Hazard prediction device, hazard prediction method, and recording medium

Abstract

This risk prediction device: detects events suggesting risks that a vehicle may encounter, on the basis of measurement information obtained by measuring the surrounding conditions of the vehicle using an ambient environment sensor; determines whether the events are dynamic events or static events; determines whether or not basic determination items are applicable on the basis of the dynamic-event-related surrounding conditions of the vehicle; if the events include a static event, adds at least one determination item to the basic determination items and also determines whether or not the added at least one determination item is applicable on the basis of the static-event-related surrounding conditions of the vehicle; and calculates information indicating the degree of risk of the situation in which the vehicle is located on the basis of the plurality of determination items determined, except for the determination items determined not to be applicable.

Description

Technical Field

[0001] The present disclosure relates to a risk prediction apparatus, a risk prediction method, and a recording medium. Background Art

[0002] As one form of driving assistance apparatus that assists a driver in driving a vehicle, there exists a system that predicts risks encountered by the vehicle and notifies the driver of the risks. For example, Patent Document 1 proposes a technique that achieves accurate risk prediction in accordance with surrounding conditions. Specifically, Patent Document 1 discloses a technique in which: observation information related to the surrounding conditions of a vehicle is acquired; the acquired observation information is converted into a logical expression representing the surrounding conditions of the vehicle; hazards that arise during vehicle driving and general knowledge are expressed as logical expressions, and using a knowledge base which is a set of such rules, proof is performed with risks predicted from the logical expressions as proof targets by weighted hypothesis reasoning; the risk level of the proven risk is obtained from the proof cost obtained in the reasoning process; and the logical expression used for the proof is associated with the observation information. Prior Art Document Patent Document

[0003] Patent Document 1 Japanese Patent Application Laid-Open No. 2016-91039 Summary of the Invention Problems to be Solved by the Invention

[0004] However, the technique disclosed in the above-mentioned Patent Document 1 calculates a risk level based on the designer's subjectivity and learning, and has a configuration that cannot logically explain why the risk level is indicated as such. For this reason, there is a possibility that the user cannot acceptably and confidently use the driving assistance function. In addition, in the technique disclosed in the above-mentioned Patent Document 1, it is unclear how to calculate the risk level when, for example, a plurality of pieces of observation information suggesting a pedestrian jumping out in front of the vehicle are obtained, so practical problems remain.

[0005] This disclosure has been made in view of the above-mentioned issues, and its purpose is to provide a hazard prediction device, a hazard prediction method, and a recording medium that can logically calculate hazards in various situations in which a vehicle may be placed and improve the reliability of driver assistance functions. [Means for solving the problem]

[0006] To solve the above problems, according to one aspect of this disclosure, a hazard prediction device for predicting hazards that a vehicle may encounter comprises one or more processors and one or more memories connected to the one or more processors in a communicative manner, wherein the one or more processors perform the following: a process of acquiring measurement information obtained by measuring the conditions around the vehicle using ambient environment sensors; a process of detecting events that suggest hazards that the vehicle may encounter based on the acquired measurement information; a process of determining whether the event is a dynamic event in which the degree of hazard can change depending on the situation, or a static event in which the degree of hazard does not change regardless of the situation; and the detection of the hazard A hazard prediction device is provided that performs the following steps: determine whether a basic determination item, which has multiple determination items related to life, is applicable based on the surrounding conditions of the vehicle related to the dynamic event; further, if the event includes the static event, add at least one determination item to the basic determination item and determine whether the added determination item is applicable based on the surrounding conditions of the vehicle related to the static event; and calculate information indicating the degree of danger in the situation in which the vehicle is located, based on the remaining determination items after excluding the determination items that have been determined not to be applicable from among the multiple determination items whose applicability has been determined.

[0007] Furthermore, in order to solve the above problems, another aspect of this disclosure provides a hazard prediction method for predicting hazards that a vehicle may encounter, the method comprising: one or more processors acquiring measurement information obtained by measuring the conditions around the vehicle using ambient environment sensors; detecting events that suggest hazards that the vehicle may encounter based on the acquired measurement information; determining whether the events are dynamic events where the degree of danger may change depending on the situation, or static events where the degree of danger does not change regardless of the situation; determining whether a basic determination item, which has a set of multiple determination items related to the occurrence of the hazard, is applicable based on the conditions around the vehicle related to the dynamic event; further, if the event includes the static event, adding at least one determination item to the basic determination item and determining whether the added determination item is applicable based on the conditions around the vehicle related to the static event; and calculating information indicating the degree of danger in the situation in which the vehicle is in based on the remaining determination items, after excluding the determination items that have been determined not to be applicable from among the multiple determination items in which the degree of applicability has been determined.

[0008] Furthermore, in order to solve the above problems, according to another aspect of this disclosure, one or more processors acquire measurement information obtained by measuring the conditions around the vehicle using ambient environment sensors, A non-temporary tangible recording medium is provided, which records a computer program that performs the following actions: detecting events that suggest dangers the vehicle may encounter based on the acquired measurement information; determining whether the events are dynamic events, where the degree of danger may change depending on the situation, or static events, where the degree of danger does not change regardless of the situation; determining whether a basic determination item, which has multiple determination items related to the occurrence of the danger, applies to the dynamic event based on the surrounding conditions of the vehicle; further, if the event includes the static event, adding at least one determination item to the basic determination item and determining whether the added determination item applies to the static event based on the surrounding conditions of the vehicle; and calculating information indicating the degree of danger in the situation the vehicle is in, based on the remaining determination items after excluding the determination items that have been determined not to apply from among the multiple determination items whose applicability has been determined. [Effects of the Invention]

[0009] As explained above, this disclosure makes it possible to logically calculate the degree of risk in various situations in which a vehicle may be placed, thereby improving the reliability of driver assistance functions. [Brief explanation of the drawing]

[0010] [Figure 1] This is a schematic diagram showing an example of the configuration of a vehicle equipped with a driver assistance device (hazard prediction device) according to one embodiment of the present disclosure. [Figure 2] This is a block diagram showing an example configuration of a driver assistance system according to the same embodiment. [Figure 3] This is a flowchart showing the main routine of the processing operation by the driver assistance device according to the same embodiment. [Figure 4] This is a flowchart of the judgment item setting process by the driver assistance device according to the same embodiment. [Figure 5] This is an explanatory diagram showing the situation of a first example of hazard prediction processing by the driver assistance device according to the same embodiment. [Figure 6]It is an explanatory diagram showing a first example of risk prediction processing performed by the driving support apparatus according to the present embodiment. [Figure 7] It is an explanatory diagram showing the situation of a second example of risk prediction processing performed by the driving support apparatus according to the present embodiment. [Figure 8] It is an explanatory diagram showing the second example of risk prediction processing performed by the driving support apparatus according to the present embodiment. [Figure 9] It is an explanatory diagram showing the situation of a third example of risk prediction processing performed by the driving support apparatus according to the present embodiment. [Figure 10] It is an explanatory diagram showing the third example of risk prediction processing performed by the driving support apparatus according to the present embodiment. [Figure 11] It is an explanatory diagram showing the situation of a fourth example of risk prediction processing performed by the driving support apparatus according to the present embodiment. [Figure 12] It is an explanatory diagram showing the fourth example of risk prediction processing performed by the driving support apparatus according to the present embodiment. DESCRIPTION OF EMBODIMENTS

[0011] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the present specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

[0012] In the following description, the driving support apparatus has a function as the risk prediction apparatus of the present disclosure.

[0013] <1. Overall configuration of vehicle> First, an example of the overall configuration of a vehicle including a driving support apparatus that functions as a risk prediction apparatus according to an embodiment of the present disclosure will be described.

[0014] FIG. 1 is a schematic diagram showing a configuration example of a vehicle 1. Vehicle 1 is configured as a two-wheel drive four-wheeled motor vehicle that transmits drive torque output from a driving force source 9 that generates drive torque to the left front wheel and the right front wheel. The driving force source 9 may be an internal combustion engine such as a gasoline engine or a diesel engine, may be a driving motor, or may include both an internal combustion engine and a driving motor.

[0015] Note that vehicle 1 may be a four-wheel drive vehicle that transmits drive torque to front wheels and rear wheels. Further, vehicle 1 may be, for example, an electric vehicle provided with two driving motors, a front-wheel driving motor and a rear-wheel driving motor, or may be an electric vehicle provided with a driving motor corresponding to each wheel. Further, when vehicle 1 is an electric vehicle or a hybrid electric vehicle, vehicle 1 is equipped with a secondary battery that stores electric power supplied to the driving motor, and a generator such as a motor or a fuel cell that generates electric power to be charged into the battery.

[0016] Vehicle 1 includes, as devices used for driving control of vehicle 1, a driving force source 9, an electric steering device 15, and brake devices 17LF, 17RF, 17LR, 17RR (hereinafter collectively referred to as "brake device 17" when no particular distinction is required). The driving force source 9 outputs drive torque that is transmitted to a front wheel drive shaft 5F via a transmission and a differential mechanism 7 (not shown). The driving of the driving force source 9 and the transmission is controlled by a vehicle control unit 41 configured to include one or more electronic control units (ECUs).

[0017] The front wheel drive shaft 5F is provided with the electric steering device 15. The electric steering device 15 includes an electric motor and a gear mechanism (not shown), and adjusts the steering angle of the front wheels when controlled by the vehicle control unit 41. During manual driving, the vehicle control unit 41 controls the electric steering device 15 based on the steering angle of the steering wheel 13 by the driver. Further, during automatic driving, the vehicle control unit 41 controls the electric steering device 15 based on a set steering angle or steering angular velocity.

[0018] Brake units 17LF, 17RF, 17LR, and 17RR apply braking force to their respective wheels. Brake units 17 are configured, for example, as hydraulic brakes. The vehicle control unit 41 adjusts the hydraulic pressure supplied to each brake unit 17 by controlling the drive of the hydraulic unit 16. If the vehicle 1 is an electric vehicle or a hybrid electric vehicle, the brake units 17 are used in conjunction with regenerative braking by the drive motor.

[0019] The vehicle control unit 41 includes one or more electronic control devices that control the drive of the power source 9, the electric steering device 15, and the hydraulic unit 16. If the vehicle 1 is equipped with a transmission that changes the speed of the output from the power source 9 and transmits it to the wheels 3, the vehicle control unit 41 has a function to control the drive of the transmission. The vehicle control unit 41 is configured to be able to acquire information transmitted from the driver assistance device 50 and to be able to perform automatic driving control of the vehicle 1.

[0020] Vehicle 1 is also equipped with front-facing cameras 31LF, 31RF, a rear-facing camera 31R, a vehicle status sensor 33, a vehicle position sensor 35, and a notification device 43.

[0021] The front-facing cameras 31LF, 31RF and the rear-facing camera 31R constitute an ambient environment sensor for acquiring information about the surrounding environment of the vehicle 1. The front-facing cameras 31LF, 31RF capture images of the area in front of the vehicle 1 and generate image data. The rear-facing camera 31R captures images of the area behind the vehicle 1 and generates image data. The front-facing cameras 31LF, 31RF and the rear-facing camera 31R are equipped with image sensors such as CCD (Charged Coupled Devices) or CMOS (Complementary Metal Oxide Semiconductor) and transmit the generated image data to the driver assistance device 50. In the vehicle 1 shown in Figure 1, the front-facing cameras 31LF, 31RF are configured as a stereo camera including a pair of left and right cameras, but the front-facing camera may be a monocular camera.

[0022] In addition to the forward-facing cameras 31LF and 31RF, the surrounding environment sensor may also include, for example, a camera mounted on a side mirror to capture images of the left rear or right rear. Furthermore, the surrounding environment sensor may include one or more sensors from among LiDAR (Light Detection and Ranging), radar sensors such as millimeter-wave radar, and ultrasonic sensors.

[0023] The vehicle state sensor 33 consists of at least one sensor that detects the operating state and behavior of the vehicle 1. The vehicle state sensor 33 includes, for example, at least one of a steering angle sensor, accelerator position sensor, brake stroke sensor, brake pressure sensor, or engine speed sensor. The vehicle state sensor 33 also includes, for example, at least one of a vehicle speed sensor, acceleration sensor, or angular velocity sensor. The vehicle state sensor 33 transmits a sensor signal indicating the detected information to the driver assistance device 50.

[0024] The vehicle position sensor 35 receives satellite signals from GNSS (Global Navigation Satellite System) positioning satellites, such as GPS (Global Positioning System). The vehicle position sensor 35 transmits the vehicle position information of vehicle 1 contained in the received satellite signals to the driver assistance device 50. In addition to the GPS sensor, the vehicle position sensor 35 may also be equipped with an antenna that receives satellite signals from other satellite systems that determine the position of vehicle 1.

[0025] The notification device 43 is driven by the driver assistance device 50 and notifies the driver of various information by means of image display, audio output, etc. The notification device 43 includes, for example, a display device provided in the instrument panel and a speaker provided in the vehicle 1. The display device may be a display device of a navigation system. The notification device 43 may also include a HUD (head-up display) that displays information on the front windshield superimposed on the scenery around the vehicle 1.

[0026] <2. Driving Assistance Systems> Next, the driver assistance device 50 according to this embodiment will be described in detail.

[0027] (2-1. Example Configuration) The driver assistance device 50 functions as a device that assists the driving of a vehicle by having one or more CPUs (Central Processing Units) or other processors execute a computer program. The computer program is a computer program that causes the processor to execute the operations that the driver assistance device 50 should perform, as described later. The computer program executed by the processor may be recorded on a recording medium that functions as a memory 53 provided in the driver assistance device 50, or it may be recorded on a recording medium built into the driver assistance device 50 or on any external recording medium that can be attached to the driver assistance device 50.

[0028] Recording media for storing computer programs may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs, DVDs, and Blu-ray®; magneto-optical media such as floppy disks; memory elements such as RAM and ROM; flash memory such as USB memory and SSDs; and other media capable of storing programs.

[0029] Figure 2 is a block diagram showing an example configuration of the driver assistance device 50 according to this embodiment. The driver assistance device 50 is connected to an ambient environment sensor 31, a vehicle status sensor 33, and a vehicle position sensor 35 via a dedicated line or a communication means such as CAN (Controller Area Network) or LIN (Local Internet). The driver assistance device 50 is also connected to a vehicle control unit 41 and a notification device 43. Note that the driver assistance device 50 is not limited to an electronic control unit mounted on the vehicle 1, but may also be a terminal device such as a smartphone or wearable device.

[0030] The driver assistance device 50 includes a processing unit 51, a storage unit 53, a map data storage unit 55, and a judgment item storage unit 57. The processing unit 51 is composed of one or more processors such as a CPU and various peripheral components. Part or all of the processing unit 51 may be composed of updatable components such as firmware, or it may be a program module that is executed by commands from the CPU, etc.

[0031] (Storage part) The memory unit 53 is composed of one or more memory elements such as RAM or ROM that are connected to the processing unit 51 in a communicative manner. However, the type and number of memory units 53 are not particularly limited. The memory unit 53 stores computer programs executed by the processing unit 51, various parameters used in arithmetic processing, detection data, calculation results, and other information. A portion of the memory unit 53 is used as the work area of ​​the processing unit 51.

[0032] (Map data storage unit) The map data storage unit 55 is composed of a memory element such as RAM or ROM, or a storage medium such as an HDD, CD, DVD, SSD, USB flash drive, or storage device, which is connected to the processing unit 51 in a communicative manner. The map data stored in the map data storage unit 55 contains information that allows the position of the vehicle 1 to be identified based on the position information detected by the vehicle position sensor 35. For example, the map data is associated with latitude and longitude information, and the processing unit 51 can identify the position of the vehicle 1 on the map data based on the latitude and longitude information of the vehicle 1 detected by the vehicle position sensor 35.

[0033] (Judgment item storage unit) The judgment item storage unit 57 is composed of a memory element such as RAM or ROM, or a storage medium such as an HDD, CD, DVD, SSD, USB flash drive, or storage device, which is connected to the processing unit 51 in a communicative manner. The judgment item storage unit 57 stores judgment items for calculating the degree of danger in the situation in which the vehicle 1 is located. The judgment item storage unit 57 stores basic judgment items, which include multiple judgment items set for one or more risk targets. The judgment item storage unit 57 also stores judgment items that are added to the basic judgment items.

[0034] The basic determination items include multiple determination items whose applicability is determined based on the circumstances surrounding Vehicle 1 related to dynamic events that suggest dangers that Vehicle 1 may encounter, as described later. Dynamic events refer to events whose degree of danger can change depending on the circumstances. For example, dynamic events are events whose existence, location, speed, or size changes depending on the time. More specific examples include "a ball rolling on the road," "another vehicle having stopped," or "a bus stopped at a bus stop."

[0035] The basic judgment items include one or more judgment items that represent the factors associated with a risk object that could cause danger to vehicle 1, leading up to the occurrence of that danger. Examples of risk objects include moving objects such as "people," "bicycles," or "cars," but other moving objects or stationary objects may also be used. For example, if the risk object is a moving object such as "people," "bicycles," or "cars," then six judgment items are set to represent the factors associated with these moving objects leading up to the occurrence of danger to vehicle 1: "people (bicycles, cars) are present," "they are moving," "they are heading in the direction of the vehicle's travel," "they are continuing," "they jump out," and "they do not jump out (No)."

[0036] The additional judgment items are those that are added to the basic judgment items when static events that suggest dangers that vehicle 1 may encounter are detected, as described later. Static events refer to events whose degree of danger does not change depending on the situation. For example, static events are events whose existence, location, speed, and size do not change with time. More specific examples include "there is a pedestrian crossing" or "there is an entrance to a park." Since the degree of danger does not change for these static events themselves, a judgment item is set to indicate whether or not danger ultimately occurs (whether or not the vehicle will suddenly appear) as a judgment item that represents the factors that cause danger to vehicle 1.

[0037] The content of the basic judgment items and additional judgment items may be set based on the results of learning the surrounding conditions of the vehicle when the vehicle encountered danger in various past driving scenarios, or they may be arbitrarily set according to the dangers that are anticipated in advance.

[0038] (2-2. Configuration of the Processing Unit) Next, the configuration of the processing unit 51 of the driver assistance device 50 will be described. The processing unit 51 includes an acquisition unit 61, a situation recognition processing unit 63, an event detection unit 65, a matching / false determination unit 67, a risk level calculation unit 69, and a risk response processing unit 71. Each of these units is a function realized by the execution of a computer program by one or more processors such as a CPU. However, some or all of the acquisition unit 61, situation recognition processing unit 63, event detection unit 65, matching / false determination unit 67, risk level calculation unit 69, and risk response processing unit 71 may be configured using analog circuits.

[0039] (Acquisition Department) The acquisition unit 61 acquires measurement information obtained by the ambient environment sensor 31 at a predetermined sampling period, which measures the conditions around the vehicle 1. In this embodiment, the acquisition unit 61 acquires image data transmitted from the front-facing cameras 31LF, 31RF and the rear-facing camera 31R. If the ambient environment sensor 31 includes sensors other than the front-facing cameras 31LF, 31RF and the rear-facing camera 31R, such as LiDAR or radar sensors, the acquisition unit 61 acquires measurement information such as point cloud data of measurement points from each of these sensors.

[0040] (Situation Awareness Processing Unit) The situation recognition processing unit 63 recognizes the surrounding environment of vehicle 1 based on measurement information acquired from the surrounding environment sensor 31. For example, the situation recognition processing unit 63 extracts feature points from image data or point cloud data and recognizes objects by matching the shape of the feature points with pre-prepared reference data. The situation recognition processing unit 63 recognizes various objects, including moving objects such as people, bicycles, motorcycles, and four-wheeled vehicles, as well as artificial or natural stationary objects and lines drawn on roads such as white lines and crosswalks. The situation recognition processing unit 63 also calculates the position and speed of the recognized object, as well as the distance to the object. This allows the surrounding environment of vehicle 1 to be understood.

[0041] The surrounding environment sensor 31 may perform processing to recognize these moving objects and stationary objects. In this case, the driver assistance device 50 acquires measurement information, including the recognition results, from the surrounding environment sensor 31.

[0042] (Event detection unit) The event detection unit 65 detects events that suggest dangers that vehicle 1 may encounter, based on the surrounding conditions of vehicle 1 recognized by the situation recognition processing unit 63. The event detection unit 65 also determines whether the detected event is a dynamic event, where the degree of danger may change depending on the situation, or a static event, where the degree of danger does not change regardless of the situation.

[0043] "Events that suggest dangers the vehicle may encounter" refer to objects or situations that foreshadow collisions, skidding, or other situations that may cause the driver of vehicle 1 to feel danger. In this embodiment, "something suddenly appearing in front of the vehicle from a blind spot" will be used as an example to explain the dangers that vehicle 1 may encounter.

[0044] Examples of events suggesting "something suddenly appearing in front of the vehicle from a blind spot" include situations where a blind spot is detected in front of vehicle 1 in the direction of travel, and "a pedestrian crossing exists" on the road vehicle 1 is traveling on, near the blind spot. Furthermore, examples of events suggesting "something suddenly appearing in front of the vehicle from a blind spot" include situations where a blind spot is detected in front of vehicle 1 in the direction of travel, and "a ball rolls out from the blind spot" or "the vehicle stops temporarily near the blind spot."

[0045] The event detection unit 65 detects the existence of a blind spot when it recognizes a three-dimensional object in front of the vehicle 1 in the direction of travel, based on the acquired measurement information. The event detection unit 65 may also detect the existence of a blind spot where an object could suddenly appear when it recognizes a three-dimensional object that is at least large enough to hide a person. The method for detecting a blind spot based on the measurement information of the surrounding environment sensor 31 is not particularly limited and may be a conventionally known method.

[0046] Furthermore, when the event detection unit 65 detects a blind spot, it also searches for events that exist around the blind spot and suggest a sudden appearance from that blind spot. For example, the event detection unit 65 detects events such as "the presence of a pedestrian crossing," "a ball rolling out from the blind spot," or "a vehicle stopping near the blind spot" as events that suggest a sudden appearance from a blind spot. The event detection unit 65 extracts the relevant events based on the measurement information of the surrounding environment sensor 31 using known matching processes or the like.

[0047] Furthermore, the event detection unit 65 determines that an event is a dynamic event if its level of danger can change depending on the situation. For example, if the event detected is "a ball rolling out from a blind spot" or "a vehicle stopped near a blind spot," the event detection unit 65 determines these to be dynamic events where the level of danger can change depending on changes in the ball's position or speed, or changes in the position or speed of the stopped vehicle. On the other hand, if the event detected is "a static event" if its level of danger does not change regardless of the situation, the event detection unit 65 determines that it is a static event where the level of danger does not change depending on the situation. For example, if the event detected is "a pedestrian crossing," the event detection unit 65 determines that the pedestrian crossing is a static object that does not show any changes, and therefore the level of danger does not change depending on the situation. These dynamic and static events that suggest something jumping out from a blind spot are pre-set according to "events that suggest danger that a vehicle may encounter" and stored in the storage unit 53.

[0048] (Applicability determination section) The matching unit 67 determines whether the judgment items stored in the judgment item storage unit 57 are matching based on the circumstances surrounding the vehicle 1. The matching unit 67 determines whether the basic judgment items, which are set out from the judgment items stored in the judgment item storage unit 57 and which include multiple judgment items indicating factors that can be associated with the event leading up to the event of danger, are matching based on the circumstances surrounding the vehicle 1 related to the dynamic event.

[0049] For example, if the detected event is a dynamic event suggesting something suddenly appearing from a blind spot, basic judgment items are set for each object that may appear (risk object). The basic judgment items are multiple judgment items related to the factors that can be associated with the risk object causing danger to vehicle 1. Each judgment item is set to be judged as "applicable" if there is a possibility of the risk object suddenly appearing. Specifically, for "person," "bicycle," and "car" as risk objects, the basic judgment items are: "present," "moving," "moving towards the direction of travel of the vehicle," "continuing," "appearing," and "not appearing (No)."

[0050] However, the risk target may be limited to just one "moving entity," or it may be limited to just a part of either "people" or "vehicles."

[0051] Furthermore, if the detected event is a static event, the determination unit 67 adds at least one determination item to the basic determination items used for determination in the case of a dynamic event, and determines whether the situation around the vehicle 1 corresponds to each determination item. In the case of a static event, the degree of danger itself does not change, so a determination item of whether or not it will jump out is added.

[0052] (Risk Calculation Unit) The risk level calculation unit 69 calculates information indicating the degree of danger in the situation in which vehicle 1 is located, based on the remaining judgment items after excluding the judgment items that have been determined not to apply from the judgment items used for determining whether or not to apply. The risk level calculation unit 69 calculates a higher degree of danger the higher the proportion of items that indicate the occurrence of danger among the remaining judgment items after excluding the judgment items that have been determined not to apply from the judgment items used for determining whether or not to apply.

[0053] In other words, in this embodiment, the determination unit 67 excludes items that do not relate to the surrounding conditions of the vehicle 1 from a plurality of determination items related to factors that can be associated with the event of danger (jumping out), and then calculates the ratio of the remaining determination items that indicate the occurrence of danger, which is used as information indicating the degree of danger.

[0054] For example, if the risk calculation unit 69 determines that there are 10 items for which a determination of applicability has been made, and 6 of those items are determined not to apply, and if there is one item among the remaining four items that indicates a risk will occur, the risk level will be set to 0.25 (one-quarter). In this example, the risk level is determined to be a value between 0 and 1, with a risk level of 1 representing the highest risk level. However, the information indicating the risk level is not limited to this example.

[0055] (Hazard Response Processing Unit) The hazard response processing unit 71 executes processing to respond to a hazard based on the information indicating the degree of hazard calculated by the hazard calculation unit 69. For example, the hazard response processing unit 71 notifies the driver of a hazard that the vehicle 1 may encounter by controlling the operation of the notification device 43. Specifically, the hazard response processing unit 71 notifies the driver of the hazard along with the information indicating the degree of hazard calculated by the hazard calculation unit 69. The hazard response processing unit 71 provides predetermined notifications to the user by outputting sound or voice, or by displaying images or text.

[0056] Furthermore, the hazard response processing unit 71 may transmit control commands to the vehicle control unit 41 to avoid potential hazards that the vehicle 1 may encounter. For example, the hazard response processing unit 71 may transmit operation commands to the vehicle control unit 41 to automatically decelerate or turn the vehicle 1.

[0057] <3. Example of operation> Next, we will specifically describe an example of the operation of the driving assistance processing by the driving assistance device 50 according to this embodiment. Hereinafter, we will use "something suddenly appearing in front of the vehicle from a blind spot" as an example of a danger that vehicle 1 may encounter.

[0058] Figure 3 is a flowchart showing an example of processing operation by the processing unit 51 of the driver assistance device 50. When the processing unit 51 detects the startup of the system including the driver assistance device 50 (step S11), the acquisition unit 61 acquires measurement information transmitted from the ambient environment sensor 31 (step S13). Instead of detecting the startup of the system, the processing unit 51 may detect the start of the driver assistance function based on a user instruction input.

[0059] Next, the situation recognition processing unit 63 performs a process to recognize the situation around vehicle 1 based on the acquired measurement information (step S15). Specifically, the situation recognition processing unit 63 recognizes various objects such as people, bicycles, motorcycles, and four-wheeled vehicles that are present around vehicle 1, as well as artificial or natural stationary objects and lines drawn on the road such as white lines and pedestrian crossings. The situation recognition processing unit 63 also calculates the position of the moving objects and stationary objects as seen from vehicle 1, the distance from vehicle 1 to the moving objects and stationary objects, and the relative speed of the moving objects and stationary objects with respect to vehicle 1.

[0060] Next, the event detection unit 65 determines whether there are any events in the surrounding environment of the recognized vehicle 1 that suggest a danger that vehicle 1 may encounter (step S17). For example, when the event detection unit 65 determines whether there are any events that suggest an object suddenly appearing in front of the vehicle from a blind spot, it determines whether there is a blind spot in front of the direction of travel of vehicle 1 and whether there are any events that suggest an object suddenly appearing in front of the vehicle from that blind spot.

[0061] Specifically, the event detection unit 65 determines that a blind spot exists in front of vehicle 1 if a three-dimensional object of a predetermined size or larger exists in front of the vehicle 1 in the direction of travel. Furthermore, if the event detection unit 65 detects that "a pedestrian crossing exists," "a ball rolled out from the blind spot," or "the vehicle stopped near the blind spot" on the road that vehicle 1 is traveling on near the blind spot, it determines that an event exists that suggests a risk of something suddenly appearing in front of the vehicle from the blind spot. However, the events that suggest a risk of something suddenly appearing in front of the vehicle from the blind spot are not limited to the examples above. For example, other arbitrary events may be set based on data from past accidents caused by something suddenly appearing from a blind spot.

[0062] If the event detection unit 65 does not determine that there are any events in the surrounding environment of the recognized vehicle 1 that would indicate a danger that vehicle 1 might encounter (S17 / No), the process proceeds to step S27, and the processing unit 51 determines whether or not to terminate the system (step S27). If the processing unit 51 determines to terminate the system (S27 / Yes), it terminates the driving support process; otherwise, it returns to step S13.

[0063] On the other hand, if the event detection unit 65 determines that there is an event in the surrounding environment of the recognized vehicle 1 that suggests a danger that vehicle 1 may encounter (S17 / Yes), the matching unit 67 sets the judgment items for that event (step S19). In this embodiment, the matching unit 67 sets pre-prepared judgment items from among the judgment items stored in the judgment item storage unit 57 according to the event that suggests a danger that vehicle 1 may encounter. Furthermore, if the detected event includes a static event, the matching unit 67 sets the basic judgment items and also sets pre-prepared judgment items according to the static event.

[0064] Figure 4 shows a flowchart of the determination item setting process by the determination unit 67. The determination unit 67 selects basic determination items for events that suggest danger that vehicle 1 may encounter (step S31). For example, if there is an event that suggests something jumping out from a blind spot in front of the vehicle as an event that suggests danger that vehicle 1 may encounter, the determination unit 67 sets basic determination items for the event that suggests something jumping out from a blind spot in front of the vehicle from among the determination items stored in the determination item storage unit 57. For example, basic determination items for predicting the occurrence of a sudden appearance are set for "person" and "car". Furthermore, basic determination items may be set for "bicycle" and other moving objects that may suddenly appear, assuming these are also possible.

[0065] Next, the determination unit 67 determines whether or not static events are included in the events that suggest danger that vehicle 1 may encounter (step S33). For example, if there is an event that suggests something suddenly jumping out from a blind spot in front of the vehicle as an event that suggests danger that vehicle 1 may encounter, the determination unit 67 determines whether or not static events such as "there is a pedestrian crossing" are included on the road that vehicle 1 is traveling on, near the blind spot.

[0066] If the determination unit 67 determines that no static events are included in the events that indicate a danger that vehicle 1 may encounter (S33 / No), it terminates the determination item setting process. In this case, only the basic determination items set for, for example, "person" and "automobile" are set. On the other hand, if the determination unit 67 determines that no static events are included in the events that indicate a danger that vehicle 1 may encounter (S33 / Yes), it adds determination items corresponding to the static events (step S35) and terminates the determination item setting process. In this case, for example, determination items corresponding to the static events are added to the basic determination items set for, for example, "person" and "automobile".

[0067] Returning to Figure 3, the matching unit 67 determines whether the judgment items set in step S19 apply based on the surrounding conditions of the vehicle 1 (step S21). Next, the risk level calculation unit 69, based on the results of the matching determination by the matching unit 67, calculates information indicating the risk level of the situation in which the vehicle 1 is located, based on the remaining judgment items after excluding the judgment items that were determined not to apply from among the multiple judgment items that were determined to apply (step S23).

[0068] The following explains specific examples of setting judgment items, determining applicability, and calculating information indicating the degree of risk in steps S19 to S23, using as an example a case where an event exists that suggests something may suddenly appear in front of the vehicle from a blind spot. In the example below, we will explain how to calculate the degree of risk of something suddenly appearing for "people" and "vehicles" as potential risk targets.

[0069] (First example where only blind spots were detected) Figure 5 shows a situation where a three-dimensional object 91 is detected to the left of an intersection ahead of the direction of travel of vehicle 1, and the area behind the three-dimensional object 91 is detected as a blind spot 93. In the first example shown in Figure 5, the blind spot 93 is detected, but neither dynamic nor static events are detected.

[0070] As shown in Figure 6, the determination unit 67 sets basic determination items for each of "person" and "vehicle," consisting of six determination items: "person (vehicle) present," "moving," "moving towards the direction of the vehicle's travel," "continuing," "jumping out," and "not jumping out (No)." In Figure 6, "person (vehicle) present," "moving," "moving towards the direction of the vehicle's travel," "continuing," "jumping out," and "not jumping out (No)" each represent factors that can be associated with a person (vehicle) causing danger to vehicle 1. Unless each determination item is found to be inapplicable (No), the system moves to the next determination item and finally ends with the determination item "jumps out" or "not jumping out (No)." Therefore, there are six determination items for each risk target (person and vehicle) (one for "jumps out" and five for "No").

[0071] When considering the presence or absence of each risk target (person, vehicle), the mere existence of a blind spot 93 is insufficient to determine the presence or absence of a risk target. Therefore, the presence / absence determination unit 67 proceeds to make a determination for both the case where a risk target is present and the case where it is not. However, if it is determined that there is no risk target, the possibility of something suddenly appearing is eliminated at this point, so no further determination items are provided.

[0072] On the other hand, if there is a risk object, it can be assumed that the risk object is moving or not. Therefore, the determination unit 67 proceeds with the determination for both the case where the risk object is moving and the case where it is not moving. However, if it is determined that the risk object is not moving, the possibility of it jumping out is eliminated at this point, so no further determination items are provided.

[0073] On the other hand, if the object of risk is moving, it can be assumed that the object of risk is either moving in the direction of travel of vehicle 1 or not. Therefore, the determination unit 67 proceeds to make a determination for both the case where the object of risk is moving in the direction of travel of the vehicle and the case where it is not. However, if it is determined that the object of risk is not moving in the direction of travel of the vehicle, the possibility of it suddenly appearing is eliminated at this point, so no further determination items are provided.

[0074] On the other hand, if the risk object is moving in the direction of travel of the vehicle, it can be assumed that the risk object will either continue moving in the direction of travel of vehicle 1 or will not. Therefore, the determination unit 67 proceeds to make a determination for both the case where the risk object continues moving in the direction of travel of the vehicle and the case where the movement in that direction will not continue. However, if it is determined that the risk object will not continue moving in the direction of travel of the vehicle, the possibility of it suddenly appearing is eliminated at this point, so no further determination items are provided.

[0075] On the other hand, if the risk object continues to move toward the direction of travel of the vehicle, it can be assumed that the risk object may or may not suddenly appear from the blind spot. Therefore, the determination unit 67 considers both the possibility that the risk object will suddenly appear in front of the direction of travel of the vehicle and the possibility that it will not appear.

[0076] In other words, in the examples shown in Figures 5 and 6, there are zero judgment items that indicate the surrounding conditions of vehicle 1 do not apply. The risk calculation unit 69 removes the judgment items that have been determined not to apply from all judgment items at which branching of judgment items ends. However, in the examples shown in Figures 5 and 6, there are zero judgment items to remove, leaving 12 judgment items. The risk calculation unit 69 calculates the risk level by determining the ratio of the number of judgment items that ultimately result in the vehicle jumping out from the remaining 12 judgment items. In the examples shown in Figures 5 and 6, the number of judgment items that ultimately result in the vehicle jumping out is "2", so the risk calculation unit 69 sets the risk level to "0.16 (2 / 12)".

[0077] (Second example where a blind spot and the ball were detected) Figure 7 shows a situation similar to Figure 5, where the area behind the three-dimensional object 91 to the left of the intersection ahead of vehicle 1 in the direction of travel is detected as a blind spot 93, and further, a ball 95 is detected flying out from the blind spot 93. The event of the ball 95 flying out from the blind spot 93 is a dynamic event.

[0078] As shown in Figure 8, the matching unit 67 sets basic judgment items for "person" and "car," each consisting of six judgment items: "person (car) present," "moving," "moving in the direction of the vehicle's movement," "continuing," "jumping out," and "not jumping out (No)." Considering the presence or absence of each risk object (person, car), since the ball 95 is something a person plays with, a "car," which is not a "person," does not qualify as a risk object that could appear following the ball 95. Therefore, the matching unit 67 determines that all judgment items for "car" do not apply. In Figure 8, judgment items with diagonal lines drawn through the square frame indicating the judgment item indicate the judgment item that was determined not to apply.

[0079] On the other hand, the mere fact that the ball 95 has flown out does not allow for determination of whether or not there is a "person" in the blind spot 93. Therefore, the determination unit 67 proceeds to determine whether or not there is a "person" and whether or not there is a "person". However, if it is determined that there is no "person", then the possibility of a "person" flying out at this point is eliminated, and no further determination items are set.

[0080] On the other hand, even if there is a "person," it is impossible to determine whether or not that "person" is chasing the ball 95, so it can be assumed that the "person" is moving or not. Therefore, the determination unit 67 proceeds to make a determination for both the case where the "person" is moving and the case where the "person" is not moving. However, if it is determined that the "person" is not moving, the possibility of the "person" running out is eliminated at this point, so no further determination items are provided.

[0081] On the other hand, if we assume that the "person" is moving, since the ball 95 is rolling forward in the direction of travel of vehicle 1, it can be assumed that the "person" is moving in the direction of travel of vehicle 1. Therefore, the determination unit 67 determines that the determination item that the "person" is not moving in the direction of travel of vehicle 1 does not apply.

[0082] On the other hand, if we assume that the "person" is moving in the direction of travel of vehicle 1, it is assumed that the "person" is continuously moving in the direction of travel of vehicle 1. Therefore, the determination unit 67 determines that the determination item that indicates the movement in the direction of travel of vehicle 1 is not continuous does not apply.

[0083] On the other hand, if the "person" continues to move in the direction of the vehicle's travel, it can be assumed that the "person" may or may not suddenly jump out from the blind spot. Therefore, the determination unit 67 considers both the possibility that the "person" jumps out in front of the vehicle's direction of travel and the possibility that the "person" does not jump out.

[0084] In other words, in the examples shown in Figures 7 and 8, the number of judgment items that indicate the surrounding conditions of vehicle 1 do not apply is "8". The risk calculation unit 69 removes the judgment items that have been determined not to apply from all judgment items at which branching of judgment items ends. In the examples shown in Figures 7 and 8, since "8" judgment items are removed out of 12 judgment items, 4 judgment items remain. The risk calculation unit 69 calculates the risk level by determining the ratio of the number of judgment items that ultimately result in the vehicle jumping out of the remaining 4 judgment items. In the examples shown in Figures 7 and 8, the number of judgment items that ultimately result in the vehicle jumping out is "1", so the risk calculation unit 69 sets the risk level to "0.25 (1 / 4)".

[0085] (Third example where a blind spot and a temporarily stopped oncoming vehicle were detected) Figure 9 shows a situation similar to Figure 5, where the area behind the three-dimensional object 91 to the left of the intersection ahead of vehicle 1 in the direction of travel is detected as a blind spot 93. Furthermore, it shows a situation where an oncoming vehicle 97 approaching from the front in the direction of travel of vehicle 1 is detected to have stopped temporarily near the blind spot 93. The event of the oncoming vehicle 97 stopping temporarily is a dynamic event.

[0086] As shown in Figure 10, the matching unit 67 sets basic determination items for each of "person" and "vehicle," consisting of six determination items: "person (vehicle) is present," "is moving," "is moving in the direction of the vehicle's travel," "is continuing," "will jump out," and "will not jump out (No)." When considering the presence or absence of each risk object (person, vehicle), the fact that the oncoming vehicle 97 stopped means that it is assumed that there is some kind of moving object in the blind spot 93, but it is not possible to determine whether it is a "person" or a "vehicle." Therefore, the matching unit 67 determines that the determination items "no person" and "no vehicle" do not apply. On the other hand, the matching unit 67 proceeds with the determination for each of "person" and "vehicle" in the case where they are present.

[0087] Assuming there is a "person" and a "vehicle," and given that the oncoming vehicle 97 stopped temporarily, it can be assumed that the "person" and "vehicle" are moving. Furthermore, it can be assumed that the "person" and "vehicle" are moving in the direction of vehicle 1's travel. Therefore, the determination unit 67 determines that the determination item for "person" and "vehicle" being stationary does not apply to each of them.

[0088] Even if a person is moving, the person's movement has a high degree of freedom, so the determination unit 67 cannot determine whether the person is continuously moving or not in the direction of travel of vehicle 1. Therefore, the determination unit 67 proceeds to make a determination for both the case where the person is continuously moving and the case where they are not moving in the direction of travel of vehicle 1. However, if it is determined that the person is not continuously moving in the direction of travel of vehicle 1, the possibility of the person suddenly jumping out is eliminated at this point, so no further determination items are provided.

[0089] On the other hand, if the "car" is moving, it cannot stop suddenly, so the determination unit 67 determines that the determination item that the "car" is not continuously moving in the direction of travel of vehicle 1 does not apply.

[0090] Furthermore, assuming that the "person" and "vehicle" continue to move toward the direction of the vehicle's travel, it can be assumed that the "person" and "vehicle" will ultimately jump out from the blind spot, or will not jump out. Therefore, the determination unit 67 considers both the possibility that the "person" and "vehicle" jump out in front of the vehicle's direction of travel and the possibility that they will not jump out.

[0091] In other words, in the examples shown in Figures 9 and 10, the number of judgment items that indicate the surrounding conditions of vehicle 1 do not apply is "7". The risk calculation unit 69 removes the judgment items that have been determined not to apply from all judgment items at which branching of judgment items ends. In the examples shown in Figures 9 and 10, since "7" judgment items are removed out of 12 judgment items, 5 judgment items remain. The risk calculation unit 69 calculates the risk level by determining the ratio of the number of judgment items that ultimately result in the vehicle jumping out of the remaining 5 judgment items. In the examples shown in Figures 9 and 10, the number of judgment items that ultimately result in the vehicle jumping out is "2", so the risk calculation unit 69 sets the risk level to "0.4 (2 / 5)".

[0092] (Fourth example in which a blind spot, a temporarily stopped oncoming vehicle, and a pedestrian crossing were detected) Figure 11 shows the situation in which a pedestrian crossing 99 is detected in addition to the situation shown in Figure 9. The event in which a pedestrian crossing 99 is present is a static event.

[0093] As shown in Figure 12, if a static event such as a pedestrian crossing 99 is detected on the road near the blind spot 93, since static events are not events where the degree of risk of someone or a vehicle suddenly appearing changes depending on the surrounding conditions of the vehicle 1, only the judgment items of "appears to appear" and "does not appear" are added. Furthermore, since the mere presence of a pedestrian crossing 99 does not allow for the determination of whether or not a "person" or "vehicle" will appear, the determination unit 67 considers both the possibility that a "person" or "vehicle" will appear in front of the vehicle's direction of travel and the possibility that it will not appear.

[0094] In other words, in the examples shown in Figures 11 and 12, the number of judgment items increases to "14," and the number of judgment items that the surrounding conditions of vehicle 1 do not meet becomes "7." The risk calculation unit 69 removes the judgment items that have been determined not to apply from all judgment items at which branching of judgment items ends. In the examples shown in Figures 11 and 12, since "7" judgment items are removed out of 14 judgment items, 7 judgment items remain. The risk calculation unit 69 calculates the risk level by determining the ratio of the number of judgment items that ultimately result in the vehicle jumping out from the remaining 7 judgment items. In the examples shown in Figures 11 and 12, the number of judgment items that ultimately result in the vehicle jumping out is "3," so the risk calculation unit 69 sets the risk level to "0.43 (3 / 7)."

[0095] Furthermore, in the case of "an example where only a blind spot is detected" shown in Figure 5, or "an example where both a blind spot and a ball are detected" shown in Figure 7, if a pedestrian crossing is detected, the presence of the pedestrian crossing is added as a criterion for calculating the level of danger.

[0096] Furthermore, the determination unit 67 determines that a determination item added due to the presence of a static event does not apply if it is determined that the determination item does not correspond to the circumstances surrounding the vehicle 1.

[0097] (Fifth example where multiple dynamic events were detected) If the surrounding conditions of vehicle 1 include multiple dynamic events, the applicability determination unit 67 determines the applicability of each basic determination item for each dynamic event. The risk level calculation unit 69 calculates information indicating the risk level based on the remaining determination items, excluding the determination items that are determined not to apply to any of the basic determination items for all dynamic events.

[0098] For example, in the "Example where a blind spot and a ball are detected" shown in Figure 7, if a temporarily stopped oncoming vehicle 97 and a pedestrian crossing 99 shown in Figure 11 are also detected, the matching unit 67 performs a matching determination of the basic determination items for each event, as shown in Figures 8 and 12. In this case, the matching determination shown in Figure 8 also includes additional determination items for "jumping out" and "not jumping out" due to the presence of the pedestrian crossing 99.

[0099] The risk calculation unit 69 then calculates information indicating the risk level based on the remaining 4 judgment items, excluding the 10 judgment items that are determined not to apply to at least one of the events. Specifically, since 10 judgment items are excluded out of 14 judgment items, 4 judgment items remain. Of the remaining 4 judgment items, the number of judgment items that ultimately result in a jump is 2, so the risk calculation unit 69 sets the risk level to 0.5 (2 / 4).

[0100] Furthermore, if the risk level calculation unit 69 acquires information that is not measured by the vehicle 1's surrounding environment sensors 31, such as information about objects in the blind spot 93 through vehicle-to-vehicle communication, vehicle-to-infrastructure communication, or communication with an external server, it may determine whether each judgment item applies based on that information. For example, if the risk level calculation unit 69 acquires information indicating that there is a "person" in the blind spot 93 but no "vehicle," it will determine that all judgment items related to a "vehicle" suddenly appearing do not apply, regardless of other circumstances. This can improve the accuracy of the calculated risk level.

[0101] Furthermore, if multiple dynamic events are detected, the risk calculation unit 69 may use the average of the risk levels calculated for each event as the final risk level.

[0102] Returning to Figure 3, after the risk level calculation unit 69 calculates information indicating the risk level, the risk response processing unit 71 executes risk response processing to deal with the risks that vehicle 1 may encounter (step S25). For example, the risk response processing unit 71 controls the operation of the notification device 43 to notify the driver of the risks that vehicle 1 may encounter along with the risk level information. The risk response processing unit 71 may change the content of the notification according to the risk level. For example, the higher the calculated risk level, the more emphasis the risk that vehicle 1 may encounter will have on the notification. Specifically, the risk response processing unit 71 may increase the volume or make the display more prominent as the risk level increases.

[0103] Furthermore, the hazard response processing unit 71 may also notify the driver of the results of the determination of whether the judgment items apply, as this is the basis for the calculated level of risk. For example, the hazard response processing unit 71 notifies the driver of the detected events (dynamic events and static events) and the content of the remaining judgment items, excluding those that were determined not to apply. For example, in the examples shown in Figures 11 and 12, the hazard response processing unit 71 notifies the driver that "there is a blind spot on the left side in front of the vehicle, and an oncoming vehicle stopped temporarily just before the crosswalk near the blind spot, so there is a possibility that a pedestrian or vehicle may suddenly appear from the blind spot." This allows the driver to understand why such a level of risk was calculated, and can increase the driver's confidence in the driver assistance function.

[0104] Furthermore, the hazard response processing unit 71 may specifically notify the driver of patterns in which a "person" or "vehicle" is predicted to suddenly appear from a blind spot, based on the surrounding conditions of vehicle 1. This notifies the driver of the process by which the degree of danger was calculated, thereby increasing the driver's confidence or satisfaction.

[0105] Furthermore, the hazard response processing unit 71 may transmit control commands to the vehicle control unit 41 to avoid potential hazards that the vehicle 1 may encounter. For example, the hazard response processing unit 71 may transmit operation commands to the vehicle control unit 41 to automatically decelerate or turn the vehicle 1. The hazard response processing unit 71 may change the content of the operation commands according to the calculated level of danger. For example, the hazard response processing unit 71 may transmit only a deceleration command until the level of danger is moderate (e.g., 0.6), and transmit both a deceleration command and a steering command when the level of danger is high (e.g., a value greater than 0.6). Alternatively, the hazard response processing unit 71 may transmit deceleration commands such that the deceleration increases as the level of danger increases.

[0106] Next, the processing unit 51 determines whether or not to stop the system (step S27). For example, the processing unit 51 may determine to stop the system in accordance with an operation input from the driver of the vehicle 1 to stop the driver assistance function. If the processing unit 51 does not determine to stop the system (S27 / No), it returns to step S13 and executes the processing of each of the steps described above. On the other hand, if the processing unit 51 determines to stop the system (S27 / Yes), it terminates the series of processes.

[0107] As described above, the driver assistance device (hazard prediction device) 50 according to this embodiment sets multiple judgment items that indicate the possibility of a hazard occurring based on the detected event, and can logically calculate information indicating the degree of hazard based on the results of the judgment of whether or not the judgment items are met. Therefore, the driver assistance device 50 can logically explain the basis for the calculated degree of hazard. Furthermore, according to the driver assistance device 50 according to this embodiment, the judgment items are changed or added depending on the type of detected event (dynamic event or static event) to calculate the degree of hazard. This allows for the setting of items for determining the possibility of a hazard occurring according to the situation around the vehicle 1, thereby improving the accuracy of the hazard calculation result.

[0108] Furthermore, in the case where multiple risk factors that could cause danger to the vehicle 1 are anticipated, the driver assistance device 50 in this embodiment determines whether each risk factor meets the basic judgment criteria. Therefore, the driver assistance device 50 can logically calculate the degree of risk according to the type of risk factor, and the accuracy of the risk calculation result can be improved.

[0109] Furthermore, in the driver assistance device 50 according to this embodiment, multiple judgment items are used as basic judgment items, each representing a factor that can be associated with one or more risk targets until danger occurs to the vehicle 1. Therefore, it is possible to logically calculate the probability of danger occurring to the vehicle 1.

[0110] Furthermore, in the case where the surrounding conditions of the vehicle include multiple dynamic events, the driver assistance device 50 in this embodiment determines whether each dynamic event meets the basic judgment criteria and calculates information indicating the degree of danger based on the remaining judgment criteria, excluding the judgment criteria that are determined not to apply to all dynamic events. Therefore, even when multiple dynamic events are detected, the degree of danger can be calculated logically according to the situation at that time.

[0111] Furthermore, the driver assistance device 50 according to this embodiment outputs information indicating the calculated degree of danger, along with information on the detected event, from the notification device. Therefore, the driver can know the dangers that vehicle 1 may encounter, along with the degree of danger in the situation in which vehicle 1 is located, and take appropriate danger avoidance actions.

[0112] Furthermore, the driver assistance device 50 according to this embodiment outputs information regarding the determination of multiple judgment items, along with information indicating the degree of danger, from the notification device. Therefore, it is possible to increase the driver's understanding of the danger and degree of danger information that is notified, and to increase the driver's trust in the system.

[0113] While preferred embodiments of the present disclosure have been described in detail above with reference to the attached drawings, the present disclosure is not limited to such examples. It is clear to any person with ordinary skill in the art to which the present disclosure pertains that various modifications or alterations may be conceived within the scope of the technical idea set forth in the claims, and these will naturally also be understood to fall within the technical scope of the present disclosure.

[0114] For example, in the above embodiment, the driver assistance system was comprised of an electronic control unit mounted on the vehicle, but the technology of this disclosure is not limited to the above example. For example, the driver assistance system may be comprised of a portable terminal or external server capable of acquiring measurement information from the vehicle's surrounding environment sensors and transmitting drive command signals to a notification device.

[0115] Furthermore, the technology disclosed herein can also be realized as a vehicle equipped with the driver assistance device described in the above embodiment, a method for predicting hazards using the driver assistance device, a computer program that causes a computer to function as the above-mentioned driver assistance device (hazard prediction device), and a non-temporary tangible recording medium on which the computer program is recorded. [Explanation of symbols]

[0116] 1: Vehicle 43:Notification device 50: Driving assistance devices 51: Processing Unit 53: Storage section 55: Map data storage unit 57: Judgment item storage section 61: Acquisition part 63: Situation Recognition Processing Unit 65: Event detection unit 67: Applicability judgment part 69: Risk Calculation Unit 71: Hazard Response Processing Unit

Claims

1. In a hazard prediction device that predicts the dangers a vehicle may encounter, It comprises one or more processors and one or more memories connected to the one or more processors in a communicative manner, The aforementioned one or more processors A process to acquire measurement information obtained by measuring the conditions around the vehicle using ambient environment sensors, Based on the acquired measurement information, a process is performed to detect events that suggest dangers the vehicle may encounter. A process to determine whether the aforementioned event is a dynamic event in which the degree of risk can change depending on the circumstances, or a static event in which the degree of risk does not change regardless of the circumstances, After determining whether the event is a dynamic event or a static event, the process involves determining whether a basic determination item, which has multiple determination items related to the occurrence of the danger, is applicable based on the surrounding conditions of the vehicle related to the dynamic event, and further, if the event includes a static event, adding at least one determination item to the basic determination item, and determining whether the added determination item is applicable based on the surrounding conditions of the vehicle related to the static event. A process to calculate information indicating the degree of danger in the situation in which the vehicle is located, based on the remaining determination items after excluding the determination items that have been determined not to apply from among the multiple determination items for which the applicability of the above-mentioned applicability has been determined, A hazard prediction device that performs this function.

2. The hazard prediction device according to claim 1, wherein the one or more processors determine whether one or more risk targets that cause the hazard to the vehicle meet the basic determination criteria.

3. The hazard prediction device according to claim 2, wherein the basic determination items are a plurality of determination items representing factors that are associated with the occurrence of the hazard in the vehicle due to one or more risk targets.

4. The aforementioned one or more processors The hazard prediction device according to claim 1, wherein, if the conditions surrounding the vehicle include a plurality of the aforementioned dynamic events, the device determines whether each of the aforementioned basic determination items applies to each of the aforementioned dynamic events, and calculates information indicating the degree of risk based on the remaining determination items after excluding the determination items that are determined not to apply to any of the aforementioned basic determination items for all of the aforementioned dynamic events.

5. The vehicle is equipped with a notification device that notifies the occupants of the vehicle, The aforementioned one or more processors The hazard prediction device according to claim 1, wherein the notification device outputs information indicating the calculated degree of hazard together with information on the detected event.

6. The aforementioned one or more processors The hazard prediction device according to claim 5, further comprising the output of information regarding the determination of whether or not the plurality of determination items are applicable from the notification device.

7. The aforementioned incident suggests the possibility of a moving object suddenly appearing from a blind spot. The hazard prediction device according to claim 1, wherein the one or more processors calculate the degree of risk of the moving body flying out.

8. In a hazard prediction method that predicts the dangers a vehicle may encounter, One or more processors, The system acquires measurement information obtained by measuring the conditions around the vehicle using ambient environment sensors, Based on the acquired measurement information, the system detects events that suggest dangers the vehicle may encounter, The process involves determining whether the aforementioned event is a dynamic event, where the degree of risk can change depending on the circumstances, or a static event, where the degree of risk does not change regardless of the circumstances. After determining whether the event is a dynamic event or a static event, the applicability of a basic determination item, which has multiple determination items related to the occurrence of the hazard, is determined based on the surrounding conditions of the vehicle related to the dynamic event. Furthermore, if the event includes a static event, at least one determination item is added to the basic determination item, and the applicability of the added determination item is determined based on the surrounding conditions of the vehicle related to the static event. Based on the remaining determination items after excluding the determination items that were determined not to apply from the multiple determination items for which the applicability of the above-mentioned applicability has been determined, information indicating the degree of danger in the situation in which the vehicle is located is calculated. A method for predicting risks and executing it.

9. One or more processors, This involves acquiring measurement information by measuring the conditions around the vehicle using ambient environment sensors, and Based on the acquired measurement information, the system detects events that suggest dangers the vehicle may encounter, The process involves determining whether the aforementioned event is a dynamic event, where the degree of risk can change depending on the circumstances, or a static event, where the degree of risk does not change regardless of the circumstances. After determining whether the event is a dynamic event or a static event, the applicability of a basic determination item, which has multiple determination items related to the occurrence of the hazard, is determined based on the surrounding conditions of the vehicle related to the dynamic event. Furthermore, if the event includes a static event, at least one determination item is added to the basic determination item, and the applicability of the added determination item is determined based on the surrounding conditions of the vehicle related to the static event. Based on the remaining determination items after excluding the determination items that were determined not to apply from the multiple determination items for which the applicability of the above-mentioned applicability has been determined, information indicating the degree of danger in the situation in which the vehicle is located is calculated. A non-temporary, tangible recording medium that stores a computer program that executes a computer program.

Images