Driving assistance device

Abstract

A driving assistance device executes deceleration assistance that causes a vehicle to automatically decelerate. A driving assistance ECU determines a deceleration request object that is a cause of a deceleration operation for decelerating the vehicle when detecting the deceleration operation by a driver of the vehicle. The driving assistance ECU learns deceleration assistance start position information indicating a position corresponding to a position of the vehicle, i.e., a deceleration assistance start position, at which the deceleration operation is started, in association with the deceleration request object determined for the deceleration operation. The driving assistance ECU executes the deceleration assistance when the vehicle reaches the deceleration assistance start position indicated by the learned deceleration assistance start position information after learning the deceleration assistance start position information. The driving assistance ECU discards the deceleration assistance start position information after learning the deceleration assistance start position information in a case where it is determined that the deceleration request object learned in association with the deceleration assistance start position indicated by the deceleration assistance start position information has changed.

Description

Technical Field

[0001] This invention relates to a driving assistance device that learns the position where the driver of a vehicle performs a deceleration operation, and then provides deceleration assistance to automatically slow down the vehicle when it passes through that position after learning. Background Technology

[0002] One type of conventional driver assistance device (hereinafter referred to as "conventional device") creates map information by associating changes in the driver's driving operations with the location information at the time the changes in driving operations occurred. The conventional device uses the created map information for vehicle control (see Patent Document 1).

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2009-103570 Summary of the Invention

[0006] However, for example, when a driver performs a deceleration maneuver, it is difficult to determine whether the deceleration was an isolated incident or caused by a driving environment requiring vehicle deceleration (e.g., a stop sign or an upcoming curve). Therefore, to create map information as with conventional technologies, it is necessary to statistically determine that the deceleration was caused by the driving environment, requiring the collection of a large amount of data. Furthermore, even after the map information has been temporarily created, if the driving environment changes, it is also necessary to statistically determine that the driving environment has changed, requiring the collection of large amounts of data. As a result, during the long period between the change in driving environment and the actual update of the map information, unnecessary vehicle controls (e.g., deceleration assist) may be implemented.

[0007] This invention was made to address the aforementioned problems. Specifically, one objective of this invention is to provide a driving assistance device capable of stopping deceleration assistance as early as possible when the driving environment changes, serving as a driving assistance based on the driving environment before the change. Furthermore, "step" will sometimes be referred to as "S" below.

[0008] One technical solution of the driving assistance device of the present invention includes a controller (10) configured to perform deceleration assistance that automatically decelerates the vehicle.

[0009] The controller is configured as follows:

[0010] The reason for the deceleration requirement is determined as a driving operation performed by the driver of the vehicle to decelerate the vehicle, i.e., a deceleration operation (S420).

[0011] The deceleration assist start position information, which represents the position of the vehicle when the deceleration operation begins (i.e., the deceleration assist start position), is associated with the deceleration requirement object determined for the deceleration operation, and is learned together with the deceleration requirement object (S455).

[0012] After learning the deceleration assist start position information, the deceleration assist is executed when the vehicle reaches the deceleration assist start position indicated by the learned deceleration assist start position information (S530).

[0013] Moreover, the controller is configured as follows:

[0014] After learning the deceleration assist start position information, if it is determined that the deceleration request object that has been learned in association with the deceleration assist start position represented by the deceleration assist start position information has changed (S520: Yes), the deceleration assist start position information for the deceleration request object that has been determined to have changed is discarded (S540).

[0015] Therefore, after learning the deceleration assist start position information, if it is determined that the deceleration requirement has changed, the deceleration assist start position information for the changed deceleration requirement is immediately discarded. Thus, when the vehicle passes through a driving environment where the deceleration requirement has changed, deceleration assist corresponding to the deceleration operation based on the previous deceleration requirement is not executed. This reduces the frequency of unnecessary deceleration assist execution.

[0016] In the foregoing description, to aid in understanding the invention, parentheses have been used to indicate the components of the invention corresponding to the embodiments described below, with the names and / or reference numerals used in those embodiments. However, the constituent elements of the invention are not limited to the embodiments specified by the names and / or reference numerals. The invention also relates to a driving assistance method implemented by a driving assistance device, and a program for causing a computer mounted in a vehicle to execute the steps of the driving assistance method. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of a driving assistance device according to an embodiment of the present invention.

[0018] Figure 2 It is a top view used to illustrate the speed reduction assist at intersections and on vehicles.

[0019] Figure 3 (A) is a table showing an example of "deceleration requirement objects and driving condition index values" stored in non-volatile memory. Figure 3(B) is a table showing an example of “deceleration requirement object and learning value” stored (learned) in non-volatile memory.

[0020] Figure 4 It is shown Figure 1 The flowchart shown is of the routines executed by the CPU of the driving assistance ECU.

[0021] Figure 5 It is shown Figure 1 The flowchart shown is of the routines executed by the CPU of the driving assistance ECU.

[0022] Figure 6 It is shown Figure 1 The flowchart shown is of the routines executed by the CPU of the driving assistance ECU.

[0023] Explanation of reference numerals in the attached figures

[0024] 10: Driver assistance ECU; 21: Camera sensor; 26: Brake pedal operation sensor; 40: Brake actuator. Detailed Implementation

[0025] (constitute)

[0026] The driving assistance device (hereinafter referred to as "device DS") according to the embodiments of the present invention includes Figure 1 The components shown are as follows. The device DS is applied (installed) in a vehicle HV. The vehicle HV can be any of the following: a vehicle powered by an internal combustion engine, a vehicle powered by an electric motor (i.e., an electric vehicle), or a hybrid vehicle.

[0027] In this specification, "ECU" refers to an electronic control device equipped with a microcomputer. A microcomputer includes a CPU (processor), ROM, RAM, non-volatile memory capable of writing data, and interfaces. ECU is also referred to as a controller or computer.

[0028] The driving assistance ECU 10 performs the deceleration assist control described later as driving assistance control. The driving assistance ECU 10 is connected to the components described below, and transmits and receives information or signals with them. The driving assistance ECU 10 may also be composed of multiple ECUs.

[0029] Camera sensor 21 captures image data of the scene surrounding the vehicle HV in front of it at predetermined intervals. Based on this image data, driver assistance ECU 10 obtains information (i.e., positional relationship information) indicating the positional relationship between objects present around the vehicle HV and various lines drawn on the road surface (e.g., lane markings) and the vehicle HV. Furthermore, driver assistance ECU 10 obtains information about the driving environment of the vehicle HV based on the image data. This information includes information about the presence of objects requiring deceleration and information determining the type of such objects. This information obtained based on the image data acquired by the camera sensor is sometimes referred to as "camera information."

[0030] A deceleration requirement object indicates a driving environment in which a vehicle (HV) needs to decelerate before reaching that object. In other words, a deceleration requirement object is the object that causes the driver of the vehicle (HV) to perform a driving operation to decelerate the vehicle (HV), i.e., a deceleration operation. Examples include at least one of the following: a temporary stop sign, a temporary stop line, a curve (or curved road) ahead of the vehicle (HV), a railway crossing signal, a gate at the entrance to a toll road, a priority road intersecting with the vehicle (HV), and other markings.

[0031] Radar sensor 22 is a known sensor that uses millimeter-wave radio waves to acquire information about objects present in front of the vehicle (HV). Radar sensor 22 sends millimeter-wave information about the transmitted and received millimeter waves to driver assistance ECU 10. Driver assistance ECU 10 obtains "radar information" based on the millimeter-wave information. The radar information includes the distance to the object, the object's orientation, and the object's relative speed, etc.

[0032] In addition, the driver assistance ECU10 generates combined information by integrating camera information and radar information.

[0033] The vehicle speed sensor 23 outputs a signal representing the vehicle's speed (i.e., vehicle speed) Vh.

[0034] Accelerometer 24 outputs a signal representing the acceleration G of the vehicle HV in the forward and backward direction.

[0035] The accelerator pedal operation amount sensor 25 outputs a signal representing the accelerator pedal operation amount AP of a vehicle HV (not shown).

[0036] The brake pedal operation amount sensor 26 outputs a signal representing the brake pedal operation amount BP of a vehicle HV (not shown).

[0037] The first shift paddle 27 is mounted on a steering wheel (not shown) and, when pressed by the driver, outputs a signal Sup to upshift a gear in a transmission (not shown). Upon receiving the Sup signal, the driver assistance ECU 10 upshifts the transmission (not shown) by one gear.

[0038] The second shift paddle 28 is mounted on a steering wheel (not shown) and, when pressed by the driver, outputs a signal Sdn to downshift a transmission stage (not shown). Upon receiving the signal Sdn, the driver assistance ECU 10 downshifts the transmission stage (not shown) by one gear.

[0039] The driver assistance ECU 10 is also connected to the power transmission actuator 30, the brake actuator 40, the steering motor (i.e., the steering actuator) 50, the alarm device 60, and the navigation ECU 70.

[0040] The power transmission actuator 30 drives the vehicle HV (not shown) as a "drive unit including a power source and a transmission" to adjust the driving force of the vehicle HV.

[0041] Brake actuator 40 drives a braking device (not shown) of vehicle HV to adjust the braking force applied to vehicle HV.

[0042] Therefore, the driving assistance ECU 10 can automatically decelerate the vehicle HV by driving the power transmission actuator 30 and the brake actuator 40.

[0043] The steering motor 50 imparts torque to the steering mechanism (not shown) of the vehicle HV to change the steering angle of the steering wheel (not shown) of the vehicle HV.

[0044] The alarm device 60 includes a display device and an alarm sound generating device. Based on an instruction signal from the driver assistance ECU 10, the alarm device 60 causes the display device to display a predetermined alarm and the alarm sound generating device to produce a predetermined alarm sound.

[0045] The navigation ECU 70 is connected to the GPS receiver 71 and the map information storage device 72. The navigation ECU 70 obtains the current position of the vehicle (HV) based on the GPS signal received by the GPS receiver 71. Based on the obtained current position and the map information stored in the map information storage device 72, the navigation ECU 70 can provide the driver assistance ECU 10 with information about the vehicle's driving environment (i.e., the presence and type of objects requiring deceleration). The navigation ECU 70 can also communicate with external devices to obtain the latest map information and update the map information stored in the map information storage device 72 based on the latest map information obtained.

[0046] (Work Summary)

[0047] Device DS, for example, uses image data to detect (identify / determine) objects requiring deceleration. Figure 2 An example is shown where a temporary stop flag (ST) is detected as an object requiring deceleration.

[0048] When the driver of the vehicle (HV) initiates a deceleration operation, the device DS determines whether the driving environment ahead of the vehicle (HV) contains an object requiring deceleration. Deceleration operations include, for example, pressing the brake pedal and downshifting the transmission. If the driving environment ahead of the vehicle (HV) contains an object requiring deceleration, the device DS will determine whether such an operation is necessary. Figure 3 As shown in example (A), the driving condition index values ​​are associated with the deceleration requirement object (category) for storage. The driving condition index values ​​include the deceleration operation start position (latitude and longitude), the deceleration operation end position (latitude and longitude), the vehicle speed at the time the deceleration operation starts (i.e., the deceleration operation start speed), and the vehicle speed at the time the deceleration operation ends (i.e., the deceleration operation end speed), etc.

[0049] When the device DS obtains a group of stored data (driving condition index values) whose deceleration operation start positions are considered to be substantially the same as the data quantity threshold Cth, it generates a learning value based on the group of stored data and establishes an association between the generated learning value and the deceleration requirement object for learning (i.e., storing it in non-volatile memory).

[0050] Learning values, for example Figure 3 As shown in example (B), it includes:

[0051] Information indicating the deceleration assist start position (latitude and longitude).

[0052] Information indicating the end position of deceleration assist (latitude and longitude), and

[0053] This indicates the vehicle speed at which the deceleration assist ends.

[0054] The deceleration assist start position is the average position of the deceleration operation start position of the group storing the data.

[0055] The deceleration assist end position is the average position of the deceleration operation end position of the group storing the data.

[0056] The deceleration assist end speed is the average speed of the vehicle at the end of the deceleration operation of the group of stored data.

[0057] However, the learning value only needs to contain at least the deceleration assist start position information, and is not limited to the above example. It is sufficient as long as it contains parameters that can determine the content of the deceleration assist (e.g., target deceleration).

[0058] Subsequently, when the vehicle's HV reaches the deceleration assist start position indicated by the learned deceleration assist start position information, the device DS performs deceleration assist at a certain deceleration rate to make the vehicle speed at the deceleration assist end position consistent with the deceleration assist end speed. Therefore, the aforementioned learned value can be considered a parameter that determines the content of the deceleration assist.

[0059] Conventional devices do not establish a correlation between learned values ​​and deceleration requirements during learning. Therefore, after the vehicle's HV reaches the learned deceleration assist initiation point, if the driver accelerates, the conventional device cannot immediately determine whether the acceleration is an isolated incident or caused by a change in the driving environment. Consequently, conventional devices only discard the learned value after such acceleration has been repeated numerous times and a statistically confirmed change in the driving environment has occurred. As a result, the period before the learned value is discarded is prolonged, during which unnecessary deceleration assist may be applied.

[0060] In contrast, when the vehicle's HV reaches the learned deceleration assist start point, if the device DS determines that the deceleration request object associated with that deceleration assist start point is different from the deceleration request object identified (determined) at that time point, it immediately discards the learned values ​​associated with that deceleration assist start point (i.e., deceleration assist start position information, deceleration assist end position information, and deceleration assist end speed information, etc.). This reduces the frequency of unnecessary deceleration assist activation.

[0061] (Specific tasks)

[0062] The CPU of the driver assistance ECU10 executes at predetermined intervals. Figures 4 to 6 The example shown.

[0063] When the scheduled time arrives, the CPU starts from... Figure 4 S400 begins processing and proceeds to S405 to determine whether a driver has performed a deceleration operation. The deceleration operation is either a braking operation that increases the brake pedal operation amount BP from "0" or a downshifting operation that causes the second shift paddle 28 to generate a signal Sdn.

[0064] In the case of a deceleration operation, the CPU proceeds from S405 to S410 to determine whether the average magnitude of the actual deceleration (acceleration G) Dav during the period from the start time of the deceleration operation to the end time of the deceleration operation is greater than or equal to a threshold Dth. Alternatively, the CPU may also determine in S410 whether the magnitude of the actual deceleration immediately following the start time of the deceleration operation is greater than or equal to a predetermined threshold. Alternatively, the CPU may omit the processing in S410. In this case, if the CPU determines "yes" in S405, it proceeds to S415, described later.

[0065] If the average value Dav is less than the threshold Dth, the CPU directly enters S495 from S410, temporarily ending the current routine. Conversely, if the average value Dav is greater than or equal to the threshold Dth, the CPU enters S415 from S410 and determines whether a position P that substantially corresponds to the vehicle HV position at the start time of this deceleration operation has been saved as the learning value for the deceleration assist start position. The position P substantially corresponding to the vehicle HV position at the start time of this deceleration operation is a position within a predetermined distance (e.g., 10m) from the vehicle HV position at the start time of this deceleration operation, hereinafter referred to as the "corresponding position P". That is, in S415, the CPU determines whether the learning for deceleration assist at the corresponding position P has been completed by checking whether the value of the learning completion flag XG(P) corresponding to the corresponding location P is "1". If the value of the learning completion flag XG(P) is "1", the CPU enters S495 from S415, temporarily ending the current routine.

[0066] Conversely, if the learning completion flag XG(P) is "0" (i.e., the learning for deceleration assistance at the corresponding position P has not ended), the CPU proceeds from S415 to S420 to determine whether one of the pre-defined deceleration request objects has been identified / determined based on the image data. If a deceleration request object has been identified / determined, the CPU proceeds from S420 to S425 to determine whether the deceleration request object identified at the current time point is the same as the deceleration request object identified when the vehicle HV last passed a position that can be considered substantially the same as the corresponding position P (i.e., the previous deceleration request object).

[0067] If the deceleration requirement object identified at the current time point is the same as the deceleration requirement object from the previous time, the CPU transitions from S425 to S430, such as... Figure 3 As shown in (A), the driving condition index value is stored in non-volatile memory in association with the deceleration requirement object. Then, in S435, the CPU increments the value of the stored data quantity C(P) at the corresponding location P by "1" and enters S450.

[0068] Conversely, if the CPU determines "No" in either step S420 or S425, it proceeds to S440 from that "No" step, discarding all driving condition indicator values ​​stored in association with the corresponding location P. Next, the CPU proceeds to S445, setting the value of the stored data quantity C(P) to "0". Afterward, the CPU proceeds to S450.

[0069] In step S450, the CPU determines whether the value of the stored data quantity C(P) is greater than or equal to the data quantity threshold Cth. That is, it determines whether there is a sufficient amount of data stored for learning the deceleration assistance for the corresponding position P. If the value of the stored data quantity C(P) is less than the data quantity threshold Cth, the CPU directly proceeds from S450 to S495, temporarily terminating this routine.

[0070] In contrast, when the value of the stored data quantity C(P) exceeds the data quantity threshold Cth, the CPU transitions from S450 to S455, generates a learning value (i.e., a parameter that determines the content of deceleration assistance) based on the driving condition index value for the corresponding location P, and stores this generated learning value in non-volatile memory in association with the category of the deceleration request object (see reference). Figure 3 (B) Next, in S460, the CPU sets the learning completion flag XG(P) to "1", and in S465, sets the stored data quantity C(P) to "0". Then, the CPU proceeds to S495. As described above, the deceleration assistance content is learned in association with the deceleration requirement object.

[0071] When the scheduled time arrives, the CPU starts from... Figure 5 The CPU starts processing in S500 and proceeds to S510, where it determines whether the current position of the vehicle HV matches any position P among the learned deceleration assist start positions. If the current position of the vehicle HV does not match any of the learned deceleration assist start positions, the CPU directly proceeds from S510 to S595, temporarily terminating the current routine. That is, in this case, deceleration assist is not executed.

[0072] Conversely, if the current position of the vehicle's HV coincides with any position P in the "learned deceleration assist start position", the CPU transitions from S510 to S520 and determines whether the driving environment (i.e., the object requiring deceleration) corresponding to position P has changed by checking whether the value of the environment change flag XCh(P) corresponding to position P is "1". The environment change flag XCh(P) is set to "1" when it is determined, as described later, that the driving environment (i.e., the object requiring deceleration) corresponding to position P has changed (see reference). Figure 6 (S615).

[0073] When the environmental change flag XCh(P) has a value of "0" (i.e., the deceleration requirement has not changed), the CPU moves from S520 to S530 and executes deceleration assistance based on the learned value for the deceleration assistance start position P (i.e., information such as the deceleration assistance start position, deceleration assistance end position, and deceleration assistance end speed, etc., indicating the content of the learned deceleration assistance). Afterward, the CPU moves to S595.

[0074] Conversely, when the environmental change flag XCh(P) is set to "1" (i.e., the deceleration requirement has changed), the CPU transitions from S520 to S540, discarding the learned values ​​for the deceleration assist start point P (i.e., deceleration assist start position information, deceleration assist end position information, and deceleration assist end speed information, etc.). Then, the CPU enters S550, sets the learning completion flag XG(P) to "0", and enters S560, setting the environmental change flag XCh(P) to "0". Finally, the CPU proceeds to S595.

[0075] When the scheduled time arrives, the CPU starts from... Figure 6 The CPU starts processing at S600 and proceeds to S605, where it determines whether the current position of the vehicle HV is consistent with any position P among the deceleration assist start positions represented by the learned deceleration assist start position information. If the current position of the vehicle HV is inconsistent with any of the learned deceleration assist start positions, the CPU directly proceeds from S605 to S695, temporarily terminating this routine.

[0076] Conversely, if the current position of the vehicle's HV coincides with any of the learned deceleration assist start positions P, the CPU proceeds from S605 to S610 to determine whether the driver has performed a specific operation to teach that the driving environment (i.e., the object of deceleration requirement) has changed. The specific operation could be, for example, continuously pressing either or both of the first shift paddle 27 and the second shift paddle 28 for a predetermined time (e.g., 2 seconds) or more. Alternatively, the specific operation could be, for example, re-pressing either or both of the first shift paddle 27 and the second shift paddle 28 a predetermined number of times (e.g., 4 times) within a predetermined time (e.g., 3 seconds).

[0077] Furthermore, the specific operation performed by the driver to inform the driver of a change in the driving environment (the object requiring deceleration) is not limited to operations on the first shift paddle 27 and the second shift paddle 28. For example, when the device DS is connected to a specific switch, the device DS can also treat operations on that specific switch as the aforementioned specific operation.

[0078] Upon detecting such a specific operation, the CPU moves from S610 to S615 and sets the value of the environmental change flag XCh(P) for position P to "1". Then, the CPU moves to S620, sets the value of the total score TSC(P) to "0", and moves to S695.

[0079] If no specific operation is detected in S610, the CPU proceeds from S610 to S625 to determine whether a preceding vehicle has been identified based on image data. If a preceding vehicle is identified, the CPU proceeds from S625 to S630 and sets the addition score SC to "0". Then, the CPU proceeds to S635 and increments the total score TSC(P) by the addition score SC. That is, the CPU accumulates the addition score SC to update the total score TSC(P). Furthermore, if a preceding vehicle is identified, the total score TSC(P) does not increase because the addition score SC is "0". This is because, when a preceding vehicle is identified, it is difficult to determine whether the driving environment has changed based on image data.

[0080] Next, the CPU enters S640 and determines whether the total score TSC(P) is above the total score threshold TSCth. If the total score TSC(P) is not above the total score threshold TSCth, the CPU directly enters S695 from S640.

[0081] Conversely, if the total score TSC(P) is above the total score threshold TSCth, the CPU determines that the driving environment at position P (i.e., the object requiring deceleration) has changed. Therefore, the CPU executes the aforementioned "processing in S615 and S620". Afterwards, the CPU proceeds to S695.

[0082] When the CPU enters S625, if no preceding vehicle is detected, the CPU transitions from S625 to S645, determining whether the deceleration request object associated with the deceleration assist start position P corresponding to the current position is different from the deceleration request object identified / determined based on image data at the current time. Even if no deceleration request object is detected at the current time, the CPU still determines that the deceleration request object associated with the deceleration assist start position P corresponding to the current position is different from the deceleration request object identified / determined based on image data at the current time. That is, in this case, the CPU also determines that the driving environment (i.e., the deceleration request object) at the deceleration assist start position P has changed.

[0083] If the deceleration requirement object associated with the deceleration assist start position P corresponding to the current position is no different (i.e., the same) from the deceleration requirement object identified / determined based on image data at the current time point, the CPU directly enters S695 from S645.

[0084] In contrast, if the deceleration request object associated with the deceleration assist start position P corresponding to the current position is different from the deceleration request object identified based on image data at the current time point, the CPU proceeds from S645 to S650, determining the addition score SC based on the category of the deceleration request object associated with the deceleration assist start position P. For example, since temporary stop signs or railway crossing signals are deceleration request objects that can be identified with relatively high accuracy based on image data, their addition score SC is set to a relatively high value A1. Conversely, since curves are deceleration request objects that are mostly difficult to determine with high accuracy based on image data, their addition score SC is set to a relatively low value A2 (i.e., a value A2 smaller than A1). In this way, the addition score SC of deceleration request objects with high accuracy identified based on image data is set to a larger value than the addition score SC of deceleration request objects with low accuracy identified based on image data. Afterwards, the CPU proceeds to processing from S635 onwards.

[0085] Therefore, when the total score TSC(P), which increases as the probability of "the deceleration request object identified at position P being different from the deceleration request object learned for position P" increases, exceeds the total score threshold TSCth, it is determined that the driving environment (i.e., the deceleration request object) at position P has changed, and the value of the environment change flag XCh(P) is set to "1".

[0086] As explained above, when a driver performs a deceleration operation, the DS device identifies the deceleration request and learns the corresponding deceleration assistance information (deceleration assistance start position information, deceleration assistance end position information, and deceleration assistance end speed information, etc.) along with the deceleration request. If the DS device determines that the deceleration request at the deceleration assistance start position, which has already been learned, has changed, it discards the learned value for that deceleration assistance start position. Therefore, deceleration assistance based on the deceleration request before the change is no longer immediately applied.

[0087] This invention is not limited to the embodiments described above, and various modifications as described below can be adopted within the scope of this invention. For example, this invention can be applied to vehicles in which the driving mode has been switched from automatic driving to driver-driven driving in an autonomous vehicle.

[0088] The device DS can also determine the deceleration requirement object based on the map information stored in the map information storage device 72. Furthermore, when the map information stored in the map information storage device 72 is updated, the device DS can detect changes in the deceleration requirement object based on the updated map information and immediately discard the learning value corresponding to the position of the changed deceleration requirement object.

Claims

1. A driving assistance device comprising a controller configured to perform deceleration assistance that automatically decelerates a vehicle. The controller is configured as follows: The object of the deceleration requirement is determined as the reason for the deceleration operation, which is a driving operation performed by the driver of the vehicle to slow down the vehicle. The deceleration assist start position information, which represents the position of the vehicle when the deceleration operation begins (i.e., the deceleration assist start position), is associated with the deceleration requirement object determined for that deceleration operation, and is then learned together with the deceleration requirement object. After learning the deceleration assist start position information, the deceleration assist is executed when the vehicle reaches the deceleration assist start position indicated by the learned deceleration assist start position information. Moreover, the controller is configured as follows: After learning the deceleration assist start position information, if it is determined that the deceleration request object, which has been learned in association with the deceleration assist start position represented by the deceleration assist start position information, has changed, the deceleration assist start position information for the deceleration request object that has been determined to have changed is discarded.

2. The driving assistance device according to claim 1, The objects requiring deceleration include at least one of the following: a temporary stop sign located in front of the vehicle, a temporary stop line, a curve, a railway crossing signal, a gate at the entrance of a toll road, and a priority road intersecting with the vehicle's travel path.

3. The driving assistance device according to claim 2, The controller is configured as follows: The content of the deceleration assistance is determined based on the driving condition index value representing the vehicle's driving status at the time of the deceleration operation, and the content of the deceleration assistance is learned by associating it with the deceleration assistance start position information. The deceleration assistance is executed according to the deceleration assistance content that has been learned.

4. The driving assistance device according to claim 3, The controller is configured as follows: The deceleration requirement is determined based on image data obtained from a camera mounted on the vehicle. If the deceleration request object determined based on the image data when the vehicle reaches the deceleration assist start position represented by the learned deceleration assist start position information differs from the deceleration request object that has been learned and associated with the deceleration assist start position reached by the vehicle, the addition operation score is determined based on the category of the learned deceleration request object. The total score is calculated by accumulating the scores from the addition operation determined when the vehicle reaches the deceleration assist start position. When the total score exceeds a predetermined score threshold, it is determined that the deceleration requirement object, which has been learned in association with the deceleration assist start position reached by the vehicle, has changed.

5. The driving assistance device according to claim 4, The controller is configured as follows: When the vehicle reaches the deceleration assist start position indicated by the learned deceleration assist start position information, if the image data includes a vehicle in front of the vehicle, the addition score is set to zero.

6. A driving assistance method for performing deceleration assistance to automatically decelerate a vehicle, comprising: The steps for determining the object of a deceleration requirement that is the cause of a deceleration operation, wherein the deceleration operation is a driving operation performed by the driver of the vehicle to slow down the vehicle. The step of establishing an association between the deceleration assist start position information, which represents the position of the vehicle when the deceleration operation begins (i.e., the deceleration assist start position), and the deceleration requirement object determined for the deceleration operation, and learning together with the deceleration requirement object; After learning the deceleration assist start position information, the deceleration assist step is executed when the vehicle reaches the deceleration assist start position indicated by the learned deceleration assist start position information; as well as After learning the deceleration assist start position information, if it is determined that the deceleration request object, which has been learned in association with the deceleration assist start position represented by the deceleration assist start position information, has changed, the step of discarding the deceleration assist start position information for the deceleration request object that has been determined to have changed is discarded.

7. The driving assistance method according to claim 6, The objects requiring deceleration include at least one of the following: a temporary stop sign located in front of the vehicle, a temporary stop line, a curve, a railway crossing signal, a gate at the entrance of a toll road, and a priority road intersecting with the vehicle's travel path.

8. The driving assistance method according to claim 7, further comprising: The steps of determining the content of the deceleration assistance based on the driving condition index value representing the driving condition of the vehicle when the deceleration operation occurs, and establishing a correlation between the content of the deceleration assistance and the deceleration assistance start position information to perform learning. and Perform the deceleration assistance steps according to the deceleration assistance content that has been learned.

9. The driving assistance method according to claim 8, The step of determining the object requiring deceleration is based on image data obtained from a camera mounted on the vehicle. The driving assistance method also includes: When the vehicle reaches the deceleration assist start position represented by the learned deceleration assist start position information, if the deceleration request object determined based on the image data is different from the deceleration request object that has been learned and associated with the deceleration assist start position reached by the vehicle, the step of determining the addition operation score based on the category of the learned deceleration request object. The step of calculating the total score by accumulating the addition score determined when the vehicle reaches the deceleration assist start position; as well as When the total score exceeds a predetermined score threshold, a step is taken to determine that the deceleration requirement object, which has been learned in association with the deceleration assist start position reached by the vehicle, has changed.

10. The driving assistance method according to claim 9, The steps to calculate the total score include the following steps: when the vehicle reaches the deceleration assist start position indicated by the learned deceleration assist start position information, if the image data includes a vehicle in front of the vehicle, the addition score is set to zero.

Images