JP2023086899A - Driving state estimation device - Google Patents

Abstract

To provide a driving state estimation device capable of accurately estimating a driving state of a driver.SOLUTION: A driving information acquisition section 2 acquires driving information at a present position of a vehicle. A driving state estimation section 4 determines whether a present position corresponds to a unique point. A radio communication section 3 acquires a first driving action pattern 11a when a present position is determined to correspond to a unique point, and acquires a second driving action pattern 11b when a present position is not determined to correspond to a unique point. Then, the driving state estimation section 4 estimates a driving state of a driver by comparing the first driving action pattern 11a or the second driving action pattern 11b with driving information at a present position.SELECTED DRAWING: Figure 1

Description

The present invention relates to a driving state estimation device for estimating the driving state of a driver of a mobile object.

2. Description of the Related Art In order to reduce accidents involving moving bodies such as vehicles, techniques have been proposed for estimating the driving state of a driver, such as drowsy driving or careless driving, and informing the driver of predetermined information.

For example, in Patent Document 1, a driving characteristic acquisition unit acquires driving characteristic information based on a driver's past driving history, a driving situation acquisition unit acquires driving situation information about the current driving situation, and obtains state level It is described that the estimation unit estimates the state of the driver based on the driving characteristic information and the driving situation information.

JP 2012-118951 A

In the case of the method of Patent Literature 1, the state of the driver is estimated by comparing the past driving behavior and the current driving behavior. In this case, if the vehicle is traveling in a place where the vehicle is not usually traveled, such as a mountain pass, the judgment cannot be made because it is out of the range of the past driving behavior. In addition, when comparing the past driving behaviors by averaging, it was found that driving in places where there is less driving than usual, such as the above-mentioned mountain pass, is different from usual driving, such as turning the steering wheel frequently and stepping on the brake more often. Due to the operation, there are cases where the average deviates greatly, and there is a possibility that the driver's condition may be misidentified even though the driver is driving normally.

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a driving state estimating device capable of estimating the driving state of a driver with high accuracy.

In order to solve the above-mentioned problems, the invention according to claim 1 provides first acquisition means for acquiring driving information at a current position of a mobile body, determination means for determining whether the current position corresponds to a singular point, A second obtaining means for obtaining first driving information when it is determined that the current position corresponds to the peculiar point, and for obtaining second driving information when it is determined that the current position does not correspond to the peculiar point and estimation means for estimating the driving state of the driver by comparing the first driving information or the second driving information with the driving information at the current position.

A ninth aspect of the present invention is a driving state estimation method for a driving state estimation device for estimating a driving state of a driver of a mobile object, comprising: a first acquisition step of acquiring driving information at the current position of the mobile object; a determination step of determining whether the current position corresponds to the peculiar point; and obtaining first driving information if it is determined that the current position corresponds to the peculiar point, and determining that the current position does not correspond to the peculiar point. If it is determined that the driver's driving state is determined by comparing a second obtaining step of obtaining the second driving information, the first driving information or the second driving information, and the driving information at the current position, and an estimating step of estimating.

The invention according to claim 10 is characterized in that the driving state estimation method according to claim 9 is executed by a computer.

According to an eleventh aspect of the invention, the driving state estimation generation program according to the tenth aspect is stored.

1 is a block diagram of a driving state estimation device according to one embodiment of the present invention; FIG. It is a specific example of an estimation method in the driving state estimation unit shown in FIG. FIG. 2 is a flow chart of the operation of the operation unit shown in FIG. 1; FIG.

A driving state estimation device according to an embodiment of the present invention will be described below. A driving state estimating device according to an embodiment of the present invention acquires driving information at a current position of a moving object by means of a first acquiring means. On the other hand, the determination means determines whether the current position corresponds to the peculiar point, and if the second acquisition means determines that the current position corresponds to the peculiar point, the first driving information is acquired, and the current position is the peculiar point. 2nd driving information is acquired when it determines with not corresponding to. Then, the estimating means compares the first driving information or the second driving information with the driving information at the current position to estimate the driving state of the driver. By doing so, it is possible to divide the driving conditions into peculiar points where the road environment is remarkably bad, such as road shapes such as sharp curves, special narrow streets, mountain passes, and crossing points with poor visibility, and other points. can be estimated, and erroneous recognition can be reduced by estimating based on the first driving information even at a point different from normal driving operation. Therefore, it is possible to accurately estimate the driving state regardless of the driving scene.

In addition, the estimation means may estimate whether or not there is a margin in the timing of the driver's driving operation as the driving state. By doing so, it is possible to estimate that the driver is falling asleep driving, careless driving, or the like due to the delay in the timing of the driver's driving operation.

Also, the first driving information and the second driving information may include position information. By doing so, it is possible to utilize the first driving information and the second driving information as the past travel history.

In addition, the estimating means may compare the first driving information or the second driving information having position information that matches the current running position of the moving object. By doing so, it is possible to directly compare the current driving information with the driving information of driving at that position in the past, and it is possible to estimate the driving state of the driver with higher accuracy.

Also, the first driving information and the second driving information may be patterned based on the road environment and road shape. By doing so, it becomes possible to compare a point that has not been traveled in the past by a pattern similar to the point.

In addition, the estimation means may compare the current traveling position of the moving body with the first driving information or the second driving information having a pattern similar to the road environment or road shape. By doing so, it is possible to compare the current driving information with the current driving information even for a point where the vehicle has not traveled in the past, and the driving state can be estimated.

Further, the first driving information and the second driving information include time information, and the estimating means estimates the driving state of the driver by comparing with the first driving information or the second driving information corresponding to the current time. may By doing so, it is possible to select and compare the driving information according to the time zone such as nighttime and daytime. Therefore, the driving state can be estimated with higher accuracy.

Further, a notification means for notifying the driver of the driving state may be provided. By doing so, it is possible to notify the driver of dangers such as drowsy driving and careless driving and their signs, and to encourage the driver to take a rest.

Also, in the driving state estimation method according to one embodiment of the present invention, the driving information at the current position of the moving object is obtained in the first obtaining step. On the other hand, in the determination step, it is determined whether the current position corresponds to the peculiar point, and in the second acquisition step, if it is determined that the current position corresponds to the peculiar point, the first driving information is acquired, and the current position is the peculiar point. 2nd driving information is acquired when it determines with not corresponding to. Then, in the estimation step, the driving state of the driver is estimated by comparing the first driving information or the second driving information with the driving information at the current position. By doing so, it is possible to divide the driving conditions into peculiar points where the road environment is remarkably bad, such as road shapes such as sharp curves, special narrow streets, mountain passes, and crossing points with poor visibility, and other points. can be estimated, and erroneous recognition can be reduced by estimating based on the first driving information even at a point different from normal driving operation. Therefore, it is possible to accurately estimate the driving state regardless of the driving scene.

Moreover, it is good also as a driving|running state estimation program which makes a computer perform the driving|running state estimation method mentioned above. By doing so, a computer can be used to identify specific points where the road environment is extremely bad, such as road shapes such as sharp curves, special narrow streets, mountain passes, and crossing points with poor visibility, and other points. It is possible to estimate the driving state by dividing , and it is possible to reduce misrecognition even in situations that differ from normal driving operations. Therefore, it is possible to accurately estimate the driving state regardless of the driving scene.

Moreover, you may store the driving|running state estimation program mentioned above in the computer-readable recording medium. By doing so, the program can be distributed as a single unit in addition to being incorporated into the device, and version upgrades and the like can be easily performed.

A driving state estimation device according to an embodiment of the present invention will be described with reference to FIGS. 1 to 3. FIG. As shown in FIG. 1, the driving state estimation device 1 includes a driving information acquisition unit 2, a wireless communication unit 3, a driving state estimation unit 4, a current position acquisition unit 5, and a notification unit 6. there is The driving state estimation device 1 shown in FIG. 1 is installed in a moving object such as a vehicle.

The driving information acquisition unit 2 as a first acquisition unit acquires information such as driving speed, operation timing of the brake, accelerator, steering wheel, etc., pedal depression amount, steering angle of the steering wheel, acceleration/deceleration, lateral acceleration, and the like. It is an interface (I/F) that acquires data from various sensors installed in the The acquired data is output to the driving state estimation unit 4 as driving information at the current position.

The wireless communication unit 3 as second acquisition means includes an electronic circuit, an antenna, and the like for wirelessly communicating with a server 11 (to be described later) via a network N such as the Internet. The wireless communication unit 3 receives (acquires) the first driving behavior pattern 11 a or the second driving behavior pattern 11 b from the server 11 and outputs the pattern to the driving state estimation unit 4 . The wireless communication unit 3 also transmits the current driving information acquired by the driving information acquisition unit 2 to the server 11 under the control of the driving state estimation unit 4 .

The driving state estimation unit 4 compares the driving information at the current position acquired by the driving information acquisition unit 2 with the first driving behavior pattern 11a or the second driving behavior pattern 11b acquired by the wireless communication unit 3 to determine whether the driver Estimate the driving state of The details of the method of estimating the driving state will be described later. In addition, the wireless communication unit 3 is caused to transmit the driving information at the current position acquired by the driving information acquisition unit 2 to the server 11 as the travel history. The driving state estimation unit 4 may be installed in the vehicle as, for example, an ECU (Electronic Control Unit) or the like, or a CPU (Central Processing Unit) installed in an in-vehicle device such as a navigation device may function. good.

The current position acquisition unit 5 acquires the current position of the vehicle in which the driving state estimation device 1 is installed, for example, using a GPS (Global Positioning System) receiver or the like.

A notification unit 6 as notification means notifies the driver or the like of the driving state as necessary based on the estimation result of the driving state estimation unit 4 . The notification unit 6 includes display means such as a liquid crystal display or a warning light that displays characters, icons, or the like, and a speaker or the like that notifies by sound such as a warning sound. Alternatively, the notification may be made by vibrating a vibrator embedded in the driver's seat.

Further, the target to be notified by the notification unit 6 is not limited to the driver. For example, it may be notified to a family member in a distant place, or to an administrator or the like in the case of a commercial vehicle such as a truck or a bus, through a communication line or the like.

The server 11 stores (stores) the first driving behavior pattern 11a and the second driving behavior pattern 11b. The server 11 transmits the first driving behavior pattern 11 a or the second driving behavior pattern 11 b in response to a request from the driving state estimation device 1 .

The first driving behavior pattern 11a is a driving behavior pattern of the driver at a specific point. The second driving behavior pattern 11b is a driving behavior pattern of the driver at a point other than the singular point. A driving behavior pattern is a pattern of driving behavior such as driving speed, operation timing of brake, accelerator, steering wheel, etc., pedal depression amount, steering angle of steering wheel, acceleration/deceleration, lateral acceleration, etc. It is. A singular point is, for example, a sharp curve, a special narrow street (such as a utility pole or guardrail protruding into the road, making it difficult to pass each other), a road shape such as a mountain pass, or a point where the road environment is extremely poor, such as an intersection with poor visibility. Say.

The first driving behavior pattern 11a and the second driving behavior pattern 11b are generated and stored for each driver.

In the server 11, the driving information acquired by the driving information acquiring means of the driving state estimation device 1 is stored as a travel history in association with the current position acquired by the current position acquiring unit 5. FIG. The first driving behavior pattern 11a is obtained by patterning the driving information related to the specific point among the accumulated driving information based on the road environment and the shape of the road. For example, it is patterned as a sharp curve, a narrow street, a mountain pass, an intersection, and the like. Note that the pattern creation is not limited to the server 11, and may be performed by another calculation server or the like. Further, when the current position is included in the travel history, the driving information itself of the history may be used as the first driving behavior pattern 11a. In this case, the position information is included in the first driving behavior pattern 11a. If there are a plurality of travel histories for that position, they may be averaged, for example.

Similarly to the first driving action pattern 11a, the second driving action pattern 11b is obtained by patterning the accumulated driving information related to points other than the specific points based on the road environment and road shape. If the current position is also included in the travel history for the second driving behavior pattern 11b, the driving information itself in the history may be used as the second driving behavior pattern 11b. In this case, the second driving behavior pattern 11b includes position information.

Note that the first driving behavior pattern 11a and the second driving behavior pattern 11b may be appropriately updated as the driving history is accumulated. In that case, it may be applied to the update of the driving behavior pattern by dividing the time period such as for the past several years. Also, the first driving behavior pattern 11 a and the second driving behavior pattern 11 b may be included in the driving state estimation device 1 instead of the server 11 .

Next, a method of estimating the driving state in the driving state estimating unit 4 of the driving state estimating device 1 having the configuration described above will be described. The driving state estimation unit 4 determines whether or not the current position acquired by the current position acquisition unit 5 corresponds to a peculiar point. Then, when it is determined that it corresponds to a peculiar point, the wireless communication unit 3 acquires the first driving behavior pattern 11a from the server 11, compares the first driving behavior pattern 11a with the current driving information, and determines the driving state. It is determined whether or not there is a margin. On the other hand, if it is determined that the location does not correspond to the peculiar point, the second driving behavior pattern 11b is acquired from the server 11 by the wireless communication unit 3, and the second driving behavior pattern 11b is compared with the current driving information. It is determined whether or not the state has a margin. That is, the driving state estimator 4 also functions as determination means.

It should be noted that whether or not it is a singular point may be determined, for example, by adding information indicating a singular point to the map information in advance and referring to it by the driving state estimation unit 4, or by referring to a separate singular point database or the like. may be referred to by the driving state estimation unit 4. Further, the map information, database, and the like may be possessed by the driving state estimation device 1, may be possessed by other in-vehicle equipment such as a navigation device, or may be acquired from an external device such as the server 11 via a network or the like. It may be acquired.

When the current position is in the travel history, as described above, the driving information itself of the history is used as the first driving behavior pattern 11a or the second driving behavior pattern 11b and compared with the driving information at the current position. If the current position is not in the travel history, the first driving behavior pattern 11a or second driving behavior pattern 11b that has been patterned is compared with the driving information at the current position. At this time, for example, if the current position is on a mountain pass, the pattern is compared with the pattern of the mountain pass. That is, the first driving behavior pattern 11a (first driving information) or the second driving behavior pattern 11b (second driving information) of patterns similar in road environment and road shape to the current position are compared.

FIG. 2 shows a left turn as a specific example of the presence or absence of a margin. When turning left, a sequence of cruising, pre-action, stepping on the brake, turning left, and accelerating is a series of sequences. The horizontal direction in FIG. 2 is the time axis, and the vertical direction indicates the magnitude of G (acceleration) when there is a margin or when there is no margin.

First, in the case of driving with a margin, (1) a pre-action such as gradually decreasing the speed from the cruising speed by, for example, releasing the accelerator pedal or applying the engine brake is performed before turning. (2) At the braking just before the left turn, since the speed has sufficiently decreased by then, the deceleration G (brake) is relatively moderate (α1 in FIG. 2). (3) Since the speed is sufficiently low, the steering wheel can be turned smoothly with plenty of room. Furthermore, (5) the steering wheel can be returned smoothly with a margin.

On the other hand, in the case of driving with no margin, (6) the timing of braking is performed immediately before the left turn, which is delayed by t1 compared to the case with margin. Therefore, the brake suddenly decelerates and the deceleration G increases (α2 in FIG. 2). Then, (7) before the left turn, the vehicle could not slow down sufficiently, and the vehicle approached the curve with the brake applied (t2 in FIG. 2), and the lateral acceleration (αy2) during turning was also large. Become. Furthermore, (8) since the speed has not completely decreased, there are unstable times, such as when the steering wheel is returned suddenly, or when the steering wheel is turned too much and then returned in a hurry (Fig. 2 t3). Therefore, acceleration is not performed smoothly.

In this way, as the current driving information, values such as the operation timing of the brake, accelerator, or steering wheel, the amount of pedal depression, the rudder angle of the steering wheel, acceleration/deceleration, lateral acceleration, etc. By comparing with the second driving behavior pattern 11b, it is possible to determine whether or not the current driving state of the driver is in a state of leeway.

For example, if the lengths of t1, t2, and t3 in FIG. 2 are each equal to or greater than a threshold value, it is determined that there is no margin. In this case, thresholds may be set individually for t1, t2, and t3. Moreover, not all of t1, t2, and t3 are equal to or longer than the threshold time, and any one or more of them may be equal to or longer than the threshold time and it may be determined that there is no margin.

In determining whether the driving state has sufficient margin, among the values included in the driving information such as the operation timing, the amount of depression of the pedal, the steering angle of the steering wheel, acceleration/deceleration, and lateral acceleration, for example, t1, t2, and t3 described above are used. It is not necessary to compare all items such as only the operation timing as in .

This determination result is not limited to reporting the presence or absence of a margin each time from the reporting unit 6, but may be reported when it is determined that there is no margin a plurality of times. This is because, for example, even if it corresponds to driving with no margin in FIG. 2, it is not necessarily the driver, but may be caused by other factors. Therefore, the notification may be made when there is no margin a plurality of times in succession, or when the frequency within a predetermined time period or within a predetermined distance is equal to or higher than a predetermined threshold value.

Next, FIG. 3 shows a flowchart of the operation (driving state estimation method) of the driving state estimation unit 4 described above. First, the driving information acquiring unit 2 acquires the current driving information (step S1), and based on the current position information acquired by the current position acquiring unit 5, it is determined whether or not the current position from which the driving information is acquired corresponds to a singular point. (Step S2).

Next, if it is determined in step S2 that the location corresponds to a peculiar point (if YES), the wireless communication unit 3 acquires the first driving behavior pattern 11a from the server 11 (step S3). If it is determined that the point does not apply (NO), the wireless communication unit 3 acquires the second driving behavior pattern 11b from the server 11 (step S4).

Next, the current driving information acquired in step S1 is compared with the first driving behavior pattern 11a acquired in step S3 or the second driving behavior pattern 11b acquired in step S4, and it is determined whether or not the driving is in a tight state. Determine (step S5).

Next, if it is determined that the driving is not enough for a predetermined number of times (step S6: YES), the notification unit 6 notifies the driver (step S7). A counter or the like may be provided inside the driving state estimating unit 4 to count the predetermined number of times. On the other hand, if it is not determined that the operation does not have enough margin for the predetermined number of times (step S6: NO), the process returns to step S1. The predetermined number of times is not one time as described above, but may be a plurality of consecutive times, a predetermined period of time, a frequency within a predetermined distance, or the like.

Next, after the notification in step S7, it is determined whether or not the operation is finished. If the operation is finished (step S8: YES), the flowchart is finished. If the operation is not finished (step S8: NO), the process proceeds to step S1. return. Whether or not the operation is finished may be determined by, for example, turning off the ignition switch.

That is, step S1 functions as first acquisition means, step S2 functions as determination means, steps S3 and S4 function as second acquisition means, and step S5 functions as estimation means.

According to this embodiment, the driving information acquisition unit 2 acquires the driving information at the current position of the vehicle. On the other hand, the driving state estimation unit 4 determines whether the current position corresponds to the peculiar point, and if the wireless communication unit 3 determines that the current position corresponds to the peculiar point, acquires the first driving behavior pattern 11a, If it is determined that the current position does not correspond to the peculiar point, the second driving behavior pattern 11b is acquired. Then, the driving state estimation unit 4 compares the first driving behavior pattern 11a or the second driving behavior pattern 11b with the driving information at the current position to estimate the driving state of the driver. By doing so, it is possible to divide the driving conditions into peculiar points where the road environment is remarkably bad, such as road shapes such as sharp curves, special narrow streets, mountain passes, and crossing points with poor visibility, and other points. can be estimated, and erroneous recognition can be reduced by estimating based on the first driving behavior pattern 11a even in situations where normal driving operations are different. Therefore, it is possible to accurately estimate the driving state regardless of the driving scene.

Further, the driving state estimating unit 4 estimates whether or not there is a margin in the timing of the driver's driving operation as the driving state. By doing so, it is possible to estimate that the driver is falling asleep driving, careless driving, or the like due to the delay in the timing of the driver's driving operation.

Also, the first driving behavior pattern 11a and the second driving behavior pattern 11b include position information. By doing so, it is possible to utilize the first driving behavior pattern 11a and the second driving behavior pattern 11b as the past travel history.

Further, the driving state estimation unit 4 may compare the first driving behavior pattern 11a or the second driving behavior pattern 11b having position information that matches the current running position of the moving object. By doing so, it is possible to directly compare the current driving information with the driving behavior pattern related to the driving information of driving at the position in the past, and it is possible to estimate the driving state with higher accuracy.

Also, the first driving behavior pattern 11a and the second driving behavior pattern 11b may be patterned based on the road environment and road shape. By doing so, it becomes possible to compare a point that has not been traveled in the past by a pattern similar to the point.

In addition, a notification unit 6 is provided to notify the driver of the driving state. By doing so, it is possible to notify the driver of dangers such as drowsy driving and careless driving and their signs, and to encourage the driver to take a rest.

Note that the accumulated driving information may include time information, and the first driving behavior pattern 11a and the second driving behavior pattern 11b may be created in a plurality of types, such as morning, noon, and night, based on the time. That is, the first driving behavior pattern 11a and the second driving behavior pattern 11b include time information, and the driving state estimation unit 4 calculates the first driving behavior pattern 11a and the second driving behavior pattern 11b corresponding to the current time. The driving state of the driver may be estimated by comparison. By doing so, it is possible to select and compare the driving information according to the time zone such as nighttime and daytime. Therefore, the driving state can be estimated with higher accuracy.

Further, in the above-described embodiment, only the notification is given when it is determined that the driving state does not have enough margin. Based on this, for example, the traveling speed, brake timing, etc. may be guided by voice or display.

In the above-described embodiment, the driving behavior pattern is acquired from the server. You can do it.

Moreover, the present invention is not limited to the above embodiments. That is, those skilled in the art can carry out various modifications according to conventionally known knowledge without departing from the gist of the present invention. As long as the configuration of the driving state estimating device of the present invention is still provided even with such modification, it is of course included in the scope of the present invention.

1 driving support information generation device 2 driving information acquisition unit (first acquisition means)
3 Wireless Communication Unit (Second Acquisition Means)
4 driving state estimation unit (judgment means, estimation means)
5 reporting unit (notifying means)
11a First driving behavior pattern (first driving information)
11b Second driving behavior pattern (second driving information)
S1 Acquisition of current driving information (first acquisition step)
S2 Determining whether it is a singular point (determining step)
S3 Acquisition of first driving behavior pattern (second acquisition step)
S4 Acquisition of second driving behavior pattern (second acquisition step)
S5 Comparison/judgment (estimation step)

Claims (1)

a first acquiring means for acquiring driving information at the current position of the moving object;
Determination means for determining whether the current position corresponds to a singular point;
A second acquiring means for acquiring first driving information when the current position is determined to correspond to the peculiar point, and acquiring second driving information when it is determined that the current position does not correspond to the peculiar point. and,
estimating means for estimating the driving state of the driver by comparing the first driving information or the second driving information with the driving information at the current position;
A driving state estimation device comprising:

Images