Information processing device, information processing method, program, and recording medium

Abstract

To provide an information processing device, an information processing method, a program and a recording medium capable of estimating an operation action of a driver without requiring a learning period and performing appropriate operation support to the driver.SOLUTION: An information processing device comprises: a mirror confirmation information acquisition section which acquires mirror confirmation frequency indicating frequency that a driver of a vehicle looks in a mirror and a mirror confirmation interval indicating a time interval from driver's previous confirmation of the mirror to driver's subsequent confirmation of the mirror; and an intention determination section which performs an intention determination process including determination of whether or not the driver intends to change a route on the basis of the mirror confirmation frequency and the mirror confirmation interval in a first period.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, a program, and a recording medium. [Background technology]

[0002] There is known a driving assistance device that estimates a driving operation to be performed by a driver and provides driving assistance for the driver to perform the driving operation. For example, Patent Document 1 discloses a driving assistance device that learns a pattern of preparatory movements before a driving operation and a surrounding situation of the vehicle when the driving operation is performed as a learning model, compares the current driver's movements and surrounding situation with the learned model, estimates the driving operation to be performed by the driver, and provides a notification according to the estimation result. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-129973 Summary of the Invention [Problem to be solved by the invention]

[0004] One of the problems with the driving assistance device described in Patent Document 1 is that, for example, there are a wide variety of safety confirmation patterns as preparatory actions when a driver changes lanes, so it takes a long time to obtain learning results at a practical level.

[0005] Furthermore, depending on the timing of the notification by the driving assistance device, one problem is that if the notification is made just before changing lanes, for example, the driver may find the notification annoying.

[0006] The present invention has been made in consideration of the above-mentioned points, and aims to provide an information processing device, an information processing method, a program, and a recording medium that are capable of estimating a driver's driving behavior without requiring a learning period and providing appropriate driving assistance to the driver. [Means for solving the problem]

[0007] The information processing device described in claim 1 is characterized by having a mirror confirmation information acquisition unit that acquires a mirror confirmation frequency indicating how often a driver of a vehicle checks the mirror and a mirror confirmation interval indicating the time interval between when the driver checks the mirror and when the driver next checks the mirror, and an intention determination unit that performs an intention determination process including determining whether the driver has the intention to change lanes based on the mirror confirmation frequency and the mirror confirmation interval within a first period.

[0008] The information processing method described in claim 10 is an information processing method executed by an information processing device, characterized in that it includes a mirror confirmation information acquisition step in which a mirror confirmation information acquisition unit acquires a mirror confirmation frequency indicating the frequency at which a driver of a vehicle checks the mirror and a mirror confirmation interval indicating the time interval between when the driver checks the mirror and when the driver next checks the mirror, and an intention determination step in which an intention determination unit performs an intention determination process including determining whether the driver has the intention to change lanes, based on the mirror confirmation frequency and the mirror confirmation interval within a first period.

[0009] The program described in claim 11 is a program to be executed by a computer, and is characterized in that the program causes the computer to execute the following steps: a mirror confirmation information acquisition step in which a mirror confirmation information acquisition unit acquires a mirror confirmation frequency indicating the frequency at which the driver of the vehicle checks the mirror and a mirror confirmation interval indicating the time interval between when the driver checks the mirror and when the driver next checks the mirror; and an intention determination step in which an intention determination unit performs an intention determination process including determining whether the driver has the intention to change lanes based on the mirror confirmation frequency and the mirror confirmation interval within a first period.

[0010] A recording medium according to claim 12 is a recording medium on which the above program is recorded. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram showing a configuration of a front seat portion of a vehicle and a view in front of the vehicle according to a first embodiment. [Figure 2] 1 is a block diagram illustrating an example of a configuration of an in-vehicle device according to a first embodiment. [Figure 3] FIG. 3 is a diagram showing a table of evaluation indexes corresponding to the levels of each evaluation element stored in the in-vehicle device according to the first embodiment. [Figure 4] FIG. 3 is a diagram showing a table of evaluation indexes corresponding to the levels of each evaluation element stored in the in-vehicle device according to the first embodiment. [Figure 5] 3 is a flowchart showing a control routine of the in-vehicle device according to the first embodiment. [Figure 6] 3 is a flowchart showing a control routine of the in-vehicle device according to the first embodiment. [Figure 7] 3 is a flowchart showing a control routine of the in-vehicle device according to the first embodiment. [Figure 8] 4 is a graph showing a change over time in the score for each of the driving behavior scenes generated by the on-vehicle device according to the first embodiment. [Figure 9] FIG. 10 is a diagram illustrating the configuration of a difficulty level identification system according to an application example. [Figure 10] FIG. 10 is a block diagram showing an example of the configuration of a server device according to an application example. [Figure 11] FIG. 10 is a diagram illustrating an example of a difficulty map indicating the difficulty of lane changes generated by a server device according to an application example. [Figure 12] 10 is a flowchart showing a control routine of a server device according to an application example. [Figure 13] 10 is a flowchart showing a control routine of a server device according to an application example. [Figure 14] FIG. 10 is a diagram showing a table of criteria for determining difficulty levels determined by a server device according to an application example. [Figure 15] FIG. 10 is a diagram showing a table of lane change difficulty data for each vehicle stored in a server device according to an application example. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, the same components are designated by the same reference numerals, and the description of the same components will be omitted. [Example]

[0013] FIG. 1 is a diagram showing a configuration of a front seat portion of a vehicle M as a moving body according to the first embodiment and a view ahead of the vehicle M. As shown in FIG.

[0014] The in-vehicle device 10 is connected to a touch panel display 12, a speaker 13, a GNSS receiver 14, and an in-vehicle camera 15, all of which are installed in the vehicle M, and includes a control unit that controls these. The in-vehicle device 10 is disposed in the center of a dashboard DB in the front seat of the vehicle M.

[0015] The touch panel display 12 is a display device that combines a display that displays a screen based on the control of the in-vehicle device 10 and a touch panel that accepts input operations from a passenger of the vehicle M. For example, a navigation image in which the current position of the vehicle M is superimposed on a map is displayed on the touch panel display 12. In this embodiment, the touch panel display 12 is disposed in the center of the dashboard DB.

[0016] The speaker 13 is an audio output device that outputs audio under the control of the in-vehicle device 10. In this embodiment, the speaker 13 is provided on each of the two A-pillars AP.

[0017] The GNSS receiver 14 is a receiver that receives signals (GNSS signals) from GNSS (Global Navigation Satellite System) satellites. The GNSS receiver 14 transmits the received GNSS signals to the in-vehicle device 10. In this embodiment, the GNSS receiver 14 is arranged on the dashboard DB.

[0018] The interior camera 15 is an imaging device that captures images of the interior of the vehicle M. In this embodiment, the interior camera 15 is a camera that captures images of the face of the driver of the vehicle M. In this embodiment, the interior camera 15 is installed near the rearview mirror RM on the ceiling inside the vehicle M.

[0019] The front camera 16 is an imaging device that captures images of the external situation of the vehicle M. In this embodiment, the front camera 16 is a camera that captures images in front of the vehicle M. In this embodiment, the front camera 16 is disposed on the dashboard DB.

[0020] In this embodiment, the in-vehicle device 10 detects the direction of the driver's line of sight based on an image of the face of the driver of the vehicle M captured by the in-vehicle camera 15. The in-vehicle device 10 also detects the driver's checking behavior of the rearview mirror RM, right side mirror RS, and left side mirror LS based on the detected direction of the driver's line of sight and the relative positions of the rearview mirror RM, right side mirror RS, and left side mirror LS with the driver's viewpoint.

[0021] Note that the positions of the in-vehicle device 10, touch panel display 12, speaker 13, GNSS receiver 14, in-vehicle camera 15, and front camera 16 in the front seat portion of the vehicle M described above are merely examples, and they may be arranged in other positions.

[0022] Figure 1 shows a situation in which vehicle M is traveling in the left lane of a two-lane road, with vehicle MA traveling ahead of vehicle M. Figure 1 shows a situation in which the driver of vehicle M feels that vehicle MA is traveling slowly and is considering overtaking it, i.e., is considering changing lanes to the right lane in the figure.

[0023] In this embodiment, the in-vehicle device 10 estimates the driving behavior that the driver of vehicle M is about to perform, based on the behavior of the driver of vehicle M, the behavior of vehicle M, position information of vehicle M, and the situation around vehicle M. Specifically, the in-vehicle device 10 calculates a score for each of the driving behavior scenes, namely, going straight, turning right, turning left, changing lanes to the right, and changing lanes to the left, based on the behavior of the driver of vehicle M, the behavior of vehicle M, the position information of vehicle M, and the situation around vehicle M, and estimates which of the above-listed driving behavior scenes the driver of vehicle M is currently performing, based on the score.

[0024] 1, for example, the on-vehicle device 10 detects that the driver of vehicle M has performed a check of the rearview mirror RM and the right side mirror RS, and that vehicle M is traveling in the left lane of a two-lane road, and calculates multiple scores, each corresponding to one of the above-mentioned scenes, based on the behavior. Then, since the score indicating a right lane change is the highest among the calculated scores, the on-vehicle device 10 estimates that the driving action that the driver of vehicle M is planning to perform next is a right lane change.

[0025] In this embodiment, when the estimated result of the driving behavior is a right lane change or a left lane change, the in-vehicle device 10 determines whether the driver has an intention to change lanes based on the score of the lane change. Note that in this specification, "having an intention to change lanes" refers to a state after the driver has an intention to change lanes, regardless of whether the driver has actually decided to change lanes. In other words, the in-vehicle device 10 determines whether the driver has an intention to change lanes.

[0026] In this embodiment, when the estimated driving behavior is a right lane change or a left lane change, the in-vehicle device 10 determines whether the driver has decided to actually change lanes based on the score of the lane change. In other words, the in-vehicle device 10 determines whether the driver has decided to change lanes.

[0027] In this embodiment, when the in-vehicle device 10 determines that the driver has an intention to change lanes or that the driver has decided to change lanes, it outputs a notification to the driver according to the determination result.

[0028] Fig. 2 is a block diagram showing an example of the configuration of the in-vehicle device 10 according to Example 1. In this example, the in-vehicle device 10 is connected to an outside-vehicle camera system 16S, an acceleration sensor 17, and a biometric sensor 18 in addition to the devices shown in Fig. 1 .

[0029] The exterior camera system 16S is an imaging system made up of imaging devices including the front camera 16 described above that captures images of the situation outside the vehicle M. In this embodiment, the exterior camera system 16S is made up of the front camera 16 that captures images in front of the vehicle M, and multiple cameras (not shown) that are configured to capture images of the sides and rear. For example, the cameras that make up the exterior camera system 16S are individually mounted on the vehicle M as the front camera 16, two side cameras, and a rear camera. The side cameras are attached, for example, to the side mirrors, and the rear camera is attached, for example, to the back window or its surroundings.

[0030] The acceleration sensor 17 is an acceleration sensor configured to be able to measure acceleration in the traveling direction of the vehicle M, i.e., the longitudinal direction, and acceleration in a direction perpendicular to the traveling direction of the vehicle M, i.e., the lateral direction of the vehicle M. The acceleration sensor 17 may be a three-axis acceleration sensor. Alternatively, the acceleration sensor 17 may be a six-axis inertial sensor or the like that is made up of a three-axis gyro sensor and a three-axis acceleration sensor.

[0031] The biosensor 18 is a biosensor that detects bioinformation of the driver of the vehicle M. In this embodiment, the biosensor 18 measures the heart rate of the driver while driving the vehicle M. In this embodiment, the biosensor 18 is built into the backrest of the seat of the vehicle M, and measures the heart rate of the driver while the driver is seated in the seat.

[0032] The biosensor 18 may be attached to a seat belt, a steering wheel, or other locations. Alternatively, the driver's smartphone or smartwatch may be connected to the in-vehicle device 10 so as to be capable of communicating with the in-vehicle device 10, and the smartphone or smartwatch may serve as the biosensor 18.

[0033] In this embodiment, the in-vehicle device 10 is a device in which a control unit 22, a communication unit 23, an input unit 24, an output unit 25, and a large-capacity storage device 26 cooperate with each other via a system bus 21.

[0034] The control unit 22 is configured with a CPU (Central Processing Unit) 22A, a ROM (Read Only Memory) 22B, a RAM (Random Access Memory) 22C, etc., and functions as a computer. The CPU 22A reads and executes various programs stored in the ROM 22B and the large-capacity storage device 26, thereby realizing various functions.

[0035] The communication unit 23 is a communication device that transmits and receives data to and from external devices in accordance with instructions from the control unit 22. The communication unit 23 is, for example, a network interface card (NIC) for connecting to a network.

[0036] The above-mentioned various programs may be acquired, for example, from another server device or the like via a network, or may be recorded on a recording medium and read via various drive devices. That is, the various programs stored in the mass storage device 26 (including a program for executing processing in the in-vehicle device 10, which will be described later) can be transmitted via a network, or can be recorded on a computer-readable recording medium and transferred.

[0037] The input unit 24 is an interface unit that is communicatively connected to the control unit 22 of the in-vehicle device 10 and each of the touch panel display 12, the GNSS receiver 14, the in-vehicle camera 15, the outside-vehicle camera system 16S, the acceleration sensor 17, and the biometric sensor 18.

[0038] In this embodiment, the control unit 22 acquires the GNSS signal received by the GNSS receiver 14 via the input unit 24. That is, the control unit 22 functions as a position information acquisition unit that acquires position information of the vehicle M based on the GNSS signal from the GNSS receiver 14.

[0039] In this embodiment, as described above, the control unit 22 acquires an image of the face of the driver of the vehicle M captured by the in-vehicle photographing camera 15 via the input unit 24. Also, as described above, the control unit 22 acquires the direction of the driver's line of sight based on the acquired image of the driver's face.

[0040] In this embodiment, as described above, the control unit 22 acquires an image of the surroundings of the vehicle M captured by the exterior camera system 16S via the input unit 24. The control unit 22 determines, for example, whether or not there is a vehicle approaching the vehicle M from behind, based on the acquired image of the rear of the vehicle M. In other words, the control unit 22 functions as a surrounding situation information acquisition unit that acquires the situation around the vehicle M.

[0041] In this embodiment, as described above, the control unit 22 acquires the acceleration in the traveling direction of the vehicle M and the acceleration in the direction lateral to the traveling direction of the vehicle M measured by the acceleration sensor 17 via the input unit 24. In other words, the control unit 22 functions as a vehicle behavior information acquisition unit that acquires vehicle behavior information that indicates the behavior of the vehicle M.

[0042] In this embodiment, as described above, the control unit 22 acquires the biometric information of the driver of the vehicle M measured by the biometric sensor 18 via the input unit 24. That is, the control unit 22 functions as a biometric information acquisition unit. In this embodiment, the control unit 22 acquires the heart rate of the driver.

[0043] The output unit 25 is an interface unit that is communicatively connected between the control unit 22 of the in-vehicle device 10 and the touch panel display 12 and speaker 13. The control unit 22 transmits a video or image signal to the touch panel display 12 via the output unit 25 to display the video or image. The control unit 22 also transmits an audio signal to the speaker 13 via the output unit 25 to output sound.

[0044] The mass storage device 26 is configured by, for example, a hard disk drive, a solid state drive (SSD), a flash memory, etc., and is a storage device that stores various programs such as an operating system and software for the terminal.

[0045] The evaluation index database (hereinafter referred to as evaluation index DB) 26A of the mass storage device 26 is a database that stores numerical information indicating evaluation indexes used to calculate a score for each of the above-mentioned driving behavior scenes.

[0046] In this embodiment, the control unit 22 calculates a score for each of the scenes of going straight, turning right, turning left, changing lanes to the right, and changing lanes to the left by introducing the above evaluation index into the score calculation formula, and based on the score, estimates which of the above-listed driving behavior scenes the driver of vehicle M is currently in.

[0047] Map information is stored in a map information database (hereinafter referred to as map information DB) 26B of the mass storage device 26. In this embodiment, the control unit 22 acquires information on the type of road and the driving lane on which the vehicle M is currently traveling, based on the map information stored in the map information DB 26B and the above-described position information of the vehicle M.

[0048] In this embodiment, as described above, the control unit 22 detects the driver's checking behavior of each of the rearview mirror RM, right side mirror RS and left side mirror LS based on the direction of the driver's line of sight and the relative position of each of the rearview mirror RM, right side mirror RS and left side mirror LS with the driver's viewpoint.

[0049] When the control unit 22 detects a mirror checking behavior in any of the rearview mirror RM, right side mirror RS, and left side mirror LS, it determines that the first mirror checking behavior monitoring period (hereinafter simply referred to as the first monitoring period), during which the driver's mirror checking behavior needs to be monitored, has begun.

[0050] In this embodiment, the control unit 22 determines that the first monitoring period has ended when no mirror-checking behavior has been detected for 10 consecutive seconds during the first monitoring period. Specifically, the control unit 22 resets the count of seconds each time a mirror-checking behavior is detected during the first monitoring period, and determines that the first monitoring period has ended when no mirror-checking behavior has been detected for 10 consecutive seconds since the last mirror-checking behavior.

[0051] In addition, in this embodiment, when the control unit 22 detects a mirror checking behavior in any of the rearview mirror RM, right side mirror RS, and left side mirror LS, it determines that a second mirror checking behavior monitoring period (hereinafter simply referred to as the second monitoring period), during which the driver's mirror checking behavior needs to be monitored, has begun.

[0052] In this embodiment, the control unit 22 determines that the second monitoring period has ended when no mirror-checking behavior has been detected for five consecutive seconds during the second monitoring period. Specifically, the control unit 22 resets the count of seconds each time a mirror-checking behavior is detected during the second monitoring period, and determines that the second monitoring period has ended when no mirror-checking behavior has been detected for five consecutive seconds since the last mirror-checking behavior.

[0053] Here, the data stored in the evaluation index DB 26A of the mass storage device 26 will be described with reference to FIGS.

[0054] FIG. 3 is a table TB1 (hereinafter referred to as evaluation index TB1) showing evaluation indexes relating to mirror checking behavior, among the evaluation indexes used to calculate the score for each of the above driving behavior scenes.

[0055] In the evaluation index TB1, the "Evaluation Element" item on the far left indicates the element to be evaluated in the driver's mirror checking behavior. The "Numerical Range" item, second from the left, indicates the numerical values ​​indicated by the evaluation element, divided into multiple ranges. Furthermore, the "Level" item, third from the left, indicates the level of each evaluation element, determined according to the numerical ranges mentioned above.

[0056] In the evaluation index TB1, the item "evaluation index by scene" on the far right indicates the evaluation index determined according to the above-mentioned levels for "1. Going straight," "2. Turning right," "3. Turning left," "4. Changing lanes to the right," and "5. Changing lanes to the left," each of which indicates a driving behavior scene. In this embodiment, a score is calculated for each of the above-mentioned scenes using the evaluation index identified with reference to the evaluation index TB1.

[0057] Here, each element shown in the above-mentioned "evaluation element" will be described in detail with reference to FIG. 3. First, "mirror check frequency X a" indicates the mirror checking frequency calculated by dividing the number of times the driver of vehicle M checks any of the rearview mirror RM, right side mirror RS, and left side mirror LS during the first monitoring period described above by the elapsed time since the start of the first monitoring period.

[0058] Next, select "Mirror Check Interval X" b " indicates the time interval between when the driver of vehicle M checks the rearview mirror RM, right side mirror RS, or left side mirror LS and when he next checks the rearview mirror RM, right side mirror RS, or left side mirror LS during the first monitoring period described above.

[0059] Next, select "Check the rearview mirror X times" c "," "Number of times checking right side mirror X d " and "Number of times to check left side mirror X e " indicates the number of times the rearview mirror RM, the right side mirror RS, and the left side mirror LS were checked during the second monitoring period. For example, in this embodiment, "number of times the right side mirror was checked X d The more times "2. Turn right" and "4. Change lane to the right" are performed, the higher the evaluation indexes for "2. Turn right" and "4. Change lane to the right" are set.

[0060] Finally, "Check right side mirror and rearview mirror alternately X times f " and "Number of times to check left side mirror and rearview mirror alternately X g " indicates the number of times the rearview mirror RM and the right side mirror RS were alternately checked and the number of times the rearview mirror RM and the left side mirror LS were alternately checked during the second monitoring period. For example, in this embodiment, "number of times X g The more times "3. Left turn" and "5. Left lane change" occur, the higher the evaluation indexes for "3. Left turn" and "5. Left lane change" will be.

[0061] In this embodiment, the control unit 22 sets the mirror check frequency Xa " and "Mirror Check Interval X b " and during the second monitoring period, "the number of times the rearview mirror is checked X c "," "Number of times checking right side mirror X d "," "Number of times checking left side mirror X e "," "Number of times to check right side mirror and rearview mirror alternately X f " and "Number of times to check right side mirror and rearview mirror alternately X g That is, in this embodiment, the control unit 22 functions as a mirror confirmation information acquisition unit that acquires mirror confirmation information related to mirror confirmation behavior.

[0062] Next, reference is made to Fig. 4. Fig. 4 is a table TB2 (hereinafter referred to as evaluation index TB2) showing evaluation indexes related to the current position of vehicle M, the surrounding conditions of vehicle M, the behavior of vehicle M, and the behavior of the driver other than the mirror checking behavior described above, among the evaluation indexes used to calculate the score for each of the driving behavior scenes described above. The explanation of each item in evaluation index TB2 is the same as that of evaluation index TB1, so the explanation will be omitted.

[0063] Here, each element shown in the "Evaluation element" will be described in detail with reference to FIG. 4. First, "Travel road type X h " indicates the type of road on which vehicle M is traveling, which is identified based on the map information stored in the map information DB 26B and the position information of vehicle M. For example, in this embodiment, when vehicle M is traveling on a highway, the evaluation indexes for "2. Turn right" and "3. Turn left" are set to be lower than those for other scenes.

[0064] Next, "Traveling lane X i" indicates the lane in which vehicle M is traveling, which is identified based on map information and position information of vehicle M. For example, in this embodiment, when vehicle M is traveling in the rightmost lane of multiple lanes on one side, the evaluation index for "3. Turn left" is set lower than the indices for other scenes, and the evaluation index for "4. Change lane to the right" is set even lower than the evaluation index for "3. Turn left" because there is no lane further to the right.

[0065] Next, the situation of other vehicles around the vehicle X j " indicates the result of identifying the driving state of other vehicles around vehicle M based on the captured image taken by the above-described exterior camera system 16S. For example, in this embodiment, when another vehicle is driving to the side of vehicle M, the evaluation indexes for "4. Right lane change" and "5. Left lane change" are set to be lower than those for other scenes.

[0066] Next, "Acceleration / deceleration of own vehicle X k " indicates the current acceleration / deceleration state of the vehicle M based on the acceleration in the direction of travel of the vehicle M and the acceleration lateral to the direction of travel of the vehicle M measured by the acceleration sensor 17 described above. For example, in this embodiment, when it is determined that the vehicle M is accelerating in the direction of travel, the evaluation indexes for "2. Turn right" and "3. Turn left" are set to be lower than those for other scenes.

[0067] Next, "Operate the turn signal X l " indicates the operation state of the right or left turn signal operated by the driver of vehicle M. For example, in this embodiment, when the right turn signal is operated by the driver, the evaluation indexes for "2. Turn right" and "4. Change lane to right" are set to be larger than those for other scenes, and the evaluation indexes for "3. Turn left" and "5. Change lane to left" are set to be lower than those for other scenes.

[0068] Finally, "Driver's Heart Rate X m" indicates the measurement result of the heart rate of the driver of the vehicle M by the biosensor 18 described above. For example, in a case where a decision to change lanes is required, the driver's level of tension regarding driving will be higher than if the driver were simply going straight, and it can be estimated that the driver's heart rate will be higher. Therefore, in this embodiment, the evaluation index for scenes other than "1. Going straight" is set so that the higher the driver's heart rate is.

[0069] [Estimation of driver behavior] A method for estimating the driving behavior of a driver in this embodiment will be described below. In this embodiment, when the current period is the first monitoring period or the second monitoring period, the control unit 22 refers to the evaluation index TB1 and the evaluation index TB2, obtains the level corresponding to each evaluation element, and extracts the evaluation index according to the level.

[0070] In this embodiment, the control unit 22 sequentially calculates a score for each driving behavior scene using the acquired evaluation index. Specifically, the control unit 22 extracts an evaluation index corresponding to the above-mentioned level by referring to the evaluation index TB1 and the evaluation index TB2, and calculates a score using the following probability calculation formula (f n ) to calculate the probability indicating the feasibility of each of going straight (f1), turning right (f2), turning left (f3), changing lanes to the right (f4), and changing lanes to the left (f5).

[0071]

number

[0072] [Lane change intention determination processing] Below, in this embodiment, we will explain the lane change intention determination process when the control unit 22 estimates that the next driving action that the driver of vehicle M is about to perform is a right lane change or a left lane change.

[0073] In this embodiment, the control unit 22 determines whether the driver has an intention to change lanes based on the estimated lane change score as described above. That is, in this embodiment, the control unit 22 functions as an intention determination unit that determines whether the driver has an intention to change lanes.

[0074] In this embodiment, the control unit 22 determines that the driver has an intention to change lanes when the estimated lane change score is equal to or greater than a first threshold. Specifically, for example, the control unit 22 determines that the driver has an intention to change lanes when the probability indicating the feasibility of the right lane change is 40% or greater.

[0075] In addition, in this embodiment, the control unit 22 determines whether or not the driver has decided to change lanes based on the estimated lane change score, as described above.

[0076] In this embodiment, the control unit 22 determines that the driver has decided to change lanes when the estimated lane change score is equal to or greater than a second threshold. Specifically, for example, the control unit 22 determines that the driver has decided to change lanes when the probability indicating the feasibility of changing to the right is 70% or greater.

[0077] In this embodiment, the control unit 22 outputs a notification to the driver via the speaker 13 based on whether the current state of the driver of the vehicle M is a state in which the driver has the intention to change lanes as described above, or a state in which the driver has made a decision regarding the intention to change lanes.

[0078] Specifically, when the control unit 22 determines that the driver intends to change lanes, it outputs an announcement to support the driver in making the lane change, a warning based on the position information of the vehicle M, or the like. For example, when the driver has set a destination and it is determined that the driver intends to change lanes to the right, the control unit 22 outputs a notice such as, "The next lane is a left turn, so please stay in the left lane without changing to the right lane." The driver of the vehicle M can receive this notice and cancel the right lane change.

[0079] On the other hand, when the control unit 22 determines that the driver has made a decision to change lanes, it outputs a simpler notification than when it determines that the driver has made the decision to change lanes, since it is assumed that the time from when the decision is made to when the lane change is actually made is short.

[0080] For example, when it is determined that the driver has decided to change lanes, the control unit 22 outputs a warning such as "Please be careful of surrounding vehicles." Also, for example, when the driver forgets to turn on a turn signal when changing lanes, the control unit 22 outputs a warning such as "You forgot to turn on your turn signal." Note that the above-mentioned notification is not limited to audio, and may be a simple buzzer sound or the like.

[0081] In this way, in this embodiment, when the driver's driving behavior is estimated to be a lane change, the type of service provided to the driver can be changed depending on the current state of the lane change.

[0082] Specific operations of the vehicle-mounted device 10 in this embodiment will be described below with reference to Figures 5 to 7. Figure 5 is a flowchart showing a behavior monitoring routine RT1 executed by the control unit 22 of the vehicle-mounted device 10.

[0083] The control unit 22 starts the behavior monitoring routine RT1, for example, when power is turned on to the in-vehicle device 10. Note that the behavior monitoring routine RT1 is repeatedly executed by the control unit 22 as long as the in-vehicle device 10 is powered on.

[0084] First, the control unit 22 determines whether or not the driver has performed a mirror check (step S101). Specifically, as described above, the control unit 22 detects the direction of the driver's line of sight based on the image of the driver's face acquired from the in-vehicle camera 15. Then, based on the detected line of sight direction and the relative positions of the rearview mirror RM, right side mirror RS, and left side mirror LS with respect to the driver's viewpoint, it determines whether or not the driver has checked any of the rearview mirror RM, right side mirror RS, and left side mirror LS.

[0085] If the control unit 22 determines that there has been no mirror checking behavior (step S101: NO), that is, that the driver has not checked any of the rearview mirror RM, right side mirror RS, and left side mirror LS, it ends the behavior monitoring routine RT1.

[0086] When the control unit 22 determines that a mirror checking behavior has occurred (step S101: YES), it outputs a monitoring period start signal to start monitoring the mirror checking behavior (step S102). Specifically, the control unit 22 determines that a mirror checking behavior has occurred when, for example, the driver of the vehicle M decides to change lanes to the right and checks the right side mirror RS, and determines that a period in which monitoring of the mirror checking behavior of the driver of the vehicle M is required has started.

[0087] After step S102, the control unit 22 determines whether or not a mirror checking behavior has occurred, similarly to step S101 (step S103). If the control unit 22 determines that a mirror checking behavior has occurred (step S103: YES), the control unit 22 repeatedly executes step S103. That is, the control unit 22 repeatedly executes the above determination as long as the driver repeatedly performs mirror checking behavior.

[0088] If the control unit 22 determines that there has been no mirror checking behavior (step S103: NO), it determines whether or not 10 seconds have passed since the last mirror checking behavior (step S104).If the control unit 22 determines that 10 seconds have not passed since the mirror checking behavior (step S104: NO), it executes step S103 again to determine whether or not there has been a mirror checking behavior.

[0089] When the control unit 22 determines that 10 seconds have passed since the mirror checking behavior (step S104: YES), it outputs a monitoring period end signal (step S105). That is, the control unit 22 determines that 10 seconds have passed since the mirror checking behavior and that the period during which it is necessary to monitor the driver's mirror checking behavior has ended. The control unit 22 ends the behavior monitoring routine RT1 after step S105.

[0090] 6 is a flowchart showing a driving behavior estimation routine RT2 executed by the control unit 22 of the in-vehicle device 10. The control unit 22 starts the driving behavior estimation routine RT2, for example, when the in-vehicle device 10 is powered on. Note that the driving behavior estimation routine RT2 is repeatedly executed by the control unit 22 as long as the in-vehicle device 10 is powered on.

[0091] First, in the behavior monitoring routine RT1, the control unit 22 determines whether or not the current period is a period during which mirror checking behavior is monitored (step S201). That is, the control unit 22 determines that the current period is one in which the mirror checking behavior of the driver needs to be monitored, based on the detection of the mirror checking behavior of the driver. When the control unit 22 determines that the current period is not a period during which mirror checking behavior is monitored (step S201: NO), the control unit 22 ends the driving behavior estimation routine RT2.

[0092] When the control unit 22 determines that the mirror checking behavior monitoring period is in progress (step S201: YES), it acquires the level of each evaluation element (step S202). Specifically, as described above, the control unit 22 refers to the evaluation index DB 26A and acquires the level according to the state or numerical value indicated by each of the evaluation elements regarding the behavior of the driver of the vehicle M, the behavior of the vehicle M, the position information of the vehicle M, and the situation around the vehicle M.

[0093] When the control unit 22 acquires the level of each evaluation element in step S202, it calculates a score for each driving behavior scene (step S203). In this embodiment, as described above, the control unit 22 refers to the evaluation index DB 26A and uses the evaluation index corresponding to the level to calculate the probability indicating the occurrence of each of going straight, turning right, turning left, changing to the right lane, and changing to the left lane.

[0094] Specifically, the control unit 22 calculates the probability indicating the possibility of each of going straight, turning right, turning left, changing to the right lane, and changing to the left lane by introducing the evaluation index identified by referring to the tables shown in Figures 3 and 4 into the score calculation formula described above.

[0095] After step S203, the control unit 22 estimates the driver's driving behavior by comparing the scores calculated for each driving behavior scene with each other (step S204). Specifically, the control unit 22 estimates the scene showing the highest probability of occurrence of each of going straight, turning right, turning left, changing to the right lane, and changing to the left lane as the driving behavior that the driver is about to perform. After step S204, the control unit 22 ends the driving behavior estimation routine RT2.

[0096] 7 is a flowchart showing the intention determination processing routine RT3 executed by the control unit 22 of the in-vehicle device 10. The control unit 22 starts the intention determination processing routine RT3, for example, when the in-vehicle device 10 is powered on. Note that the intention determination processing routine RT3 is repeatedly executed by the control unit 22 as long as the in-vehicle device 10 is powered on.

[0097] First, the control unit 22 determines whether the driving behavior estimated by the driving behavior estimation routine RT2 is a lane change (a right lane change or a left lane change) (step S301). If the control unit 22 determines that the estimated driving behavior is not a lane change (step S301: NO), that is, if the estimated driving behavior is going straight, turning right, or turning left, the control unit 22 ends the intention determination processing routine RT3.

[0098] When the control unit 22 determines that the estimated driving behavior is a lane change (step S301: YES), it determines whether the score of the lane change calculated by the score calculation formula is equal to or greater than a first threshold (step S302). In this embodiment, as described above, it determines whether the estimated probability of a lane change is equal to or greater than the first threshold.

[0099] When the control unit 22 determines that the probability of a lane change is not equal to or greater than the first threshold (step S302: NO), that is, when the control unit 22 determines that the probability of a lane change occurring is low because the probability of a lane change does not meet the first threshold, it terminates the intention determination processing routine RT3.

[0100] When the control unit 22 determines that the probability of a lane change is equal to or greater than the first threshold (step S302: YES), it determines that the driver has an intention to change lanes (step S303). That is, the control unit 22 determines that the driver has an intention to change lanes.

[0101] After step S303, the control unit 22 determines whether the lane change score calculated by the score calculation formula is equal to or greater than the second threshold (step S304). In this embodiment, as described above, it determines whether the estimated lane change probability is equal to or greater than the second threshold.

[0102] When the control unit 22 determines that the probability of changing lanes is equal to or greater than the second threshold (step S304: YES), it determines that the driver has decided to change lanes (step S305). That is, the control unit 22 determines that the driver has decided to change lanes.

[0103] The control unit 22 determines that the probability of lane change is not equal to or greater than the second threshold (step S304: NO), or outputs a notification according to the determination result of the lane change state after step S305 (step S306). That is, the control unit 22 changes the notification to be output to the driver depending on whether the driver has an intention to change lanes or has made a decision about the intention to change lanes.

[0104] For example, as described above, when the control unit 22 determines that the driver has an intention to change lanes, it outputs a notice such as "The next lane is a left turn, so please keep in the left lane without changing to the right lane" while the driver is setting a destination. Also, for example, when the control unit 22 determines that the driver has decided to change lanes, it outputs a simple warning such as "Please be careful of surrounding vehicles."

[0105] The control unit 22 outputs a notice according to the result of the above determination in step S306, and then ends the intention determination processing routine RT3.

[0106] According to this embodiment, the behavior monitoring routine RT1 and the driving behavior estimation routine RT2 described above make it possible to estimate what driving behavior the driver is about to perform based on the behavior of the driver of the vehicle M, the behavior of the vehicle M, and the situation around the vehicle M. In other words, by using the score calculation formula described above, it is possible to instantly estimate the driving behavior of the driver without setting a learning period for the pattern of preparatory movements for driving behavior.

[0107] Furthermore, according to this embodiment, the above-described intention determination processing routine RT3 can change the content of the information output to the driver depending on whether the driver has an intention to change lanes or has decided to change lanes. Therefore, according to this embodiment, it is possible to provide services according to the current situation at appropriate timing.

[0108] In particular, if a driver receives a notification when he or she has already decided to change lanes, he or she can change his or her driving behavior in response to the notification because there is sufficient time before the actual lane change. Also, if a driver receives a notification when he or she has already decided to change lanes, he or she can accept only a simple notification because he or she has already decided to change lanes, and can avoid feeling annoyed by notifications urging him or her to change his or her driving behavior.

[0109] Therefore, according to this embodiment, the driving behavior of the driver can be estimated instantaneously without requiring a long learning period, and driving assistance can be provided to the driver at an appropriate timing.

[0110] [Examples of changes in each score] Here, the change in the score for each scene calculated by the score calculation formula described above will be described with reference to FIG. 8. FIG. 8 shows the change in the score for each scene calculated by the probability calculation formula (f n 8 is a graph showing the change over time in the probability for each scene calculated by the following equation. In Fig. 8, the horizontal axis represents time and the vertical axis represents probability (%).

[0111] In addition, in Figure 8, the two-dot chain line indicates the probability change of the above-mentioned "going straight (f1)", the one-dot chain line indicates the probability change of the above-mentioned "turning right (f2)", the dashed line indicates the probability change of the above-mentioned "turning left (f3)", the solid line indicates the probability change of the above-mentioned "changing lane to the right (f4)", and the dotted line indicates the probability change of the above-mentioned "changing lane to the left (f5)". In Figure 8, the probability threshold Th1 as the above-mentioned first threshold is set to 40%. Furthermore, the probability threshold Th2 as the above-mentioned second threshold is set to 70%.

[0112] 8, the control unit 22 determines that the driver has an intention to change lanes when the probability of changing lanes to the right exceeds a threshold value Th1. In this embodiment, the point P1 where the probability of changing lanes to the right and the threshold value Th1 overlap is the intention generation point P1 at which it is determined that the driver has an intention to change lanes.

[0113] 8, the control unit 22 determines that the driver has decided to change lanes when the probability of changing lanes to the right exceeds a threshold value Th2. In this embodiment, the point P2 where the probability of changing lanes to the right and the threshold value Th2 overlap is the decision point P2 at which it is determined that the driver has decided to change lanes.

[0114] In this embodiment, the control unit 22 determines that a lane change has been performed based on the behavior of the vehicle M, and ends the calculation of the probability for each scene. For example, in FIG. 8, the control unit 22 determines that a right lane change has been performed at point P3, and resets the monitoring period for the mirror checking behavior described above, thereby newly calculating the probability for each scene. In this embodiment, the above-mentioned point P3 is the time point P3 when the lane change was performed.

[0115] As described above, the control unit 22 of the in-vehicle device 10 calculates a score for each driving behavior scene, and when the driving behavior is estimated to be a lane change based on a comparison of the scores, the control unit 22 can determine the current state based on the above-mentioned threshold value.

[0116] In this embodiment, the control unit 22 calculates a probability indicating the feasibility of each driving behavior scene as a score, and estimates the scene with the highest probability as the driver's driving behavior, but the manner of estimating the driving behavior is not limited to this. For example, the control unit 22 may calculate a score regarding the possibility that each driving behavior scene will not be performed, and estimate the scene with the lowest score as the driving behavior the driver will attempt to perform next. In other words, it is sufficient that the scores calculated for each driving behavior scene can be compared with each other.

[0117] Furthermore, in this embodiment, the scores for five driving behavior scenes, "1. Going straight," "2. Turning right," "3. Turning left," "4. Changing lanes to the right," and "5. Changing lanes to the left," are calculated and compared with each other. However, the types of scenes are not limited to this as long as the scores of lane changes can be compared with other scenes. For example, scenes of "stopping" and "driving slowly" may be provided in addition to the above. Furthermore, for example, as a course change other than a lane change, movement within the same lane, such as pulling left when turning left, may be added to the above scenes.

[0118] In this embodiment, the control unit 22 detects the driver's checking behavior in the rearview mirror RM, the right side mirror RS, and the left side mirror LS based on the direction of the driver's line of sight and the relative positions of the rearview mirror RM, the right side mirror RS, and the left side mirror LS with respect to the driver's viewpoint, but this is not limited to this. For example, the control unit 22 may detect the driver's checking behavior in the mirror based on the direction of the driver's face, or may detect the mirror checking behavior by taking into account the driver's movement to directly check outside the window, etc.

[0119] In this embodiment, the level of each evaluation element related to mirror checking behavior shown in the evaluation index TB1 is acquired, and the score is calculated based on the evaluation index corresponding to the level. However, it is not necessary to use all the evaluation elements shown in the evaluation index TB1. The control unit 22 may use at least "mirror checking frequency X" as the mirror checking behavior. a " and "Mirror Check Interval X b It is sufficient if the above score can be calculated based on the above.

[0120] In this embodiment, the level of each evaluation element shown in the evaluation index TB2 described above is obtained, and a score is calculated based on the evaluation index corresponding to that level. However, the evaluation elements shown in the evaluation index TB2 are merely an example, and the number of evaluation elements may be increased or decreased.

[0121] For example, as another evaluation element, the steering angle when the driver operates the steering wheel may be acquired, and the evaluation index may be determined according to a change in the steering angle. Furthermore, for example, the in-vehicle device 10 may be equipped with a distance sensor capable of measuring the distance between the host vehicle and another vehicle, and the evaluation index may be determined according to the distance between the host vehicle and another vehicle. Furthermore, for example, the speed of the vehicle M may be calculated based on the acceleration measured by the acceleration sensor 17, and the evaluation index may be determined according to a change in the speed.

[0122] In this embodiment, the heart rate is measured as the biological information of the driver acquired by the biological sensor 18, but this is not limited thereto, and the respiratory rate and blood pressure of the driver may also be measured, and the evaluation index may be determined according to changes in the respiratory rate and blood pressure. Note that the biological sensor 18 may be a wearable device that can be worn by the driver of the vehicle M.

[0123] Furthermore, for example, when the in-vehicle device 10 is powered on, the driver's driving history may be input as pre-registered information to the touch panel display 12. For example, an evaluation index may be determined according to the length of the driving history.

[0124] In this embodiment, the levels of each of the evaluation elements shown in the above-mentioned evaluation index TB1 and evaluation index TB2 are obtained, and a score corresponding to each of multiple driving actions is calculated based on the evaluation index corresponding to that level.If the score satisfies a predetermined condition, the driver is identified as having the intention to change lanes.However, the evaluation index used to calculate the score after it is identified that the driver has the intention to change lanes may be changed from the evaluation index used to calculate the score before it is identified that the driver has the intention to change lanes.

[0125] Specifically, the evaluation index DB26A of the large-capacity storage device 26 stores, as evaluation index TB1, evaluation index TB1a used to calculate the score before it is determined that the driver has the intention to change lanes, and evaluation index TB1b used to calculate the score after it is determined that the driver has the intention to change lanes, and which has different content from evaluation index TB1a.

[0126] In addition, the evaluation index DB26A stores, as evaluation index TB2, evaluation index TB2a used to calculate the score before it is determined that the driver has the intention to change lanes, and evaluation index TB2b used to calculate the score after it is determined that the driver has the intention to change lanes, and which has different content from evaluation index TB2a.

[0127] For example, the control unit 22 calculates a score corresponding to each of the multiple driving actions by referring to the evaluation index TB1a and the evaluation index TB2a until it determines that the driver has the intention to change lanes, and after it determines that the driver has the intention to change lanes, it calculates a score corresponding to each of the multiple driving actions by referring to the evaluation index TB1b and the evaluation index TB2b.

[0128] After the driver has the intention to change lanes, changes occur in the behavior of the driver and the vehicle, such as the driver checking the mirrors more frequently to find a timing when the lane change is feasible, increasing the distance between the vehicle and the vehicle ahead, etc. Therefore, for example, by using evaluation index TB1b and evaluation index TB2b that are weighted more heavily to the driver and vehicle behavior specific to lane changes after it has been determined that the driver has the intention to change lanes, it is possible to more accurately determine whether the driver has subsequently decided to change lanes.

[0129] In this embodiment, the levels of each of the evaluation elements shown in the above-mentioned evaluation index TB1 and evaluation index TB2 are obtained, and if the lane change score calculated based on the evaluation index corresponding to that level is equal to or greater than the second threshold, it is determined that the driver has made a decision to change lanes; however, the determination that the driver has made a decision to change lanes may also be made without using the second threshold.

[0130] Specifically, the evaluation index DB 26A of the mass storage device 26 stores, as the evaluation index TB1, an evaluation index TB1c used in calculating a score for determining whether the driver has an intention to change lanes, and an evaluation index TB1d that gives more weight to the driver's behavior that is specific to changing lanes than the evaluation index TB1c. The evaluation index DB 26A also stores, as the evaluation index TB2, an evaluation index TB2c used in calculating a score for determining whether the driver has an intention to change lanes, and an evaluation index TB2d that gives more weight to the driver's behavior that is specific to changing lanes than the evaluation index TB2c.

[0131] The control unit 22 acquires the levels of the evaluation elements corresponding to the evaluation indexes TB1c, TB2c, TB1d, and TB2d, respectively, and calculates a score based on the evaluation indexes corresponding to the levels. That is, the control unit 22 simultaneously calculates a first score based on the evaluation indexes for identifying that the driver has an intention to change lanes, and a second score based on the evaluation indexes that more heavily weight the driver and vehicle behaviors specific to lane changes.

[0132] Then, when the first score exceeds the first threshold value, it is determined that the driver has decided to change lanes, and then when the second score exceeds the first score, it is determined that the driver has decided to change lanes.

[0133] In addition to lane changes, other course changes, including right and left turns, can also be determined using a similar method to determine whether a decision to change course has been made. Even in this method, for example, by using an evaluation index that assigns more weight to the driver's or vehicle's behavior specific to lane changes, it is possible to more accurately determine whether a decision to change lane has been made.

[0134] In this embodiment, as described above, the control unit 22 sequentially estimates the driver's driving behavior by comparing the scores calculated for each scene with each other, but an embodiment may also be adopted in which the calculated score is multiplied by a coefficient to correct a driving behavior that has a strong or weak causal relationship with the immediately preceding estimated driving behavior. For example, if the immediately preceding estimated driving behavior is a right lane change, the control unit 22 may determine that the driving behavior is related to overtaking and increase the score for "left lane change" when estimating the next driving behavior.

[0135] Also, for example, if the driving behavior estimated immediately before was a left lane change, the control unit 22 may determine that there is a low possibility of changing left lanes again, and may lower the score for "left lane change" when estimating the next driving behavior.

[0136] In this embodiment, the above-described estimation process of the driver's driving behavior and the process of determining the driver's intention when estimating a lane change are performed by the in-vehicle device 10 mounted on the vehicle M as a moving body, but the configuration of the device is not limited to this as long as it is capable of performing the processes. For example, the configuration of the in-vehicle device 10 may be applied to a portable communication terminal such as a smartphone or tablet terminal that can communicate with the in-vehicle device 10.

[0137] Specifically, for example, when the in-vehicle device 10 detects a mirror checking behavior, the in-vehicle device 10 may be able to sequentially transmit data indicating the state and numerical values ​​of each of the above-mentioned evaluation elements to the communication terminal. The communication terminal may receive the data, calculate a score for each scene, and transmit the results of an estimation of the driving behavior based on the score calculated for each scene to the in-vehicle device 10.

[0138] In addition, when the estimated driving behavior is a lane change, the communication terminal may be configured to execute the above-mentioned intention determination process based on the score of the lane change, and transmit the current state of the lane change to the in-vehicle device 10 as a result of executing the intention determination process.

[0139] In addition, the evaluation index DB26A and map information DB26B stored in the large-capacity storage device 26 of the in-vehicle device 10 may be stored in a server device that can communicate with the in-vehicle device 10, and the server device may receive data indicating the status and numerical values ​​of each of the above-mentioned evaluation elements that are sequentially transmitted from the in-vehicle device 10, thereby estimating the driver's driving behavior.

[0140] In addition, in this embodiment, an example has been described in which the on-board device 10 estimates a lane change as the driver's driving behavior, but this is not limited to this, and the on-board device 10 may estimate a driving behavior related to a course change including at least one of a right turn, a left turn, a right lane change, and a left lane change as the driving behavior that the driver is going to perform next.

[0141] [Application of Example 1] An application example of the first embodiment will be described below. First, the overall system configuration will be described. FIG. 9 is a diagram showing the configuration of a difficulty level identification system 100 according to the application example. As shown in FIG. 9, the difficulty level identification system 100 includes a server device 30 and an in-vehicle device 10 mounted in each of a plurality of vehicles M. The number of in-vehicle devices 10 constituting the difficulty level identification system 100 may be any number as long as the system capacity allows.

[0142] In the difficulty level identification system 100, the in-vehicle device 10 and the server device 30 can transmit and receive data to and from each other via a network NW using a communication protocol such as TCP / IP. The connection between the server device 30 and the network NW can be established by mobile communication such as 4G (4th Generation) or 5G (5th Generation), or wireless communication such as Wi-Fi (registered trademark).

[0143] 10 is a block diagram showing an example of the configuration of a server device 30 according to this application example. In this application example, the server device 30 is a device in which a control unit 32, a communication unit 33, and a large-capacity storage device 34 cooperate with each other via a system bus 31.

[0144] The control unit 32 is configured with a CPU 32A, a ROM 32B, a RAM 32C, etc., and functions as a computer. The CPU 32A reads and executes various programs stored in the ROM 32B and the mass storage device 34, thereby realizing various functions.

[0145] The communication unit 33 is a communication device that transmits and receives data to and from external devices in accordance with instructions from the control unit 32. The communication unit 33 is, for example, a NIC for connecting to a network.

[0146] The various programs described above may be obtained, for example, from another server device or the like via a network, or may be recorded on a recording medium and read via various drive devices. That is, the various programs stored in the mass storage device 34 (including a program for executing processing in the server device 30, which will be described later) can be transmitted via a network, or can be recorded on a computer-readable recording medium and transferred.

[0147] The mass storage device 34 is configured by, for example, a hard disk drive, an SSD, a flash memory, etc., and is a storage device that stores various programs such as an operating system and terminal software. As in the first embodiment, the mass storage device 34 stores an evaluation index DB 34A and a map information DB 34B.

[0148] In this application example, the control unit 32 of the server device 30 is configured to be able to sequentially acquire, via communication with the in-vehicle device 10, information indicating the driver's mirror checking behavior, image information captured by the in-vehicle camera 15 and the in-vehicle camera system 16S, position information of the vehicle M, behavior information of the vehicle M, etc., which are sequentially transmitted from the in-vehicle device 10.

[0149] In this application example, the control unit 32 acquires the above information sequentially transmitted from the in-vehicle device 10, calculates a score for each of the above scenes based on the evaluation index TB1 and evaluation index TB2 stored in the evaluation index DB 34A of the mass storage device 34, and estimates the driver's driving behavior based on the score. That is, in this application example, the control unit 32 of the server device 30 executes the above-mentioned behavior monitoring routine RT1 and driving behavior estimation routine RT2.

[0150] In this application example, when the driving behavior estimation routine RT2 estimates that the driver's driving behavior is a lane change, the control unit 32 determines whether the driver has an intention to change lanes based on whether the probability indicating the feasibility of a lane change is equal to or greater than a first threshold. The control unit 32 also determines whether the driver has decided to change lanes based on whether the probability indicating the feasibility of a lane change is equal to or greater than a second threshold. That is, the control unit 32 functions as an intention determination processing unit that executes a lane change intention determination process.

[0151] In this application example, the control unit 32 identifies an intention occurrence time point P1 as the point at which the driver has an intention to change lanes, based on the score for the lane change, as shown in Fig. 8. That is, the control unit 32 functions as an intention occurrence time point identifying unit.

[0152] In this application example, the control unit 32 identifies a decision point P2 as the point at which the driver decides to change lanes, based on the score for the lane change. That is, the control unit 32 functions as a decision point identifying unit.

[0153] Furthermore, in this application example, the control unit 32 identifies an execution time point P3 as the point at which the estimated lane change was executed, based on the behavior of the vehicle M. That is, the control unit 32 functions as an execution time point identification unit.

[0154] In this application example, the control unit 32 determines the difficulty level of lane changes at the location where the driver makes one lane change based on the results of determining the intention occurrence time P1, decision time P2, and execution time P3 described above.

[0155] Specifically, the control unit 32 records the time of intention generation time P1, the time of decision time P2, and the time of execution time P3, and calculates a time length T1 indicating the time length from intention generation time P1 to decision time P2, and a time length T2 indicating the time length from decision time P2 to execution time P3. Based on the acquired time lengths T1 and T2, the control unit 32 identifies the difficulty level of lane changes at the location where the driver made one lane change.

[0156] In this application example, the control unit 32 creates a difficulty level map that indicates the difficulty level of lane changes for each predetermined section of the road on the map, based on the lane change difficulty level identified for each of the multiple vehicles M. More specifically, the control unit 32 statistically processes the difficulty level determined based on the time lengths T1 and T2 acquired from the multiple vehicles M that attempted to change lanes in each predetermined section of the road, thereby identifying the difficulty level of lane changes in the predetermined section, and creates the difficulty level map by associating the predetermined section with the identified lane change difficulty level and storing them in the map information DB 34B.

[0157] Here, the difficulty level map will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of a difficulty level map created by the control unit 32. Fig. 11 shows the difficulty level of lane changes for each predetermined section on a certain expressway (the arrow in the figure indicates the direction of travel).

[0158] In FIG. 11, for section A1 where merging from ramp RA to main road ML occurs, the control unit 32 sets the difficulty of lane changing in section A1 as high, for example, based on data obtained indicating that lane changing is difficult or impossible for multiple vehicles.

[0159] Also, in Figure 11, for section A2, which is the section after section A1, the control unit 32 sets the difficulty of lane changes in section A2 to be medium, for example, based on the data obtained indicating that lane changes took time but were feasible for multiple vehicles.

[0160] Also, in Figure 11, for section A3, which is the section just before section A1, the control unit 32 sets the difficulty of lane changes in section A3 to be low, for example, based on the fact that data has been obtained indicating that lane changes can be easily performed by multiple vehicles.

[0161] For example, when the driver of vehicle M changes lanes in the current road section, the control unit 32 of the server device 30 acquires the above-mentioned time lengths T1 and T2, and compares them with the time lengths T1 and T2 for each difficulty level shown in the difficulty map created above, thereby evaluating the current driver's driving ability.

[0162] For example, if the control unit 32 determines that the time length T1 and time length T2 of the lane change performed by the driver in the current section are longer than the time length T1 and time length T2 indicated by the difficulty of the lane change in the same section in the difficulty map, i.e., if it determines that the driver's driving ability is inferior to the standard, it can issue a notification according to the determination result.

[0163] Specific operations of the server device 30 in this application example will be described below with reference to Figures 12 and 13. Figures 12 and 13 are flowcharts showing a difficulty level identification routine RT4 executed by the control unit 32 of the server device 30. In the following description, the behavior monitoring routine RT1 and the driving behavior estimation routine RT2 are the same as those in the first embodiment, and therefore will not be described again.

[0164] The control unit 32 starts the difficulty level identification routine RT4, for example, when power is turned on to the in-vehicle device 10. Note that the difficulty level identification routine RT4 is repeatedly executed by the control unit 32 as long as the in-vehicle device 10 is powered on.

[0165] First, as in the first embodiment, when the estimation result is a lane change, the control unit 32 determines whether the score of the lane change is equal to or greater than a first threshold (step S302), and if it determines that the score is equal to or greater than the first threshold (step S302: YES), it determines that the driver has an intention to change lanes and records the time at which this occurred (step S403). That is, the control unit 32 identifies the point at which the probability as the score of the lane change exceeds the first threshold as the intention occurrence time P1, and records the time at which this occurred.

[0166] After step S403, the control unit 32 determines whether the lane change score is equal to or greater than the second threshold (step S304), as in the first embodiment, and if it determines that the score is equal to or greater than the second threshold (step S304: YES), it determines that the driver has made a decision to change lanes, and records the time at which this decision was made (step S405). That is, the control unit 32 identifies the point at which the probability as the lane change score exceeds the second threshold as the decision time P2, and records the time at which this decision was made.

[0167] After step S405, the control unit 32 determines whether the estimated lane change has been executed (step S406). Specifically, the control unit 32 determines whether the vehicle M has moved from the current lane to an adjacent lane based on the behavior of the vehicle M. For example, when a right lane change is estimated, the control unit 32 determines that a right lane change has been executed by acquiring that the driver has operated the steering wheel and that the acceleration in the right direction relative to the traveling direction of the vehicle M exceeds a predetermined value.

[0168] When the control unit 32 determines that the estimated lane change has been executed (step S406: YES), it records the time when the lane change was executed (step S407). That is, the control unit 32 identifies the point where the lane change was executed based on the behavior of the vehicle M as the execution time point P3, and records the time at which this occurred.

[0169] When the control unit 32 determines that the estimated lane change has not been performed (step S406: NO), it determines whether a predetermined time has elapsed (step S408). Specifically, when the probability of lane change is less than the second threshold, the control unit 32 determines whether a predetermined time has elapsed since the intention time P1, and when the probability of lane change is equal to or greater than the second threshold, it determines whether a predetermined time has elapsed since the decision time P2.

[0170] If the control unit 32 determines that the predetermined time has not elapsed (step S408: NO), it executes step S406 again to determine whether the estimated lane change has been performed. If the control unit 32 determines that the predetermined time has elapsed (step S408: YES) or after step S407, it identifies the difficulty level of the lane change at the location where the driver of the vehicle M performed one lane change based on each of the recorded times (step S409).

[0171] Specifically, when an estimated lane change is executed, the control unit 32 acquires a time length T1 indicating the time length from the intention generation time P1 to the decision time P2, and a time length T2 indicating the time length from the decision time P2 to the execution time P3, as described above. Based on the acquired time lengths T1 and T2, the control unit 32 determines the difficulty level of the lane change at the location where the driver executed one lane change.

[0172] For example, if the time length T1 is longer than a first threshold value as a predetermined time length and the time length T2 is longer than a second threshold value as a predetermined time length, the control unit 32 determines that the difficulty of the lane change at the location where the lane change was made is high.

[0173] In this application example, if it is determined in step S408 that a predetermined time has elapsed, i.e., if the execution point P3 described above has not been identified, the control unit 32 determines that the driver has an intention to change lanes or that the driver has decided to change lanes but ultimately abandoned the lane change.

[0174] In this application example, when the control unit 32 determines that the lane change has been abandoned, it identifies the location where the lane change was abandoned, i.e., the location a predetermined time after the intention-to-change point P1 or the decision-to-change point P2, as being of high difficulty.

[0175] After step S409, the control unit 32 associates the vehicle ID assigned to each vehicle M for identifying each vehicle M, the position where the lane change was performed or the position where the lane change was abandoned, and the difficulty level of the lane change at that position, and stores them in the mass storage device 34 (step S410). After step S410, the control unit 32 ends the difficulty level identification routine RT4.

[0176] According to this application example, the control unit 32 can create the difficulty map described above based on the lane change difficulty level determined for each of the multiple vehicles M by the difficulty level determination routine RT4 described above. Furthermore, the control unit 32 can evaluate the current driving ability of the driver of the vehicle M by comparing the time lengths T1 and T2 acquired when the driver of the vehicle M makes one lane change with the time lengths T1 and T2 for each difficulty level shown in the difficulty level map. Furthermore, the control unit 32 can notify the driver of the evaluation result via the in-vehicle device 10.

[0177] For example, if it is determined that the time lengths T1 and T2 of the lane change performed by the driver in the current section are longer than the time lengths T1 and T2 indicated by the difficulty of lane changes in the same section in the difficulty map, i.e., if the current lane change is relatively difficult compared to the difficulty of lane changes in the same section, the control unit 32 can output a congratulatory announcement such as "That was tough" via the in-vehicle device 10.

[0178] Also, for example, in the above case, the control unit 32 can prompt the driver of the vehicle M to take a break earlier than normal. Specifically, the control unit 32 can make a notification according to the current situation via the in-vehicle device 10, for example, by shortening the time to take a break from two hours of driving to one and a half hours.

[0179] Furthermore, for example, if a situation occurs frequently where a predetermined time has passed since the above-mentioned intention generation point P1 and decision point P2, i.e., if the driver frequently gives up on changing lanes, the driver's ability to grasp his or her surroundings is deemed to be low, and the driver's driving skill evaluation can be lowered and support can be provided according to the evaluation results.

[0180] [An example of criteria for determining the difficulty of changing lanes] Here, an example of difficulty determination criteria used by the control unit 32 to determine the difficulty of a lane change will be described with reference to Fig. 14. Fig. 14 is an example of a table TB3 (hereinafter referred to as difficulty determination criteria TB3) showing criteria for determining the difficulty of a lane change at a location where one lane change is made by the driver of vehicle M.

[0181] In the difficulty determination standard TB3, for example, when the time length T1 is 5 seconds or less and the time length T2 is 3 seconds or less, the difficulty of changing lanes is determined to be low (score 1).

[0182] In addition, in the difficulty determination standard TB3, for example, if the above-mentioned time length T1 is more than 5 seconds and less than 10 seconds, and the time length T2 is more than 3 seconds and less than 8 seconds, the difficulty of changing lanes is determined to be medium (score 2).

[0183] In addition, in the difficulty determination standard TB3, for example, when the time length T1 exceeds 10 seconds and the time length T2 exceeds 8 seconds, the difficulty of changing lanes is determined to be high (score 3).

[0184] In this manner, in this application example, the difficulty level of changing lanes is determined based on the acquired time lengths T1 and T2.

[0185] [Example of recorded data related to lane changes] FIG. 15 is a diagram showing a table TB4 of recorded data relating to lane changes stored for each vehicle in the mass storage device 34 of the server device 30 (hereinafter referred to as recorded data TB4).

[0186] In the recorded data TB4, the "Location" field indicates the name of the road, such as "near the △□ IC on the outbound lane of the ○× Expressway." The "Vehicle ID" field indicates the vehicle ID assigned to each vehicle to identify it.

[0187] The items "intention generation time," "decision time," and "execution time" indicate the time at the intention generation time P1, the time at the decision time P2, and the time at the execution time P3, respectively.

[0188] The "execution interval" item indicates the interval in the "location" mentioned above. The "duration T1" item indicates the time difference between the "intention occurrence time" and the "decision time". The "duration T2" item indicates the time difference between the "decision time" and the "execution time".

[0189] The "Difficulty" item indicates the difficulty of changing lanes as a result of comparing the "time length T1" and the "time length T2" with the difficulty determination standard TB3. For example, as described above, when the time length T1 is 5 seconds or less and the time length T2 is 3 seconds or less, the control unit 32 determines that the difficulty of changing lanes is low (score 1).

[0190] In this application example, the control unit 32 can create the difficulty level map described above based on the data relating to lane changes recorded in the recorded data TB4 described above.

[0191] In this application example, the difficulty level determination criteria shown in the above-mentioned difficulty level determination criteria TB3 are merely an example, and the determination criteria may be set arbitrarily. For example, in the difficulty level determination criteria TB3, the difficulty level of lane changes is shown in three levels of scores 1 to 3, but this is not limitative. For example, the score may be further increased.

[0192] In this application example, the control unit 32 determines that a lane change has not been made when a predetermined time has passed since the intention generation time P1 or the decision time P2, but the determination method is not limited to this. For example, the control unit 32 may determine that a lane change has not been made when a predetermined distance has been moved from the position of the intention generation time P1 or the position of the decision time P2 based on the position information of the vehicle M.

[0193] In this application example, the control unit 32 determines the difficulty of changing lanes by comparing the acquired time lengths T1 and T2 with the difficulty determination criterion TB3, but the determination criterion may also be changed depending on the type of vehicle.

[0194] For example, large trucks and large trailers may take longer to change lanes than standard vehicles. Therefore, a difficulty level determination criterion TB3 may be created for each vehicle type, and for example, when the vehicle type is acquired from the in-vehicle device 10 of the vehicle M, the difficulty level determination criterion according to the current vehicle type may be applied.

[0195] In this application example, the control unit 32 creates a lane-changing difficulty map based on the lane-changing difficulty level identified for each of the multiple vehicles M. However, the control unit 32 may also create difficulty maps by day of the week or time of day. Creating difficulty maps that reflect differences in traffic volume by day of the week or time of day allows for more accurate driving evaluation.

[0196] In this application example, the server device 30 acquires information indicating the driver's mirror checking behavior sequentially transmitted from the in-vehicle device 10, image information captured by the in-vehicle camera 15 and the in-vehicle camera system 16S, position information of the vehicle M, behavior information of the vehicle M, etc., and estimates the driver's driving behavior. However, the in-vehicle device 10 may estimate the driver's driving behavior and transmit to the server device 30 the position information of the vehicle M when a lane change is estimated as the driving behavior, as well as the above-mentioned time lengths T1 and T2.

[0197] The control routines shown in the above-described first embodiment and the application example of the first embodiment are merely examples, and can be appropriately selected and changed depending on the application or conditions of use. [Explanation of symbols]

[0198] 10 Onboard equipment 12 Touch panel display 13 speakers 14 GNSS receivers 15 In-car camera 16. Front camera 17 Acceleration Sensor 18 Biometric sensors 21, 31 System Bus 22, 32 Control unit 23, 33 Communications Department 24 Input section 25 Output section 26, 34 mass storage device 30 Server device

Claims

1. a mirror confirmation information acquisition unit that acquires a mirror confirmation frequency indicating a frequency at which a driver of a vehicle checks a mirror and a mirror confirmation interval indicating a time interval from when the driver checks the mirror until when the driver checks the mirror again; an intention determination unit that performs an intention determination process, including a determination as to whether the driver has an intention to change course, based on the mirror confirmation frequency and the mirror confirmation interval within a first period; The information processing device is characterized in that the intention determination unit performs the intention determination processing using a first group of evaluation indexes consisting of a plurality of evaluation indexes determined by the mirror check frequency and each corresponding to each driving behavior including lane changes, and a second group of evaluation indexes consisting of a plurality of evaluation indexes determined by the mirror check interval and each corresponding to each driving behavior including lane changes.

2. The information processing device described in Claim 1, characterized in that the intention determination unit substitutes the first group of evaluation indicators and the second group of evaluation indicators into a mathematical formula to calculate multiple scores, each corresponding to a driving behavior including a course change, and performs the intention determination processing based on the multiple scores.

3. 3. The information processing apparatus according to claim 1, wherein the intention determination process includes determining whether or not a decision has been made regarding the intention.

4. an output unit that outputs a notification to the driver based on a result of the intention determination process; The information processing device according to claim 3, characterized in that the output unit outputs different types of notification when the intention determination unit determines that the driver has an intention to change course and when it determines that a decision has been made regarding the intention.

5. The information processing device according to claim 2, characterized in that the intention determination unit performs the intention determination processing when the relationship between the score corresponding to a course change and the score corresponding to another driving action among the multiple scores is a predetermined relationship.

6. a vehicle behavior information acquisition unit that acquires vehicle behavior information indicating the behavior of the vehicle; 6. The information processing apparatus according to claim 1, wherein the intention determination unit performs the intention determination process based on the vehicle behavior information.

7. a location information acquisition unit that acquires location information indicating a current location of the vehicle; 7. The information processing apparatus according to claim 1, wherein the intention determination unit performs the intention determination process based on the position information.

8. a surrounding situation information acquisition unit that acquires surrounding situation information indicating a situation around the vehicle; 8. The information processing apparatus according to claim 1, wherein the intention determination unit performs the intention determination process based on the surrounding situation information.

9. 9. The information processing device according to claim 1, further comprising a biometric information acquisition unit that acquires biometric information of the driver of the vehicle, and the intention determination unit performs the intention determination process based on the biometric information.

10. An information processing method executed by an information processing device, a mirror confirmation information acquisition step in which a mirror confirmation information acquisition unit acquires a mirror confirmation frequency indicating a frequency at which a driver of a vehicle checks a mirror and a mirror confirmation interval indicating a time interval from when the driver checks the mirror until when the driver checks the mirror again; an intention determination step in which an intention determination unit performs an intention determination process including a determination as to whether or not the driver has an intention to change course based on the mirror confirmation frequency and the mirror confirmation interval within a first period; An information processing method characterized in that the intention determination unit performs the intention determination processing using a first group of evaluation indexes consisting of a plurality of evaluation indexes determined by the mirror check frequency and each corresponding to each driving behavior including lane changes, and a second group of evaluation indexes consisting of a plurality of evaluation indexes determined by the mirror check interval and each corresponding to each driving behavior including lane changes.

11. A program to be executed by a computer, a mirror confirmation information acquisition step in which a mirror confirmation information acquisition unit acquires a mirror confirmation frequency indicating a frequency at which a driver of a vehicle checks a mirror and a mirror confirmation interval indicating a time interval from when the driver checks the mirror until when the driver checks the mirror again; an intention determination step in which an intention determination unit performs an intention determination process including a determination as to whether or not the driver has an intention to change course based on the mirror confirmation frequency and the mirror confirmation interval within a first period; The intention determination unit performs the intention determination process using a first group of evaluation indexes, which are determined by the mirror check frequency and consist of a plurality of evaluation indexes, each of which corresponds to a driving behavior including a lane change, and a second group of evaluation indexes, which are determined by the mirror check interval and consist of a plurality of evaluation indexes, each of which corresponds to a driving behavior including a lane change.

12. A recording medium storing the program according to claim 11.

Images