Driving assistance systems
The driver assistance system uses object and evasive driving detection to assess concentration levels and provide effective notifications, addressing the inaccuracies of existing systems in detecting reduced focus and enhancing safe driving.
Patent Information
- Application Number
- JP2023145663
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2023-09-07
- Publication Date
- 2026-11-11
- Estimated Expiration
- 2043-09-07
AI Technical Summary
Existing driving assistance devices struggle to accurately detect a decrease in a driver's level of concentration on driving, particularly when the driver is looking at potential risk objects without recognizing them as hazards, and fail to provide effective notifications to encourage safe driving.
A driver assistance system that includes an object detection unit to identify hazardous objects, an evasive driving detection unit to analyze driving maneuvers, and a concentration level determination unit to assess the driver's focus based on evasive driving characteristics, issuing notifications when concentration is detected to be low.
The system accurately determines a decrease in driver concentration by analyzing evasive driving behaviors, providing targeted notifications that enhance safe driving practices without causing annoyance, thus improving driving safety.
Smart Images

Figure 0007948112000001 
Figure 0007948112000002 
Figure 0007948112000003
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to a driving assistance device that assists a driver in driving. BACKGROUND ART
[0002] As an example of a driving assistance device, Patent Document 1 describes an alarm system that detects a driver's consciousness level and the like, and issues an alarm to the driver according to the situation. This driving assistance device performs image processing on an image of the driver's face captured by an in-vehicle camera or the like, detects a change in the opening / closing time of the eyelids during blinking or the direction of the line of sight, and detects the driver's consciousness level based on the inattentive driving state. PRIOR ART DOCUMENTS PATENT DOCUMENTS
[0003] PATENT DOCUMENT 1 Japanese Unexamined Patent Application Publication No. 2003-317197 SUMMARY OF THE INVENTION PROBLEMS TO BE SOLVED BY THE INVENTION
[0004] However, as a result of detailed studies by the inventors, it has been found that the driving assistance device described in Patent Document 1 has the following problems. (i) In image processing using an in-vehicle camera, the target object at which the driver is directing their line of sight may not be stably detected. In particular, the farther the driver directs their line of sight, the more difficult it becomes to determine what the driver is specifically looking at. (ii) Even when a target object that poses a risk of causing an accident (hereinafter referred to as "risk target object") exists in the direction of the driver's line of sight, the driver may only be staring blankly in that direction and may not recognize it as a risk target object. (iii) Even when the driver recognizes the risk target object in the direction of their line of sight, the safety awareness for avoiding the risk target object may be reduced, for example, due to haste caused by a trouble or the like.
[0005] The driver assistance device described in Patent Document 1 may not be able to accurately detect a decrease in the driver's level of awareness, i.e., their level of concentration on driving, due to the problems described in (i), (ii), and (iii) above, and may not be able to effectively provide notifications to encourage safe driving.
[0006] In view of the above points, this disclosure aims to provide a driver assistance device capable of accurately determining a decrease in the driver's level of concentration while driving. [Means for solving the problem]
[0007] According to one aspect of this disclosure, the driver assistance system is An object detection unit (2) detects hazardous objects (13, 15) that pose a risk of causing an accident in the path (11) of the vehicle (10) and in the surrounding area (12, 16), The object detection unit (3) detects the characteristics of evasive driving, in which the driver performs driving maneuvers to avoid the risk of an accident when the vehicle approaches and passes a dangerous object detected by the object detection unit, A concentration level determination unit (4) determines the driver's level of concentration on driving based on the characteristics of the driver's evasive driving detected by the evasive driving detection unit, The system includes a notification unit (5) that, if the concentration level determination unit determines that the driver's level of concentration on driving has decreased, provides notification to encourage safe driving.
[0008] According to this, the driver assistance system of this disclosure determines the driver's level of concentration on driving based on the characteristics of evasive driving, in which the driver avoids an object that poses a risk of causing an accident to the vehicle (i.e., a hazardous object) through the driver's driving operations. Therefore, compared to methods that determine the driver's level of concentration on driving based solely on the driver's facial expression or gaze, such as the one described in Patent Document 1, the driver assistance system of this disclosure can determine a decrease in the driver's level of concentration on driving with high accuracy. For example, the driver assistance system of this disclosure can determine a decrease in the driver's level of concentration on driving even if the driver sees a hazardous object but is only vaguely looking at it and does not recognize it as a hazardous object. Also, for example, the driver assistance system of this disclosure can determine a decrease in the driver's level of concentration on driving even if the driver recognizes it as a hazardous object, but their safety awareness is reduced due to anxiety or other reasons. Therefore, the driver assistance system of this disclosure can effectively encourage safe driving by making the notifications that promote safe driving acceptable to the driver, reducing the annoyance the driver feels about those notifications, and promoting safe driving.
[0009] The reference numerals in parentheses attached to each component indicate an example of the correspondence between that component and the specific components described in the embodiments described later. [Brief explanation of the drawing]
[0010] [Figure 1] This is a block diagram showing the schematic configuration of the driver assistance device according to the first embodiment. [Figure 2] This is an explanatory diagram illustrating how a concentration level reduction determination is performed in the driver assistance system according to the first embodiment when the vehicle approaches and passes a vehicle parked on the roadside. [Figure 3] Following Figure 2, this is an explanatory diagram illustrating how notification is triggered when your vehicle passes a vehicle parked on the shoulder of the road. [Figure 4] This is a diagram showing the algorithm executed by the driver assistance device according to the first embodiment. [Figure 5] Figure 4 is a flowchart showing the process of S200. [Figure 6] This is a flowchart showing the process of S300 in FIG. 4. [Figure 7] This is a block diagram showing a schematic configuration of the driving support device according to the second embodiment. [Figure 8] This is an explanatory diagram illustrating a state in which characteristics of the driver's avoidance driving are learned when the host vehicle approaches and passes a roadside parked vehicle in the driving support device according to the second embodiment. [Figure 9] This is an explanatory diagram illustrating a state in which determination and notification of a decrease in concentration are executed when the host vehicle approaches and passes another roadside parked vehicle in a scene different from that in FIG. 8. [Figure 10] This is a flowchart showing an algorithm executed by the driving support device according to the second embodiment. [Figure 11] This is a flowchart showing the process of S200 in FIG. 10. [Figure 12] This is a flowchart showing the process of S300 in FIG. 10. [Figure 13] This is a flowchart showing the process of S500 in FIG. 10. [Figure 14] This is an explanatory diagram illustrating a state in which characteristics of the driver's avoidance driving are learned when the host vehicle approaches a roadside parked vehicle in the driving support device according to the third embodiment. [Figure 15] This is an explanatory diagram illustrating a state in which determination and notification of a decrease in concentration are executed when the host vehicle approaches another roadside parked vehicle in a scene different from that in FIG. 14. [Figure 16] This is a flowchart showing an algorithm executed by the driving support device according to the third embodiment. [Figure 17] This is a flowchart showing the process of S200 in FIG. 16. [Figure 18] This is a flowchart showing the process of S300 in FIG. 16. [Figure 19] This is a flowchart showing the process of S500 in FIG. 16. [Figure 20]This is an explanatory diagram illustrating how the characteristics of the driver's evasive driving are learned when a crossing pedestrian is present around the travel path of the host vehicle in the driving support device according to the fourth embodiment. [Figure 21] This is an explanatory diagram illustrating how the determination of reduced concentration level and notification are executed when another crossing pedestrian is present around the travel path of the host vehicle in a scene different from that of Figure 20. [Figure 22] This is a flowchart showing the algorithm executed by the driving support device according to the fourth embodiment. [Figure 23] This is a flowchart showing the processing of S200 in Figure 22. [Figure 24] This is a flowchart showing the processing of S300 in Figure 22. [Figure 25] This is a flowchart showing the processing of S500 in Figure 22. [Figure 26] This is an explanatory diagram illustrating how the reduced concentration level determination is executed when the host vehicle approaches and passes a roadside parked vehicle in the driving support device according to the fifth embodiment. [Figure 27] This is an explanatory diagram illustrating how notification is executed as the host vehicle passes the roadside parked vehicle, continuing from Figure 26. [Figure 28] This is a flowchart showing the algorithm executed by the driving support device according to the fifth embodiment. [Figure 29] This is a flowchart showing the processing of S200 in Figure 28. [Figure 30] This is a flowchart showing the processing of S300 in Figure 28. [Figure 31] This is an explanatory diagram illustrating how the characteristics of the driver's evasive driving are learned when a crossing pedestrian is present around the travel path of the host vehicle in the driving support device according to the sixth embodiment. [Figure 32] This is an explanatory diagram illustrating how the determination of reduced concentration level and notification are executed when another crossing pedestrian is present around the travel path of the host vehicle in a scene different from that of Figure 31. [Figure 33]This is an explanatory diagram illustrating how notification is triggered when there are other pedestrians crossing the road around the vehicle's path, in a different scenario from Figures 31 and 32. [Figure 34] This is an explanatory diagram illustrating how a notification is issued when your vehicle approaches a vehicle parked on the roadside, in a different scenario from Figures 31 and 32. [Figure 35] This is a diagram showing the algorithm executed by the driver assistance system according to the sixth embodiment. [Figure 36] This is a state transition diagram illustrating the process in S300 of Figure 35. [Figure 37] This is an explanatory diagram illustrating how the driver's evasive driving characteristics are learned when the vehicle approaches and passes a vehicle parked on the roadside in the driver assistance system according to the seventh embodiment. [Figure 38] This is an explanatory diagram illustrating how a decrease in concentration is detected and reported when your vehicle approaches and passes another vehicle parked on the shoulder of the road, in a different scenario from Figure 37. [Figure 39] This is an explanatory diagram illustrating how notification is issued when there are pedestrians crossing the road around the vehicle's path, in a different scenario from Figures 37 and 38. [Figure 40] This is an explanatory diagram illustrating how a notification is issued when your vehicle approaches another vehicle parked on the roadside, in a different scenario from Figures 37 and 38. [Modes for carrying out the invention]
[0011] The embodiments of this disclosure will be described below with reference to the drawings. In the following embodiments, parts that are the same or equivalent to each other will be denoted by the same reference numerals, and their descriptions will be omitted.
[0012] (First Embodiment) The first embodiment will now be described. The driver assistance device of the first embodiment provides a notification to encourage safe driving when the driver's concentration on driving is reduced. Furthermore, by accurately determining the driver's reduced concentration on driving, this driver assistance device can reduce the annoyance the driver feels from the notification and effectively encourage safe driving.
[0013] The driver assistance system consists of a processor, a microcomputer including memory such as ROM and RAM, and an electronic control unit having peripheral circuits. The driver assistance system is connected to on-board cameras (not shown), various sensors, and other electronic control units mounted in the vehicle via an in-vehicle LAN or wire harness, for example, using CAN communication. CAN stands for Controller Area Network, and LAN stands for Local Area Network.
[0014] As shown in Figure 1, the driver assistance device 1 functions as an object detection unit 2, an avoidance driving detection unit 3, a concentration level determination unit 4, and a notification unit 5, etc., by having the processor execute a program stored in memory, and performs various control processing.
[0015] The object detection unit 2 analyzes image data transmitted from the in-vehicle camera to detect objects that pose a risk of causing an accident (hereinafter referred to as "hazardous objects") in and around the path of the vehicle to which the driver assistance system 1 is applied (hereinafter simply referred to as "the vehicle"). The area around the vehicle's path includes, for example, the road shoulder, roadside, sidewalk, and bicycle lane. Hazardous objects include, for example, road shoulders around the vehicle's path, or roadside parked vehicles that are encroaching on the vehicle's path from the road shoulder, and pedestrians crossing or about to cross the vehicle's path. The object detection unit 2 transmits information about the detected hazardous objects to the evasive driving detection unit 3, the concentration level determination unit 4, and the notification unit 5, etc.
[0016] The evasive driving detection unit 3 detects the characteristics of evasive driving (hereinafter referred to as "driver's evasive driving characteristics") in which the driver performs driving maneuvers to avoid the risk of an accident when the vehicle approaches and passes a dangerous object.
[0017] One characteristic of evasive driving by a driver is the distance between the vehicle and the hazardous object when the vehicle passes next to the object (hereinafter referred to as "lateral distance Lm"). If the hazardous object is a parked vehicle on the roadside, the lateral distance Lm may be the distance between the center of the vehicle and the outer wall surface of the parked vehicle on the vehicle's side, or it may be the distance between the outer wall surface of the vehicle on the roadside's side and the outer wall surface of the parked vehicle on the vehicle's side.
[0018] Another characteristic of evasive driving is the time to avoid collision when the driver begins braking before reaching a hazardous object. Hereafter, collision time will be referred to as TTC. TTC is an abbreviation for Time To Collision. TTC is the value obtained by dividing the distance between the vehicle's position and the hazardous object by the vehicle's current speed. The distance between the vehicle and the hazardous object is detected by, for example, millimeter-wave radar or LiDAR. LiDAR is an abbreviation for Light Detection and Ranging or Laser Imaging Detection and Ranging. The vehicle's speed is detected by a vehicle speed sensor.
[0019] The avoidance driving detection unit 3 transmits the characteristics of the driver's avoidance driving to the concentration level determination unit 4.
[0020] The concentration level determination unit 4 determines the driver's level of concentration on driving based on the driver's evasive driving characteristics. In the first embodiment, the concentration level determination unit 4 determines that the driver's level of concentration on driving is low if the lateral distance Lm is smaller than a preset distance threshold. The distance threshold is set in advance through experiments or the like and stored in the memory of the driving support device 1. The distance threshold may be a distance that is greater the faster the vehicle's speed, a function of the vehicle's speed, or may have different values depending on the presence or absence of vehicles in adjacent lanes or oncoming vehicles.
[0021] Furthermore, the concentration level determination unit 4 determines that the driver's concentration level has decreased if the TTC is less than a preset time threshold. The time threshold is set in advance through experiments or other means and stored in the memory of the driver assistance device 1. The time threshold may be longer as the vehicle speed increases, may be a function of the vehicle speed, or may have different values depending on the presence or absence of vehicles in adjacent lanes or oncoming vehicles.
[0022] The concentration level determination unit 4 transmits the result of the determination of the driver's level of concentration on driving to the notification unit 5.
[0023] If the concentration level determination unit 4 determines that the driver's concentration level has decreased, the notification unit 5 will issue a notification to encourage safe driving. For example, the notification unit 5 will control an in-car speaker (not shown) to output a warning sound of "pop" followed by the voice message "Beware of vehicles suddenly pulling out from roadside parking." Alternatively, the notification unit 5 may control a head-up display (not shown) to surround roadside parked vehicles with a colored frame and display the text "Beware of vehicles suddenly pulling out from roadside parking."
[0024] Next, Figures 2 and 3 show how, when the vehicle to which the driver assistance device 1 of the first embodiment is applied approaches and passes a vehicle parked on the roadside, the driver assistance device 1 determines a decrease in the driver's concentration on driving based on the characteristics of the driver's evasive driving and provides notification.
[0025] As shown in Figure 2, a parked vehicle 13 is parked on the shoulder 12 ahead of the path 11 (i.e., the driving lane) that vehicle 10 is traveling in. In this case, there is a possibility that a pedestrian or other person (not shown) may suddenly appear from the blind spot 14 of the parked vehicle 13. Therefore, for safe driving, it is preferable for vehicle 10 to reduce its speed and maintain as large a lateral distance Lm between itself and the parked vehicle 13 as possible when passing the parked vehicle 13.
[0026] However, if the driver becomes anxious or otherwise loses concentration on driving, they may pass the parked vehicle 13 without slowing down, reducing the lateral distance Lm between the vehicle 10 and the parked vehicle 13, as shown by arrow R in Figure 2. In the first embodiment, the concentration level determination unit 4 determines that the driver's concentration on driving has decreased if the lateral distance Lm, which is a characteristic of the driver's evasive driving, is smaller than the distance threshold.
[0027] In that case, as shown in Figure 3, after the vehicle 10 has passed the roadside parked vehicle 13, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving. This allows the driver assistance device 1 to encourage the driver to regain their concentration on driving in the subsequent driving.
[0028] Incidentally, conventional automatic braking systems issue warnings or apply brakes to avoid collisions when the driver's concentration on driving decreases and a collision with a hazardous object is imminent. In contrast, the driver assistance device 1 of this embodiment detects in advance the tendency for the driver's concentration to decrease and restores their concentration on driving through notification, so as not to create a dangerous situation where a collision with a hazardous object is imminent.
[0029] Next, an example of an algorithm executed by the driver assistance device 1 according to the first embodiment will be described with reference to Figures 4 to 6. In this algorithm, the hazardous object is described as a roadside parked vehicle 13, and the characteristics of the driver's evasive driving are described as the lateral distance Lm. Furthermore, this algorithm is executed repeatedly at a predetermined control cycle interval (for example, every 100 ms).
[0030] In the following explanation and flowchart, steps will simply be denoted as "S".
[0031] In S100 of Figure 4, the object detection unit 2 detects hazardous objects present in the path of the vehicle 10 and its surroundings. The hazardous objects are, for example, roadside parked vehicles 13.
[0032] Next, in S200, the avoidance driving detection unit 3 detects the characteristics of the driver's avoidance driving in relation to the hazardous object. The process in S200 will be explained in detail with reference to Figure 5.
[0033] In S211 of Figure 5, the evasive driving detection unit 3 determines whether the object detection unit 2 is detecting the roadside parked vehicle 13 as a dangerous object. If the evasive driving detection unit 3 determines in S211 that the object detection unit 2 is detecting the roadside parked vehicle 13, it proceeds to S212. In S212, the evasive driving detection unit 3 calculates the lateral distance Lm when its own vehicle 10 passes the roadside parked vehicle 13 as a characteristic of the driver's evasive driving, then terminates the process in S200 and proceeds to S300. The evasive driving detection unit 3 stores in memory the minimum value of the lateral distance Lm between its own vehicle 10 and the roadside parked vehicle 13 detected before and after the vehicle 10 passes the roadside parked vehicle 13.
[0034] On the other hand, if the avoidance driving detection unit 3 determines in S211 that the object detection unit 2 is not currently detecting the roadside parked vehicle 13, it terminates the process in S200 and proceeds to S300.
[0035] Next, returning to Figure 4, in S300 the concentration level determination unit 4 determines a decrease in the driver's concentration on driving. The process in S300 will be explained in detail with reference to Figure 6.
[0036] In S311 of Figure 6, the concentration determination unit 4 determines whether the vehicle 10 has completed passing the roadside parked vehicle 13. If the concentration determination unit 4 determines that the vehicle 10 has completed passing the roadside parked vehicle 13, it proceeds to S312.
[0037] In S312, the concentration determination unit 4 determines whether the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13 is less than or equal to the distance threshold. If the concentration determination unit 4 determines that the lateral distance Lm is less than or equal to the distance threshold, it proceeds to S313. In S313, the concentration level determination unit 4 determines that the driver's level of concentration on driving is decreasing, terminates the process in S300, and proceeds to S400.
[0038] On the other hand, if the concentration determination unit 4 determines in S311 that the vehicle 10 has not yet completed passing the roadside parked vehicle 13, that is, that it is either before passing (i.e., approaching) or in the process of passing, it proceeds to S314. Also, if the concentration determination unit 4 determines in S312 that the lateral distance Lm when the vehicle 10 has passed the roadside parked vehicle 13 is greater than the distance threshold, it proceeds to S314. In S314, the concentration level determination unit 4 determines that the driver's concentration level on driving is not decreasing, terminates the process in S300, and proceeds to S400.
[0039] Returning to Figure 4, at S400, if the concentration level determination unit 4 determines that the driver's concentration level is decreasing, the notification unit 5 issues a notification to encourage safe driving. On the other hand, if the concentration level determination unit 4 determines that the driver's concentration level is not decreasing, the notification unit 5 does not issue a notification. After S400, the process ends temporarily and is repeated from S100 at a predetermined control cycle.
[0040] The driving assistance device 1 of the first embodiment described above provides the following effects. (1) In the first embodiment, the driver assistance device 1 includes an object detection unit 2, an evasive driving detection unit 3, a concentration level determination unit 4, and a notification unit 5 as functional units that perform various control processing. The object detection unit 2 detects the path 11 of the vehicle 10 and any hazardous objects present around that path 11. The evasive driving detection unit 3 detects the characteristics of the driver's evasive driving in relation to the hazardous objects. The concentration level determination unit 4 determines the driver's level of concentration on driving based on the characteristics of the driver's evasive driving. If the notification unit 5 determines that the driver's level of concentration on driving has decreased, it provides a notification to encourage safe driving. According to this, the driver assistance device 1 determines the driver's level of concentration on driving based on the driver's evasive driving characteristics. Therefore, compared to methods that determine the driver's level of concentration on driving based solely on the driver's facial expression or gaze, as described in Patent Document 1, the driver assistance device 1 of the first embodiment can determine a decrease in the driver's level of concentration on driving with high accuracy. Consequently, this driver assistance device 1 can make the driver's notifications encouraging safe driving understandable, reduce the annoyance the driver feels about those notifications, and effectively encourage safe driving.
[0041] (2) In the first embodiment, one of the characteristics of evasive driving by the driver is the lateral distance Lm between the vehicle 10 and the hazardous object when the vehicle 10 passes alongside the object. This makes it possible to determine with high accuracy the decrease in the driver's concentration on driving.
[0042] (3) In the first embodiment, one of the characteristics of evasive driving by the driver is the time to contact (TTC) when the driver starts braking in front of the hazardous object. This also allows for highly accurate determination of the decrease in the driver's concentration on driving.
[0043] (Second Embodiment) A second embodiment will now be described. The second embodiment is a modification of the configuration and algorithm of the driver assistance device 1 compared to the first embodiment, but is otherwise the same as the first embodiment. Therefore, only the differences from the first embodiment will be described.
[0044] As shown in Figure 7, the driving support device 1 of the second embodiment includes a learning unit 6 in addition to the object detection unit 2, avoidance driving detection unit 3, concentration level determination unit 4, and notification unit 5 as functional units that perform various control processing. That is, the driving support device 1 of the second embodiment functions as the object detection unit 2, avoidance driving detection unit 3, concentration level determination unit 4, notification unit 5, and learning unit 6 by having the processor execute a program stored in memory, and performs various control processing.
[0045] The learning unit 6 receives information about hazardous objects from the object detection unit 2 and information about the driver's avoidance driving characteristics from the avoidance driving detection unit 3. Based on this information, the learning unit 6 learns the driver's avoidance driving characteristics under normal circumstances. The learned values obtained by the learning unit 6 are transmitted to the concentration level determination unit 4. If the learning values are valid, the concentration level determination unit 4 uses those learned values in place of the distance threshold or time threshold described in the first embodiment.
[0046] Figures 8 and 9 show how, when the vehicle 10 to which the driver assistance device 1 of the second embodiment is applied approaches and passes a roadside parked vehicle 13, the driver assistance device 1 learns the characteristics of the driver's evasive driving, and then determines a decrease in the driver's concentration on driving and issues a notification. In the figures referred to in the following description, the jagged arrow B schematically indicates that the vehicle 10 has decelerated, and the curved arrow R indicates the driving route of the vehicle 10.
[0047] As shown in Figure 8, a roadside parked vehicle 13a, which is a hazardous object, is parked on the shoulder 12 ahead of the path 11 (i.e., the driving lane) in which the vehicle 10 is traveling. Under normal circumstances, a driver would perform evasive driving, slowing down before the roadside parked vehicle 13a and passing the roadside parked vehicle 13a while maintaining the largest possible lateral distance Lm between the vehicle 10 and the roadside parked vehicle 13a. If the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13a is greater than or equal to the distance threshold described in the first embodiment, it can be said that the driver performed evasive driving under normal circumstances. Furthermore, if the TTC when the vehicle 10 begins braking before the roadside parked vehicle 13a is greater than or equal to the time threshold described in the first embodiment, it can be said that the driver performed evasive driving under normal circumstances.
[0048] In this case, the learning unit 6 stores the lateral distance Lm when its own vehicle 10 passes the roadside parked vehicle 13a as a characteristic of the driver's evasive driving under normal circumstances, and calculates a lateral distance learning value Lm_l based on one or more lateral distances Lm. Furthermore, as will be explained in the third embodiment described later, the learning unit 6 may store the TTC when the driver begins braking in front of the roadside parked vehicle 13a as a characteristic of the driver's evasive driving during normal operation, and calculate the TTC learning value TTCf_l based on one or more TTCs. In that case, the learning unit 6 saves the TTC when the driver begins braking in front of the roadside parked vehicle 13a to a predetermined folder TTCf set in memory, and calculates the TTC learning value TTCf_l based on that TTCf.
[0049] Next, Figure 9 shows a scene after the vehicle 10 has passed through the scene in Figure 8 and continued driving, that is, a different scene from Figure 8. As shown in Figure 9, a different roadside parked vehicle 13b is parked on the shoulder 12 ahead of the path 11 (i.e., the driving lane) that the vehicle 10 is traveling in. In this case, the driver's concentration on driving may decrease due to impatience or other reasons, and the vehicle 10 may overlook the roadside parked vehicle 13b, causing it to pass the roadside parked vehicle 13b with a close lateral distance Lm, as shown by arrow R in Figure 9. If the lateral distance Lm, which is a characteristic of the driver's evasive driving, is smaller than the lateral distance learned value Lm_l obtained from learning in scenes such as the one shown in Figure 8, the concentration level determination unit 4 determines that the driver's concentration on driving has decreased.
[0050] In that case, after the vehicle 10 has passed the roadside parked vehicle 13b, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving. This allows the driver assistance device 1 to encourage the driver to regain their concentration on driving in the subsequent driving.
[0051] Next, an example of an algorithm executed by the driver assistance device 1 according to the second embodiment will be described with reference to Figures 10 to 13. In this algorithm, the hazardous object is described as a roadside parked vehicle 13, the driver's evasive driving characteristics are described as the lateral distance Lm, and the learned value obtained by the learning unit 6 is described as the lateral distance learned value Lm_l. Furthermore, this algorithm is executed repeatedly at a predetermined control cycle interval (for example, an interval of 100 ms).
[0052] In S100 of Figure 10, the object detection unit 2 detects hazardous objects present in the path of the vehicle 10 and its surroundings. The hazardous objects are, for example, roadside parked vehicles 13.
[0053] Next, in S200, the avoidance driving detection unit 3 detects the characteristics of the driver's avoidance driving in relation to the hazardous object. The process in S200 will be explained in detail with reference to Figure 11.
[0054] In S221 of Figure 11, the evasive driving detection unit 3 determines whether the object detection unit 2 is detecting the roadside parked vehicle 13 as a dangerous object. If the evasive driving detection unit 3 determines in S221 that the object detection unit 2 is detecting the roadside parked vehicle 13, it proceeds to S222. In S222, the evasive driving detection unit 3 calculates the lateral distance Lm when its own vehicle 10 passes the roadside parked vehicle 13 as a characteristic of the driver's evasive driving, then terminates the process in S200 and proceeds to S300. The evasive driving detection unit 3 stores in memory the minimum value of the lateral distance Lm between its own vehicle 10 and the roadside parked vehicle 13 detected before and after the vehicle 10 passes the roadside parked vehicle 13.
[0055] On the other hand, if the avoidance driving detection unit 3 determines in S221 that the object detection unit 2 is not currently detecting the roadside parked vehicle 13, it terminates the process in S200 and proceeds to S300.
[0056] Next, returning to Figure 10, in S300 the concentration level determination unit 4 determines a decrease in the driver's concentration on driving. The process in S300 will be explained in detail with reference to Figure 12.
[0057] In S321 of Figure 12, the concentration determination unit 4 determines whether the vehicle 10 has completed passing the roadside parked vehicle 13. If the concentration determination unit 4 determines that the vehicle 10 has completed passing the roadside parked vehicle 13, it proceeds to S322.
[0058] In S322, the concentration level determination unit 4 determines whether the lateral distance learning value Lm_l obtained by the learning unit 6 through learning is valid. This determination is made, for example, by checking whether the lateral distance learning value Lm_l has been updated a predetermined number of times or more after the driving switch of the vehicle 10 is turned on. The number of updates of the lateral distance learning value Lm_l is reset when the driving switch of the vehicle 10 is turned off. The method for updating the lateral distance learning value Lm_l will be described later. If the concentration level determination unit 4 determines that the lateral distance learning value Lm_l is valid if the lateral distance learning value Lm_l has been updated a predetermined number of times or more after the driving switch of the vehicle 10 is turned on, the process proceeds to S323.
[0059] In S323, the concentration determination unit 4 determines whether the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13 is less than or equal to the lateral distance learned value Lm_l. If the concentration determination unit 4 determines that the lateral distance Lm is less than or equal to the lateral distance learned value Lm_l, it proceeds to S324. In S324, the concentration level determination unit 4 determines that the driver's concentration level on driving is decreasing, terminates the process in S300, and proceeds to S400.
[0060] On the other hand, if the concentration determination unit 4 determines in S321 that the vehicle 10 has not yet completed passing the roadside parked vehicle 13, that is, that it is either before or in the process of passing it, the process proceeds to S325. Also, if the concentration determination unit 4 determines in S322 that the lateral distance learning value Lm_l obtained by the learning unit 6 through learning is not valid, the process proceeds to S325. Also, if the concentration determination unit 4 determines in S323 that the lateral distance Lm when the vehicle 10 has passed the roadside parked vehicle 13 is greater than the lateral distance learning value Lm_l, the process proceeds to S325. In S325, the concentration level determination unit 4 determines that the driver's concentration level on driving is not decreasing, terminates the process in S300, and proceeds to S400.
[0061] Returning to Figure 10, at S400, if the concentration level determination unit 4 determines that the driver's concentration level is decreasing, the notification unit 5 issues a notification to encourage safe driving and proceeds to S500. On the other hand, if the concentration level determination unit 4 determines that the driver's concentration level is not decreasing, the notification unit 5 does not issue a notification and proceeds to S500.
[0062] In S500, the learning unit 6 learns the characteristics of the driver's evasive driving during normal operation. The process in S500 will be explained in detail with reference to Figure 13.
[0063] In S521 of Figure 13, the learning unit 6 determines whether the driver's concentration on driving is decreasing at the time when its own vehicle 10 has finished passing the roadside parked vehicle 13, as determined in the process of S300. If the learning unit 6 does not determine in the process of S300 that the driver's concentration on driving is decreasing, it proceeds to S522.
[0064] In S522, the learning unit 6 updates the lateral distance learning value Lm_l using the lateral distance Lm when its own vehicle 10 passes the roadside parked vehicle 13. The case where it is not determined that the driver's concentration on driving is decreasing means that it is a normal state. Therefore, if it is not determined that the driver's concentration on driving is decreasing, the lateral distance learning value Lm_l is updated using the lateral distance Lm, which is a characteristic of the driver's evasive driving in a normal state. For example, the moving average method is used to update the lateral distance learning value Lm_l. In the moving average method, the average of the lateral distance Lm of the past N scenes and the lateral distance Lm detected in the current scene is calculated.
[0065] On the other hand, if the learning unit 6 determines in S521 that the driver's concentration on driving is decreasing during the processing in S300, it terminates the process without updating the lateral distance learning value Lm_l. In that case, the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13 is not a characteristic of the driver's evasive driving under normal circumstances, so the lateral distance learning value Lm_l is not updated.
[0066] After S500, the process temporarily ends and is then repeated from S100 at a predetermined control cycle.
[0067] The driving assistance device 1 of the second embodiment described above provides the following effects. (1) In the second embodiment, the driving support device 1 further includes a learning unit 6 as a functional unit that performs various control processing, in addition to the object detection unit 2, the evasive driving detection unit 3, the concentration level determination unit 4, and the notification unit 5. The learning unit 6 learns the characteristics of the driver's evasive driving under normal conditions. The concentration level determination unit 4 compares the characteristics of the driver's evasive driving learned by the learning unit 6 with the characteristics of the driver's evasive driving detected by the evasive driving detection unit 3 and determines that the driver's concentration on driving has decreased. According to this, the driver receives a notification encouraging safe driving when the characteristics of evasive driving in their normal driving differ from those of evasive driving in their current driving. This leads to a greater sense of acceptance of the notification and reduces annoyance. Therefore, the driver assistance device 1 can effectively encourage safe driving in the driver.
[0068] (2) In the second embodiment, if the characteristics of the driver's evasive driving do not meet a predetermined standard, the learning unit 6 does not reflect the characteristics of the evasive driving at that time in its learning. On the other hand, if the characteristics of the driver's evasive driving meet a predetermined standard, the learning unit 6 reflects the characteristics of the evasive driving at that time in its learning. According to this, the learning unit 6 learns the characteristics of the driver's evasive driving only if those characteristics meet predetermined criteria. Therefore, the characteristics of the driver's evasive driving learned by the learning unit 6 are modified to be safer than the predetermined threshold setting. Consequently, the driver assistance device 1 can provide highly safe notifications that correspond to the normal driving of each individual driver. The predetermined criteria may be, for example, the time threshold and distance threshold described in the first embodiment. Furthermore, a case in which the characteristics of the driver's evasive driving do not meet the predetermined criteria is, for example, when it is determined that the driver's level of concentration is decreasing. On the other hand, a case in which the characteristics of the driver's evasive driving meet the predetermined criteria is, for example, when it is not determined that the driver's level of concentration is decreasing, that is, when the driver is in a normal state.
[0069] (Third embodiment) A third embodiment will now be described. The third embodiment has the same configuration as the second embodiment, but with some modifications to the algorithm compared to the second embodiment.
[0070] Figures 14 and 15 show how, when the vehicle 10 to which the driver assistance device 1 of the third embodiment is applied approaches and passes a roadside parked vehicle 13, the driver assistance device 1 learns the characteristics of the driver's evasive driving, and then determines a decrease in the driver's concentration on driving and provides notification.
[0071] As shown in Figure 14, a roadside parked vehicle 13a, which is a hazardous object, is parked on the shoulder 12 ahead of the path 11 (i.e., the driving lane) in which the vehicle 10 is traveling. Under normal circumstances, a driver would perform evasive driving, slowing down before the roadside parked vehicle 13a, and passing the roadside parked vehicle 13a while maintaining the largest possible lateral distance Lm between the vehicle 10 and the roadside parked vehicle 13a. If the time to traffic control (TTC) when the vehicle 10 begins braking before the roadside parked vehicle 13a is greater than or equal to the time threshold described in the first embodiment, it can be said that the driver performed evasive driving under normal circumstances. Furthermore, if the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13a is greater than or equal to the distance threshold described in the first embodiment, it can be said that the driver performed evasive driving under normal circumstances.
[0072] In this case, the learning unit 6 stores the TTC at the moment the driver begins braking before the roadside parked vehicle 13a as a characteristic of the driver's evasive driving during normal conditions in TTCf, and calculates the TTC learning value TTCf_l based on TTCf. Alternatively, as described in the second embodiment, the learning unit 6 may also store the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13a as a characteristic of the driver's evasive driving during normal conditions, and calculate the lateral distance learning value Lm_l.
[0073] Next, Figure 15 shows a scene after the vehicle 10 has passed through the scene in Figure 14 and continued driving, that is, a different scene from Figure 14. As shown in Figure 15, a different roadside parked vehicle 13b is parked on the shoulder 12 ahead of the path 11 (i.e., the driving lane) that the vehicle 10 is traveling in. In this case, the driver's concentration on driving may decrease due to impatience or other reasons, and the TTC may shorten due to overlooking the roadside parked vehicle 13b. If the TTC, which is a characteristic of the driver's evasive driving, is smaller than the TTC learning value TTCf_l obtained by learning from scenes such as the one shown in Figure 14, the concentration level determination unit 4 determines that the driver's concentration on driving has decreased.
[0074] In that case, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification to encourage safe driving. This notification may occur before the vehicle 10 passes the roadside parked vehicle 13b (i.e., while approaching it) or after the vehicle has passed the roadside parked vehicle 13b. This allows the driver assistance device 1 to encourage the driver to regain their concentration on driving in the subsequent driving.
[0075] Next, an example of an algorithm executed by the driver assistance device 1 according to the third embodiment will be described with reference to Figures 16 to 19. In this algorithm, the hazardous object will be described as a roadside parked vehicle 13, the characteristics of the driver's evasive driving as TTC, and the learned value obtained by the learning unit 6 as the TTC learned value TTCf_l. Furthermore, this algorithm is executed repeatedly at a predetermined control cycle interval (for example, an interval of 100 ms).
[0076] In S100 of Figure 16, the object detection unit 2 detects hazardous objects present in the path of the vehicle 10 and its surroundings. The hazardous objects are, for example, roadside parked vehicles 13.
[0077] Next, in S200, the avoidance driving detection unit 3 detects the characteristics of the driver's avoidance driving in relation to the hazardous object. The process in S200 will be explained in detail with reference to Figure 17.
[0078] In S231 of Figure 17, the avoidance driving detection unit 3 determines whether the object detection unit 2 is detecting the roadside parked vehicle 13 as a hazardous object. If the avoidance driving detection unit 3 determines in S231 that the object detection unit 2 is detecting the roadside parked vehicle 13, the process proceeds to S232. In S232, the avoidance driving detection unit 3 determines whether or not the driver's avoidance driving has been detected. If the avoidance driving detection unit 3 determines in S232 that the driver's avoidance driving has not been detected, the process proceeds to S233.
[0079] In S233, the avoidance driving detection unit 3 determines whether or not an avoidance driving operation by the driver has been detected. If an avoidance driving operation by the driver is detected in S233, the process proceeds to S234. In S234, the evasive driving detection unit 3, recognizing the characteristics of the driver's evasive driving, stores (latches) the TTCn when the driver began braking in front of the roadside parked vehicle 13 as the TTC at the time of evasive driving with respect to the roadside parked vehicle in TTCf, and then proceeds to S300.
[0080] On the other hand, if the avoidance driving detection unit 3 determines in S231 that the object detection unit 2 is not currently detecting the roadside parked vehicle 13, it terminates the process in S200 and proceeds to S300. Also, if the avoidance driving detection unit 3 determines in S232 that it has already detected the driver's avoidance driving, it terminates the process in S200 and proceeds to S300. Also, if the avoidance driving detection unit 3 determines in S233 that it has not detected the driver's avoidance driving, it terminates the process in S200 and proceeds to S300.
[0081] Next, returning to Figure 16, in S300 the concentration level determination unit 4 determines a decrease in the driver's concentration on driving. The process in S300 will be explained in detail with reference to Figure 18.
[0082] In S331 of Figure 18, the concentration determination unit 4 determines whether the object detection unit 2 is detecting a roadside parked vehicle 13 as a hazardous object. If the concentration determination unit 4 determines in S331 that the object detection unit 2 is detecting a roadside parked vehicle 13, the process proceeds to S332. In S332, the concentration level determination unit 4 determines whether the avoidance driving detection unit 3 has already detected the driver's avoidance driving. If the concentration level determination unit 4 determines in S332 that the avoidance driving detection unit 3 has not detected the driver's avoidance driving, the process proceeds to S333.
[0083] In S333, the concentration level determination unit 4 determines whether the TTC learning value TTCf_l obtained by the learning unit 6 through learning is valid. This determination is made, for example, by checking whether the TTC learning value TTCf_l has been updated a predetermined number of times or more after the driving switch of the vehicle 10 is turned on. The number of updates of the TTC learning value TTCf_l is reset when the driving switch of the vehicle 10 is turned off. The method for updating the TTC learning value TTCf_l will be described later. If the concentration level determination unit 4 determines that the TTC learning value TTCf_l is valid if the TTC learning value TTCf_l has been updated a predetermined number of times or more after the driving switch of the vehicle 10 is turned on, the process proceeds to S334.
[0084] In S334, the concentration determination unit 4 determines whether the value obtained by subtracting the real-time TTCn from the TTC learning value TTCf_l to the roadside parked vehicle 13 (i.e., TTCf_l-TTCn) is greater than or equal to a predetermined threshold. Note that TTCn is the value obtained by dividing the distance from the vehicle to the hazardous object by the vehicle speed, regardless of whether the driver has started braking or not. Therefore, even before the driver starts braking, the above subtraction process is performed in real time and the concentration determination is carried out. If the concentration determination unit 4 determines in S334 that TTCf_l-TTCn is greater than or equal to the predetermined threshold, the process proceeds to S335. The predetermined threshold can be 0 or a positive number. In S335, the concentration level determination unit 4 determines that the driver's concentration level on driving is decreasing, terminates the process in S300, and proceeds to S400.
[0085] On the other hand, if the concentration level determination unit 4 determines in S331 that the object detection unit 2 is not currently detecting the roadside parked vehicle 13, the process proceeds to S336. Also, if the concentration level determination unit 4 determines in S332 that the avoidance driving detection unit 3 has already detected the driver's avoidance driving, the process proceeds to S336. Also, if the concentration level determination unit 4 determines in S333 that the TTC learning value TTCf_l obtained by the learning unit 6 through learning is not valid, the process proceeds to S336. Also, if the concentration level determination unit 4 determines in S333 that TTCf_l-TTCn is less than a predetermined threshold, the process proceeds to S336. In S336, the concentration level determination unit 4 determines that the driver's concentration level on driving is not decreasing, terminates the process in S300, and proceeds to S400.
[0086] Returning to Figure 16, at S400, if the concentration level determination unit 4 determines that the driver's concentration level is decreasing, the notification unit 5 issues a notification to encourage safe driving and proceeds to S500. On the other hand, if the concentration level determination unit 4 determines that the driver's concentration level is not decreasing, the notification unit 5 does not issue a notification and proceeds to S500.
[0087] In S500, the learning unit 6 learns the characteristics of the driver's evasive driving during normal operation. The process in S500 will be explained in detail with reference to Figure 19.
[0088] In S531 of Figure 19, the learning unit 6 determines, at the time when its own vehicle 10 has finished passing the roadside parked vehicle 13, whether or not the processing in S300 has determined that the driver's concentration on driving was decreasing during the time between its own vehicle 10 passing the roadside parked vehicle 13. If the learning unit 6 has not determined that the driver's concentration on driving was decreasing during the time between its own vehicle 10 passing the roadside parked vehicle 13, it proceeds to S532.
[0089] In S532, the learning unit 6 updates the TTC learning value TTCf_l for the roadside parked vehicle 13 using TTCn, which is the time when the vehicle 10 began braking in front of the roadside parked vehicle 13. If it is not determined that the driver's concentration on driving is decreasing, it means that the situation is normal. Therefore, if it is not determined that the driver's concentration on driving is decreasing, the TTC learning value TTCf_l for the roadside parked vehicle 13 is updated using TTCf, which is a characteristic of the driver's evasive driving in normal conditions. For example, a moving average method may be used to update the TTC learning value TTCf_l. In the moving average method, the average of the TTC of the past N scenes and the TTCn detected in the current scene is calculated.
[0090] On the other hand, in S531, if the learning unit 6 determines in the processing of S300 that the driver's concentration on driving has decreased while the vehicle 10 has passed the roadside parked vehicle 13, it terminates the process without updating the TTC learning value TTCf_l. In that case, since this is not a characteristic of the driver's evasive driving under normal circumstances, the TTC learning value TTCf_l is not updated.
[0091] After S500, the process temporarily ends and is then repeated from S100 at a predetermined control cycle.
[0092] The driver assistance device 1 of the third embodiment described above also provides the same effects and advantages as the second embodiment.
[0093] (Fourth Embodiment) A fourth embodiment will now be described. The fourth embodiment has the same configuration as the second embodiment, with a part of the algorithm modified compared to the second embodiment.
[0094] Figures 20 and 21 show how, when the vehicle 10 to which the driver assistance device 1 of the fourth embodiment is applied approaches and passes a pedestrian crossing the road, the driver assistance device 1 learns the characteristics of the driver's evasive driving, and then determines a decrease in the driver's concentration on driving and issues a notification.
[0095] As shown in Figure 20, a pedestrian 15a is present on the sidewalk 16 ahead of the path 11 (i.e., the driving lane) in which the vehicle 10 is traveling, and is a hazardous object attempting to cross the path 11 of the vehicle 10. In normal driving conditions, the driver would begin braking before the pedestrian 15a, stop temporarily before the crosswalk if one exists, or stop or slow down if there is no crosswalk, so as not to obstruct the pedestrian 15a's passage. If the time to traffic control (TTC) when the vehicle 10 begins braking before the pedestrian 15a is equal to or greater than the time threshold described in the first embodiment, it can be said that this is normal driving conditions.
[0096] In this case, the learning unit 6 saves the TTC (Time Toll) when the driver begins braking before the pedestrian crossing 15a as a characteristic of the driver's evasive driving during normal conditions to a predetermined folder TTCf in memory, and calculates the TTC learning value TTCf_l based on TTCf.
[0097] Next, Figure 21 shows a scene after the vehicle 10 has passed through the scene in Figure 20 and continued driving, that is, a different scene from Figure 20. As shown in Figure 21, a different pedestrian 15b, not the one shown in Figure 20, is attempting to cross the path 11 (i.e., the driving lane) of the vehicle 10 on the sidewalk 16 ahead of the path 11 (i.e., the driving lane). In this case, the driver's concentration on driving may decrease due to anxiety or other reasons, and the TTC may shorten. If the TTC, which is a characteristic of the driver's evasive driving, is smaller than the TTC learning value TTCf_l obtained by learning from scenes such as the one shown in Figure 20, the concentration level determination unit 4 determines that the driver's concentration on driving has decreased.
[0098] In that case, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving. This notification may occur before the vehicle 10 passes the pedestrian 15b (i.e., while approaching) or after the vehicle has passed the pedestrian 15b. This allows the driver assistance device 1 to encourage the driver to regain their concentration on driving.
[0099] Next, an example of an algorithm executed by the driver assistance device 1 according to the fourth embodiment will be described with reference to Figures 22 to 25. In this algorithm, the dangerous object will be described as a pedestrian crossing 15, the characteristics of the driver's evasive driving will be described as TTC, and the learned value obtained by the learning unit 6 will be described as the TTC learned value TTCf_l. Furthermore, this algorithm is executed repeatedly at a predetermined control cycle interval (for example, an interval of 100 ms).
[0100] In S100 of Figure 22, the object detection unit 2 detects hazardous objects present in the path of the vehicle 10 and its surroundings. The hazardous object is, for example, a pedestrian crossing the road 15.
[0101] Next, in S200, the avoidance driving detection unit 3 detects the characteristics of the driver's avoidance driving in relation to the hazardous object. The process in S200 will be explained in detail with reference to Figure 23.
[0102] In S241 of Figure 23, the avoidance driving detection unit 3 determines whether the object detection unit 2 is detecting a pedestrian crossing the road as a dangerous object. If the avoidance driving detection unit 3 determines that the object detection unit 2 is detecting a pedestrian crossing the road, it proceeds to S242. In S242, the avoidance driving detection unit 3 determines whether or not the driver's avoidance driving has been detected. If the avoidance driving detection unit 3 determines that the driver's avoidance driving has not been detected, the process proceeds to S243.
[0103] In S243, the avoidance driving detection unit 3 determines whether or not the driver has performed an avoidance maneuver. If the avoidance driving detection unit 3 detects the driver performing an avoidance maneuver, it proceeds to S244. In S244, the evasive driving detection unit 3, recognizing the characteristics of the driver's evasive driving, stores (latches) the TTCn when the driver began braking before the pedestrian crossing 15 as the TTC at the time of evasive driving towards the pedestrian crossing in TTCf, and then proceeds to processing in S300.
[0104] On the other hand, if the avoidance driving detection unit 3 determines in S241 that the object detection unit 2 is not currently detecting a pedestrian crossing 15, it terminates the process in S200 and proceeds to S300. Also, if the avoidance driving detection unit 3 determines in S242 that it has already detected the driver's avoidance driving, it terminates the process in S200 and proceeds to S300. Also, if the avoidance driving detection unit 3 determines in S243 that it has not detected the driver's avoidance driving, it terminates the process in S200 and proceeds to S300.
[0105] Next, returning to Figure 22, in S300 the concentration level determination unit 4 determines a decrease in the driver's concentration on driving. The process in S300 will be explained in detail with reference to Figure 24.
[0106] In S341 of Figure 24, the concentration level determination unit 4 determines whether or not the object detection unit 2 is currently detecting a pedestrian crossing the road 15. If the concentration level determination unit 4 determines in S341 that the object detection unit 2 is currently detecting a pedestrian crossing the road 15, the process proceeds to S342. In S342, the concentration level determination unit 4 determines whether the avoidance driving detection unit 3 has already detected the driver's avoidance driving. If the concentration level determination unit 4 determines in S342 that the avoidance driving detection unit 3 has not detected the driver's avoidance driving, the process proceeds to S343.
[0107] In S343, the concentration determination unit 4 determines whether the TTC learning value TTCf_l obtained by the learning unit 6 through learning is valid. This determination is made, for example, by checking whether the TTC learning value TTCf_l has been updated a predetermined number of times or more after the driving switch of the vehicle 10 is turned on. The number of updates of the TTC learning value TTCf_l is reset when the driving switch of the vehicle 10 is turned off. If the concentration determination unit 4 determines that the TTC learning value TTCf_l is valid if the TTC learning value TTCf_l has been updated a predetermined number of times or more after the driving switch of the vehicle 10 is turned on, the process proceeds to S344.
[0108] In S344, the concentration determination unit 4 determines whether the value obtained by subtracting the real-time TTCn up to the pedestrian crossing 15 from the TTC learning value TTCf_l (i.e., TTCf_l-TTCn) is greater than or equal to a predetermined threshold. If the concentration determination unit 4 determines in S344 that TTCf_l-TTCn is greater than or equal to the predetermined threshold, the process proceeds to S345. The predetermined threshold can be 0 or a positive number. In S345, the concentration level determination unit 4 determines that the driver's level of concentration on driving is decreasing, terminates the process in S300, and proceeds to S400.
[0109] On the other hand, if the concentration level determination unit 4 determines in S341 that the object detection unit 2 is not currently detecting a pedestrian crossing 15, the process proceeds to S346. Also, if the concentration level determination unit 4 determines in S342 that the avoidance driving detection unit 3 has already detected the driver's avoidance driving, the process proceeds to S346. Also, if the concentration level determination unit 4 determines in S343 that the TTC learning value TTCf_l obtained by the learning unit 6 through learning is not valid, the process proceeds to S346. Also, if the concentration level determination unit 4 determines in S344 that TTCf_l-TTCn is less than a predetermined threshold, the process proceeds to S346. In S346, the concentration level determination unit 4 determines that the driver's concentration level on driving is not decreasing, terminates the process in S300, and proceeds to S400.
[0110] Returning to Figure 22, at S400, if the concentration level determination unit 4 determines that the driver's concentration level is decreasing, the notification unit 5 issues a notification to encourage safe driving and proceeds to S500. On the other hand, if the concentration level determination unit 4 determines that the driver's concentration level is not decreasing, the notification unit 5 does not issue a notification and proceeds to S500.
[0111] In S500, the learning unit 6 learns the characteristics of the driver's evasive driving during normal operation. The process in S500 will be explained in detail with reference to Figure 25.
[0112] In S541 of Figure 25, the learning unit 6 determines whether, at the time when the vehicle 10 has finished passing the pedestrian crossing 15, the driver's concentration on driving was determined to be decreasing in the process of S300 during the time the vehicle 10 passed the pedestrian crossing 15. If the learning unit 6 does not determine in S541 that the driver's concentration on driving was decreasing during the time the vehicle 10 passed the pedestrian crossing 15, the process proceeds to S542.
[0113] In S542, the learning unit 6 updates the TTC learning value TTCf_l for the pedestrian crossing 15 using TTCn, which is the time when the vehicle 10 began braking before reaching the pedestrian crossing 15. The case where the driver's concentration on driving is not determined to be decreasing means normal conditions. Therefore, if the driver's concentration on driving is not determined to be decreasing, the TTCf, which is a characteristic of the driver's evasive driving in normal conditions, is used to update the TTC learning value TTCf_l for the pedestrian crossing 15. For example, a moving average method may be used to update the TTC learning value TTCf_l.
[0114] On the other hand, in S541, if the learning unit 6 determines in the processing of S300 that the driver's concentration on driving was decreasing while the vehicle 10 had passed the pedestrian crossing 15, it terminates the process without updating the TTC learning value TTCf_l. In that case, since this is not a characteristic of the driver's evasive driving under normal circumstances, the TTC learning value TTCf_l is not updated.
[0115] After S500, the process temporarily ends and is then repeated from S100 at a predetermined control cycle.
[0116] The driver assistance device 1 of the fourth embodiment described above also provides the same effects and advantages as the second and third embodiments.
[0117] (Fifth embodiment) Next, we will describe the fifth embodiment. The fifth embodiment is a modification of the algorithm of the driver assistance device 1 compared to the first embodiment, and is otherwise the same as the first embodiment. Therefore, only the parts that differ from the first embodiment will be described.
[0118] The fifth embodiment of the driver assistance device 1 processes images of the driver's face captured by an imaging device (not shown) mounted on the vehicle, and determines the driver's level of concentration on driving, including the driver's gaze toward a dangerous object when the vehicle 10 approaches the dangerous object. As the imaging device, for example, a Driver Status Monitor (registered trademark) manufactured by Denso Corporation can be used, but it is not limited to that, and other imaging devices may be used.
[0119] Figures 26 and 27 show how, when the vehicle 10 to which the driving assistance device 1 of the fifth embodiment is applied approaches and passes a roadside parked vehicle 13, the driving assistance device 1 determines a decrease in the driver's concentration on driving based on the characteristics of the driver's evasive driving and provides notification.
[0120] As shown in Figure 26, a parked vehicle 13 is parked on the shoulder 12 ahead of the path 11 (i.e., the driving lane) that vehicle 10 is traveling in. In this case, there is a possibility that a pedestrian or other person may suddenly appear from the blind spot 14 of the parked vehicle 13. Therefore, for safe driving, it is preferable for vehicle 10 to reduce its speed, maintain as large a lateral distance Lm as possible between vehicle 10 and the parked vehicle 13, and pass the parked vehicle 13 while paying attention to the possibility of someone suddenly appearing from the blind spot 14 of the parked vehicle 13.
[0121] However, if the driver becomes anxious or otherwise loses concentration on driving, they may pass the parked vehicle 13 without slowing down, reducing the lateral distance Lm between the vehicle 10 and the parked vehicle 13, as shown by arrow R in Figure 26. In addition, the driver may pass the parked vehicle 13 without looking at the parked vehicle 13 or its blind spot 14.
[0122] In the fifth embodiment, the concentration level determination unit 4 determines that the driver's concentration on driving is reduced if the lateral distance Lm, which is a characteristic of the driver's evasive driving, is smaller than a distance threshold. Furthermore, the concentration level determination unit 4 determines that the driver's concentration on driving is reduced if, when the vehicle 10 approaches the roadside parked vehicle 13, the driver's visibility of the roadside parked vehicle 13 and its blind spot 14 is insufficient.
[0123] In that case, as shown in Figure 27, after the vehicle 10 has passed the roadside parked vehicle 13, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving. This allows the driver assistance device 1 to encourage the driver to regain their concentration on driving in the subsequent driving.
[0124] Next, an example of an algorithm executed by the driver assistance device 1 according to the fifth embodiment will be described with reference to Figures 28 to 30. In this algorithm, the hazardous object is described as a roadside parked vehicle 13, and the characteristics of the driver's evasive driving are described as the lateral distance Lm. Furthermore, this algorithm is executed repeatedly at a predetermined control cycle interval (for example, 100 ms interval).
[0125] In S100 of Figure 28, the object detection unit 2 detects hazardous objects present in the path of the vehicle 10 and its surroundings. The hazardous objects are, for example, roadside parked vehicles 13.
[0126] Next, in S200, the avoidance driving detection unit 3 detects the characteristics of the driver's avoidance driving in relation to the hazardous object. The process in S200 will be explained in detail with reference to Figure 29.
[0127] In S251 of Figure 29, the evasive driving detection unit 3 determines whether the object detection unit 2 is detecting the roadside parked vehicle 13 as a dangerous object. If the evasive driving detection unit 3 determines in S251 that the object detection unit 2 is detecting the roadside parked vehicle 13, it proceeds to S252. In S252, the evasive driving detection unit 3 calculates the lateral distance Lm when its own vehicle 10 passes the roadside parked vehicle 13 as a characteristic of the driver's evasive driving, then terminates the process in S200 and proceeds to S300. The evasive driving detection unit 3 stores in memory the minimum value of the lateral distance Lm between its own vehicle 10 and the roadside parked vehicle 13 detected before and after the vehicle 10 passes the roadside parked vehicle 13.
[0128] On the other hand, if the avoidance driving detection unit 3 determines in S251 that the object detection unit 2 is not currently detecting the roadside parked vehicle 13, it terminates the process in S200 and proceeds to S300.
[0129] Next, returning to Figure 28, in S300 the concentration level determination unit 4 determines a decrease in the driver's concentration on driving. The process in S300 will be explained in detail with reference to Figure 30.
[0130] In S351 of Figure 30, the concentration determination unit 4 determines whether the vehicle 10 has completed passing the roadside parked vehicle 13. If the concentration determination unit 4 determines that the vehicle 10 has completed passing the roadside parked vehicle 13, it proceeds to S352.
[0131] In S352, the concentration determination unit 4 determines whether the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13 is less than or equal to the distance threshold. If the concentration determination unit 4 determines that the lateral distance Lm is less than or equal to the distance threshold, it proceeds to S353.
[0132] In S353, the concentration determination unit 4 processes the image of the driver's face captured by the imaging device when the vehicle 10 approaches the roadside parked vehicle 13, and determines whether the driver has sufficient visibility of the roadside parked vehicle 13 and its blind spot 14. If the concentration determination unit 4 determines that the driver does not have sufficient visibility of the roadside parked vehicle 13 and its blind spot 14, the process proceeds to S354.
[0133] In S354, the concentration level determination unit 4 determines that the driver's concentration level on driving is decreasing, terminates the process in S300, and proceeds to S400.
[0134] On the other hand, if the concentration determination unit 4 determines in S351 that the vehicle 10 has not yet completed passing the roadside parked vehicle 13, that is, that it is either before or in the process of passing it, the process proceeds to S355. Also, if the concentration determination unit 4 determines in S352 that the lateral distance Lm when the vehicle 10 has passed the roadside parked vehicle 13 is greater than the distance threshold, the process proceeds to S355. Furthermore, if the concentration determination unit 4 determines in S353 that the driver has sufficient visibility of the roadside parked vehicle 13 and its blind spot 14, the process proceeds to S355.
[0135] In S355, the concentration level determination unit 4 determines that the driver's concentration level on driving is not decreasing, terminates the process in S300, and proceeds to S400.
[0136] Returning to Figure 28, at S400, if the concentration level determination unit 4 determines that the driver's concentration level is decreasing, the notification unit 5 issues a notification to encourage safe driving. On the other hand, if the concentration level determination unit 4 determines that the driver's concentration level is not decreasing, the notification unit 5 does not issue a notification.
[0137] The driving assistance device 1 of the fifth embodiment described above determines a decrease in the driver's concentration level based on the driver's gaze toward a dangerous object when the vehicle 10 approaches the dangerous object, in addition to the characteristics of the driver's evasive driving. According to this, the concentration level determination unit 4 detects whether the driver is paying attention to a hazardous object based on the driver's gaze when the vehicle 10 approaches the hazardous object. Therefore, it can accurately capture the direction in which the driver's gaze is directed, thereby improving the accuracy of determining the driver's level of concentration on driving.
[0138] (Sixth Embodiment) The sixth embodiment will now be described. The sixth embodiment is a modification of the algorithm of the driver assistance device 1 compared to the second to fourth embodiments, and is otherwise the same as the second to fourth embodiments. Therefore, only the parts that differ from the second to fourth embodiments will be described.
[0139] Figures 31 to 34 show how, when the vehicle 10 to which the driver assistance device 1 of the sixth embodiment is applied approaches and passes a pedestrian crossing 15, the driver assistance device 1 learns the characteristics of the driver's evasive driving, then determines a decrease in the driver's concentration on driving, and then provides notification.
[0140] As shown in Figure 31, a pedestrian 15a is present on the sidewalk 16 ahead of the path 11 (i.e., the driving lane) in which the vehicle 10 is traveling, and is a hazardous object attempting to cross the path 11 of the vehicle 10. In normal driving conditions, the driver would begin braking before the pedestrian 15a, stop temporarily before the crosswalk if one exists, or stop or slow down if there is no crosswalk, so as not to obstruct the pedestrian 15a's passage. If the TTC when the vehicle 10 begins braking before the pedestrian 15a is equal to or greater than the time threshold described in the first embodiment, it can be said that this is normal driving conditions.
[0141] In this case, the learning unit 6 saves the TTC (Time Toll) when the driver begins braking before the pedestrian crossing 15a as a characteristic of the driver's evasive driving during normal conditions to a predetermined folder TTCf in memory, and calculates the TTC learning value TTCf_l based on TTCf.
[0142] Next, Figure 32 shows a scene after the vehicle 10 has passed through the scene in Figure 31 and continued driving, that is, a different scene from Figure 31. As shown in Figure 32, a different pedestrian 15b than the one shown in Figure 31 is attempting to cross the sidewalk 16 ahead of the path 11 in which the vehicle 10 is traveling. In this case, the driver's concentration on driving may decrease due to anxiety or other reasons, and the time to corner (TTC) may shorten. If the TTC, which is a characteristic of the driver's evasive driving, is smaller than the TTC learning value TTCf_l obtained by learning from scenes such as the one shown in Figure 31, the concentration level determination unit 4 determines that the driver's concentration on driving has decreased.
[0143] Next, Figure 33 shows a different scene from Figures 31 and 32, occurring after the scene in Figure 32 has passed, but before a predetermined time (e.g., 30 minutes) has elapsed since the scene in Figure 32 has passed. Alternatively, Figure 33 may show a different scene from Figures 31 and 32 after a predetermined number of consecutive occurrences of a scene in which the driver's concentration on driving is determined to be reduced, such as in Figure 32.
[0144] In Figure 33, a pedestrian 15c, different from the one shown in Figures 31 and 32, is attempting to cross the sidewalk 16 ahead of the path 11 in which the vehicle 10 is traveling. In this case, when the object detection unit 2 detects the pedestrian 15c as a hazardous object, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving when the TTC of the vehicle 10 relative to the pedestrian 15c falls below a predetermined value. As a result, the driver assistance device 1 can prevent accidents by issuing a notification encouraging safe driving well in advance of the vehicle 10 passing the pedestrian 15c (i.e., while approaching).
[0145] Furthermore, Figure 34, like Figure 33, shows a different scene from Figures 31 and 32 after the scene in Figure 32 has passed, and before a predetermined time (e.g., 30 minutes) has elapsed since the scene in Figure 32 has passed. Alternatively, Figure 34 may show a different scene from Figures 31 and 32 after a predetermined number of consecutive occurrences of a scene in which the driver's concentration on driving is judged to be reduced, such as in Figure 32.
[0146] In Figure 34, a roadside parked vehicle 13c is parked on the shoulder 12 ahead of the path 11 in which the vehicle 10 is traveling. In this case, when the object detection unit 2 detects the roadside parked vehicle 13c as a hazardous object, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving when the TTC of the vehicle 10 relative to the roadside parked vehicle 13c falls below a predetermined value. As a result, the driver assistance device 1 can prevent accidents by issuing a notification encouraging safe driving with ample time before the vehicle 10 passes the roadside parked vehicle 13c (i.e., while approaching it).
[0147] Next, an example of an algorithm executed by the driver assistance device 1 according to the sixth embodiment will be described with reference to Figures 35 and 36. This algorithm is executed repeatedly at predetermined control cycle intervals (for example, 100 ms intervals).
[0148] In S100 of Figure 35, the object detection unit 2 detects hazardous objects present in the path of the vehicle 10 and its surroundings.
[0149] Next, in S200, the avoidance driving detection unit 3 detects the characteristics of the driver's avoidance driving toward the hazardous object. The processing in S200 is as described in the second to fourth embodiments with reference to Figures 11, 17, or 23.
[0150] Next, in S300, the concentration level determination unit 4 determines a decrease in the driver's concentration on driving. As for the processing in S300, first, the process described in the second to fourth embodiments with reference to Figures 12, 18, or 24 is executed.
[0151] Furthermore, as shown in Figure 36, in S300, the concentration level determination unit 4 holds a determination result in S361 that "the driver's concentration level is not decreasing" under predetermined conditions. Also, in S300, the concentration level determination unit 4 holds a determination result in S361 that "the driver's concentration level is decreasing" under predetermined conditions.
[0152] The predetermined condition for maintaining the judgment result in S361 that "the driver's concentration on driving is not decreasing" is that the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit 3 satisfy the characteristics of the driver's avoidance driving learned by the learning unit 6 for a predetermined number of consecutive times Y or more. Note that the predetermined number Y can be set to multiple times.
[0153] Alternatively, the predetermined condition for maintaining the determination in S361 that "the driver's concentration on driving is not decreasing" may be that a predetermined time (e.g., 30 minutes) has elapsed since the start of maintaining the determination that "the driver's concentration on driving is decreasing."
[0154] On the other hand, the predetermined condition for maintaining the judgment result in S362 that "the driver's concentration on driving is decreasing" is that the determination that the driver's avoidance driving characteristics detected by the avoidance driving detection unit 3 do not satisfy the driver's avoidance driving characteristics learned by the learning unit 6 has occurred for a predetermined number of X or more consecutive times. The predetermined number of times X can also be set to multiple times. Note that the predetermined number of times X and Y may be the same value or different values.
[0155] Next, in S400, if all of the following requirements (A), (B), and (C) are met, the notification unit 5 issues a notification to encourage safe driving and proceeds to S500. On the other hand, if even one of the following requirements (A), (B), and (C) is not met, the notification unit 5 does not issue a notification and proceeds to S500.
[0156] (A) The object detection unit 2 has detected a hazardous object (for example, a parked vehicle 13 on the roadside or a pedestrian crossing the road 15). (B) The concentration level determination unit 4 holds a determination result that "the driver's level of concentration on driving is decreasing." (C) The TTC (Time To Contact) with respect to the hazardous object falls below a predetermined value. The predetermined value is set to a value such that, for example, the driver can avoid contact with the hazardous object if they perform evasive maneuvers after the notification.
[0157] Next, in S500, the learning unit 6 learns the characteristics of the driver's evasive driving during normal operation. The process in S500 is the same as that described in the second to fourth embodiments with reference to Figures 13, 19, or 25. After S500, the process temporarily ends and is then repeated from S100 at a predetermined control cycle.
[0158] The driving assistance device 1 of the sixth embodiment described above provides the following effects. (1) In the sixth embodiment, the concentration level determination unit 4 can retain for a predetermined time the determination result that the driver's concentration level on driving is decreasing. When the concentration level determination unit 4 retains the determination result that "the driver's concentration level on driving is decreasing", the notification unit 5, when the object detection unit 2 detects a dangerous object, will provide a notification to encourage safe driving before the vehicle 10 passes the dangerous object. Note that before the vehicle 10 passes the object is, for example, when the TTC to the dangerous object falls below a predetermined value. According to this, if the driver's concentration on driving is reduced, the notification unit 5 can prevent accidents by providing a timely notification encouraging safe driving before the vehicle 10 passes a hazardous object (i.e., while approaching it). The specified time can be set arbitrarily, for example, 10 minutes, 30 minutes, 1 hour, or until the driving switch is turned off.
[0159] (2) In the sixth embodiment, the concentration level determination unit 4 can maintain a determination result that "the driver's concentration level on driving is decreasing" under predetermined conditions. The predetermined conditions are that the determination that the driver's avoidance driving characteristics detected by the avoidance driving detection unit 3 do not satisfy the driver's avoidance driving characteristics learned by the learning unit 6 has occurred for a predetermined number of times X or more. Furthermore, the concentration level determination unit 4 can maintain a determination result that "the driver's concentration level on driving is not decreasing" under predetermined conditions. These predetermined conditions are that the determination that the driver's avoidance driving characteristics detected by the avoidance driving detection unit 3 satisfy the driver's avoidance driving characteristics learned by the learning unit 6 has occurred for a predetermined number of times Y or more. Furthermore, if the concentration level determination unit 4 holds a determination result that "the driver's concentration level on driving is decreasing," and the object detection unit 2 detects an object, the notification unit 5 will issue a notification to encourage safe driving before the vehicle 10 passes the object. According to this, if the driver's concentration on driving is reduced, the notification unit 5 can prevent accidents by providing a timely notification encouraging safe driving before the vehicle 10 passes a hazardous object (i.e., while approaching it).
[0160] (Seventh Embodiment) The seventh embodiment will now be described. The seventh embodiment is a modification of the sixth embodiment.
[0161] Figures 37 to 40 show how, when the vehicle 10 to which the driver assistance device 1 of the seventh embodiment is applied approaches and passes a roadside parked vehicle 13, the driver assistance device 1 learns the characteristics of the driver's evasive driving, then determines a decrease in the driver's concentration on driving, and then provides notification.
[0162] As shown in Figure 37, a roadside parked vehicle 13a, which is a hazardous object, is parked on the shoulder 12 ahead of the path 11 (i.e., the driving lane) in which the vehicle 10 is traveling. Under normal circumstances, a driver would perform evasive driving, slowing down before the roadside parked vehicle 13a, and passing the roadside parked vehicle 13a while maintaining the largest possible lateral distance Lm between the vehicle 10 and the roadside parked vehicle 13a. If the time to traffic control (TTC) when the vehicle 10 begins braking before the roadside parked vehicle 13a is greater than or equal to the time threshold described in the first embodiment, it can be said that the driver performed evasive driving under normal circumstances. Furthermore, if the lateral distance Lm when the vehicle 10 passes the roadside parked vehicle 13a is greater than or equal to the distance threshold described in the first embodiment, it can be said that the driver performed evasive driving under normal circumstances.
[0163] In this case, the learning unit 6 stores the TTC (Time To Travel) at the moment the driver begins braking before the parked vehicle 13a as a characteristic of the driver's evasive driving during normal conditions in TTCf, and calculates the TTC learning value TTCf_l based on TTCf. Alternatively, the learning unit 6 may also store the lateral distance Lm when its own vehicle 10 passes the parked vehicle 13a as a characteristic of the driver's evasive driving during normal conditions, and calculate the lateral distance learning value Lm_l.
[0164] Next, Figure 38 shows a scene after the vehicle 10 has passed through the scene in Figure 37 and continued driving, that is, a different scene from Figure 37. As shown in Figure 38, a different roadside parked vehicle 13b from the one shown in Figure 37 is parked on the roadside 12 ahead of the path 11 in which the vehicle 10 is traveling. In this case, the driver's concentration on driving may decrease due to anxiety or other reasons, and the TTC may shorten. If the TTC, which is a characteristic of the driver's evasive driving, is smaller than the TTC learning value TTCf_l obtained by learning from scenes such as the one shown in Figure 37, the concentration level determination unit 4 determines that the driver's concentration on driving has decreased.
[0165] Next, Figure 39 shows a different scene from Figures 37 and 38, occurring after the scene in Figure 38 has passed, but before a predetermined time (e.g., 30 minutes) has elapsed since the scene in Figure 38 has passed. Alternatively, Figure 39 may show a different scene from Figures 37 and 38 after a predetermined number of consecutive occurrences of a scene in which the driver's concentration on driving is determined to be reduced, such as in Figure 38.
[0166] In Figure 39, a pedestrian 15c is attempting to cross the sidewalk 16 ahead of the path 11 in which the vehicle 10 is traveling. In this case, when the object detection unit 2 detects the pedestrian 15c as a hazardous object, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving when the TTC for the hazardous object falls below a predetermined value. As a result, the driver assistance device 1 can prevent accidents by issuing a notification encouraging safe driving well in advance of the vehicle 10 passing the pedestrian 15c (i.e., while approaching).
[0167] Furthermore, Figure 40, like Figure 39, shows a different scene from Figures 37 and 38 after the scene in Figure 38 has passed, but before a predetermined time (e.g., 30 minutes) has elapsed since the scene in Figure 38 has passed. Alternatively, Figure 40 may show a different scene from Figures 37 and 38 after a predetermined number of consecutive occurrences of a scene in which the driver's concentration on driving is judged to be reduced, such as in Figure 38.
[0168] In Figure 40, a roadside parked vehicle 13c is parked on the shoulder 12 ahead of the path 11 in which the vehicle 10 is traveling. In this case, when the object detection unit 2 detects the roadside parked vehicle 13c as a hazardous object, the notification unit 5 controls the in-vehicle speaker and other devices to issue a notification encouraging safe driving when the TTC of the vehicle 10 with respect to the hazardous object falls below a predetermined value. As a result, the driver assistance device 1 can prevent accidents by issuing a notification encouraging safe driving with ample time before the vehicle 10 passes the roadside parked vehicle 13c (i.e., while approaching it).
[0169] The driver assistance device 1 of the seventh embodiment described above also provides the same effects and advantages as the sixth embodiment.
[0170] (Other embodiments) (1) In each of the above embodiments, the number of times the learned value has been updated has been described as being reset when the vehicle's driving switch is turned off, but it is not limited to this, and it may be reset by a predetermined switch operation or at a predetermined timing, or it may not be reset at all.
[0171] (2) In each of the above embodiments, the moving average method was used to update the learned values, but the method is not limited to this, and various averaging methods such as the weighted average method, a predetermined function, the median, the mode, etc. may be used.
[0172] (3) In each of the above embodiments, the driving assistance system has been described as being composed of an electronic control unit mounted on the vehicle, but it is not limited to that, and may, for example, assist the driver's driving through communication between a server and the vehicle.
[0173] (4) In each of the above embodiments, the driver assistance device 1 has been described as being composed of one electronic control device mounted on the vehicle, but it is not limited to this and may be composed of multiple electronic control devices.
[0174] This disclosure is not limited to the embodiments described above, and modifications may be made as appropriate within the scope of the claims. Furthermore, the embodiments and parts thereof are not unrelated to each other and can be combined as appropriate, except in cases where the combination is clearly impossible. In addition, it goes without saying that the elements constituting the embodiments are not necessarily essential, except in cases where they are explicitly stated to be particularly essential or where they are clearly considered essential in principle. Furthermore, in the embodiments, when numerical values such as the number, numerical values, quantities, or ranges of the components of the embodiments are mentioned, the embodiments are not limited to those specific numbers, except in cases where they are explicitly stated to be particularly essential or where they are clearly limited to a specific number in principle. Furthermore, when the shapes, positional relationships, etc., of the components, etc., are mentioned in the embodiments, the embodiments are not limited to those shapes, positional relationships, etc., except in cases where they are explicitly stated to be particularly essential or where they are clearly limited to a specific shape, positional relationship, etc., in principle.
[0175] The control unit and its method described herein may be implemented by a dedicated computer provided by configuring a processor and memory programmed to perform one or more functions embodied by a computer program. Alternatively, the control unit and its method described herein may be implemented by a dedicated computer provided by configuring a processor by one or more dedicated hardware logic circuits. Alternatively, the control unit and its method described herein may be implemented by one or more dedicated computers configured by a combination of a processor and memory programmed to perform one or more functions and a processor configured by one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by the computer on a computer-readable non-transitional tangible recording medium.
[0176] (Perspective of this disclosure) The above disclosure can be understood from the following perspectives, for example. [First point of view] In driver assistance systems, An object detection unit (2) detects hazardous objects (13, 15) that pose a risk of causing an accident in the path (11) of the vehicle (10) and the surrounding area (12, 16) of the path, The object detection unit (3) detects the characteristics of evasive driving in which the driver performs driving operations to avoid the risk of an accident when the vehicle approaches and passes the hazardous object detected by the object detection unit, A concentration level determination unit (4) determines the degree of concentration of the driver on driving based on the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit, A driving assistance device comprising: a notification unit (5) that provides notification to encourage safe driving when the concentration level determination unit determines that the driver's level of concentration on driving has decreased. [Second perspective] The system further includes a learning unit (6) that learns the characteristics of the driver's evasive driving during normal operation, The driver assistance device according to the first aspect, wherein the concentration level determination unit compares the characteristics of the driver's evasive driving during normal times, which have been learned by the learning unit, with the characteristics of the driver's evasive driving detected by the evasive driving detection unit, and determines that the driver's level of concentration on driving has decreased. [Third perspective] The driver assistance device according to the second aspect, wherein the learning unit does not reflect the characteristics of the driver's evasive driving in the learning process if the characteristics of the driver's evasive driving do not meet predetermined criteria, and reflects the characteristics of the driver's evasive driving in the learning process if the characteristics of the driver's evasive driving meet predetermined criteria. [Fourth perspective] The driver assistance device according to any one of the first to third viewpoints, wherein the concentration level determination unit determines a decrease in the driver's concentration level based on the driver's gaze toward the hazardous object when the vehicle approaches the hazardous object, in addition to the characteristics of the driver's evasive driving toward the hazardous object. [Fifth perspective] The concentration level determination unit retains the determination result that "the driver's level of concentration on driving is decreasing" for a predetermined time. The driving assistance device according to any one of the first to fourth aspects, wherein if the concentration level determination unit holds a determination result that "the driver's concentration level on driving is decreasing," and the object detection unit detects the hazardous object, the notification unit provides notification to encourage safe driving before the vehicle passes the hazardous object. [Sixth perspective] The aforementioned concentration level determination unit is If the avoidance driving detection unit determines that the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit do not satisfy the characteristics of the driver's avoidance driving learned by the learning unit, and this determination is made for a predetermined number of times (X) or more, the determination result "the driver's level of concentration on driving is decreasing" is retained. If the avoidance driving detection unit determines that the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit satisfy the characteristics of the driver's avoidance driving learned by the learning unit, and this determination is made for a predetermined number of times (Y) or more, the determination result that "the driver's level of concentration on driving is not decreasing" is maintained. The driving assistance device according to any one of the second to fourth aspects, wherein if the concentration level determination unit holds a determination result that "the driver's level of concentration on driving is decreasing," and the object detection unit detects the hazardous object, the notification unit provides notification to encourage safe driving before the vehicle passes the hazardous object. [Seventh perspective] The driver assistance device according to any one of the first to sixth views, wherein the characteristic of the driver's evasive driving is the time to contact (TTC) when the driver begins braking in front of the hazardous object. [Perspective 8] The driver assistance device according to any one of the first to sixth views, wherein the characteristic of the driver's evasive driving is the lateral distance (Lm) between the vehicle and the hazardous object when the vehicle passes beside the hazardous object. [Explanation of Symbols]
[0177] 2. Object detection unit 3. Avoidance Driving Detection Unit 4 Concentration level determination section 5 Hochi Department 10. Own vehicle 11. Career Paths 12. Shoulder 13. Vehicles parked on the roadside (hazardous objects) 15. Pedestrians crossing the road (hazardous object) 16 Sidewalk
Claims
1. In driver assistance systems, An object detection unit (2) detects hazardous objects (13, 15) that pose a risk of causing an accident in the path (11) of the vehicle (10) and in the vicinity (12, 16) of the path, The object detection unit (3) detects the characteristics of evasive driving in which the driver performs driving operations to avoid the risk of an accident when the vehicle approaches and passes the hazardous object detected by the object detection unit, A concentration level determination unit (4) determines the degree of concentration of the driver on driving based on the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit, The system includes a notification unit (5) that provides notification to encourage safe driving when the concentration level determination unit determines that the driver's level of concentration on driving has decreased, The concentration level determination unit retains the determination result that "the driver's level of concentration on driving is decreasing" for a predetermined time. If the concentration level determination unit holds a determination result that "the driver's level of concentration on driving is decreasing," and the object detection unit detects the hazardous object, the notification unit provides a notification to encourage safe driving before the vehicle passes the hazardous object, in a driving assistance device.
2. The system further includes a learning unit (6) that learns the characteristics of the driver's evasive driving during normal operation, The driver assistance device according to claim 1, wherein the concentration level determination unit compares the characteristics of the driver's evasive driving during normal times, which have been learned by the learning unit, with the characteristics of the driver's evasive driving detected by the evasive driving detection unit, and determines that the driver's level of concentration on driving has decreased.
3. In a driving assistance device, An object detection unit (2) detects hazardous objects (13, 15) that pose a risk of causing an accident in the path (11) of the vehicle (10) and in the vicinity (12, 16) of the path, The object detection unit (3) detects the characteristics of evasive driving in which the driver performs driving operations to avoid the risk of an accident when the vehicle approaches and passes the hazardous object detected by the object detection unit, A concentration level determination unit (4) determines the degree of concentration of the driver on driving based on the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit, If the concentration level determination unit determines that the driver's level of concentration on driving has decreased, the notification unit (5) provides notification to encourage safe driving. The system includes a learning unit (6) that learns the characteristics of the driver's evasive driving during normal operation, The concentration level determination unit compares the characteristics of the driver's evasive driving during normal times, which have been learned by the learning unit, with the characteristics of the driver's evasive driving detected by the evasive driving detection unit, and determines that the driver's level of concentration on driving has decreased. If the avoidance driving detection unit determines that the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit do not satisfy the characteristics of the driver's avoidance driving learned by the learning unit, and this determination is made for a predetermined number of times (X) or more, the determination result "the driver's level of concentration on driving is decreasing" is retained. If the avoidance driving detection unit determines that the characteristics of the driver's avoidance driving detected by the avoidance driving detection unit satisfy the characteristics of the driver's avoidance driving learned by the learning unit, and this determination is made for a predetermined number of times (Y) or more, the determination result that "the driver's level of concentration on driving is not decreasing" is maintained. If the concentration level determination unit holds a determination result that "the driver's level of concentration on driving is decreasing," and the object detection unit detects the hazardous object, the notification unit provides a notification to encourage safe driving before the vehicle passes the hazardous object, in a driving assistance device.
4. The driving assistance device according to claim 2 or 3, wherein the learning unit does not reflect the characteristics of the driver's evasive driving in the learning process if the characteristics of the driver's evasive driving do not meet a predetermined standard, and reflects the characteristics of the driver's evasive driving in the learning process if the characteristics of the driver's evasive driving meet a predetermined standard.
5. The driver assistance device according to any one of Claims 1 to 3, wherein the concentration level determination unit determines a decrease in the driver's concentration level based on the driver's gaze toward the hazardous object when the vehicle approaches the hazardous object, in addition to the characteristics of the driver's evasive driving toward the hazardous object.
6. The driver assistance device according to any one of claims 1 to 3, wherein the characteristic of the driver's evasive driving is the collision time (TTC) when the driver starts braking in front of the hazardous object.
7. The driver assistance device according to any one of claims 1 to 3, wherein the characteristic of the driver's evasive driving is the lateral distance (Lm) between the vehicle and the hazardous object when the vehicle passes beside the hazardous object.
Citation Information
Patent Citations
Alarm system
JP2003317197A
Driving support system
JP2008129772A
Driver state determination device and driver support device
JP2011248535A
Vehicle control device and vehicle control method
JP2019021229A
Driving assistance system for vehicle and vehicle equipped with driving assistance system for vehicle
US20100198456A1
