pedal of the host vehicle has been released. The accelerator off determination unit 106 determines whether or not the operation of the accelerator pedal of the host vehicle has been released from the operation amount of the accelerator pedal. The accelerator off determination unit 106 may use the most recent operation amount of the accelerator pedal stored in the information storage unit 104 as the operation amount of the accelerator pedal. The accelerator off determination unit 106 may use the most recent operation amount of the accelerator pedal acquired by the vehicle information acquisition unit 103 as the operation amount of the accelerator pedal. The accelerator off determination unit 106 may determine that the operation of the accelerator pedal of the host vehicle has been released when the operation amount of the accelerator pedal is 0. The accelerator off determination unit 106 may determine that the operation of the accelerator pedal of the host vehicle has been released when the state in which the operation amount of the accelerator pedal is 0 is maintained for a certain period of time or more. In this case, the accelerator off determination unit 106 may determine that the operation of the accelerator pedal of the host vehicle has not been released when the state in which the operation amount of the accelerator pedal is 0 is not maintained for a certain period of time or more.

[0034] The time series data identifying unit 107 identifies pre-off time series data from the accelerator pedal operation amount sequentially acquired by the vehicle information acquiring unit 103. As described above, the pre-off time series data is time series data that indicates a change in the accelerator pedal operation amount before the operation is released. The time series data identifying unit 107 may identify the pre-off time series data when the accelerator off determining unit 106 determines that the accelerator pedal operation has been released. The time series data identifying unit 107 extracts the pre-off time series data from a data group of changes in the accelerator sensor operation amount stored in the information storing unit 104. The extraction of the pre-off time series data is performed in the same manner as described for creating the case DB.

[0035] It is preferable that the time series data identifying unit 107 identifies the pre-off time series data for each time window using two or more types of time windows with different times for extracting the time series data. This makes it possible to improve the accuracy of estimating the intention to decelerate, as described above. It is preferable that the time series data identifying unit 107 identifies the pre-off time series data for each time window using two or more types of time windows with different time lengths for extracting the time series data. This also makes it possible to improve the accuracy of estimating the intention to decelerate, as described above. In the example of this embodiment, a case where two types of time windows, the short time window and the long time window, are used will be described as an example.

[0036] The classification unit 108 classifies the pre-off time series data identified by the time series data identification unit 107 or the change-related data that is a value based on the pre-off time series data. The classification unit 108 classifies the change-related data according to the tendency of the change in the operation amount of the accelerator pedal before the operation is turned off. The classification unit 108 may perform classification in the same manner as described for creating the case DB. In detail, the classification unit 108 may perform classification as follows. The classification unit 108 calculates statistics such as the average, standard deviation, and root mean square for the pre-off time series data cut out in the short-time window and the long-time window. The calculated six-dimensional data is subjected to dimensional compression, for example, by PCA. This data after dimensional compression corresponds to a value based on the pre-off time series data. Next, the dimensionally compressed data is classified according to the tendency of the change in the operation amount of the accelerator pedal using a clustering method.

[0037] Accelerator operation amount determination unit 109 determines whether the operation amount of the accelerator pedal is greater than 0 and less than a specified value. The specified value may be an operation amount set as the accelerator pedal play. This operation amount that is greater than 0 and less than the specified value is called a specified range. Accelerator operation amount determination unit 109 sequentially determines whether the operation amount of the accelerator pedal is within the specified range.

[0038] The preparation / non-preparation specifying unit 110 uses the tendency of the change in the accelerator pedal operation amount before the operation is turned off to specify whether or not the driver of the vehicle is in a preparation state capable of decelerating with respect to the attention target. The preparation state in which the driver is capable of decelerating is hereinafter simply referred to as a preparation state. The preparation / non-preparation specifying unit 110 may specify whether or not the driver is in a preparation state according to the tendency classified by the classification unit 108 for the change in the accelerator pedal operation amount before the operation is turned off. The preparation / non-preparation specifying unit 110 specifies whether or not the driver is in a preparation state based on the tendency classified by the classification unit 108 by referring to the case DB of the case center. In detail, the preparation / non-preparation specifying unit 110 specifies whether or not the driver is in a preparation state linked to a case group that matches the tendency classified by the classification unit 108 in the case DB. Then, when the case group that matches the tendency classified by the classification unit 108 is linked to the intention to decelerate, the preparation state is specified. On the other hand, when the case group that matches the tendency classified by the classification unit 108 is linked to the intention to decelerate, the preparation state is specified.

[0039] It is preferable that the preparation state specifying unit 110 specifies whether or not the driver is in a preparation state for the above-mentioned attention area as a target of attention. This makes it possible to more accurately estimate the driver's intention to decelerate in the area where attention should be paid to objects jumping out, and to issue a warning that causes less discomfort.

[0040] It is preferable that the preparation state determination unit 110 determines whether the driver is in a preparation state for the road parking obstructed area described above as a target of attention. This makes it possible to more accurately estimate the driver's intention to decelerate for the road parking obstructed area and to call attention to the road parking obstructed area with less discomfort.

[0041] It is preferable that the preparation state determination unit 110 determines whether the driver is in a preparation state for the intersection obstructed area described above as a target of attention. This makes it possible to more accurately estimate the driver's intention to decelerate for the intersection obstructed area and to issue a less uncomfortable warning.

[0042] It is preferable that the preparation status determination unit 110 determines whether or not the driver is in a preparation state for the aforementioned caution crosswalk as a caution target. This makes it possible to more accurately estimate the driver's intention to decelerate for the caution crosswalk and to issue a less awkward warning.

[0043] It is preferable that the preparation state specification unit 110 does not specify whether or not the vehicle is in the preparation state when the margin time specified by the margin time specification unit 105 is equal to or greater than a threshold value. The threshold value may be a margin time estimated to be a margin time that should be used to call attention to the attention target when the driver has no intention of decelerating with respect to the attention target. This threshold value corresponds to a threshold value Th1 described later. On the other hand, the preparation state specification unit 110 may specify whether or not the vehicle is in the preparation state when the margin time specified by the margin time specification unit 105 is less than the threshold value. According to the above configuration, it is possible to suppress the unnecessary processing load of specifying whether or not the vehicle is in the preparation state when the margin time is a time that does not require a warning to be issued to the attention target. In the example of this embodiment, it specifies whether or not the vehicle is in the preparation state when the margin time is less than the threshold value and the operation of the accelerator pedal is released.

[0044] It is preferable that the preparation state determination unit 110 sequentially determines whether the target of attention is in a preparation state. In other words, once the determination of whether the target of attention is in a preparation state is started, the preparation state may be sequentially determined for the target of attention until the target of attention is changed or passed. The determination of whether the target of attention is in a preparation state may be performed each time a condition for starting the determination of whether the target of attention is in a preparation state is satisfied. Then, in the process of sequentially determining whether the target of attention is in a preparation state, if the preparation state determination unit 110 determines that the target of attention is in a preparation state, the preparation state determination unit 110 determines that the target of attention is in a preparation state. This makes it possible to avoid issuing a warning, which will be described later, even if the target of attention is erroneously determined to be not in a preparation state for a certain period of time. This makes it possible to reduce the annoyance of issuing a warning despite the intention to decelerate with respect to the target of attention.

[0045] Even if the driver is determined not to be in a prepared state according to the tendency classified by the classification unit 108 with respect to the change in the accelerator pedal operation amount before the operation is turned off, the preparation / non-preparation determination unit 110 preferably performs the following. If the accelerator pedal operation amount before the operation is turned off continues to be less than the above-mentioned specified value for a predetermined time or more, the preparation / non-preparation determination unit 110 may determine whether the accelerator pedal operation amount before the operation is turned off is less than the above-mentioned specified value from the determination result of the accelerator operation amount determination unit 109. The predetermined time referred to here is a value that can be set arbitrarily. The predetermined time may be a time estimated to be a time that the accelerator pedal operation amount is kept less than the specified value when there is an intention to decelerate on a dry road. When the driver has an intention to decelerate, the accelerator pedal operation is not turned off, but there is also a characteristic of the operation that the accelerator pedal operation amount is kept less than the specified value. In contrast, according to the above configuration, even if the driver is determined not to be in a prepared state according to the tendency classified by the classification unit 108, if such a characteristic is observed, it is possible to determine the driver to be in a prepared state. Therefore, it is possible to estimate the driver's intention to decelerate with even greater accuracy.

[0046] When the preparation status specifying unit 110 specifies that the device is in a preparation state, the presentation control unit 111 does not cause a call for attention to be issued for the attention target. On the other hand, when the preparation status specifying unit 110 specifies that the device is not in a preparation state, the presentation control unit 111 causes a call for attention to be issued for the attention target.

[0047] When the driver intends to decelerate, the way of releasing the accelerator pedal may not be a monotonous decrease, but may be complex as described above. On the other hand, in the configuration of Embodiment 1, whether it is in a ready state is specified by using the tendency of the change in the operation amount of the accelerator pedal before the operation is turned off. Therefore, compared with the case of using the magnitude of the operation amount of the accelerator pedal, it becomes possible to more accurately estimate whether it is in this ready state. That is, it becomes possible to more accurately estimate whether the driver has an intention to decelerate. Further, when it is in the ready state, no warning is given to the target. Therefore, it is possible to suppress the discomfort of the driver caused by the warning being given even though there is an intention to decelerate. As a result, it becomes possible to more accurately estimate the driver's intention to decelerate and to give a warning with less discomfort.

[0048] <Attention唤起制御関連処理in HCU10> Subsequently, using the flowchart of FIG. 5, an example of the flow of the process related to the control of attention arousal in HCU10 (hereinafter, the process related to attention arousal control) will be described. The flowchart of FIG. 5 may be configured to start when a switch (hereinafter, a power switch) for starting the internal combustion engine or the motor generator of the host vehicle is turned on. In FIG. 5, the margin time is represented by TTC. The operation amount of the accelerator pedal is represented by Ac.

[0049] First, in step S1, when the target recognition unit 102 recognizes a target of attention (YES in S1), the process proceeds to step S2. On the other hand, when the target recognition unit 102 does not recognize a target of attention (NO in S1), the process proceeds to step S11. In step S2, the margin time specifying unit 105 specifies the margin time TTC until approaching the target of attention.

[0050] In step S3, if the margin time TTC determined in S2 is less than the threshold value Th1 (YES in S3), the process proceeds to step S4. On the other hand, if the margin time TTC determined in S2 is equal to or greater than the threshold value Th1 (NO in S3), the process proceeds to step S13. As the threshold value Th1, a margin time estimated to be required for a driver to be alerted when the driver has no intention of decelerating with respect to the attention object may be used.

[0051] In step S4, if the accelerator pedal operation amount Ac is less than the aforementioned specified value (YES in S4), the process proceeds to step S5. On the other hand, if the operation amount Ac is equal to or greater than the specified value (NO in S4), the process proceeds to step S11. The accelerator pedal operation amount Ac may be determined by accelerator operation amount determination unit 109.

[0052] In step S5, if accelerator off determination unit 106 determines that the accelerator pedal operation has been released (YES in S5), the process proceeds to step S7. Release of the accelerator pedal operation is called accelerator off. On the other hand, if accelerator off determination unit 106 determines that the accelerator is not released (NO in S5), the process proceeds to step S6. In step S6, preparation status determination unit 110 counts the duration during which it is determined that the operation amount Ac is less than the specified value, and the process proceeds to step S11. This counting continues in the process of repeating the flow until the operation amount Ac becomes equal to or greater than the specified value or until it is determined that the accelerator is released.

[0053] In step S7, the time-series data identification unit 107 identifies pre-off time-series data from the accelerator pedal operation amount sequentially acquired by the vehicle information acquisition unit 103. In step S8, the classification unit 108 calculates statistics from the pre-off time-series data identified in S7 and performs dimensionality compression. The classification unit 108 then classifies the dimensionality-compressed data using a clustering technique.

[0054] In step S9, if the classification performed in S8 matches a case associated with an intention to decelerate in the case DB (YES in S9), the process proceeds to step S10. A case associated with an intention to decelerate in the case DB is referred to as a deceleration case. On the other hand, if the classification performed in S8 does not match a case associated with an intention to decelerate in the case DB (NO in S9), the process proceeds to step S12.

[0055] In step S10, the preparation state determination unit 110 determines that the vehicle is in a preparation state and turns on a no-call flag. The no-call flag is turned on when no attention is to be issued. When the no-call flag is on, the presentation control unit 111 does not issue an attention call. When the margin time TTC is equal to or less than a threshold value Th1 and the no-call flag is not switched on, the presentation control unit 111 issues an attention call.

[0056] In step S11, if it is time to end the attention control-related process (YES in S11), the attention control-related process is ended. On the other hand, if it is not time to end the attention control-related process (NO in S11), the process returns to S1 and is repeated. An example of the end timing of the attention control-related process is when the power switch is turned off.

[0057] In step S12, which is performed if S9 is NO, if the duration counted in S6 is equal to or longer than the predetermined time (YES in S12), the process proceeds to S10. In other words, if the accelerator pedal operation amount before the operation is turned off has remained less than a specified value for a predetermined time or longer, the preparation state determination unit 110 determines that the vehicle is in a preparation state. On the other hand, if the duration counted in S6 is less than the predetermined time (NO in S12), the process proceeds to S11.

[0058] In step S13, which is performed when NO in S3, when the remaining time TTC identified in S2 exceeds the threshold Th2 (YES in S13), the process proceeds to step S14. On the other hand, when the remaining time TTC identified in S2 is less than or equal to the threshold Th2 (NO in S13), the process proceeds to S10. This threshold Th2 is a value larger than the threshold Th1. In step S14, the no-arousal flag is turned off. In S14, it is switched off when the no-arousal flag is on. In S14, it remains off when the no-arousal flag is off. According to this, when the remaining time TTC becomes larger than the value requiring attention arousal and the necessity of attention arousal becomes low, the no-arousal flag that was on can be turned off.

[0059] (Embodiment 2) Not limited to the configuration of the foregoing embodiment, the configuration of the following Embodiment 2 may also be adopted. Hereinafter, an example of the configuration of Embodiment 2 will be described with reference to the drawings. The vehicle system 1 of Embodiment 2 is the same as the vehicle system 1 of Embodiment 1, except that it includes an HCU10a instead of the HCU10.

[0060] <Schematic Configuration of HCU10a> Subsequently, the schematic configuration of the HCU10a will be described with reference to FIG. 6. The HCU10a is the same as the HCU10 of Embodiment 1, except that some of the processes are different. The HCU10a includes an external information acquisition unit 101, an object recognition unit 102, a vehicle information acquisition unit 103, an information storage unit 104, a remaining time identification unit 105, an accelerator-off determination unit 106, a time-series data identification unit 107, a classification unit 108, an accelerator operation amount determination unit 109, a readiness determination unit 110a, a presentation control unit 111, and a brake determination unit 112 as functional blocks. The HCU10a includes a readiness determination unit 110a instead of the readiness determination unit 110. The HCU10a includes a brake determination unit 112. The HCU10a is the same as the HCU10 of Embodiment 1 except for these points. This HCU10a also corresponds to a vehicle attention arousal control device.

[0061] The brake determination unit 112 determines the amount of operation of the brake pedal of the vehicle. The brake determination unit 112 determines whether or not the brake pedal of the vehicle has been operated on, based on the amount of operation of the brake pedal. The brake determination unit 112 may use the most recent brake pedal operation amount stored in the information storage unit 104 as the amount of operation of the brake pedal. The brake determination unit 112 may use the most recent brake pedal operation amount acquired by the vehicle information acquisition unit 103 as the amount of operation of the brake pedal. The brake determination unit 112 may determine that the brake pedal of the vehicle has been operated on, when the amount of operation of the brake pedal becomes greater than 0.

[0062] The preparation / non-preparation determining unit 110a is similar to the preparation / non-preparation determining unit 110 of the first embodiment, except for some differences in processing. The following describes these differences. The preparation / non-preparation determining unit 110a determines whether or not the vehicle is in a preparation state for the attention target by using the amount of operation of the brake pedal of the vehicle as well as the tendency of change in the amount of operation of the accelerator pedal before the operation is released.

[0063] It is preferable that the preparation / non-preparation determination unit 110a determines that the driver is in a preparation state for the attention target when the brake determination unit 112 determines that the brake pedal operation has been turned on, regardless of the tendency of change in the accelerator pedal operation amount before the operation is turned off. The classification result by the classification unit 108 corresponds to the tendency of change in the accelerator pedal operation amount before the operation is turned off. With the above configuration, it is possible to further suppress erroneous determination that the driver is not in a preparation state despite the driver's intention to decelerate. As a result, it is possible to more accurately estimate the driver's intention to decelerate.

[0064] It is preferable that the preparation presence / absence specification unit 110a specifies whether or not the target of attention is in a preparation state by using not only the tendency of change in the accelerator pedal operation amount before the operation is turned off, but also the tendency of change in the brake pedal operation amount at the start of operation. In this case, the case DB may be configured to link a combination of a group of cases of the tendency of change in the accelerator pedal operation amount before the operation is turned off and a group of cases of the tendency of change in the brake pedal operation amount at the start of operation with the intention of deceleration. The tendency of change in the brake pedal operation amount at the start of operation may be classified in the same manner as the tendency of change in the accelerator pedal operation amount before the operation is turned off. In this case, the time series data specification unit 107 and the classification unit 108 may classify the tendency of change in the brake pedal operation amount at the start of operation in the same manner as the tendency of change in the accelerator pedal operation amount. According to the above configuration, it is possible to estimate the driver's intention of deceleration with higher accuracy by using the tendency of change in the brake pedal operation amount at the start of operation.

[0065] (Embodiment 3) In the above embodiment, a configuration has been shown in which the section cut out by the long-time window includes the section cut out by the short-time window, but this is not necessarily limited to this. For example, a configuration may be used in which the sections cut out by each of the multiple time windows do not overlap. In this case, the time lengths of the multiple time windows may be the same. Even with the above configuration, it is possible to include complex changes in the amount of operation of the accelerator pedal as a target. Therefore, it is possible to estimate the intention to decelerate from such tendencies of complex changes, and the estimation accuracy of the intention to decelerate can be improved.

[0066] (Embodiment 4) In the above embodiment, the statistics of the time series data cut out by a plurality of time windows are calculated, and the data obtained by compressing the dimensions of the statistics is used for classification. However, the present invention is not limited to this. For example, the time series data cut out by a plurality of time windows may be classified. Alternatively, the statistics may not be compressed in terms of dimensions.

[0067] (Embodiment 5) In the above-described embodiment, the HCU 10, 10a is configured to include the time series data identification unit 107 and the classification unit 108, but this is not necessarily limited to the above. For example, the case center may have the functions of the time series data identification unit 107 and the classification unit 108. In this case, the HCU 10, 10a may transmit the accelerator pedal operation amount to the case center via the communication module 15 and obtain the result classified by the case center. Note that the case center may have the functions of either the time series data identification unit 107 or the classification unit 108. In these cases, the configuration including the case center and the HCU 10, 10a corresponds to a vehicle attention warning control device.

[0068] (Embodiment 6) In the above embodiment, the case DB is provided in the case center, but this is not necessarily limited to this. For example, the case DB may be provided in a non-volatile memory of the vehicle.

[0069] (Embodiment 7) In the above embodiment, the HCU 10, 10a corresponds to the vehicle attention control device, but this is not necessarily limited to this. For example, an ECU other than the HCU 10, 10a may correspond to the vehicle attention control device.

[0070] The present disclosure is not limited to the above-described embodiment, and various modifications are possible within the scope of the claims. The embodiments obtained by appropriately combining the technical means disclosed in the different embodiments are also included in the technical scope of the present disclosure. The control unit and the method described in the present disclosure may be realized by a dedicated computer constituting a processor programmed to execute one or more functions embodied by a computer program. Alternatively, the device and the method described in the present disclosure may be realized by a dedicated hardware logic circuit. Alternatively, the device and the method described in the present disclosure may be realized by one or more dedicated computers configured by a combination of a processor that executes a computer program and one or more hardware logic circuits. The computer program may be stored in a computer-readable non-transient tangible recording medium as instructions executed by the computer. [Explanation of symbols]

[0071] 1 Vehicle system, 10, 10a HCU (vehicle attention control device), 103 vehicle information acquisition unit (operation amount acquisition unit), 105 margin time determination unit, 107 time series data determination unit, 108 classification unit, 110, 110a preparation presence / absence determination unit, 111 presentation control unit

Claims

1. Used in vehicles, a preparation presence / absence determination unit (110, 110a) that determines whether or not a driver of the vehicle is in a preparation state capable of decelerating with respect to an object that requires attention while the vehicle is traveling, using a tendency of a change in an accelerator pedal operation amount before the operation of the accelerator pedal of the vehicle is released; A vehicle attention warning control device comprising: a presentation control unit (111) that, when the preparation / non-preparation determination unit determines that the vehicle is in the preparation state, does not issue a warning about the target, and, when the preparation / non-preparation determination unit determines that the vehicle is not in the preparation state, issues a warning about the target.

2. 2. The vehicle attention calling control device according to claim 1, The preparation status determination unit determines whether or not an area in which attention should be paid to an object jumping out is in the preparation state as the target.

3. 3. The vehicle attention warning control device according to claim 2, The preparation / non-preparation determination unit is a vehicle attention warning control device that determines whether or not the target is in the preparation state for an area blocked from the vehicle by a parked vehicle on the road.

4. 3. The vehicle attention warning control device according to claim 2, The preparation / non-preparation determination unit is configured to determine whether the vehicle is in a preparation state for an obstructed area at an intersection for the vehicle, the obstruction being caused by an obstruction as the target.

5. 3. The vehicle attention warning control device according to claim 2, The preparation status determination unit is configured to determine whether or not a pedestrian crossing at which a pedestrian is likely to cross is in the preparation status as the target.

6. The vehicle attention calling control device according to any one of claims 1 to 5, A margin time specification unit (105) is provided which specifies a margin time until approaching the target, The preparation / non-preparation determination unit does not determine whether the vehicle is in the preparation state or not when the margin time determined by the margin time determination unit is equal to or greater than a threshold value.

7. 7. The vehicle attention warning control device according to claim 6, The readiness determination unit sequentially determines whether the driver of the vehicle is in a ready state in which he or she can decelerate for an object that requires attention while the vehicle is traveling, and once it is determined that the object is in the ready state during the process of sequentially determining whether the object is in the ready state, the vehicle attention warning control device confirms and identifies the object as being in the ready state.

8. 2. The vehicle attention calling control device according to claim 1, an operation amount acquisition unit (103) that sequentially acquires an operation amount of an accelerator pedal of the vehicle; a time series data identification unit (107) that identifies, from the operation amounts sequentially acquired by the operation amount acquisition unit, time series data indicating a change in an accelerator pedal operation amount before the accelerator pedal operation of the vehicle is released; a classification unit (108) that classifies the time series data identified by the time series data identification unit or change-related data that is a value based on the time series data, according to a trend of change in the manipulated variable, The preparation / non-preparation determination unit determines whether the vehicle is in the preparation state based on the tendency classified by the classification unit regarding changes in the amount of accelerator pedal operation before the accelerator pedal operation of the vehicle is released.

9. 9. The vehicle attention warning control device according to claim 8, The time series data identification unit uses two or more types of time windows having different times for extracting the time series data, and identifies the time series data for each time window from the operation amount sequentially acquired by the operation amount acquisition unit.

10. 9. The vehicle attention warning control device according to claim 8, The time series data identification unit uses two or more types of time windows having different time lengths for extracting the time series data, and identifies the time series data for each time window from the operation amount sequentially acquired by the operation amount acquisition unit.

11. 9. The vehicle attention warning control device according to claim 8, The classification unit classifies the change-related data according to a trend of change in the operation amount using a clustering method.

12. The vehicle attention calling control device according to any one of claims 8 to 11, The preparation / non-preparation determination unit determines that the vehicle is in the preparation state when the amount of accelerator pedal operation before the accelerator pedal operation of the vehicle is released remains greater than 0 and less than a specified value for a predetermined period of time or more, even if the preparation state is determined to be not ready based on the tendency classified by the classification unit.

13. 2. The vehicle attention calling control device according to claim 1, The preparation / preparation determination unit determines whether the target is in the preparation state by using not only the tendency of change in the amount of accelerator pedal operation before the accelerator pedal operation of the vehicle is released, but also the amount of brake pedal operation of the vehicle.

Images