Drive support device and vehicle
The driving assistance device addresses misinterpretations of traffic signals at pedestrian-vehicle split intersections by using sensors to predict misidentifications and provide timely warnings or braking, thereby preventing collisions.
Patent Information
- Application Number
- JP2024054261
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-03-28
- Publication Date
- 2025-10-09
AI Technical Summary
Drivers and pedestrians often mistakenly interpret traffic lights at pedestrian-vehicle split intersections, leading to potential collisions due to misidentification of traffic signals.
A driving assistance device equipped with sensors and a control unit that acquires data on traffic light states and pedestrian/cyclist positions, determining the likelihood of misidentification and controlling notifications or braking to prevent unintended entry into intersections.
Prevents collisions by accurately predicting and mitigating misinterpretations of traffic signals at split intersections through timely warnings and braking interventions.
Smart Images

Figure 2025152392000001_ABST
Abstract
Description
[Technical Field]
[0001] The present disclosure relates to a driving assistance device and a vehicle. [Background technology]
[0002] Drivers of vehicles may mistakenly enter intersections ahead of their vehicles despite the warning signals of the vehicle traffic lights at the intersection, and pedestrians or cyclists may mistakenly enter crosswalks despite the warning signals of the pedestrian traffic lights.
[0003] A technique for preventing a driver from entering an intersection due to a misidentification is disclosed in, for example, Patent Document 1. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent No. 6922479 Summary of the Invention [Means for solving the problem]
[0005] A driving assistance device according to a first embodiment of the present disclosure includes an acquisition unit and a control unit. The acquisition unit is capable of acquiring first data regarding the illumination states of a plurality of traffic lights installed at an intersection ahead of a stopped vehicle. The control unit is capable of controlling at least one of notifying a driver of the vehicle and braking the vehicle based on the first data. The control unit is capable of performing the following two operations: (A1) In response to a change in the lighting state of a second traffic light, which is different from a first traffic light for vehicles, among a plurality of traffic lights, determining the possibility that a vehicle will start entering an intersection contrary to the indication of the first traffic light. (A2) Controlling at least one of notification and braking depending on the magnitude of the possibility.
[0006] A driving assistance device according to a second embodiment of the present disclosure includes an acquisition unit and a control unit. The acquisition unit is capable of acquiring first data regarding the lighting status of multiple traffic lights installed at an intersection ahead of a stopped vehicle, and second data regarding one or more pedestrians or cyclists present in front of a crosswalk at an intersection that intersects with the stopped vehicle. The control unit is capable of controlling at least one of notifying the driver of the vehicle and braking the vehicle based on the first data and the second data. The control unit is capable of performing the following two operations. (B1) In response to a change in the lighting state of a first traffic light for vehicles or a second traffic light for traffic participants crossing a crosswalk among a plurality of traffic lights, determining the possibility that at least one subject among one or more pedestrians or cyclists will begin entering the crosswalk despite the indication of the second traffic light. (B2) Controlling at least one of notification and braking depending on the magnitude of the possibility.
[0007] A driving assistance device according to a third embodiment of the present disclosure includes an acquisition unit and a control unit. The acquisition unit is capable of acquiring first data regarding the illumination status of multiple traffic lights installed at an intersection ahead of a stopped vehicle, and second data regarding one or more intersecting vehicles stopped near the intersection at an intersection where the vehicle intersects with the intersection. The control unit is capable of controlling at least one of notifying the driver of the vehicle and braking the vehicle based on the first data and the second data. The control unit is capable of performing the following two operations. (C1) In response to a change in the lighting state of a second traffic light for crossing vehicles, which is different from a first traffic light for vehicles, among the plurality of traffic lights, determining the possibility that at least one target vehicle among one or more crossing vehicles will start entering the intersection contrary to the indication of the second traffic light. (C2) Controlling at least one of notification and braking depending on the magnitude of the possibility.
[0008] A vehicle according to a first embodiment of the present disclosure includes a driving assistance device. The driving assistance device has an acquisition unit and a control unit. The acquisition unit is capable of acquiring first data regarding the lighting status of multiple traffic lights installed at an intersection ahead of a stopped vehicle, and second data regarding one or more pedestrians or cyclists present in front of a crosswalk at an intersection that intersects with the stopped vehicle. The control unit is capable of controlling at least one of notifying the driver of the vehicle and braking the vehicle based on the first data and the second data. The control unit is capable of performing the following two operations. (A1) In response to a change in the lighting state of a second traffic light, which is different from a first traffic light for vehicles, among a plurality of traffic lights, determining the possibility that a vehicle will start entering an intersection contrary to the indication of the first traffic light. (A2) Controlling at least one of notification and braking depending on the magnitude of the possibility.
[0009] A vehicle according to a second embodiment of the present disclosure includes a driving assistance device. The driving assistance device includes an acquisition unit and a control unit. The acquisition unit is capable of acquiring first data regarding the lighting status of multiple traffic lights installed at an intersection ahead of a stopped vehicle, and second data regarding one or more pedestrians or cyclists present in front of a crosswalk at an intersection where the vehicle intersects with the intersection. The control unit is capable of controlling at least one of notifying the driver of the vehicle and braking the vehicle based on the first data and the second data. The control unit is capable of performing the following two operations. (B1) In response to a change in the lighting state of a first traffic light for vehicles among the plurality of traffic lights, determine the possibility that at least one subject among one or more pedestrians or cyclists will begin entering a crosswalk contrary to the indication of a second traffic light for the subject. (B2) Controlling at least one of notification and braking depending on the magnitude of the possibility.
[0010] A vehicle according to a third embodiment of the present disclosure includes a driving assistance device. The driving assistance device has an acquisition unit and a control unit. The acquisition unit is capable of acquiring first data regarding the lighting status of multiple traffic lights installed at an intersection ahead of a stopped vehicle, and second data regarding one or more intersecting vehicles stopped near the intersection at an intersection where the vehicle intersects with the intersection. The control unit is capable of controlling at least one of notifying the driver of the vehicle and braking the vehicle based on the first data and the second data. The control unit is capable of performing the following two operations. (C1) In response to a change in the lighting state of a second traffic light for crossing vehicles, which is different from a first traffic light for vehicles, among the plurality of traffic lights, determining the possibility that at least one target vehicle among one or more crossing vehicles will start entering the intersection contrary to the indication of the second traffic light. (C2) Controlling at least one of notification and braking depending on the magnitude of the possibility. [Brief explanation of the drawings]
[0011] The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate one embodiment and, together with the description, serve to explain the principles of the disclosure.
[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of a traffic situation assumed in the first embodiment of the present disclosure. [Figure 2] FIG. 2 is a diagram illustrating an example of functional blocks of a vehicle according to the first embodiment of the present disclosure. [Figure 3] FIG. 3 is a diagram illustrating an example of a driving assistance procedure in the vehicle of FIG. [Figure 4] FIG. 4 is a diagram illustrating a modified example of a traffic situation assumed in the first embodiment of the present disclosure. [Figure 5] FIG. 5 is a diagram illustrating a modified example of a traffic situation assumed in the first embodiment of the present disclosure. [Figure 6]FIG. 6 is a diagram illustrating a modified example of a traffic situation assumed in the first embodiment of the present disclosure. [Figure 7] FIG. 7 is a diagram illustrating a modified example of a traffic situation assumed in the first embodiment of the present disclosure. [Figure 8] FIG. 8 is a diagram illustrating an example of a traffic situation assumed in the second embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating an example of functional blocks of a vehicle according to the second embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of a traffic situation assumed in the third embodiment of the present disclosure. [Figure 11] FIG. 11 is a diagram illustrating an example of functional blocks of a vehicle according to the third embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION
[0013] Some exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that the following description illustrates one specific example of the present disclosure and should not be construed as limiting the present disclosure. For example, each element, including numerical values, shapes, materials, parts, the position of each part, and the connection method of each part, is merely an example and should not be construed as limiting the present disclosure. Furthermore, in the following exemplary embodiments, components not described in independent claims based on the highest concept of the present disclosure are optional and may be provided as needed. The drawings are schematic and are not intended to be drawn to scale. Throughout this specification and the drawings, components having substantially the same function and configuration are designated by the same reference numerals, and redundant description will be omitted. Furthermore, components not directly related to one embodiment of the present disclosure are not shown in the drawings.
[0014] <1. Background> Typically, at intersections with traffic lights, the indications of the traffic lights for vehicles traveling in the same direction and the traffic lights for pedestrians traveling in the same direction are consistent. However, for example, at a pedestrian-vehicle split intersection, the indications of the traffic lights for vehicles traveling in the same direction and the traffic lights for pedestrians may not be consistent. For example, at a pedestrian-vehicle split intersection where a first lane and a second lane intersect, after the traffic light for vehicles in the first lane changes from green to red, the traffic light for vehicles in the second lane may continue to remain red even after the pedestrian traffic light for the crosswalk in the first lane changes from red to green, and then turn green after a predetermined period of time has passed.
[0015] However, drivers who have little or no experience passing through such pedestrian-vehicle split intersections are likely to mistakenly believe that the vehicle and pedestrian traffic lights, which are traveling in the same direction, are green. In this case, the driver may not correctly recognize the vehicle traffic lights, and may mistakenly believe that the pedestrian traffic light is green when looking at the pedestrian traffic light. This may lead to the driver entering the pedestrian-vehicle split intersection without slowing down or attempting to start from a stopped position, which could result in a collision with other traffic participants.
[0016] In addition, pedestrians and cyclists may mistakenly believe that the vehicle and pedestrian traffic lights for vehicles traveling in the same direction are the same. In this case, the pedestrian or cyclist may, for example, be concentrating on operating their device and not carefully checking the pedestrian traffic light, and mistakenly believe that the pedestrian traffic light is green based on the movement of a vehicle traveling in the same direction. As a result, the pedestrian or cyclist may start crossing the crosswalk even though the pedestrian traffic light is red, putting them at risk of colliding with a vehicle turning left or a vehicle turning right from the opposite direction.
[0017] Therefore, after extensive research, the inventors of the present application came up with a technology that can predict the possibility (possibility of misidentification) that the vehicle or other traffic participants will enter an intersection contrary to the indication of the traffic light. Below, we will explain the background of this newly conceived technology by giving an example of a traffic situation in which misidentification may occur.
[0018] FIG. 1 shows an example of a traffic situation in which a misidentification may occur. In FIG. 1, a vehicle (host vehicle) 100a is traveling on a road La with one lane in each direction. The road La is made up of a traveling lane La1 in which the vehicle 100a is traveling and an oncoming lane La2 that runs along the traveling lane La2 with a center line interposed between them. An intersection CL is provided on the road La ahead of the vehicle 100a. The road La intersects with a road Lb at the intersection CL. The road Lb is made up of a traveling lane Lb1 in which the vehicle 100b (intersecting vehicle) is traveling and an oncoming lane Lb2 that runs along the traveling lane Lb1 with a center line interposed between them.
[0019] On road La, a crosswalk CWa and a traffic light TLa are provided in front of and behind intersection CL in relation to vehicle 100a. On road Lb, a crosswalk CWb and a traffic light TLb are provided in front of and behind intersection CL in relation to vehicle 100b.
[0020] Traffic light TLa is in a state (red light) prohibiting entry into intersection CL. Vehicle 100a approaches intersection CL while decelerating and stops just before the stop line. After that, traffic light TLb changes from a state (green light) permitting entry into intersection CL to a state (red light) prohibiting entry into intersection CL. Vehicle 100b decelerates just before the intersection CL in response to this change in the lighting state of traffic light TLb. At this time, the driver of vehicle 100a is not paying close attention to traffic light TLa, but is watching vehicle 100b decelerate just before the intersection CL. In other words, the driver of vehicle 100a is not paying close attention to what is ahead of the vehicle and is looking away. Seeing vehicle 100b decelerating just before the intersection CL, the driver of vehicle 100a has the illusion that traffic light TLa is about to change from a state (red light) prohibiting entry into intersection CL to a state (green light) permitting entry into intersection CL. As a result, the driver of the vehicle 100a mistakenly believes that such a change in the lighting state of the traffic light TLa has occurred and attempts to start the vehicle 100a. In other words, the vehicle 100a attempts to start entering the intersection CL despite the indication of the traffic light TLa.
[0021] If the traffic situation in which the driver of the vehicle 100a may be mistaken as described above could be determined before the vehicle 100a starts to enter the intersection CL, it would be possible to reliably provide a warning or brake the vehicle 100a to avoid a collision with other traffic participants. Therefore, the inventors of the present application have conceived of a technology that can determine a traffic situation in which the driver of the vehicle 100a may be mistaken before the vehicle 100a starts to enter the intersection CL, and can provide a predetermined warning to the driver of the vehicle 100a or brake the vehicle 100a when the vehicle 100a is about to enter the intersection CL. A driving assistance device and a vehicle for realizing this technology will be described in detail below.
[0022] 2. First Embodiment [Configuration example] First, a vehicle 1 equipped with a control unit 30 according to a first embodiment of the present disclosure will be described. FIG. 2 shows an example of functional blocks of the vehicle 1. The control unit 30 corresponds to a specific example of a "driving assistance device" of the present disclosure. The vehicle 1 corresponds to a specific example of a vehicle 100a described below, and corresponds to a specific example of a "vehicle" of the present disclosure.
[0023] The vehicle 1 is capable of traveling by being driven by a prime mover (engine or motor). The vehicle 1 includes, for example, a sensor unit 10, a communication unit 20, a control unit 30, a storage unit 40, a notification unit 50, and an accelerator pedal motor 60, as shown in FIG.
[0024] The sensor unit 10 is configured to include various sensors mounted on the vehicle 1. The sensor unit 10 is configured to include, for example, a brake depression amount sensor, a vehicle speed sensor, an acceleration sensor, and an angular velocity sensor. The sensor unit 10 may also include sensors other than those described above.
[0025] The brake depression amount sensor is capable of detecting the amount of depression of the brake pedal and outputting time-series data (brake depression amount data) on the detected depression amount to the control unit 30.
[0026] The vehicle speed sensor is capable of detecting the speed (vehicle speed) of the vehicle 1. The vehicle speed sensor is capable of outputting time series data (vehicle speed data) about the detected vehicle speed to the control unit 30. The acceleration sensor is capable of detecting acceleration applied to the vehicle 1. The acceleration sensor is capable of outputting time series data (acceleration data) about the detected acceleration in three directions to the control unit 30. The angular velocity sensor is capable of detecting the angular velocity of the vehicle 1. The angular velocity sensor is capable of outputting time series data (angular velocity data) about the detected three angular velocities (yaw angular velocity, roll angular velocity, pitch angular velocity) to the control unit 30.
[0027] The sensor unit 10 further includes a camera capable of capturing images of the interior of the vehicle 1, including the driver of the vehicle 1, and a driver state detection unit. The camera is placed at a position where the driver of the vehicle 1 is the subject of image capture, and is capable of outputting image data obtained by capturing the image to the driver state detection unit. The driver state detection unit is capable of outputting data (gaze data Da) regarding the line of sight or facial direction of the driver of the vehicle 1 to the control unit 30 based on the image data.
[0028] The sensor unit 10 further includes a stereo camera and a driving environment detection unit. The stereo camera is an autonomous sensor that senses the real space around the vehicle 1. The stereo cameras are arranged, for example, at symmetrical positions on either side of the central part in the width direction of the vehicle 1, and are capable of capturing stereo images of the area in front of the vehicle 1 from different viewpoints. The stereo cameras are capable of outputting image data Db (a pair of stereo image data) obtained by capturing images to the control unit 30.
[0029] The stereo camera is capable of generating distance image data Dc calculated from the amount of displacement between corresponding objects based on image data Db (a pair of stereo image data) obtained by capturing images. The driving environment detection unit is capable of, for example, calculating lane markings that divide the road around the vehicle 1 based on the distance image data Dc. The driving environment detection unit is also capable of calculating the road curvature of the markings that divide the left and right sides of the road (driving lane) on which the vehicle 1 is traveling, and the width between the left and right markings (vehicle width). The driving environment detection unit is also capable of performing predetermined pattern matching on the distance image data Dc to detect lanes and three-dimensional objects such as structures present around the vehicle 1.
[0030] Here, when detecting a three-dimensional object in the driving environment detection unit, for example, the type of the three-dimensional object, the distance to the three-dimensional object, the speed of the three-dimensional object, and the relative speed between the three-dimensional object and the vehicle (host vehicle) are detected. Examples of three-dimensional objects to be detected include traffic lights, intersections, road signs, stop lines, other vehicles, pedestrians, bicycles, and buildings. Examples of buildings include detached houses, apartment complexes (condominiums), commercial facilities, factories, and signs. The driving environment detection unit is capable of outputting driving environment data Dd around the vehicle 1, including the thus acquired information on the three-dimensional object, to the control unit 30.
[0031] The communication unit 20 can acquire data to supplement data that cannot be obtained from the image data Db and the distance image data Dc, for example, through vehicle-to-vehicle communication, road-to-vehicle communication, and satellite communication. The communication unit 20 can output the acquired data to the control unit 30.
[0032] The communication unit 20 is capable of acquiring data (e.g., vehicle position, vehicle speed) obtained by other vehicles, for example, through vehicle-to-vehicle communication. The communication unit 20 is capable of receiving positioning signals transmitted from multiple positioning satellites, for example, through satellite communication.
[0033] The communication unit 20 is capable of acquiring road map data of the surroundings of the vehicle 1, for example, through road-to-vehicle communication. The road map data consists of, for example, highly accurate road map information (dynamic map), and has static information and quasi-static information that mainly constitute road information, and quasi-dynamic information and dynamic information that mainly constitute traffic information.
[0034] Static information that makes up road information includes information that needs to be updated within one month, such as roads, structures on roads, structures around roads, lane information, road surface information, and permanent traffic regulations. "Roads" include, for example, road locations and shapes, intersections, and road attributes (e.g., national roads, prefectural roads, city roads, private roads, priority roads, non-priority roads, general roads, and expressways). "Structures on roads" include, for example, traffic signs, traffic lights, convex mirrors, footbridges, bus stops, and garbage collection stations. "Structures around roads" include, for example, various buildings and parks.
[0035] The quasi-static information that constitutes road information is composed of information that needs to be updated every hour or less, such as traffic regulation information due to road construction or events, wide-area weather information, and traffic congestion forecasts.
[0036] The semi-dynamic information that makes up traffic information is composed of information that must be updated within one minute, such as the actual traffic congestion situation at the time of observation, driving restrictions, temporary driving obstructions such as fallen objects and obstacles, actual accident conditions, and narrow-area weather information.
[0037] The dynamic information that constitutes the traffic information is composed of information that needs to be updated every second, such as information sent and exchanged between moving bodies, information on currently displayed traffic signals, information on pedestrians and bicycles at intersections, information on vehicles traveling on roads, etc. Such road map information is maintained and updated periodically until the next information is received from each vehicle, and the updated road map information is transmitted to each vehicle as appropriate via the communication unit 20.
[0038] The control unit 30 is capable of controlling the entire vehicle 1. The control unit 30 is, for example, a so-called ECU (Electronic Control Unit) and is configured to include, for example, one or more processors and one or more memories. The control unit 30 may be configured to include, for example, a CPU (Central Processing Unit). In this case, the control unit 30 is capable of controlling the entire vehicle 1 by, for example, executing a program stored in a storage unit.
[0039] The control unit 30 includes, for example, a locator unit. The locator unit is capable of acquiring the position coordinates of the vehicle 1 based on the positioning signal received through the communication unit 20. The locator unit is capable of estimating the vehicle's position on a road map by map-matching the acquired position coordinates with route map information. Based on the acquired position coordinates of the vehicle 1, the locator unit acquires map information of a predetermined range including the vehicle 1 from map information stored in a road map DB (database) 41 (described later).
[0040] In an environment where it is not possible to receive valid positioning signals from positioning satellites due to reduced sensitivity, such as when driving inside a tunnel, the locator unit can switch to autonomous navigation, which estimates the vehicle's position based on the vehicle speed, angular velocity, and longitudinal acceleration detected by sensor unit 10, and estimate the vehicle's position on a road map.
[0041] As described above, the locator unit estimates the position of vehicle 1 (vehicle position) on a road map based on the positioning signal received through communication unit 20 or information detected by sensor unit 10, and is then able to determine the road type, etc. of the road on which vehicle 1 is traveling based on the estimated vehicle position on the road map.
[0042] The locator unit adds data about the estimated vehicle position to the passage history data 42 together with the passage time, thereby updating the passage history data 42 to the latest state. The locator unit is able to update the road map information stored in the road map DB 41 to the latest state using road map information acquired by external communication (roadside-to-vehicle communication and vehicle-to-vehicle communication) via the communication unit 20. This information update is performed not only on static information, but also on quasi-static information, quasi-dynamic information, and dynamic information. As a result, the road map information includes road information and traffic information acquired by communication outside the vehicle, and information on moving objects such as vehicles traveling on roads is updated in approximately real time.
[0043] The locator unit verifies road map information based on the traveling environment data Dd recognized as described above, and updates the road map information stored in the road map DB 41 to the latest version. This information update is performed not only on static information, but also on quasi-static information, quasi-dynamic information, and dynamic information. As a result, information on moving objects such as vehicles traveling on roads recognized as described above is updated in real time.
[0044] The control unit 30 further includes a driving control unit 31, for example, as shown in Fig. 2. The driving control unit 31 is capable of controlling the driving of the vehicle 1 (for example, the accelerator pedal depression amount) and notifications related to the driving of the vehicle 1. The driving control unit 31 includes, for example, a data acquisition unit 32, an error determination unit 33, an assistance determination unit 34, a notification control unit 35, and an accelerator pedal control unit 36, as shown in Fig. 2.
[0045] The data acquisition unit 32 is capable of acquiring various data acquired from the sensor unit 10, various data acquired from the outside via the communication unit 20, and various control signals for various devices of the vehicle 1 (e.g., turn signals). The data acquisition unit 32 is capable of acquiring the following lighting state data De, the following other vehicle data Df, and the above-mentioned gaze data Da based on the acquired various data and various control signals. The data acquisition unit 32 is further capable of reading out passage history data Dg of an intersection CL ahead of the vehicle 100a from the passage history data 42 stored in the memory unit 40. The memory unit 40 is configured to include, for example, a non-volatile memory. For example, as shown in FIG. 2, the memory unit 40 stores a road map DB 41 and passage history data Dg. Note that the following symbols correspond to the symbols in FIG. 1. The lighting state data De corresponds to a specific example of "first data" in the present disclosure. The gaze data Da corresponds to a specific example of "second data" in the present disclosure. The traffic participant data Df corresponds to a specific example of "sixth data" in the present disclosure.
[0046] (Lighting status data Dd) The lighting state data Dd is data about the lighting state of multiple traffic lights (e.g., traffic lights TLa, TLb) installed at an intersection CL ahead of the stopped vehicle 100a. The lighting state data Dd is data about the lighting state of multiple traffic lights (e.g., traffic lights TLa, TLb) installed at the intersection CL when there are no other vehicles ahead of the vehicle 100a before the intersection CL (i.e., when the vehicle 100a is at the front of a line of vehicles). Traffic light TLa corresponds to a specific example of a "first traffic light" in the present disclosure. Traffic light TLb corresponds to a specific example of a "second traffic light" in the present disclosure.
[0047] (Other vehicle data Df) The other vehicle data Df is data about the vehicle 100b that is present on the road Lb, for example, data about the position and speed of the vehicle 100b that is present on the road Lb.
[0048] (Passage history data Dg) The passage history data Dg is data on the history of the vehicle 100a passing through the intersection CL. In the passage history data Dg, for example, position data of the vehicle 100a is stored in association with the passage time.
[0049] The misconception determination unit 33 is capable of detecting a change in the lighting state of the traffic light TLb based on the lighting state data Dd. "A change in the lighting state of the traffic light TLb" refers to a change in the lighting state of the traffic light TLb from a state in which entry into the intersection CL is permitted (green light) to a state in which entry into the intersection CL is prohibited (red light). Hereinafter, data regarding the change in the lighting state of the traffic light TLb based on the lighting state data Dd will be referred to as state change data Dh.
[0050] When the error determination unit 33 detects a change in the lighting state of the traffic light TLb (when the state change data Dh is obtained), it is possible to detect, based on the other vehicle data Df, a traffic situation in which the vehicle 100b is decelerating or stopping before the intersection CL in response to the change in the lighting state of the traffic light TLb. Hereinafter, data on a traffic situation in which the vehicle 100b is decelerating or stopping before the intersection CL in response to the change in the lighting state of the traffic light TLb will be referred to as other vehicle data Di. The other vehicle data Di corresponds to a specific example of "third data" in the present disclosure.
[0051] The misidentification determination unit 33 is capable of determining the possibility that the vehicle 100a will start entering the intersection CL despite the indication of the traffic light TLa in response to a change in the illumination state of the traffic light TLb. When the other vehicle data Di is obtained, the misidentification determination unit 33 is capable of determining the possibility based on the line of sight or facial direction of the driver of the vehicle 100a obtained from the gaze data Da. For example, when the other vehicle data Di is obtained, the misidentification determination unit 33 is capable of determining that the possibility is high when the line of sight or facial direction of the driver of the vehicle 100a obtained from the gaze data Da is directed toward the vehicle 100b. For example, when the other vehicle data Di is obtained, the misidentification determination unit 33 is capable of determining that the possibility is high when the line of sight or facial direction of the driver of the vehicle 100a is directed toward the vehicle 100b while the vehicle 100b is decelerating or stopped in front of the intersection CL in response to a change in the illumination state of the traffic light TLb. The misidentification determination unit 33 is capable of determining the magnitude of the above-mentioned possibility, for example, based on the length of time that the driver of vehicle 100a's line of sight or face is directed toward vehicle 100b while vehicle 100b is slowing down or stopped in front of intersection CL in response to a change in the lighting state of traffic light TLb.
[0052] The determination of whether the line of sight or the direction of the face of the driver of vehicle 100a is directed toward vehicle 100b is made, for example, based on whether the direction of the face or line of sight of the driver of vehicle 100a is within a predetermined range of viewing angle θa that includes the direction of vehicle 100b. The misperception determination unit 33 can determine that the above-mentioned possibility is high, for example, when the direction of the face or line of sight of the driver of vehicle 100a is within the range of viewing angle θa. In other words, when vehicle 100a is stopped before intersection CL (before the stop line), if the driver of vehicle 100a is not gazing at what is ahead of the vehicle (for example, traffic light TLa) but is looking away for a long time, the misperception determination unit 33 can determine that the above-mentioned possibility is high.
[0053] The misconception determination unit 33 is capable of determining the above possibility based on the passage history data Dg. For example, the misconception determination unit 33 can count the number of pieces of position data corresponding to the position data of the intersection CL that are included in the passage history data Dg, and use the count value obtained thereby as the number of times Co the intersection CL has been passed. For example, the misconception determination unit 33 is capable of determining the above possibility based on the number of times Co the intersection CL has been passed.
[0054] The error determination unit 33 is capable of calculating, as a numerical value (error rate R), the magnitude of the possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa in response to a change in the lighting state of the traffic light TLb. The error determination unit 33 is capable of calculating the error rate R, for example, using the following formulas (1) to (5).
[0055] R=αFego+βVego+γAego+ε…(1) α+β+γ+ε=1…(2) Fego=1 / Co…(3) Vego=1-(T1 / T2)…(4) Aego:1-(D1 / D2)…(5)
[0056] Fego: Frequency of passing through intersection CL by the driver of vehicle 100a (value between 0 and 1) Vego: The visual observation rate of the traffic light TLa by the driver of vehicle 100a (value between 0 and 1) Aego: Amount of brake pedal operation by the driver of vehicle 100a (value between 0 and 1) α, β, γ: coefficients (values between 0 and 1) ε: Correction value (value between 0 and 1) T1: visual inspection time (s) of traffic light TLa by the driver of vehicle 100a T2: Time (s) that vehicle 100a is stopped waiting for a traffic light D1: Brake pedal depression amount by the driver of the vehicle 100a D2: Maximum brake pedal depression amount
[0057] The support decision unit 34 can determine the driving support method based on the magnitude of the misrecognition ratio R obtained by the misrecognition determination unit 33. The support decision unit 34 can control at least one of the notification to the driver of the vehicle 100a and the braking of the vehicle 100a based on the magnitude of the misrecognition ratio R obtained by the misrecognition determination unit 33.
[0058] When the misrecognition ratio R is small (0 < R1~R2), the driver of the vehicle 100a has a low possibility of misrecognizing that a change in the lighting state of the traffic signal TLa has occurred. Here, R1 is, for example, 0.3, and R2 is, for example, 0.5. At this time, the support decision unit 34 can select notification as the driving support method and determine to perform icon display as the notification method. The support decision unit 34 can output a control signal for performing icon display to the notification control unit 35.
[0059] When the misrecognition ratio R is medium (R2~R3), the driver of the vehicle 100a has a relatively high possibility of misrecognizing that a change in the lighting state of the traffic signal TLa has occurred. Here, R3 is, for example, 0.7. At this time, the support decision unit 34 can select notification as the driving support method and determine to perform not only icon display but also emit a warning sound (for example, a beep sound) as the notification method. The support decision unit 34 can output a control signal for performing icon display and warning sound emission to the notification control unit 35.
[0060] When the misrecognition rate R is high (R3 to R1), the support decision unit 34 determines that the driver of the vehicle 100a is highly likely to have mistakenly recognized that a change in the illumination state of the traffic light TLa has occurred. In this case, the support decision unit 34 can select both notification and braking as the driving support method, and can determine that not only the icon display but also a warning sound (e.g., a beep) or a warning voice (an announcement to warn of a danger) is issued as the notification method, and further determine that the braking method is to limit accelerator pedal depression. The support decision unit 34 can output a control signal to the notification control unit 35 for displaying the icon and issuing the warning sound or warning voice. The support decision unit 34 can also output a control signal to the accelerator pedal control unit 36 for limiting accelerator pedal depression.
[0061] The notification control unit 35 is capable of causing the notification unit 50 to issue a notification in accordance with a control signal input from the assistance determination unit 34. When a control signal for displaying an icon is input from the assistance determination unit 34, the notification control unit 35 is capable of outputting a video signal for displaying an icon based on the input control signal to the notification unit 50. An example of the icon is an image of a traffic light showing a red light. The notification unit 50 is, for example, a display device, and is capable of displaying an image according to the video signal input from the notification control unit 35. The driver of the vehicle 100a can realize his or her mistake by looking at the display on the notification unit 50 and can stop the start of the vehicle 100a.
[0062] When a control signal for issuing a warning sound (e.g., a beep) or a warning voice (announcement informing of a danger) is input from the assistance determination unit 34, the notification control unit 35 is capable of outputting a sound signal for outputting a sound based on the input control signal to the notification unit 50. The notification unit 50 is, for example, a speaker or a display device with a sound output function, and is capable of outputting a sound corresponding to the sound signal input from the notification control unit 35. The driver of the vehicle 100a becomes aware of his or her own mistake by hearing the sound output from the notification unit 50, and is able to stop the start of the vehicle 100a.
[0063] The accelerator pedal control unit 36 is capable of limiting accelerator pedal depression in accordance with a control signal input from the assistance decision unit 34. When the accelerator pedal control unit 36 receives a control signal for limiting accelerator pedal depression from the assistance decision unit 34, it is capable of outputting a torque control signal based on the input control signal to the accelerator pedal motor 60. The accelerator pedal motor 60 is capable of outputting torque that limits accelerator pedal depression to a connecting member connected to the accelerator pedal, which displaces in accordance with accelerator pedal depression. The driver of the vehicle 100a becomes aware of his or her mistake when the accelerator pedal depression is restricted, and is able to stop the vehicle 100a by changing the pedal that is depressed from the accelerator pedal to the brake pedal.
[0064] Next, a driving assistance procedure for the vehicle 1 in the traffic situation of FIG. 1 will be described.
[0065] 3 shows an example of a driving assistance procedure in the vehicle 1. The driving control unit 31 acquires various data including image data Db and the like (step S101). The driving control unit 31 also acquires various control signals as necessary. Next, the driving control unit 31 determines whether or not an intersection CL exists ahead of the vehicle 100a (host vehicle) based on the acquired various data and various control signals (step S102). The driving control unit 31 detects the intersection CL ahead of the vehicle 100a based on, for example, the image data Db.
[0066] When the driving control unit 31 determines that an intersection CL exists ahead of the vehicle 100a (step S102; Y), it determines whether the intersection CL is an intersection where traffic is controlled according to a normal traffic light schedule based on the acquired various data and control signals (step S103). An "intersection where traffic is controlled according to a normal traffic light schedule" refers to an intersection where, among the vehicular traffic lights provided on each of two intersecting roads (a first road and a second road), the vehicular traffic light on the second road changes from red to green in synchronization with the vehicular traffic light on the first road changing from green to red. Also, an "intersection where traffic is controlled according to a normal traffic light schedule" refers to an intersection where, among the pedestrian traffic lights provided on each of two intersecting roads (a first road and a second road), the pedestrian traffic light on the second road changes from red to green in synchronization with the pedestrian traffic light on the first road changing from green to red. The driving control unit 31 determines, for example, based on the information of the intersection CL included in the traffic road map DB 41, whether or not the intersection CL is an intersection where traffic control is performed according to a normal traffic light schedule.
[0067] If the driving control unit 31 determines that the intersection CL is not an intersection where traffic control is performed according to a normal traffic light schedule (step S103; N), the driving control unit 31 determines whether or not there is another vehicle ahead of the vehicle 100a before the intersection CL (i.e., whether the vehicle 100a is at the head of the vehicle train) based on the acquired various data and various control signals (step S104). The driving control unit 31 detects whether or not there is another vehicle ahead of the vehicle 100a based on, for example, image data Db.
[0068] When the driving control unit 31 determines that the vehicle 100a is at the front of the convoy (step S104; Y), it calculates the probability of misidentification by the driver of the vehicle 100a (misidentification rate R) based on the acquired various data and various control signals (step S105).The driving control unit 31 controls at least one of notifying the driver of the vehicle 100a and braking the vehicle 100a according to the magnitude of the calculated probability of misidentification (misidentification rate R) (step S106).
[0069] If the driving control unit 31 does not want to end the driving assistance (step S107; N), the process returns to step S101. In this manner, driving assistance for the vehicle 1 in the traffic situation of FIG.
[0070] [effect] Next, the effects of the vehicle 1 will be described.
[0071] In this embodiment, in response to a change in the illumination state of traffic light TLb, a determination is made as to the possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of traffic light TLa, and at least one of a notification and braking is controlled depending on the magnitude of the obtained possibility. This makes it possible to notify the driver of vehicle 100a or to brake vehicle 100a before the driver of vehicle 100a erroneously enters the intersection CL as a result of looking away and not carefully looking ahead of vehicle 100a.
[0072] In this embodiment, the possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa is determined based on the line of sight or the direction of the face of the driver of the vehicle 1. This makes it possible to notify the driver of the vehicle 100a or to brake the vehicle 100a before the driver of the vehicle 100a mistakenly causes the vehicle 100a to enter the intersection CL by looking away instead of carefully looking ahead of the vehicle 100a.
[0073] In this embodiment, when the vehicle 100b is slowing down or stopping before the intersection CL in response to a change in the illumination state of the traffic light TLb, and the line of sight or face of the driver of the vehicle 100a is facing the direction of the vehicle 100b, it is determined that there is a high possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa. This makes it possible to notify the driver of the vehicle 100a or to brake the vehicle 100a before the driver of the vehicle 100a mistakenly enters the intersection CL as a result of not looking carefully ahead of the vehicle 100a and being distracted by the movement of the vehicle 100b.
[0074] In this embodiment, the possibility that the vehicle 100a will start entering the intersection CL despite the indication of the traffic light TLa is determined based on the vehicle 100a's history of passing through the intersection CL. This makes it possible to notify the driver of the vehicle 100a or brake the vehicle 100a before the driver of the vehicle 100a mistakenly enters the intersection CL due to being unfamiliar with the traffic control characteristics at the intersection CL.
[0075] <3. Modification of the First Embodiment> Next, a vehicle 1 according to a modification of the first embodiment will be described.
[0076] Other traffic situations in which the driver of the vehicle 100a may mistakenly believe that a change in the lighting state of the traffic light TLa has occurred include, for example, the traffic situations shown in Figures 4, 5, 6, and 7. Figures 4, 5, 6, and 75 show other examples of traffic situations in which the driver of the vehicle 100a may mistakenly believe that a change in the lighting state of the traffic light TLa has occurred.
[0077] [Variation A] FIG. 4 shows an example of a traffic situation in which a misperception may occur. In FIG. 4, the driver of vehicle 100a is not paying close attention to traffic light TLa, but is instead watching the change in the lighting state of traffic light TLb. In other words, the driver of vehicle 100a is not paying close attention to the area ahead of the vehicle, but is instead looking away. Seeing the change in the lighting state of traffic light TLb, the driver of vehicle 100a is under the illusion that traffic light TLa is about to change from a state prohibiting entry into intersection CL (red light) to a state permitting entry into intersection CL (green light). As a result, the driver of vehicle 100a mistakenly believes that such a change in the lighting state of traffic light TLa has occurred and attempts to start vehicle 100a. In other words, vehicle 100a attempts to start entering intersection CL despite the warning from traffic light TLa.
[0078] In the traffic situation shown in Fig. 4, the misconception determination unit 33 is capable of determining the possibility that the vehicle 100a will start entering the intersection CL in response to a change in the lighting state of traffic light TLb, contrary to the indication of traffic light TLa. When a change in the lighting state of traffic light TLb is detected (when state change data Dh is obtained), the misconception determination unit 33 is capable of determining that the above possibility is high if the line of sight or the facial direction of the driver of the vehicle 100a obtained from the line of sight data Da is directed toward traffic light TLb. For example, the misconception determination unit 33 is capable of determining that the above possibility is high when the line of sight or the facial direction of the driver of the vehicle 100a is directed toward traffic light TLb while the lighting state of traffic light TLb is changing (for example, while traffic light TLb changes from green to yellow and from yellow to red). The misperception determination unit 33 is capable of determining the magnitude of the above-mentioned possibility, for example, depending on the length of time that the line of sight or face of the driver of the vehicle 100a is directed toward the traffic light TLb while the lighting state of the traffic light TLb is changing.
[0079] In such a traffic situation, similarly to the above embodiment, a possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa is determined in accordance with a change in the lighting state of the traffic light TLb, and at least one of a warning and braking is controlled depending on the magnitude of the obtained possibility. This makes it possible to warn the driver of the vehicle 100a or to brake the vehicle 100a before the driver of the vehicle 100a mistakenly enters the intersection CL as a result of looking away and not carefully looking ahead of the vehicle 100a.
[0080] [Variation B] FIG. 5 illustrates an example of a traffic situation in which misidentification may occur. In FIG. 5, a traffic light TLc for pedestrian 100c and cyclist 100d crossing a crosswalk CWb is provided at an intersection CL. Pedestrian traffic light TLc changes its state from a state prohibiting entry into the crosswalk CWb (red light) to a state permitting entry into the crosswalk CWb (green light) in synchronization with a change in the lighting state of traffic light TLb. Pedestrian 100c and cyclist 100d see this change in the lighting state of traffic light TLbc and begin to enter the crosswalk CWb. The driver of vehicle 100a is not paying close attention to traffic light TLa, but is watching the movements of pedestrian 100c and cyclist 100d (their start of entry into the crosswalk CWb). In other words, the driver of vehicle 100a is not paying close attention to the road ahead of the vehicle and is instead looking away. The driver of vehicle 100a, seeing the movements of pedestrian 100c and bicyclist 100d, has the misconception that traffic light TLa and traffic light TLb have changed from a state prohibiting entry into intersection CL (red light) to a state permitting entry into intersection CL (green light). As a result, the driver of vehicle 100a mistakenly believes that such a change in the lighting state of traffic light TLa has occurred and attempts to start vehicle 100a. In other words, vehicle 100a attempts to start entering intersection CL despite the indication of traffic light TLa.
[0081] In the traffic situation shown in FIG. 5, the data acquisition unit 32 is able to acquire the following lighting state data Dj, the following pedestrian data Dk, and gaze data Da based on the acquired various data and various control signals. The data acquisition unit 32 is further able to read out passage history data Dg of an intersection CL ahead of the vehicle 100a from the passage history data 42 in the memory unit 40. The following symbols correspond to the symbols in FIG. 5. The lighting state data Dj corresponds to a specific example of "first data" in the present disclosure. The gaze data Da corresponds to a specific example of "second data" in the present disclosure. The pedestrian data Dk corresponds to a specific example of "fourth data" in the present disclosure. The traffic participant data Df corresponds to a specific example of "sixth data" in the present disclosure.
[0082] (Lighting status data Dj) The lighting state data Dj is data about the lighting state of multiple traffic lights (e.g., traffic lights TLa, TLb, TLc) installed at an intersection CL ahead of the stopped vehicle 100a. The lighting state data Dj is data about the lighting state of multiple traffic lights (e.g., traffic lights TLa, TLb, TLc) installed at the intersection CL when there are no other vehicles ahead of the vehicle 100a just before the intersection CL (i.e., when the vehicle 100a is at the front of a line of vehicles). Traffic light TLa corresponds to a specific example of a "first traffic light" in the present disclosure. Traffic light TLc corresponds to a specific example of a "second traffic light" in the present disclosure.
[0083] (Pedestrian Data Dk) The pedestrian data Dk is data about a pedestrian 100c and a bicyclist 100d near the intersection CL, for example, data about the position and speed of the pedestrian 100c and the bicyclist 100d near the intersection CL.
[0084] The misconception determination unit 33 is capable of detecting a change in the lighting state of the traffic light TLc based on the lighting state data Dj. A "change in the lighting state of the traffic light TLc" refers to a change in the lighting state of the traffic light TLc from a state in which entry into the pedestrian crossing CWb is prohibited (red light) to a state in which entry into the pedestrian crossing CWb is permitted (green light). Hereinafter, data regarding a change in the lighting state of the traffic light TLc based on the lighting state data Dj will be referred to as state change data Dl.
[0085] The misperception determination unit 33 is capable of determining the possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa as the lighting state of the traffic light TLc changes. When the misperception determination unit 33 detects a change in the lighting state of the traffic light TLc (when the state change data Dl is obtained), it is capable of determining the possibility based on the line of sight or the facial direction of the driver of the vehicle 100a obtained from the line of sight data Da.
[0086] When a change in the lighting state of traffic light TLc is detected (when state change data Dl is obtained), if the direction of the line of sight or face of the driver of vehicle 100a obtained from the gaze data Da is directed toward pedestrian 100c and bicyclist 100d, the misperception determination unit 33 can determine that the above possibility is high. For example, when the direction of the line of sight or face of the driver of vehicle 100a is directed toward pedestrian 100c and bicyclist 100d while the lighting state of traffic light TLc is changing (for example, while traffic light TLc is changing from a state prohibiting entry to pedestrian crossing CWb (red light) to a state permitting entry to pedestrian crossing CWb (green light)), the misperception determination unit 33 can determine that the above possibility is high. The misidentification determination unit 33 is capable of determining the magnitude of the above-mentioned possibility, for example, based on the length of time that the line of sight or face of the driver of the vehicle 100a is directed in the direction of the pedestrian 100c and the bicyclist 100d while the lighting state of the traffic light TLc is changing.
[0087] 5, as in the above embodiment, a possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa is determined in accordance with a change in the lighting state of the traffic light TLc, and at least one of a warning and braking is controlled depending on the magnitude of the obtained possibility. This makes it possible to warn the driver of the vehicle 100a or to brake the vehicle 100a before the driver of the vehicle 100a mistakenly enters the intersection CL as a result of looking away and not carefully looking ahead of the vehicle 100a.
[0088] [Variation C] FIG. 6 illustrates an example of a traffic situation in which misperception may occur. In FIG. 6, a traffic light TLc for pedestrian 100c and cyclist 100d crossing a crosswalk CWb is provided at an intersection CL. In synchronization with a change in the lighting state of traffic light TLb, traffic light TLc for pedestrians changes from a state in which traffic light TLc prohibits entry into the crosswalk CWb (red light) to a state in which traffic light TLc permits entry into the crosswalk CWb (green light). Seeing this change in the lighting state of traffic light TLbc, pedestrian 100c and cyclist 100d begin entering the crosswalk CWb. The driver of vehicle 100a is not paying close attention to traffic light TLa, but is instead watching the change in the lighting state of traffic light TLbc. In other words, the driver of vehicle 100a is not paying close attention to the area ahead of the vehicle, but is instead looking away. The driver of the vehicle 100a, seeing the change in the lighting state of the traffic light TLbc, has the misconception that the traffic light TLa has changed from a state in which the traffic light TLb prohibits entry into the intersection CL (red light) to a state in which entry into the intersection CL is permitted (green light). As a result, the driver of the vehicle 100a mistakenly believes that such a change in the lighting state of the traffic light TLa has occurred and attempts to start the vehicle 100a. In other words, the vehicle 100a attempts to start entering the intersection CL despite the indication of the traffic light TLa.
[0089] The misconception determination unit 33 is capable of detecting a change in the lighting state of the traffic light TLc based on the lighting state data Dj. A "change in the lighting state of the traffic light TLc" refers to a change in the lighting state of the traffic light TLc from a state in which entry into the pedestrian crossing CWb is prohibited (red light) to a state in which entry into the pedestrian crossing CWb is permitted (green light). Hereinafter, data regarding a change in the lighting state of the traffic light TLc based on the lighting state data Dj will be referred to as state change data Dl.
[0090] The misperception determination unit 33 is capable of determining the possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa as the lighting state of the traffic light TLc changes. When the misperception determination unit 33 detects a change in the lighting state of the traffic light TLc (when the state change data Dl is obtained), it is capable of determining the possibility based on the line of sight or the facial direction of the driver of the vehicle 100a obtained from the line of sight data Da.
[0091] When detecting a change in the lighting state of the traffic light TLc (when the state change data Dl is obtained), the misconception determination unit 33 can determine that the above possibility is high if the line of sight or the facial direction of the driver of the vehicle 100a obtained from the line of sight data Da is directed toward the traffic light TLc. The misconception determination unit 33 can determine that the above possibility is high, for example, when the line of sight or the facial direction of the driver of the vehicle 100a is directed toward the traffic light TLc while the lighting state of the traffic light TLc is changing (for example, while the traffic light TLc is changing from a state prohibiting entry into the pedestrian crossing CWb (red light) to a state permitting entry into the pedestrian crossing CWb (green light)). The misconception determination unit 33 can determine the magnitude of the above possibility based on, for example, the length of time that the line of sight or the facial direction of the driver of the vehicle 100a is directed toward the traffic light TLc while the lighting state of the traffic light TLc is changing.
[0092] 6, as in the above embodiment, a possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLa is determined in accordance with a change in the lighting state of the traffic light TLc, and at least one of a warning and braking is controlled depending on the magnitude of the obtained possibility. This makes it possible to warn the driver of the vehicle 100a or to brake the vehicle 100a before the driver of the vehicle 100a mistakenly enters the intersection CL as a result of looking away and not carefully looking ahead of the vehicle 100a.
[0093] [Variation D] FIG. 7 shows an example of a traffic situation in which a misidentification may occur. In FIG. 7, vehicle (host vehicle) 100a is traveling on road Lc, which has two lanes on each side. Road Lc is composed of a lane Lc1 in which vehicle 100a is traveling, a lane Lc2 in which vehicle 100e is traveling and whose traveling direction is the same as lane La1, and two oncoming lanes Lc3 and Lc4 that are provided along lane Lc2 with a center line interposed between them. In oncoming lane Lc3, vehicle 100f is traveling in the opposite direction to vehicle 100a, and in oncoming lane Lc4, vehicle 100g is traveling in the opposite direction to vehicle 100a. On road Lc, intersections CL are provided ahead of vehicles 100a and 100e and ahead of vehicles 100f and 100g. Road Lc intersects with road Lb at intersection CL. The road Lb is made up of a driving lane Lb1 and an oncoming lane Lb2.
[0094] On road Lc, a crosswalk CWa and traffic lights TLc3 and TLc4 for vehicles are provided just before intersection CL in relation to vehicles 100a and 100e, and a crosswalk CWa and traffic lights TLc1 and TLc2 are provided further back from intersection CL in relation to vehicles 100a and 100e.
[0095] Traffic lights TLc1, TLc2, TLc3, and TLc4 are in a state (red light) prohibiting entry into the intersection CL. Furthermore, traffic light TLb is in a state (red light) prohibiting entry into the intersection CL. Vehicles 100a, 100b, 100f, and 100g approach the intersection CL while decelerating and stop just before the stop line. After that, traffic lights TLc2 and TLc3 change from a state (red light) prohibiting entry into the intersection CL to a state (green light) permitting entry into the intersection CL. In response to this change in the lighting status of traffic lights TLc2 and TLc3, vehicles 100e and 100f begin entering the intersection CL. At this time, the driver of vehicle 100a is not paying close attention to traffic light TLc1, but is watching vehicle 100e begin to move. In other words, the driver of vehicle 100a is not paying close attention to the area ahead of the vehicle and is looking away. The driver of vehicle 100a, seeing vehicle 100e starting to move, has the misconception that traffic light TLc1 has changed from a state prohibiting entry into intersection CL (red light) to a state permitting entry into intersection CL (green light). As a result, the driver of vehicle 100a mistakenly believes that such a change in the lighting state of traffic light TLc1 has occurred and attempts to start vehicle 100a. In other words, vehicle 100a attempts to start entering intersection CL despite the indication of traffic light TLc1.
[0096] In the traffic situation shown in FIG. 7, the data acquisition unit 32 is able to acquire the following lighting state data Dm, the following other vehicle data Dn, and the above gaze data Da based on the acquired various data and various control signals. The data acquisition unit 32 is further able to read out passage history data Dg of an intersection CL ahead of the vehicle 100a from the passage history data 42 in the memory unit 40. The following symbols correspond to the symbols in FIG. 7. The lighting state data Dm corresponds to a specific example of "first data" in the present disclosure. The other vehicle data Dn corresponds to a specific example of "fifth data" in the present disclosure. The gaze data Da corresponds to a specific example of "second data" in the present disclosure. The traffic participant data Df corresponds to a specific example of "sixth data" in the present disclosure.
[0097] (Lighting status data Dm) The lighting state data Dm is data about the lighting state of a plurality of traffic lights (e.g., traffic lights TLc1 to TLc4) installed at an intersection CL ahead of the stopped vehicle 100a. The lighting state data Dm is data about the lighting state of a plurality of traffic lights (e.g., traffic lights TLc1 to TLc4) installed at the intersection CL when there are no other vehicles ahead of the vehicle 100a before the intersection CL (i.e., when the vehicle 100a is at the front of a line of vehicles). Traffic light TLc1 corresponds to a specific example of a "first traffic light" in the present disclosure. Traffic light TLc2 corresponds to a specific example of a "second traffic light" in the present disclosure.
[0098] (Other vehicle data Dn) The other vehicle data Dn is data about the vehicle 100e that is present in the driving lane Lc2, for example, data about the position and speed of the vehicle 100e that is present in the driving lane Lc2.
[0099] The misconception determination unit 33 is capable of detecting a change in the lighting state of the traffic lights TLc2 and TLc3 based on the lighting state data Dm. "A change in the lighting state of the traffic lights TLc2 and TLc3" refers to a change in the lighting state of the traffic lights TLc2 and TLc3 from a state in which entry into the intersection CL is prohibited (red light) to a state in which entry into the intersection CL is permitted (green light). Hereinafter, data regarding the change in the lighting state of the traffic lights TLc2 and TLc3 based on the lighting state data Dm will be referred to as state change data Do.
[0100] The misperception determination unit 33 is capable of determining the possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLc1 as the lighting states of the traffic lights TLc2 and TLc3 change. When the misperception determination unit 33 detects a change in the lighting states of the traffic lights TLc2 and TLc3 (when the state change data Do is obtained), it is capable of determining the possibility based on the line of sight or facial direction of the driver of the vehicle 100a obtained from the line of sight data Da.
[0101] When a change in the lighting state of the traffic lights TLc2 and TLc3 is detected (when the state change data Do is obtained), if the line of sight or the facial direction of the driver of the vehicle 100a obtained from the line of sight data Da is directed toward the vehicle 100e, the mistake determination unit 33 can determine that the above possibility is high. For example, when the lighting state of the traffic lights TLc2 and TLc3 changes (for example, when the traffic lights TLc2 and TLc3 change from red to green), and when the line of sight or the facial direction of the driver of the vehicle 100a is directed toward the vehicle 100e during a predetermined period after the change in the lighting state of the traffic lights TLc2 and TLc3 is completed (for example, during a predetermined period after the traffic lights TLc2 and TLc3 change from green), the mistake determination unit 33 can determine that the above possibility is high. The misperception determination unit 33 is capable of determining the magnitude of the above-mentioned possibility, for example, based on the length of time that the line of sight or face of the driver of vehicle 100a is directed toward vehicle 100e when the lighting status of traffic lights TLc2 and TLc3 changes and during a predetermined period after the lighting status of traffic lights TLc2 and TLc3 has completed changing.
[0102] 7, as in the above-described embodiment, a possibility that the vehicle 100a will start entering the intersection CL contrary to the indication of the traffic light TLc1 is determined in accordance with a change in the lighting state of the traffic lights TLc2 and TLc3, and at least one of a warning and braking is controlled depending on the magnitude of the obtained possibility. This makes it possible to warn the driver of the vehicle 100a or to brake the vehicle 100a before the driver of the vehicle 100a mistakenly enters the intersection CL as a result of looking away and not carefully looking ahead of the vehicle 100a.
[0103] 4. Second Embodiment [Configuration example] Next, a vehicle 2 according to a second embodiment of the present disclosure will be described. In the following, descriptions of components having the same reference numerals as those assigned to the components in the vehicle 1 according to the first embodiment will be omitted as appropriate.
[0104] FIG. 8 illustrates an example of a traffic situation in which a misidentification may occur. In FIG. 8, a traffic light TLc for traffic participants crossing a pedestrian crossing CWb is provided at an intersection CL. The traffic light TLc is not synchronized with the changes in the lighting state of traffic lights TLa and TLb. At the same time that traffic light TLb changes from a state permitting entry into the intersection CL (green light) to a state prohibiting entry into the intersection CL (red light), traffic light TLc remains in a state prohibiting entry into the pedestrian crossing CWb (red light) for a predetermined period of time after traffic light TLa changes from a state prohibiting entry into the intersection CL (red light) to a state permitting entry into the intersection CL (green light).
[0105] Pedestrian 100c and cyclist 100d are on the sidewalk just before intersection CL as seen from vehicle 100a. Pedestrian 100c and cyclist 100d are located close to each other. Pedestrian 100c may be standing just before intersection CL, operating a terminal, reading, or having a conversation, and is not paying attention to traffic light TLc. Meanwhile, cyclist 100d is moving toward intersection CL.
[0106] When pedestrian 100c sees the change in the lighting state of traffic light TLa or traffic light TLb, he or she is under the illusion that traffic light TLc has changed from a state prohibiting entry into the crosswalk CWb (red light) to a state permitting entry into the crosswalk CWb (green light). As a result, pedestrian 100c mistakenly believes that such a change in the lighting state of traffic light TLc has occurred and attempts to enter the crosswalk CWb. In other words, pedestrian 100c attempts to begin entering the crosswalk CWb despite the indication of traffic light TLc.
[0107] If traffic conditions that could cause the pedestrian 100c to misinterpret the traffic signal as described above could be identified before the pedestrian 100c begins to enter the crosswalk CWb, it would be possible to reliably issue a warning or brake the vehicle 100a to avoid a collision with the pedestrian 100c. Therefore, the inventors of the present application have conceived a technology that could identify traffic conditions that could cause the pedestrian 100c to misinterpret the traffic signal before the pedestrian 100c begins to enter the crosswalk CWb, and issue a predetermined warning to the driver of the vehicle 100a or brake the vehicle 100a when the vehicle 100a attempts to enter the intersection CL. A driving assistance device and a vehicle for achieving this will be described in detail below. In the above example, the subject who misinterprets the change in the illumination state of the traffic signal TLc may be a bicyclist 100d, rather than the pedestrian 100c. In this case, the pedestrian 100c is moving toward the intersection CL.
[0108] 9 shows a schematic configuration example of vehicle 2. Control unit 30 corresponds to a specific example of a "driving assistance device" in the present disclosure. Vehicle 2 corresponds to a specific example of vehicle 100a, which corresponds to a specific example of a "vehicle" in the present disclosure.
[0109] The vehicle 2 is capable of traveling by being driven by a prime mover (engine or motor). As shown in Fig. 9, the vehicle 2 includes a sensor unit 10, a communication unit 20, a control unit 30, a memory unit 40, a notification unit 50, and an accelerator pedal motor 60. A road map DB 41 is stored in the memory unit 40.
[0110] The control unit 30 has, for example, a driving control unit 31 as shown in Fig. 9. The driving control unit 31 is capable of controlling the driving of the vehicle 2 (for example, the accelerator pedal depression amount) and notifications related to the driving of the vehicle 2. The driving control unit 31 has, for example, a data acquisition unit 32, an error determination unit 37, an assistance determination unit 34, a notification control unit 35, and an accelerator pedal control unit 36 as shown in Fig. 9.
[0111] The data acquisition unit 32 is capable of acquiring various data acquired from the sensor unit 10, various data acquired from the outside via the communication unit 20, and various control signals for various devices of the vehicle 1 (e.g., turn signals). The data acquisition unit 32 is capable of acquiring the above-mentioned lighting state data Dj, the below-mentioned pedestrian data Dk, and the below-mentioned gaze data Dp based on the acquired various data and various control signals. The following symbols correspond to the symbols in FIG. 8. The lighting state data Dj corresponds to a specific example of "first data" in the present disclosure. The pedestrian data Dk corresponds to a specific example of "second data" in the present disclosure. The gaze data Dp corresponds to a specific example of "third data" in the present disclosure.
[0112] (Pedestrian Data Dk) The pedestrian data Dk is data about pedestrians 100c and cyclists 100d near the intersection CL, and includes, for example, data about the position and speed of pedestrians 100c and cyclists 100d near the intersection CL, and data about the status and movement of pedestrians 100c and cyclists 100d near the intersection CL.
[0113] (Gaze data Dp) The gaze data Dp is data on the gaze or facial direction of the pedestrian 100c and the bicyclist 100d. The driver state detection unit is capable of outputting data on the gaze or facial direction of the pedestrian 100c and the bicyclist 100d (gaze data Dp) to the control unit 30 based on image data obtained by the camera.
[0114] The misconception determination unit 37 is capable of detecting a change in the lighting state of the traffic signal TLa or a change in the lighting state of the traffic signal TLb based on the lighting state data Dj. A "change in the lighting state of the traffic signal TLa" refers to a change in the lighting state of the traffic signal TLb from a state in which entry into the intersection CL is prohibited (red light) to a state in which entry into the intersection CL is permitted (green light). A "change in the lighting state of the traffic signal TLb" refers to a change in the lighting state of the traffic signal TLb from a state in which entry into the intersection CL is permitted (green light) to a state in which entry into the intersection CL is prohibited (red light). Hereinafter, data regarding a change in the lighting state of the traffic signal TLa or a change in the lighting state of the traffic signal TLb based on the lighting state data Dj will be referred to as state change data Dq.
[0115] When the error determination unit 37 detects a change in the lighting state of the traffic light TLa or the lighting state of the traffic light TLb (when the state change data Dq is obtained), it is possible to determine, based on the pedestrian data Dk, whether or not the pedestrian 100c will start entering the crosswalk CWb despite the indication of the traffic light TLc in response to the change in the lighting state of the traffic light TLa or the traffic light TLb. The error determination unit 37 is able to determine this possibility based on the state and movement of the pedestrian 100c contained in the pedestrian data Dk. Assume that the pedestrian data Dk includes actions of the pedestrian 100c that make it easier for the pedestrian 100c to overlook the traffic light TLc, such as operating a terminal, reading, or talking. In this case, the error determination unit 37 is able to determine that this possibility is high.
[0116] The misconception determination unit 37 is capable of determining the above possibility based on the line of sight or facial direction of the pedestrian 100c obtained from the gaze data Dp when a change in the lighting state of traffic light TLa or traffic light TLb is detected (when the state change data Dq is obtained). When the state change data Dq is obtained, the misconception determination unit 37 is capable of determining that the above possibility is high if the line of sight or facial direction of the pedestrian 100c obtained from the gaze data Dp is facing in a direction different from the directions of traffic lights TLa and TLb. For example, the misconception determination unit 37 is capable of determining that the above possibility is high when the line of sight or facial direction of the pedestrian 100c is facing in a direction different from the directions of traffic lights TLa and TLb while the lighting state of traffic light TLa or traffic light TLb is changing. The misperception determination unit 37 is capable of determining the magnitude of the above-mentioned possibility, for example, depending on the length of time that the line of sight or face of the pedestrian 100c is facing in a direction different from the direction of the traffic lights TLa and TLb while the lighting state of the traffic lights TLa or TLb is changing.
[0117] The determination of whether the line of sight or the direction of the face of the pedestrian 100c is facing in a direction different from the direction of traffic lights TLa and TLb is made, for example, by determining whether the direction of the face or line of sight of the pedestrian 100c obtained from the image data Db is outside a predetermined range of viewing angles that includes the directions of traffic lights TLa and TLb. The misidentification determination unit 37 can determine that the above possibility is high, for example, when the direction of the face or line of sight of the pedestrian 100c is outside the above range of viewing angles. In other words, when the vehicle 100a is stopped before the intersection CL (before the stop line), the misidentification determination unit 37 can determine that the above possibility is high if the pedestrian 100c is not gazing at the traffic light TLc but is looking away for a long time.
[0118] The misidentification determination unit 37 can determine the above possibility based on the movement of traffic participants (e.g., bicyclist 100d) around the pedestrian 100c, which is included in the pedestrian data Dk. For example, when the bicyclist 100d is moving near the pedestrian 100c toward the intersection CL, the misidentification determination unit 37 can determine that the above possibility is high.
[0119] The error determination unit 37 is capable of calculating, as a numerical value (error rate R), the magnitude of the possibility that the pedestrian 100c will start entering the crosswalk CWb contrary to the indication of the traffic light TLc in response to a change in the lighting state of the traffic light TLa or the traffic light TLb. The error determination unit 37 is capable of calculating the error rate R, for example, using the following equations (6) to (9).
[0120] R = α' × Dsub × Msub + ε'...(6) α'+ε'=1…(7) Dsub=1 or 0…(8) Msub=1 / L…(9)
[0121] Dsub: Whether or not pedestrian 100c owns a mobile device (Yes: 1, No: 0) Msub: Distance between pedestrian 100c and cyclist 100d (m) α': Coefficient (value between 0 and 1) ε': Correction value (value between 0 and 1)
[0122] If the subject who misidentifies the change in the lighting state of traffic light TLc is bicyclist 100d and the traffic participant moving near the subject who misidentifies the change in the lighting state of traffic light TLc is pedestrian 100c, then in equations (6) to (9), pedestrian 100c should be read as bicyclist 100d and bicyclist 100d should be read as pedestrian 100c. If the subject who misidentifies the change in the lighting state of traffic light TLc is pedestrian 100c and the traffic participant moving near the subject who misidentifies the change in the lighting state of traffic light TLc is a pedestrian different from pedestrian 100c, then bicyclist 100d should be read as pedestrian in equations (6) to (9).
[0123] The assistance decision unit 34 is capable of determining a driving assistance method based on the magnitude of the error rate R obtained by the error determination unit 37. The assistance decision unit 34 is capable of controlling at least one of notifying the driver of the vehicle 100a and braking the vehicle 100a based on the magnitude of the error rate R obtained by the error determination unit 37. The notification control unit 35 is capable of causing the notification unit 50 to issue a notification in accordance with a control signal input from the assistance decision unit 34. The accelerator pedal control unit 36 is capable of limiting depression of the accelerator pedal in accordance with a control signal input from the assistance decision unit 34.
[0124] Next, with reference to FIG. 3, a driving assistance procedure for the vehicle 2 in the traffic situation of FIG. 8 will be described.
[0125] The driving control unit 31 acquires various data including image data Db and the like (step S101). The driving control unit 31 also acquires various control signals as necessary. Next, the driving control unit 31 determines whether or not an intersection CL exists ahead of the vehicle 100a (host vehicle) based on the acquired various data and various control signals (step S102). The driving control unit 31 detects the intersection CL ahead of the vehicle 100a based on, for example, the image data Db.
[0126] When the driving control unit 31 determines that an intersection CL exists ahead of the vehicle 100a (step S102; Y), the driving control unit 31 determines whether or not the intersection CL is an intersection where traffic control is performed according to a normal traffic light schedule based on the acquired various data and various control signals (step S103). The driving control unit 31 determines whether or not the intersection CL is an intersection where traffic control is performed according to a normal traffic light schedule based on, for example, information about the intersection CL included in the traffic road map DB 41.
[0127] If the driving control unit 31 determines that the intersection CL is not an intersection where traffic control is performed according to a normal traffic light schedule (step S103; N), the driving control unit 31 determines whether or not there is another vehicle ahead of the vehicle 100a before the intersection CL (i.e., whether the vehicle 100a is at the head of the vehicle train) based on the acquired various data and various control signals (step S104). The driving control unit 31 detects whether or not there is another vehicle ahead of the vehicle 100a based on, for example, image data Db.
[0128] When the driving control unit 31 determines that the vehicle 100a is at the front of the vehicle train (step S104; Y), it calculates the probability of misidentification by the pedestrian 100c (misidentification rate R) based on the acquired various data and various control signals (step S105).The driving control unit 31 controls at least one of notifying the driver of the vehicle 100a and braking the vehicle 100a according to the magnitude of the calculated probability of misidentification (misidentification rate R) (step S106).
[0129] If the driving control unit 31 does not want to end the driving assistance (step S107; N), the process returns to step S101. In this manner, driving assistance for the vehicle 2 in the traffic situation of FIG.
[0130] [effect] Next, the effects of vehicle 2 will be described.
[0131] In this embodiment, in response to a change in the lighting state of traffic light TLa or traffic light TLb, a determination is made as to the possibility that pedestrian 100c will start entering the crosswalk CWb despite the indication of traffic light TLc, and at least one of a warning and braking is controlled depending on the magnitude of the obtained possibility. This makes it possible to warn the driver of vehicle 100a or brake vehicle 100a before pedestrian 100c accidentally enters the crosswalk CWb as a result of not paying close attention to traffic light TLc and looking away.
[0132] In this embodiment, the possibility that the pedestrian 100c will start entering the pedestrian crossing CWb despite the warning from the traffic light TLc is determined based on the behavior of the pedestrian 100c. This makes it possible to notify the driver of the vehicle 100a or brake the vehicle 100a before the pedestrian 100c fails to pay close attention to the traffic light TLc and ends up accidentally entering the pedestrian crossing CWb.
[0133] In this embodiment, the possibility that the pedestrian 100c will start entering the crosswalk CWb despite the indication of the traffic light TLc is determined based on the line of sight or the direction of the face of the pedestrian 100c. This makes it possible to notify the driver of the vehicle 100a or brake the vehicle 100a before the pedestrian 100c mistakenly enters the crosswalk CWb as a result of not paying close attention to the traffic light TLc and instead looking away.
[0134] In this embodiment, the possibility that pedestrian 100c will start entering the crosswalk CWb despite the warning from traffic light TLc is determined based on the movement of bicyclist 100d traveling near pedestrian 100c. This makes it possible to warn the driver of vehicle 100a or brake vehicle 100a before pedestrian 100c fails to pay close attention to traffic light TLc and is lured by the movement of bicyclist 100d, resulting in erroneously entering the crosswalk CWb.
[0135] 5. Third Embodiment [Configuration example] Next, a vehicle 3 according to a third embodiment of the present disclosure will be described. In the following, descriptions of components having the same reference numerals as those assigned to the components in the vehicle 1 according to the first embodiment will be omitted as appropriate.
[0136] FIG. 10 shows an example of a traffic situation. In FIG. 10, vehicle (host vehicle) 100a is traveling on road Lc, which has two lanes on each side. Road Lc is made up of trafic lanes Lc1 and Lc2 and oncoming lanes Lc3 and Lc4. An intersection CL is provided on road Lc ahead of vehicles 100a and 100e and ahead of vehicles 100f and 100g. Road Lc intersects with road Lb at the intersection CL. Road Lb is made up of trafic lane Lb1 and oncoming lane Lb2. On road Lc, a crosswalk CWa and traffic lights TLc3 and TLc4 are provided just before the intersection CL in relation to vehicles 100a and 100e, and a crosswalk CWa and traffic lights TLc1 and TLc2 are provided further back from the intersection CL in relation to vehicles 100a and 100e.
[0137] Traffic lights TLc1, TLc2, TLc3, and TLc4 are in a state prohibiting entry into intersection CL (red light). Furthermore, traffic light TLb is in a state prohibiting entry into intersection CL (red light). Vehicles 100a, 100b, 100f, and 100g approach intersection CL while decelerating and stop just before the stop line. Then, traffic lights TLc1 and TLc4 change from a state prohibiting entry into intersection CL (red light) to a state permitting entry into intersection CL (green light). In response to this change in the lighting status of traffic lights TLc1 and TLc4, vehicles 100a and 100g attempt to begin entering intersection CL. At this time, the driver of vehicle 100f is not paying attention to traffic light TLc3, but is watching vehicle 100g, adjacent to vehicle 100f, begin to move. In other words, the driver of vehicle 100f is not paying close attention to the area ahead of the vehicle and is looking away. The driver of vehicle 100f, seeing vehicle 100g starting to move, has the misconception that traffic light TLc3 has changed from a state prohibiting entry into intersection CL (red light) to a state permitting entry into intersection CL (green light). As a result, the driver of vehicle 100f mistakenly believes that such a change in the lighting state of traffic light TLc3 has occurred and attempts to start vehicle 100f. In other words, vehicle 100f attempts to start entering intersection CL despite the indication of traffic light TLc3.
[0138] If the traffic conditions that may cause the vehicle 100f to make a mistake as described above could be determined before the vehicle 100f starts to enter the intersection CL, it would be possible to reliably provide a warning or brake the vehicle 100a to avoid a collision with the vehicle 100f. Therefore, the inventors of the present application have conceived of a technology that can determine the traffic conditions that may cause the vehicle 100f to make a mistake before the vehicle 100f starts to enter the intersection CL, and provide a predetermined warning to the driver of the vehicle 100a or brake the vehicle 100a when the vehicle 100a attempts to enter the intersection CL. A driving assistance device and a vehicle for realizing this will be described in detail below.
[0139] 11 shows an example of a schematic configuration of vehicle 3. Control unit 30 corresponds to a specific example of a "driving assistance device" in the present disclosure. Vehicle 3 corresponds to a specific example of vehicle 100a, which corresponds to a specific example of a "vehicle" in the present disclosure.
[0140] The vehicle 3 is capable of traveling by being driven by a prime mover (engine or motor). As shown in Fig. 11, the vehicle 2 includes a sensor unit 10, a communication unit 20, a control unit 30, a memory unit 40, a notification unit 50, and an accelerator pedal motor 60. A road map DB 41 is stored in the memory unit 40.
[0141] The control unit 30 has a driving control unit 31, for example, as shown in Fig. 11. The driving control unit 31 is capable of controlling the driving of the vehicle 3 (for example, the accelerator pedal depression amount) and notifications related to the driving of the vehicle 3. The driving control unit 31 has a data acquisition unit 32, an error determination unit 38, an assistance determination unit 34, a notification control unit 35, and an accelerator pedal control unit 36, for example, as shown in Fig. 11.
[0142] The data acquisition unit 32 is capable of acquiring various data acquired from the sensor unit 10, various data acquired from the outside via the communication unit 20, and various control signals for various devices of the vehicle 3 (e.g., turn signals). The data acquisition unit 32 is capable of acquiring lighting status data Dm, other vehicle data Dr described below, and gaze data Ds described below, based on the acquired various data and various control signals. The following symbols correspond to the symbols described in FIG. 10. The lighting status data Dm corresponds to a specific example of "first data" in the present disclosure. The other vehicle data Dr corresponds to a specific example of "second data" in the present disclosure. The gaze data Da corresponds to a specific example of "third data" in the present disclosure.
[0143] (Other vehicle data Dr) The other vehicle data Dn is data about the vehicle 100f that is present in the driving lane Lc3, for example, data about the position and speed of the vehicle 100f that is present in the driving lane Lc3.
[0144] (Gaze data Ds) The gaze data Dp is data on the gaze or facial direction of the driver of the vehicle 100f. The driver state detection unit is capable of outputting data on the gaze or facial direction of the driver of the vehicle 100f (gaze data Ds) to the control unit 30 based on image data obtained by the camera.
[0145] The misconception determination unit 33 is capable of detecting changes in the lighting states of the traffic lights TLc1 and TLc4 based on the lighting state data Dm. "Changes in the lighting states of the traffic lights TLc1 and TLc4" refers to changes in the lighting states of the traffic lights TLc1 and TLc4 from a state in which entry into the intersection CL is prohibited (red light) to a state in which entry into the intersection CL is permitted (green light). Hereinafter, data regarding changes in the lighting states of the traffic lights TLc1 and TLc4 based on the lighting state data Dm will be referred to as state change data Dt.
[0146] When the error determination unit 33 detects a change in the lighting states of the traffic lights TLc1 and TLc4 (when the state change data Dt is obtained), it is possible to determine, based on the other vehicle data Dr, whether the change in the lighting states of the traffic lights TLc1 and TLc4 will cause the vehicle 100f to start entering the intersection CL contrary to the indication of the traffic light TLc3. When the error determination unit 33 detects a change in the lighting states of the traffic lights TLc1 and TLc4 (when the state change data Dt is obtained), it is possible to determine the above possibility based on the line of sight or facial direction of the driver of the vehicle 100f obtained from the line of sight data Ds.
[0147] When a change in the lighting state of the traffic lights TLc1 and TLc4 is detected (when the state change data Dt is obtained), if the line of sight or the facial direction of the driver of the vehicle 100f obtained from the gaze data Ds is directed toward the vehicle 100g, the misperception determination unit 33 can determine that the above possibility is high. For example, when the lighting state of the traffic lights TLc1 and TLc4 changes (for example, when the traffic lights TLc1 and TLc4 change from red to green), and when the line of sight or the facial direction of the driver of the vehicle 100f is directed toward the vehicle 100g during a predetermined period after the change in the lighting state of the traffic lights TLc1 and TLc4 is completed (for example, during a predetermined period after the traffic lights TLc1 and TLc4 change from green), the misperception determination unit 33 can determine that the above possibility is high. The misidentification determination unit 33 is capable of determining the magnitude of the above-mentioned possibility, for example, based on the length of time that the driver of vehicle 100f's line of sight or face is directed toward vehicle 100g when the lighting status of traffic lights TLc1 and TLc4 changes and during a predetermined period after the lighting status of traffic lights TLc1 and TLc4 has completed changing.
[0148] The error determination unit 33 is capable of calculating, as a numerical value (error rate R), the magnitude of the possibility that the vehicle 100f will start entering the intersection CL contrary to the indication of the traffic light TLc3 in response to a change in the lighting state of the traffic lights TLc1 and TLc4. The error determination unit 33 is capable of calculating the error rate R, for example, using the following equations (10) to (13).
[0149] R = β'Uego × Lsub + ε''...(10) β'+ε'=1…(11) Uego=1-(T3 / T4)…(12) Lsub=1 / L…(13)
[0150] Uego: The visual observation rate of traffic light TLc3 by the driver of vehicle 100f (value between 0 and 1) Lsub: Distance between vehicle 100f and vehicle 100g (m) β': Coefficient (value between 0 and 1) ε): Correction value (value between 0 and 1) T3: The visual inspection time (s) of traffic light TLc3 by the driver of vehicle 100f T4: Time (s) that vehicle 100f is stopped waiting for a traffic light
[0151] The assistance decision unit 34 is capable of determining a driving assistance method based on the magnitude of the error rate R obtained by the error determination unit 33. The assistance decision unit 34 is capable of controlling at least one of notifying the driver of the vehicle 100a and braking the vehicle 100a based on the magnitude of the error rate R obtained by the error determination unit 33. The notification control unit 35 is capable of causing the notification unit 50 to issue a notification in accordance with a control signal input from the assistance decision unit 34. The accelerator pedal control unit 36 is capable of limiting depression of the accelerator pedal in accordance with a control signal input from the assistance decision unit 34.
[0152] Next, with reference to FIG. 3, a driving assistance procedure for the vehicle 3 in the traffic situation of FIG. 10 will be described.
[0153] The driving control unit 31 acquires various data including image data Db and the like (step S101). The driving control unit 31 also acquires various control signals as necessary. Next, the driving control unit 31 determines whether or not an intersection CL exists ahead of the vehicle 100a (host vehicle) based on the acquired various data and various control signals (step S102). The driving control unit 31 detects the intersection CL ahead of the vehicle 100a based on, for example, the image data Db.
[0154] When the driving control unit 31 determines that an intersection CL exists ahead of the vehicle 100a (step S102; Y), the driving control unit 31 determines whether or not the intersection CL is an intersection where traffic control is performed according to a normal traffic light schedule based on the acquired various data and various control signals (step S103). The driving control unit 31 determines whether or not the intersection CL is an intersection where traffic control is performed according to a normal traffic light schedule based on, for example, information about the intersection CL included in the traffic road map DB 41.
[0155] If the driving control unit 31 determines that the intersection CL is not an intersection where traffic control is performed according to a normal traffic light schedule (step S103; N), the driving control unit 31 determines whether or not there is another vehicle ahead of the vehicle 100a before the intersection CL (i.e., whether the vehicle 100a is at the head of the vehicle train) based on the acquired various data and various control signals (step S104). The driving control unit 31 detects whether or not there is another vehicle ahead of the vehicle 100a based on, for example, image data Db.
[0156] When the driving control unit 31 determines that the vehicle 100a is at the front of the vehicle train (step S104; Y), it calculates the probability of misidentification (misidentification rate R) by the vehicle 100f based on the acquired various data and various control signals (step S105).The driving control unit 31 controls at least one of notifying the driver of the vehicle 100a and braking the vehicle 100a according to the magnitude of the calculated probability of misidentification (misidentification rate R) (step S106).
[0157] If the driving control unit 31 does not want to end the driving assistance (step S107; N), the process returns to step S101. In this manner, driving assistance for the vehicle 3 in the traffic situation of FIG.
[0158] [effect] Next, the effects of vehicle 3 will be described.
[0159] In this embodiment, in accordance with changes in the lighting states of the traffic lights TLc1 and TLc4, a determination is made as to the possibility that the vehicle 100f will start entering the intersection CL contrary to the indication of the traffic light TLc3, and at least one of a notification and braking is controlled depending on the magnitude of the obtained possibility. This makes it possible to notify the driver of the vehicle 100a or to brake the vehicle 100a before the vehicle 100f mistakenly enters the intersection CL as a result of not paying close attention to the traffic light TLc3 and looking away.
[0160] In this embodiment, the possibility that the vehicle 100f will start entering the intersection CL contrary to the indication of the traffic light TLc3 is determined based on the line of sight or the direction of the face of the vehicle 100f. This makes it possible to notify the driver of the vehicle 100a or brake the vehicle 100a before the vehicle 100f mistakenly enters the intersection CL as a result of not paying close attention to the traffic light TLc3 and looking away.
[0161] The effects described in this specification are merely examples and are not limiting, and other effects may also be present.
[0162] Furthermore, for example, the present disclosure can be configured as follows. (1) an acquisition unit capable of acquiring first data regarding the lighting states of a plurality of traffic lights installed at an intersection ahead of a stopped vehicle; a control unit capable of controlling at least one of a notification to a driver of the vehicle and braking of the vehicle based on the first data; Equipped with The control unit determining, in response to a change in the lighting state of a second traffic light among the plurality of traffic lights, which is different from the first traffic light for the vehicle, the possibility that the vehicle will start entering the intersection contrary to the indication of the first traffic light; controlling at least one of the notification and the braking in accordance with the magnitude of the possibility; It is possible to carry out Driving assistance device. (2) The acquisition unit is capable of acquiring second data regarding the driver's line of sight or facial direction, The control unit is capable of determining the possibility based on the driver's line of sight or face direction obtained from the second data. A driving assistance device as described in (1). (3) the acquisition unit is capable of acquiring third data indicating that the second traffic light is a traffic light for an intersecting vehicle traveling on an intersection that intersects with the intersection, and that the intersecting vehicle is decelerating or stopping in front of the intersection in accordance with a change in the lighting state of the second traffic light; The control unit is capable of determining that the possibility is high when the driver's line of sight or face is directed toward the intersecting vehicle when the third data is obtained. (2) A driving assistance device according to the present invention. (4) The control unit is capable of determining that the possibility is high when the second traffic light is a traffic light for crossing vehicles traveling on an intersection that intersects with the intersection, and when the second traffic light changes to a state prohibiting entry into the intersection, the driver's line of sight or face is directed toward the second traffic light. (2) A driving assistance device according to the present invention. (5) the acquisition unit is capable of acquiring fourth data indicating that the pedestrian or the light vehicle is about to cross the crosswalk in accordance with a change in the lighting state of the second traffic light, in a case where the second traffic light is a traffic light for the pedestrian or the light vehicle located in front of a crosswalk at an intersection where roads intersect at the intersection, and The control unit is capable of determining that the possibility is high when the driver's line of sight or face direction is directed toward the pedestrian or the light vehicle when the fourth data is obtained. (2) A driving assistance device according to the present invention. (6) The control unit is capable of determining that the possibility is high when the second traffic light is a traffic light for the pedestrian or the light vehicle crossing a crosswalk at an intersection, and when the driver's line of sight or face is directed toward the second traffic light and the second traffic light changes to a state permitting entry into the crosswalk. (2) A driving assistance device according to the present invention. (7) the acquisition unit is capable of acquiring fifth data indicating that the adjacent vehicle is about to enter the intersection in accordance with a change in the lighting state of the second traffic light in a case where the second traffic light is a traffic light for an adjacent vehicle traveling in an adjacent lane adjacent to a roadway on which the vehicle is traveling and traveling in the same direction as the vehicle, and The control unit is capable of determining that the possibility is high when the driver's line of sight or face is directed toward the adjacent vehicle when the fifth data is obtained. (2) A driving assistance device according to the present invention. (8) The acquisition unit is capable of acquiring passage history data of the vehicle through the intersection, The control unit is capable of determining the possibility based on the passage history data. A driving assistance device according to any one of (1) to (7). (9) an acquisition unit capable of acquiring first data on the lighting status of a plurality of traffic lights installed at an intersection ahead of a stopped vehicle, and second data on one or more pedestrians or cyclists located in front of a crosswalk at an intersection that intersects with the stopped vehicle at the intersection; a control unit capable of controlling at least one of a notification to a driver of the vehicle and braking of the vehicle based on the first data and the second data; Equipped with The control unit determining, in accordance with a change in the lighting state of a first traffic light for vehicles or a second traffic light for traffic participants crossing the crosswalk among the plurality of traffic lights, whether or not at least one subject among the one or more pedestrians or cyclists will start entering the crosswalk despite the indication of the second traffic light; controlling at least one of the notification and the braking in accordance with the magnitude of the possibility; It is possible to carry out Driving assistance device. (10) The control unit is capable of determining the possibility based on a movement of the subject. (9) A driving assistance device according to the present invention. (11) the acquisition unit is capable of acquiring third data regarding a line of sight or a facial direction of the subject, The control unit is capable of determining the possibility based on the gaze or facial direction of the subject obtained from the third data. A driving assistance device according to (9) or (10). (12) The control unit is capable of determining the possibility based on the movement of the pedestrian or the automobile driver other than the target person, which is included in the second data. A driving assistance device according to any one of (9) to (11). (13) an acquisition unit capable of acquiring first data on the lighting status of a plurality of traffic lights installed at an intersection ahead of a stopped vehicle, and second data on one or a plurality of intersecting vehicles stopped near the intersection at an intersection that intersects with the intersection; a control unit capable of controlling at least one of a notification to a driver of the vehicle and braking of the vehicle based on the first data and the second data; Equipped with The control unit determining, in response to a change in the lighting state of a second traffic light for the intersecting vehicle, which is different from the first traffic light for the vehicle, among the plurality of traffic lights, a possibility that at least one target vehicle among the one or more intersecting vehicles will start entering the intersection contrary to the indication of the second traffic light; controlling at least one of the notification and the braking in accordance with the magnitude of the possibility; It is possible to carry out Driving assistance device. (14) the acquisition unit is capable of acquiring third data regarding a line of sight or a facial direction of a driver of the target vehicle, The control unit is capable of determining the possibility based on the driver's line of sight or face direction obtained from the third data. A driving assistance device according to (13). (15) A driving assistance device according to any one of (1) to (14) is provided. vehicle.
[0163] The control unit 30 shown in FIGS. 1, 8, and 10 can be implemented by circuitry including at least one semiconductor integrated circuit, such as at least one processor (e.g., a central processing unit (CPU)), at least one application-specific integrated circuit (ASIC), and / or at least one field-programmable gate array (FPGA). The at least one processor can be configured to perform all or a portion of the various functions of the control unit 30 shown in FIGS. 1, 8, and 10 by reading instructions from at least one non-transitory, tangible computer-readable medium. Such medium can take various forms, including, but not limited to, various magnetic media such as hard disks, various optical media such as CDs or DVDs, and various semiconductor memories (i.e., semiconductor circuits) such as volatile or non-volatile memories. Volatile memories can include DRAM and SRAM. Non-volatile memories can include ROM and NVRAM. An ASIC is an integrated circuit (IC) specialized to perform all or a portion of the various functions of the control unit 30 shown in FIGS. 1, 8, and 10. The FPGA is an integrated circuit designed to be configurable after manufacture to perform all or part of the various functions of the control unit 30 shown in FIGS. [Explanation of symbols]
[0164] 1, 2, 3... vehicle, 10... sensor unit, 20... communication unit, 30... control unit, 31... driving control unit, 32... data acquisition unit, 33, 37, 38... misidentification determination unit, 34... assistance determination unit, 35... notification control unit, 36... accelerator pedal control unit, 40... memory unit, 41... road map DB, 42... passage history data, 50... notification unit, 60... accelerator pedal motor, 100a, 100b, 100e, 100f, 100g... vehicle, 100c... pedestrian, 100d... cyclist, CL... intersection, CWa, CWb... crosswalk, Da... gaze data, Db... image data, Dc... distance image data, Dd...driving environment data, De...lighting status data, Df...other vehicle data, Dg...passing history data, Dh...status change data, Di...other vehicle data, Dj...lighting status data, Dk...pedestrian data, Dl...status change data, Dm...lighting status data, Dn...other vehicle data, Do...status change data, Dp...gaze data, Dq...status change data, Dr...other vehicle data, Ds...gaze data, La, Lb...road, La1...driving lane, La2...oncoming lane, Lb1...driving lane, Lb2...oncoming lane, TLa, TLb, TLc, TLc1, TLc2, TLc3, TLc4...traffic lights.
Claims
1. an acquisition unit capable of acquiring first data regarding lighting states of a plurality of traffic lights installed at an intersection ahead of a stopped vehicle; a control unit capable of controlling at least one of a notification to a driver of the vehicle and braking of the vehicle based on the first data; Equipped with The control unit determining, in response to a change in the lighting state of a second traffic light among the plurality of traffic lights, which is different from the first traffic light for the vehicle, the possibility that the vehicle will start entering the intersection contrary to the indication of the first traffic light; controlling at least one of the notification and the braking in accordance with the magnitude of the possibility; It is possible to carry out Driving assistance device.
2. The acquisition unit is capable of acquiring second data regarding a line of sight or a facial direction of the driver, The control unit is capable of determining the possibility based on the driver's line of sight or face direction obtained from the second data. The driving assistance device according to claim 1 .
3. the acquisition unit is capable of acquiring third data indicating that the second traffic light is a traffic light for an intersecting vehicle traveling on an intersection that intersects with the intersection, and that the intersecting vehicle is decelerating or stopping in front of the intersection in accordance with a change in the lighting state of the second traffic light; The control unit is capable of determining that the possibility is high when the driver's line of sight or face is directed in the direction of the intersecting vehicle when the third data is obtained. The driving assistance device according to claim 2 .
4. The control unit is capable of determining that the possibility is high when the second traffic light is a traffic light for vehicles traveling on an intersection that intersects with the intersection, and when the second traffic light changes to a state prohibiting entry into the intersection, the driver's line of sight or face is directed toward the second traffic light. The driving assistance device according to claim 2 .
5. the acquisition unit is capable of acquiring fourth data indicating that the pedestrian or the light vehicle is about to cross the crosswalk in accordance with a change in the lighting state of the second traffic light, in a case where the second traffic light is a traffic light for the pedestrian or the light vehicle located in front of a crosswalk at an intersection where roads intersect at the intersection, and The control unit is capable of determining that the possibility is high when the driver's line of sight or face direction is directed toward the pedestrian or the light vehicle when the fourth data is obtained. The driving assistance device according to claim 2 .
6. The control unit is capable of determining that the possibility is high when the second traffic light is a traffic light for the pedestrian or the light vehicle crossing a crosswalk at an intersection, and when the driver's line of sight or face is directed toward the second traffic light and the second traffic light changes to a state permitting entry into the crosswalk. The driving assistance device according to claim 2 .
7. the acquisition unit is capable of acquiring fifth data indicating that the adjacent vehicle is about to enter the intersection in accordance with a change in the lighting state of the second traffic light in the case where the second traffic light is a traffic light for an adjacent vehicle traveling in an adjacent lane adjacent to the road on which the vehicle is traveling and traveling in the same direction as the vehicle, The control unit is capable of determining that the possibility is high when the driver's line of sight or face is directed toward the adjacent vehicle when the fifth data is obtained. The driving assistance device according to claim 2 .
8. The acquisition unit is capable of acquiring passage history data of the vehicle through the intersection, The control unit is capable of determining the possibility based on the passage history data. The driving assistance device according to any one of claims 1 to 7.
9. an acquisition unit capable of acquiring first data on the lighting status of a plurality of traffic lights installed at an intersection ahead of a stopped vehicle, and second data on one or more pedestrians or cyclists present at a crosswalk at an intersection that intersects with the stopped vehicle at the intersection; a control unit capable of controlling at least one of a notification to a driver of the vehicle and braking of the vehicle based on the first data and the second data; Equipped with The control unit determining, in accordance with a change in the lighting state of a first traffic light for vehicles or a second traffic light for traffic participants crossing the crosswalk among the plurality of traffic lights, whether or not at least one of the one or more pedestrians or cyclists is likely to start entering the crosswalk despite the indication of the second traffic light; controlling at least one of the notification and the braking in accordance with the magnitude of the possibility; It is possible to carry out Driving assistance device.
10. The control unit is capable of determining the possibility based on a movement of the subject. The driving assistance device according to claim 9.
11. the acquisition unit is capable of acquiring third data regarding a line of sight or a facial direction of the subject, The control unit is capable of determining the possibility based on the line of sight or face direction of the subject obtained from the third data. The driving assistance device according to claim 9.
12. The control unit is capable of determining the possibility based on the movement of traffic participants around the target person included in the second data. The driving assistance device according to any one of claims 9 to 11.
13. an acquisition unit capable of acquiring first data on the lighting status of a plurality of traffic lights installed at an intersection ahead of a stopped vehicle, and second data on one or a plurality of intersecting vehicles stopped near the intersection at an intersection crossing at the intersection; a control unit capable of controlling at least one of a notification to a driver of the vehicle and braking of the vehicle based on the first data and the second data; Equipped with The control unit determining, in response to a change in the lighting state of a second traffic light for the intersecting vehicle, which is different from the first traffic light for the vehicle, among the plurality of traffic lights, a possibility that at least one target vehicle among the one or more intersecting vehicles will start entering the intersection contrary to the indication of the second traffic light; controlling at least one of the notification and the braking in accordance with the magnitude of the possibility; It is possible to carry out Driving assistance device.
14. the acquisition unit is capable of acquiring third data regarding a line of sight or a facial direction of a driver of the target vehicle, The control unit is capable of determining the possibility based on the line of sight or the direction of the face of the driver obtained from the third data. The driving assistance device according to claim 13.
15. A vehicle equipped with the driving assistance device according to any one of claims 1, 9 and 13. vehicle.
Citation Information
Patent Citations
Driving assistance devices
JP6922479B2