Ontology update device, vehicle, and ontology update method

Abstract

An ontology update device according to one embodiment of the present invention is provided with a control unit capable of updating an ontology. The control unit is capable of executing the following two steps. (1) A step for determining the degree of similarity between the surrounding situation of the first vehicle and the dangerous situation described in the ontology, and determining that the surrounding situation is not described in the ontology when it is determined that the degree of similarity is low. (2) a determination is made as to whether there is a danger around the first vehicle on the basis of data obtained from a device mounted on the first vehicle when the surrounding situation is acquired, and if it is determined that there is a danger around the first vehicle as a result, the surrounding situation is associated with the danger and added to the main body, and the surrounding situation is determined to have a danger around the first vehicle. And updating the ontology.

Description

Technical Field

[0001] The invention relates to a body updating device, a vehicle and a body updating method. Background Art

[0002] Technologies for assisting the driving of a vehicle taking into account the dangers existing around the vehicle are known. For example, Patent Document 1 discloses a technology for warning a driver who does not comply with the traffic rules described in the ontology. In addition, Patent Document 2 discloses a technology for predicting a sudden appearance in front of a vehicle based on the traffic rules and / or inference rules described in the ontology.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent No. 5932984

[0006] Patent document 2: Japanese Patent No. 6978313. Summary of the invention

[0007] The main body update device according to the first aspect of the present invention includes a control unit capable of updating the main body. The control unit can execute the following two steps.

[0008] (A1) A step of determining the degree of similarity between the surrounding condition of the first vehicle and the dangerous condition recorded in the main body, and when the result of determining that the degree of similarity is low, determining that the surrounding condition is not recorded in the main body.

[0009] (A2) A step of determining whether there are dangerous phenomena around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there are dangerous phenomena around the first vehicle, associating the surrounding conditions with the dangerous phenomena and adding them to the main body, thereby updating the main body.

[0010] A vehicle according to a second aspect of the present invention includes a storage unit storing a main body and a control unit capable of updating the main body. The control unit can execute the following two steps.

[0011] (B1) A step of determining the degree of similarity between the surrounding conditions of the first vehicle and the dangerous conditions recorded in the main body, and when the degree of similarity is determined to be low, determining that the surrounding conditions are not recorded in the main body.

[0012] (B2) A step of determining whether there are dangerous phenomena around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired. When it is determined that there are dangerous phenomena around the first vehicle, the surrounding conditions are associated with the dangerous phenomena and added to the main body, thereby updating the main body.

[0013] A driving assistance method according to a third aspect of the present invention includes the following (C1) and (C2).

[0014] (C1) A step of determining the degree of similarity between the surrounding condition of the first vehicle and the dangerous condition recorded in the main body, and when the result of determining that the degree of similarity is low, determining that the surrounding condition is not recorded in the main body.

[0015] (C2) A step of determining whether there are dangerous phenomena around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there are dangerous phenomena around the first vehicle, associating the surrounding conditions with the dangerous phenomena and adding them to the main body, thereby updating the main body. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are provided to provide a further understanding of the present invention, and are incorporated into and constitute a part of this specification. The accompanying drawings illustrate one embodiment and together with the description serve to explain the principle of the present invention.

[0017] Figure 1 It is a diagram showing a schematic configuration example of a travel control system according to an embodiment of the present invention.

[0018] Figure 2 Yes means Figure 1 A diagram showing an example of inference rules described in an ontology DB.

[0019] Figure 3 Yes means Figure 1 A diagram showing an example of traffic regulations described in the ontology DB.

[0020] Figure 4 Yes means Figure 1 An example of a road concept described in the ontology DB.

[0021] Figure 5 1 is a diagram showing an example of a traffic condition and a scene of a dangerous situation A.

[0022] Figure 6 It means in Figure 5 A diagram showing how AEB works under different traffic conditions.

[0023] Figure 7 It means in Figure 5 A diagram showing how ABS works under different traffic conditions.

[0024] Figure 8 It means in Figure 5 AES operation diagram under different traffic conditions.

[0025] Fig. 9 It means in Figure 5 Figure 2 shows how VDC warning works under different traffic conditions.

[0026] Fig.10 It means in Figure 5 A diagram showing the airbag operation under different traffic conditions.

[0027] Fig.11 Yes means Figure 5 FIG. 1 is a diagram showing an example of a driving assistance sequence under traffic conditions.

[0028] Fig.12 This is a diagram showing an example of the update order of the main body.

[0029] Fig.13 This is a diagram showing a modified example of the update order of the main body.

[0030] Fig.14 This is a diagram showing a modified example of the update order of the main body. DETAILED DESCRIPTION

[0031] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0032] Hereinafter, several exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that the following description shows a specific example of the present invention and shall not be construed as limiting the present invention. For example, each element including numerical values, shapes, materials, components, positions of each component, and connection methods of each component is only an example and shall not be construed as limiting the present invention. In addition, in the following exemplary embodiments, constituent elements not recorded in the independent claims based on the highest concept of the present invention are arbitrary and can be set as needed. The accompanying drawings are schematic and are not intended to be illustrated according to the original dimensions. In the entirety of this specification and the accompanying drawings, the same reference symbol is marked for constituent elements having substantially the same function and substantially the same structure and repeated descriptions are omitted. In addition, constituent elements that are not directly related to an embodiment of the present invention are not illustrated in the accompanying drawings.

[0033] <1. Background>

[0034] In recent years, in vehicles such as automobiles, the development of automatic driving control technology that allows the vehicle to automatically travel without the need for a driver's driving operation has been promoted. In addition, various schemes for driving assistance devices that use such automatic driving control technology to perform various controls for assisting the driver's driving operation have been proposed and are widely used in practice. For example, patent documents 1 and 2 disclose technologies related to such driving assistance devices.

[0035] Patent document 1 discloses a technology for warning drivers who do not comply with traffic rules described in the ontology. Patent document 2 discloses a technology for suddenly appearing in front of a vehicle based on traffic rules and / or inference rules described in the ontology. However, in the inventions described in each of Patent documents 1 and 2, there is a problem that inference cannot be established in rules that are not described in the ontology.

[0036] Therefore, the inventors of the present application have made intensive studies and have come up with a technology that enables inference to be established even in an inference rule that is not described in the body. A driving control system for realizing this technology will be described in detail below.

[0037] <2. Implementation Method>

[0038] [Configuration example]

[0039] Figure 1 FIG. 1 is a diagram showing a schematic configuration example of a driving control system 1 according to an embodiment of the present invention. Figure 1 As shown, the travel control system 1 includes a travel control device 10, each of which is mounted on a plurality of vehicles, and a control device 200, which is provided in a network environment NW where the plurality of travel control devices 10 are connected via wireless communication. The travel control device 10 corresponds to a specific example of a "main body update device" according to an embodiment of the present invention.

[0040] The control device 200 sequentially integrates and updates the road map information transmitted from the driving control device 10 of each vehicle, and transmits the updated road map information to each vehicle. The control device 200 includes, for example, a road map information integration ECU 201 and a transceiver 202 .

[0041] The road map boundary information integration_ECU 201 integrates the road map information collected from multiple vehicles through the transceiver 202, and sequentially updates the road map information around the vehicle on the road. The road map information is composed of, for example, a dynamic map, and has static information and quasi-static information that mainly constitutes road information, and quasi-dynamic information and dynamic information that mainly constitutes traffic information.

[0042] Static information constituting road information is composed of information that requires an update frequency of less than one month, such as roads and / or structures on the roads, structures around the roads, lane information, road surface information, permanent restriction information, etc. "Roads" include, for example, the location and shape of roads, intersections, and road attributes (for example, national roads, provincial roads, municipal roads, private roads, priority roads, non-priority roads, general roads, and expressways). "Structures on roads" include, for example, traffic signs, traffic lights, traffic corner mirrors, overpasses, etc. "Structures around roads" include, for example, various buildings, parks, etc.

[0043] The quasi-static information constituting the road information is constituted by information requiring an update frequency within one hour, such as traffic restriction information due to road construction and / or events, wide-area weather information, and congestion forecasts.

[0044] The quasi-dynamic information that constitutes traffic information is composed of information that requires an update frequency of less than 1 minute, such as actual congestion conditions and / or driving restrictions at the observation time, fallen objects and / or obstacles, temporary driving obstructions, actual accident conditions, narrow-area weather information, etc.

[0045] The dynamic information constituting the traffic information is composed of information that requires an update frequency of 1 second, such as information transmitted / exchanged between moving bodies and / or information on currently displayed signals, information on pedestrians / bicycles at intersections, and information on vehicles traveling on the road. Such road map information is maintained / updated in a cycle until the next information is received from each vehicle, and the updated road map information is appropriately transmitted to each vehicle via the transceiver 202.

[0046] The driving control device 10 has a driving environment recognition unit 11 and a positioning unit 12 as units for recognizing the driving environment around the vehicle. In addition, the driving control device 10 has a driving control unit (hereinafter referred to as "driving_ECU") 21, an engine control unit (hereinafter referred to as "E / G_ECU") 22, a power steering control unit (hereinafter referred to as "PS_ECU") 23, a brake control unit (hereinafter referred to as "BK_ECU") 24, and a body control unit (hereinafter referred to as "body_ECU") 25. These control units 21 to 25 are connected to the driving environment recognition unit 11 and the positioning unit 12 via an in-vehicle communication line such as CAN (Controller Area Network).

[0047] The driving_ECU 21 controls the vehicle, for example, according to the driving mode. As driving modes, for example, a manual driving mode and a driving control mode can be listed. The manual driving mode refers to a driving mode that needs to be controlled by the driver, for example, a driving mode in which the vehicle is driven according to driving operations such as steering, acceleration and braking performed by the driver. The driving control mode refers to a driving mode that assists the driver in the driving operation performed by the driver in order to improve the safety of pedestrians and / or vehicles around the vehicle (the vehicle). In the driving control mode, for example, when the vehicle (the vehicle) approaches an intersection, the driving_ECU 21 can predict the behavior of a driving vehicle or a parked vehicle (hereinafter referred to as a "target vehicle") on a road that intersects the intersection. When the predicted result is that the target vehicle is likely to enter the intersection, for example, a warning and / or a warning to the driver is performed, and further a hazard avoidance control such as braking is performed. The detailed processing content in the driving control mode will be described in detail later.

[0048] A throttle actuator 26 is connected to the output side of the E / G_ECU 22. The throttle actuator 26 is a device that opens and closes the throttle valve of the electronically controlled throttle provided in the throttle body of the engine. The E / G_ECU 22 controls the operation of the throttle actuator 26 by outputting a drive signal to the throttle actuator 26. The throttle actuator 26 opens and closes the throttle valve based on the drive signal from the E / G_ECU 22 to adjust the intake air flow rate, thereby generating a desired engine output.

[0049] The electric power steering motor 27 is connected to the output side of the PS_ECU 23. The electric power steering motor 27 is a device that uses the rotational force of the motor to impart steering torque to the steering mechanism. The PS_ECU 23 controls the operation of the electric power steering motor 27 by outputting a drive signal to the electric power steering motor 27. In automatic driving, the electric power steering motor 27 performs lane keeping driving control to maintain driving in the current driving lane and lane change control to move the vehicle to an adjacent lane (lane change control for overtaking control, etc.) based on the drive signal from the PS_ECU 23.

[0050] The output side of BK_ECU24 is connected to a brake actuator 28. The brake actuator 28 adjusts the brake fluid pressure supplied to the wheel cylinder provided at each wheel. BK_ECU24 controls the operation of the brake actuator 28 by outputting a drive signal to the brake actuator 28. The brake actuator 28 generates a braking force on each wheel using the wheel cylinder based on the drive signal from BK_ECU24, thereby forcibly decelerating the vehicle.

[0051] The body_ECU 25 is connected to a body database 29 . The body database 29 is a database written in OWL (Web Ontrogy Language) and stored in a large-capacity storage medium such as HDD. The body_ECU 25 reads data from the body database 29 or updates data in the body database 29 under control from the travel_ECU 21 .

[0052] The ontology database 29 has, for example, Figure 2 to Figure 4 The conceptually embodied ontological data structure of the inference rule 28A, traffic rules 28B, and traffic information 28C shown. In the inference rule 28A, multiple dangerous conditions (A, B, ..., S) that may exist around the vehicle are described in the form of a scene. In the scene, an identifier is assigned to each vehicle that exists around the vehicle, and the position and / or speed of each vehicle corresponds to each vehicle. In the scene, the driving lane and / or its type of each vehicle is also corresponded to each vehicle, and traffic rules and / or traffic information are added. Traffic rules refer to rules that traffic participants must follow in order to participate in traffic in a rule-abiding manner, for example, rules for road information collected by the road map boundary information integration ECU201. Traffic information refers to, for example, traffic information collected by the road map boundary information integration ECU201. In the inference rule 28A, each dangerous condition is further corresponded to a dangerous phenomenon that can occur under the dangerous condition. As a dangerous phenomenon, for example, a traffic participant suddenly appears from a blind spot. In the inference rule 28A, the dangerous situation (scenario) is described as a condition item, and the dangerous phenomenon is described as a result item. In the traffic rule 28B, the rules for the road information collected by the road map boundary information integration ECU201 are described. In the traffic information 28C, the traffic information collected by the road map boundary information integration ECU201 is described. The traffic rule 28B and the traffic information 28C have the function of serving as the background knowledge required for inferring the dangerous phenomenon based on the scenario.

[0053] The driving environment recognition unit 11 is fixed, for example, to the upper center of the inner front part of the vehicle and includes an onboard camera (stereo camera) composed of a main camera 11a and a sub-camera 11b, an image processing unit (IPU) 11c, and a driving environment detection unit 11d.

[0054] The main camera 11a and the sub-camera 11b are autonomous sensors that sense the actual space around the vehicle. The main camera 11a and the sub-camera 11b are disposed, for example, at left-right symmetrical positions across the center of the vehicle in the width direction, and can capture stereoscopic images of the front of the vehicle from different perspectives.

[0055] The IPU 11 c can generate a distance image obtained from the amount of deviation of the position of the corresponding object based on a pair of stereo images of the front of the vehicle acquired by capturing using the main camera 11 a and the sub-camera 11 b .

[0056] The driving environment detection unit 11d can, for example, determine the lane dividing lines that divide the road around the vehicle based on the distance image received from the IPU 11c. The driving environment detection unit 11d can also, for example, determine the road curvature [1 / m] of the dividing lines that divide the driving road (driving lane) on which the vehicle is traveling on the left and right, and the width between the left and right dividing lines (vehicle width). The driving environment detection unit 11d can also, for example, perform predetermined pattern matching on the distance image to detect lanes and / or three-dimensional objects such as structures that exist around the vehicle.

[0057] Here, in the detection of the three-dimensional object in the driving environment detection unit 11d, for example, the type of the three-dimensional object, the distance to the three-dimensional object, the speed of the three-dimensional object, the relative speed between the three-dimensional object and the vehicle (the vehicle), etc. are detected. For example, the three-dimensional object as the detection object can be listed as a signal, an intersection, a road sign, a stop line, another vehicle, a pedestrian, various buildings, etc. The driving environment detection unit 11d can output the information of the detected three-dimensional object to the driving_ECU 21, for example.

[0058] The positioning unit 12 is a device for estimating the position of the vehicle on the road map (the vehicle's position), and has a positioning operation unit 13 for estimating the vehicle's position. The input side of the positioning operation unit 13 is connected to the sensor type required for estimating the vehicle's position (the vehicle's position). As such sensor types, for example, there are an acceleration sensor 14, a vehicle speed sensor 15, a gyro sensor 16, a GNSS receiver 17, etc. The acceleration sensor 14 can detect the longitudinal acceleration of the vehicle. The vehicle speed sensor 15 can detect the speed of the vehicle. The gyro sensor 16 can detect the angular velocity or angular acceleration of the vehicle. The GNSS receiver 17 can receive positioning signals sent from multiple positioning satellites. In addition, a transceiver 18 is connected to the positioning operation unit 13, and the transceiver 18 is used to send and receive information between the control device 200 and between other vehicles.

[0059] In addition, the positioning operation unit 13 is connected to a high-precision road map database 19. The high-precision road map database 19 is a large-capacity storage medium such as an HDD, and stores high-precision road map information (dynamic map). The high-precision road map information, for example, has static information and quasi-static information that mainly constitute road information, and quasi-dynamic information and dynamic information that mainly constitute traffic information, similar to the road map information included in the road map information integration ECU 201.

[0060] The positioning calculation unit 13 includes, for example, a map information acquisition unit 13 a , a vehicle position estimation unit 13 b , and a running environment recognition unit 13 c .

[0061] The vehicle position estimation unit 13b can acquire the position coordinates of the vehicle (the vehicle itself) based on the positioning signal received by the GNSS receiver 17. In addition, the vehicle position estimation unit 13b can map match the acquired position coordinates on the route map information to estimate the position of the vehicle on the road map. The map information acquisition unit 13a can acquire map information within a predetermined range including the vehicle (the vehicle itself) from the map information stored in the high-precision road map database 19 based on the position coordinates of the vehicle (the vehicle itself) acquired by the vehicle position estimation unit 13b.

[0062] In an environment such as driving in a tunnel where the sensitivity of the GNSS receiver 17 is reduced and it is impossible to receive effective positioning signals from the positioning satellite, the vehicle position estimation unit 13b can switch to autonomous navigation that estimates the vehicle position based on the vehicle speed detected by the vehicle speed sensor 15, the angular velocity detected by the gyro sensor 16, and the longitudinal acceleration detected by the acceleration sensor 14, thereby estimating the vehicle position on the road map.

[0063] If the vehicle position estimation unit 13b estimates the position of the vehicle (host vehicle position) on the road map based on the positioning signal received by the GNSS receiver 17 or the information detected by the gyro sensor 16, etc. as described above, it can determine the road type of the road on which the vehicle (host vehicle) is traveling based on the estimated host vehicle position on the road map.

[0064] The driving environment recognition unit 13c can update the road map information stored in the high-precision road map database 19 to the latest state using the road map information acquired through external communication (road-to-vehicle communication and vehicle-to-vehicle communication) via the transceiver 18. This information update is performed not only on static information, but also on quasi-static information, quasi-dynamic information, and dynamic information. Thus, the road map information is configured to include road information and traffic information acquired through communication with the outside of the vehicle, and to update the information of mobile bodies such as vehicles traveling on the road in real time.

[0065] The driving environment recognition unit 13c can verify the road map information based on the driving environment information recognized by the driving environment recognition unit 11, and update the road map information stored in the high-precision road map database 19 to the latest state. This information update is performed not only on static information, but also on quasi-static information, quasi-dynamic information, and dynamic information. In this way, the information of mobile objects such as vehicles traveling on the road recognized by the driving environment recognition unit 11 is updated in real time.

[0066] Then, the updated road map information is transmitted to the control device 200 and the surrounding vehicles of the vehicle (host vehicle) through the road-to-vehicle communication and vehicle-to-vehicle communication via the transceiver 18. In addition, the driving environment recognition unit 13c can output the map information of a predetermined range including the host vehicle position estimated by the vehicle position estimation unit 13b in the updated road map information together with the host vehicle position (vehicle position information) to the driving_ECU 21.

[0067] The travel control device 10 further includes a driving assistance system 31. The driving assistance system 31 includes, for example, an AEB (Autonomous Emergency Braking) system, an AES (Automatic Emergency Steering) system, an ABS (Anti-lock Brake System), a VDC (Vehicle Dynamics Control) system, and an airbag system.

[0068] The AEB system detects the preceding vehicle and / or the obstacle ahead, and performs braking control on behalf of the driver when it determines that a collision with the preceding vehicle and / or the obstacle is unavoidable. The AEB system outputs an AEB Level 1 braking operation flag if AEB Level 1 braking is performed, and outputs an AEB Level 2 braking operation flag if AEB Level 2 braking is performed. If the AEB system is in operation, the AEB system outputs an AEB warning flag.

[0069] The AES system is a system that detects a preceding vehicle and / or an obstacle ahead and performs steering control to avoid a collision with the detected preceding vehicle and / or obstacle. The AES system outputs an AES operation flag when performing steering control.

[0070] ABS is a system that performs braking control to prevent tires from locking when the driver applies emergency braking. When ABS performs braking control, it outputs an ABS operation flag.

[0071] The VDC system is a system for controlling the traction of the vehicle. The VDC system outputs a VDC warning sign when the vehicle reaches the limit of traction.

[0072] The airbag system is a system that mitigates the impact on the driver's head caused by collision with the steering wheel, dashboard, front windshield, etc. when the vehicle collides with the vehicle ahead and / or an obstacle in front. If the airbag is activated, the airbag system outputs an airbag activation flag.

[0073] Next, the inference rule 28A will be described in detail. Figure 5This is an example of a traffic condition and a scenario representing a dangerous situation A included in the inference rule 28A.

[0074] In dangerous situation A, it is assumed that the first vehicle (the vehicle itself) 100a is traveling on a single-lane road. The first vehicle 100a is equivalent to a specific example of the "first vehicle" of one embodiment of the present invention. The single-lane road is composed of a driving lane L1 on which the first vehicle 100a is traveling and an opposite lane L2 arranged along the driving lane L1 across a center line. On the single-lane road, an unsignalized intersection CL is arranged in front of the first vehicle 100a. For the single-lane road, the relationship between the roads that intersect with the single-lane road at the unsignalized intersection CL makes it a priority road Lm. That is, the first vehicle 100a is traveling on the priority road Lm.

[0075] On the other hand, the road intersecting the priority road Lm at the unsignalized intersection CL becomes a non-priority road Ls due to the relationship with the priority road Lm. On the non-priority road Ls, the second vehicle (dangerous vehicle) 100b travels toward the unsignalized intersection CL. There is no signal at the unsignalized intersection CL.

[0076] The driver of the first vehicle 100a recognizes that the first vehicle 100a is traveling on the priority road Lm. Therefore, the first vehicle 100a is about to enter the unsignalized intersection CL without decelerating. At this time, in the non-priority road Ls, the second vehicle 100b is traveling toward the unsignalized intersection CL. However, for the driver of the first vehicle 100a, the second vehicle 100b enters the blind spot caused by the fifth vehicle 100e traveling in the opposite lane L2, and the driver of the first vehicle 100a does not recognize the existence of the second vehicle 100b. The fourth vehicle 100d is traveling in front of the first vehicle 100a. The fourth vehicle 100d is traveling toward the unsignalized intersection CL while decelerating. In addition to the fifth vehicle 100e, there is a third vehicle 100c in the opposite lane L2. The third vehicle 100c stops in front of the unsignalized intersection CL. The driver of the second vehicle 100b recognizes the existence of the fourth vehicle 100d that is decelerating and the third vehicle 100c that is stopping. However, since the first vehicle 100a exists in the blind spot caused by the fifth vehicle 100e for the driver of the second vehicle 100b, the existence of the first vehicle 100a is not recognized. Therefore, the driver of the second vehicle 100b attempts to pass through the unsignalized intersection CL immediately after the fourth vehicle 100d passes through the unsignalized intersection CL. Under such traffic conditions, the possibility of a collision accident when the first vehicle 100a and the second vehicle 100b meet at the unsignalized intersection CL is high.

[0077] Such a scenario of the dangerous situation A is stored in the inference rule 28A. In the inference rule 28A, for example, the following contents are described in the scenario of the dangerous situation A.

[0078] ~Scene of Dangerous Situation A~

[0079] Priority road Lm and non-priority road Ls intersect at the unsignalized intersection CL

[0080] The first vehicle 100a is traveling on the priority road Lm and is heading for the unsignalized intersection CL

[0081] The second vehicle 100b is traveling on the non-priority road Ls and is heading for the unsignalized intersection CL

[0082] · From the first vehicle 100a, the second vehicle 100b is hidden in the blind spot

[0083] The third vehicle 100c stops in front of the unsignalized intersection CL in the opposite lane L2 of the first vehicle 100a.

[0084] The fourth vehicle 100d is traveling ahead of the first vehicle 100a and is decelerating.

[0085] In the dangerous situation A, when the driver of the first vehicle 100a performs a braking operation, for example, Figure 6 The AEB system of the first vehicle 100a shown in the figure is working and an AEB working sign (e.g., an AEB level 1 braking sign, an AEB level 2 braking sign, or an AEB warning sign) is output from the AEB system. Alternatively, in the dangerous situation A, when the driver of the first vehicle 100a performs a braking operation, for example, Figure 7 The ABS system of the first vehicle 100a is shown to be operating and an ABS operating flag is outputted from the ABS system.

[0086] Alternatively, in the dangerous situation A, when the driver of the first vehicle 100a performs a driving operation, for example, Figure 8 The AES system of the first vehicle 100a shown in FIG. 1 is operating and an AES operating flag is output from the AES system. Alternatively, in a dangerous situation A, when the driver of the first vehicle 100a performs a driving operation, for example, Fig. 9 The VDC system of the first vehicle 100a shown is operated and a VDC warning sign is output from the VDC system. Alternatively, in a dangerous situation A, for example, Fig.10 It is shown that the first vehicle 100a collides with the second vehicle 100b, whereby the airbag system is activated and an airbag activation flag is outputted from the airbag system.

[0087] In this way, when the AEB operation flag, ABG operation flag, AES operation flag, VDC warning flag or airbag operation flag is output, the possibility of a collision accident when the first vehicle 100a and the second vehicle 100b meet at the unsignalized intersection CL is high. In this specification, a phenomenon with a high probability of occurring in the dangerous situation A is referred to as a dangerous phenomenon. In the inference rule 28A, for example, the scene of the dangerous situation A is associated with a dangerous phenomenon with a high probability of occurring in the dangerous situation A.

[0088] (Driving Assistance Sequence)

[0089] Next, refer to Fig.11 The driving assistance procedure in the driving control system 1 will be described. Fig.11 1 is a diagram showing an example of a driving assistance sequence in the driving control system 1 .

[0090] First, the stereo camera installed in the first vehicle 100a captures the front of the first vehicle 100a and outputs the stereo image thus obtained to the IPU11c. The IPU11c generates a distance image based on the stereo image acquired by the stereo camera and outputs it to the driving environment detection unit 11d. The driving environment detection unit 11d performs predetermined pattern matching on the distance image generated by the IPU11c, and detects the priority road Lm, the driving lane L1, the oncoming lane L2, the non-priority road Ls, the unsignalized intersection CL, the vehicles on the priority road Lm (for example, 100a, 100c~100e), and the vehicles on the non-priority road Ls (for example, 100b).

[0091] Next, the driving environment recognition unit 13c uses the road map information acquired from external communication to detect the priority road Lm, the driving lane L1, the oncoming lane L2, the non-priority road Ls, the unsignalized intersection CL, the vehicles on the priority road Lm (e.g., 100a, 100c to 100e), and the vehicles on the non-priority road Ls (e.g., 100b). Here, it is assumed that the road map information acquired from external communication includes the information of the vehicles on the priority road Lm (e.g., 100a, 100c to 100e), and the information of the vehicles on the non-priority road Ls (e.g., 100b). At this time, the driving environment recognition unit 13c can detect the vehicles on the priority road Lm (e.g., 100a, 100c to 100e), and the vehicles on the non-priority road Ls (e.g., 100b) using the road map information acquired from external communication.

[0092] The vehicle position estimating unit 13b acquires the position coordinates of the first vehicle 100a based on the positioning signal received by the GNSS receiver 17. The vehicle position estimating unit 13b also acquires the vehicle speed detected by the vehicle speed sensor 15 (the speed of the first vehicle 100a).

[0093] Next, the driving_ECU 21 obtains road information Da and vehicle information Db based on various information obtained from the driving environment detection unit 11d, the vehicle position estimation unit 13b, and the driving environment recognition unit 13c (step S101). Here, the road information Da includes information on the priority road Lm, the driving lane L1, the oncoming lane L2, the non-priority road Ls, and the unsignalized intersection CL detected by the driving environment detection unit 11d or the driving environment recognition unit 13c. The vehicle information Db includes information on the speed (vehicle speed) of the first vehicle 100a obtained from the vehicle position estimation unit 13b, and information on vehicles (e.g., 100a, 100c to 100f) on the priority road Lm and vehicles (e.g., 100b) on the non-priority road Ls obtained from the driving environment detection unit 11d or the driving environment recognition unit 13c.

[0094] Next, the driving_ECU 21 outputs the road information Da and the vehicle information Db to the main body_ECU 25. If the main body_ECU 25 obtains the road information Da and the vehicle information Db from the driving_ECU 21, it creates a scene of the surrounding conditions of the first vehicle 100a based on the acquired road information Da and the vehicle information Db (step S102). For example, the main body_ECU 25 creates the scene of the surrounding conditions of the first vehicle 100a at a predetermined period (for example, 0.5 seconds) from the time (remaining time) until the first vehicle 100a reaches the unsignalized intersection CL is less than a predetermined threshold.

[0095] The main body_ECU 25 determines the similarity between the surrounding conditions (scenario) of the first vehicle 100a and each dangerous situation (scenario) recorded in the main body database 29 (step S103). At this time, the main body_ECU 25 determines the similarity based on, for example, the instance generation ratio of the surrounding conditions (scenario) of the first vehicle 100a and each dangerous situation (scenario) recorded in the main body database 29.

[0096] The main body_ECU 25 determines that the similarity is high when the example generation ratio is greater than a predetermined threshold value, for example (step S104; Yes). At this time, the main body_ECU 25 determines that the surrounding conditions (scenes) of the first vehicle 100a are recorded in the main body database 29. On the other hand, the main body_ECU 25 determines that the similarity is low when the example generation ratio is less than a predetermined threshold value, for example (step S104; No). At this time, the main body_ECU 25 determines that the surrounding conditions (scenes) of the first vehicle 100a are not recorded in the main body database 29.

[0097] When the body_ECU 25 determines that the similarity is high, it notifies the driver of the occurrence of a dangerous phenomenon corresponding to the dangerous situation (scenario) determined to be highly similar (step S105). For example, the body_ECU 25 generates alarm sound data and outputs it to the speaker of the first vehicle 100a, and the speaker of the first vehicle 100a outputs a sound based on the input alarm sound data.

[0098] When the body_ECU 25 determines that the similarity is high, it also outputs a control signal indicating that the possibility of the occurrence of the dangerous phenomenon corresponding to the dangerous situation (scenario) determined to be high in the similarity is high to the driving_ECU 21. When the driving_ECU 21 receives such a control signal from the body_ECU 25, it performs driving control for avoiding the dangerous phenomenon corresponding to the dangerous situation (scenario) determined to be high in the similarity (step S106).

[0099] (Update order of the main body)

[0100] Next, refer to Fig.12 The updating procedure of the main body in the travel control system 1 will be described. Fig.11 1 is a diagram showing an example of a driving assistance sequence in the driving control system 1 .

[0101] When the body_ECU 25 determines that the similarity is low, it determines whether a predetermined flag of the driving assistance system 31 is output (step S107). The body_ECU 25 determines, for example, whether an AEB level 1 brake operation flag, an AEB level 2 brake operation flag, an AES operation flag, an ABS operation flag, a VDC warning flag, or an airbag operation flag is output. The body_ECU 25 uses the predetermined flag of the driving assistance system 31 to determine whether the possibility of a dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a is high (step S108). The body_ECU 25 determines, for example, whether an AEB level 1 brake operation flag, an AEB level 2 brake operation flag, an AES operation flag, an ABS operation flag, a VDC warning flag, or an airbag operation flag is output to determine whether the possibility of a dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a is high. It should be noted that when the predetermined flag of the driving assistance system 31 is not output, it means that the driving assistance system 31 is not working.

[0102] The main body_ECU25 infers the dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a based on the surrounding conditions (scenes) of the first vehicle 100a and the traffic rules 28B and traffic information 28C of the main body database 29. Then, when the predetermined flag of the driving assistance system 31 is output, the main body_ECU25 determines that the possibility of the dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a occurring is high (step S108; yes). On the other hand, when the predetermined flag of the driving assistance system 31 is not output, the main body_ECU25 determines that the possibility of the dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a occurring is low (step S108; no).

[0103] When it is determined that the possibility of the dangerous phenomenon corresponding to the surrounding conditions (scenario) of the first vehicle 100a occurring is high, the main body_ECU25 associates (corresponds) the surrounding conditions (scenario) of the first vehicle 100a and the dangerous phenomenon obtained by reasoning, and adds them to the main body database 29. In this way, the main body_ECU25 updates the main body database 29 by adding a set of new inference rules 28A with the surrounding conditions (scenario) of the first vehicle 100a as a condition item and the dangerous phenomenon obtained by reasoning as a result item to the main body database 29 (step S109). At the moment when it is determined that there is a dangerous phenomenon around the first vehicle 100a, the main body_ECU25 starts updating the main body database 29. On the other hand, when it is determined that the possibility of the dangerous phenomenon corresponding to the surrounding conditions (scenario) of the first vehicle 100a occurring is low, the main body_ECU25 does not update the main body database 29.

[0104] [Effect]

[0105] Next, the effects of the travel control system 1 according to the embodiment of the present invention will be described.

[0106] In the present embodiment, the degree of similarity between the surrounding conditions (scenes) of the first vehicle 100a and each dangerous condition (scene) recorded in the main body database 29 is determined. If the result is that the similarity is low, it is determined that the surrounding conditions (scenes) of the first vehicle 100a are not recorded in the main body database 29. And, if the similarity is low, it is determined whether there is a dangerous phenomenon around the first vehicle 100a based on a predetermined flag of the driving assistance system 31. If the result is that there is a dangerous phenomenon around the first vehicle 100a, the surrounding conditions (scenes) of the first vehicle 100a are added to the main body database 29 by corresponding to the dangerous phenomenon obtained by reasoning, thereby updating the main body database 29.

[0107] Thus, in the present embodiment, when the first vehicle 100a encounters a dangerous situation (scenario) that does not exist in the existing main body database 29 and there is a dangerous phenomenon around the first vehicle 100a, the main body database 29 is updated by matching the dangerous situation (scenario) at this time with the dangerous phenomenon and adding them to the main body database 29. Therefore, after the main body database 29 is updated, the first vehicle 100a can perform control that predicts the occurrence of the dangerous phenomenon read from the main body database 29 when encountering the same dangerous situation.

[0108] In the present embodiment, whether there is a dangerous phenomenon around the first vehicle 100a is determined based on a signal (e.g., a predetermined operation flag) output from the driving assistance system 31. This can prevent situations (scenarios) that are not that dangerous from being added to the main body database 29. As a result, the first vehicle 100a can perform control that predicts the occurrence of a dangerous phenomenon read from the main body database 29 only in an actually dangerous situation.

[0109] In the present embodiment, when it is determined that there is a dangerous phenomenon around the first vehicle 100a, the updating of the main body database 29 is started. Thereby, the main body database 29 can be always maintained in the latest state.

[0110] In this embodiment, a set of new inference rules 28A with the surrounding conditions (scenario) of the first vehicle 100a as condition items and the dangerous phenomenon obtained by inference as result items is added to the ontology database 29, thereby updating the ontology database 29. After the ontology database 29 is updated, the first vehicle 100a can perform control that predicts the occurrence of the dangerous phenomenon read from the ontology database 29 when encountering the same dangerous situation.

[0111] In the present embodiment, the degree of similarity is determined based on the ratio of instance generation between the surrounding conditions (scenes) of the first vehicle 100a and each dangerous condition (scene) described in the main body database 29. Thus, for example, when the instance generation ratio is above a predetermined threshold value, it is determined that the degree of similarity is high, and it can be determined that the surrounding conditions (scenes) of the first vehicle 100a are described in the main body database 29. On the other hand, for example, when the instance generation ratio is less than a predetermined threshold value, it is determined that the degree of similarity is low, and it can be determined that the surrounding conditions (scenes) of the first vehicle 100a are not described in the main body database 29. As a result, it is possible to easily determine whether the main body database 29 needs to be updated based on the instance generation ratio.

[0112] <3. Modifications>

[0113] As mentioned above, although embodiment was given and this invention was demonstrated, this invention is not limited to this embodiment, Various deformation|transformation is possible.

[0114] [Variation 3-1]

[0115] In the above embodiment, the main body_ECU25 determines whether the possibility of the occurrence of a dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a is high based on whether the predetermined flag of the driving assistance system 31 is output. However, in the above embodiment, the main body_ECU25 may also consider not only the predetermined flag of the driving assistance system 31 but also other factors to determine whether the possibility of the occurrence of a dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a is high.

[0116] Fig.13 1 is a diagram showing a modified example of the update order of the main body database 29. After executing step S107, the main body_ECU25 detects one or more risk factors included in the information (stereoscopic image) obtained from the driving environment detection unit 11d. After executing step S107, the main body_ECU25 may detect one or more risk factors included in the data obtained through external communication (road-to-vehicle communication and vehicle-to-vehicle communication) via the transceiver 18, for example.

[0117] The main body_ECU25 determines whether a part of other traffic participants (such as the second vehicle 100b) appears from the blind spot with low accuracy (whether there is a risk factor) based on the information obtained from the driving environment detection unit 11d (information on three-dimensional objects such as structures existing around the first vehicle 100a) (step S110). The main body_ECU25 can also determine whether a part of other traffic participants (such as the second vehicle 100b) appears from the blind spot with low accuracy (whether there is a risk factor) based on data obtained through external communication (road-to-vehicle communication and vehicle-to-vehicle communication) via the transceiver 18. Here, as a "blind spot", for example, vehicles parked on the road can be listed. It should be noted that when a part of other traffic participants (such as the second vehicle 100b) appears from the blind spot with high accuracy, the main body_ECU25 can make a judgment using the similarity of the information of other traffic participants in the above-mentioned step S103.

[0118] The main body_ECU25 also determines the driving attitude of the driver of the first vehicle 100a based on data obtained from a camera or the like (sensor) provided in the first vehicle 100a. The main body_ECU25 determines whether the driver of the first vehicle 100a is looking ahead, for example, based on data obtained from a camera or the like (sensor) provided in the first vehicle 100a. The main body_ECU25 determines whether the driver of the first vehicle 100a is looking at the other traffic participants mentioned above, for example, based on data obtained from a camera or the like provided in the first vehicle 100a (step S111).

[0119] The main body_ECU25 also determines whether the driver of the first vehicle 100a is taking evasive action (step S112). The main body_ECU25 can also determine whether the driver of the first vehicle 100a is taking evasive action based on the data obtained from various sensors installed in the first vehicle 100a and the following three data combinations. It should be noted that in the following (2) and (3), the fact that the direction of the route symbol of the first vehicle 100a is opposite to that of other traffic participants means that the driver of the first vehicle 100a is taking evasive action.

[0120] (1) Braking pressure change rate + deceleration of the first vehicle 100a

[0121] (2) Rate of change of steering angle + sign of the path of the first vehicle 100a

[0122] (3) Steering wheel torque change rate+travel path sign of the first vehicle 100a.

[0123] In this way, the main body_ECU25 not only considers the predetermined signs of the driving assistance system 31, but also adds other factors (for example, the presence of other traffic participants, the driving attitude of the driver of the first vehicle 100a, and the biological indicators of the driver of the first vehicle 100a) to determine whether the possibility of the occurrence of the dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a is high (step S108). In such a case, the possibility of the occurrence of the dangerous phenomenon corresponding to the surrounding conditions (scenes) of the first vehicle 100a can be estimated with higher accuracy. Thus, it is possible to avoid adding conditions (scenes) that are not so dangerous to the main body database 29. As a result, the first vehicle 100a can perform control that predicts the occurrence of dangerous phenomena read from the main body database 29 only in actually dangerous conditions.

[0124] In addition, in this variation, even when the driving assistance system 31 is not working, it is possible to estimate the possibility of a dangerous phenomenon corresponding to the surrounding conditions (scene) of the first vehicle 100a by setting other factors (for example, the presence of other traffic participants, the driving attitude of the driver of the first vehicle 100a, and the biological indicators of the driver of the first vehicle 100a) as judgment factors.

[0125] In addition, in this modified example, it is determined with low accuracy whether a part of another traffic participant (for example, the second vehicle 100b) has appeared from the blind spot based on the information obtained from the driving environment detection unit 11d (information on three-dimensional objects such as structures existing around the first vehicle 100a) and the data acquired through external communication (road-to-vehicle communication and vehicle-to-vehicle communication) via the transceiver 18. Thus, even with low accuracy, it is possible to make an inference with sufficient reliability.

[0126] [Variation 3-2]

[0127] In the above-mentioned modification 3-1, the main body_ECU 25 may also be configured as follows, for example: Fig.14 As shown in the figure, it is determined whether the data obtained from the sensor capable of detecting the biological index of the driver of the first vehicle 100a exceeds a predetermined threshold value (step S113), instead of step S112. The main body_ECU25 can estimate the psychological state of the driver of the first vehicle 100a by using the biological index. Thus, even when the driving assistance system 31 is not working, the main body_ECU25 can determine whether the driver of the first vehicle 100a is taking evasive action. As a result, the main body_ECU25 can determine whether there is a dangerous phenomenon around the first vehicle 100a.

[0128] [Variation 3-3]

[0129] In the above-mentioned embodiment and its modified example, the present invention is applied to driving assistance at the intersection CL where the priority road Lm intersects with the non-priority road Ls. However, in the above-mentioned embodiment and its modified example, for example, the present invention may also be applied to driving assistance at a junction where the non-priority road Ls and the priority road Lm merge. Even in such a case, the same effect as that of the above-mentioned embodiment and its modified example can be obtained.

[0130] [Variation 3-4]

[0131] In the above-mentioned embodiment and its modification, when it is difficult for the first vehicle 100a to communicate with the network environment NW, the travel_ECU 21 may acquire the road information Da and the vehicle information Db based on various data obtained from various sensors mounted on the first vehicle 100a. Here, the road information Da includes information on the priority road Lm, the driving lane L1, the oncoming lane L2, the non-priority road Ls, and the unsignalized intersection CL detected by the driving environment recognition unit 13c. The vehicle information Db includes information on the speed (vehicle speed) of the first vehicle 100a acquired from the vehicle position estimation unit 13b, and information on vehicles on the priority road Lm (e.g., 100a, 100c to 100e) and vehicles on the non-priority road Ls (e.g., 100b). In this way, even when the judgment of whether there is a dangerous phenomenon around the first vehicle 100a is performed based on the traffic conditions in front of the first vehicle 100a obtained from various sensors mounted on the first vehicle 100a, the same effect as the above-mentioned embodiment and its modification can be obtained.

[0132] It should be noted that the effects described in this specification are merely illustrative. The effects of the present invention are not limited to the effects described in this specification. The present invention may also have effects other than those described in this specification.

[0133] In addition, for example, the present invention can take the following configurations. (1)

[0135] A main body updating device, wherein:

[0136] A control unit is provided, which can update the main body,

[0137] The control unit can perform the following steps:

[0138] a step of determining the degree of similarity between the surrounding conditions of the first vehicle and the dangerous conditions recorded in the main body, and determining that the surrounding conditions are not recorded in the main body when the degree of similarity is determined to be low, and

[0139] A step of determining whether there is a dangerous phenomenon around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there is a dangerous phenomenon around the first vehicle, associating the surrounding conditions with the dangerous phenomenon and adding them to the main body, thereby updating the main body. (2)

[0141] The main body updating device according to (1), wherein:

[0142] The device is a driving assistance system installed in the first vehicle,

[0143] The control unit can determine whether there is a dangerous phenomenon around the first vehicle based on the signal output from the driving assistance system. (3)

[0145] The main body updating device according to (2), wherein:

[0146] The device can use the working flag of the driving assistance system to determine whether there is a dangerous phenomenon around the first vehicle. (4)

[0148] The main body updating device according to any one of (1) to (3), wherein:

[0149] The device includes a first sensor capable of detecting traffic conditions in front of the first vehicle,

[0150] The control unit can determine whether there is a dangerous phenomenon around the first vehicle based on data obtained from the first sensor when the driving assistance system mounted on the first vehicle is not operating. (5)

[0152] The main body updating device according to (4), wherein:

[0153] The first sensor is a binocular camera capable of acquiring a stereoscopic image of the front of the first vehicle,

[0154] The control unit can detect one or more dangerous factors included in the stereoscopic image obtained by the binocular camera, and determine whether there is a dangerous phenomenon around the first vehicle based on the detection result. (6)

[0156] The main body updating device according to (4), wherein:

[0157] The device includes the first sensor and a second sensor capable of detecting a driving attitude, evasive action or biological indicator of a driver of the first vehicle,

[0158] The control unit can determine whether there is a dangerous phenomenon around the first vehicle based on data obtained from both the first sensor and the second sensor when the driving assistance system is not operating. (7)

[0160] The main body updating device according to (4), wherein:

[0161] The control unit can determine whether there are dangerous phenomena around the first vehicle by obtaining the phenomena from at least one of a third sensor mounted on the first vehicle and capable of detecting phenomena in front of the first vehicle, and a communication unit capable of obtaining phenomena in front of the first vehicle from an external device. (8)

[0163] The main body updating device according to any one of (1) to (7), wherein:

[0164] The control unit can start updating the main body when it is determined that a dangerous phenomenon occurs around the first vehicle. (9)

[0166] The main body updating device according to any one of (1) to (8), wherein:

[0167] The control unit can update the ontology by adding a set of new inference rules that use the surrounding conditions as condition items and the dangerous phenomenon as result items to the ontology. (10)

[0169] The main body updating device according to any one of (1) to (9), wherein:

[0170] The control unit can determine the degree of similarity based on a ratio of instance generation between the surrounding situation and the dangerous situation described in the main body. (11)

[0172] A vehicle, comprising:

[0173] a storage unit storing the main body; and

[0174] a control unit capable of updating the main body,

[0175] The control unit can perform the following steps:

[0176] a step of determining the degree of similarity between the surrounding conditions of the first vehicle and the dangerous conditions recorded in the main body, and determining that the surrounding conditions are not recorded in the main body when the degree of similarity is determined to be low, and

[0177] A step of determining whether there is a dangerous phenomenon around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there is a dangerous phenomenon around the first vehicle, associating the surrounding conditions with the dangerous phenomenon and adding them to the main body, thereby updating the main body. (12)

[0179] A ontology updating method, comprising:

[0180] a step of determining the degree of similarity between the surrounding conditions of the first vehicle and the dangerous conditions recorded in the main body, and determining that the surrounding conditions are not recorded in the main body when the degree of similarity is determined to be low, and

[0181] A step of determining whether there is a dangerous phenomenon around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there is a dangerous phenomenon around the first vehicle, associating the surroundings with the dangerous phenomenon and adding them to the main body, thereby updating the main body.

[0182] Figure 1 The driving control device 10 shown can be implemented by at least one processor (e.g., a central processing unit (CPU)), at least one application specific integrated circuit (ASIC) and / or at least one field programmable gate array (FPGA) or other circuits including at least one semiconductor integrated circuit. The at least one processor can be configured to execute by reading instructions from at least one non-transitory and tangible computer-readable medium. Figure 1 Such a medium can be in various forms including various magnetic media such as a hard disk, various optical media such as a CD or a DVD, and various semiconductor memories (i.e., semiconductor circuits) such as volatile memories or non-volatile memories, but is not limited to these. Volatile memories can include DRAM and SRAM. Non-volatile memories can include ROM and NVRAM. ASIC is a memory dedicated to executing Figure 1 The FPGA is an integrated circuit (IC) that is designed to be able to execute all or part of the various functions of the driving control device 10 after manufacturing. Figure 1 The illustrated travel control device 10 may include an integrated circuit that implements all or part of the various functions of the travel control device 10 .

Claims

1. A main body updating device, characterized in that: A control unit is provided, which can update the main body, The control unit can perform the following steps: a step of determining the degree of similarity between the surrounding conditions of the first vehicle and the dangerous conditions recorded in the main body, and determining that the surrounding conditions are not recorded in the main body when the degree of similarity is determined to be low, and A step of determining whether there is a dangerous phenomenon around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there is a dangerous phenomenon around the first vehicle, associating the surrounding conditions with the dangerous phenomenon and adding them to the main body, thereby updating the main body.

2. The main body updating device according to claim 1, characterized in that: The device is a driving assistance system installed in the first vehicle, The control unit can determine whether there is a dangerous phenomenon around the first vehicle based on the signal output from the driving assistance system.

3. The main body updating device according to claim 2, characterized in that: The device can use the working flag of the driving assistance system to determine whether there is a dangerous phenomenon around the first vehicle.

4. The main body updating device according to claim 1, characterized in that: The device includes a first sensor capable of detecting traffic conditions in front of the first vehicle, The control unit can determine whether there is a dangerous phenomenon around the first vehicle based on data obtained from the first sensor when the driving assistance system mounted on the first vehicle is not operating.

5. The main body updating device according to claim 4, characterized in that: The first sensor is a binocular camera capable of acquiring a stereoscopic image of the front of the first vehicle, The control unit can detect one or more dangerous factors included in the stereoscopic image obtained by the binocular camera, and determine whether there is a dangerous phenomenon around the first vehicle based on the detection result.

6. The main body updating device according to claim 4, characterized in that: The device includes the first sensor and a second sensor capable of detecting a driving attitude, evasive action or biological indicator of a driver of the first vehicle, The control unit can determine whether there is a dangerous phenomenon around the first vehicle based on data obtained from both the first sensor and the second sensor when the driving assistance system is not operating.

7. The main body updating device according to claim 4, characterized in that: The control unit can determine whether there are dangerous phenomena around the first vehicle by obtaining the phenomena from at least one of a third sensor mounted on the first vehicle and capable of detecting phenomena in front of the first vehicle, and a communication unit capable of obtaining phenomena in front of the first vehicle from an external device.

8. The main body updating device according to claim 1, characterized in that: The control unit can start updating the main body when it is determined that a dangerous phenomenon occurs around the first vehicle.

9. The main body updating device according to claim 1, characterized in that: The control unit can update the ontology by adding a set of new inference rules that use the surrounding conditions as condition items and the dangerous phenomenon as result items to the ontology.

10. The main body updating device according to claim 1, characterized in that: The control unit can determine the degree of similarity based on a ratio of instance generation between the surrounding situation and the dangerous situation described in the main body.

11. A vehicle, characterized in that: have: a storage unit storing the main body; and a control unit capable of updating the main body, The control unit can perform the following steps: a step of determining the degree of similarity between the surrounding conditions of the first vehicle and the dangerous conditions recorded in the main body, and determining that the surrounding conditions are not recorded in the main body when the degree of similarity is determined to be low, and A step of determining whether there is a dangerous phenomenon around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there is a dangerous phenomenon around the first vehicle, associating the surrounding conditions with the dangerous phenomenon and adding them to the main body, thereby updating the main body.

12. A ontology updating method, characterized in that: include: a step of determining the degree of similarity between the surrounding conditions of the first vehicle and the dangerous conditions recorded in the main body, and determining that the surrounding conditions are not recorded in the main body when the degree of similarity is determined to be low, and A step of determining whether there is a dangerous phenomenon around the first vehicle based on data obtained from a device mounted on the first vehicle when the surrounding conditions are acquired, and when it is determined that there is a dangerous phenomenon around the first vehicle, associating the surroundings with the dangerous phenomenon and adding them to the main body, thereby updating the main body.

Images