Traffic safety support system and traffic safety support method

Abstract

This traffic safety assistance system comprises: a target traffic area recognition unit for acquiring recognition information concerning each of traffic participants; a driving subject information acquisition unit for acquiring driving subject state information correlated to the driving ability of a driving subject of a movement body recognized as a traffic participant; a prediction unit for predicting the future of a plurality of the traffic participants on the basis of the recognition information and the driving subject state information; and a cooperative assistance information notification unit for making notification of cooperative assistance information according to a prediction result. The prediction unit is characterized by: recognizing a motorcycle 3a, a four-wheeled vehicle 2b, and a pedestrian group 4a as first to third traffic participants, respectively; and predicting, on the basis of the recognition information and the driving subject state information, a future behavior of the motorcycle 3a, a future behavior of the four-wheeled vehicle 2b according to the future behavior of the motorcycle 3a, and a chain risk of the pedestrian group 4a in the future according to at least one of the future behaviors of the motorcycle 3a and the four-wheeled vehicle 2b.

Description

[Technical field]

[0001] The present invention relates to a traffic safety support system and a traffic safety support method, and more particularly to a traffic safety support system and a traffic safety support method for supporting the safety of traffic participants as people or moving bodies in a target traffic area. [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 traffic participants in such public transportation, for example, Patent Document 1 discloses a mobile object support system that supports safe travel by mobile objects by predicting the future of traffic participants.

[0003] More specifically, in the mobile object support system shown in Patent Document 1, participant information regarding traffic participants in the vicinity of a first mobile object is acquired, and based on the acquired participant information, a future state of the traffic participants is predicted, and shared map information including the predicted future state of the traffic participants is generated. Based on the generated shared map information, a second mobile object different from the first mobile object is set as a support target that supports dealing with the traffic participants, and information based on the above prediction results is provided to this support target.

[0004] According to such a mobile object support system, for example, when a first moving object, a second moving object, and a pedestrian are present at a common intersection, and the pedestrian can be seen by the first moving object but not by the second moving object, the second moving object set as the support target is provided with future predictions of the pedestrian based on information acquired by the first moving object, thereby making it possible to avoid risks between the second moving object and the pedestrian before they occur. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2020-42553 A Summary of the Invention [Problem to be solved by the invention]

[0006] The mobile object support system shown in Patent Document 1 is effective in avoiding the risk of two parties, that is, in the above example, the second mobile object and the pedestrian, becoming the main parties. However, Patent Document 1 does not fully consider the risk of a chain reaction occurring between three or more traffic participants who become the parties.

[0007] The present invention aims to provide a traffic safety support system and a traffic safety support method that can improve traffic safety, convenience, and smoothness by contributing to avoid the risk of three or more traffic participants becoming involved. [Means for solving the problem]

[0008] (1) A traffic safety support system according to the present invention (for example, a traffic safety support system 1 described later) detects people (for example, a pedestrian 4 and a pedestrian group 4a described later) or moving objects (for example, four-wheeled automobiles 2, 2a, and 2b and motorcycles 3,3a) and acquires recognition information regarding each traffic participant (for example, traffic participant recognition information and traffic environment recognition information described later), and The present invention relates to a driving subject information acquisition means (e.g., a driving subject information acquisition unit 61, a driving subject state sensor 23, an in-vehicle communication device 24, a portable information processing terminal 25, a lidar state sensor 33, an in-vehicle communication device 34, a portable information processing terminal 35, and a driving history database 65) for acquiring state information (e.g., driving subject state information described later) correlated with the driving ability of a driving subject of a moving body being recognized, and a prediction means (e.g., a prediction means for predicting the future of a plurality of traffic participants recognized by the recognition means based on the recognition information and the state information). The present invention is characterized in that the present invention includes a prediction unit 62 described later, a collaborative support information notification unit 63, a driver HMI 22, an in-vehicle communication device 24, a mobile information processing terminal 25, a rider HMI 32, an in-vehicle communication device 34, a mobile information processing terminal 35, and a mobile information processing terminal 40 described later, which notifies support information to at least one of the multiple prediction targets by the prediction means based on the prediction result by the prediction means, and the prediction means predicts the future behavior of the first moving body, the future behavior of the second moving body according to the future behavior of the first moving body, and the future risk of the third traffic participant according to the future behavior of at least one of the first and second moving bodies based on the recognition information and the state information when the first and second traffic participants among the first, second, and third traffic participants that are the prediction targets are first and second moving bodies in the target traffic area and state information of at least one of the first and second moving bodies is acquired by the driving subject information acquisition means.

[0009] (2) In this case, when the prediction means predicts the occurrence of a future risk for the third traffic participant, it is preferable that the notification means notifies the communication interface of the third traffic participant (for example, a mobile information processing terminal of a pedestrian group 4a in Example 1 described below, and an in-vehicle communication device of a second four-wheeled vehicle 2b in Example 2 described below) of the assistance information.

[0010] (3) In this case, when the driving subject is a human, it is preferable that the driving subject information acquisition means acquires the status information based on time-lapse data during driving of at least any of the driving subject's biometric information, appearance information, and voice information.

[0011] (4) In this case, when the driving entity is a human, the driving entity information acquisition means acquires characteristic information regarding the characteristics of the driving entity (e.g., the driving entity characteristic information described below) based on at least one of the driving entity's past driving history and the status information, and it is preferable that the prediction means predicts the future of the prediction target based on the recognition information, the status information and the characteristic information.

[0012] (5) In this case, it is preferable that the recognition means acquires the recognition information regarding a recognition target including each traffic participant in the target traffic area and a traffic environment of each traffic participant in the target traffic area.

[0013] (6) In this case, it is preferable that the prediction means constructs a virtual space simulating the target traffic area by a computer, and predicts the future of the prediction target by performing a simulation based on the recognition information and the status information in the virtual space.

[0014] (7) In this case, it is preferable that the prediction means includes a behavior estimation means (e.g., a behavior estimation unit 623 described later) that associates a first input including at least the recognition information among the recognition information and the state information with at least one of a plurality of predetermined pattern behaviors of the driving subject, and a simulator (e.g., a simulator 626 described later) that predicts the future of the prediction target by performing a simulation in the virtual space based on the pattern behavior associated by the behavior estimation means.

[0015] (8) In this case, it is preferable that the behavior estimation means includes driving ability estimation means (e.g., a driving ability estimation unit 624 described below) that estimates the decline in driving ability for each ability element based on the first input, and association means (e.g., an association unit 625 described below) that associates the ability element estimated to have declined by the driving ability estimation means with at least one of the multiple pattern behaviors.

[0016] (9) In this case, it is preferable that the driving ability is divided into at least four ability elements: cognitive ability, prediction ability, judgment ability, and operation ability of the driver.

[0017] (10) In this case, it is preferable that the prediction means comprises a high-risk traffic participant identification means (e.g., the high-risk traffic participant identification unit 621 described below) which identifies, from among the multiple traffic participants recognized by the recognition means, a traffic participant who is estimated to have a high possibility of engaging in a predetermined chain risk inducing behavior in the future as a high-risk traffic participant based on a second input including at least the recognition information among the recognition information and the status information, and a prediction target determination means (e.g., the prediction target determination unit 622 described below) which determines the high-risk traffic participant as the first traffic participant and determines two persons extracted from the multiple traffic participants present around the first traffic participant as the second and third traffic participants.

[0018] (11) A traffic safety support method according to the present invention is a method for supporting the safety of traffic participants by a computer (e.g., a cooperative support device 6 described later), and includes a step of recognizing traffic participants as people (e.g., a pedestrian 4 and a pedestrian group 4a described later) or moving objects (e.g., four-wheeled vehicles 2, 2a, and 2b and motorcycles 3 and 3a described later) in a target traffic area (e.g., a target traffic area 9 described later) and acquiring recognition information (e.g., traffic participant recognition information and traffic environment recognition information described later) regarding each traffic participant (e.g., a step of step ST1 in FIG. 4 described later); a step of acquiring status information (e.g., driving subject status information described later) correlated with the driving ability of a driving subject of the moving object recognized as a traffic participant (e.g., a step of step ST2 in FIG. 4 described later); and predicting the future of a plurality of prediction targets determined from a plurality of recognized traffic participants based on the recognition information and the status information. The method includes a step of predicting the future of a plurality of prediction targets based on a prediction result for the prediction target (e.g., a step of step ST3 in FIG. 4 described later), and a step of notifying support information (e.g., collaborative support information described later) to at least one of the prediction targets based on a prediction result for the prediction target (e.g., a step of step ST4 in FIG. 4 described later). In the step of predicting the future of the prediction targets, if the first and second traffic participants among the first, second and third traffic participants that are the prediction targets are first and second moving bodies in the target traffic area and status information of at least any of the first and second moving bodies has been acquired, a future behavior of the first moving body, a future behavior of the second moving body according to the future behavior of the first moving body, and a future risk of the third traffic participant according to the future behavior of at least any of the first and second moving bodies are predicted based on the recognition information and the status information. Effect of the Invention

[0019] (1) In the traffic safety support system according to the present invention, the prediction means predicts the future of multiple traffic participants recognized by the recognition means based on the recognition information on each traffic participant acquired by the recognition means and the state information correlated with the driving ability of the driver of the mobile object recognized as a traffic participant. Therefore, the prediction means can predict the future of multiple traffic participants, including the irregular behavior of a specific mobile object, taking into account the deterioration of the driving ability of the driver of the specific mobile object at that time. In addition, the notification means notifies at least one of the multiple prediction objects of support information based on the prediction results for the multiple prediction objects by the prediction means, thereby making it possible to avoid predicted risks for these prediction objects in advance, thereby improving the safety, convenience, and smoothness of traffic.

[0020] In particular, in the present invention, when the first and second traffic participants among the first, second and third traffic participants to be predicted are the first and second moving bodies in the target traffic area and the state information of at least one of the driving subjects of the first and second moving bodies is acquired, the prediction means predicts the future behavior of the first traffic participant, the future behavior of the second traffic participant corresponding to the future behavior of the first traffic participant, and the future risk of the third traffic participant corresponding to the future behavior of at least one of the first and second traffic participants based on the recognition information and the state information. In addition, the notification means notifies at least one of the first and second moving bodies and the third traffic participant of the support information based on the prediction result of the future behavior of the first and second traffic participants and the prediction result of the future risk of the third traffic participant. In this way, it is possible to prevent a chain reaction risk that occurs among the multiple traffic participants due to a decrease in the driving ability of at least one of the driving subjects of the first and second traffic participants and affects the third traffic participant in advance when three or more parties including the first, second and third traffic participants become involved. Therefore, according to the present invention, it is possible to further improve traffic safety, convenience, and smoothness.

[0021] (2) When the third traffic participant is viewed as a subject, it is often difficult to predict in advance a chain reaction risk that may occur between the first and second traffic participants other than the third traffic participant and ultimately affect the third traffic participant. For this reason, the third traffic participant often has little time to take action to avoid such a chain reaction risk. In response to this, in the traffic safety support system according to the present invention, when the prediction means predicts the occurrence of a chain reaction risk in the future of the third traffic participant, the notification means notifies the communication interface held by the third traffic participant of support information. This allows the third traffic participant to have time to take action to avoid the chain reaction risk, thereby improving the safety of the third traffic participant.

[0022] (3) In the traffic safety support system according to the present invention, when the driver is a human, the driver information acquisition means acquires state information based on time-series data of at least one of the driver's biometric information, appearance information, and voice information. By using such state information, the prediction means can appropriately grasp the driving ability of the driver while driving and predict the future behavior of the moving object driven by the driver, thereby predicting various risks that may be posed to the prediction target. Thus, according to the present invention, the safety, convenience, and smoothness of traffic can be further improved.

[0023] (4) In the traffic safety support system according to the present invention, when the driver is a human, the driver information acquisition means acquires characteristic information on the characteristics of the driver based on at least one of the driver's past driving history and time-dependent state information. In addition to the recognition information and state information, the prediction means uses the driver's characteristic information to appropriately grasp the driver's driving ability and characteristics while driving, and predict the future behavior of the moving object driven by the driver, thereby predicting various risks that may be posed to the prediction target. Thus, according to the present invention, the safety, convenience, and smoothness of traffic can be further improved.

[0024] (5) In the traffic safety support system according to the present invention, the recognition means acquires recognition information on the recognition target, including each traffic participant in the target traffic area and the traffic environment of each traffic participant in the target traffic area. In addition, the prediction means uses such recognition information to appropriately grasp the traffic environment around each traffic participant and predict the future of the prediction target, thereby predicting various risks that may be posed to the prediction target. Therefore, according to the present invention, it is possible to further improve the safety, convenience, and smoothness of traffic.

[0025] (6) In the traffic safety support system according to the present invention, the prediction means constructs a virtual space simulating the target traffic area by a computer, and predicts the future of the prediction target by performing a simulation based on the recognition information and state information in this virtual space. As a result, the prediction means reproduces each traffic participant in the target traffic area and the traffic environment around them, and monitors events that may occur in the target traffic area from a bird's-eye view, thereby predicting various risks that may be posed to the prediction target. Therefore, according to the present invention, it is possible to further improve the safety, convenience, and smoothness of traffic.

[0026] (7) In the traffic safety support system according to the present invention, the behavior estimation means associates a first input including at least the recognition information among the recognition information and the state information with at least one of a plurality of predetermined pattern behaviors of the driving subject, and the simulator predicts the future of the prediction target by performing a simulation in a virtual space based on the pattern behavior associated by the behavior estimation means. In the present invention, by predetermining future behaviors that the driving subject of the moving body may take as pattern behaviors, the prediction means can quickly predict the future of the prediction target, and therefore support information based on the prediction result by the prediction means can also be quickly notified, and thus each traffic participant can have time to take action to avoid risks that may occur in the future. Thus, according to the present invention, the safety, convenience, and smoothness of traffic can be further improved.

[0027] (8) In the traffic safety support system according to the present invention, the behavior estimation means includes a driving ability estimation means for estimating a decline in the driving ability of the driver for each ability element based on a first input including at least recognition information, and an association means for associating the ability element estimated to be declined by the driving ability estimation means with at least one of a plurality of predetermined pattern behaviors. This allows the association means to quickly determine the pattern behavior from the first input, so that each traffic participant can have more time to take action to avoid future risks, as described above. Therefore, according to the present invention, the safety, convenience, and smoothness of traffic can be further improved.

[0028] (9) In the traffic safety support system according to the present invention, the driving ability estimation means divides the driving ability that the driver should have in order to drive a moving object appropriately into at least four ability elements, namely, cognitive ability, predictive ability, judgment ability, and operation ability, and estimates the decline in the driving ability of the driver for each of these four ability elements. This allows the behavior estimation means to quickly determine an appropriate pattern behavior according to the decline in each ability element, so that each traffic participant can have more time to take action to avoid future risks, as described above. Therefore, according to the present invention, the safety, convenience, and smoothness of traffic can be further improved.

[0029] (10) In the target traffic area, there are actually three or more traffic participants, and if all of these traffic participants are treated as prediction targets and the above-mentioned chain risk is evaluated, the load on the prediction means may be large. In contrast, in the traffic safety support system according to the present invention, the high-risk traffic participant identification means identifies a traffic participant who is estimated to be likely to take a predetermined chain risk inducing behavior in the future as a high-risk traffic participant from among the multiple traffic participants recognized by the recognition means, and the prediction target determination means determines the high-risk traffic participant as the first traffic participant and two traffic participants extracted from the multiple traffic participants around the first traffic participant as the second and third traffic participants. In this way, the prediction means narrows down the prediction targets to the high-risk traffic participant and the traffic participants around it, thereby reducing the load on the prediction means, and therefore the future of the prediction target can be predicted quickly, and thus each traffic participant can have time to take action to avoid a risk that may occur in the future. Therefore, according to the present invention, the safety, convenience, and smoothness of traffic can be further improved.

[0030] (11) According to the traffic safety support method of the present invention, it is possible to improve traffic safety, convenience, and smoothness for the same reasons as the invention of (1). [Brief description of the drawings]

[0031] [Figure 1] 1 is a diagram showing a configuration of a traffic safety support system according to an embodiment of the present invention and a part of a target traffic area supported by the traffic safety support system. [Diagram 2] 1 is a block diagram showing a configuration of a collaborative support device and a plurality of area terminals communicably connected to the collaborative support device. [Diagram 3] FIG. 11 is a functional block diagram showing a specific configuration of a prediction unit. [Figure 4] 1 is a flowchart showing a specific procedure of a traffic safety support method. [Diagram 5] 13 is a flowchart showing a specific procedure of a chain risk prediction process performed by a prediction unit. [Figure 6] FIG. 13 is a diagram showing the state of the target traffic area before the time predicted by the prediction unit from the time when the chain risk in Case 1 may occur. [Figure 7] FIG. 7 is a diagram showing the chain risk of Case 1 predicted by the prediction unit as possibly occurring in the future after the prediction time from the point shown in FIG. 6. [Figure 8] FIG. 13 is a diagram showing the state of the target traffic area before the time predicted by the prediction unit from the time when the chain risk in Case 2 may occur. [Figure 9] FIG. 9 is a diagram showing the chain risk of Case 2 predicted by the prediction unit as possibly occurring in the future after the prediction time from the point shown in FIG. 8. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0032] Hereinafter, a traffic safety support system and a traffic safety support method according to an embodiment of the present invention will be described with reference to the drawings.

[0033] 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 the traffic safety support system 1 provides support.

[0034] The traffic safety support system 1 recognizes pedestrians 4, which are people, and moving bodies such as four-wheeled vehicles 2 and motorcycles 3, which are moving bodies within the target traffic area 9, as individual traffic participants, and notifies each traffic participant of support information generated through this recognition, thereby supporting the safe and smooth traffic of each traffic participant in the target traffic area 9 by 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.

[0035] FIG. 1 illustrates a case where a target traffic area 9 is an area around an intersection 52 in an urban area, including 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 vehicles 2 and 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. Note that, in the following, a case where all four-wheeled vehicles 2 moving in the target traffic area 9 are driven by human drivers will be described, but the present invention is not limited to this. The present invention is also applicable to a case where all or some of the multiple four-wheeled vehicles 2 moving in the target traffic area 9 are autonomous vehicles driven by non-human computers.

[0036] 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 traffic lights 54, and a collaboration support device 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.

[0037] The cooperative support device 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 cooperative support device 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.

[0038] FIG. 2 is a block diagram showing the configuration of the collaboration support device 6 and a plurality of area terminals connected to the collaboration support device 6 so as to be able to communicate with each other.

[0039] 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, a driver HMI (Human Machine Interface) 22 that notifies the driver of driving assistance information transmitted from the on-board driving assistance device 21 and collaborative assistance information (described below) transmitted from the collaborative assistance device 6, a driving subject state sensor 23 that detects the state of the driver while driving, an on-board communication device 24 that wirelessly communicates between the vehicle and the collaborative assistance device 6, and a portable information processing terminal 25 owned or worn by the driver.

[0040] 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 exterior camera unit that captures the surroundings of the vehicle, a radar unit or a Light Detection and Ranging (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 by the exterior camera unit and the radar unit. 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.

[0041] The driving assistance ECU executes driving assistance controls such as lane keeping control, lane departure suppression control, lane change control, preceding vehicle following control, collision mitigation brake control, and erroneous start suppression control based on information acquired by an external sensor unit, a vehicle state sensor, a navigation device, etc. The driving assistance ECU also generates driving assistance information for supporting safe driving by the driver based on information acquired by an external sensor unit, a vehicle state sensor, a navigation device, etc., and transmits the information to the driver HMI 22.

[0042] The driver's subject state sensor 23 is composed of various devices that acquire time-dependent data of information correlated with the driver's driving ability while driving. The driver's subject state sensor 23 is composed of, for example, an in-vehicle camera that detects the direction of the driver's line of sight and whether or not the driver's eyes are open while driving, a seat belt sensor attached to the seat belt worn by the driver to detect the driver's pulse and whether or not the driver is breathing, a steering sensor attached to the steering wheel held by the driver to detect the driver's skin potential, an in-vehicle microphone that detects whether or not the driver is talking to a passenger, etc.

[0043] The in-vehicle communication device 24 has a function of transmitting information acquired by the driving assistance ECU (including information acquired by an external sensor unit, the vehicle's status sensor, a 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, to the collaborative assistance device 6, and a function of receiving collaborative assistance information transmitted from the collaborative assistance device 6 and transmitting the received collaborative assistance information to the driver HMI 22.

[0044] The driver HMI 22 is composed of various devices that notify the driver of the driving support information transmitted from the in-vehicle driving support device 21 and the cooperative support information transmitted from the cooperative support device 6 through the driver's vision, hearing, touch, etc. The driver HMI 22 is composed of, for example, a seat belt control device that notifies the driver of the driving support information and the cooperative support information by changing the tension of the seat belt worn by the driver, an audio device that notifies the driver of the driving support information and the cooperative support information by producing a voice, a warning sound, a melody, etc., a head-up display that notifies the driver of the driving support information and the cooperative support information by displaying an image, etc.

[0045] The mobile information processing terminal 25 is, for example, a wearable terminal worn by the driver of the four-wheeled vehicle 2, a smartphone held by the driver, or the like. The wearable terminal has a function of measuring the driver's biological information, such as heart rate, blood pressure, and blood oxygen saturation, and transmitting the measurement data of the biological information to the collaboration support device 6, and a function of receiving collaboration support information transmitted from the collaboration support device 6 and notifying the driver of a message corresponding to the collaboration support information by an image, a voice, a warning sound, a vibration, or the like. The smartphone also has a function of transmitting information about the driver, such as the driver's position information, movement acceleration, and schedule information, to the collaboration support device 6, and a function of receiving collaboration support information transmitted from the collaboration support device 6, and notifying the driver of a message corresponding to the collaboration support information by an image, a voice, a warning sound, a melody, a vibration, or the like.

[0046] 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, a rider HMI 32 that notifies the rider of driving assistance information transmitted from the on-board driving assistance device 31 and collaborative assistance information transmitted from the collaborative assistance device 6, a rider status sensor 33 that detects the status of the rider while driving, and a portable information processing terminal 35 owned or worn by the rider.

[0047] 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 exterior camera unit that captures the surroundings of the vehicle, 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 by the exterior camera unit or the radar unit. 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.

[0048] The driving assistance ECU executes driving assistance controls such as lane keeping control, lane departure suppression control, lane change control, preceding vehicle following control, and collision mitigation brake control based on information acquired by the external sensor unit, the vehicle status sensor, the navigation device, etc. The driving assistance ECU also generates driving assistance information for assisting the rider in safe driving based on information acquired by the external sensor unit, the vehicle status sensor, the navigation device, etc., and transmits the information to the rider HMI 32.

[0049] The rider condition sensor 33 is composed of various devices that acquire information correlated with the driving ability of the rider while driving. The rider condition sensor 33 is composed of, for example, 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, and the like, and 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, and the like.

[0050] The in-vehicle communication device 34 has a function of transmitting information acquired by the driving assistance ECU (including information acquired by an external sensor unit, the vehicle status sensor, and a 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, to the collaborative assistance device 6, and a function of receiving collaborative assistance information transmitted from the collaborative assistance device 6 and transmitting the received collaborative assistance information to the rider HMI 32.

[0051] The rider HMI 32 is composed of various devices that notify the rider of the driving support information transmitted from the in-vehicle driving support device 21 and the cooperative support information transmitted from the cooperative support device 6 through the driver's vision, hearing, touch, etc. The rider HMI 32 is composed of, for example, an audio device that is provided in a helmet worn by the rider and notifies the driver of the driving support information and the cooperative support information by issuing a voice, a warning sound, a melody, etc., and a head-up display that notifies the driver of the driving support information and the cooperative support information by displaying an image.

[0052] The mobile information processing terminal 40 owned or worn by the pedestrian 4 in the target traffic area 9 is, for example, a wearable terminal worn by the pedestrian 4 or a smartphone owned by the pedestrian 4. The wearable terminal has a function of measuring the biological information of the pedestrian 4, such as the heart rate, blood pressure, and blood oxygen saturation, and transmitting the measurement data of the biological information to the collaboration support device 6, and a function of receiving the collaboration support information transmitted from the collaboration support device 6 and notifying the pedestrian 4 of a message corresponding to the collaboration support information by an image, a voice, a warning sound, a vibration, or the like. The smartphone also has a function of transmitting pedestrian information related to the pedestrian 4, such as the position information, movement acceleration, and schedule information of the pedestrian 4, to the collaboration support device 6, and a function of receiving the collaboration support information transmitted from the collaboration support device 6 and notifying the pedestrian 4 of a message corresponding to the collaboration support information by an image, a voice, a warning sound, a melody, a vibration, or the like.

[0053] The infrastructure camera 56 captures 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, sidewalks, etc., and transmits the obtained image information to the collaborative support device 6.

[0054] The signal control device 55 controls traffic lights and transmits to the collaboration support device 6 traffic light status information regarding the current lighting color of traffic lights installed in the target traffic area and the timing for changing the lighting color.

[0055] The collaborative support device 6 is a computer that supports safe and smooth traffic for traffic participants in the target traffic area by generating collaborative support information to promote communication between traffic participants and awareness of the surrounding traffic environment based on information obtained from multiple area terminals present in the target traffic area as described above, and notifying each traffic participant of the information.

[0056] The collaborative assistance device 6 includes a target traffic area recognition unit 60 that recognizes people and moving bodies 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 body recognized as a traffic participant by the target traffic area recognition unit 60, a prediction unit 62 that predicts the future of a prediction target determined from among the multiple traffic participants recognized by the target traffic area recognition unit 60, a collaborative assistance information notification unit 63 that notifies at least any of the prediction targets of collaborative assistance information corresponding to the prediction result based on the prediction result by the prediction unit 62, a traffic environment database 64 that accumulates information on the traffic environment in the target traffic area, and a driving history database 65 that accumulates information on the past driving history of pre-registered driving subjects.

[0057] The traffic environment database 64 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 road 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 64 is also referred to as registered traffic environment information.

[0058] The driving history database 65 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 65 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 65 is also referred to as registered driving history information.

[0059] The target traffic area recognition unit 60 recognizes recognition objects including each traffic participant, who 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 the registered traffic environment information read from the traffic environment database 64, and obtains recognition information regarding these recognition objects.

[0060] 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 64 includes information on the traffic environment of each traffic participant, such as map information of the target traffic area and risk area information.

[0061] Therefore, based on the information transmitted from these area terminals, the target traffic area recognition unit 60 can obtain recognition information of each traffic participant in the target traffic area, such as the position in the target traffic area of ​​each traffic participant, the moving speed, the moving acceleration, the moving direction, 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. (hereinafter also referred to as "traffic participant recognition information"). Also, based on the information transmitted from these area terminals, the target traffic area recognition unit 60 can obtain recognition information of the traffic environment of each traffic participant in the target traffic area, 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 (hereinafter also referred to as "traffic environment recognition information").

[0062] Therefore, in this embodiment, the recognition means that recognizes a target traffic area and traffic participants in this target traffic area as recognition targets and acquires traffic participant recognition information and traffic environment recognition information related to these recognition targets is composed of a target traffic area recognition unit 60, an on-board driving assistance device 21, an on-board communication device 24, and a portable information processing terminal 25 included in the on-board device group 20 of the four-wheeled automobile 2, an on-board driving assistance device 31, an on-board communication device 34, and a portable information processing terminal 35 included in the on-board device group 30 of the motorcycle 3, the portable information processing terminal 40 of the pedestrian 4, an infrastructure camera 56, a signal control device 55, and a traffic environment database 64.

[0063] 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 collaboration support information notification unit 63, and the like.

[0064] 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 65.

[0065] 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.

[0066] Here, the information transmitted from the driver's state sensor 23 and the vehicle-mounted communication device 24 included in the vehicle-mounted device group 20 to the driver's information acquisition unit 61 includes time-based data on the driver's appearance such as the direction of the driver's gaze and whether or not the driver's eyes are open while driving, biological information such as pulse, whether or not breathing, and skin potential, and voice information such as whether or not the driver is talking, and includes information that is correlated with the driver's driving ability while driving. The information transmitted from the rider's state sensor 33 and the vehicle-mounted communication device 34 included in the vehicle-mounted device group 30 to the driver's information acquisition unit 61 includes time-based data on the rider's biological information such as pulse, whether or not breathing, and skin potential, and includes information that is correlated with the driver's driving ability while driving. The information transmitted from the mobile information processing terminals 25 and 35 included in the vehicle-mounted device groups 20 and 30 to the driver's information acquisition unit 61 includes the driver's and rider's personal schedule information. For example, when the driver or rider is driving a moving object under a tight schedule, the driver or rider may become impatient and his or her driving ability may decrease. For this reason, the driver's and rider's personal schedule information can be said to be information that is correlated with his or her own driving ability.

[0067] Therefore, in this embodiment, the driver subject information acquisition means for acquiring driver subject state information correlated with the driver's current driving ability is composed of a driver subject information acquisition unit 61, a driver subject state sensor 23, an on-board communication device 24 and a portable information processing terminal 25 included in the on-board device group 20 of the four-wheeled vehicle 2, and a rider state sensor 33, an on-board communication device 34 and a portable information processing terminal 25 included in the on-board device group 30 of the motorcycle 3.

[0068] In addition, 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 65.

[0069] Therefore, in this embodiment, the driving subject information acquisition means for acquiring driving subject characteristic information correlated with the driving subject's current driving ability is composed of a driving subject information acquisition unit 61, a driving subject state sensor 23, an on-board communication device 24 and a portable information processing terminal 25 included in the on-board device group 20 of the four-wheeled vehicle 2, a rider state sensor 33, an on-board communication device 34 and a portable information processing terminal 35 included in the on-board device group 30 of the motorcycle 3, and a driving history database 65.

[0070] 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.

[0071] The prediction unit 62 predicts the future of a plurality of prediction targets determined from a plurality of traffic participants recognized by the target traffic area recognition unit 60, 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. More specifically, the prediction unit 62 constructs a virtual space simulating the target traffic area based on the traffic participant recognition information and traffic environment recognition information acquired by the target traffic area recognition unit 60, and predicts the future of the plurality of prediction targets by performing a simulation in the virtual space based on the traffic participant recognition information, traffic environment recognition information, driving subject state information, and driving subject characteristic information. Note that the procedure of determining a plurality of prediction targets and the procedure of predicting the future of these prediction targets in the prediction unit 62 will be described in detail later with reference to FIG. 3.

[0072] The collaboration assistance information notification unit 63 notifies at least one of the multiple prediction targets by the prediction unit 62 of collaboration assistance information for promoting communication between the multiple prediction targets and recognition of the surrounding traffic environment, based on the prediction result by the prediction unit 62. More specifically, when the prediction unit 62 predicts that some risk will occur between the multiple prediction targets, it specifies multiple traffic participants who may be involved as parties in the predicted risk as notification targets, generates collaboration assistance information whose content corresponds to each notification target and the prediction result, and further notifies the collaboration assistance information to one or more notification targets that are capable of wireless communication among the multiple notification targets.

[0073] When the identified notification target is a pedestrian recognized as a traffic participant by the target traffic area recognition unit 60, the collaboration support information notification unit 63 notifies the collaboration support information to the portable information processing terminal 40 carried or worn by the pedestrian. As described above, when the portable information processing terminal 40 receives the collaboration support information, it notifies the pedestrian, who is the owner, of the collaboration support information.

[0074] Furthermore, when the identified notification target is a moving body recognized as a traffic participant by the target traffic area recognition unit 60, the cooperative support information notification unit 63 notifies the in-vehicle device group 20, 30 mounted on the moving body of the cooperative support information. As described above, when the in-vehicle communication device 24 included in the in-vehicle device group 20 receives the cooperative support information, it transmits it to the driver HMI 22, and the driver HMI 22 notifies the driver of the received cooperative support information. When the portable information processing terminal 25 included in the in-vehicle device group 20 receives the cooperative support information, it notifies the driver, who is the owner, of the cooperative support information. When the in-vehicle communication device 34 included in the in-vehicle device group 30 receives the cooperative support information, it transmits it to the rider HMI 32, and the rider HMI 32 notifies the rider of the received cooperative support information. When the portable information processing terminal 35 included in the in-vehicle device group 30 receives the cooperative support information, it notifies the rider, who is the owner, of the cooperative support information.

[0075] Therefore, in this embodiment, the notification means for notifying at least one of the multiple prediction targets of collaborative assistance information based on the prediction result by the prediction unit 62 is composed of the collaborative assistance information notification unit 63, the in-vehicle communication device 24, the driver HMI 22, and the portable information processing terminal 25 included in the in-vehicle device group 20, the in-vehicle communication device 34, the rider HMI 32, and the portable information processing terminal 35 included in the in-vehicle device group 30, and the portable information processing terminal 40 owned by the pedestrian.

[0076] Fig. 3 is a functional block diagram showing a specific configuration of the prediction unit 62. Fig. 3 illustrates only a function related to predicting a chain risk (hereinafter also referred to as a "chain risk") that occurs when three or more of the multiple traffic participants recognized by the target traffic area recognition unit 60 become involved, among the risk prediction functions for each traffic participant by the prediction unit 62.

[0077] The prediction unit 62 includes a high-risk traffic participant identification unit 621, a prediction target determination unit 622, a behavior estimation unit 623, and a simulator 626, and uses these to predict chain risks for multiple prediction targets.

[0078] The high-risk traffic participant identification unit 621 identifies, based on the traffic participant recognition information and traffic environment recognition information (hereinafter collectively referred to as "recognition information") acquired by the target traffic area recognition unit 60, traffic participants who are estimated to have a high probability of engaging in a specified chain risk-inducing behavior in the future as high-risk traffic participants from among all traffic participants recognized by the target traffic area recognition unit 60.

[0079] Here, the chain risk inducing behavior refers to a behavior that is highly likely to induce the above-mentioned chain risk.Specific examples of the chain risk inducing behavior include sudden acceleration, sudden deceleration, sudden lane change, cutting in, closing the distance to the vehicle ahead or following, continuing to drive across lanes, meandering, driving the wrong way, ignoring traffic signals, driving at a speed that is a predetermined speed or more faster than surrounding moving objects, driving at a predetermined speed or more slower than surrounding moving objects, driving at a predetermined speed or more faster than the speed limit, driving at a predetermined speed or more slower than the speed limit, and obstructing the movement of surrounding traffic participants.

[0080] The multiple chain risk inducing behaviors listed above are often performed due to a decline in the driving ability of the driver of the moving object. For this reason, it is preferable that the high-risk traffic participant identification unit 621 identifies high-risk traffic participants based on at least one of the driver's state information and the driver's characteristic information (hereinafter, these are also collectively referred to as "driver's information") acquired by the driver's information acquisition unit 61 in addition to the above-mentioned recognition information. In addition, the high-risk traffic participant identification unit 621 may identify high-risk traffic participants by, for example, estimating the behavior of the driver of the moving object using the behavior estimation unit 623 described later.

[0081] The prediction target determination unit 622 extracts N persons (N is any integer equal to or greater than 3) who may be involved in a chain risk from among the multiple traffic participants recognized by the target traffic area recognition unit 60, and determines the extracted first traffic participant, second traffic participant, third traffic participant, ..., Nth traffic participant as prediction targets.

[0082] More specifically, the prediction target determination unit 622 determines, as a first traffic participant, a traffic participant identified by the high-risk traffic participant identification unit 621 as a high-risk traffic participant among a plurality of traffic participants recognized by the target traffic area recognition unit 60. The prediction target determination unit 622 also extracts a plurality of traffic participants existing around the first traffic participant based on the recognition information, and extracts N-1 persons who may be involved in a chain risk induced by the first traffic participant's future chain risk inducing behavior from among the extracted plurality of traffic participants, and determines these N-1 persons as the second traffic participant, the third traffic participant, ..., the Nth traffic participant, respectively.

[0083] The behavior estimation unit 623 identifies a moving object from among the first to Nth traffic participants determined as prediction targets by the prediction target determination unit 622 based on the recognition information, and estimates future behaviors that the driving subject of each moving object recognized as a traffic participant may take. In the behavior estimation unit 623, future behaviors that the driving subject may take are predetermined as a plurality of pattern behaviors, and the behavior estimation unit 623 estimates future behaviors that the driving subject of each moving object may take by associating a behavior estimation input including at least the recognition information out of the recognition information and the driving subject information with at least one of the predetermined plurality of pattern behaviors.

[0084] The pattern behaviors that the driver may adopt here include intentional behaviors such as acceleration operations, deceleration operations, steering operations, lane keeping operations, checking the surroundings, and lane changing operations, as well as involuntary behaviors such as delayed forward recognition, delayed rear recognition, and delayed lateral recognition.

[0085] The behavior estimation unit 623 includes a driving ability estimation unit 624 that estimates the decline in the driving ability of the main driver for each predetermined ability element based on the above behavior estimation input, taking into consideration the surrounding traffic environment including other traffic participants, and an association unit 625 that associates the ability element estimated to be declining by the driving ability estimation unit 624 with at least one of the above-mentioned multiple pattern behaviors, taking into consideration the traffic environment.By using the driving ability estimation unit 624 and the association unit 625, the behavior that the main driver of each moving object may take in the future is determined from multiple pattern behaviors.

[0086] Here, the driving ability estimation unit 624 divides the driving ability that the driving subject should have in order to drive a moving object appropriately into at least four ability elements, namely, cognitive ability, predictive ability, judgment ability, and operational ability. The cognitive ability is the ability of the driving subject to appropriately recognize the state of the vehicle, the traffic environment around the vehicle, and the traffic participants. The predictive ability is the ability of the driving subject to appropriately predict changes in the vehicle, the traffic environment around the vehicle, and the traffic participants. The judgment ability is the ability of the driving subject to appropriately judge according to the state of the vehicle, the traffic environment around the vehicle, and the traffic participants. Furthermore, the operational ability is the ability of the driving subject to appropriately operate the vehicle. The behavior that the driving subject can take varies depending on the ability element that is reduced. Therefore, the behavior estimation unit 623 can narrow down the number of pattern behaviors associated with the behavior estimation input by estimating the reduction in the driving ability of the driving subject for each of the above ability elements based on the behavior estimation input as described above.

[0087] Through the above-mentioned procedure, the behavior estimation unit 623 estimates the future behavior of the driver of each moving object that is recognized as a traffic participant by the target traffic area recognition unit 60 among the multiple prediction targets.

[0088] The simulator 626 constructs a virtual space simulating a target traffic area based on the recognition information, and predicts the future behavior of each of the first to Nth traffic participants determined as a prediction target and the future chain reaction risk of each of the first to Nth traffic participants by performing a simulation based on the recognition information and the driving subject information in this virtual space. More specifically, the simulator 626 predicts the behavior of each of the first to Nth traffic participants determined as a prediction target from the present to a predetermined predicted future time ahead and the chain reaction risk from the present to the predicted future time ahead by performing a simulation based on the recognition information for the first to Nth traffic participants and the pattern behavior associated with each driving subject of each moving body by the behavior estimation unit 623 in the virtual space constructed based on the recognition information.

[0089] Here, the above-mentioned chain risk is considered to occur in a chain reaction among the first to Nth traffic participants while influencing each other, triggered by a high-risk inducing behavior by the first traffic participant recognized as a high-risk traffic participant. Therefore, the simulator 626 performs a simulation in a virtual space considering the influence of the behavior of each traffic participant on the behavior of other traffic participants, based on the recognition information for each traffic participant and the pattern behavior associated with each driving subject of each moving body, to predict the behavior and risk of the first traffic participant from the present to the future, the behavior and risk of the second traffic participant from the present to the future according to the behavior of the first traffic participant, the behavior and risk of the third traffic participant from the present to the future according to the behavior of at least one of the first and second traffic participants, and the behavior and risk of the n+1th traffic participant from the present to the future according to the behavior of the first to nth traffic participants (n is any integer between 2 and N-1).

[0090] As described above, when any of the multiple traffic participants recognized by the target traffic area recognition unit 60 is identified as a high-risk traffic participant by the high-risk traffic participant identification unit 621, the prediction unit 62 predicts the future of multiple prediction targets including this high-risk traffic participant through simulation by the simulator 626. Note that when multiple high-risk traffic participants are identified by the high-risk traffic participant identification unit 621, the prediction unit 62 predicts the future of these prediction targets by performing a simulation for the prediction targets determined for each high-risk traffic participant. After predicting the behavior and risk of the multiple prediction targets through the above procedure, the prediction unit 62 transmits information regarding these prediction results to the collaboration support information notification unit 63.

[0091] When the prediction unit 62 predicts the occurrence of a chain reaction risk involving three or more parties among multiple prediction targets, the collaboration support information notification unit 63 acquires information on these multiple parties and information on the content of the predicted chain reaction risk from the target traffic area recognition unit 60 and the prediction unit 62, generates collaboration support information for each party based on the acquired information, and notifies each party of the generated collaboration support information. At this time, it is preferable that the collaboration support information notification unit 63 generates collaboration support information suitable for each party so that the occurrence of the predicted chain reaction risk can be avoided by encouraging communication between the multiple predicted parties and recognition of the surrounding traffic environment, and taking actions suitable for each party.

[0092] FIG. 4 is a flowchart showing a specific procedure of a traffic safety support method for supporting safe and smooth traffic of each traffic participant in a target traffic area using the above-described traffic safety support system.

[0093] First, in step ST1, the target traffic area recognition unit 60 recognizes recognition objects including multiple traffic participants and their traffic environments in the target traffic area 9 based on information transmitted from multiple area terminals in the target traffic area 9 and registered traffic environment information read from the traffic environment database 64, and obtains traffic participant recognition information regarding these multiple traffic participants and traffic environment recognition information regarding the traffic environment, and then proceeds to step ST2.

[0094] Next, in step ST2, 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 multiple area terminals in the target traffic area 9 and registered driving history information read from the driving history database 65, and proceeds to step ST3.

[0095] Next, in step ST3, the prediction unit 62 executes a chain risk prediction process according to the procedure described later with reference to Figure 5 to determine a plurality of prediction targets from among the plurality of traffic participants recognized by the target traffic area recognition unit 60, and predicts the future behavior of these plurality of prediction targets and the future chain risk of these plurality of prediction targets based on the traffic participant recognition information, traffic environment recognition information, driving subject state information, and driving subject characteristic information, and then proceeds to step ST4.

[0096] Next, in step ST4, the collaboration support information notification unit 63 notifies one or more notification targets determined from among the multiple prediction targets based on the prediction results for the multiple prediction targets by the chain risk prediction process in step ST3, and returns to step ST1. More specifically, when the collaboration support information notification unit 63 executes the chain risk prediction process to predict the occurrence of a chain risk for the multiple prediction targets, it identifies multiple traffic participants who may be involved as parties in the chain risk as notification targets, and notifies at least one of these parties, and more preferably all of the parties, of the collaboration support information.

[0097] FIG. 5 is a process showing a specific procedure for the linkage risk prediction process by the prediction unit 62. In FIG.

[0098] First, in step ST11, the high-risk traffic participant identification unit 621 identifies, from among all traffic participants recognized by the target traffic area recognition unit 60, traffic participants who are estimated to have a high probability of engaging in chain risk-inducing behavior in the future as high-risk traffic participants based on the traffic participant recognition information, traffic environment recognition information, driving subject state information, and driving subject characteristic information, and then proceeds to step ST12.

[0099] Next, in step ST12, the prediction target determination unit 622 determines, as prediction targets, the first to Nth traffic participants who may be involved in a chain risk induced by the future chain risk inducing behavior of the corresponding risk traffic participant identified in step ST11, from among the multiple traffic participants recognized by the target traffic area recognition unit 60, and proceeds to step ST13. More specifically, the prediction target determination unit 622 determines the high-risk traffic participant as the first traffic participant, extracts N-1 participants who may be involved in a chain risk from among the multiple traffic participants around the first traffic participant, and determines these N-1 participants as the second traffic participant, the third traffic participant, ..., the Nth traffic participant, respectively.

[0100] Next, in step ST13, the behavior estimation unit 623 identifies moving bodies from among the prediction targets, estimates possible future behaviors of the driving subjects of each moving body recognized as a traffic participant, and proceeds to step ST14. More specifically, the driving ability estimation unit 624 of the behavior estimation unit 623 estimates the decline in the driving ability of each driving subject for each ability element based on the traffic participant recognition information, the traffic environment recognition information, the driving subject state information, and the driving subject characteristic information, and further, the associating unit 625 of the behavior estimation unit 623 associates the ability element estimated to be declined by the driving ability estimation unit 624 with at least one of a plurality of predetermined pattern behaviors, taking the traffic environment into consideration, thereby associating the driving subject of each moving body with the pattern behavior.

[0101] Next, in step ST14, the simulator 626 constructs a virtual space simulating the target traffic area based on the traffic participant recognition information and the traffic environment recognition information, and predicts the future behavior and each of the future chain risks of the first to Nth traffic participants determined as prediction targets by performing a simulation based on the recognition information and the driving subject information in the virtual space, and returns to step ST4 in Fig. 4. More specifically, the simulator 626 predicts the future behavior and risk of the first traffic participant, the future behavior and risk of the second traffic participant according to the behavior of the first traffic participant, the future behavior and risk of the third traffic participant according to at least one of the behaviors of the first and second traffic participants, and the future behavior and risk of the n+1th traffic participant according to the behavior of the first to nth traffic participants (n is any integer between 2 and N-1) by performing a simulation based on the recognition information and the pattern behavior associated with each driving subject of each moving object in the virtual space.

[0102] Next, the chain of risks that can be predicted and avoided by the above-described traffic safety support system 1 and traffic safety support method will be described based on two specific examples.

[0103] <Case Study 1> FIG. 6 is a diagram showing the state of the target traffic area 9 before the time predicted by the prediction unit 62 from the time when the chain risk in Case 1 may occur.

[0104] Fig. 6 shows a case where a first four-wheeled vehicle 2a and a first motorcycle 3a are traveling on the central roadway 51a of two lanes 51a, 51b in a target traffic area 9, and a second four-wheeled vehicle 2b is traveling on the roadway 51b on the sidewalk side. Fig. 6 also shows a case where these moving bodies 2a, 2b, and 3a are all traveling at approximately the same speed from left to right in Fig. 6. Fig. 6 also shows a case where the first four-wheeled vehicle 2a is in the lead, and the first four-wheeled vehicle 2a, the first motorcycle 3a, and the second four-wheeled vehicle 2b are traveling while maintaining appropriate distances between each of them. 6 also shows a case where a group of pedestrians 4a is walking in the opposite direction to the moving direction of the moving bodies 2a, 2b, 3a at a position sufficiently far from the moving bodies 2a, 2b, 3a in the forward direction of the moving bodies 2a, 2b, 3a among the sidewalks 53a adjacent to the roadway 51b in the target traffic area 9. In Case 1, the target traffic area recognition unit 60 of the collaboration support device 6 recognizes the first four-wheeled vehicle 2a, the second four-wheeled vehicle 2b, the first motorcycle 3a, and the group of pedestrians 4a as individual traffic participants, and acquires information on the position, speed, acceleration, moving direction, vehicle type, vehicle class, etc. of each traffic participant and information on the traffic environment around each traffic participant as traffic participant recognition information and traffic environment recognition information.

[0105] In case 1, the rider who is the driver of the first motorcycle 3a is a delivery person whose job is to deliver ordered items to customers, and is driving the first motorcycle 3a to deliver the items to the customer. In case 1, it is assumed that the rider is feeling impatient at the time shown in FIG. 6 because the customer's designated time is approaching. The psychological state of the rider of the first motorcycle 3a is acquired as the driver's driver state information and driver's driver characteristic information by the driver information acquisition unit 61 based on, for example, the rider's schedule information transmitted from the mobile information processing terminal owned by the rider to the collaboration support device 6, and the detection information of the rider state sensor (for example, the driver's pulse, skin potential, etc.) transmitted from the in-vehicle communication device to the collaboration support device 6.

[0106] In addition, in case 1, the driver who is the driving subject of the second four-wheeled vehicle 2b is driving the second four-wheeled vehicle 2b to move to a travel destination together with his / her spouse who is sitting in the passenger seat. In case 1, at the time shown in FIG. 6, the driver and his / her spouse are having a lively conversation about the travel destination, so the driver is not fully concentrating on driving his / her own vehicle and recognizing the traffic participants around his / her own vehicle. The state of the driver of the second four-wheeled vehicle 2b is acquired as the driving subject information and the driving subject characteristic information of the driver by the driving subject information acquisition unit 61 based on, for example, the driver's schedule information transmitted from the mobile information processing terminal owned by the driver to the collaboration support device 6, and the detection information of the driving subject state sensor transmitted from the in-vehicle communication device to the collaboration support device 6 (for example, the driver's line of sight direction, pulse, skin potential, and the presence or absence of conversation, etc.).

[0107] In addition, in case 1, the pedestrian group 4a is composed of three pedestrians, a couple and their child, and these three people are assumed to be moving together in the same direction. Therefore, in case 1, the target traffic area recognition unit 60 recognizes the pedestrian group 4a composed of these three people as one traffic participant. In addition, among the three people constituting the pedestrian group 4a, the wearable terminal worn by the father as a mobile information processing terminal is assumed to be wirelessly connected to the collaboration support device 6 and to be capable of receiving collaboration support information transmitted from the collaboration support device 6.

[0108] Fig. 7 is a diagram showing the chain reaction risk of Case 1 predicted to occur in the future after the prediction time from the time shown in Fig. 6 by the simulation performed by the prediction unit 62 at the time shown in Fig. 6. More specifically, Fig. 7 is a diagram showing the future behavior and chain reaction risk of each prediction target predicted by the prediction unit 62 based on the recognition information and driving subject information acquired by the target traffic area recognition unit 60 and the driving subject information acquisition unit 61 up to the time shown in Fig. 6, with four targets, namely, moving bodies 2a, 2b, 3a and pedestrian group 4a, as prediction targets. Note that in Fig. 7, the behavior of traffic participants who are involved in the chain reaction risk of Case 1 is illustrated by dashed lines.

[0109] 7 shows a case where the high-risk traffic participant identification unit 621 of the prediction unit 62 identifies the first motorcycle 3a, whose rider is estimated to be impatient based on the recognition information and the driving subject information, as a high-risk traffic participant, and the prediction target determination unit 622 of the prediction unit 62 determines the first motorcycle 3a as the first traffic participant, determines the second four-wheeled vehicle 2b following the first traffic participant as the second traffic participant, determines the pedestrian group 4a approaching the front side in the traveling direction of the second traffic participant as the third traffic participant, and further determines the first four-wheeled vehicle 2a, which is the vehicle in front of the first traffic participant, as the fourth traffic participant, and sets these first to fourth traffic participants as prediction targets. In the following, a case will be described where the driving subject information acquisition unit 61 can acquire driving subject information of both the rider of the first motorcycle 3a, which is the first traffic participant, and the driver of the second four-wheeled vehicle 2b, which is the second traffic participant, but the present invention is not limited to this. Although the prediction accuracy is lower compared to when the driving subject information of both of these traffic participants can be acquired, the driving subject information acquisition unit 61 can make a meaningful prediction by the prediction unit 62 as long as the driving subject information of at least one of the first and second traffic participants is acquired.

[0110] 7, the driving ability estimation section 624 of the prediction unit 62 estimates that, among a plurality of ability elements constituting the driving ability of the rider of the first motorcycle 3a recognized as the first traffic participant, two in particular, "judgment ability" and "operation ability", have declined based on the recognition information and the driving subject information. In response to the estimation that the two "judgment ability" and "operation ability" of this rider have declined, the association section 625 of the prediction unit 62 determines, taking into account the traffic environment of this rider, two pattern behaviors, "lane change" and "steering operation", to be associated with the driving subject of this first traffic participant.

[0111] 7, the driving ability estimation unit 624 of the prediction unit 62 estimates that, among the multiple ability elements constituting the driving ability of the driver of the second four-wheeled vehicle 2b recognized as the second traffic participant, two in particular, "cognitive ability" and "operating ability", have declined based on the recognition information and the driving subject information. In response to the estimation that the two "cognitive ability" and "operating ability" of this driver have declined, the association unit 625 of the prediction unit 62 determines, in consideration of the traffic environment of this driver, two pattern behaviors, "lateral recognition delay" and "steering operation", to be associated with the driving subject of this second traffic participant.

[0112] The simulator 626 performs a simulation in a virtual space based on the recognition information, the driving entity information, and the pattern behavior associated with the driving entities of the first and second traffic participants, thereby predicting the future behavior and risk of the first traffic participant, the future behavior and risk of the second traffic participant depending on the behavior of the first traffic participant, and the future behavior and risk of the third traffic participant depending on the behavior of at least one of the first and second traffic participants.

[0113] The driver of the first motorcycle 3a, which is the first traffic participant, is associated with two pattern behaviors: "lane change" and "steering operation." Therefore, the simulator 626 can predict, as the future behavior of this first traffic participant, a trajectory in which the first traffic participant will overtake the first four-wheeled vehicle 2a, which is recognized as the fourth traffic participant, while changing lanes, as shown in FIG. 7.

[0114] In addition, the driver of the second four-wheeled vehicle 2b, which is the second traffic participant, is associated with two pattern behaviors: "delayed lateral recognition" and "steering operation." Therefore, the simulator 626 can predict, as the future behavior of the second traffic participant according to the future behavior of the first traffic participant as described above, a trajectory in which the second traffic participant will recognize the presence of the first traffic participant with a delay, be surprised, and steer in a hurry to proceed onto the sidewalk, as shown in FIG. 7.

[0115] In addition, the simulator 626 can predict, as a future behavior of the third traffic participant according to the behavior of at least one of the first and second traffic participants as described above, a trajectory in which the third traffic participant proceeds along the sidewalk without fully recognizing the presence of the first and second traffic participants, as shown in Fig. 7. As a result, the simulator 626 can predict that there is a possibility that a risk of contact between the second traffic participant and the third traffic participant will occur after the prediction time.

[0116] As described above, the prediction unit 62 can predict the occurrence of a chain reaction risk in which the second traffic participant, surprised by the lane change of the first traffic participant, contacts the third traffic participant after the prediction time at the time shown in Fig. 6, i.e., the time when the third traffic participant is sufficiently distant from the first, second and fourth traffic participants. Furthermore, when the prediction unit 62 predicts the occurrence of a chain reaction risk as shown in Fig. 7, the collaboration support information notification unit 63 notifies the first to third traffic participants, who are the parties involved in the chain reaction risk, of collaboration support information for promoting communication between the traffic participants and recognition of the surrounding traffic environment.

[0117] Here, at the time shown in Figure 6, the collaborative assistance information notification unit 63 notifies the rider of the first motorcycle 3a, who is the first traffic participant, of collaborative assistance information that encourages him / her to recognize traffic participants around his / her vehicle, including the second four-wheeled vehicle 2b behind, and notifies the driver of the second four-wheeled vehicle 2b, who is the second traffic participant, of collaborative assistance information that encourages him / her to recognize traffic participants around his / her vehicle, including the first motorcycle 3a and group of pedestrians 4a in front, and to maintain an appropriate inter-vehicle distance between these surrounding traffic participants, and notifies the group of pedestrians 4a, who is the third traffic participant, of collaborative assistance information that encourages him / her to recognize the moving objects 2a, 2b, 3a ahead in the direction of travel.

[0118] As a result, the driver of the second four-wheeled vehicle 2b recognizes the first motorcycle 3a and the group of pedestrians 4a, and slows down a little to increase the distance between the first motorcycle 3a and the first motorcycle 3a. The rider of the first motorcycle 3a recognizes the second four-wheeled vehicle 2b, and after confirming that a sufficient distance is maintained between the first motorcycle 3a and the second four-wheeled vehicle 2b, can safely and smoothly change lanes. The father, who is part of the group of pedestrians 4a, recognizes the moving bodies 2a, 2b, and 3a ahead of him, and can move his child away from the roadway. The traffic safety support system 1 and the traffic safety support method according to this embodiment can predict the occurrence of the chain risk of the above-mentioned case 1 and avoid it before it happens.

[0119] <Case Study 2> FIG. 8 is a diagram showing the state of the target traffic area 9 before the time predicted by the prediction unit 62 from the time when the chain risk of the case 2 may occur.

[0120] FIG. 8 shows a case where a first four-wheeled vehicle 2a and a first motorcycle 3a are traveling on the central roadway 51a of two lanes 51a and 51b in the target traffic area 9, and a second four-wheeled vehicle 2b is traveling on the roadway 51b on the sidewalk side. FIG. 8 also shows a case where these moving bodies 2a, 2b, and 3a are traveling from left to right in FIG. 8 at approximately the same speed. FIG. 8 also shows a case where the first four-wheeled vehicle 2a is in the lead, and the first motorcycle 3a and the second four-wheeled vehicle 2b are traveling side by side behind it. FIG. 8 also shows a case where a crosswalk 53b is present at a position sufficiently far in front of the moving bodies 2a, 2b, and 3a. FIG. 8 also shows a case where the first four-wheeled vehicle 2a, which is a vehicle traveling in front of the first motorcycle 3a, is slightly larger than a general four-wheeled vehicle. Therefore, it is assumed that the rider of the first motorcycle 3a has a harder time recognizing what is ahead than when a general four-wheeled vehicle is the vehicle in front. Also, at the time shown in Fig. 8, the light color of the traffic light 54a for the roadways 51a and 51b on which these moving bodies 2a, 2b, and 3a are traveling is blue, which means "you may proceed." Also, in Case 2, it is assumed that the light color of the traffic light 54a is scheduled to change sequentially to yellow and red, which means "stop," between the time shown in Fig. 8 and the predicted time.

[0121] In Case 2, the target traffic area recognition unit 60 of the collaboration assistance device 6 recognizes the first four-wheeled vehicle 2a, the second four-wheeled vehicle 2b, and the first motorcycle 3a as individual traffic participants, and acquires information regarding the position, speed, acceleration, direction of movement, vehicle type, vehicle class, etc. of each traffic participant, as well as information regarding the traffic environment around the traffic participants, such as information regarding the position of the crosswalk 53b and traffic light status information of the traffic light 54a for the roadways 51a, 51b, as traffic participant recognition information and traffic environment recognition information.

[0122] In Case 2, the driver who is the driving subject of the first four-wheeled vehicle 2a is not fully able to concentrate on driving the vehicle and recognizing the traffic participants and the traffic environment around the vehicle, for example, for the same reason as the driver of the second four-wheeled vehicle 2b in the above-mentioned Case 1. The state of the driver of the first four-wheeled vehicle 2a is acquired as the driving subject information and driving subject characteristic information of the driver by the driving subject information acquisition unit 61, for example, based on the driver's schedule information transmitted from the mobile information processing terminal owned by the driver to the collaboration support device 6, and the detection information of the driving subject state sensor transmitted from the in-vehicle communication device to the collaboration support device 6 (for example, the driver's line of sight direction, pulse, skin potential, and the presence or absence of conversation, etc.).

[0123] Fig. 9 is a diagram showing the chain reaction risk of Case 2 predicted to occur in the future after the prediction time from the time shown in Fig. 8 by the simulation performed by the prediction unit 62 at the time shown in Fig. 8. More specifically, Fig. 9 shows the future behavior and chain reaction risk of each prediction target predicted by the prediction unit 62 based on the recognition information and driving subject information acquired by the target traffic area recognition unit 60 and the driving subject information acquisition unit 61 up to the time shown in Fig. 8, with the three moving objects 2a, 2b, and 3a as prediction targets. Note that in Fig. 9, the behavior of the first motorcycle 3a and the second four-wheeled vehicle 2b among the traffic participants who are the parties to the chain reaction risk of Case 2 is particularly illustrated by dashed lines.

[0124] 9 shows a case where the high-risk traffic participant identification unit 621 of the prediction unit 62 identifies the first four-wheeled vehicle 2a, which is estimated to be unable to fully recognize the traffic participants and traffic environment around the vehicle based on the recognition information and the driving subject information, as a high-risk traffic participant, and the prediction target determination unit 622 of the prediction unit 62 determines the first four-wheeled vehicle 2a as the first traffic participant, determines the first motorcycle 3a following the first traffic participant as the second traffic participant, and determines the second four-wheeled vehicle 2b running parallel to the second traffic participant as the third traffic participant, and sets these first to third traffic participants as prediction targets. In the following, the driving subject information acquisition unit 61 will be described as being able to acquire the driving subject information of the driver of the first four-wheeled vehicle 2a, which is the first traffic participant, but the present invention is not limited to this. If the driving subject information acquisition unit 61 can acquire driving subject information of at least one of the first and second traffic participants, the prediction unit 62 can make a meaningful prediction.

[0125] 9, the driving ability estimation unit 624 of the prediction unit 62 estimates that, among a plurality of ability elements constituting the driving ability of the driver of the first four-wheeled vehicle 2a recognized as the first traffic participant, two in particular, "cognitive ability" and "operational ability", have declined based on the recognition information and the driving subject information. In addition, in response to the estimation that the two "cognitive ability" and "operational ability" of this driver have declined, the association unit 625 of the prediction unit 62 determines two pattern behaviors, "forward recognition delay" and "deceleration operation", to be associated with the driving subject of this first traffic participant, taking into consideration the traffic environment of this driver (particularly, the timing when the lighting color of the traffic light 54a changes).

[0126] 9, the driving ability estimation unit 624 of the prediction unit 62 estimates that, among the multiple ability elements constituting the driving ability of the rider, the "prediction ability" and the "operation ability" have declined, by grasping based on the recognition information that the first four-wheeled vehicle 2a, which is relatively large, is traveling ahead of the rider of the first motorcycle 3a recognized as the second traffic participant, as shown in FIG. 9. In response to the estimation that the two "prediction ability" and "operation ability" of the rider have declined, the association unit 625 of the prediction unit 62 determines the two "forward recognition delay" and "steering operation" as pattern behaviors to be associated with the driving subject of the second traffic participant, taking into consideration the traffic environment of the rider (particularly, the distance between the vehicle and the vehicle ahead and the vehicle ahead) of the rider.

[0127] The simulator 626 performs a simulation in a virtual space based on the recognition information, the driving entity information, and the pattern behavior associated with the driving entity of the first traffic participant, thereby predicting the future behavior and risk of the first traffic participant, the future behavior and risk of the second traffic participant depending on the behavior of the first traffic participant, and the future behavior and risk of the third traffic participant depending on the behavior of at least one of the first and second traffic participants.

[0128] The driving subject of the first four-wheeled vehicle 2a, which is the first traffic participant, is associated with two pattern behaviors: "delayed recognition of the front" and "deceleration operation." For this reason, the simulator 626 can predict, as the future behavior of this first traffic participant, a trajectory in which the first traffic participant will suddenly decelerate in a panic and stop just before the stop line 53c, by recognizing that the color of the traffic light 54a has changed from green to red slightly before the stop line 53c, as shown in Fig. 9.

[0129] In addition, the driver of the first motorcycle 3a, which is the second traffic participant, is associated with two pattern behaviors, namely, "delayed recognition of the front" and "steering operation." Therefore, the simulator 626 can predict, as the future behavior of the second traffic participant according to the future behavior of the first traffic participant as described above, a trajectory in which the second traffic participant, like the first traffic participant, is unable to recognize that the color of the traffic light 54a has changed from green to red, travels at the same speed as the first traffic participant until a little before the stop line 53c, and steers in a panic in response to the first traffic participant's sudden stop, to avoid the first traffic participant and move onto the roadway 51b on the sidewalk 53a side, as shown in FIG. 9.

[0130] In addition, the simulator 626 can predict a trajectory of deceleration with ample time to spare as a future behavior of the third traffic participant according to at least one of the behaviors of the first and second traffic participants as described above, by recognizing that the color of the traffic light 54a has changed from green to red from a position sufficiently far from the stop line 53c, as shown in Fig. 9. As a result, the simulator 626 can predict that there is a risk of the second traffic participant coming into contact with the third traffic participant after the predicted time.

[0131] As described above, the prediction unit 62 can predict the occurrence of a chain reaction risk in which the second traffic participant, surprised by the sudden stop of the first traffic participant, contacts the third traffic participant after the prediction time at the time shown in Fig. 8, i.e., the time when the first to third traffic participants are sufficiently away from the crosswalk 53b. Furthermore, when the prediction unit 62 predicts the occurrence of a chain reaction risk as shown in Fig. 8, the collaboration support information notification unit 63 notifies the first to third traffic participants, who are the parties involved in the chain reaction risk, of collaboration support information for promoting communication between the traffic participants and recognition of the surrounding traffic environment.

[0132] Here, at the time shown in Figure 8, the collaborative assistance information notification unit 63 notifies the driver of the first four-wheeled vehicle 2a, who is the first traffic participant, of collaborative assistance information that encourages the driver to recognize the traffic environment around the vehicle, including the traffic light 54a in front and the first motorcycle 3a behind, and notifies the rider of the first motorcycle 3a, who is the second traffic participant, of collaborative assistance information that encourages the rider to recognize traffic participants around the vehicle, including the first four-wheeled vehicle 2a in front and the second four-wheeled vehicle 2b to the side, and to maintain an appropriate inter-vehicle distance between these surrounding traffic participants, and notifies the second four-wheeled vehicle 2b, who is the third traffic participant, of collaborative assistance information that encourages the rider to recognize the first motorcycle 3a to the side.

[0133] As a result, the driver of the first four-wheeled vehicle 2a can recognize the crosswalk 53b and traffic light 54a ahead and the first motorcycle 3a behind, and can start decelerating from a position sufficiently away from the stop line 53c so as not to suddenly decelerate, and can safely and smoothly stop his / her vehicle in front of the stop line 53c. Also, the rider of the first motorcycle 3a, while recognizing the presence of the second four-wheeled vehicle 2b on the side, gradually decelerates from a position sufficiently away from the stop line 53c so as to ensure a sufficient distance between the first four-wheeled vehicle 2a ahead and his / her vehicle. Also, by ensuring a sufficient distance between the first four-wheeled vehicle 2a ahead and his / her vehicle, the rider of the first motorcycle 3a can recognize the presence of the traffic light 54a on the other side of the first four-wheeled vehicle 2a, and can start decelerating from a position sufficiently away from the stop line 53c, and can safely and smoothly stop his / her vehicle in front of the first four-wheeled vehicle 2a. Furthermore, by recognizing the first motorcycle 3a beside the driver of the second four-wheeled vehicle 2b, the driver can safely and smoothly stop his / her vehicle before the stop line 53c while maintaining a safe distance between the first motorcycle 3a and his / her vehicle in case the first motorcycle 3a suddenly changes lanes. The traffic safety support system 1 and traffic safety support method according to this embodiment can predict the occurrence of the chain of risks in Case 2 as described above and prevent it from happening.

[0134] The traffic safety support system 1 and the traffic safety support method according to the present embodiment provide the following advantages. (1) In the traffic safety support system 1, the prediction unit 62 predicts the future of multiple traffic participants recognized by the target traffic area recognition unit 60 based on the recognition information on each traffic participant acquired by the target traffic area recognition unit 60 and the driving subject state information correlated with the driving ability of the driving subject of the moving body recognized as a traffic participant. Therefore, the prediction unit 62 can predict the future of multiple traffic participants including the irregular behavior of a specific moving body, taking into account the deterioration of the driving ability of the driving subject of the specific moving body at that time. In addition, the cooperation support information notification unit 63 notifies at least one of the multiple prediction targets based on the prediction results for these prediction targets by the prediction unit 62 of cooperation support information, thereby preventing the risks predicted for these prediction targets from occurring, thereby improving the safety, convenience, and smoothness of traffic.

[0135] Furthermore, when the first and second traffic participants among the first, second and third traffic participants to be predicted are the first and second moving bodies in the target traffic area 9 and the driving subject state information of at least one of the driving subjects of the first and second moving bodies has been acquired, the prediction unit 62 predicts the future behavior of the first traffic participant, the future behavior of the second traffic participant according to the future behavior of the first traffic participant, and the future risk of the third traffic participant according to the future behavior of at least one of the first and second traffic participants, based on the recognition information and the driving subject state information. Furthermore, the collaboration assistance information notification unit 63 notifies at least one of the first to third traffic participants of collaboration assistance information based on the prediction results of the future behaviors of the first and second traffic participants and the prediction results of the future risk of the third traffic participant. This makes it possible to prevent a chain reaction risk that may occur among the multiple traffic participants due to a decrease in the driving ability of at least one of the first and second traffic participants, which may affect the third traffic participant, when three or more traffic participants including the first, second and third traffic participants are involved. Therefore, according to the present invention, it is possible to further improve the safety, convenience and smoothness of traffic.

[0136] (2) When the third traffic participant is viewed as a subject, it is often difficult to predict in advance a chain reaction risk that may occur between the first and second traffic participants other than the third traffic participant and ultimately affect the third traffic participant. For this reason, the third traffic participant often has little time to take action to avoid such a chain reaction risk. In response to this, in the traffic safety support system 1, when the prediction unit 62 predicts the occurrence of a chain reaction risk in the future of the third traffic participant, the cooperative support information notification unit 63 notifies the communication interface of the mobile information processing terminal, the in-vehicle communication device, or the like possessed by the third traffic participant of cooperative support information. This allows the third traffic participant to have time to take action to avoid the chain reaction risk, thereby improving the safety of the third traffic participant.

[0137] (3) In the traffic safety support system 1, when the driver is a human, the driver information acquisition unit 61 acquires driver state information based on time-series data of at least one of the driver's biological information, appearance information, and voice information. By using such driver state information, the prediction unit 62 can appropriately grasp the driving ability of the driver while driving and predict the future behavior of the moving object driven by the driver, thereby predicting various chain risks that may affect the prediction target. Therefore, the traffic safety support system 1 can further improve the safety, convenience, and smoothness of traffic.

[0138] (4) In the traffic safety support system 1, the driver information acquisition unit 61 acquires driver characteristic information on the characteristics of the driver based on at least one of the driver's past driving history and time-dependent state information when the driver is a human. In addition, the prediction unit 62 uses the driver characteristic information of the driver in addition to the recognition information and driver state information to appropriately grasp the driver's driving ability and characteristics while driving, and predicts the future behavior of the moving object driven by the driver, thereby predicting various chain risks that may affect the prediction target. Therefore, the traffic safety support system 1 can further improve the safety, convenience, and smoothness of traffic.

[0139] (5) In the traffic safety support system 1, the target traffic area recognition unit 60 acquires traffic participant recognition information on each traffic participant in the target traffic area 9 and traffic environment recognition information on the traffic environment of each traffic participant in the target traffic area 9. In addition, the prediction unit 62 uses such traffic participant recognition information and traffic environment recognition information to appropriately grasp the traffic environment around each traffic participant and predict the future of the prediction target, thereby predicting various chain risks that may affect the prediction target. Therefore, the traffic safety support system 1 can further improve the safety, convenience, and smoothness of traffic.

[0140] (6) In the traffic safety support system 1, the prediction unit 62 constructs a virtual space simulating the target traffic area 9 by computer, and predicts the future of the prediction target by performing a simulation based on the recognition information and the driver's subject state information in this virtual space. In this way, the prediction unit 62 reproduces each traffic participant in the target traffic area 9 and the traffic environment around them, and monitors events that may occur in the target traffic area 9 from a bird's-eye view, thereby predicting various chain risks that may affect the prediction target. Therefore, the traffic safety support system 1 can further improve the safety, convenience, and smoothness of traffic.

[0141] (7) In the traffic safety support system 1, the behavior estimation unit 623 associates a behavior estimation input including at least the recognition information among the recognition information and the driver's state information with at least one of a plurality of predetermined pattern behaviors of the driver, and the simulator 626 predicts the future of the prediction target by performing a simulation based on the pattern behavior associated by the behavior estimation unit 623 in a virtual space. In the traffic safety support system 1, the behavior that the driver of the moving body may take in the future is predetermined as a pattern behavior, so that the prediction unit 62 can quickly predict the future of the prediction target, and the cooperation support information based on the prediction result by the prediction unit 62 can also be quickly notified, and thus each traffic participant can have time to take action to avoid a chain reaction risk that may occur in the future. Therefore, the traffic safety support system 1 can further improve the safety, convenience, and smoothness of traffic.

[0142] (8) In the traffic safety support system 1, the behavior estimation unit 623 includes a driving ability estimation unit 624 that estimates the decline in the driving ability of the driver for each ability element based on a behavior estimation input including at least recognition information, and an association unit 625 that associates the ability element estimated to be declined by the driving ability estimation unit 624 with at least one of a plurality of predetermined pattern behaviors. As a result, the association unit 625 can quickly determine the pattern behavior from the behavior estimation input, so that each traffic participant can have more time to take action to avoid a chain reaction risk that may occur in the future, as described above. Therefore, the traffic safety support system 1 can further improve the safety, convenience, and smoothness of traffic.

[0143] (9) In the traffic safety support system 1, the driving ability estimation unit 624 divides the driving ability that the driver should have in order to drive a moving object appropriately into at least four ability elements, namely, cognitive ability, predictive ability, judgment ability, and operation ability, and estimates the decline in the driving ability of the driver for each of these four ability elements. This allows the behavior estimation unit 623 to quickly determine an appropriate pattern behavior according to the decline in each ability element, so that each traffic participant can further secure time to take action to avoid a chain reaction risk that may occur in the future, as described above. Therefore, the traffic safety support system 1 can further improve the safety, convenience, and smoothness of traffic.

[0144] (10) In the target traffic area 9, there are actually three or more traffic participants. If all of these traffic participants are the targets of prediction and the chain reaction risk that may occur in a chain reaction as described above is evaluated, the load on the prediction unit 62 may become large. In contrast, in the traffic safety support system 1 according to the present embodiment, the high-risk traffic participant identification unit 621 identifies a traffic participant who is estimated to be likely to take a predetermined chain reaction risk in the future as a high-risk traffic participant from among the multiple traffic participants recognized by the target traffic area recognition unit 60, and the prediction target determination unit 622 determines the high-risk traffic participant as the first traffic participant and two traffic participants extracted from the multiple traffic participants around the first traffic participant as the second and third traffic participants. In this way, the prediction unit 62 can reduce the load on the prediction unit 62 by narrowing down the prediction targets to the high-risk traffic participant and the traffic participants around them, so that the future of the prediction target can be predicted quickly, and thus time can be secured for each traffic participant to take action to avoid a chain reaction risk that may occur in the future. Therefore, according to the present invention, the safety, convenience, and smoothness of traffic can be further improved.

[0145] Although an embodiment of the present invention has 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, the four-wheeled vehicles 2 moving within the target traffic area 9 are all described as being driven by human drivers, but the present invention is not limited thereto. The present invention is also applicable to cases where all or some of the multiple four-wheeled vehicles 2 moving within the target traffic area are automatic drivers driven by non-human computers. In this way, when the driving subject is a computer, the driving subject information acquisition unit 61 can acquire driving subject state information and driving subject characteristic information that are correlated with the driving ability of the driving subject of the automatic driver by acquiring a control signal related to automatic driving control from the vehicle-mounted communication device 24 of the vehicle-mounted device group 20, for example. [Explanation of symbols]

[0146] 1. Traffic safety support system 9. Target traffic area 2…Four-wheeled vehicle (mobile object, transportation participant) 20…In-vehicle equipment group 21...In-vehicle driving assistance device (recognition means) 22...Driver HMI (notification means) 23...Driver status sensor (driver information acquisition means) 24...In-vehicle communication device (recognition means, driving subject information acquisition means, notification means) 25...Portable information processing terminal (recognition means, driving subject information acquisition means, notification means) 3…Motorcycles (mobile objects, transportation participants) 30…In-vehicle equipment group 31...In-vehicle driving assistance device (recognition means) 32…Rider HMI (notification means) 33... Lidar status sensor (means for acquiring driving subject information) 34...In-vehicle communication device (recognition means, driving subject information acquisition means, notification means) 35...Portable information processing terminal (recognition means, driving subject information acquisition means, notification means) 4...Pedestrians (people, traffic participants) 40...Portable information processing terminal (recognition means, notification means) 51…Roadway (traffic environment) 52...Intersection (traffic environment) 53...Sidewalks (traffic environment) 54…Traffic light (traffic environment) 55...Signal control device (recognition means) 56...Infrastructure camera (recognition means) 6…Coordination support device 60...Target traffic area recognition unit (recognition means) 61...Driver information acquisition unit (driver information acquisition means) 62...Prediction unit (prediction means) 621...High-risk traffic participant identification unit (high-risk traffic participant identification means) 622... prediction target determination unit (prediction target determination means) 623... Behavior estimation unit (behavior estimation means) 624...Driving ability estimation unit (driving ability estimation means) 625...Association unit (association means) 626…Simulator 63... Collaborative support information notification unit (notification means) 64…Traffic environment database (recognition means) 65...Driving history database (means for acquiring driving subject information)

Claims

1. A recognition means for recognizing traffic participants as persons or moving objects in a target traffic area and obtaining recognition information about each traffic participant; a driver information acquisition means for acquiring status information correlated with the driving ability of a driver of a moving object recognized as a traffic participant by the recognition means; a prediction means for predicting the future of a plurality of traffic participants recognized by the recognition means based on the recognition information and the state information; A traffic safety support system including: a notification means for notifying support information to at least one of a plurality of targets predicted by the prediction means based on a prediction result by the prediction means, The prediction means includes: When the first and second traffic participants among the first, second and third traffic participants to be predicted are first and second moving bodies in the target traffic area and state information of at least the first moving body is acquired by the driving subject information acquisition means, predicting a future behavior of the first moving body, a future behavior of the second moving body according to the future behavior of the first moving body, and a future risk of the third traffic participant according to the future behaviors of the first and second moving bodies based on the recognition information and the state information; A traffic safety support system characterized in that the notification means notifies the communication interface of the first traffic participant of the support information at the time when the prediction means predicts the occurrence of a future risk for the third traffic participant.

2. A recognition means for recognizing traffic participants as people or moving objects in a target traffic area and acquiring recognition information about each traffic participant; a driver information acquisition means for acquiring status information correlated with the driving ability of a driver of a moving object recognized as a traffic participant by the recognition means; a prediction means for predicting the future of a plurality of traffic participants recognized by the recognition means based on the recognition information and the state information; A traffic safety support system including: a notification means for notifying support information to at least one of a plurality of targets predicted by the prediction means based on a prediction result by the prediction means, The prediction means includes: When the first and second traffic participants among the first, second and third traffic participants to be predicted are first and second moving bodies in the target traffic area and state information of at least the first moving body is acquired by the driving subject information acquisition means, predicting a future behavior of the first moving body, a future behavior of the second moving body according to the future behavior of the first moving body, and a future risk of the third traffic participant according to the future behaviors of the first and second moving bodies based on the recognition information and the state information; A traffic safety support system characterized in that the notification means notifies the communication interface of the third traffic participant of the support information at the time when the prediction means predicts the occurrence of a future risk for the third traffic participant.

3. The traffic safety support system described in claim 1 or 2, characterized in that, when the driving subject is a human, the driving subject information acquisition means acquires the status information based on time-lapse data of at least any of the driving subject's biometric information, appearance information, and voice information while driving.

4. The driving subject information acquisition means, when the driving subject is a human, acquires characteristic information regarding characteristics of the driving subject based on at least one of a past driving history of the driving subject and the state information; 4. The traffic safety support system according to claim 3, wherein the prediction means predicts the future of the prediction target based on the recognition information, the state information, and the characteristic information.

5. The traffic safety support system according to any one of claims 1 to 4, characterized in that the recognition means acquires the recognition information regarding a recognition target including each traffic participant in the target traffic area and a traffic environment of each traffic participant in the target traffic area.

6. The traffic safety support system according to claim 5, characterized in that the prediction means constructs a virtual space simulating the target traffic area by a computer, and predicts the future of the predicted object by performing a simulation based on the recognition information and the status information in the virtual space.

7. The prediction means includes: a behavior estimating means for associating a first input including at least the recognition information of the recognition information and the state information with at least one of a plurality of predetermined pattern behaviors of a driver subject; The traffic safety support system according to claim 6, further comprising: a simulator that predicts the future of the prediction object by performing a simulation in the virtual space based on the pattern behavior associated by the behavior estimation means.

8. The behavior estimation means is a driving ability estimation means for estimating a decline in the driving ability for each ability element based on the first input; The traffic safety support system according to claim 7, further comprising an association means for associating the ability element estimated to be declining by the driving ability estimation means with at least one of the plurality of pattern behaviors.

9. 9. The traffic safety support system according to claim 8, wherein the driving ability is divided into at least four ability elements, namely, a cognitive ability, a predictive ability, a judgment ability, and an operating ability of the driver.

10. The prediction means includes: a high-risk traffic participant identification means for identifying, as a high-risk traffic participant, a traffic participant that is estimated to have a high possibility of performing a predetermined chain risk inducing behavior in the future, from among the multiple traffic participants recognized by the recognition means, based on a second input including at least the recognition information among the recognition information and the state information; The traffic safety support system according to any one of claims 1 to 9, further comprising a prediction target determination means for determining the high-risk traffic participant as the first traffic participant, and determining two persons extracted from a plurality of traffic participants existing around the first traffic participant as the second and third traffic participants.

11. A traffic safety support method for supporting the safety of traffic participants by a computer, comprising: recognizing traffic participants as persons or moving objects in a target traffic area and obtaining recognition information about each traffic participant; acquiring state information correlated with a driving ability of a driving subject of a mobile object recognized as a traffic participant; predicting the future of a plurality of prediction targets determined from a plurality of recognized traffic participants based on the recognition information and the state information; and notifying at least one of the plurality of prediction targets of support information based on a prediction result for the prediction target, In the step of predicting the future of the prediction target, When the first and second traffic participants among the first, second and third traffic participants to be predicted are first and second moving bodies in the target traffic area and status information of at least the first moving body is acquired, predicting a future behavior of the first moving body, a future behavior of the second moving body according to the future behavior of the first moving body, and a future risk of the third traffic participant according to the future behaviors of the first and second moving bodies based on the recognition information and the state information; A traffic safety support method, characterized in that in the step of notifying the support information, the support information is notified to a communication interface of the first traffic participant at a time when a future risk occurrence of the third traffic participant is predicted.

12. A traffic safety support method for supporting the safety of traffic participants by a computer, comprising: recognizing traffic participants as persons or moving objects in a target traffic area and obtaining recognition information about each traffic participant; acquiring state information correlated with a driving ability of a driving subject of a mobile object recognized as a traffic participant; predicting the future of a plurality of prediction targets determined from a plurality of recognized traffic participants based on the recognition information and the state information; and notifying at least one of the plurality of prediction targets of support information based on a prediction result for the prediction target, In the step of predicting the future of the prediction target, When the first and second traffic participants among the first, second and third traffic participants to be predicted are first and second moving bodies in the target traffic area and status information of at least the first moving body is acquired, predicting a future behavior of the first moving body, a future behavior of the second moving body according to the future behavior of the first moving body, and a future risk of the third traffic participant according to the future behaviors of the first and second moving bodies based on the recognition information and the state information; A traffic safety support method, characterized in that in the step of notifying the support information, the support information is notified to a communication interface of the third traffic participant at a time when a future risk occurrence of the third traffic participant is predicted.

13. A recognition means for recognizing traffic participants as persons or moving objects in a target traffic area and acquiring recognition information about each traffic participant; a driver information acquisition means for acquiring status information correlated with the driving ability of a driver of a moving object recognized as a traffic participant by the recognition means; a prediction means for predicting the future of a plurality of traffic participants recognized by the recognition means based on the recognition information and the state information; A traffic safety support system including: a notification means for notifying support information to at least one of a plurality of targets predicted by the prediction means based on a prediction result by the prediction means, The prediction means includes: a behavior estimating means for associating a first input including at least the recognition information of the recognition information and the state information with at least one of a plurality of predetermined pattern behaviors of a driver subject; a simulator that constructs a virtual space simulating the target traffic area by a computer, and predicts the future of the prediction target by performing a simulation based on the recognition information, the state information, and the pattern behavior associated by the behavior estimation means in the virtual space, The simulator includes: When the first and second traffic participants among the first, second and third traffic participants to be predicted are first and second moving bodies in the target traffic area and state information of at least the first moving body is acquired by the driving subject information acquisition means, A traffic safety support system characterized by predicting, by performing the simulation, the future behavior of the first moving body, the future behavior of the second moving body depending on the future behavior of the first moving body, and the future risk of the third traffic participant depending on the future behavior of at least one of the first and second moving bodies.

Images