JP2014041434A - Cutting-in prediction device, cutting-in prediction method and driving support system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a cutting-in prediction device and a cutting-in prediction method the prediction accuracy of a cutting-in vehicle of which can be improved, and to provide a driving support system that does a driving support on the basis of a cutting-in prediction result having high accuracy.SOLUTION: The cutting-in prediction device according to the present invention is configured to: acquire a driving environment regarding an own vehicle; predict cutting-in of a surrounding vehicle in front of the own vehicle on the basis of cutting-in prediction probability to be calculated by comparing the acquired driving environment regarding the own vehicle with a driving environment of a vehicle cutting-in scene stored in a storage device; detect the cutting-in of the surrounding vehicle; and update the driving environment of the vehicle cutting-in scene stored in the storage device on the basis of the driving environment of the own vehicle acquired upon detecting the cutting-in of the surrounding vehicle. Herein, the cutting-in prediction device of the present invention predicts the cutting-in of the surrounding vehicle using the updated driving environment of the vehicle cutting-in scene.

Description

  The present invention relates to an interrupt prediction device, an interrupt prediction method, and a driving support system.

  Conventionally, an interrupt detection technique for detecting a vehicle interruption has been developed. For example, Patent Document 1 discloses a technique of observing the surroundings in front of the host vehicle with a camera or the like and detecting an interrupted vehicle by image processing.

  In recent years, an interrupt prediction technique for predicting a vehicle interruption has been developed. For example, Patent Document 2 discloses a technique for predicting an interruption of another vehicle by comparing the behaviors of the host vehicle and the surrounding vehicle with a vehicle interruption scene stored in an in-vehicle storage device. Patent Document 3 discloses a technique for predicting an interruption of another vehicle by comparing the behavior of a surrounding vehicle with dangerous vehicle behavior model data stored in an in-vehicle storage device.

JP 2003-281700 A JP 2007-41788 A JP 2006-085285 A

  However, in the prior art, the data stored in the storage device used when predicting the vehicle interruption may be different from the situation where the vehicle interruption actually occurs. Prediction accuracy may be reduced. Thus, the conventional technology has room for further improvement in terms of vehicle interrupt prediction accuracy.

  The present invention has been made in view of the above circumstances, and is based on an interrupt prediction apparatus and an interrupt prediction method capable of improving the interrupt prediction accuracy of a vehicle, and an interrupt prediction result with high prediction accuracy. The purpose is to provide a driving support system that performs driving support.

  The present invention is an interrupt prediction device that predicts a vehicle interruption, a travel environment acquisition unit that acquires a travel environment related to the host vehicle, and a current travel environment related to the host vehicle acquired by the travel environment acquisition unit; An interrupt prediction unit that predicts an interruption of a surrounding vehicle ahead of the host vehicle based on an interrupt occurrence probability calculated by comparison with a traveling environment of a past vehicle interrupt scene stored in a storage device; An interrupt detection unit that detects an interruption of the surrounding vehicle; and a storage environment that is stored when the interruption detection unit detects an interruption of the surrounding vehicle, and is stored in the storage device. A data updating unit that updates a traveling environment of the vehicle interruption scene, and the interrupt prediction unit uses the traveling environment of the vehicle interruption scene updated by the data updating unit. Characterized by predicting interrupts both.

  In the interrupt prediction device described above, the interrupt prediction unit predicts an interruption of the surrounding vehicle by comparing the interrupt occurrence probability with an interrupt occurrence determination threshold stored in the storage device, and the data The update unit determines whether the prediction result is correct based on a detection result of the interruption of the surrounding vehicle by the interrupt detection unit and a prediction result of the interruption of the surrounding vehicle by the interrupt prediction unit, and the prediction When the result is incorrect, it is preferable to change the interruption occurrence determination threshold related to the traveling environment of the corresponding vehicle interruption scene.

  Moreover, this invention is the driving assistance system provided with the interruption prediction apparatus of the above-mentioned description, the driving assistance with respect to the said own vehicle, Comprising: The said interruption prediction apparatus is the said interruption prediction part. And a system control unit that calculates a control amount for controlling the driving support device based on the prediction result by the control unit and causes the driving support device to perform the driving support based on the calculated control amount. It is characterized by.

  The present invention is also an interrupt prediction method for predicting a vehicle interruption, a travel environment acquisition step for acquiring a travel environment related to the host vehicle, and a travel environment related to the host vehicle acquired in the travel environment acquisition step. And an interrupt prediction step for predicting an interruption of a surrounding vehicle ahead of the host vehicle based on an interrupt occurrence probability calculated by comparison with the traveling environment of the vehicle interrupt scene stored in the storage device, An interruption detection step for detecting an interruption of the surrounding vehicle, and a storage environment stored in the storage device based on a traveling environment related to the own vehicle acquired when the interruption of the surrounding vehicle is detected in the interruption detection step. Updating the travel environment of the vehicle interrupt scene, and in the interrupt prediction step, the vehicle interrupt sequence updated in the update step. Characterized by predicting the interruption of the peripheral vehicle using the emission driving environment.

  The interrupt prediction device, the interrupt prediction method, and the driving support system according to the present invention can improve the interrupt prediction accuracy of the vehicle and can perform driving support based on the interrupt prediction result with high prediction accuracy. There is an effect.

FIG. 1 is a block diagram illustrating an example of a configuration of a driving support system including an interrupt prediction device according to the present embodiment. FIG. 2 is a diagram illustrating an example of a situation where an interruption of a surrounding vehicle occurs in the present embodiment. FIG. 3 is a flowchart showing an example of database creation processing in the present embodiment. FIG. 4 is a flowchart illustrating an example of the interrupt prediction process and the data update process in the present embodiment. FIG. 5 is a diagram illustrating an example of a situation where a vehicle interruption occurs in the first modification of the present embodiment. FIG. 6 is a flowchart illustrating an example of the interrupt prediction process in Modification 1 of the present embodiment. FIG. 7 is a diagram illustrating an example of a situation where a vehicle interruption occurs in the second modification of the present embodiment. FIG. 8 is a flowchart illustrating an example of an interrupt detection process according to the second modification of the present embodiment.

  Hereinafter, embodiments of an interrupt prediction device, an interrupt prediction method, and a driving support system according to embodiments of the present invention will be described in detail with reference to the drawings. In addition, this invention is not limited by this embodiment. In addition, constituent elements in the following embodiments include those that can be easily assumed by those skilled in the art or those that are substantially the same.

[Embodiment]
The configuration of the driving support system according to the embodiment of the present invention will be described with reference to FIG. FIG. 1 is a block diagram illustrating an example of a configuration of a driving support system including an interrupt prediction device according to the present embodiment.

  As shown in FIG. 1, a vehicle (hereinafter also referred to as “own vehicle”) 10 includes a driving support ECU 11, a brake ECU 12, an engine ECU 13, a steering ECU 14, a brake 21, an engine 22, a steering 23, and an output. Device 24, car navigation 30, database 31, inter-vehicle communication device 40, infrastructure communication device 41, in-vehicle camera 42, in-vehicle radar 43, GPS 44, vehicle speed sensor 45, acceleration sensor 46, and gyro sensor 47, a brake sensor 48, an accelerator sensor 49, and a steering angle sensor 50. In the vehicle 10, the brake 21, the engine 22, the steering 23, and the output device 24 are included in the driving support device 20. In the vehicle 10, the surrounding environment information acquisition unit 51 includes an inter-vehicle communication device 40, an infrastructure communication device 41, an in-vehicle camera 42, and an in-vehicle radar 43. In the vehicle 10, the vehicle information acquisition means 52 includes a GPS 44, a vehicle speed sensor 45, an acceleration sensor 46, a gyro sensor 47, a brake sensor 48, an accelerator sensor 49, and a steering angle sensor 50.

  As shown in FIG. 1, the vehicle 10 includes a driving assistance ECU 11 (including an interrupt prediction device according to the present embodiment) that performs various controls for assisting the driver who drives the vehicle 10 with the driving operation. Is provided. The driving support ECU 11 is a microcomputer that includes a CPU that executes various arithmetic processes, a ROM that stores various control programs, a RAM that is used as a work area for data storage and program execution, an input / output interface, a memory, and the like. It is configured. In the present embodiment, the driving assistance ECU 11 executes various types of control related to driving assistance, determines timing at which driving assistance should be performed based on various conditions, and outputs information and signals related to driving assistance along the timing. Therefore, the driving assistance ECU 11 stores in advance various programs for executing driving assistance, various parameters used for assistance, and the like. The various parameters include values indicating the characteristics and performance of the vehicle 10 used for calculations such as driving support timing. The driving assistance ECU 11 includes a brake ECU 12, an engine ECU 13, a steering ECU 14, a car navigation 30, a database 31, an output device 24, an inter-vehicle communication device 40, an infrastructure communication device 41, an in-vehicle camera 42, and an in-vehicle camera. The radar 43, the GPS 44, the vehicle speed sensor 45, the acceleration sensor 46, the gyro sensor 47, the brake sensor 48, the accelerator sensor 49, and the steering angle sensor 50 constitute an in-vehicle network such as a CAN (Control Area Network). Are connected to be able to communicate with each other. The detailed configuration of the driving assistance ECU 11 will be described later. In addition, although illustration of wiring was abbreviate | omitted in FIG. 1, each part of the vehicle 10 is connected so that communication is possible via vehicle-mounted network other than driving assistance ECU11.

  The brake ECU 12 is an ECU that controls the brake 21 of the vehicle 10, to which various sensors such as a vehicle speed sensor 45 and a brake sensor 48 are connected, and based on signals from the various sensors, the brake 21 of the vehicle 10. A braking force is generated in the vehicle 10 through the control. Specifically, the brake 21 is controlled by calculating the required braking force based on the speed of the vehicle 10 grasped based on the signal from the vehicle speed sensor 45, the signal of the brake depression amount of the brake sensor 48, and the like.

  The engine ECU 13 is an ECU that controls the operation of the engine 22 of the vehicle 10, and is connected to an accelerator sensor 49 that detects an accelerator depression amount, a sensor that detects an intake air amount, and the like, a throttle valve drive circuit, The drive circuit of various apparatuses, such as a drive circuit of a fuel injection valve, is connected. The engine ECU 13 detects the operating state of the engine 22 that is grasped based on the detection signals input from the sensors, and outputs command signals for the drive circuits of the various devices. Thus, the operation control of the engine 22 is performed through the engine ECU 13.

  The steering ECU 14 is an ECU that controls the steering 23 of the vehicle 10. The steering ECU 14 is connected to various sensors such as a gyro sensor 47 and a steering angle sensor 50, and is based on electric assist control based on signals from the various sensors. The steering 23 is controlled.

  The brake ECU 12, the engine ECU 13, and the steering ECU 14 are similar to the driving assistance ECU 11 described above, as a CPU that executes various arithmetic processes, a ROM that stores various control programs, and a work area for data storage and program execution, respectively. It is mainly composed of a microcomputer provided with a RAM, an input / output interface, a memory and the like.

  The output device 24 is electrically connected to the driving support ECU 11 and outputs notifications corresponding to various information. In the present embodiment, the output device 24 includes a speaker 24a and a display 24b.

  The speaker 24a is an audio device that outputs a notification by voice. The speaker 24a generates a sound, a warning sound, or the like for alerting the driver based on, for example, a notification related to driving assistance. The speaker 24a outputs a voice guidance message or an alarm sound according to a signal from the driving support ECU 11. For example, the speaker 24a outputs sounds and sounds corresponding to sound / voice data input from a car navigation system 30 described later. To the speaker 24a, sound information such as route guidance and traffic information, sound information corresponding to the driving support information from the driving support ECU 11, and the like are input from the car navigation 30 as sound / voice data. The driving support information is information for supporting the driving of the vehicle 10 and includes, for example, information that instructs the driver of the vehicle 10 how to drive the vehicle 10.

  The display 24b is a display device that outputs a notification as an image or video. The display 24b is installed near the center console in the vehicle interior, for example. An image corresponding to image data input from the car navigation system 30 is displayed on the display 24b. The display 24 b displays image data such as map display image data and notification display corresponding to the driving support information input from the driving support ECU 11 from the car navigation 30.

  When the display 24b displays driving support information that supports driving of the vehicle 10, for example, based on the detection result of the obstacle present in the vicinity of the vehicle 10, the driver 24 is notified of the presence or absence of the obstacle. Displays driving support information that provides information. Further, the display 24b displays driving support information for alerting that the surrounding vehicle is approaching based on the speed and distance of the surrounding vehicle calculated when the surrounding vehicle is in front of the vehicle 10. In addition, the display 24b may collide with the surrounding vehicle after several seconds based on the time from the speed and distance of the surrounding vehicle calculated when the surrounding vehicle is in front of the vehicle 10 to the collision. Driving assistance information for giving an alarm instructing how to control the vehicle 10 in order to do this is displayed. In the present embodiment, when the display 24b displays driving support information, corresponding audio information may also be output from the speaker 24a.

  The car navigation system 30 detects the current position of the vehicle 10 using a GPS (Global Positioning System) 44 and the like, and refers to road map information stored in advance to reach the driver. The travel route of the vehicle 10 is guided. The car navigation system 30 of the present embodiment acquires and uses road map information stored in the database 31 in advance. In addition, the car navigation 30 transmits position information related to the position of the vehicle 10, road map information extracted as information around the current position, and the like to the driving assistance ECU 11. As a result, the car navigation 30 outputs image data that combines the current position of the vehicle 10 and the surrounding map, and displays an image that combines the position of the vehicle 10 and the surrounding map on the display 24b. .

  The database 31 is a device that stores data used in processing of each unit and data detected by each unit, and an HDD (Hard Disk Drive) that is a nonvolatile storage device is used as the storage device. The road map information is information relating to the map, and is composed of data for displaying the road and the background of the road map, data including the names of intersections, and the like. The road map information includes road ancillary information such as road shape, information on intersections and crosswalks on the road. Specifically, the road map information includes information such as the location of target intersections and temporary stop points where traffic lights are provided, road shapes, roads, tunnels, pedestrian crossings, accident-prone points, and road surface conditions as road ancillary information. It is. For this reason, the road map information transmitted from the car navigation 30 to the driving support ECU 11 also includes the above-described road accessory information and the like.

  The database 31 includes map data 31a and interrupt occurrence result data 31b. The map data 31a is a database of road map information used for car navigation processing. The interruption occurrence record data 31b stores the running environment related to the vehicle 10 immediately before the occurrence of the interruption and the interruption occurrence record, which are acquired when an interruption of a surrounding vehicle ahead of the vehicle 10 has occurred in the past, in association with each other. This is a database of interrupt occurrence results. In the present embodiment, the traveling environment means information indicating a traveling environment related to the vehicle 10 under a specific situation. This travel environment is acquired from the surrounding environment information acquisition means 51, the own vehicle information acquisition means 52, the map data 31a, etc. by the travel environment acquisition part 60 described later. The interruption occurrence record data 31b stores a traveling environment of a vehicle interruption scene that is a situation in which an interruption of a surrounding vehicle ahead of the vehicle 10 has occurred in the past. For example, the driving environment of the vehicle interruption scene includes the state of the vehicle immediately before the occurrence of the interruption (for example, traveling speed, acceleration, etc.), the relative relationship between the own vehicle and the preceding vehicle (for example, inter-vehicle distance, relative speed, relative position, etc.) ), The relative relationship between the vehicle in front and the surrounding vehicle, the traffic flow status (eg, congestion) depending on the time and time zone, information on the location where the vehicle is traveling or the characteristics of the location, date, etc. For example, but not limited to. The features of the location include, for example, the road width, number of lanes, slope, curvature, presence / absence of infrastructure (signals, etc.), presence / absence of traffic rules (temporary stop points, etc.), speed limit, intersection shape, road shape, etc. However, it is not limited to these.

  Further, the interrupt occurrence result data 31b associates an interrupt occurrence determination threshold C used when an interrupt prediction unit 64 described below predicts an interruption of a surrounding vehicle with a traveling environment of a corresponding vehicle interruption scene. And remember. Whether the interrupt occurrence determination threshold C is highly likely to generate an interrupt or whether an interrupt is generated based on a comparison with an interrupt occurrence probability P calculated by an interrupt occurrence probability calculating unit 62 described later. Is a parameter used to determine whether it is indefinite. In the present embodiment, the initial value of the interrupt occurrence determination threshold value C is set to a value having an arbitrary magnitude between 0 and 1. The initial value is updated to an appropriate size as needed by a data updating unit 70 described later.

  Next, each unit included in the surrounding environment information acquisition unit 51 will be described. Each unit included in the surrounding environment information acquisition unit 51 detects various information around the vehicle 10. The surrounding environment information acquisition unit 51 acquires, for example, information on a sensor that detects a relationship with a surrounding vehicle, information on a surrounding where the vehicle 10 is traveling, for example, information on a traveling route, and the like. The vehicle-to-vehicle communication device 40 is a communication device that performs so-called vehicle-to-vehicle communication, in which various types of information such as position information and travel information of the vehicle 10 are transmitted to and from surrounding vehicles located around the vehicle 10 by wireless communication. is there. In vehicle-to-vehicle communication, vehicle information is periodically exchanged with each of a plurality of vehicles in the communicable area. The vehicle information includes a vehicle ID uniquely assigned to each vehicle, an absolute position of the vehicle detected by the vehicle GPS, a vehicle speed, a traveling direction of the vehicle, and a vehicle type / vehicle height information. Yes. The inter-vehicle communication device 40 transmits the vehicle information of the surrounding vehicles received by the inter-vehicle communication to the driving support ECU 11. As a result, the vehicle information of the surrounding vehicle is input to the driving assistance ECU 11, and the driving assistance ECU 11 can grasp the running state of the surrounding vehicle located around the vehicle 10. That is, the driving assistance ECU 11 can receive vehicle information related to surrounding vehicles located around the vehicle 10 that becomes an obstacle.

  The infrastructure communication device 41 is a communication device that communicates with an infrastructure device provided at an intersection, a road, or the like by an optical signal such as an infrared signal. The infrastructure communication device 41 receives the infrastructure information signal transmitted from the infrastructure device, and transmits the received infrastructure information signal to the driving support ECU 11. As a result, the driving support ECU 11 can grasp the infrastructure information. For example, the infrastructure communication device 41 receives date and time information and road traffic information distributed from the VICS (registered trademark) center as one piece of infrastructure information via the infrastructure device. The road traffic information includes, for example, traffic jam information such as a traffic jam section and a traffic jam degree, traffic regulation information such as a traffic stop. In addition, the infrastructure information is detected based on incidental information accompanying the road, such as the road conditions (including intersection shape, curvature, slope, and number of lanes) of the surrounding road where the infrastructure device is installed, and ground facilities. Mobile body information indicating the position and speed of a mobile body such as a surrounding vehicle or a pedestrian is also included. Thereby, driving assistance ECU11 can receive the mobile body information regarding the surrounding vehicle, the pedestrian, etc. which are located in the circumference | surroundings of the vehicle 10 used as an obstruction. Further, the infrastructure information includes signal lighting information indicating the lighting state of the traffic light at the place where the infrastructure device is provided. The signal lighting information is information indicating whether the lighting state of the target traffic light is red, yellow, or blue. In addition, the signal lighting information may include information indicating a blinking state of a red signal or a yellow signal, a lighting state of an arrow signal indicating a direction in which the vehicle in front of the traffic light can travel, and the like.

  The in-vehicle camera 42 images a predetermined range in front of the vehicle 10 with an optical CCD camera or the like installed on the back side of the room mirror, and transmits an image signal based on the captured image to the driving support ECU 11. Based on the image signal captured by the in-vehicle camera 42, the driving assistance ECU 11 extracts the lighting state (for example, signal color and blinking) of the front traffic light and the state of the front vehicle and the oncoming vehicle located in front. .

  The in-vehicle radar 43 irradiates a predetermined range in front of the vehicle with the laser beam, thereby detecting a distance, a relative speed, an azimuth, and the like with a reflecting object such as a front vehicle that reflects the laser beam. These detection results are transmitted to the driving support ECU 11 for each reflective object. Thereby, the driving assistance ECU 11 acquires obstacle detection information including moving bodies such as other vehicles and pedestrians in front of the vehicle 10, and determines the presence and type of the obstacle based on the detection information, It is possible to grasp the separation distance.

  Next, each part included in the own vehicle information acquisition means 52 will be described. Each unit included in the own vehicle information acquisition unit 52 detects various information related to the vehicle 10. The GPS 44 receives a GPS satellite signal to detect the absolute position of the vehicle 10 and detects the position of the vehicle 10 based on the received GPS satellite signal. The GPS 44 transmits the detected position information of the vehicle 10 to the driving support ECU 11. Thereby, the driving assistance ECU 11 can grasp the position of the vehicle 10. The vehicle speed sensor 45 transmits a signal corresponding to the detected wheel rotation speed to the driving assistance ECU 11. The acceleration sensor 46 transmits a signal corresponding to the detected acceleration of the vehicle 10 to the driving support ECU 11. The gyro sensor 47 transmits a signal corresponding to the detected traveling direction of the vehicle 10 to the driving assistance ECU 11. The brake sensor 48 transmits a signal corresponding to the detected presence or absence of the operation of the brake pedal by the driver and the depression amount of the brake pedal to the driving support ECU 11. The accelerator sensor 49 transmits a signal corresponding to the detected presence or absence of the operation of the accelerator pedal by the driver and the depression amount of the pedal to the driving support ECU 11. The steering angle sensor 50 transmits a signal corresponding to the detected change amount of the steering angle of the steering wheel 23 to the driving assistance ECU 11, and the driving assistance ECU 11 calculates the steering angle based on the received signal. In addition, the own vehicle information acquisition means 52 may include a direction indication detector that detects the lighting state of the blinker lamp of the own vehicle.

  Since various signals from the respective sensors are transmitted to the driving assistance ECU 11 at predetermined intervals, the driving assistance ECU 11 determines the vehicle such as the position, speed, direction, etc. of the vehicle 10 based on the various signals transmitted. The situation can be grasped sequentially.

  The vehicle 10 may be provided with an input device. As the input device, for example, a touch switch or a mechanical switch integrated with the display 24b is used, and is used for various input operations.

  Next, the driving assistance ECU 11 will be described. The driving support ECU 11 includes a travel environment acquisition unit 60, an interrupt occurrence probability calculation unit 62, an interrupt prediction unit 64, an interrupt detection unit 66, a database creation unit 68, a data update unit 70, and a system control unit. 72.

  The traveling environment acquisition unit 60 acquires the traveling environment related to the vehicle 10 (own vehicle) from the surrounding environment information acquisition unit 51, the own vehicle information acquisition unit 52, the map data 31a, and the like. In the present embodiment, for example, the traveling environment acquisition unit 60 acquires vehicle information related to surrounding vehicles, relative information between the preceding vehicle and surrounding vehicles, traffic flow conditions, date and time, and the like from the surrounding environment information acquisition unit 51. . The travel environment acquisition unit 60 acquires information indicating the host vehicle state, the relative relationship between the host vehicle and the preceding vehicle, the location where the host vehicle is traveling, and the like from the host vehicle information acquisition unit 52. The traveling environment acquisition unit 60 acquires information indicating the characteristics of the place where the vehicle is traveling from the map data 31a.

  The interruption occurrence probability calculation unit 62 compares the traveling environment related to the vehicle 10 acquired by the traveling environment acquisition unit 60 with the traveling environment of the vehicle interruption scene stored in the interruption occurrence result data 31b of the database 31. Thus, the degree of approximation between the two driving environments is obtained, and the interrupt probability P is calculated according to the magnitude of the degree of approximation. Here, in the interruption occurrence record data 31b, when the interruption of the surrounding vehicle ahead of the vehicle 10 has occurred in the past, the traveling environment related to the vehicle 10 immediately before the occurrence of the interruption acquired by the traveling environment acquisition unit 60, and The interrupt occurrence record is stored in association with each other. Therefore, the higher the degree of approximation between the travel environment related to the current vehicle 10 acquired by the travel environment acquisition unit 60 and the travel environment of the past vehicle interrupt scene stored in the interrupt occurrence result data 31b, the future vehicle It is considered that the probability that an interruption of a surrounding vehicle ahead of 10 will increase. Therefore, the interrupt occurrence probability calculation unit 62 sets the interrupt occurrence probability P having a relatively large value when the degree of approximation between the current traveling environment and the traveling environment of the vehicle interruption scene in which the interruption has occurred in the past is large. Calculate. On the other hand, when the degree of approximation between the current driving environment and the driving environment of the vehicle interruption scene in which the interruption has occurred in the past is small, the interrupt occurrence probability calculating unit 62 sets the interrupt occurrence probability P having a relatively small value. Calculate.

  The interrupt prediction unit 64 compares the travel environment related to the current vehicle 10 acquired by the travel environment acquisition unit 60 with the travel environment of past vehicle interrupt scenes stored in the interrupt occurrence result data 31b of the database 31. Based on the interrupt occurrence probability P calculated by the above, an interruption of a surrounding vehicle ahead of the vehicle 10 is predicted. In the present embodiment, the interrupt prediction unit 64 includes the interrupt occurrence probability P calculated by the interrupt occurrence probability calculation unit 62, and the interrupt occurrence determination threshold C stored in the interrupt occurrence result data 31b of the database 31. The interruption of the surrounding vehicle is predicted by the comparison. Specifically, when the interrupt occurrence probability P is equal to or greater than the interrupt occurrence determination threshold C (C ≦ P), the interrupt predicting unit 64 predicts that there is a high possibility that an interruption of a surrounding vehicle will occur. On the other hand, when the interrupt occurrence probability P is smaller than the interrupt occurrence determination threshold C (C> P), the interrupt predicting unit 64 predicts whether or not an interruption of a surrounding vehicle occurs is indeterminate. Here, the interrupt prediction unit 64 predicts an interruption of a surrounding vehicle by using a traveling environment of a vehicle interrupt scene that is updated as needed by a data update unit 70 described later.

  The interrupt detection unit 66 detects an interruption of a surrounding vehicle ahead of the vehicle 10. In the present embodiment, the interrupt detection unit 66 detects an interruption of a surrounding vehicle based on information acquired by the traveling environment acquisition unit 60 from the surrounding environment information acquisition unit 51 and the like. For example, the interrupt detection unit 66 detects an object (target) in front of the vehicle 10 with the in-vehicle camera 42 or the in-vehicle radar 43 and determines whether the detected object is an interrupted vehicle using an interrupt detection method such as image processing. It is determined whether or not the surrounding vehicle is interrupted. The interrupt detection method is not limited to image processing, and may be any detection method used for interrupt detection in this technical field. In addition, when the driver or the like determines that there is an interrupting vehicle in front of the vehicle 10, the interrupt detection unit 66 detects that there is an interrupting vehicle via the input device and An interrupt may be detected.

  When the interrupt detection unit 66 detects an interruption of a surrounding vehicle, the database creation unit 68 associates the travel environment acquired by the travel environment acquisition unit 60 as the travel environment of the vehicle interrupt scene with the interrupt occurrence record. By storing the data in the database 31, an interrupt occurrence record database (that is, interrupt occurrence record data 31b) is created.

  When the interrupt detection unit 66 detects an interruption of a surrounding vehicle ahead of the vehicle 10, the data update unit 70 determines whether the database 31 is allocated based on the travel environment related to the vehicle 10 acquired by the travel environment acquisition unit 60. The traveling environment of the vehicle interruption scene stored in the occurrence record data 31b is updated. In this embodiment, the data update unit 70 corrects the prediction result based on the detection result of the interruption of the surrounding vehicle by the interrupt detection unit 66 and the prediction result of the interruption of the surrounding vehicle by the interruption prediction unit 64. judge. The data update unit 70 stores the correctness of the determined prediction result in association with the traveling environment of the vehicle interruption scene stored in the interruption occurrence result data 31b of the database 31. Here, when the prediction result is incorrect, the data update unit 70 changes the interruption occurrence determination threshold C related to the traveling environment of the corresponding vehicle interruption scene.

  The system control unit 72 calculates a control amount for controlling each unit included in the driving support device 20 based on the prediction result by the interrupt prediction unit 64, and determines the driving support device 20 based on the calculated control amount. Provide driving assistance. For example, when performing vehicle control as driving assistance, the system control unit 72 controls the brake ECU 12, the engine ECU 13, the steering ECU 14, and the like based on the calculated control amount. As a result, the system control unit 72 operates the brake 21, engine 22, steering 23, etc. of the driving support device 20, and performs brake control, engine control, steering control, etc. so as to avoid collision with the interrupting vehicle. To do. Further, when performing output control of driving support information as driving support, the system control unit 72 operates the output device 24 of the driving support device 20 based on the calculated control amount to avoid a collision with an interrupted vehicle. Driving assistance information that prompts the driver to be output to the driver.

  Next, with reference to FIGS. 2 to 4, processing in the present embodiment performed in the driving support system having the above-described configuration will be described in detail. FIG. 2 is a diagram illustrating an example of a situation where an interruption of a surrounding vehicle occurs in the present embodiment. FIG. 3 is a flowchart showing an example of database creation processing in the present embodiment. FIG. 4 is a flowchart illustrating an example of the interrupt prediction process and the data update process in the present embodiment.

  In the present embodiment, a situation is assumed in which an interruption of a surrounding vehicle as shown in FIG. 2 occurs. In the situation shown in FIG. 2, the surrounding vehicle 80-1 and the surrounding vehicle 80-2 are traveling ahead of the vehicle 10 (the host vehicle). Then, between the vehicle 10 and a surrounding vehicle 80-2 traveling in the same traveling lane as the vehicle 10, the surrounding vehicle 80-1 traveling in the traveling lane on the right side of the vehicle 10 is connected to the surrounding vehicle 80-. The lane is changed to the left front direction 102 with respect to the traveling direction of 1. That is, the surrounding vehicle 80-1 is interrupted between the vehicle 10 and the surrounding vehicle 80-2.

  The database creation process executed under the situation shown in FIG. 2 will be described with reference to FIG.

  As shown in FIG. 3, first, the driving assistance ECU 11 acquires a driving environment related to the vehicle 10 by the driving environment acquisition unit 60 (step ST101). The travel environment acquired in step ST101 includes, for example, the host vehicle state of the vehicle 10 (travel speed, acceleration, etc. of the vehicle 10 in FIG. 2), and the relative relationship between the host vehicle and the front vehicle (in FIG. Distance, relative speed, relative position, etc. with surrounding vehicles 80-1, 2), traffic flow conditions (low congestion in the example of FIG. 2), location and time (or time zone) during travel, etc. is there.

  The driving assistance ECU 11 detects an interruption of the surrounding vehicle 80-1 ahead of the vehicle 10 by the interrupt detection unit 66 (step ST102).

  The driving assistance ECU 11 uses the timing when the interruption of the surrounding vehicle 80-1 is detected by the interrupt detection unit 66 as a trigger, and creates a database of interrupt occurrence results (that is, interrupt occurrence result data 31b) by the database creation unit 68. (Step ST103). In step ST103, the database creating unit 68 determines the vehicle state of the vehicle 10, the relative relationship between the vehicle and the preceding vehicle, and the traffic flow acquired immediately before the occurrence of the interruption in step ST101. In association with the time zone), it is stored in the database 31 as the traveling environment of the vehicle interruption scene. At this time, the database creation unit 68 creates a database of interrupt occurrence results by further storing the traveling environment of the vehicle interrupt scene in the database 31 in association with the interrupt occurrence results.

  Next, the interrupt prediction process executed by using the interrupt occurrence result data 31b created by performing the database creation process as shown in FIG. 3, and the interrupt occurrence result data 31b are executed. The data update process will be described with reference to FIG.

  As shown in FIG. 4, the driving assistance ECU 11 acquires the driving environment related to the vehicle 10 by the driving environment acquisition unit 60 (step ST201). The travel environment acquired in step ST201 is, for example, the host vehicle state of the vehicle 10, the relative relationship between the host vehicle and the preceding vehicle, the traffic flow situation, the location where the vehicle is traveling, and its time.

  Based on the current travel environment of the vehicle 10 acquired in step ST201 (for example, the location and time during which the vehicle 10 is traveling), the driving support ECU 11 stores a plurality of interrupt occurrence results data 31b stored in the database 31 in advance. Search for corresponding or similar data from the driving environment of the vehicle interruption scene. In this way, the driving support ECU 11 selects an interrupt occurrence record database (interrupt occurrence record data 31b) appropriate for use in predicting the occurrence of an interrupt according to the location and time during travel (step ST202). ).

  The driving support ECU 11 uses the interruption occurrence probability calculation unit 62 to obtain the vehicle interruption scene stored in the traveling environment related to the vehicle 10 acquired by the traveling environment acquisition unit 60 in step ST201 and the interruption occurrence result data 31b of the database 31. Compare with the driving environment. Then, the interrupt occurrence probability calculation unit 62 obtains an approximation degree between the two travel environments by this comparison, and calculates an interrupt occurrence probability P according to the magnitude of the approximation degree (step ST203). In step ST203, the interrupt occurrence probability calculation unit 62, when the degree of approximation between the current driving environment and the driving environment of the vehicle interruption scene in which the interruption has occurred in the past is large, the interrupt occurrence probability having a relatively large value. P is calculated. On the other hand, when the degree of approximation between the current driving environment and the driving environment of the vehicle interruption scene in which the interruption has occurred in the past is small, the interrupt occurrence probability calculating unit 62 sets the interrupt occurrence probability P having a relatively small value. Calculate.

  The driving support ECU 11 uses the interrupt prediction unit 64 to determine the interrupt occurrence stored in the interrupt occurrence probability P calculated by the interrupt occurrence probability calculation unit 62 in step ST203 and the interrupt occurrence result data 31b of the database 31. An interruption of a surrounding vehicle is predicted by comparison with the threshold C (steps ST204 to ST205, ST208). Specifically, when the interrupt prediction unit 64 determines in step ST204 that the interrupt occurrence probability P is greater than or equal to the interrupt occurrence determination threshold C (C ≦ P) (step ST204: Yes), Predict that there is a high probability of a vehicle interruption. Thereafter, the process proceeds to step ST206. On the other hand, when it is determined in step ST204 that the interrupt occurrence probability P is smaller than the interrupt occurrence determination threshold C (C> P) (step ST204: No), the interrupt prediction unit 64 receives an interrupt from a surrounding vehicle in step ST208. It is predicted that it will be uncertain. Thereafter, the process proceeds to step ST209.

  If the driving support ECU 11 predicts in step ST205 that there is a high possibility that an interruption of the surrounding vehicle will occur, the data update unit 70 generates an interruption based on the detection result of the interruption of the surrounding vehicle by the interruption detection unit 66. Is detected (step ST206). That is, in step ST206, the data update unit 70 determines whether the prediction result is correct based on the detection result of the interruption of the surrounding vehicle by the interruption detection unit 66 and the prediction result of the interruption of the surrounding vehicle by the interruption prediction unit 64. Determine. Here, the data updating unit 70 may store the correctness of the prediction result determined in step ST206 in association with the traveling environment of the vehicle interruption scene stored in the interruption occurrence result data 31b of the database 31.

  Here, if the driving assistance ECU 11 determines that the occurrence of an interrupt has been detected in step ST206 (step ST206: Yes), this process ends.

  On the other hand, when it determines with driving assistance ECU11 not having detected interruption generation | occurrence | production in step ST206 (step ST206: No), the magnitude | size of the value of interruption generation | occurrence | production determination threshold value C is used for determination by the data update part 70. It is updated to a value larger than the value of the immediately preceding interrupt occurrence determination threshold C (step ST207). In other words, in step ST207, when the prediction result that the possibility of the interruption of the surrounding vehicle is high is incorrect, the data updating unit 70 uses the interrupt used for predicting the interruption of the surrounding vehicle in step ST204. It is determined that the magnitude of the occurrence determination threshold C is not an appropriate value, and parameter adjustment is performed on the interrupt occurrence determination threshold C so that the prediction accuracy is improved. Thereafter, this process is terminated.

  The description of this process is continued from step ST208. If the driving support ECU 11 predicts in step ST208 that the interruption of the surrounding vehicle will be indeterminate, the data update unit 70 causes the interruption detection unit 66 to interrupt the surrounding vehicle based on the detection result of the interruption of the surrounding vehicle. It is determined whether or not occurrence has been detected (step ST209). That is, in step ST209, the data update unit 70 determines whether the prediction result is correct based on the detection result of the interruption of the surrounding vehicle by the interruption detection unit 66 and the prediction result of the interruption of the surrounding vehicle by the interruption prediction unit 64. Determine. Here, the data update unit 70 may store the correctness of the prediction result determined in step ST209 in association with the traveling environment of the vehicle interruption scene stored in the interruption occurrence result data 31b of the database 31.

  Here, when it determines with driving assistance ECU11 having detected interruption generation | occurrence | production in step ST209 (step ST209: Yes), the magnitude | size of the value of interruption generation | occurrence | production determination threshold value C is used for determination by the data update part 70. It is updated to a value smaller than the value of the interrupt occurrence determination threshold value C just before (step ST210). In other words, in step ST210, if the prediction result that the surrounding vehicle interrupt is uncertain is incorrect, the data updating unit 70 uses the rate used for predicting the surrounding vehicle interruption in step ST204. It is determined that the magnitude of the interruption occurrence determination threshold C is not an appropriate value, and parameter adjustment is performed on the interruption occurrence determination threshold C so that the prediction accuracy is improved. Thereafter, this process is terminated.

  On the other hand, when it determines with driving assistance ECU11 not having detected interruption generation | occurrence | production in step ST209 (step ST209: No), this process is complete | finished.

  Although not shown, the driving assistance ECU 11 predicts that an interrupt is highly likely to occur due to the above-described processing (step ST205) and / or detects that an interrupt has occurred (step ST206: Yes, In step ST209: Yes), the system control unit 72 causes the driving support apparatus 20 to perform driving support so as to avoid a collision with the interrupted vehicle.

  According to the embodiment described above, the driving environment of the past vehicle interruption scene stored in the interruption occurrence record data 31b of the database 31 is corrected as needed based on the actual driving environment of the vehicle interruption scene. Therefore, the information of the interrupt occurrence record data 31b is close to the actual vehicle interrupt scene, and the interrupt prediction accuracy of surrounding vehicles can be improved. For example, according to the above-described embodiment, the interrupt occurrence determination threshold C can be corrected so that the prediction and the result are likely to match in an environment where the interrupt prediction has been mistaken in the past, so that the prediction accuracy is further improved. be able to. Thus, according to the above-described embodiment, it is possible to improve the interrupt prediction accuracy of the vehicle, and therefore it is possible to implement appropriate driving support according to the situation based on the interrupt prediction result with high prediction accuracy. it can.

  According to the above-described embodiment, by detecting an interrupt in advance before detecting an interrupt by various sensors or the like, it is possible to perform driving support such as alerting the driver prior to the occurrence of the actual interrupt or the driver's awareness. it can. Thus, according to the above-described embodiment, the start of driving assistance can be accelerated compared to the case where the interruption is detected after the interruption of the vehicle occurs and driving assistance such as collision avoidance or warning to the driver is performed. Therefore, the possibility of a rear-end collision or the like can be reduced.

  In the above-described embodiment, the interrupt prediction unit 64 performs an analysis based on information acquired from each unit and acquires a prediction result, but is not limited thereto. The interrupt prediction unit 64 may acquire a prediction result calculated by another device. That is, a process of performing an analysis based on information and calculating a prediction result may be performed by another device. For example, a communication unit may be provided in the vehicle 10 to communicate with a server via the communication unit, and the prediction result may be acquired from the server.

[Modification 1 of Embodiment]
Here, with reference to FIGS. 5-6, the process in the modification 1 of this embodiment performed with the driving assistance system of the structure mentioned above is demonstrated. FIG. 5 is a diagram illustrating an example of a situation where a vehicle interruption occurs in the first modification of the present embodiment. FIG. 6 is a flowchart illustrating an example of the interrupt prediction process in Modification 1 of the present embodiment.

  In the first modification of the present embodiment, a situation is assumed in which an interruption of a surrounding vehicle as shown in FIG. 5 occurs. In the situation shown in FIG. 5, the surrounding vehicle 80-1, the surrounding vehicle 80-2, and the surrounding vehicle 80-3 travel in front of the vehicle 10 (the host vehicle), and the surrounding vehicle 80-4 and the surrounding vehicle behind the vehicle 10. 80-5 is running. Then, between the vehicle 10 and a surrounding vehicle 80-2 traveling in the same traveling lane as the vehicle 10, the surrounding vehicle 80-1 traveling in the traveling lane on the right side of the vehicle 10 is connected to the surrounding vehicle 80-. The lane is changed to the left front direction 102 with respect to the traveling direction of 1. That is, the surrounding vehicle 80-1 is interrupted between the vehicle 10 and the surrounding vehicle 80-2.

  An interrupt prediction process executed under the situation shown in FIG. 5 will be described with reference to FIG.

  As illustrated in FIG. 6, the driving assistance ECU 11 acquires a driving environment related to the vehicle 10 and surrounding vehicles by the driving environment acquisition unit 60 (step ST301). The travel environment acquired in step ST301 includes, for example, the host vehicle state of the vehicle 10 (such as the travel speed and acceleration of the vehicle 10 in FIG. 5), and the relative relationship between the host vehicle and the preceding vehicle (in FIG. The distance between the surrounding vehicles 80-1 to 80-3, relative speed, relative position, etc.) and the relative relationship between the preceding vehicle and the surrounding vehicle (in FIG. 5, for example, the surrounding vehicle 80-1 (the preceding vehicle) and the surrounding vehicle 80 -2-5, inter-vehicle distance, relative speed, relative position, etc.), traffic flow status (high congestion in the example of FIG. 5), traveling location and its time, and the like.

  The driving support ECU 11 stores a plurality of interrupt occurrence results data 31b stored in advance in the database 31 based on the current traveling environment of the vehicle 10 acquired in step ST301 (for example, the location or time during which the vehicle 10 is traveling). Search for corresponding or similar data from the driving environment of the vehicle interruption scene. In this manner, the driving assistance ECU 11 selects a database of interrupt occurrence results (interrupt occurrence result data 31b) appropriate for use in predicting the occurrence of interrupts according to the location and time during travel (step ST302). ).

  Here, in the first modification, the driving support ECU 11 performs the following processing in step S303 and processing in step S304 in parallel using the interruption occurrence record database selected in step ST302.

  The driving assistance ECU 11 uses the interrupt occurrence probability calculation unit 62 to acquire the travel environment related to the vehicle 10 acquired by the travel environment acquisition unit 60 in step ST301 (for example, the current host vehicle state, the relative relationship between the host vehicle and the preceding vehicle, The traffic flow status and the like are compared with the traveling environment of the vehicle interruption scene stored in the interruption occurrence result data 31b of the database 31. Then, the interrupt occurrence probability calculating unit 62 obtains an approximation degree between the two travel environments by this comparison, and calculates an interrupt occurrence probability P according to the magnitude of the approximation degree (step ST303). In step ST303, when the degree of approximation between the current driving environment and the driving environment of the vehicle interruption scene in which an interrupt has occurred in the past is large, the interrupt occurrence probability calculating unit 62 has a relatively large value of the interrupt occurrence probability. P is calculated. On the other hand, when the degree of approximation between the current driving environment and the driving environment of the vehicle interruption scene in which the interruption has occurred in the past is small, the interrupt occurrence probability calculating unit 62 sets the interrupt occurrence probability P having a relatively small value. Calculate. Thereafter, the process proceeds to step ST305.

  The driving assistance ECU 11 determines the driving environment (for example, the current surrounding vehicle state and the relative relationship between the preceding vehicle and the surrounding vehicle) acquired by the driving environment acquisition unit 60 in step ST301 by the interrupt occurrence probability calculating unit 62. , Traffic flow conditions, etc.) and the traveling environment of the vehicle interruption scene stored in the interruption occurrence result data 31b of the database 31 are compared. Then, the interrupt occurrence probability calculation unit 62 obtains an approximation degree between the two travel environments by this comparison, and an interrupt occurrence probability Pi (i = 1, 2, n) according to the magnitude of the approximation degree. Is calculated for each surrounding vehicle (step ST304). Thereafter, the process proceeds to step ST305.

  The driving support ECU 11 determines, with respect to all i, whether or not the interrupt occurrence probability P related to the own vehicle is larger than the interrupt occurrence probability Pi related to the surrounding vehicle by the interrupt prediction unit 64 (step ST305). Here, it is considered that a vehicle that wants to change lanes is going to interrupt somewhere between a plurality of traveling vehicles. Therefore, as shown in FIG. 5, the interrupt occurrence probability P indicating the probability that the surrounding vehicle 80-1 interrupts between the vehicle 10 and the surrounding vehicle 80-2 is set in front of the surrounding vehicle 80-2 or the surrounding vehicle 80-5. If it is larger than the interrupt occurrence probability Pi indicating the probability of the surrounding vehicle 80-1 interrupting before the vehicle, it is determined that the possibility of the surrounding vehicle 80-1 interrupting between the vehicle 10 and the surrounding vehicle 80-2 is high. it can. Therefore, in step ST305, the interrupt predicting unit 64 determines whether or not the interrupt occurrence probability P related to the host vehicle is greater than the interrupt occurrence probability Pi related to the surrounding vehicle with respect to all i. The interruption of the surrounding vehicle 80-1 ahead is predicted.

  Here, the driving support ECU 11 determines that the interrupt occurrence probability P related to the own vehicle is larger for all i than the interrupt occurrence probability Pi related to surrounding vehicles (P> Pi) by the interrupt prediction unit 64 in step ST305. When it does (step ST305: Yes), it estimates that the possibility that the surrounding vehicle 80-1 will interrupt ahead of the vehicle 10 is high (step ST306). Thereafter, this process is terminated.

  On the other hand, when the driving support ECU 11 determines by the interrupt prediction unit 64 that the interrupt occurrence probability P related to the host vehicle is not greater than the interrupt occurrence probability Pi related to the surrounding vehicle in step ST305 (step i). ST305: No), it is predicted that it is indeterminate whether the surrounding vehicle 80-1 cuts in front of the vehicle 10 (step ST307). Thereafter, this process is terminated.

  Although not shown, when the driving assistance ECU 11 predicts that there is a high possibility that the surrounding vehicle 80-1 will interrupt the front of the vehicle 10 by the above-described processing (step ST306), the system control unit 72 causes the interrupting vehicle to The driving support device 20 is made to perform driving support so as to avoid a collision with the vehicle.

  According to the first modification of the embodiment described above, the interrupt occurrence probability P related to the host vehicle and the interrupt occurrence probability Pi related to the surrounding vehicle are calculated, and the relative relationship between the interrupt occurrence probability P and the interrupt occurrence probability Pi is calculated. Therefore, the occurrence of an interrupt can be predicted. Thus, according to the first modification of the above-described embodiment, when the occurrence of an interrupt is predicted, the interrupt generation determination threshold C as illustrated in FIG. 4 of the above-described embodiment is not necessary. Instead, according to the first modification of the embodiment described above, the relative magnitudes of the interrupt occurrence probability P and the interrupt occurrence probability Pi are compared. Thus, the interrupt occurrence probability P indicating the probability that the interrupting vehicle will be interrupted ahead of the vehicle 10 is the interrupt indicating the probability that the interrupting vehicle will be interrupted ahead of other peripheral vehicles other than the vehicle 10. When it is larger than the occurrence probability Pi, it can be determined that there is a high possibility that the interrupting vehicle will interrupt the front of the vehicle 10.

[Modification 2 of the embodiment]
Furthermore, with reference to FIGS. 7-8, the process in the modification 2 of this embodiment performed with the driving assistance system of the structure mentioned above is demonstrated. FIG. 7 is a diagram illustrating an example of a situation where a vehicle interruption occurs in the second modification of the present embodiment. FIG. 8 is a flowchart illustrating an example of an interrupt detection process according to the second modification of the present embodiment.

  Modification 2 of the present embodiment assumes a situation in which an interruption of a surrounding vehicle as shown in FIG. 7 occurs. In the situation shown in FIG. 7, the surrounding vehicle 80-1 and the surrounding vehicle 80-2 are traveling ahead of the vehicle 10 (own vehicle). Here, the vehicle 10 holds the prediction result 104 that the surrounding vehicle 80-1 interrupts between the vehicle 10 and the surrounding vehicle 80-2 in advance. Then, between the vehicle 10 and a surrounding vehicle 80-2 traveling in the same traveling lane as the vehicle 10, the surrounding vehicle 80-1 traveling in the traveling lane on the right side of the vehicle 10 is connected to the surrounding vehicle 80-. The lane is changed to the left front direction 102 with respect to the traveling direction of 1. That is, the surrounding vehicle 80-1 is interrupted between the vehicle 10 and the surrounding vehicle 80-2.

  An interrupt prediction process executed under the situation shown in FIG. 7 will be described with reference to FIG.

  As shown in FIG. 8, the driving assistance ECU 11 acquires the driving environment by the driving environment acquisition unit 60 (step ST401). The travel environment acquired in step ST401 is the same as the travel environment acquired in step ST201 of FIG. 4 or step ST301 of FIG.

  The driving support ECU 11 uses the interrupt prediction unit 64 to acquire the travel environment related to the current vehicle 10 acquired by the travel environment acquisition unit 60 in step ST401 and past vehicle discounts stored in the interrupt occurrence result data 31b of the database 31. Based on the interrupt occurrence probability P calculated by comparison with the driving environment of the crowded scene, an interruption of the surrounding vehicle ahead of the vehicle 10 is predicted (step ST402). In step ST402, the interrupt prediction unit 64 predicts an interruption of a surrounding vehicle ahead of the vehicle 10 by performing the same process as the interrupt prediction process shown in FIG. 4 or FIG.

  The driving assistance ECU 11 detects an object in front of the vehicle 10 present at an appropriate position as an interrupted vehicle via the in-vehicle camera 42 and the in-vehicle radar 43 by the interrupt detection unit 66 (step ST403).

  Here, in the second modification, the driving assistance ECU 11 determines whether or not an interruption of a surrounding vehicle ahead of the vehicle 10 is predicted by the interrupt prediction unit 64 in step ST402 (step ST404).

  When the driving assistance ECU 11 determines in step ST404 that an interruption of a surrounding vehicle ahead of the vehicle 10 is predicted (step ST404: Yes), the interrupt detection unit 66 terminates the initial detection process of the interrupt determination. Detect interrupts without waiting. In other words, in step ST403, the interrupt detection unit 66 does not wait for the end of the initial discovery process such as determining whether or not the detected object is an interrupted vehicle using an interrupt detection method such as image processing, for example. Detects an interruption of a surrounding vehicle ahead of. Thereafter, this process is terminated.

  On the other hand, if the driving assistance ECU 11 determines in step ST404 that the interruption of the surrounding vehicle ahead of the vehicle 10 is not predicted (step ST404: No), the driving assistance ECU 11 performs the interruption detection according to the normal process (step ST406). That is, in step ST404, the interrupt detection unit 66 detects, for example, an object (target) in front of the vehicle 10 with the in-vehicle camera 42 or the in-vehicle radar 43, and detects the detected object using an interrupt detection method such as image processing. It is determined whether or not is an interrupting vehicle, and an interruption of a surrounding vehicle is detected. Thereafter, this process is terminated.

  Although not shown, when the driving support ECU 11 detects that the surrounding vehicle 80-1 has interrupted the front of the vehicle 10 by the above-described processing, the system control unit 72 avoids a collision with the interrupting vehicle. Then, the driving support device 20 is caused to perform driving support.

  According to the second modification of the above-described embodiment, when it is predicted by the interrupt prediction unit 64 that there is a high possibility that an interrupt will occur, the interrupt detection unit 66 immediately detects some target at an appropriate distance. It can be determined that an interrupt has occurred. Thus, according to the second modification of the above-described embodiment, the interrupt detection unit 66 interrupts the detected object using an interrupt detection method such as image processing according to the prediction result by the interrupt prediction unit 64. It is possible to shorten the initial discovery process of determining whether the vehicle is a vehicle. As a result, according to the second modification of the above-described embodiment, the possibility that the start of driving support is delayed can be reduced, and the avoidance rate of rear-end collisions and collision accidents with respect to interrupted vehicles can be improved.

10 Vehicle (own vehicle)
11 Driving assistance ECU
12 Brake ECU
13 Engine ECU
14 Steering ECU
20 Driving support device 21 Brake 22 Engine 24 Output device 24a Speaker 24b Display 30 Car navigation 31 Database 31a Map data 31b Interrupt generation result data 40 Inter-vehicle communication device 41 Infrastructure communication device 42 In-vehicle camera 43 In-vehicle radar 44 GPS
45 Vehicle speed sensor 46 Acceleration sensor 47 Gyro sensor 48 Brake sensor 49 Accelerometer sensor 50 Steering angle sensor 51 Surrounding environment information acquisition means 52 Own vehicle information acquisition means 60 Driving environment acquisition part 62 Interrupt occurrence probability calculation part 64 Interrupt prediction part 66 Detection unit 68 database creation unit 70 data update unit 72 system control unit 80-1-5 peripheral vehicle

Claims (4)

An interrupt prediction device for predicting a vehicle interruption,
A driving environment acquisition unit that acquires a driving environment related to the host vehicle;
Based on the interruption occurrence probability calculated by comparing the traveling environment regarding the current vehicle acquired by the traveling environment acquisition unit with the traveling environment of the past vehicle interruption scene stored in the storage device, An interrupt prediction unit for predicting an interruption of a surrounding vehicle ahead of the host vehicle;
An interrupt detection unit for detecting an interruption of the surrounding vehicle;
A data update unit that updates the traveling environment of the vehicle interruption scene stored in the storage device based on the traveling environment related to the host vehicle acquired when the interruption detection unit detects an interruption of the surrounding vehicle. When,
With
The interrupt prediction unit
An interruption prediction apparatus that predicts an interruption of the surrounding vehicle using a traveling environment of the vehicle interruption scene updated by the data update unit. The interrupt prediction unit
Predicting the interruption of the surrounding vehicle by comparing the interrupt occurrence probability and the interrupt occurrence determination threshold stored in the storage device,
The data update unit
Based on the detection result of the interruption of the surrounding vehicle by the interrupt detection unit and the prediction result of the interruption of the surrounding vehicle by the interruption prediction unit, the correctness of the prediction result is determined, and the prediction result is incorrect. The interrupt prediction device according to claim 1, wherein the interrupt occurrence determination threshold relating to a traveling environment of the corresponding vehicle interrupt scene is changed. A driving support system comprising the interrupt prediction device according to claim 1, a driving support device that implements driving support for the host vehicle,
The interrupt prediction device
A system control unit that calculates a control amount for controlling the driving support device based on the prediction result by the interrupt prediction unit, and causes the driving support device to implement the driving support based on the calculated control amount. A driving support system, further comprising: An interrupt prediction method for predicting vehicle interruption,
A driving environment acquisition step for acquiring a driving environment related to the own vehicle;
Based on the interrupt occurrence probability calculated by comparing the travel environment related to the host vehicle acquired in the travel environment acquisition step and the travel environment of the vehicle interrupt scene stored in the storage device, An interrupt prediction step for predicting an interruption of a surrounding vehicle ahead;
An interrupt detection step for detecting an interruption of the surrounding vehicle;
An update step of updating the traveling environment of the vehicle interruption scene stored in the storage device based on the traveling environment related to the host vehicle acquired when the interruption of the surrounding vehicle is detected in the interrupt detection step. When,
Including
In the interrupt prediction step,
An interruption prediction method, wherein an interruption of the surrounding vehicle is predicted using a traveling environment of the vehicle interruption scene updated in the updating step.

Images