Traffic safety support system and computer program

Abstract

To start support control with a margin under a small processing load.SOLUTION: A prediction unit 62 of a traffic safety support system includes: a movement state information acquisition section 620 that acquires movement state information of a prediction target; a surrounding state information acquisition section 621 that acquires surrounding state information of surrounding traffic participants; a driver state information acquisition section 623 that acquires driver state information of a driver of the prediction target; a first movement state prediction section 624 that predicts a first predicted movement state of the prediction target on the basis of the movement state information; a second movement state prediction section 625 that predicts a second predicted movement state of the prediction target on the basis of the driver state information; a collision risk calculation section 626 that calculates a first collision risk value for the first predicted movement state and a second collision risk value for the second predicted movement state; and a support control unit 65 that executes support control fro the prediction target in a case where at least any one of the first and second collision risk values is greater than a collision determination threshold value.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a traffic safety support system and a computer program, and more particularly to a traffic safety support system and a computer program that support the safe movement of traffic participants as people or mobile objects. [Background technology]

[0002] In public transportation, various traffic participants, such as moving objects such as four-wheeled automobiles, motorcycles, and bicycles, as well as pedestrians, move at different speeds based on their own will. As a technology for improving the safety and convenience of such traffic participants in public transportation, for example, Patent Document 1 discloses a driving safety device that supports safe driving by vehicle drivers.

[0003] The collision avoidance device shown in Patent Document 1 predicts the acceleration when the vehicle starts moving based on the result of judging the degree of haste when the vehicle stops at an intersection, and further predicts the possibility of a collision after the vehicle starts moving based on this acceleration. Furthermore, when the collision avoidance device predicts the possibility of a collision, it issues a warning to avoid the collision. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2011-118723 A Summary of the Invention [Problem to be solved by the invention]

[0005] Generally, in order to predict the possibility of a collision of a vehicle in the future, it is necessary to predict the future behavior of the vehicle with high accuracy. However, in many cases, there are many patterns of the future behavior of a traveling vehicle, so it takes time to narrow down the most likely behavior pattern from among the multiple behavior patterns that the vehicle may take in the future. In addition, in order to avoid a collision of the vehicle, it is necessary to start assistance control as soon as possible, but in order to do so, it is necessary to narrow down the most likely behavior pattern in a short time, which increases the processing load.

[0006] An object of the present invention is to provide a traffic safety support system and a computer program that can start support control with ample time under a small processing load. [Means for solving the problem]

[0007] (1) A traffic safety support system according to the present invention supports safe traffic in a traffic area of ​​a prediction target that is a moving body moving within the traffic area of ​​the prediction target, and is characterized in that it includes a moving state information acquisition unit that acquires moving state information related to the moving state of the prediction target, a surrounding state information acquisition unit that acquires surrounding state information related to the moving states of surrounding traffic participants present around the prediction target in the traffic area, a driver state information acquisition unit that acquires driver state information related to the state of the driver of the prediction target, a first moving state prediction unit that predicts a first predicted moving state of the prediction target based on the moving state information, a second moving state prediction unit that predicts a second predicted moving state of the prediction target based on the driver state information, a collision risk calculation unit that calculates a first collision risk value between the prediction target and the surrounding traffic participants in the first predicted moving state and a second collision risk value between the prediction target and the surrounding traffic participants in the second predicted moving state based on the surrounding state information, and an assistance control unit that executes assistance control for the prediction target when at least one of the first collision risk value and the second collision risk value is greater than a predetermined threshold.

[0008] (2) In this case, it is preferable that the assistance control unit executes the assistance control so that the predicted object takes a first avoidance action to realize the first predicted movement state when the first collision risk value is equal to or less than the threshold value and the second collision risk value is greater than the threshold value, executes the assistance control so that the predicted object takes a second avoidance action to realize the second predicted movement state when the second collision risk value is equal to or less than the threshold value and the first collision risk value is greater than the threshold value, and executes the assistance control so that the predicted object takes a collision avoidance action to avoid a collision with the surrounding traffic participant or a collision damage mitigation action to reduce damage caused by a collision when both the first collision risk value and the second collision risk value are greater than the threshold value.

[0009] (3) In this case, it is preferable that the collision risk calculation unit calculates the first collision risk value by searching a risk map that associates the movement speed of the prediction object and a future collision risk value of the prediction object based on a first predicted movement speed profile corresponding to the first predicted movement state, and calculates the second collision risk value by searching the risk map based on a second predicted movement speed profile corresponding to the second predicted movement state.

[0010] (4) In this case, it is preferable that the traffic safety support system includes a group of on-board devices that move together with the predicted object, and a traffic management server capable of communicating with the group of on-board devices, the traffic management server including the movement state information acquisition unit, the surrounding state information acquisition unit, the driver state information acquisition unit, the first movement state prediction unit, the second movement state prediction unit, the collision risk calculation unit, and the assistance control unit, the group of on-board devices including an on-board notification device that notifies the driver of information by at least one of an image and a sound, and the assistance control unit executes notification control as the assistance control by activating the on-board notification device to notify the driver of information for avoiding a collision with the predicted object or reducing damage caused by the collision.

[0011] (5) In this case, it is preferable that, in the notification control, the assistance control unit notifies the driver of information encouraging acceleration or deceleration in accordance with the first avoidance action, the second avoidance action, the collision avoidance action, or the collision damage mitigation action.

[0012] (6) In this case, in the notification control, it is preferable that the assistance control unit displays on the in-vehicle notification device an image generated by plotting a moving speed profile corresponding to the first avoidance action, the second avoidance action, the collision avoidance action, or the collision damage mitigation action on the risk map.

[0013] (7) In this case, it is preferable that the assistance control unit highlights areas on the risk map in which the collision risk value is greater than the threshold value and displays them on the in-vehicle notification device.

[0014] (8) In this case, it is preferable that the driver state information acquisition unit acquires information regarding the driver's surrounding confirmation state as the driver state information, and the second movement state prediction unit predicts the second predicted movement state based on the movement state information, the surrounding state information, and the driver state information.

[0015] (9) In this case, it is preferable that the traffic safety support system further includes a traffic environment information acquisition unit that acquires traffic environment information around the prediction target in the traffic area, and the second movement state prediction unit includes a traffic scene identification unit that identifies a traffic scene of the prediction target based on the movement state information, the surrounding state information, and the traffic environment information, a behavior pattern selection unit that selects at least one from a plurality of predetermined behavior patterns as a predicted behavior pattern based on the traffic scene and the driver state information, and a behavior prediction unit that predicts the second predicted movement state based on the predicted behavior pattern.

[0016] (10) In this case, it is preferable that the traffic safety support system includes a group of on-board devices that move together with the predicted object, and a traffic management server capable of communicating with the group of on-board devices, the traffic management server including the movement state information acquisition unit, the surrounding state information acquisition unit, the driver state information acquisition unit, the first movement state prediction unit, the second movement state prediction unit, the collision risk calculation unit, and the assistance control unit, the group of on-board devices including an on-board driving assistance device that automatically controls the behavior of the predicted object, and the assistance control unit executes automatic behavior control as the assistance control, which operates the on-board driving assistance device so as to avoid a collision of the predicted object or reduce damage caused by a collision. Effect of the Invention

[0017] (1) In a traffic safety support system, the moving state information acquisition unit acquires moving state information on the moving state of a prediction target, the surrounding state information acquisition unit acquires surrounding state information on the moving states of surrounding traffic participants, and the driver state information acquisition unit acquires driver state information on the state of the driver of the prediction target. The first moving state prediction unit predicts a first predicted moving state of the prediction target based on the moving state information, the second moving state prediction unit predicts a second predicted moving state of the prediction target based on the driver state information, and the collision risk calculation unit calculates a first collision risk value between the prediction target and the surrounding traffic participants in the first predicted moving state and a second collision risk value between the prediction target and the surrounding traffic participants in the second predicted moving state based on the surrounding state information. The support control unit executes support control for the prediction target when at least one of the first and second collision risk values ​​is greater than a threshold value. That is, in the present invention, the support control unit predicts a predicted moving state corresponding to the future behavior of the prediction target by two different algorithms, and starts support control for the prediction target when at least one of these prediction results is predicted to cause a collision with the surrounding traffic participants. Therefore, according to the present invention, assistance control can be started without narrowing down the future behavior pattern of the prediction target, thereby reducing the processing load and enabling the timing for starting assistance control to be advanced.

[0018] (2) When the first collision risk value is equal to or less than the threshold and the second collision risk value is greater than the threshold, the support control unit executes support control so that the predicted target performs a first avoidance action that realizes a first predicted moving state with a low collision risk, and when the second collision risk value is equal to or less than the threshold and the first collision risk value is greater than the threshold, the support control unit executes support control so that the predicted target performs a second avoidance action that realizes a second predicted moving state with a low collision risk. The support control unit executes support control so that the predicted target performs an avoidance action that realizes a predicted moving state that is already known to have a low collision risk in this way, thereby enabling the support control unit to promptly start support control. Furthermore, when both the first and second collision risk values ​​are greater than the threshold, the support control unit executes support control so that the predicted target performs a collision avoidance action or a collision damage reduction action. This makes it possible to avoid a collision of the predicted target or reduce damage due to a collision even when both the first and second collision risk values ​​are greater than the threshold.

[0019] (3) The collision risk calculation unit can quickly calculate the first and second collision risk values ​​by using a risk map that associates the moving speed of the prediction target with the future collision risk value of the prediction target. Furthermore, according to the present invention, the time required to calculate the collision risk value can be shortened, and the timing to start the support control can be accordingly advanced.

[0020] (4) The traffic safety support system includes a group of on-board devices that move in a traffic area together with a prediction target, and a traffic management server that can communicate with the group of on-board devices. The traffic management server is configured with the above-mentioned moving state information acquisition unit, surrounding state information acquisition unit, driver state information acquisition unit, first moving state prediction unit, second moving state prediction unit, collision risk calculation unit, and support control unit. Therefore, according to the present invention, the moving state information, surrounding state information, driver state information, etc. of the prediction target can be collected by the traffic management server, so that the future collision risk of the prediction target can be predicted with high accuracy. The support control unit of the traffic management server also executes, as support control, a notification control that notifies the driver of information for avoiding a collision of the prediction target or reducing damage due to the collision by activating the on-board notification device of the group of on-board devices. Therefore, according to the present invention, the driver of the prediction target who receives the notification can take action to avoid the predicted collision or reduce damage due to the collision.

[0021] (5) In the notification control, the support control unit notifies the driver of information encouraging acceleration or deceleration according to the first avoidance action, the second avoidance action, the collision avoidance action, or the collision damage mitigation action. Thus, according to the present invention, the driver of the prediction target can avoid the predicted collision or mitigate damage caused by the collision by performing an acceleration operation or a deceleration operation in accordance with the notification.

[0022] (6) In the notification control, the support control unit displays an image generated by plotting a moving speed profile corresponding to the first avoidance action, the second avoidance action, the collision avoidance action, or the collision damage mitigation action on a risk map on the in-vehicle notification device. Thus, according to the present invention, the driver of the prediction target can easily recognize the presence of a risk and the moving speed profile for avoiding this risk by looking at the image displayed by the in-vehicle notification device.

[0023] (7) In the present invention, when the assistance control unit displays an image of the risk map on the in-vehicle notification device based on the notification control, the assistance control unit displays on the in-vehicle notification device an area on the risk map where the collision risk value is greater than a threshold value in an emphasized manner. Thus, according to the present invention, the driver of the prediction target can quickly recognize the existence of a risk by looking at the image displayed by the in-vehicle notification device.

[0024] (8) In the present invention, the driver state information acquisition unit acquires information on the driver's surroundings confirmation state as the driver state information, and the second movement state prediction unit predicts the second predicted movement state based on the movement state information, the surroundings state information, and the driver state information. Therefore, according to the present invention, the second predicted movement state can be predicted reflecting the surroundings confirmation state by the driver, so that the future collision risk can be predicted with high accuracy.

[0025] (9) In the present invention, the second movement state prediction unit includes a traffic scene identification unit that identifies a traffic scene of a prediction target based on movement state information, surrounding state information, and traffic environment information, a behavior pattern selection unit that selects at least one from a plurality of predetermined behavior patterns as a predicted behavior pattern based on the traffic scene and the driver state information, and a behavior prediction unit that predicts a second predicted movement state based on the predicted behavior pattern. Thus, according to the present invention, by using the traffic scene in which the prediction target is placed and the driver state information of the driver of the prediction target, it is possible to efficiently narrow down the predicted behavior pattern from among a plurality of behavior patterns in consideration of the driver's state. Therefore, according to the present invention, the second predicted movement state can be predicted with a small processing load in consideration of the driver's state, so that a future collision risk can be accurately predicted.

[0026] (10) A traffic safety support system includes a group of on-board devices that move in a traffic area together with a prediction target, and a traffic management server that can communicate with the group of on-board devices. The traffic management server is configured with the above-mentioned moving state information acquisition unit, surrounding state information acquisition unit, driver state information acquisition unit, first moving state prediction unit, second moving state prediction unit, collision risk calculation unit, and support control unit. According to the present invention, the moving state information, surrounding state information, driver state information, and the like of the prediction target can be collected by the traffic management server, so that the future collision risk of the prediction target can be predicted with high accuracy. The support control unit of the traffic management server executes automatic behavior control as support control, which operates the on-board driving support device of the group of on-board devices so as to avoid a collision of the prediction target or reduce damage due to the collision. According to the present invention, the traffic management server can automatically control the behavior of the prediction target through the automatic behavior control, so that the predicted collision can be automatically avoided or damage due to the collision can be reduced. [Brief description of the drawings]

[0027] [Figure 1] 1 is a diagram showing the configuration of a traffic safety support system according to a first embodiment of the present invention and a part of a target traffic area supported by the traffic safety support system. [Diagram 2] 2 is a block diagram showing the configuration of a traffic management server and a plurality of area terminals communicably connected to the traffic management server. FIG. [Diagram 3] FIG. 11 is a functional block diagram showing a specific configuration of a prediction unit. [Figure 4] 4 is a functional block diagram showing a specific configuration of a second movement state prediction unit. FIG. [Diagram 5] FIG. 2 is a diagram illustrating an example of a monitoring area. [Figure 6] FIG. 6 is a diagram showing an example of a risk map generated by a risk map generating unit with a first traffic participant as a prediction target in the example shown in FIG. 5. [Figure 7] FIG. 6 is a diagram showing an example of a risk map generated by a risk map generating unit with a second traffic participant as a prediction target in the example shown in FIG. 5. [Figure 8A] 6 is a diagram showing an example of a cognitive state estimation map in a case where a first traffic participant is a prediction target in the example shown in FIG. 5. FIG. [Figure 8B] 6 is a diagram showing an example of a cognitive state estimation map in a case where a first traffic participant is a prediction target in the example shown in FIG. 5. FIG. [Figure 9] 11A and 11B are diagrams illustrating an example of an image displayed on an in-vehicle notification device based on notification control by the assistance control unit. [Figure 10] 10 is a flowchart showing a specific procedure of a traffic safety support process performed by the traffic management server. [Figure 11] FIG. 11 is a functional block diagram showing a specific configuration of a prediction unit of a traffic safety support system according to a second embodiment of the present invention. [Figure 12] 4 is a functional block diagram showing a specific configuration of a second movement state prediction unit. FIG. [Figure 13] FIG. 2 is a diagram illustrating an example of a monitoring area. [Figure 14] 10 is a flowchart showing a specific procedure of a traffic safety support process performed by the traffic management server. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] First Embodiment Hereinafter, a traffic safety support system according to a first embodiment of the present invention will be described with reference to the drawings.

[0029] FIG. 1 is a diagram showing a schematic configuration of a traffic safety support system 1 according to this embodiment and a part of a target traffic area 9 in which traffic participants who are targets of support by this traffic safety support system 1 exist.

[0030] The traffic safety support system 1 recognizes pedestrians 4, which are people, and moving objects such as four-wheeled vehicles 2 and motorcycles 3, which are moving objects in the target traffic area 9, as individual traffic participants, and notifies each traffic participant of support information generated through this recognition, encouraging communication between each traffic participant moving based on their own will (specifically, for example, mutual recognition between each traffic participant) and recognition of the surrounding traffic environment, and automatically controlling the behavior of the moving objects, thereby supporting the safe and smooth traffic of each traffic participant in the target traffic area 9.

[0031] Fig. 1 illustrates a case where a target traffic area 9 is the vicinity of an intersection 52 in an urban area, which includes a roadway 51, an intersection 52, a sidewalk 53, and a traffic light 54 as traffic infrastructure facilities. Fig. 1 illustrates a case where a total of seven four-wheeled automobiles 2 and a total of two motorcycles 3 are moving on the roadway 51 and the intersection 52, and a total of three pairs of pedestrians 4 are moving on the sidewalk 53 and the intersection 52. Fig. 1 also illustrates a case where a total of three infrastructure cameras 56 are installed.

[0032] The traffic safety support system 1 comprises a group of on-board devices 20 (including on-board devices mounted on the four-wheeled automobiles 2 as well as a portable information processing terminal held or worn by the driver of the four-wheeled automobile 2) that moves with each four-wheeled automobile 2, a group of on-board devices 30 (including on-board devices mounted on the motorcycles 3 as well as a portable information processing terminal held or worn by the driver of the motorcycle 3) that moves with each motorcycle 3, a portable information processing terminal 40 held or worn by each pedestrian 4, a plurality of infrastructure cameras 56 installed in the target traffic area 9, a signal control device 55 that controls a traffic light 54, and a traffic management server 6 that is communicatively connected to a plurality of terminals (hereinafter simply referred to as "area terminals") present in the target traffic area 9, such as the groups of on-board devices 20, 30, the portable information processing terminal 40, the infrastructure cameras 56, and the signal control device 55.

[0033] The traffic management server 6 is composed of one or more computers communicatively connected to the above-mentioned multiple area terminals via a base station 57. More specifically, the traffic management server 6 is composed of a server connected to the multiple area terminals via the base station 57, a network core, and the Internet, an edge server connected to the multiple area terminals via the base station 57 and a MEC (Mulch-access Edge Computing) core, etc.

[0034] FIG. 2 is a block diagram showing the configuration of the traffic management server 6 and a plurality of area terminals connected to the traffic management server 6 so as to be able to communicate with each other.

[0035] The group of on-board devices 20 mounted on four-wheeled vehicles 2 in the target traffic area 9 includes, for example, an on-board driving assistance device 21 that assists the driver in driving, an on-board notification device 22 that notifies the driver of various information, a driving subject state sensor 23 that detects the state of the driver while driving, and an on-board communication device 24 that wirelessly communicates between the vehicle and the traffic management server 6 or between other vehicles in the vicinity of the vehicle.

[0036] The in-vehicle driving assistance device 21 includes an external sensor unit, a vehicle state sensor, a navigation device, and a driving assistance ECU. The external sensor unit includes an external camera unit that captures the surroundings of the vehicle, a plurality of in-vehicle external sensors mounted on the vehicle, such as a radar unit and a LIDAR (Light Detection and Ranging (LIDAR)) unit that detect objects outside the vehicle by using electromagnetic waves, and an external recognition device that acquires information about the surrounding state of the vehicle by performing sensor fusion processing on the detection results of the in-vehicle external sensors. The vehicle state sensor is composed of sensors that acquire information about the running state of the vehicle, such as a vehicle speed sensor, an acceleration sensor, a steering angle sensor, a yaw rate sensor, a position sensor, and an orientation sensor. The navigation device includes, for example, a GNSS receiver that identifies the current position of the vehicle based on a signal received from a GNSS (Global Navigation Satellite System) satellite, a storage device that stores map information, and the like.

[0037] The driving assistance ECU executes driving assistance control that automatically controls the behavior of the vehicle body, such as lane departure suppression control, lane change control, preceding vehicle following control, false start suppression control, collision mitigation brake control, and collision avoidance control, based on information acquired by on-board sensing devices such as an external sensor unit, a vehicle state sensor, and a navigation device, and on cooperation assistance information transmitted from the traffic management server 6. The driving assistance ECU also generates driving assistance information for supporting safe driving by the driver, based on information acquired by the external sensor unit, the vehicle state sensor, and the navigation device, and transmits it to the on-board notification device 22.

[0038] The driver's subject state sensor 23 is composed of various devices that acquire time-dependent data of information correlated with the driving ability of the driver while driving. The driver's subject state sensor 23 is composed of, for example, an in-vehicle camera that acquires facial image data of the driver while driving, a biometric information sensor that acquires biometric information of the driver while driving, etc. More specifically, the biometric information sensor here is a seat belt sensor that is attached to the seat belt worn by the driver and detects the driver's pulse, the presence or absence of breathing, etc., a steering sensor that is attached to the steering wheel held by the driver and detects the skin potential of the driver, and a wearable terminal that detects the heart rate, blood pressure, blood oxygen saturation, etc.

[0039] The in-vehicle communication device 24 has a function of transmitting information acquired by the driving assistance ECU (including information acquired by the external sensor unit, the vehicle status sensor, and the navigation device, etc., and control information related to driving assistance control currently being executed), and information related to the driving subject acquired by the driving subject status sensor 23 (the driver's facial image data and biometric information), etc., to the traffic management server 6, and a function of receiving collaborative assistance information transmitted from the traffic management server 6, and transmitting the received collaborative assistance information to the in-vehicle driving assistance device 21 and the in-vehicle notification device 22.

[0040] The in-vehicle notification device 22 is composed of various devices that notify the driver of various information through the driver's hearing, vision, touch, etc. by operating a man-machine interface (hereinafter sometimes abbreviated as "HMI (Human Machine Interface)") in a manner determined based on the driving assistance information transmitted from the in-vehicle driving assistance device 21 and the collaborative assistance information transmitted from the traffic management server 6.

[0041] The group of on-board devices 30 mounted on motorcycles 3 in the target traffic area 9 includes, for example, an on-board driving assistance device 31 that assists the rider in driving, an on-board notification device 32 that notifies the rider of various information, a rider status sensor 33 that detects the status of the rider while driving, and an on-board communication device 34 that wirelessly communicates between the vehicle and the traffic management server 6 or between the vehicle and other vehicles in the vicinity of the vehicle.

[0042] The in-vehicle driving assistance device 31 includes an external sensor unit, a vehicle state sensor, a navigation device, and a driving assistance ECU. The external sensor unit includes an external camera unit that captures the surroundings of the vehicle, a plurality of in-vehicle external sensors mounted on the vehicle, such as a radar unit or a lidar unit that detects objects outside the vehicle by using electromagnetic waves, and an external recognition device that acquires information about the surroundings of the vehicle by performing sensor fusion processing on the detection results of the in-vehicle external sensors. The vehicle state sensor is composed of sensors that acquire information about the running state of the vehicle, such as a vehicle speed sensor and a 5-axis or 6-axis inertial measurement unit. The navigation device includes, for example, a GNSS receiver that identifies the current position based on a signal received from a GNSS satellite, a storage device that stores map information, and the like.

[0043] The driving assistance ECU executes driving assistance control that automatically controls the behavior of the vehicle body, such as lane keeping control, lane departure suppression control, lane change control, preceding vehicle following control, false start suppression control, and collision mitigation brake control, based on information acquired by on-board sensing devices such as an external sensor unit, a vehicle state sensor, and a navigation device, and on cooperation assistance information transmitted from the traffic management server 6. The driving assistance ECU also generates driving assistance information for supporting safe driving by the rider, based on information acquired by the external sensor unit, the vehicle state sensor, and the navigation device, and transmits it to the on-board notification device 32.

[0044] The rider status sensor 33 is composed of various devices that acquire information correlated with the driving ability of the rider while driving. The rider status sensor 33 is composed of, for example, an in-vehicle camera that acquires facial image data of the rider while driving, a biometric information sensor that acquires biometric information of the rider while driving, etc. More specifically, the biometric information sensor is a seat sensor that is provided on the seat on which the rider sits and detects the rider's pulse, the presence or absence of breathing, etc., a helmet sensor that is provided on the helmet worn by the rider and detects the rider's pulse, the presence or absence of breathing, skin potential, etc., a wearable terminal that detects the heart rate, blood pressure, blood oxygen saturation, etc., etc.

[0045] The in-vehicle communication device 34 has a function of transmitting information acquired by the driving assistance ECU (including information acquired by the external sensor unit, the vehicle status sensor, and the navigation device, etc., and control information related to driving assistance control currently being executed), and information related to the rider acquired by the rider status sensor 33 (facial image data and biometric information of the rider), etc., to the traffic management server 6, and a function of receiving collaborative assistance information transmitted from the traffic management server 6, and transmitting the received collaborative assistance information to the in-vehicle driving assistance device 31 and the in-vehicle notification device 32.

[0046] The in-vehicle notification device 32 is composed of various devices that notify the rider of various information through the rider's hearing, vision, touch, etc. by operating the HMI in a predetermined manner based on the driving assistance information transmitted from the in-vehicle driving assistance device 21 and the collaborative assistance information transmitted from the traffic management server 6.

[0047] The portable information processing terminal 40 owned or worn by the pedestrian 4 in the target traffic area 9 is composed of, for example, a wearable terminal worn by the pedestrian 4 or a smartphone owned by the pedestrian 4. The wearable terminal has functions to measure the biometric information of the pedestrian 4, such as the heart rate, blood pressure, and blood oxygen saturation, and transmit the measurement data of this biometric information to the traffic management server 6, transmit pedestrian information related to the pedestrian 4, such as the position information, movement acceleration, and schedule information of the pedestrian 4, to the traffic management server 6, and receive collaboration support information transmitted from the traffic management server 6.

[0048] The mobile information processing terminal 40 also includes a notification device 42 that notifies pedestrians of various information through their hearing, vision, touch, etc. by operating the HMI in a manner determined based on the received collaborative support information.

[0049] The infrastructure camera 56 takes images of traffic infrastructure facilities including roads, intersections, and sidewalks in the target traffic area, as well as moving objects and pedestrians moving on these roads, intersections, and sidewalks, and transmits the obtained image information to the traffic management server 6.

[0050] The signal control device 55 controls the traffic lights and transmits traffic light status information regarding the current lighting color of the traffic lights installed in the target traffic area and the timing for changing the lighting color to the traffic management server 6.

[0051] The traffic management server 6 is a computer that generates, for each traffic participant to be supported, cooperative support information for encouraging communication between traffic participants and awareness of the surrounding traffic environment based on information acquired from multiple area terminals present in the target traffic area as described above, and notifies each traffic participant of the cooperative support information. In this embodiment, the traffic participants to be supported by the traffic management server 6 are those among the multiple traffic participants present in the target traffic area who are equipped with means (e.g., the in-vehicle device group 20, 30, the mobile information processing terminal 40, the notification device 22, 32, 42) that receive the cooperative support information generated by the traffic management server 6 and operate the HMI in a mode determined based on the received cooperative support information.

[0052] The traffic management server 6 includes a target traffic area recognition unit 60 that recognizes people and moving objects in a target traffic area as individual traffic participants, a driving subject information acquisition unit 61 that acquires driving subject state information correlated with the driving ability of the driving subject of the moving object recognized as a traffic participant by the target traffic area recognition unit 60, a prediction unit 62 that predicts the future of multiple traffic participants in the target traffic area, an assistance control unit 65 that uses the prediction results by the prediction unit 62 to execute assistance control to support safe traffic for each traffic participant recognized as an assistance target by the target traffic area recognition unit 60, a traffic environment database 67 that accumulates information about the traffic environment in the target traffic area, and a driving history database 68 that accumulates information about the past driving history of pre-registered driving subjects.

[0053] The traffic environment database 67 stores information related to the traffic environment of traffic participants in a target traffic area, such as map information of the target traffic area registered in advance (e.g., road width, number of lanes, speed limit, sidewalk width, presence or absence of guardrails between the roadway and sidewalk, and location of crosswalks) and risk area information related to particularly high-risk areas within the target traffic area. Hereinafter, the information stored in the traffic environment database 67 is also referred to as registered traffic environment information.

[0054] The driving history database 68 stores information on the past driving history of a previously registered driver in association with the registration number of a mobile object owned by the driver. Therefore, if the registration number of a recognized mobile object can be identified by the target traffic area recognition unit 60 described later, the driving history database 68 can be searched based on the registration number to obtain the past driving history of the driver of the recognized mobile object. Hereinafter, the information stored in the driving history database 68 is also referred to as registered driving history information.

[0055] The target traffic area recognition unit 60 recognizes recognition objects including each traffic participant, which is a person or a moving object, in the target traffic area and the traffic environment of each traffic participant in the target traffic area, based on information transmitted from the above-mentioned area terminals (the vehicle-mounted device group 20, 30, the mobile information processing terminal 40, the infrastructure camera 56, and the signal control device 55) in the target traffic area and registered traffic environment information read from the traffic environment database 67, and obtains recognition information regarding these recognition objects.

[0056] Here, the information transmitted from the on-board driving support device 21 and the on-board communication device 24 included in the on-board device group 20 to the target traffic area recognition unit 60, and the information transmitted from the on-board driving support device 31 and the on-board communication device 34 included in the on-board device group 30 to the target traffic area recognition unit 60 include information on the state of traffic participants and traffic environment around the vehicle acquired by the external sensor unit, and information on the state of the vehicle as a traffic participant acquired by the vehicle state sensor, navigation device, etc. The information transmitted from the mobile information processing terminal 40 to the target traffic area recognition unit 60 includes information on the state of pedestrians as a traffic participant, such as position and movement acceleration. The image information transmitted from the infrastructure camera 56 to the target traffic area recognition unit 60 includes information on each traffic participant and its traffic environment, such as the appearance of traffic infrastructure facilities such as roadways, intersections, and sidewalks in the target traffic area, and the appearance of traffic participants moving in the target traffic area. The traffic light status information transmitted from the signal control device 55 to the target traffic area recognition unit 60 includes information on the traffic environment of each traffic participant, such as the current lighting color of the traffic light and the timing of changing the lighting color. In addition, the registered traffic environment information that the target traffic area recognition unit 60 reads from the traffic environment database 67 includes information on the traffic environment of each traffic participant, such as map information of the target traffic area and risk area information.

[0057] Therefore, based on the information transmitted from these area terminals, the target traffic area recognition unit 60 can obtain the recognition information of each traffic participant (hereinafter also referred to as "traffic participant recognition information"), such as the position in the target traffic area of ​​each traffic participant in the target traffic area, the movement vector (i.e., a vector extending along the movement direction and having a length proportional to the movement speed), the movement acceleration, the vehicle type of the moving body, the vehicle class of the moving body, the registration number of the moving body, the number of pedestrians, the age group of the pedestrians, etc. Based on the information transmitted from these area terminals, the target traffic area recognition unit 60 can also obtain the recognition information of the traffic environment of each traffic participant in the target traffic area (hereinafter also referred to as "traffic environment recognition information"), such as the width of the roadway, the number of lanes, the speed limit, the width of the sidewalk, the presence or absence of a guardrail between the roadway and the sidewalk, the lighting color of the traffic light and its switching timing, and risk area information, etc.

[0058] The target traffic area recognition unit 60 transmits the traffic participant recognition information and traffic environment recognition information acquired as described above to the driving subject information acquisition unit 61, the prediction unit 62, the assistance control unit 65, and the like.

[0059] The driving subject information acquisition unit 61 acquires driving subject state information and driving subject characteristic information that are correlated with the current driving ability of the driving subject of the mobile body recognized as a traffic participant by the target traffic area recognition unit 60 based on information transmitted from the above-mentioned area terminals (particularly, the vehicle-mounted device groups 20, 30) in the target traffic area and registered driving history information read from the driving history database 68.

[0060] More specifically, when the driver of a four-wheeled vehicle recognized as a traffic participant by the target traffic area recognition unit 60 is a human, the driver subject information acquisition unit 61 acquires information transmitted from the on-board device group 20 mounted on the four-wheeled vehicle as driver subject state information of the driver. Also, when the driver of a motorcycle recognized as a traffic participant by the target traffic area recognition unit 60 is a human, the driver subject information acquisition unit 61 acquires information transmitted from the on-board device group 30 mounted on the motorcycle as driver subject state information of the rider.

[0061] Here, the information transmitted from the driving subject state sensor 23 and the in-vehicle communication device 24 included in the in-vehicle device group 20 to the driving subject information acquisition unit 61 includes time-lapse data such as face image data of the driver while driving and biometric information of the driver while driving, and includes information correlated with the driving ability of the driver while driving. Furthermore, the information transmitted from the rider state sensor 33 and the in-vehicle communication device 34 included in the in-vehicle device group 30 to the driving subject information acquisition unit 61 includes time-lapse data such as face image data of the rider while driving and biometric information of the rider while driving, and includes information correlated with the driving ability of the rider while driving. Furthermore, the information transmitted from the mobile information processing terminals 25, 35 included in the in-vehicle device groups 20, 30 to the driving subject information acquisition unit 61 includes schedule information of the driver or rider. For example, when the driver or rider is driving a moving body under a tight schedule, he or she may become impatient and his or her driving ability may decrease. For this reason, it can be said that the schedule information of the driver or rider is information correlated with his or her own driving ability.

[0062] The driving subject information acquisition unit 61 acquires driving subject characteristic information regarding the driving subject's characteristics (e.g., excessive sudden lane changes, excessive sudden acceleration / deceleration, etc.) that are correlated with the driving subject's current driving ability while driving, by using both or either of the driving subject state information for the driving subject acquired by the above procedure and the registered driving history information read from the driving history database 68.

[0063] The driver subject information acquisition unit 61 transmits the driver subject state information and driver subject characteristic information of the driver subject acquired as described above to the prediction unit 62, the assistance control unit 65, and the like.

[0064] The prediction unit 62 extracts a portion of the target traffic area as a monitoring area, and predicts the future risk of a prediction target selected from among multiple traffic participants in this monitoring area, based on the traffic participant recognition information and traffic environment recognition information acquired by the target traffic area recognition unit 60, and the driving subject state information and driving subject characteristic information acquired by the driving subject information acquisition unit 61.

[0065] The target traffic area is a relatively wide area determined by, for example, a city, town, or village, whereas the surveillance area is an area that a four-wheeled vehicle can pass through within several tens of seconds if traveling at the legal speed, such as an intersection or the vicinity of a specific facility.

[0066] FIG. 3 is a functional block diagram showing a specific configuration of the prediction unit 62. As shown in FIG. The prediction unit 62 includes a movement state information acquisition unit 620, a surrounding state information acquisition unit 621, a traffic environment information acquisition unit 622, a driver state information acquisition unit 623, a first movement state prediction unit 624, a second movement state prediction unit 625, a collision risk calculation unit 626, and an assistance action decision unit 627, and by using these, predicts future risks in the monitoring area to be predicted.

[0067] The moving state information acquisition unit 620 determines one of the multiple traffic participants present in the monitoring area as a prediction target based on the traffic participant recognition information transmitted from the target traffic area recognition unit 60, and acquires moving state information related to the moving state of the prediction target. More specifically, the moving state information acquisition unit 620 extracts information related to the moving state of the prediction target from the traffic participant recognition information acquired by the target traffic area recognition unit 60, and acquires this as moving state information. Here, the moving state information is composed of multiple parameters that characterize the moving state of the prediction target, such as the position, moving vector, moving acceleration, vehicle type, and vehicle class of the prediction target.

[0068] The surrounding state information acquisition unit 621 identifies multiple traffic participants (hereinafter, the traffic participants existing around the prediction target are also referred to as "surrounding traffic participants") existing around the prediction target in the monitoring area based on the traffic participant recognition information transmitted from the target traffic area recognition unit 60, and acquires surrounding state information related to the movement state of the multiple traffic participants existing around the prediction target. More specifically, the surrounding state information acquisition unit 621 extracts information related to the movement state of the multiple traffic participants existing around the prediction target from the traffic participant recognition information acquired by the target traffic area recognition unit 60, and acquires this as surrounding state information. Here, the surrounding state information is composed of multiple parameters that characterize the movement state of each traffic participant, such as the position, movement vector, movement acceleration, vehicle type, and vehicle class of each traffic participant existing around the prediction target.

[0069] The traffic environment information acquisition unit 622 acquires traffic environment information around the prediction target in the monitoring area based on the traffic environment recognition information transmitted from the target traffic area recognition unit 60 and the registered traffic environment information stored in the traffic environment database 67. More specifically, the traffic environment information acquisition unit 622 extracts information on the traffic environment around the monitoring area or the prediction target from the traffic environment recognition information acquired by the target traffic area recognition unit 60 and the registered traffic environment information stored in the traffic environment database 67, and acquires this as traffic environment information. Here, the traffic environment information is composed of a plurality of parameters that characterize the traffic environment around the prediction target, such as the width of the roadway, the number of lanes, the speed limit, the width of the sidewalk, the presence or absence of a guardrail between the roadway and the sidewalk, the lighting color of the traffic light and the switching timing thereof, risk area information, etc.

[0070] The driver state information acquisition unit 623 acquires driver state information related to the state of the driver to be predicted based on the driver subject state information transmitted from the driver subject information acquisition unit 61. More specifically, the driver state information acquisition unit 623 acquires information related to the surrounding confirmation state of the driver to be predicted as driver state information based on the driver subject state information transmitted from the driver subject information acquisition unit 61, the movement state information acquired by the movement state information acquisition unit 620, the surrounding state information acquired by the surrounding state information acquisition unit 621, and the traffic environment information acquired by the traffic environment information acquisition unit 622.

[0071] More specifically, the driver status information acquisition unit 623 extracts objects whose presence and status the driver of the predicted target should check in order for the predicted target to move safely and smoothly within the monitoring area (e.g., the presence of moving objects and pedestrians around the predicted target, such as the vehicle in front, the vehicle following, and the vehicle running alongside, as well as the status of traffic lights, etc.) based on the movement status information, surrounding status information, and traffic environment information.

[0072] The driver state information acquisition unit 623 also extracts information about the driver of the prediction target from the driver subject state information transmitted from the driver subject information acquisition unit 61, and generates information about the confirmation state of each confirmation target extracted as described above as driver state information based on the driver subject state information about the driver of the prediction target. The driver subject information acquired by the driver subject information acquisition unit 61 as described above includes time-series data such as face image data and biological information of the driver of the prediction target, and schedule information of the driver. Therefore, the driver state information acquisition unit 623 generates driver state information based on such driver subject information.

[0073] In this embodiment, a case will be described in which the driver's confirmation count and confirmation time of the confirmation target are used as the driver state information. In this case, the driver state information acquisition unit 623 calculates the driver's gaze direction based on the face image data of the driver of the prediction target. The driver state information acquisition unit 623 also calculates the relative position of each confirmation target with respect to the driver of the prediction target based on the movement state information, surrounding state information, and traffic environment information, and calculates the gaze range of the driver's gaze direction for each confirmation target according to the calculated relative position. The driver state information acquisition unit 623 also counts up the number of confirmations and the confirmation time for the confirmation target on the condition that the driver's gaze direction is within the gaze range determined for each confirmation target.

[0074] The first moving state prediction unit 624 predicts a moving state of the prediction target in the monitoring area up to a predetermined predicted time ahead (hereinafter, the moving state of the prediction target up to the predicted time ahead predicted by the first moving state prediction unit 624 is also referred to as a "first predicted moving state") based on the moving state information, surrounding state information, and traffic environment information. In other words, the first moving state prediction unit 624 calculates a moving speed profile of the prediction target from the present to the predicted time ahead (hereinafter, the moving speed profile calculated by the first moving state prediction unit 624 is also referred to as a "first predicted moving speed profile") as a parameter characterizing the first predicted moving state of the prediction target up to the predicted time ahead.

[0075] More specifically, the first moving state prediction unit 624 calculates a predicted moving route of the prediction target in the monitoring area up to a predicted time ahead based on the moving state information, surrounding state information, traffic environment information, etc. The first moving state prediction unit 624 also acquires the current moving speed and moving acceleration of the prediction target based on the moving state information, and calculates a first predicted moving speed profile under the assumption that the prediction target moves along this predicted moving route. More specifically, the first moving state prediction unit 624 calculates the first predicted moving speed profile by assuming that the prediction target accelerates and decelerates from the current moving speed under the current moving acceleration until a predetermined time ahead, and then transitions to a constant speed.

[0076] The second moving state prediction unit 625 predicts a moving state of the prediction target in the monitoring area up to a predicted time future (hereinafter, the moving state of the prediction target up to a predicted time future predicted by the second moving state prediction unit 625 is also referred to as a "second predicted moving state") based on the moving state information, the surrounding state information, the traffic environment information, and the driver state information. In other words, the second moving state prediction unit 625 calculates a moving speed profile of the prediction target from the present to a predicted time future (hereinafter, the moving speed profile calculated by the second moving state prediction unit 625 is also referred to as a "second predicted moving speed profile") as a parameter characterizing the second predicted moving state of the prediction target up to a predicted time future.

[0077] More specifically, the second movement state prediction unit 625 calculates a predicted movement route of the prediction target in the monitoring area up to the predicted time ahead by the same procedure as the first movement state prediction unit 624. Furthermore, the second movement state prediction unit 625 calculates a second predicted movement speed profile in a case where the prediction target is assumed to move along this predicted movement route based on the driver state information including information on the surrounding confirmation state by the driver of the prediction target as described above. Below, a specific procedure for calculating the second predicted movement speed profile of the prediction target in the second movement state prediction unit 625 will be described with reference to Figs. 4 to 8B.

[0078] 4 is a functional block diagram showing a specific configuration of the second moving state prediction unit 625. The second moving state prediction unit 625 includes a risk map generation unit 6251, a cognitive state estimation map generation unit 6252, and a moving speed profile calculation unit 6253, and calculates a second predicted moving speed profile of the prediction target by using these units.

[0079] The risk map generating unit 6251 first calculates a predicted moving route of the prediction target in the monitoring area to the predicted time ahead based on the moving state information, surrounding state information, traffic environment information, etc. At this time, the risk map generating unit 6251 may calculate the predicted moving route taking into consideration the registered driving history information of the driver of the prediction target transmitted from the driving subject information acquiring unit 61.

[0080] Next, the risk map generating unit 6251 generates a risk map that associates the moving speed of the prediction target with the future collision risk value of the prediction target based on the moving state information, the surrounding state information, and the traffic environment information. Here, a specific example of the risk map and a specific procedure for generating the risk map in the risk map generating unit 6251 will be described with reference to Figs. 5 to 7.

[0081] FIG. 5 is a diagram showing an example of a monitoring area 90. FIG. 5 shows a case where three traffic participants 91, 92, and 93, which are four-wheeled vehicles, are traveling in the monitoring area 90, which is a straight road with two lanes in each direction. As shown in FIG. 5, at the time when the prediction process in the second moving state prediction unit 625 is started, the third traffic participant 93 and the first traffic participant 91 are traveling in the right lane from the front, and the second traffic participant 92 is traveling slightly behind the first traffic participant 91 in the left lane. In addition, at the time when the prediction process in the second moving state prediction unit 625 is started, it is assumed that the third traffic participant 93 is traveling at a slower speed than the first traffic participant 91, and the second traffic participant 92 is traveling at a faster speed than the first traffic participant 91.

[0082] First, the risk map generating unit 6251 calculates the predicted movement paths 91a, 92a, and 93a of the traffic participants 91, 92, and 93, as shown by the dashed arrows in Fig. 5. That is, the risk map generating unit 6251 calculates a predicted movement path 93a for the third traffic participant 93 that goes straight in the right lane, and calculates a predicted movement path 92a for the second traffic participant 92 that goes straight in the left lane. In addition, the risk map generating unit 6251 calculates a predicted movement path 91a for the first traffic participant 91 that goes straight in the right lane and then changes lanes to the left lane when the first traffic participant 91 reaches a predetermined distance behind the third traffic participant 93, thereby overtaking the third traffic participant 93.

[0083] Next, the risk map generation unit 6251 generates a risk map for the predicted target based on the movement state information, surrounding state information, and traffic environment information, assuming that each traffic participant 91-93 moves along the predicted movement routes 91a-93a to the predicted time ahead.

[0084] Fig. 6 is a diagram showing an example of a risk map generated by the risk map generating unit 6251 with the first traffic participant 91 as a prediction target under the example shown in Fig. 5. As shown in Fig. 6, the risk map is a three-dimensional map obtained by plotting a collision risk value with respect to the prediction target on a two-dimensional plane with the horizontal axis representing time and the vertical axis representing speed. Note that in Fig. 6, the current speed of the prediction target, i.e., the moving speed of the first traffic participant 91 at the start of the prediction process, is indicated by a white circle.

[0085] As shown in Fig. 6, the risk map generated for the first traffic participant 91, which is the prediction target, in the example shown in Fig. 5 includes two high-risk areas 97 and 98 with particularly high collision risk values. The high-risk area 97 appearing in the high-speed area in Fig. 6 indicates that the first traffic participant 91 may rear-end the third traffic participant 93, and the high-risk area 98 appearing in the low-speed area indicates that the first traffic participant 91, who has changed lanes, may come into contact with the second traffic participant 92.

[0086] Therefore, according to the risk map shown in FIG. 6, for example, if the predicted object accelerates according to a moving speed profile as shown in the dashed line 99a, it can be predicted that the predicted object is likely to collide with the third traffic participant 93. Also, according to the risk map shown in FIG. 6, for example, if the predicted object decelerates according to a moving speed profile as shown in the dashed line 99b, it can be predicted that the predicted object is likely to come into contact with the second traffic participant 92. Also, according to the risk map shown in FIG. 6, for example, if the predicted object decelerates at a deceleration greater than that of the dashed line 99b, as shown in the dashed line 99c, it can be predicted that the predicted object is likely to be able to avoid a collision with the third traffic participant 93 and the second traffic participant 92. This indicates that in the example shown in FIG. 5, the first traffic participant 91, which is the predicted object, can avoid a collision with the other traffic participants 92, 93 by decelerating until the second traffic participant 92 overtakes the first traffic participant 91, then changing lanes and overtaking the third traffic participant 93.

[0087] Fig. 7 is a diagram showing an example of a risk map generated by the risk map generating unit 6251 with the second traffic participant 92 as a prediction target under the example shown in Fig. 5. In Fig. 7, the current speed of the prediction target, that is, the moving speed of the second traffic participant 92 at the start time of the prediction process, is indicated by a white circle.

[0088] As shown in Fig. 7, the risk map generated for the second traffic participant 92, which is the prediction target in the example shown in Fig. 5, includes one high-risk area 96 with a particularly high collision risk value. The high-risk area 96 shown in Fig. 7 indicates that the second traffic participant 92 may come into contact with the first traffic participant 91 who has changed lanes. Note that since it is assumed that the second traffic participant 92 moves in a different lane from the third traffic participant 93, there is no possibility of the second traffic participant 92 colliding with the third traffic participant 93. Therefore, unlike the risk map for the first traffic participant 91 shown in Fig. 6, the risk map for the second traffic participant 92 does not include a high-risk area corresponding to the third traffic participant 93.

[0089] Returning to Fig. 4, the risk map generating unit 6251 generates the above-mentioned risk map based on the moving state information, surrounding state information, and traffic environment information. At this time, the risk map generating unit 6251 generates the risk map for the prediction target without using the driver state information for the driver of the prediction target. This corresponds to the risk map generated by the risk map generating unit 6251 generating the risk map for the prediction target only from objective information (moving state information, surrounding state information, and traffic environment information) that excludes the subjective opinion of the driver of the prediction target (driver state information related to the driver's surrounding confirmation state).

[0090] The cognitive state estimation map generation unit 6252 corrects the risk map generated by the risk map generation unit 6251 based on the driver state information of the driver to be predicted, thereby generating a cognitive state estimation map corresponding to the risk map as seen by the driver to be predicted.

[0091] As described with reference to Fig. 6 and Fig. 7, the risk map generated by the risk map generating unit 6251 is generated without being influenced by the subjectivity of the driver of the prediction target. That is, in the example shown in Fig. 6, the risk map for the first traffic participant 91 includes two high-risk areas 97, 98, but the driver of the first traffic participant 91 cannot properly recognize the existence of these high-risk areas 97, 98 unless he properly grasps the existence, position, speed, etc. of the surrounding traffic participants 92, 93. Therefore, the cognitive state estimation map generating unit 6252 generates a cognitive state estimation map by correcting the risk map for the prediction target generated by the risk map generating unit 6251 based on the driver state information for the driver of the prediction target.

[0092] More specifically, the recognition state estimation map generating unit 6252 first estimates the recognition level of each confirmation target present around the prediction target based on the driver state information for the driver of the prediction target generated by the driver state information acquiring unit 623. Note that, in the following, a case where the recognition level of each confirmation target is divided into three stages (high, medium, low) will be described, but the present invention is not limited to this.

[0093] If the number of confirmations of the confirmation object is equal to or greater than a predetermined first confirmation number, or the confirmation time for the confirmation object is equal to or greater than a predetermined first confirmation time, the cognitive state estimation map generation unit 6252 estimates that the driver is properly aware of the presence, position, speed, etc. of the confirmation object, and estimates the driver's degree of awareness of the confirmation object to be "high."

[0094] If the number of confirmations for the confirmation target is less than the first confirmation count and is equal to or greater than the second confirmation count set smaller than the first confirmation count, or if the confirmation time for the confirmation target is less than the first confirmation time and is equal to or greater than the second confirmation time set shorter than the first confirmation time, the cognitive state estimation map generation unit 6252 estimates that the driver recognizes the existence of the confirmation target but may not be able to properly recognize its position, speed, etc., and estimates the driver's degree of awareness of the confirmation target to be "medium".

[0095] In addition, if the number of times the confirmation target is confirmed is less than the second confirmation number or the confirmation time for the confirmation target is less than the second confirmation time, the cognitive state estimation map generation unit 6252 estimates that the driver may not be aware of the existence of the confirmation target, and estimates the driver's degree of recognition of the confirmation target to be "low".

[0096] Next, the cognitive state estimation map generating unit 6252 generates a cognitive state estimation map by correcting the risk map based on the driver's degree of recognition estimated for each confirmation object. More specifically, the cognitive state estimation map generating unit 6252 generates the cognitive state estimation map by eliminating the presence of any of the multiple high-risk areas included in the risk map that correspond to confirmation objects estimated to have a "low" degree of recognition.

[0097] Fig. 8A is a diagram showing an example of a cognitive state estimation map for a driver to be predicted in the example shown in Fig. 5, in which the first traffic participant 91 is the prediction target, the recognition degree of the third traffic participant 93 by the driver to be predicted is set to "high", and the recognition degree of the second traffic participant 92 is set to "low". As is clear from a comparison of the cognitive state estimation map shown in Fig. 8A with the reference risk map shown in Fig. 6, the driver to be predicted cannot recognize the existence of the second traffic participant 92, and therefore the cognitive state estimation map (see Fig. 8A) for the driver to be predicted does not include the high risk area 98 shown in Fig. 6.

[0098] In addition, the cognitive state estimation map generation unit 6252 generates a cognitive state estimation map by changing the position of one of the multiple high-risk areas included in the risk map that corresponds to a confirmation target whose degree of awareness is estimated to be ``medium'' to the far side from the predicted target.

[0099] FIG. 8B is a diagram showing an example of a cognitive state estimation map for a driver of a prediction target in the example shown in FIG. 5, in which the first traffic participant 91 is a prediction target, the recognition degree of the third traffic participant 93 by the driver of the prediction target is set to "high", and the recognition degree of the second traffic participant 92 is set to "medium". As is clear from a comparison of the cognitive state estimation map shown in FIG. 8B with the risk map shown in FIG. 6, the position of the high-risk area 98 in the cognitive state estimation map of FIG. 8B is corrected to a later position along the time axis than the position of the high-risk area 98 in the risk map of FIG. 6. That is, it is considered that the driver of the prediction target recognizes the existence of the second traffic participant 92, but erroneously recognizes its position as being farther away than its actual position. For this reason, the cognitive state estimation map generating unit 6252 corrects the position of the high-risk area 98 to a later position along the time axis than the risk map of FIG. 6.

[0100] Furthermore, the cognitive state estimation map generating unit 6252 generates the cognitive state estimation map without making corrections for the multiple high risk areas included in the risk map that correspond to the confirmation target whose recognition level is estimated to be "high." That is, in the example shown in Fig. 5, when the first traffic participant 91 is the prediction target and the recognition levels of the second traffic participant 92 and the third traffic participant 93 by the driver of the prediction target are both "high," the cognitive state estimation map for the driver of the prediction target is equal to the risk map shown in Fig. 6.

[0101] 4, the movement speed profile calculation unit 6253 calculates a second predicted movement speed profile up to the predicted time of the prediction target based on the cognitive state estimation map for the driver of the prediction target generated by the cognitive state estimation map generation unit 6252 according to the above-mentioned procedure. More specifically, the movement speed profile calculation unit 6253 calculates the second predicted movement speed profile by assuming that the driver of the prediction target moves the prediction target at a constant acceleration / deceleration from the current speed and then shifts to a constant speed in order to avoid a risk estimated based on the cognitive state estimation map.

[0102] More specifically, the moving speed profile calculation unit 6253 calculates a moving speed profile from the current time to a predetermined time ahead as a second predicted moving speed profile so that the evaluation value shown in the following formula (1) is maximized. In the following formula (1), the "maximum risk value" is the maximum value of the collision risk value calculated by searching the cognitive state estimation map based on the moving speed profile. In the following formula (1), the "moving time" is the time from the current time to a constant speed in the moving speed profile. Also, in the following formula (1), the "acceleration / deceleration" is the absolute value of the acceleration of the predicted target from the current time to a constant speed in the moving speed profile. Also, in the following formula (1), "a" and "b" are positive coefficients. Evaluation value = 1 / (maximum risk value + a × travel time + b × acceleration / deceleration) (1)

[0103] Since the driver of the prediction target tries to avoid the risk he / she recognizes as much as possible, the evaluation value becomes larger as the collision risk value calculated based on the cognitive state estimation map becomes smaller, as shown in the above formula (1). Since the driver of the prediction target tends to avoid the risk with the smallest possible acceleration / deceleration, the evaluation value becomes larger as the acceleration / deceleration becomes smaller, as shown in the above formula (1). Furthermore, since the driver of the prediction target tends to avoid the risk as quickly as possible, the evaluation value becomes larger as the movement time until the speed changes to a constant speed becomes shorter, as shown in the above formula (1). Therefore, the movement speed profile calculation unit 6253 calculates the second predicted movement speed profile so that the collision risk value calculated based on the cognitive state estimation map and the acceleration / deceleration of the prediction target are both small and the movement time until the speed changes to a constant speed becomes short.

[0104] A specific example of the evaluation value will now be described with reference to the cognitive state estimation map shown in FIG. 6. In FIG. 6, the maximum risk values ​​calculated under the moving speed profiles shown by the dashed lines 99a and 99b are both greater than the maximum risk values ​​calculated under the moving speed profiles shown by the dashed lines 99c and 99d. The acceleration / deceleration in the moving speed profile shown by the dashed line 99a is greater than the acceleration / deceleration in the moving speed profile shown by the dashed line 99b. The acceleration / deceleration in the moving speed profile shown by the dashed line 99d is greater than the acceleration / deceleration in the moving speed profile shown by the dashed line 99c. Therefore, in the example shown in FIG. 6, the evaluation values ​​increase in the order of the dashed lines 99a, 99b, 99d, and 99c. Therefore, when the cognitive state estimation map is equal to the risk map shown in Figure 6, i.e., when the driver of the first traffic participant 91, which is the prediction target, properly recognizes the second traffic participant 92 and the third traffic participant 93 present in the vicinity, the movement speed profile calculation unit 6253 calculates the movement speed profile indicated by the dashed line 99c, which has the maximum evaluation value, as the second predicted movement speed profile.

[0105] In addition, when the cognitive state estimation map is equal to the cognitive state estimation map shown in Figure 8A, that is, when the driver of the first traffic participant 91, which is the prediction target, is unable to recognize the presence of the second traffic participant 92, the movement speed profile calculation unit 6253 calculates the movement speed profile shown by the dashed line 99e as the second predicted movement speed profile that maximizes the evaluation value.

[0106] In addition, when the cognitive state estimation map is equal to the cognitive state estimation map shown in Figure 8B, that is, when the driver of the first traffic participant 91, which is the prediction target, is unable to properly recognize the position and speed of the second traffic participant 92, the movement speed profile calculation unit 6253 calculates the movement speed profile indicated by the dashed line 99f as the second predicted movement speed profile that maximizes the evaluation value.

[0107] The second moving state prediction unit 625 predicts the second predicted moving state of the prediction target based on an algorithm different from that used by the first moving state prediction unit 624 through the above-mentioned procedure.

[0108] Returning to Figure 3, the collision risk calculation unit 626 calculates a first collision risk value indicating the collision risk between the predicted object and surrounding traffic participants in the first predicted movement state and a second collision risk value indicating the collision risk between the predicted object and surrounding traffic participants in the second predicted movement state based on the movement state information, the surrounding state information, and the traffic environment information.

[0109] More specifically, the collision risk calculation unit 626 obtains a risk map for the prediction target generated by the above-mentioned risk map generation unit 6251, calculates a first collision risk value by searching the risk map based on the first predicted movement speed profile calculated by the first movement state prediction unit 624, and calculates a second collision risk value by searching the risk map based on the second predicted movement speed profile calculated by the second movement state prediction unit 625.

[0110] If at least one of the first collision risk value and the second collision risk value calculated by the collision risk calculation unit 626 is greater than a predetermined collision determination threshold, the support behavior decision unit 627 decides that the predicted target is highly likely to collide with the surrounding traffic participant between the present and the predicted time ahead, and decides a support behavior for avoiding a collision between the predicted target and the surrounding traffic participant or reducing damage caused by the collision. If both the first collision risk value and the second collision risk value are equal to or less than the collision determination threshold, the support behavior decision unit 627 decides that the predicted target is unlikely to collide with the surrounding traffic participant, and does not decide on a support behavior.

[0111] More specifically, when the first collision risk value is equal to or less than the collision judgment threshold and the second collision risk value is greater than the collision judgment threshold, the support behavior decision unit 627 decides that the first avoidance behavior that realizes the first predicted moving state of the predicted target, i.e., acceleration / deceleration behavior in accordance with the first predicted moving speed profile, is the support behavior.

[0112] When the second collision risk value is less than or equal to the collision judgment threshold and the first collision risk value is greater than the collision judgment threshold, the support behavior decision unit 627 decides that the second avoidance behavior that realizes the second predicted moving state of the predicted target, i.e., acceleration / deceleration behavior in accordance with the second predicted moving speed profile, is the support behavior.

[0113] Furthermore, when both the first collision risk value and the second collision risk value are greater than the collision determination threshold, the support behavior determination unit 627 calculates a collision avoidance behavior for avoiding a collision between the prediction target and the surrounding traffic participants, and determines this collision avoidance behavior as the support behavior. At this time, when the support behavior determination unit 627 cannot calculate a feasible collision avoidance behavior, it calculates a collision damage mitigation behavior for reducing damage caused by the collision between the prediction target and the surrounding traffic participants as much as possible, and determines this collision damage mitigation behavior as the support behavior. For example, the support behavior determination unit 627 calculates a moving speed profile that characterizes the collision avoidance behavior or the collision damage mitigation behavior based on the risk map generated by the risk map generation unit 6251.

[0114] Here, a procedure for determining a support action by the support action determination unit 627 will be described with reference to the risk map in FIG. 6 as an example. In the following, a case will be described in which the dashed line 99g in FIG. 6 is the first predicted moving speed profile, and the dashed line 99e in FIG. 6 is the second predicted moving speed profile. As shown in FIG. 6, the second predicted moving speed profile indicated by the dashed line 99e crosses the center of the high risk area 98, and the first predicted moving speed profile indicated by the dashed line 99g crosses the foot of the high risk areas 97, 98. Therefore, the second collision risk value obtained by searching the risk map in FIG. 6 based on the second predicted moving speed profile is greater than the first collision risk value obtained by searching the risk map in FIG. 6 based on the first predicted moving speed profile. In addition, both the first collision risk value and the second collision risk value are greater than the collision determination threshold. In this case, the support action determination unit 627 calculates an acceleration / deceleration action along the moving speed profile indicated by the dashed line 99c in FIG. 6 as a collision avoidance action, and determines this collision avoidance action as a support action.

[0115] Returning to Figure 2, when the prediction unit 62 determines that the predicted object is highly likely to collide with a surrounding traffic participant, if at least one of the first collision risk value and the second collision risk value is greater than a collision judgment threshold, the assistance control unit 65 executes assistance control for the predicted object so that the predicted object performs the assistance action determined by the assistance action determination unit 627.

[0116] As described above, the in-vehicle device group 20, 30 communicably connected to the traffic management server 6 includes the in-vehicle notification device 22, 32 that operates the HMI in a manner determined based on the cooperative support information transmitted from the assistance control unit 65, and the in-vehicle driving assistance device 21, 31 that automatically controls the behavior of the vehicle body in a manner determined based on the cooperative support information. In other words, the assistance control unit 65 can activate the in-vehicle notification device 22, 32 or the in-vehicle driving assistance device 21, 31 by transmitting cooperative support information determined based on the assistance behavior to the in-vehicle device group 20, 30 of the prediction target, thereby encouraging the prediction target to perform the assistance behavior. Therefore, when at least one of the first collision risk value and the second collision risk value is greater than the collision determination threshold, the assistance control unit 65 executes both or either of the notification control that encourages the assistance behavior by activating the in-vehicle notification device 22, 32 of the prediction target and the automatic behavior control that encourages the assistance behavior by activating the in-vehicle driving assistance device 21, 31 of the prediction target as the assistance control.

[0117] When performing notification control, the assistance control unit 65 transmits collaborative assistance information, including information on the assistance action decided by the assistance action decision unit 627 and information on the risk map for the predicted target, to the group of in-vehicle devices 20, 30 of the predicted target, and by activating the in-vehicle notification devices 22, 32 based on this collaborative assistance information, notifies the driver of the predicted target of information for avoiding a collision of the predicted target or reducing damage caused by the collision (for example, audio or images encouraging acceleration or deceleration in accordance with the assistance action), and encourages the driver of the predicted target to perform driving operations in accordance with the assistance action.

[0118] Fig. 9 is a diagram showing an example of an image displayed on the in-vehicle notification device 22, 32 based on the notification control by the assistance control unit 65. More specifically, Fig. 9 shows an example of an image display when an acceleration / deceleration action along the moving speed profile shown by the dashed line 99c in the risk map shown in Fig. 6 is determined as the assistance action.

[0119] As shown in FIG. 9, the assistance control unit 65 may display an image generated by plotting a circle 100 indicating the current speed and a moving speed profile 101 according to the assistance action on a risk map on the in-vehicle notification device 22, 32. In addition, in this case, the assistance control unit 65 may display an area on the risk map where the collision risk value is greater than the collision determination threshold (i.e., the high-risk areas 97, 98 in FIG. 6) in red, for example, as shown by areas 102, 103 in FIG. 9, so that the driver who sees the image can quickly recognize the high-risk area. In addition, although not shown, the in-vehicle notification device 22, 32 may display an icon to call attention in a portion corresponding to the high-risk area on the map image displayed by the navigation device. By viewing such an image, the driver who is the target of prediction can recognize the existence of a collision risk with surrounding traffic participants and the procedure of driving operations to avoid or reduce the collision risk.

[0120] Furthermore, when performing automatic behavior control, the assistance control unit 65 transmits cooperative assistance information including information on the assistance action determined by the assistance action determination unit 627 to the in-vehicle device group 20, 30 of the prediction target, and operates the in-vehicle driving assistance devices 21, 31 based on the cooperative assistance information. More specifically, the assistance control unit 65 operates the in-vehicle driving assistance devices 21, 31 to perform the assistance action determined to avoid the predicted collision or reduce damage caused by the collision.

[0121] Fig. 10 is a flowchart showing the specific steps of a traffic safety support process for supporting safe traffic of traffic participants in a traffic target area by the traffic management server 6. Each step shown in the flowchart in Fig. 10 is realized by the traffic management server 6 executing a computer program stored in a storage medium (not shown).

[0122] First, in step ST1, the traffic management server 6 determines a monitoring area from the target traffic area, and then proceeds to step ST2. In step ST2, the traffic management server 6 recognizes multiple traffic participants present in the monitoring area, and further determines a prediction target from among the multiple traffic participants, and then proceeds to step ST3.

[0123] In step ST3, the traffic management server 6 acquires moving state information of the prediction target, and proceeds to step ST4. In step ST4, the traffic management server 6 acquires surrounding state information of surrounding traffic participants existing around the prediction target in the monitoring area, and proceeds to step ST5. In step ST5, the traffic management server 6 acquires traffic environment information around the prediction target in the monitoring area, and proceeds to step ST6. In step ST6, the traffic management server 6 acquires driver state information regarding the surrounding confirmation state by the driver of the prediction target, and proceeds to step ST7.

[0124] In step ST7, the traffic management server 6 predicts a first predicted moving state of the prediction target based on the moving state information, surrounding state information, and traffic environment information, and proceeds to step ST8. In step ST8, the traffic management server 6 predicts a second predicted moving state of the prediction target based on the moving state information, surrounding state information, traffic environment information, and driver state information, and proceeds to step ST9. As described above, in this step ST8, the traffic management server 6 generates a risk map for the prediction target based on the moving state information, surrounding state information, and traffic environment information, generates a cognitive state estimation map by correcting the risk map based on the driver state information, and further predicts the second predicted moving state of the prediction target based on this cognitive state estimation map.

[0125] In step ST9, the traffic management server 6 uses a risk map for the predicted object to calculate a first collision risk value between the predicted object and surrounding traffic participants in the first predicted movement state and a second collision risk value between the predicted object and surrounding traffic participants in the second predicted movement state, and proceeds to step ST10.

[0126] In step ST10, the traffic management server 6 determines whether or not at least one of the first collision risk value and the second collision risk value is greater than the collision determination threshold value. If the result of the determination in step ST10 is NO, the traffic management server 6 returns to step ST1, and if the result is YES, the traffic management server 6 proceeds to step ST11.

[0127] In step ST11, the traffic management server 6 determines a support action for the prediction target, and proceeds to step ST12. In step ST12, the traffic management server 6 executes both or either of the notification control for activating the in-vehicle notification device 22, 32 of the prediction target so that the prediction target performs the support action and the automatic behavior control for activating the in-vehicle driving support device 21, 31 of the prediction target so that the prediction target performs the support action as the support control, and returns to step ST1.

[0128] <Second embodiment> Next, a traffic safety support system according to a second embodiment of the present invention will be described with reference to the drawings. The traffic safety support system according to this embodiment differs from the traffic safety support system 1 according to the first embodiment in the configuration of the prediction unit of the traffic management server. In the following description of the traffic safety support system according to this embodiment, the same components as those in the traffic safety support system 1 according to the first embodiment are given the same reference numerals, and detailed description will be omitted.

[0129] Fig. 11 is a functional block diagram showing a specific configuration of the prediction unit 62A according to this embodiment. As shown in Fig. 11, the prediction unit 62A according to this embodiment differs from the prediction unit 62 according to the first embodiment shown in Fig. 3 in the configurations of a driver state information acquisition unit 623A, a first movement state prediction unit 624A, a second movement state prediction unit 625A, and a collision risk calculation unit 626A.

[0130] The driver state information acquisition unit 623A acquires driver state information on the state of the driver to be predicted based on the driver subject state information transmitted from the driver subject information acquisition unit 61. In this embodiment, the driver state information is information that is correlated with the driver's driving ability at that time, and more specifically, is information that reflects the driver's emotional state and physical condition at that time. In this embodiment, a case will be described in which the driver state information is an impatience parameter value that quantifies the intensity of the driver's impatience, but the present invention is not limited to this. In this embodiment, a case will be described in which the impatience parameter value can take three values: a value 0 indicating a normal state, a value 1 indicating a slightly impatient state, and a value 2 indicating a strongly impatient state, but the present invention is not limited to this.

[0131] As described above, the driver subject information acquired by the driver subject information acquisition unit 61 includes time-dependent data such as facial image data and biological information of the driver to be predicted, the driver's schedule information, etc. The driver state information acquisition unit 623A calculates an impatience parameter value indicating the driver's current level of impatience based on the time-dependent data such as facial image data and biological information, the schedule information, etc.

[0132] The first moving state prediction unit 624A predicts a first predicted moving state, which is a moving state of the prediction target in the monitoring area until a predetermined predicted time ahead, based on the moving state information, the surrounding state information, and the traffic environment information. In other words, the first moving state prediction unit 624A calculates a predicted moving path from the present to the predicted time ahead of the prediction target (hereinafter, the predicted moving path calculated by the first moving state prediction unit 624A is also referred to as a "first predicted moving path") and a moving speed profile (hereinafter, the moving speed profile calculated by the first moving state prediction unit 624A is also referred to as a "first predicted moving speed profile") as parameters that characterize the first predicted moving state of the prediction target until the predicted time ahead. Note that the procedure for predicting the first predicted moving state by the first moving state prediction unit 624A is the same as the procedure for predicting the first predicted moving state by the first moving state prediction unit 624 according to the first embodiment, and therefore a detailed description thereof will be omitted.

[0133] The second moving state prediction unit 625A predicts a second predicted moving state, which is a moving state of the prediction target in the monitoring area until the predicted time ahead, based on the moving state information, surrounding state information, traffic environment information, and driver state information. In other words, the second moving state prediction unit 625A calculates a predicted moving route and moving speed profile of the prediction target from the present to the predicted time ahead as a second predicted moving route and a second predicted moving speed profile, as parameters that characterize the second predicted moving state of the prediction target until the predicted time ahead. Hereinafter, a specific procedure for calculating the second predicted moving route and the second predicted moving speed profile of the prediction target in the second moving state prediction unit 625A will be described with reference to Figs. 12 and 13.

[0134] 12 is a functional block diagram showing a specific configuration of the second moving state prediction unit 625A. The second moving state prediction unit 625A includes a traffic scene identification unit 6255, a behavior pattern selection unit 6256, and a behavior prediction unit 6257, and calculates a second predicted moving route and a second predicted moving speed profile of the prediction target by using these.

[0135] The traffic scene identification unit 6255 identifies a traffic scene to be predicted in the monitoring area based on the moving state information, the surrounding state information, and the traffic environment information. More specifically, the traffic scene identification unit 6255 identifies a traffic scene to be predicted by determining values ​​of a plurality of traffic scene parameters that characterize the traffic scene to be predicted based on the moving state information, the surrounding state information, and the traffic environment information.

[0136] Here, the traffic scene parameters include, for example, the number of lanes on the road currently being traveled, the type of lane, the width of the lane, the position of the lane on which the prediction target is located, the legal speed limit of the road currently being traveled, the speed range of the prediction target, the presence or absence of a vehicle ahead of the prediction target, the speed range of this vehicle ahead, the distance between this vehicle ahead and the prediction target, the vehicle class of this vehicle ahead, the presence or absence of a following vehicle behind the prediction target, the speed range of this following vehicle, the distance between this following vehicle and the prediction target, the vehicle class of this following vehicle, the presence or absence of a vehicle running alongside on the right of the prediction target, the speed range of this vehicle ahead, the distance between this vehicle ahead and the prediction target, the vehicle class of this vehicle ahead, the presence or absence of a vehicle running alongside on the left of the prediction target, the speed range of this vehicle ahead, the distance between this vehicle ahead and the prediction target, the vehicle class of this vehicle ahead, the presence or absence of a traffic light ahead of the prediction target, the color of the traffic light, and the distance to the traffic light.

[0137] The behavior pattern selection unit 6256 selects at least one from a plurality of predetermined behavior patterns as a predicted behavior pattern based on the driver state information acquired by the driver state information acquisition unit 623A and the traffic scene identified by the traffic scene identification unit 6255. Here, the behavior pattern selection unit 6256 predetermines a number of behavior patterns, including a constant speed behavior for maintaining the current speed, a deceleration behavior for reducing the speed from the current speed, a stopping behavior for stopping the predicted target, an accelerating behavior for increasing the speed from the current speed, a vehicle-following behavior for following a vehicle in front, a left-hand vehicle-following behavior for following a vehicle in front on the left, a right-hand vehicle-following behavior for following a vehicle in front on the right, a right-hand lane-changing behavior for changing the driving lane to the right lane, a left-hand lane-changing behavior for changing the driving lane to the left lane, a right-hand cutting-in behavior for cutting in between the vehicle in front and the vehicle in front on the right, a left-hand cutting-in behavior for cutting in between the vehicle in front and the vehicle in front on the left, a right-hand overtaking behavior for overtaking the vehicle in front from the right, a left-hand overtaking behavior for overtaking the vehicle in front from the left, and combinations of these actions.

[0138] The behavior pattern selection unit 6256, for example, selects at least one of the multiple behavior patterns as a predicted behavior pattern by using a behavior pattern prediction model that outputs at least one behavior pattern from the multiple behavior patterns when inputting input data generated based on driver state information and traffic scenes for the prediction target. The behavior pattern prediction model associates the driver state information and traffic scenes for the prediction target with a predicted behavior pattern that is likely to be taken by the prediction target in the near future. That is, the behavior pattern selection unit 6256 sets the output of the behavior pattern prediction model when input data generated based on the driver state information and traffic scenes is input to the behavior pattern prediction model as a predicted behavior pattern. Here, the behavior pattern selection unit 6256 uses a DNN (Deep Neural Network) constructed for each prediction target by machine learning using data obtained from the prediction target as the behavior pattern prediction model.

[0139] Such a behavior pattern prediction model uses a DNN constructed by repeatedly executing a learning method described below for each prediction target. This learning method includes a step of generating input data for the behavior pattern prediction model based on traffic scene and driver state information acquired in a predetermined first period, a step of generating correct answer data for the output of the behavior pattern prediction model based on movement state information acquired in a second period immediately following the first period, and a step of learning the behavior pattern prediction model using learning data that combines the input data and the correct answer data.

[0140] As described above, in this embodiment, the behavior pattern selection unit 6256 selects a predicted behavior pattern by using a behavior pattern prediction model, but the present invention is not limited to this. The behavior pattern selection unit 6256 may select at least one predicted behavior pattern from among multiple behavior patterns by using a table that associates driver state information and traffic scenes for a prediction target with predicted behavior patterns that are likely to be taken by the prediction target in the near future.

[0141] Here, a specific procedure for the behavior pattern selection unit 6256 to select a predicted behavior pattern from among a plurality of behavior patterns will be described with reference to FIG.

[0142] Fig. 13 is a diagram showing an example of a monitoring area 80. Fig. 13 shows a case where three four-wheeled vehicles, namely traffic participants 81, 82, and 83, are traveling in the monitoring area 80, which is a straight road with two lanes in each direction. In the following, a case will be described in which the behavior pattern selection unit 6256 selects the first traffic participant 81, among these traffic participants 81 to 83, as a prediction target, and selects a predicted behavior pattern of the prediction target from among a plurality of behavior patterns.

[0143] As shown in Fig. 13, at the time when the behavior pattern selection unit 6256 selects the predicted behavior pattern of the prediction target, the third traffic participant 83 and the first traffic participant 81 are traveling in the right lane from the front with a certain distance between them, and the second traffic participant 82 is traveling in the left lane slightly ahead of the first traffic participant 81 and slightly behind the third traffic participant 83. Therefore, the third traffic participant 83 is a vehicle traveling ahead from the perspective of the prediction target, and the second traffic participant 82 is a vehicle traveling parallel to the left from the perspective of the prediction target. The above-mentioned traffic scene identification unit 6255 identifies the traffic scene in which the prediction target is located, such as the number of lanes of the road on which the prediction target is traveling and the presence or absence of a vehicle traveling ahead, by determining the values ​​of multiple traffic scene parameters.

[0144] The behavior pattern selection unit 6256 defines a plurality of behavior patterns that the first traffic participant 81, which is the prediction target, may take from the state shown in Fig. 13 until a predetermined time ahead. For example, the dashed arrow 12a is a movement route of the prediction target associated with "behavior of following the vehicle ahead", the dashed arrow 12b is a movement route of the prediction target associated with "behavior of following the vehicle running parallel on the left", the dashed arrow 12c is a movement route of the prediction target associated with "behavior of decelerating", the dashed arrow 12d is a movement route of the prediction target associated with "behavior of cutting in on the left", and the dashed arrow 12e is a movement route of the prediction target associated with "behavior of overtaking on the left".

[0145] The behavior pattern selection unit 6256 selects at least one of a plurality of predetermined behavior patterns as shown in FIG. 13 as a predicted behavior pattern based on the traffic scene (i.e., the value of the traffic scene parameter) identified by the traffic scene identification unit 6255 and the driver state information (i.e., the impatience parameter value) acquired by the driver state information acquisition unit 623A. More specifically, in a traffic scene as shown in FIG. 13, when the impatience parameter value for the driver of the prediction target is 0, the behavior pattern selection unit 6256 selects the "deceleration behavior" associated with the dashed arrow 12c as a predicted behavior pattern. In contrast, in a traffic scene as shown in FIG. 13, when the impatience parameter value for the driver of the prediction target is 2, the behavior pattern selection unit 6256 selects the "left-hand cut-in behavior" associated with the dashed arrow 12d as a predicted behavior pattern. The behavior pattern selection unit 6256 selects a predicted behavior pattern according to the state of the driver of the prediction target at that time by utilizing a behavior pattern prediction model constructed based on data previously acquired from the prediction target.

[0146] Returning to FIG. 12, the behavior prediction unit 6257 calculates a second predicted movement route and a second predicted movement speed profile from the current time to the predicted time ahead of the predicted target in the monitoring area based on the movement state information, the surrounding state information, the traffic environment information, and the predicted behavior pattern selected by the behavior pattern selection unit 6256, etc.

[0147] Returning to Figure 11, the collision risk calculation unit 626A calculates a first collision risk value indicating the collision risk between the predicted object and surrounding traffic participants in the first predicted movement state and a second collision risk value indicating the collision risk between the predicted object and surrounding traffic participants in the second predicted movement state based on the movement state information, surrounding state information, and traffic environment information.

[0148] More specifically, the collision risk calculation unit 626A generates a first risk map according to the first predicted movement route calculated by the first movement state prediction unit 624A and a second risk map according to the second predicted movement route calculated by the second movement state prediction unit 625A by the same procedure as that of the risk map generation unit 6251 according to the first embodiment. In addition, the collision risk calculation unit 626A calculates a first collision risk value by searching the first risk map based on the first predicted movement speed profile calculated by the first movement state prediction unit 624A, and calculates a second collision risk value by searching the second risk map based on the second predicted movement speed profile calculated by the second movement state prediction unit 625A.

[0149] Fig. 14 is a flowchart showing the specific steps of a traffic safety support process in which a traffic management server supports safe traffic for traffic participants in a traffic target area. Each step shown in the flowchart of Fig. 14 is realized by the traffic management server executing a computer program stored in a storage medium (not shown). Note that the processes of steps ST21 to ST27 and ST30 to ST32 in the flowchart shown in Fig. 14 are the same as the processes of steps ST1 to ST7 and ST10 to ST12 in the flowchart shown in Fig. 10, and therefore detailed explanations will be omitted.

[0150] In step ST28, the traffic management server predicts a second predicted moving state of the prediction target based on the moving state information, surrounding state information, traffic environment information, and driver state information, and proceeds to step ST29. As described above, in this step ST28, the traffic management server identifies a traffic scene of the prediction target based on the moving state information, surrounding state information, and traffic environment information, and then selects at least one of a plurality of predetermined behavior patterns as a predicted behavior pattern based on the driver state information and the identified traffic scene. The traffic management server also predicts a second predicted moving state of the prediction target based on the selected predicted behavior pattern.

[0151] In step ST29, the traffic management server calculates a first collision risk value between the predicted object and the surrounding traffic participants in the first predicted movement state and a second collision risk value between the predicted object and the surrounding traffic participants in the second predicted movement state by using a first risk map corresponding to the first predicted movement route and a second risk map corresponding to the second predicted movement route, and then proceeds to step ST30.

[0152] Although the first and second embodiments of the present invention have been described above, the present invention is not limited thereto. Within the scope of the present invention, the detailed configuration may be appropriately changed. For example, in the above embodiment, a prediction unit that predicts the future in a monitoring area of ​​a prediction target, which is a moving object, is provided in a traffic management server that is communicatively connected to the prediction target, but the present invention is not limited thereto. The prediction unit may be configured by a group of in-vehicle devices that move together with the support target. In this case, although the amount of information such as moving state information, surrounding state information, and traffic environment information that can be acquired by the prediction unit is less than the amount of information that can be acquired by the traffic management server, there is an advantage in that the delay due to communication is small. [Explanation of symbols]

[0153] 1. Traffic safety support system 2…Four-wheeled vehicle (mobile object, transportation participant) 20…In-vehicle equipment group 21...In-vehicle driving assistance device 22…In-vehicle notification device 3…Motorcycles (moving objects, traffic participants) 30…In-vehicle equipment group 31...In-vehicle driving assistance device 32…In-vehicle notification device 6…Traffic management server 60…Target traffic area recognition unit 61...Driver information acquisition unit 62,62A…Prediction unit 620...Moving state information acquisition unit 621... Surrounding state information acquisition unit 622…Traffic environment information acquisition department 623, 623A…Driver status information acquisition unit 624, 624A…First moving state prediction unit 625, 625A…Second moving state prediction unit 6251…Risk map generation section 6252…Cognitive state estimation map generation unit 6253...Movement speed profile calculation unit 6255…Traffic Scene Specific Section 6256…Behavior pattern selection section 6257…Behavioral Prediction Department 626, 626A…Collision risk calculation section 627…Support Action Decision-Making Department 65...Assistance control unit (assistance control section) 9. Target traffic area 90…Surveillance area 91…1st transportation participant 92…Second transportation participant 93…Third transportation participant

Claims

1. A traffic safety support system that supports safe traffic in a traffic area, the traffic area being a prediction target, the traffic safety support system comprising: a movement state information acquisition unit that acquires movement state information related to the movement state of the prediction target; a surrounding state information acquisition unit that acquires surrounding state information regarding the movement states of surrounding traffic participants existing around the prediction target in the traffic area; a driver state information acquisition unit that acquires driver state information regarding a state of the driver of the prediction target; a first movement state prediction unit that predicts a first predicted movement state including a first predicted movement speed profile along a predicted movement route of the prediction target up to a predicted time ahead based on the movement state information and the surrounding state information; a second moving state prediction unit that predicts a second predicted moving state including a second predicted moving speed profile along the predicted moving route of the prediction target up to the predicted time ahead based on the moving state information, the surrounding state information, and the driver state information by an algorithm different from that of the first moving state prediction unit; a collision risk calculation unit that calculates a first collision risk value between the prediction object and the surrounding traffic participants in the first predicted movement state and a second collision risk value between the prediction object and the surrounding traffic participants in the second predicted movement state based on the surrounding state information; and an assistance control unit that executes assistance control for the predicted object when at least one of the first collision risk value and the second collision risk value is greater than a predetermined threshold.

2. The support control unit is When the first collision risk value is equal to or less than the threshold value and the second collision risk value is greater than the threshold value, the assistance control is executed so that the predicted object performs a first avoidance action that realizes the first predicted moving state; When the second collision risk value is equal to or less than the threshold value and the first collision risk value is greater than the threshold value, the assistance control is executed so that the predicted object performs a second avoidance action that realizes the second predicted moving state; The traffic safety support system described in claim 1, characterized in that when the first collision risk value and the second collision risk value are both greater than the threshold value, the support control is executed so that the predicted object takes a collision avoidance action to avoid a collision with the surrounding traffic participant or a collision damage mitigation action to reduce damage caused by the collision.

3. The collision risk calculation unit calculating the first collision risk value by searching a risk map that associates a moving speed of the prediction object with a future collision risk value of the prediction object based on the first predicted moving speed profile; 3. The traffic safety support system according to claim 2, wherein the second collision risk value is calculated by searching the risk map based on the second predicted travel speed profile.

4. A group of in-vehicle devices moving together with the prediction target; A traffic management server capable of communicating with the vehicle-mounted device group, the traffic management server includes the movement state information acquisition unit, the surrounding state information acquisition unit, the driver state information acquisition unit, the first movement state prediction unit, the second movement state prediction unit, the collision risk calculation unit, and the assistance control unit; The in-vehicle device group includes an in-vehicle notification device that notifies the driver of information by at least one of an image and a sound, The traffic safety support system according to claim 3, characterized in that the support control unit executes notification control as the support control, which notifies the driver of information for avoiding the predicted collision or reducing damage caused by the collision by activating the in-vehicle notification device.

5. The traffic safety support system according to claim 4, characterized in that, in the notification control, the support control unit notifies the driver of information encouraging acceleration or deceleration in accordance with the first avoidance action, the second avoidance action, the collision avoidance action, or the collision damage mitigation action.

6. The traffic safety support system of claim 5, characterized in that, in the notification control, the support control unit displays on the in-vehicle notification device an image generated by plotting a moving speed profile corresponding to the first avoidance action, the second avoidance action, the collision avoidance action, or the collision damage mitigation action on the risk map.

7. The traffic safety support system according to claim 6, characterized in that the support control unit highlights areas on the risk map where the collision risk value is greater than the threshold value and displays the areas on the in-vehicle notification device.

8. The driver state information acquisition unit acquires information regarding a surrounding confirmation state of the driver as the driver state information, The traffic safety support system according to claim 1 , wherein the second moving state prediction unit predicts the second predicted moving state based on the moving state information, the surrounding state information, and the driver state information.

9. A traffic environment information acquisition unit that acquires traffic environment information around the prediction target in the traffic area, The second moving state prediction unit is a traffic scene identification unit that identifies the traffic scene to be predicted based on the moving state information, the surrounding state information, and the traffic environment information; a behavior pattern selection unit that selects at least one of a plurality of predetermined behavior patterns as a predicted behavior pattern based on the traffic scene and the driver state information; The traffic safety support system according to claim 1 , further comprising: a behavior prediction unit that predicts the second predicted moving state based on the predicted behavior pattern.

10. A group of in-vehicle devices moving together with the prediction target; A traffic management server capable of communicating with the vehicle-mounted device group, the traffic management server includes the movement state information acquisition unit, the surrounding state information acquisition unit, the driver state information acquisition unit, the first movement state prediction unit, the second movement state prediction unit, the collision risk calculation unit, and the assistance control unit; The in-vehicle device group includes an in-vehicle driving assistance device that automatically controls the behavior of the prediction target, The traffic safety support system according to claim 1, characterized in that the support control unit executes automatic behavior control as the support control, which operates the in-vehicle driving support device so as to avoid the predicted collision or reduce damage caused by the collision.

11. A computer that predicts a future state of a mobile object moving within a traffic area as a prediction target in the traffic area, acquiring movement state information regarding the movement state of the prediction target; acquiring surrounding state information regarding the movement states of surrounding traffic participants existing around the prediction target in the traffic area; acquiring driver state information regarding a state of the driver to be predicted; predicting a first predicted moving state including a first predicted moving speed profile along a predicted moving route of the prediction target up to a predicted time ahead based on the moving state information and the surrounding state information; predicting a second predicted moving state including a second predicted moving speed profile along the predicted moving route of the prediction target up to the predicted time ahead based on the moving state information, the surrounding state information, and the driver state information by an algorithm different from the algorithm predicting the first predicted moving state; calculating a first collision risk value between the predicted object and the surrounding traffic participants in the first predicted moving state and a second collision risk value between the predicted object and the surrounding traffic participants in the second predicted moving state based on the surrounding state information; and executing assistance control for the predicted object when at least one of the first collision risk value and the second collision risk value is greater than a predetermined threshold.

Images