Driving support device and recording medium recording a computer program

Abstract

Provided are a driving assistance device and a recording medium recording a computer program that are capable of reducing the risk of collision between a subject vehicle and a moving object in consideration of a predicted motion of the moving object. This driving assistance device executes processes including: detecting moving objects around a subject vehicle and a surrounding environment of the subject vehicle; predicting driving behavior of the detected moving objects; calculating, for each predicted driving behavior of the moving objects, the risk of collision between the moving objects and the subject vehicle after a predetermined period of time on the basis of distances between the moving objects and the subject vehicle after the predetermined period of time and the probability of driving behaviors being carried out by the moving objects; and setting a driving condition for the subject vehicle whereby the risk of collision is minimized.

Description

Technical Field

[0001] The present disclosure relates to a driving support device that supports driving of a vehicle based on a collision risk with an obstacle around the vehicle, and a recording medium storing a computer program.

Background Art

[0002] In recent years, mainly for the purpose of reducing traffic accidents and driving load, the practical application of vehicles equipped with driving support functions and autonomous driving functions has been promoted. For example, based on information detected by various sensors such as an external camera or LiDAR (Light Detection and Ranging) provided in the host vehicle, an obstacle existing around the host vehicle is detected, and a device that supports driving of the host vehicle so as to avoid a collision between the host vehicle and the obstacle is known.

[0003] As such a driving support device, Patent Document 1 proposes a collision avoidance control device that determines whether an avoidance route is a safe driving route. Specifically, Patent Document 1 includes an avoidance route setting means for setting an avoidance route for avoiding a collision with a forward obstacle, a reliability calculation means for calculating the reliability of the avoidance route, an automatic steering control means for determining whether to execute automatic steering along the avoidance route, and a unit area specifying means for specifying whether a unit area obtained by dividing a region in front of the vehicle into a plurality of regions is an obstacle region or an unknown region. At the same distance from the host vehicle, the cost of the obstacle region is set higher than that of the unknown region. The reliability calculation means calculates an avoidance region cost based on the number and cost of obstacle regions and the number and cost of unknown regions existing in an avoidance region including the avoidance route, and discloses a collision avoidance control device that calculates the reliability of the avoidance route based on the avoidance region cost.

[0004] In addition, Patent Document 2 proposes a system that determines or identifies the behavior that an obstacle intends to perform within its environment and reduces the risk of collision. Specifically, Patent Document 2 calculates one or more predicted trajectories for each object based on a map and route information, generates a set of predicted trajectories for that object, enumerates a plurality of combinations of predicted trajectories in which the object may move within the driving environment using the set of predicted trajectories, calculates a risk value for each combination, generates a plurality of corresponding risk values, and discloses a system that controls an autonomous vehicle based on the combination having the lowest risk value included in the corresponding risk values.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, since the collision avoidance control device described in Patent Document 1 does not consider the movement of other vehicles around the host vehicle, there is a risk that the risk of collision and the risk of obstacles generated at the time of collision may increase depending on the movement of other vehicles. In addition, although the system described in Patent Document 2 considers the movement of other vehicles, it only predicts the movement intention of other vehicles such as left turn, right turn, straight ahead, or reverse in consideration of map and route information and traffic rules, and cannot predict the movement of other vehicles that cannot be predicted from the map and route. For this reason, also in the system described in Patent Document 2, there is a risk that the risk of collision and the risk of obstacles generated at the time of collision may increase depending on the movement of other vehicles.

[0007] The present disclosure has been made in view of the above problems, and an object of the present disclosure is to provide a driving support device and a recording medium storing a computer program that can reduce the risk of collision of a host vehicle with a moving object in consideration of the predicted movement of the moving object.

Means for Solving the Problems

[0008] In order to solve the above problems, according to an aspect of the present disclosure, in a driving support device that sets driving conditions of a host vehicle based on a collision risk with an obstacle around the host vehicle, one or more processors, and one or more memories communicably connected to the one or more processors, the processor detects a moving object and the surrounding environment around the host vehicle, predicts the driving behavior of the detected moving object, and for each of the predicted driving behaviors of the moving object, calculates a collision risk between the moving object and the host vehicle after a predetermined time based on the distance between the moving object and the host vehicle after a predetermined time and the probability that the moving object performs each driving behavior, and sets driving conditions of the host vehicle that minimize the collision risk, and a driving support device that executes a process including this is provided.

[0009] Further, in order to solve the above problems, according to another aspect of the present disclosure, there is provided a recording medium storing a computer program applied to a driving support device that sets driving conditions of a host vehicle based on a collision risk with an obstacle around the host vehicle, the computer program causing a processor to detect a moving object and the surrounding environment around the host vehicle, predict the driving behavior of the detected moving object, calculate a collision risk between the moving object and the host vehicle after a predetermined time based on the distance between the moving object and the host vehicle after a predetermined time and the probability that the moving object performs each driving behavior, and set driving conditions of the host vehicle that minimize the collision risk, and a recording medium storing a computer program that executes a process including this is provided.

Effects of the Invention

[0010] As described above, according to the present disclosure, it is possible to reduce the risk of collision of the host vehicle with a moving object in consideration of the predicted movement of the moving object.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0012] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

[0013] <1. Overall configuration of the vehicle> FIG. 1 is a schematic diagram showing a configuration example of a vehicle 1 equipped with a driving assistance device 50 according to the present embodiment. The vehicle 1 shown in FIG. 1 is configured as a four-wheel drive vehicle that transmits the driving torque output from a driving power source 9 that generates the driving torque of the vehicle 1 to the left front wheel 3LF, the right front wheel 3RF, the left rear wheel 3LR, and the right rear wheel 3RR (hereinafter, collectively referred to as "wheel 3" when no particular distinction is required). The driving power source 9 may be an internal combustion engine such as a gasoline engine or a diesel engine, may be a driving motor, or may be provided with both an internal combustion engine and a driving motor.

[0014] Note that the vehicle 1 may be an electric vehicle equipped with, for example, two driving motors, a front-wheel driving motor and a rear-wheel driving motor, or may be an electric vehicle equipped with a driving motor corresponding to each wheel 3. Further, when the vehicle 1 is an electric vehicle or a hybrid electric vehicle, the 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 for charging the battery.

[0015] The vehicle 1 includes a driving power source 9, an electric steering device 15, and a brake hydraulic control unit 20 as devices used for driving control of the vehicle 1. The driving power source 9 outputs a driving torque that is transmitted to the front-wheel drive shaft 5F and the rear-wheel drive shaft 5R via a transmission (not shown), a front-wheel differential mechanism 7F, and a rear-wheel differential mechanism 7R. The driving of the driving power source 9 and the transmission is controlled by a vehicle control device 41 configured to include one or more electronic control units (ECUs: Electronic Control Unit).

[0016] An electric power steering device 15 is provided on the front-wheel drive shaft 5F. The electric power steering device 15 includes an electric motor and a gear mechanism (not shown). The electric power steering device 15 adjusts the steering angles of the left front wheel 3LF and the right front wheel 3RF by being controlled by the vehicle control device 41. During manual driving, the vehicle control device 41 controls the electric power steering device 15 based on the steering angle of the steering wheel 13 by the driver. Also, during automatic driving, the vehicle control device 41 controls the electric power steering device 15 based on the target steering angle set by the driving support device 50 or an automatic driving control device (not shown).

[0017] The braking system of the vehicle 1 is configured as a hydraulic braking system. The brake hydraulic control unit 20 adjusts the hydraulic pressure supplied to the brake calipers 17LF, 17RF, 17LR, 17RR (hereinafter, collectively referred to as "brake caliper 17" when no particular distinction is required) provided on the front, rear, left, and right drive wheels 3LF, 3RF, 3LR, 3RR, respectively, to generate braking force. The drive of the brake hydraulic control unit 20 is controlled by the vehicle control device 41. When the vehicle 1 is an electric vehicle or a hybrid electric vehicle, the brake hydraulic control unit 20 is used in combination with the regenerative brake by the drive motor.

[0018] The vehicle control device 41 includes one or a plurality of electronic control devices that control the driving of a driving force source 9 that outputs the driving torque of the vehicle 1, an electric steering device 15 that controls the steering angle of the steering wheel 13 or the steered wheels, and a brake hydraulic control unit 20 that controls the braking force of the vehicle 1. The vehicle control device 41 may have a function of controlling the driving of a transmission that shifts the output output from the driving force source 9 and transmits it to the wheels 3. The vehicle control device 41 is configured to be able to acquire information transmitted from a driving assistance device 50 or an automatic driving control device (not shown), and is configured to be able to execute automatic driving control of the vehicle 1. Further, during manual driving of the vehicle 1, the vehicle control device 41 acquires information on the operation amount by the driver's driving, and controls the driving of the driving force source 9 that outputs the driving torque of the vehicle 1, the electric steering device 15 that controls the steering angle of the steering wheel 13 or the steered wheels, and the brake hydraulic control unit 20 that controls the braking force of the vehicle 1.

[0019] Further, the vehicle 1 includes front cameras 31LF and 31RF, a LiDAR (Light Detection And Ranging) 31S, and a vehicle state sensor 35.

[0020] The front cameras 31LF and 31RF and the LiDAR 31S constitute ambient environment sensors for acquiring information on the ambient environment of the vehicle 1. The front cameras 31LF and 31RF capture the front of the vehicle 1 and generate image data. The front cameras 31LF and 31RF include image sensors such as CCD (Charged-Coupled Devices) or CMOS (Complementary Metal-Oxide-Semiconductor), and transmit the generated image data to the driving assistance device 50.

[0021] In the vehicle 1 shown in FIG. 1, the front cameras 31LF and 31RF are configured as a stereo camera including a pair of left and right cameras, but may be monocular cameras. In addition to the front cameras 31LF and 31RF, the vehicle 1 may include, for example, a rear camera provided at the rear of the vehicle 1 that captures the rear or cameras provided on the side mirrors 11L and 11R that capture the left rear or right rear.

[0022] LiDAR31S transmits an optical wave and receives the reflected wave of the optical wave, and detects an obstacle, the distance to the obstacle, and the position of the obstacle based on the time from when the optical wave is transmitted until the reflected wave is received. LiDAR31S transmits the detection data to the driving assistance device 50. The vehicle 1 may be provided with one or more sensors such as a radar sensor such as a millimeter-wave radar or an ultrasonic sensor instead of or in combination with LiDAR31S as a surrounding environment sensor for acquiring information on the surrounding environment.

[0023] The vehicle state sensor 35 consists of one or more sensors that detect the operating state and behavior of the vehicle 1. The vehicle state sensor 35 includes at least one of, for example, a steering angle sensor, an accelerator position sensor, a brake stroke sensor, a brake pressure sensor, or an engine speed sensor. These sensors respectively detect the operating state of the vehicle 1 such as the steering angle of the steering wheel 13 or the steering wheel, the accelerator opening, the brake operation amount, or the engine speed. In addition, the vehicle state sensor 35 includes at least one of, for example, a vehicle speed sensor, an acceleration sensor, or an angular velocity sensor. These sensors respectively detect the behavior of the vehicle such as the vehicle speed, longitudinal and lateral accelerations, and yaw rate. In addition, the vehicle state sensor 35 may include a sensor that detects the operation of the turn indicator. The vehicle state sensor 35 transmits a sensor signal including the detected information to the driving assistance device 50.

[0024] <2. Driving Assistance Device> Next, the driving assistance device 50 according to the present embodiment will be specifically described. In the following description, the vehicle to be supported equipped with the driving assistance device 50 is referred to as the host vehicle, and the vehicles around the host vehicle 1 are referred to as other vehicles.

[0025] (2-1. Configuration Example) FIG. 2 is a block diagram showing a configuration example of the driving assistance device 50 according to the present embodiment. The driving support device 50 functions as a device that supports the driving of the host vehicle 1 by a processor such as one or more CPUs (Central Processing Units) executing a computer program. The computer program is a computer program for causing the processor to execute operations described later that the driving support device 50 should execute. The computer program executed by the processor may be recorded on a recording medium that functions as a storage unit (memory) 53 provided in the driving support device 50, or may be recorded on a recording medium built into the driving support device 50 or any recording medium that can be externally attached to the driving support device 50.

[0026] Examples of the recording medium for recording the computer program include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs (Compact Disk Read Only Memories), DVDs (Digital Versatile Disks), and Blu-ray (registered trademark), magneto-optical media such as floptical disks, storage elements such as RAMs (Random Access Memories) and ROMs (Read Only Memories), and flash memories such as USB (Universal Serial Bus) memories and SSDs (Solid State Drives), and other media capable of storing programs.

[0027] The ambient environment sensor 31 and the vehicle state sensor 35 are connected to the driving support device 50 via a dedicated line or communication means such as CAN (Controller Area Network) or LIN (Local Inter Net). Also, the vehicle control device 41 is connected to the driving support device 50 via a dedicated line or communication means such as CAN or LIN. Note that the driving support device 50 is not limited to an electronic control device mounted on the host vehicle 1, and may be a terminal device such as a smartphone or a wearable device.

[0028] The driving support device 50 includes a processing unit 51 and a storage unit 53. The processing unit 51 is configured to include one or more processors such as a CPU. Part or all of the processing unit 51 may be configured with updatable components such as firmware, or may be program modules executed according to instructions from a CPU or the like. The storage unit 53 is constituted by a memory such as a RAM or a ROM. The storage unit 53 is communicably connected to the processing unit 51. However, the number and type of the storage unit 53 are not particularly limited. The storage unit 53 stores computer programs executed by the processing unit 51, various parameters used for arithmetic processing, detection data, arithmetic results, and other information.

[0029] (2-2. Functional Configuration) As shown in FIG. 2, the processing unit 51 of the driving support device 50 includes a surrounding environment information acquisition unit 61, a host vehicle information acquisition unit 63, a risk calculation unit 65, and a driving condition setting unit 67. Each of these units is a function realized by the execution of a computer program by a processor such as a CPU. However, a part of each of these units may be configured to include an analog circuit. Hereinafter, after briefly explaining the functions of each unit of the processing unit 51, specific processing operations will be described.

[0030] (Surrounding Environment Information Acquisition Unit) The surrounding environment information acquisition unit 61 detects the surrounding environment of the host vehicle 1 based on the detection data transmitted from the surrounding environment sensor 31. Specifically, the surrounding environment information acquisition unit 61 detects at least obstacles and driving lanes existing around the host vehicle 1. The surrounding environment information acquisition unit 61 obtains information about the detected obstacles, such as the type, size, position, speed, distance from the host vehicle 1 to the obstacle, and relative speed between the host vehicle 1 and the obstacle. The detected obstacles include all objects existing around the host vehicle 1 during driving, such as other vehicles, parked vehicles, pedestrians, bicycles, sidewalls, curbs, buildings, utility poles, traffic signs, traffic signal lights, natural objects, and the like. In addition, the surrounding environment information acquisition unit 61 may calculate the distance from the host vehicle 1 to the boundary of the driving lane. The boundary of the driving lane is recognized by, for example, white lines, sidewalls, curbs, etc.

[0031] In addition, when the surrounding environment information acquisition unit 61 detects another vehicle, it obtains the yaw rate of the other vehicle. The yaw rate of the other vehicle is obtained by calculation based on, for example, the attitude change of the other vehicle obtained from the image data of the front cameras 31LF and 31RF. When the host vehicle 1 and the other vehicle can communicate with each other via vehicle-to-vehicle communication, the surrounding environment information acquisition unit 61 may obtain necessary information such as the yaw rate, yaw acceleration, yaw angular acceleration, vehicle speed, and acceleration from the other vehicle via vehicle-to-vehicle communication. The surrounding environment information acquisition unit 61 detects the information of the surrounding environment at a predetermined cycle and stores it in the storage unit 53.

[0032] (Host vehicle information acquisition unit) The host vehicle information acquisition unit 63 obtains information on the operation state and behavior of the host vehicle 1 based on the detection data transmitted from the vehicle state sensor 35. The host vehicle information acquisition unit 63 obtains information on the operation state of the host vehicle 1, such as the steering angle of the steering wheel or the steering wheel, the accelerator opening, the brake operation amount, or the engine speed. In addition, the host vehicle information acquisition unit 63 obtains information on the behavior of the host vehicle 1, such as the vehicle speed, the longitudinal acceleration, the lateral acceleration, and the yaw rate. The host vehicle information acquisition unit 63 obtains these information at each predetermined calculation cycle and stores them in the storage unit 53.

[0033] (Risk calculation unit) The risk calculation unit 65 calculates the collision risk of the host vehicle 1 with respect to the moving object detected by the surrounding environment information acquisition unit 61 by calculation. The collision risk may include not only the risk of collision between the moving object and the host vehicle 1 but also the risk of obstacles generated when the host vehicle 1 collides with the moving object. Specifically, the risk calculation unit 65 predicts a plurality of driving behaviors of the detected moving object. In addition, the risk calculation unit 65 sets a plurality of driving conditions of the host vehicle 1. Then, for each of the driving conditions of the host vehicle 1, the risk calculation unit 65 calculates the collision risk between the moving object and the host vehicle 1 after a predetermined time based on the distance between the moving object and the host vehicle 1 after the predicted predetermined time and the probability that the moving object performs the operation of each driving behavior.

[0034] The driving behavior of a moving object refers to the motion state of the moving object defined by the steering angular velocity ωo and the acceleration αo of the moving object. Also, the driving conditions of the host vehicle 1 refer to the driving conditions of the host vehicle 1 defined by the steering angular velocity ωe and the acceleration αe of the steering wheel of the host vehicle 1.

[0035] (Driving condition setting unit) Based on the collision risk obtained by the risk calculation unit 65, the driving condition setting unit 67 selects the driving conditions of the host vehicle 1 that minimize the collision risk. The driving condition setting unit 67 transmits the steering angular velocity ωe and the acceleration αe corresponding to the selected driving conditions as target values to the vehicle control device 41. The vehicle control device 41 that has received the information on the driving conditions controls the driving of each control device based on the set information on the driving conditions. As a result, the risk of the host vehicle 1 colliding with the moving object is reduced. Alternatively, the risk of damage that occurs when the host vehicle 1 collides with the moving object is reduced.

[0036] <3. Specific processing of the driving support device> Subsequently, an operation example of the driving support device 50 according to the present embodiment will be specifically described. In the following description, an example in which the moving object is another vehicle will be described.

[0037] FIG. 3 shows a flowchart showing an example of the processing executed by the processing unit 51 of the driving support device 50. First, when an in-vehicle system including the driving support device 50 is activated (step S11), the host vehicle information acquisition unit 63 of the processing unit 51 acquires information on the host vehicle 1 (step S13). Specifically, the host vehicle information acquisition unit 63 acquires information on the operation state and behavior of the host vehicle 1 based on the detection data transmitted from the vehicle state sensor 35. The host vehicle information acquisition unit 63 acquires at least the operation state of the host vehicle 1 such as the steering angle of the steering wheel or the steering wheel, the accelerator opening, the brake operation amount, or the engine speed, and information on the behavior of the host vehicle 1 such as the vehicle speed, the longitudinal acceleration, the lateral acceleration, and the yaw rate. The host vehicle information acquisition unit 63 stores the acquired information in the storage unit 53.

[0038] Next, the surrounding environment information acquisition unit 61 of the processing unit 51 acquires the surrounding environment information of the host vehicle 1 (step S15). Specifically, the surrounding environment information acquisition unit 61 detects obstacles existing around the host vehicle 1 and the driving lane of the host vehicle 1 based on the detection data transmitted from the surrounding environment sensor 31. Further, the surrounding environment information acquisition unit 61 calculates the position, size, orientation, speed, distance from the host vehicle 1 to the obstacle, and relative speed of the obstacle with respect to the host vehicle 1. Furthermore, the surrounding environment information acquisition unit 61 calculates the distance from the host vehicle 1 to the end of the detected driving lane.

[0039] For example, the surrounding environment information acquisition unit 61 processes the image data transmitted from the front cameras 31LF and 31RF, and detects obstacles in front of the host vehicle 1 and the types of the obstacles by using a pattern matching technique or the like. Further, the surrounding environment information acquisition unit 61 calculates the position, size, and distance to the obstacle as seen from the host vehicle 1 based on the position of the obstacle in the image data, the size occupied by the obstacle in the image data, and the parallax information of the left and right front cameras 31LF and 31RF. Further, the surrounding environment information acquisition unit 61 calculates the relative speed of the obstacle with respect to the host vehicle 1 by differentiating the change in distance with respect to time. Furthermore, the surrounding environment information acquisition unit 61 calculates the speed of the obstacle by adding the speed of the host vehicle 1 to the relative speed of the obstacle with respect to the host vehicle 1.

[0040] Further, the surrounding environment information acquisition unit 61 may detect an obstacle based on the detection data transmitted from the LiDAR 31S. For example, the surrounding environment information acquisition unit 61 may calculate the position, type, size, distance from the host vehicle 1 to the obstacle, relative speed of the obstacle with respect to the host vehicle 1, and speed of the obstacle based on the time from transmitting an electromagnetic wave from the LiDAR 31S to receiving the reflected wave, the direction in which the reflected wave is received, and the range of the measured point group of the reflected wave.

[0041] In addition, when the surrounding environment information acquisition unit 61 detects another vehicle, it calculates the direction of the other vehicle. The direction of the other vehicle can be estimated based on, for example, the inclination of the front or rear part of the other vehicle with respect to the viewing angle of the front cameras 31LF and 31RF or the LiDAR 31S. However, the method for obtaining the direction of the other vehicle is not limited to the above example.

[0042] Furthermore, when the surrounding environment information acquisition unit 61 detects another vehicle, it calculates the yaw rate of the other vehicle. The yaw rate of the other vehicle can be estimated based on, for example, the attitude change of the other vehicle obtained from the detection data of the front cameras 31LF and 31RF or the LiDAR 31S. However, the method for obtaining the yaw rate of the other vehicle is not limited to the above example. Also, when the host vehicle 1 and the other vehicle can communicate via vehicle-to-vehicle communication, the surrounding environment information acquisition unit 61 may acquire information such as the yaw rate, yaw acceleration, yaw angular acceleration, vehicle speed, and acceleration from the other vehicle through vehicle-to-vehicle communication. The surrounding environment information acquisition unit 61 stores the acquired surrounding environment information in the storage unit 53.

[0043] Next, the risk calculation unit 65 of the processing unit 51 determines whether another vehicle is detected as an obstacle detected by the surrounding environment information acquisition unit 61 (step S17). If another vehicle is not detected (S17 / No), the processing unit 51 determines whether the in-vehicle system has stopped (step S25). As long as the in-vehicle system has not stopped (S25 / No), it returns to step S13 and repeatedly executes the processing of each step described so far. On the other hand, if another vehicle is detected (S17 / Yes), the risk calculation unit 65 calculates the collision risk of the host vehicle 1 with respect to the other vehicle (step S19).

[0044] FIG. 4 shows a flowchart showing the risk calculation process. First, the risk calculation unit 65 predicts a plurality of driving behaviors of other vehicles (step S31). The risk calculation unit 65 sets a plurality of steering angular velocities ωo and accelerations αo of other vehicles within a range assumed from the current driving states such as the yaw rate and vehicle speed of other vehicles detected by the surrounding environment information acquisition unit 61. For example, data in which the range of the assumed steering angular velocity ωo according to the value of the yaw rate is set in advance, and data in which the range of the assumed acceleration αo according to the vehicle speed is set in advance are stored in the storage unit 53 in advance, and the risk calculation unit 65 refers to these data to set a plurality of steering angular velocities ωo and accelerations αo of other vehicles. Further, the risk calculation unit 65 calculates the positions of other vehicles after a predetermined time based on the set steering angular velocity ωo and acceleration αo, and the position, orientation, vehicle speed, and yaw rate of other vehicles detected by the surrounding environment information acquisition unit 61, respectively.

[0045] FIG. 5 is an explanatory diagram showing an example of predicting the driving behavior of another vehicle 90. The other vehicle 90 shown in FIG. 5 is an other vehicle 90 traveling parallel to the host vehicle 1 in the same direction. The risk calculation unit 65 sets a plurality of steering angular velocities ωo and accelerations αo of the other vehicle 90 within a range assumed from the vehicle speed and yaw rate of the other vehicle 90. In FIG. 5, combinations (ωo, αo) of the steering angular velocity ωo and the acceleration αo are set to four patterns of (-5, 0), (0, 0), (5, 0), and (5, -1). Further, the positions of the other vehicle 90 after 1 second and 2 seconds when the other vehicle 90 travels according to each driving behavior are calculated. The steering angular velocity ωo has a positive value in the clockwise direction.

[0046] Note that in FIG. 5, four driving behaviors are set, but the number of driving behaviors to be set is not limited to four, and may be set to any number within the range in which the steering angular velocity ωo and the acceleration αo can be set. Further, the time interval indicating the position of the other vehicle 90 does not have to be 1 second intervals, and may be set to any time. When there are a plurality of other vehicles, the risk calculation unit 65 calculates a plurality of assumed driving behaviors for each other vehicle, and the position of the other vehicle 90 after a predetermined time when the other vehicle 90 travels with each driving behavior.

[0047] In addition, when predicting the driving behavior of the other vehicle 90, the risk calculation unit 65 may predict the driving behavior in consideration of the presence of obstacles around the other vehicle 90. For example, the risk calculation unit 65 may limit the range of the set steering angular velocity ωo and acceleration αo in consideration of the driving behavior of the other vehicle 90 to avoid a collision with an obstacle.

[0048] Next, the risk calculation unit 65 sets a plurality of driving conditions of the host vehicle 1 (step S33). The risk calculation unit 65 sets a plurality of steering angular velocities ωe and accelerations αe of the host vehicle 1 within a range assumed from the current driving state of the host vehicle 1 acquired by the host vehicle information acquisition unit 63. For example, similarly for the host vehicle 1, the risk calculation unit 65 refers to the data stored in the storage unit 53 in advance and sets a plurality of steering angular velocities ωe and accelerations αe of the host vehicle 1. Further, the risk calculation unit 65 calculates the positions of the host vehicle 1 after a predetermined time based on the set steering angular velocity ωe and acceleration αe, and the current position, orientation, vehicle speed, and steering angle of the host vehicle 1, respectively.

[0049] Next, the risk calculation unit 65 obtains the collision risk of the host vehicle 1 with respect to the other vehicle 90 by calculation for each of the driving conditions of the host vehicle 1 set in step S33 (step S35). In the present embodiment, the risk calculation unit 65 calculates the collision risk R based on the distance D between the host vehicle 1 and the other vehicle 90 after a predetermined time when the other vehicle 90 travels according to each set driving behavior, and the probability that the other vehicle 90 takes each driving behavior. More specifically, in the present embodiment, the risk calculation unit 65 sets the sum of the risks r at each time from time 0 seconds to an arbitrary time t seconds as the collision risk R for each combination of the driving condition of the host vehicle 1 and the driving behavior of the other vehicle 90.

[0050] Figs. 6 to 9 are explanatory diagrams showing an example of calculating the risk r at a predetermined time. Fig. 6 shows the position of the host vehicle 1 after 1 second when the combination (ωe, αe) of the steering angular velocity ωe and the acceleration αe is set to (5, 0) as the driving condition of the host vehicle 1. In this case, as shown in Fig. 7, for example, when the combination (ωo, αo) of the steering angular velocity ωo and the acceleration αo of the other vehicle 90 is (5, -1) as the driving behavior of the other vehicle 90, the distance D between the other vehicle 90 and the host vehicle 1 after 1 second is 2 m. Note that the positions of the other vehicle 90 and the host vehicle 1 may be the center-of-gravity positions of the vehicles set in advance, may be the positions at the center of the front part of the vehicles, or may be set at arbitrary positions.

[0051] The risk calculation unit 65 calculates the risk r based on the distance D between the host vehicle 1 and the other vehicle 90 after a predetermined time and the probabilities that the other vehicle 90 is operated by respective driving behaviors, using the following formula (1). The risk r shown in the following formula (1) is obtained by multiplying the reciprocal of the distance D between the other vehicle 90 and the host vehicle 1 at the same time by the probability that the other vehicle 90 exists at the position, with respect to the position of the host vehicle 1 at each time. In the following formula (1), the probability that the other vehicle 90 exists at the position is expressed as the product of the probability Ps that the set steering angular velocity ωo of the other vehicle 90 is realized and the probability Pa that the acceleration αo is realized.

[0052] Risk r = (1 / D) × (Ps) × (Pa) …(1) r: Risk at each time D: Distance between the other vehicle 90 and the host vehicle 1 Ps: Probability of the steering angular velocity ωo of the other vehicle 90 Pa: Probability of the acceleration αo of the other vehicle 90

[0053] FIG. 8 and FIG. 9 are explanatory diagrams showing examples of the probability Ps [%] of the steering angular velocity ωo and the probability Pa [%] of the acceleration αo of the other vehicle 90, respectively. The data of the respective probabilities Ps and Pa are obtained based on the frequency of the operation amount from the statistical data of the operation amounts of past vehicles. The data of the probabilities Ps and Pa may be set according to at least one of the yaw angular acceleration or the longitudinal and lateral accelerations of the vehicle. By obtaining the respective probabilities Ps and Pa according to the yaw angular acceleration or the longitudinal and lateral accelerations of the other vehicle 90, the probabilities Ps and Pa of the steering angular velocity ωo and the acceleration αo that the other vehicle 90 can operate can be obtained more accurately. The data of the probabilities Ps and Pa may be prepared in advance and stored in the storage unit 53, or may be stored in an external server capable of communicating with the driving support device 50 via the mobile wireless communication means.

[0054] Alternatively, the risk calculation unit 65 may calculate the probabilities Ps and Pa that the other vehicle 90 performs respective driving actions in the detected driving state and surrounding environment of the other vehicle 90. In this case, the driving support device 50 includes a driving action database that stores the driving actions performed by a plurality of vehicles in the past, not limited to the host vehicle 1 and a specific other vehicle 90, in association with the information on the driving state and surrounding environment during vehicle travel. Then, the risk calculation unit 65 extracts the driving action data acquired in the same environment from the driving action database based on the detected driving state and surrounding environment of the other vehicle 90, and obtains the probability Ps of the steering angular velocity ωo and the probability Pa of the acceleration αo. Thereby, the probabilities that the other vehicle 90 takes respective driving actions can be obtained more accurately.

[0055] In the example shown in FIG. 7, the distance D between the host vehicle 1 and the other vehicle 90 after 1 second is 2 m, the probability Ps of the steering angular velocity ωo is 10 (%), and the probability Pa of the acceleration αo is 20 (%). The risk r obtained by the following formula (1) is "100 (= 1 / 2 × 10 × 20)". The risk calculation unit 65 calculates the risk r for each combination of the driving conditions of the host vehicle 1 and the driving behavior of the other vehicle 90 from time 0 seconds to an arbitrary time t seconds, and sets the sum of the calculated risks r as the collision risk R for each driving condition of the host vehicle 1. Therefore, for each driving condition of the host vehicle 1, the collision risk R corresponding to the number of driving behaviors of the set other vehicle 90 is calculated.

[0056] Returning to FIG. 3, after the execution of the risk calculation process in step S19, the driving condition setting unit 67 selects the driving condition of the host vehicle 1 that minimizes the obtained collision risk R (step S21). Specifically, the driving condition setting unit 67 identifies the minimum collision risk R from among the collision risks R obtained by the risk calculation process, and sets the driving condition of the host vehicle 1 used for the calculation of the collision risk R as the driving condition to be output to the vehicle control device 41.

[0057] Next, the driving condition setting unit 67 transmits the information on the steering angular velocity ωe and the acceleration α e set as the driving condition to the vehicle control device 41 (step S23). The vehicle control device 41 that has received the information on the steering angular velocity ωe and the acceleration α e executes the automatic driving control of the host vehicle 1 with the steering angular velocity ωe and the acceleration α e as the target values. Thereby, the collision risk of the host vehicle 1 with respect to the other vehicle 90 can be reduced.

[0058] As described above, when another vehicle 90 is detected around the host vehicle 1, the driving support device 50 according to the present embodiment predicts a plurality of driving actions of the other vehicle 90, and for each of the driving conditions that can be set for the host vehicle 1, calculates a collision risk R after a predetermined time when the other vehicle 90 takes each driving action by calculation. Then, the driving support device 50 selects the driving condition of the host vehicle 1 that minimizes the obtained collision risk R and sets it as the driving condition to be output to the vehicle control device 41. Thereby, the driving condition of the host vehicle 1 is set based on the collision risk R reflecting the predicted driving actions of the other vehicle 90, and the risk of collision of the host vehicle 1 with respect to the other vehicle 90 can be reduced.

[0059] In addition, the driving support device 50 according to the present embodiment obtains the position of the host vehicle 1 after a predetermined time for each of the driving conditions that can be set for the host vehicle 1. Further, the driving support device 50 calculates the distance between the other vehicle 90 and the host vehicle 1 after a predetermined time based on the current yaw rate and speed of the detected other vehicle 90, the assumed steering angular velocity ωo and acceleration αo of the other vehicle 90, the probability Ps that the other vehicle 90 is operated with the set steering angular velocity ωo, and the probability Pa that the other vehicle 90 is operated with the set acceleration αo, and calculates a risk r after a predetermined time for each of the driving actions of the other vehicle 90. Then, the driving support device 50 sets the sum of the risks r from time 0 seconds to an arbitrary time t seconds as the collision risk R for each driving action of the other vehicle 90 for each driving condition of the host vehicle 1. Thereby, the higher the probability that the other vehicle 90 takes each driving action, the higher the collision risk R becomes, and the effect of reducing the collision risk of the host vehicle 1 with respect to the other vehicle 90 can be enhanced. Further, since the driving condition of the host vehicle 1 is set based on the collision risk over a predetermined period, the effect of reducing the collision risk of the host vehicle 1 with respect to the other vehicle 90 can be enhanced.

[0060] In addition, the driving support device 50 can also calculate the probability that each other vehicle 90 will take its respective driving action based on a driving action database that stores the driving actions performed by a plurality of vehicles in the past in association with information on the driving state and the surrounding environment during vehicle travel. As a result, the probability that each other vehicle 90 will take its respective driving action can be obtained more accurately. Further, when the driving action database is stored in a server accessible from the driving support device 50 via the mobile communication means, the data on the driving actions of a plurality of vehicles can be sequentially updated or accumulated in association with information on the driving state and the surrounding environment during vehicle travel. Therefore, the accuracy of the probability that each other vehicle 90 will take its respective driving action can be improved, and the effect of reducing the collision risk of the host vehicle 1 with respect to the other vehicle 90 can be enhanced.

[0061] <4. Modification Example> So far, one embodiment of the technology of the present disclosure has been described. However, various modifications or additions of functions are possible to the above embodiment. Hereinafter, some modification examples of the driving support device 50 according to the above embodiment will be described.

[0062] (4-1. First Modification Example) In the driving support device 50 according to the above embodiment, the collision risk R considering the possibility of collision between the host vehicle 1 and the other vehicle 90 has been calculated. However, the collision risk R may be calculated in consideration of the risk of an obstacle (hereinafter, also simply referred to as "obstacle risk") that occurs when a collision occurs between the host vehicle 1 and the other vehicle 90.

[0063] For example, the risk calculation unit 65 may calculate the risk r1 after a predetermined time based on at least one of the relative speed ΔV of the other vehicle 90 with respect to the host vehicle 1 or the angle θ formed by the direction of the host vehicle 1 and the direction of the other vehicle 90. Generally, the greater the relative speed ΔV of the other vehicle 90 with respect to the host vehicle 1, the greater the obstacle that occurs at the time of collision. Also, the smaller the angle θ formed by the direction of the host vehicle 1 and the direction of the other vehicle 90, the greater the impact at the time of collision and the greater the obstacle that occurs.

[0064] For example, the risk calculation unit 65 calculates the risk r1 based on the distance D between the host vehicle 1 and the other vehicle 90 after a predetermined time, the probability that the other vehicle 90 is operated in each driving behavior, the relative speed ΔV of the other vehicle 90 with respect to the host vehicle 1, and the angle θ formed by the direction of the host vehicle 1 and the direction of the other vehicle 90, using the following formula (2). The risk r1 shown in the following formula (2) is obtained by adding the relative speed ΔV of the other vehicle 90 with respect to the host vehicle 1 and the reciprocal of the angle θ formed by the direction of the host vehicle 1 and the direction of the other vehicle 90 to the risk r obtained by the above formula (1).

[0065] Risk r1 = (1 / D) × (Ps) × (Pa) + (ΔV) + (1 / θ) …(2) r1: Risk at each time D: Distance between the other vehicle 90 and the host vehicle 1 Ps: Probability of the steering angular velocity ωo of the other vehicle 90 Pa: Probability of the acceleration αo of the other vehicle 90 ΔV: Relative speed of the other vehicle 90 with respect to the host vehicle 1 θ: Angle formed by the direction of the host vehicle 1 and the direction of the other vehicle 90

[0066] When calculating the risk r1 by considering only one of the relative speed ΔV of the other vehicle 90 with respect to the host vehicle 1 or the angle θ formed by the direction of the host vehicle 1 and the direction of the other vehicle 90, either the relative speed ΔV or the reciprocal of the angle θ in the above formula (2) may be omitted or calculated as zero.

[0067] FIG. 10 is an explanatory diagram showing an example of calculating risk r1 at a predetermined time in consideration of obstacle risks. FIG. 10 shows the positions of the host vehicle 1 and the other vehicle 90 after 1 second shown in FIG. 7, with the directions of the host vehicle 1 and the other vehicle 90 represented respectively. The direction of the host vehicle 1 after a predetermined time can be estimated based on the set steering angular velocity ωe and acceleration αe, and information on the running state of the current host vehicle 1 such as vehicle speed, acceleration, and yaw rate. Also, the direction of the other vehicle 90 after a predetermined time can be estimated based on the set steering angular velocity ωo and acceleration αo, and information on the running state of the current other vehicle 90 such as vehicle speed, acceleration, and yaw rate. The risk calculation unit 65 may further estimate the direction of the host vehicle 1 or the other vehicle 90 in consideration of the road surface friction state.

[0068] The risk calculation unit 65 calculates the risk r1 for each combination of the driving conditions of the host vehicle 1 and the driving behavior of the other vehicle 90 from time 0 seconds to an arbitrary time t seconds, and sets the sum of the calculated risks r1 as the collision risk R for each driving condition of the host vehicle 1. In this way, by calculating the risk r1 after a predetermined time in consideration of at least one of the relative speed ΔV of the other vehicle 90 with respect to the host vehicle 1 or the angle θ formed by the direction of the host vehicle 1 and the direction of the other vehicle 90, the risk of collision of the host vehicle 1 with respect to the other vehicle 90 can be reduced, and the risk of obstacles occurring even when a collision occurs can also be reduced.

[0069] Furthermore, the risk calculation unit 65 may calculate a risk r2 after a predetermined time based on the collision position of the host vehicle 1 with respect to the other vehicle 90. In this case, for example, using the following formula (3), the risk r2 is calculated based on the distance D between the host vehicle 1 and the other vehicle 90 after a predetermined time, the probability that the other vehicle 90 is operated by each driving behavior, and the collision position risk Q corresponding to the collision position of the host vehicle 1 with respect to the other vehicle 90. The risk r2 shown in the following formula (3) is obtained by adding the collision position risk Q corresponding to the assumed collision position to the risk r obtained by the above formula (1).

[0070] Risk r2 = (1 / D)×(Ps)×(Pa)+(Q) …(3) r2: Risk at each moment D: Distance between other vehicle 90 and own vehicle 1 Ps: Probability of steering angular velocity ωo of other vehicle 90 Pa: Probability of acceleration αo of other vehicle 90 Q: Collision position risk of own vehicle 1 with respect to other vehicle 90

[0071] The collision position risk Q may be a risk value set for each collision position of own vehicle 1 based on, for example, a characteristic indicating the impact that own vehicle 1 receives due to a collision. In this case, data on the collision position risk set for each collision position of own vehicle 1 based on the characteristic indicating the impact that own vehicle 1 receives due to a collision is stored in advance in the storage unit 53. Also, the collision position risk Q may be a risk value set for each collision position according to the position and physique of the occupant of own vehicle 1. In this case, for example, when starting the operation of own vehicle 1, the driving support device 50 acquires information such as the position, physique, or age of the occupant input by the user and stores it in the storage unit 53.

[0072] FIG. 11 is an explanatory diagram showing an example of calculating the risk r2 at a predetermined time considering the collision position risk. FIG. 11 shows the positions of own vehicle 1 and other vehicle 90 one second after shown in FIG. 7, and represents the directions of own vehicle 1 and other vehicle 90, the information of the occupant of own vehicle 1, and the collision position risk, respectively. In the example shown in FIG. 11, own vehicle 1 has a driver sitting in the driver's seat Dr and an infant B sitting on the right side of the rear seat. For this reason, the collision position risk of the left rear part of own vehicle 1 close to infant B is set to 100 (points), the collision position risks of the left front part and the right rear part are set to 10 (points), and the collision position risk of the front part is set to 1 (point). For this reason, the risk r2 of the driving condition of own vehicle 1 where the collision position of own vehicle 1 with respect to other vehicle 90 can be the left rear part becomes high. However, the setting of the collision position risk is not limited to the example shown in FIG. 11.

[0073] In this way, by setting the collision position risk of the host vehicle 1 with respect to another vehicle 90 and calculating the risk r2 after a predetermined time, there is no possibility of setting a driving condition in which it is assumed that the obstacle generated at the time of collision becomes large, and the risk of collision of the host vehicle 1 with respect to another vehicle 90 can be reduced, and the risk of the obstacle generated even when a collision occurs can be reduced.

[0074] Note that the obstacle risk is not limited to the collision position risk set according to the collision position of the host vehicle 1, and other risks related to obstacles that are considered to occur at the time of collision may be arbitrarily set. For example, when the weight of another vehicle 90 is large, it is considered that the collision energy becomes large and the obstacle generated becomes large. Therefore, the risk calculation unit 65 may calculate the collision risk by adding the weight risk set based on the weight of another vehicle 90 estimated from the type or size of another vehicle 90.

[0075] (4-2. Second Modification Example) In the driving support device 50 according to the above embodiment, the probability that each of the other vehicles 90 takes its respective driving action is calculated without considering the tendency of the driving action of the other vehicle 90. However, the probability that each of the other vehicles 90 takes its respective driving action may be calculated based on the driving characteristics representing the tendency of the driving action of the other vehicle 90. For example, an external server accessible by the driving support device 50 via wireless communication means is provided with a driving action database that stores the driving actions performed by a plurality of vehicles in the past, not limited to the host vehicle 1 and a specific other vehicle 90, in association with the identification information of each vehicle, the driving state when the vehicle is traveling, and the information on the surrounding environment.

[0076] Here, the "driving characteristics" that represent the tendency of driving behavior refer to personal characteristics related to the orientation towards driving, such as driving style and the way of feeling fear towards driving, and the tendency of driving actions. For example, as driving styles, there are exemplified "want to comply with the speed limit", "want to ensure a sufficient distance from the vehicle ahead", "want to decelerate sufficiently before entering a curve", "want to advance as far as possible even by changing lanes", "want to reduce the distance from the vehicle ahead as much as possible", etc. Also, as the way of feeling fear towards driving, for example, assuming in what kind of driving environment fear is felt, there are exemplified "roads with many parked cars", "driving at night", "roads with many blind spots", "situations with many vehicles traveling at high speeds", "situations with heavy traffic", etc. The driving characteristics are stored in association with the identification information of the vehicle as data obtained by evaluating, for example, one or more items representing driving characteristics, such as cautiousness or hastiness, on a 5 - level scale.

[0077] The risk calculation unit 65 transmits information that can identify the other vehicle 90 to an external server together with the information on the driving state of the detected other vehicle 90 and the surrounding environment, and specifies the driving characteristics of the other vehicle 90. The information that can identify the other vehicle 90 may be, for example, the numbers of the license plate specified from the detection data of the front cameras 31LF and 31RF, or may be the identification information obtained from the other vehicle 90 by vehicle - to - vehicle communication. In addition, when the other vehicle 90 records information on its driving characteristics, the risk calculation unit 65 may obtain the information on the driving characteristics from the other vehicle 90 by vehicle - to - vehicle communication.

[0078] Further, the risk calculation unit 65 extracts driving behavior data that a vehicle with the same driving characteristics as the driving characteristics of the other vehicle 90 has performed in the same environment in the past from the driving behavior database. Then, the risk calculation unit 65 predicts a plurality of driving behaviors of the other vehicle 90 based on the driving behavior data extracted from the driving behavior database and performed in the same environment in the past, and calculates the probability that the other vehicle 90 performs each driving behavior in the driving state and surrounding environment of the other vehicle 90. Thereby, it is possible to obtain the probability that the other vehicle 90 takes each driving behavior in consideration of the detected driving characteristics of the other vehicle 90. Therefore, the collision risk R reflecting the predicted driving behavior of the other vehicle 90 can be obtained more accurately, and driving conditions with a low risk of collision of the host vehicle 1 with respect to the other vehicle 90 can be set.

[0079] (4-3. Third Modification Example) In the above embodiment, the risk calculation unit 65 has set the driving behavior of the other vehicle 90. However, when the other vehicle 90 is a vehicle in automatic driving, the risk calculation unit 65 may acquire information on driving conditions from the other vehicle 90. In this case, the risk calculation unit 65 can estimate the position of the other vehicle 90 after a predetermined time by acquiring information on the planned travel trajectory, vehicle speed, and acceleration of the other vehicle 90 via, for example, vehicle-to-vehicle communication. The risk calculation unit 65 sets the probability that the other vehicle 90 performs the driving behavior to 100% and calculates the risk r of the host vehicle 1 at a predetermined time. Thereby, the collision risk R of the host vehicle 1 with respect to the other vehicle 90 after a predetermined time is calculated based on the information on the driving behavior of the other vehicle 90 with high accuracy, and driving conditions with a low risk of collision of the host vehicle 1 with respect to the other vehicle 90 can be set.

[0080] As described above, the preferred embodiments of the present disclosure have been described in detail with reference to the accompanying drawings. However, the present disclosure is not limited to such examples. It is obvious that those having ordinary knowledge in the technical field to which the present disclosure pertains can conceive of various modification examples or correction examples within the scope of the technical idea described in the claims, and it is naturally understood that these also belong to the technical scope of the present disclosure.

[0081] For example, in the above embodiment, all the functions of the driving support device 50 were mounted on the host vehicle 1, but the present disclosure is not limited to such an example. For example, a part of the functions of the driving support device 50 may be provided in a server device that can communicate via mobile communication means, and the driving support device 50 may be configured to transmit and receive data to and from the server device.

[0082] Also, in the above embodiment, an example in which the moving object is another vehicle 90 was described as an example of the specific processing of the driving support device 50, but the moving object is not limited to a vehicle. The moving object may be a bicycle or a pedestrian. In this case, the probability of the driving behavior of each moving object can be set based on, for example, statistical data of the driving behavior of the moving object associated with the type, direction, surrounding environment, etc. of the moving object. Further, when the moving object is a pedestrian or a bicycle, it is considered that the damage generated at the time of collision becomes larger than when the moving object is a vehicle. Therefore, a moving object risk corresponding to the type of the moving object may be set, and the moving object risk may be added to calculate the collision risk.

Explanation of Reference Numerals

[0083] 1: Vehicle (host vehicle), 9: Driving force source, 13: Steering wheel, 15: Electric steering device, 20: Brake hydraulic control unit, 31: Surrounding environment sensor, 35: Vehicle state sensor, 41: Vehicle control device, 50: Driving support device, 51: Processing unit, 53: Storage unit, 61: Surrounding environment information acquisition unit, 63: Host vehicle information acquisition unit, 65: Risk calculation unit, 67: Driving condition setting unit, 90: Another vehicle, αe: Acceleration of the host vehicle, αo: Acceleration of the other vehicle, ωe: Steering angular velocity of the host vehicle, ωo: Steering angular velocity of the other vehicle

Claims

1. In a driving support device that sets the driving conditions of the host vehicle based on the risk of collision with obstacles around the host vehicle, comprising one or more processors and one or more memories communicably connected to the one or more processors, the one or more processors detect a moving object and the surrounding environment around the host vehicle, predict the driving behavior of the moving object based on the acceleration and steering angular velocity of the moving object assumed from the current yaw rate and speed of the detected moving object, for each of the predicted driving behaviors of the moving object, based on the distance between the moving object and the host vehicle after a predetermined time, the probability of an operation at the acceleration, the probability of an operation at the steering angular velocity, and a hazard risk indicating the magnitude of the obstacle that occurs when a collision occurs between the host vehicle and the moving object, calculate the collision risk between the moving object and the host vehicle after a predetermined time, set the driving conditions of the host vehicle based on the collision risk, A driving support device that executes a process including this.

2. The one or more processors obtain the position of the host vehicle after a predetermined time for each of the driving conditions that can be set for the host vehicle, For each of the predicted driving behaviors of the moving object, based on the distance between the moving object and the host vehicle after a predetermined time, the probability of an operation at the acceleration, the probability of an operation at the steering angular velocity, the position of the host vehicle after each predetermined time according to the driving conditions that can be set for the host vehicle, and the hazard risk, calculate the collision risk after the predetermined time. The driving support device according to claim 1.

3. The one or more processors calculate the hazard risk after a predetermined time for each of the driving behaviors of the moving object based on at least one of the relative speed between the host vehicle and the moving object or the angle formed by the direction of the host vehicle and the direction of the moving object. The driving support device according to claim 1.

4. The one or more processors calculate the hazard risk after a predetermined time for each of the driving behaviors of the moving object based on the collision position of the host vehicle with respect to the moving object. The driving support device according to claim 1.

5. The driving support device comprises a driving behavior database that stores the driving behaviors performed by a plurality of moving objects in association with the driving state and the surrounding environment in the past, the one or more processors The driving support device according to claim 1, which calculates the probability that the detected moving object performs each of the driving actions in the driving state of the moving object and the surrounding environment based on the driving action database.

6. The driving action database stores information on the driving characteristics of each of the moving objects and the past driving actions of the moving objects in association with the driving state and the surrounding environment. The one or more processors The driving support device according to claim 5, which calculates the probability that the detected moving object performs each of the driving actions in the driving state of the moving object and the surrounding environment based on the driving action database.

7. The one or more processors When the moving object includes a vehicle in automatic driving, the driving support device according to claim 1 acquires information on the driving action of the automatic driving vehicle, further calculates the collision risk of the host vehicle using the acquired information on the driving action, and sets the driving conditions of the host vehicle.

8. A recording medium recording a computer program applied to a driving support device that sets the driving conditions of the host vehicle based on the collision risk with an obstacle around the host vehicle, to one or more processors detect the moving objects and the surrounding environment around the host vehicle; predict the driving action of the moving object based on the acceleration and steering angular velocity of the moving object assumed from the current yaw rate and speed of the detected moving object; for each of the predicted driving actions of the moving object, calculate the collision risk between the moving object and the host vehicle after a predetermined time based on the distance between the moving object and the host vehicle after the predetermined time, the probability that an operation is performed at the acceleration, the probability that an operation is performed at the steering angular velocity, and the obstacle risk indicating the size of the obstacle that occurs when a collision occurs between the host vehicle and the moving object; set the driving conditions of the host vehicle based on the collision risk; A recording medium recording a computer program that causes the above processing to be executed.

Images