Mobile body behavior prediction method, behavior prediction device, and vehicle

Abstract

In the behavior prediction method, the position of the host vehicle (1) is determined (S10); the position of another vehicle (4a) on a second driving lane (3) which is an opposite lane to a first driving lane (2) on which the host vehicle is traveling is determined (S11); an intersecting passage (5) intersecting with the second driving lane in front of the host vehicle is detected (S13); it is determined whether the other vehicle is within a specified range (R1) (S13) and the other vehicle is in any of a stopped state and a decelerated state (S12), wherein the specified range (R1) is a range from an intersection position (6) of the intersecting passage and the second driving lane to a point which is away from the intersection position (6) by a specified distance in a direction opposite to the forward direction of the vehicle on the second driving lane; and when the other vehicle is within the specified range and the other vehicle is in any of a stopped state and a decelerated state, it is predicted that there is a possibility that a moving body (8a) enters the first driving lane from the intersecting passage (S14).

Description

Technical Field

[0001] The present invention relates to a behavior prediction method, a behavior prediction device and a vehicle for a mobile object. Background Art

[0002] Patent document 1 describes a vehicle driving assistance device that detects a blind spot and calculates a movable range when an object is present in the blind spot and flies out, thereby performing driving assistance control by performing an evasive operation so that the vehicle does not collide with the object.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2006-260217 Summary of the invention

[0006] Problem that the invention aims to solve

[0007] However, if the driving assist control is always performed in a manner assuming that an object will fly out from a blind spot, unnecessary avoidance operations will be performed.

[0008] An object of the present invention is to improve the accuracy of predicting the possibility that another mobile object will enter a lane in which a host vehicle is traveling.

[0009] Solutions for solving problems

[0010] In a behavior prediction method involved in one embodiment of the present invention, the position of the vehicle is determined; the position of other vehicles on the second driving lane which is the opposite lane of the first driving lane in which the vehicle is traveling is determined; an intersecting passage that intersects with the second driving lane in front of the vehicle is detected; it is determined whether the other vehicles are located within a specified range and are in any one of a parked state and a decelerated state, wherein the specified range is a range from the intersection position of the intersecting passage and the second driving lane to a point that is a specified distance away from the intersection position in a direction opposite to the forward direction of the vehicle on the second driving lane; and when the other vehicles are located within the specified range and are in any one of a parked state and a decelerated state, it is predicted that there is a possibility that a moving body enters the first driving lane from the intersecting passage.

[0011] Effects of the Invention

[0012] According to one aspect of the present invention, the accuracy of prediction of the possibility that another moving object will enter the lane in which the host vehicle is traveling is improved.

[0013] The objects and advantages of the present invention are realized and achieved by using the elements and combinations thereof shown in the claims. It should be understood that both the above general description and the following detailed description are merely illustrative and explanatory and do not limit the present invention as the claims do. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic structural diagram of a vehicle according to an embodiment.

[0015] Figure 2 It is an explanatory diagram of the behavior prediction method in the first embodiment.

[0016] Figure 3 This is a block diagram showing an example of the functional configuration of the driving assistance device in the first embodiment.

[0017] Figure 4 This is a flowchart of an example of the driving assistance method according to the embodiment.

[0018] Figure 5 This is a flowchart of the moving body behavior prediction routine in the first embodiment.

[0019] Figure 6 This is a flowchart of a moving body entry prediction routine according to an embodiment.

[0020] Figure 7 It is an explanatory diagram of the behavior prediction method in the second embodiment.

[0021] Figure 8 This is a block diagram showing an example of the functional configuration of the driving assistance device in the second embodiment.

[0022] Fig. 9 This is a flowchart of a moving body behavior prediction routine in the second embodiment.

[0023] Fig.10 It is an explanatory diagram of the behavior prediction method in the third embodiment.

[0024] Fig.11 This is an explanatory diagram of another example of a cross passage.

[0025] Fig.12 This is a block diagram showing an example of the functional configuration of the driving assistance device in the third embodiment.

[0026] Fig.13 This is a flowchart of a moving body behavior prediction routine in the third embodiment. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0028] (First Embodiment)

[0029] (structure)

[0030] Reference Figure 1 The vehicle 1 is provided with a driving assistance device 10 for assisting the driving of the vehicle 1. The driving assistance performed by the driving assistance device 10 may include an automatic driving control for automatically driving the vehicle 1 without the driver's participation based on the driving environment around the vehicle 1, and a driving assistance control for assisting the driver in driving the vehicle 1.

[0031] Driving assistance control includes not only driving control such as automatic steering, automatic braking, constant speed driving control, lane keeping control, and merging assist control, but also outputting messages to the driver to urge them to perform steering operations or deceleration operations.

[0032] The driving assistance device 10 includes an object sensor 11, a vehicle sensor 12, a positioning device 13, a map database 14, a communication device 15, a notification device 16, a deceleration mechanism 17, and a controller 18. In the drawings, the map database is referred to as "map DB".

[0033] The object sensor 11 includes a plurality of different types of object detection sensors such as a laser radar, a millimeter wave radar, and a camera mounted on the host vehicle 1 to detect objects around the host vehicle 1 .

[0034] The vehicle sensor 12 is mounted on the vehicle 1 and is used to detect various information (vehicle signals) related to the state of the vehicle 1. The vehicle sensor 12 includes, for example, a vehicle speed sensor for detecting the running speed (vehicle speed) of the vehicle 1, a wheel speed sensor for detecting the rotation speed of each tire of the vehicle 1, a three-axis acceleration sensor (G sensor) for detecting the acceleration (including deceleration) of the vehicle 1 in three axes, a steering angle sensor for detecting the steering angle (including the turning angle), a gyro sensor for detecting the angular velocity generated by the vehicle 1, and a yaw rate sensor for detecting the yaw rate.

[0035] The positioning device 13 includes a global navigation satellite system (GNSS) receiver, and receives radio waves from a plurality of navigation satellites to measure the current position of the host vehicle 1. The GNSS receiver may be, for example, a global positioning system (GPS) receiver, etc. The positioning device 13 may be, for example, an inertial navigation device.

[0036] The map database 14 stores preferred high-precision map data (hereinafter referred to as "high-precision map") as a map for autonomous driving. The high-precision map is map data with higher precision than map data for navigation (hereinafter referred to as "navigation map"), and the high-precision map contains more detailed lane unit information than road unit information.

[0037] For example, a high-precision map includes information on lane nodes representing reference points on a lane reference line (e.g., the center line within a lane) and information on lane links (in Japanese: 車線リンク) representing the section method of the lane between lane nodes as lane unit information.

[0038] The information on lane nodes includes the identification number, position coordinates, number of connected lane links, and identification numbers of the connected lane links of the lane node. The information on lane links includes the identification number of the lane link, type of lane, width of the lane, type of lane boundary line, shape of the lane, shape of the lane separator line, and shape of the lane reference line. The high-precision map also includes the types and position coordinates of road features such as traffic lights, stop lines, signs, buildings, utility poles, curbs, crosswalks, etc. existing on or near the lane, and the identification numbers of lane nodes and lane links corresponding to the position coordinates of the road features, etc. as road feature information.

[0039] Since the high-precision map includes node and line information in lane units, it is possible to determine the lane in which the vehicle 1 is traveling on the driving path. The high-precision map has coordinates capable of representing positions in the extending direction and width direction of the lane. The high-precision map has coordinates capable of representing positions in a three-dimensional space (e.g., longitude, latitude, and altitude), and lanes and the above-mentioned road features can also be described as shapes in a three-dimensional space.

[0040] The communication device 15 performs wireless communication with a communication device outside the vehicle 1. The communication method of the communication device 15 can be, for example, wireless communication using a public mobile phone network, vehicle-to-vehicle communication, vehicle-to-roadside communication, or satellite communication.

[0041] The notification device 16 is an information output device that outputs information (e.g., messages urging steering operations and deceleration operations) presented by the driving assistance device 10 to the driver for driving assistance. The notification device 16 can include, for example, a display device, a lamp, or an instrument that outputs visual information, or a speaker that outputs sound information.

[0042] The deceleration mechanism 17 applies a braking force to the rotation of the wheels through a mechanical brake, an engine brake, or a regenerative brake to reduce the traveling speed of the vehicle 1.

[0043] The controller 18 is an electronic control unit (ECU: Electronic Control Unit) that performs driving assistance control of the vehicle 1. The controller 18 includes peripheral components such as a processor 20 and a storage device 21. The processor 20 can be, for example, a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit).

[0044] The storage device 21 includes a semiconductor storage device, a magnetic storage device, an optical storage device, etc. The storage device 21 may include a register, a cache memory, a ROM (Read Only Memory) used as a main storage device, a RAM (Random Access Memory), and other memories.

[0045] The functions of the controller 18 described below are realized by, for example, the processor 20 executing a computer program stored in the storage device 21 .

[0046] Alternatively, the controller 18 may be formed by dedicated hardware for executing each information processing described below.

[0047] For example, the controller 18 may include a functional logic circuit set in a general-purpose semiconductor integrated circuit. For example, the controller 18 may include a programmable logic device (PLD: Programmable Logic Device) such as a field programmable gate array (FPGA: Field-Programmable Gate Array).

[0048] When performing the driving assist control, the controller 18 predicts the behavior of other moving objects so as to avoid a collision between the host vehicle 1 and other moving objects entering the driving lane of the host vehicle 1. The controller 18 is an example of a behavior prediction device described in the claims.

[0049] Figure 2 The vehicle 1 is traveling in the first driving lane 2, and other vehicles 4a, 4b, etc. are present in the second driving lane 3 which is the opposite lane to the first driving lane 2. Figure 2 In the example described, the vehicle is traveling on the left side. That is, the forward direction of the vehicle 1 (i.e., the forward direction of the vehicle on the first driving lane 2) is from the bottom to the top of the paper, and the forward directions of the other vehicles 4a, 4b, etc. (i.e., the forward direction of the vehicle on the second driving lane 3) are from the top to the bottom of the paper. In the following embodiments, the case where the vehicle is traveling on the left side is used as an example for explanation.

[0050] In front of the vehicle 1, there is an intersection passage 5 intersecting with the second driving lane 3. The intersection passage 5 may be, for example, a branch road or a private land exit. For example, the branch road may be a narrow merging road where no traffic signal is provided at the merging point with the second driving lane 3.

[0051] Here, if there is another vehicle 4a on the second driving lane 3 within a predetermined range R1 on the front side relative to the intersection position 6 where the intersection passage 5 intersects with the second driving lane 3 (i.e., a predetermined range from the intersection position 6 to a point away from the intersection position 6 by a predetermined distance in the direction opposite to the advancing direction of the vehicle traveling on the second driving lane 3), and the other vehicle 4a is in a stopped state or a decelerated state, it is considered that there is a possibility that the vehicle 4a is giving way to another moving body (e.g., a vehicle, a motorcycle, a bicycle, a pedestrian, etc.) entering from the intersection passage 5. In addition, here, the front side on the first driving lane 2 and the second driving lane 3 below refers to the direction opposite to the advancing direction of the vehicle traveling on the driving lanes. On the contrary, if there is another vehicle 4a within the predetermined range R1 on the front side relative to the intersection position 6, and the other vehicle 4a is not in a stopped state or a decelerated state, it is considered that there is no other moving body entering from the intersection passage 5.

[0052] Therefore, when other vehicles 4a are in a stopped state or a decelerated state within a predetermined range R1 on the front side relative to the intersection position 6, the controller 18 predicts that there is a possibility that the vehicle 8a (i.e., other moving body) enters the first driving lane 2 from the intersection passage 5 as shown by arrow 9. On the contrary, when other vehicles 4a are not in a stopped state or a decelerated state within the predetermined range R1, the controller 18 predicts that there is no possibility that other moving bodies enter the first driving lane 2 from the intersection passage 5.

[0053] Thus, even if the intersection 5 enters the blind spot 7 of the other vehicle 4 b on the second driving lane 3 , the controller 18 can predict the presence or absence of another moving object entering from the intersection 5 based on the behavior of the other vehicle 4 a .

[0054] Here, the intersection position 6 is the position at the frontmost side of the entrance and exit of the intersection passage 5 facing the second driving lane 3, and the state in which the body of the other vehicle 4a does not come out of the prescribed range R1 is regarded as the state in which the other vehicle 4a exists within the prescribed range R1. That is, in the case where a part of the body of the other vehicle 4a blocks a part of the entrance and exit side of the intersection passage 5 facing the second driving lane 3 from the intersection position 6, the other vehicle 4a blocks the forward path of the moving body (vehicle 8a) that wants to enter the second driving lane 3 from the intersection passage 5, and it is determined that the other vehicle 4a does not give way to the forward path of the other moving body entering from the intersection passage 5. However, as described above, the intersection position 6 is a position that serves as a reference for determining whether the body of the other vehicle 4a blocks the forward path of the moving body (vehicle 8a) that wants to enter the second driving lane 3 from the intersection passage 5. For example, when the road width of the intersection passage 5 is wide enough, even if the body of the other vehicle 4a blocks the entrance and exit side of the intersection passage 5 facing the second driving lane 3 to some extent, there is a case in which the forward path of the moving body (vehicle 8a) is not blocked. Therefore, regarding the intersection position 6, strictly speaking, the intersection position 6 may not be the frontmost position of the entrance and exit of the intersection passage 5 facing the second driving lane 3, but may be set on the entrance and exit side of the intersection passage 5 at a specified distance from the frontmost position of the entrance and exit of the intersection passage 5 facing the second driving lane 3 so as not to hinder the forward route of a moving body that wants to enter the second driving lane 3 from the intersection passage 5.

[0055] Reference Figure 3 The functions of the controller 18 are described in detail. The controller 18 includes an object detection unit 30, a host vehicle position estimation unit 31, a map acquisition unit 32, a detection integration unit 33, an object tracking unit 34, an in-map position calculation unit 35, a behavior prediction unit 36, a host vehicle path generation unit 37, and a vehicle control unit 38.

[0056] The object detection unit 30 detects the position, posture, size, speed, etc. of objects around the host vehicle 1, such as vehicles, motorcycles, pedestrians, obstacles, etc., with respect to the host vehicle 1 based on the detection signal of the object sensor 11. The object detection unit 30 outputs the detection result that expresses the two-dimensional position, posture, size, speed, etc. of the object in, for example, a top view (also called a bird's-eye view) of the host vehicle 1 from the air.

[0057] The vehicle position estimation unit 31 measures the absolute position of the vehicle 1 , that is, the position, posture, and speed of the vehicle 1 relative to a predetermined reference point, based on an odometer using the measurement results obtained by the positioning device 13 and the detection results from the vehicle sensor 12 .

[0058] The map acquisition unit 32 acquires map information indicating the structure of the road on which the host vehicle 1 travels from the map database 14. The map acquisition unit 32 may acquire map information from an external map data server via the communication device 15.

[0059] The detection integration unit 33 integrates a plurality of detection results obtained by the object detection unit 30 from a plurality of object detection sensors, and outputs one detection result for each object.

[0060] Specifically, based on the behaviors of the objects obtained from the object detection sensors, the most reasonable behavior of the object with the least error is calculated taking into account the error characteristics of the object detection sensors.

[0061] Specifically, by using known sensor fusion technology, the detection results obtained by multiple types of sensors are comprehensively evaluated to obtain more accurate detection results.

[0062] The object tracking unit 34 tracks the object detected by the object detection unit 30. Specifically, based on the detection results integrated by the detection integration unit 33, the identity of the object at different times is verified (correlated) according to the behavior of the object output at different times, and the behavior of the object such as the speed is predicted based on the correlation.

[0063] The on-map position calculation unit 35 estimates the position and posture of the host vehicle 1 on the map based on the absolute position of the host vehicle 1 obtained by the host vehicle position estimation unit 31 and the map information acquired by the map acquisition unit 32. In addition, the on-map position calculation unit 35 determines the road on which the host vehicle 1 is traveling and also determines the lane in which the host vehicle 1 is traveling on the road.

[0064] The behavior prediction unit 36 ​​predicts the behavior of other objects around the host vehicle 1 based on the detection results obtained by the detection integration unit 33 and the object tracking unit 34 and the position of the host vehicle 1 specified by the in-map position calculation unit 35 .

[0065] Furthermore, the behavior prediction unit 36 ​​predicts whether there is a possibility that another moving object will enter the first driving lane 2 which is the driving lane of the host vehicle from the intersection 5 which intersects with the second driving lane 3 which is the oncoming lane of the driving lane of the host vehicle 1 in front of the host vehicle 1 .

[0066] The behavior prediction unit 36 ​​includes a lane determination unit 40 , an oncoming vehicle determination unit 41 , a stop determination unit 42 , an intersecting traffic detection unit 43 , and an entry prediction unit 44 .

[0067] The lane determination unit 40 estimates the positions and postures of other vehicles around the host vehicle 1 on the map based on the detection results obtained by the detection integration unit 33 and the object tracking unit 34 and the position of the host vehicle 1 determined by the map position calculation unit 35. In addition, it determines which lane the other vehicles belong to in the map.

[0068] In addition, the oncoming vehicle determination unit 41 determines whether another vehicle around the host vehicle 1 is an oncoming vehicle existing in the second driving lane 3 which is an oncoming lane opposite to the first driving lane in which the host vehicle 1 is traveling. Thus, the oncoming vehicle determination unit 41 determines whether another vehicle 4a around the host vehicle 1 is an oncoming vehicle in the second driving lane 3.

[0069] When the other vehicle 4a is an oncoming vehicle, the stop determination unit 42 determines whether the other vehicle 4a is stopped or decelerated. In this specification, "stopped" includes not only a case where the speed is zero, but also a state where the speed is below a predetermined vehicle speed that is approximately close to zero.

[0070] The intersecting passage detection unit 43 detects an intersecting passage 5 intersecting with the second driving lane 3 in front of the host vehicle 1 based on the map information.

[0071] In addition, the intersection detection unit 43 detects whether the position of another vehicle 4a in a parked state or a decelerated state is within a specified range R1 on the front side of the intersection position 6 where the intersection 5 intersects the second driving lane 3 (i.e., a specified range from the intersection position 6 to a point that is a specified distance away from the intersection position 6 in a direction opposite to the forward direction of the second driving lane 3).

[0072] The entry prediction unit 44 determines whether there is a possibility that the moving object will enter the first driving lane 2 from the intersection 5 .

[0073] When the other vehicle 4 a is not in a stopped state or a decelerated state within the predetermined range R1 , the entry prediction unit 44 predicts that there is no possibility that another moving object will enter the first driving lane 2 from the intersection 5 .

[0074] On the other hand, when the position of another vehicle 4 a in a stopped state or a decelerated state is within the predetermined range R1 , the entry prediction unit 44 predicts that there is a possibility that another moving body may enter the first driving lane 2 from the intersection 5 .

[0075] For example, when the other vehicle 4 a is stopped or decelerated on the front side of the intersection 5 , it is considered that the other vehicle 4 a is making way for the vehicle 8 a entering from the intersection 5 .

[0076] For example, when another vehicle 4a stops at the entrance of the intersection 5 while changing its posture by turning nearly 90 degrees, it is considered that there is a high possibility that a pedestrian is crossing the intersection 5 or that the intersection 5 is congested and cannot enter. However, when another vehicle 4a stops at the entrance of the intersection 5 while leaving the entrance of the intersection 5 without turning, it is considered that there is a possibility that the vehicle 8a wants to enter from the intersection 5 and is giving way to the vehicle.

[0077] In this situation, considering that the vehicle 8a that has been given up the way wants to quickly enter the intersection 5 to allow other vehicles 4a to start again, the vehicle 8a may suddenly enter the intersection 5. When the vehicle 8a suddenly enters the driving lane 2 of the host vehicle 1, there is a possibility that the host vehicle 1 and the vehicle 8a are closer than expected. In this case, the host vehicle 1 and the vehicle 8a need to decelerate suddenly.

[0078] By predicting such a scenario in advance using the entry prediction unit 44 , the vehicle can be decelerated and driven slowly on the front side of the intersection 5 , thereby avoiding sudden deceleration.

[0079] Furthermore, when determining that the intersection 5 is a branch road or a private land exit, the entry prediction unit 44 may determine whether there is a possibility that the vehicle 8 a as a moving object may enter the first driving lane 2 from the intersection 5 .

[0080] Alternatively, when the intersection 5 is determined to be a crosswalk, the entry prediction unit 44 may determine whether there is a possibility that a pedestrian as a moving object may enter the first driving lane 2 from the intersection 5. Alternatively, when the intersection 5 is not any of a fork, a private land exit, and a crosswalk, it may be determined that there is no possibility that a moving object may enter the first driving lane 2 from the intersection 5.

[0081] Alternatively, the entry prediction unit 44 may determine whether the intersecting passage 5 has entered the blind spot 7 when viewed from the host vehicle 1, and only when it is determined that the intersecting passage 5 has entered the blind spot 7, predict whether there is a possibility that the moving object will enter the first driving lane 2 from the intersecting passage 5. In addition, the blind spot 7 here refers to a situation where it is a blind spot when viewed from the driver of the host vehicle 1, or refers to a blind spot of the object sensor 11 that detects objects around the host vehicle 1.

[0082] The entry prediction unit 44 includes a road width determination unit 50 , a leading vehicle determination unit 51 , a stop time determination unit 52 , and a possibility estimation unit 53 .

[0083] The road width determination unit 50 determines the road width W of the cross passage 5 (see Figure 2) is less than a predetermined value. The road width determination unit 50 may acquire information on the road width W from the map acquisition unit 32. The predetermined value is set to, for example, a width at which two vehicles can pass each other without difficulty.

[0084] When the road width W of the intersection passage 5 is smaller than a predetermined value, the possibility estimation unit 53 estimates that the possibility that the moving object enters the first driving lane 2 from the intersection passage 5 is high.

[0085] When the road width W of the intersection 5 is smaller than the above-mentioned predetermined value, the driver of the other vehicle 4a that passes the vehicle 8a bears psychological and technical burdens. Therefore, it is considered that the driver of the other vehicle 4a will choose to let the vehicle 8a enter the intersection 5 first rather than passing the vehicle 8a in the intersection 5, because the possibility of the other vehicle 4a giving way to the vehicle 8a increases.

[0086] The preceding vehicle determination unit 51 determines a predetermined distance range R2 (see Figure 2 ) whether there are other vehicles in the range R2. Figure 2 As shown, it may be a range far in front of the host vehicle 1 , or it may be a range from a point far in front of the host vehicle 1 by a predetermined distance to the position of the host vehicle 1 .

[0087] When it is determined that there is no other vehicle within a range R2 of a predetermined distance in front of the host vehicle 1 , the possibility estimation unit 53 estimates that there is a high possibility that the moving object will enter the first driving lane 2 from the intersection passage 5 .

[0088] This is because: when there is a vehicle in front of the vehicle 1 on the first driving lane 2, the possibility of the moving object entering from the intersection 5 is also reduced. Conversely, when there is no vehicle in front of the vehicle 1, the moving object can easily enter the first driving lane 2 from the intersection 5.

[0089] The parking time determination unit 52 determines the parking time of the other vehicle 4a as the time elapsed from the time when the other vehicle 4a stopped or the time when the other vehicle 4a was observed to be parking. The parking time determination unit 52 determines whether the parking time of the other vehicle 4a is longer than a predetermined time.

[0090] When it is determined that the parking time of the other vehicle 4a is longer than the predetermined time, the possibility estimation unit 53 predicts that the possibility of the moving body entering the first driving lane from the intersection is low. This is because: when the parking time is long, it is considered that the other vehicle 4a is stopped for reasons other than the moving body intending to enter from the intersection 5.

[0091] As described above, the possibility estimation unit 53 estimates the level of possibility that the moving object will enter the first driving lane from the intersecting passage based on the determination results of the road width determination unit 50 , the front vehicle determination unit 51 , and the stop time determination unit 52 .

[0092] For example, the possibility estimation unit 53 may estimate the possibility Pa of the moving object entering the first driving lane from the intersecting passage based on the following equation (1).

[0093] Pa=Pr+Aw×Xw+Af×Xf-As×Xs…(1)

[0094] Here, Pr is a basic probability (constant), Aw, Af, and As are positive coefficients, and Xw, Xf, and Xs are variables representing the determination results of the road width determination unit 50 , the preceding vehicle determination unit 51 , and the stop time determination unit 52 .

[0095] For example, the value of Xw is "1" when the road width W of the intersection passage 5 is less than a predetermined value, and is "0" when the road width W of the intersection passage 5 is greater than the predetermined value. The value of Xf is "1" when there is no other vehicle within a range R2 of a predetermined distance in front of the host vehicle 1, and is "0" when there is another vehicle within the range R2. The value of Xs is "1" when the parking time of the other vehicle 4a is greater than a predetermined time, and is "0" when the parking time of the other vehicle 4a is less than the predetermined time.

[0096] The vehicle path generation unit 37 generates a smooth target driving trajectory and speed curve based on the prediction results of the movements of other objects around the vehicle 1 predicted in the behavior prediction unit 36, so that the vehicle 1 can drive in accordance with traffic regulations (for example, driving along the first driving lane 2, etc.) without colliding with other objects and can drive without sudden deceleration or sudden turning according to the behavior of other objects.

[0097] In addition, when the entry prediction unit 44 predicts that there is a possibility that another moving object may enter the first driving lane 2 from the intersection passage 5, the vehicle path generation unit 37 generates a speed curve that preliminarily decelerates or stops the vehicle 1 and moves the position of the vehicle 1 away from the oncoming lane.

[0098] In addition, for example, when the possibility Pa of other moving objects entering the first driving lane 2 from the intersection passage 5 is greater than a threshold, the vehicle path generation unit 37 generates a speed curve that preliminarily decelerates or stops the vehicle 1 and generates a target driving trajectory that moves the lateral position of the vehicle 1 away from the second driving lane 3.

[0099] The vehicle control unit 38 drives the deceleration mechanism 17 , the acceleration device, and the steering device based on the target travel trajectory and the speed curve obtained by the vehicle path generation unit 37 , thereby performing travel control of the vehicle 1 .

[0100] Thus, when the entry prediction unit 44 predicts that another moving object may enter the first driving lane 2 from the intersection 5 (or when the possibility Pa is greater than the threshold), the vehicle control unit 38 can operate the deceleration mechanism 17 to decelerate the host vehicle 1.

[0101] The driving control by the vehicle control unit 38 does not necessarily require a target driving trajectory or a speed profile. For example, braking control, acceleration control, and steering control may be performed based on the relative distance to an object (eg, an obstacle) around the host vehicle 1 .

[0102] Alternatively, when the entry prediction unit 44 predicts that there is a possibility that another moving object may enter the first driving lane 2 from the intersection 5 (or when the possibility Pa is above a threshold), the behavior prediction unit 36 ​​may activate the notification device 16 to notify the occupants of the vehicle 1 of an alarm.

[0103] In this case, the notification device 16 may output, for example, a voice message or a visual message for notifying that there is a possibility that another moving object may enter the first driving lane 2 from the intersection 5 .

[0104] (action)

[0105] Next, refer to Figure 4 An example of the operation of the driving assistance device 10 in the embodiment will be described.

[0106] In step S1 , the object detection unit 30 detects the position, posture, size, speed, etc. of an object around the host vehicle 1 using a plurality of object detection sensors.

[0107] In step S2 , the detection integration unit 33 integrates the detection results obtained from the multiple object detection sensors and outputs a detection result for each object. The object tracking unit 34 tracks the detected and integrated objects to predict the position and behavior of the objects around the vehicle 1 relative to the vehicle 1 .

[0108] In step S3 , the host vehicle position estimation unit 31 measures the position, posture, and speed of the host vehicle 1 relative to a predetermined reference point based on the odometer using the measurement result of the positioning device 13 and the detection result from the vehicle sensor 12 .

[0109] In step S4 , the map acquisition unit 32 acquires map information indicating the structure of the road on which the host vehicle 1 travels.

[0110] In step S5 , the on-map position calculation unit 35 estimates the position and posture of the host vehicle 1 on the map based on the position of the host vehicle 1 measured in step S3 and the map data acquired in step S4 .

[0111] In step S6 , the behavior prediction unit 36 ​​predicts the positions and actions of other vehicles around the host vehicle 1 on the map based on the detection result (behavior of objects around the host vehicle 1 ) obtained in step S2 and the position of the host vehicle 1 determined in step S5 .

[0112] In addition, the behavior prediction unit 36 ​​predicts whether there is a possibility that the moving object will enter the first driving lane 2 from the intersection 5. Figure 5 and Figure 6 A moving body behavior prediction routine for predicting the possibility that the moving body enters the first driving lane 2 from the intersection passage 5 will be described later.

[0113] In step S7 , the host vehicle path generation unit 37 generates a target travel track and a speed curve of the host vehicle 1 based on the behavior of the other vehicles predicted in step S6 .

[0114] When it is predicted that there is a possibility that other moving objects may enter the first driving lane 2 from the intersection passage 5 (or when the possibility Pa is above a threshold), the vehicle path generation unit 37 generates a speed curve that preliminarily decelerates or stops the vehicle 1 and generates a target driving trajectory that moves the position of the vehicle 1 away from the oncoming lane.

[0115] In step S8 , the vehicle control unit 38 controls the host vehicle 1 so that the host vehicle 1 travels according to the target travel track and speed profile generated in step S7 .

[0116] Reference Figure 5 To illustrate Figure 4 Mobile behavior prediction routine.

[0117] In step S10, the lane determination unit 40 determines the positions of other vehicles 4a around the vehicle 1 on the map based on the detection results obtained by the detection integration unit 33 and the object tracking unit 34 and the position of the vehicle 1 determined by the position calculation unit 35 within the map, and determines which lane the other vehicle 4a belongs to within the map.

[0118] In step S11, the oncoming vehicle determination unit 41 determines whether the other vehicle 4a around the host vehicle 1 is an oncoming vehicle in the second driving lane 3. If the other vehicle 4a is an oncoming vehicle (S11: "Yes"), the process proceeds to step S12. If the other vehicle 4a is not an oncoming vehicle (S11: "No"), the process proceeds to step S15.

[0119] In step S12, the stop determination unit 42 determines whether the other vehicle 4a is in a stopped state or a decelerated state. If the other vehicle 4a is in a stopped state or a decelerated state (S12: "Yes"), the process proceeds to step S13. If the other vehicle 4a is not in a stopped state or a decelerated state (S12: "No"), the process proceeds to step S15.

[0120] In step S13, the intersecting passage detection unit 43 detects the intersecting passage 5 intersecting with the second driving lane 3 in front of the host vehicle 1. The intersecting passage detection unit 43 detects whether the position of the other vehicle 4a is located within the prescribed range R1 on the front side relative to the intersection position 6 where the intersecting passage 5 intersects with the second driving lane 3. When the position of the other vehicle 4a is located within the prescribed range R1 (S13: "Yes"), the process proceeds to step S14. When the position of the other vehicle 4a is not located within the prescribed range R1 (S13: "No"), the process proceeds to step S15.

[0121] In step S14, the entry prediction unit 44 predicts that there is a possibility that the moving object will enter the first driving lane 2 from the intersection 5. Figure 6 The moving body entry prediction routine performed by the entry prediction unit 44 will be described later.

[0122] In step S15, the behavior prediction unit 36 ​​determines whether the processing of steps S10 to S14 has been performed on all other vehicles around the host vehicle 1. If steps S10 to S14 have been performed on all other vehicles (S15: "Yes"), the moving body behavior prediction routine is terminated and the processing enters step S20. Figure 4 If steps S10 to S14 have not been performed on any other vehicle (S15: No), the other vehicle that has not been processed is selected as a processing target during the processing and the processing returns to step S10.

[0123] Reference Figure 6 To illustrate Figure 5 The moving body enters the prediction routine.

[0124] In step S20, the road width determination unit 50 determines the road width W of the intersecting passage 5 (see Figure 2 ) is less than the specified value.

[0125] In step S21, the front vehicle determination unit 51 determines a predetermined distance range R2 (see Figure 2 ) to see if there are other vehicles in the area.

[0126] In step S22 , the parking time determination unit 52 determines whether the parking time of the other vehicle 4 a is longer than a predetermined time.

[0127] When the road width W of the intersection passage 5 is smaller than the predetermined value in step S23 , the possibility estimation unit 53 estimates that the possibility that the moving object enters the first driving lane 2 from the intersection passage 5 is high.

[0128] Furthermore, when it is determined that there is no other vehicle within a range R2 of a predetermined distance in front of the host vehicle 1 , the possibility estimation unit 53 estimates that there is a high possibility that the moving object will enter the first driving lane 2 from the intersection 5 .

[0129] Furthermore, when it is determined that the stop time of the other vehicle 4 a is longer than the predetermined time, the possibility estimation unit 53 predicts that the possibility of the moving body entering the first driving lane from the intersection passage is low.

[0130] After processing returns Figure 5 Step S15.

[0131] (Effects of the First Embodiment)

[0132] (1) The on-map position calculation unit 35 determines the position of the host vehicle 1. The lane determination unit 40 and the oncoming vehicle determination unit 41 determine the position of another vehicle 4a in the second driving lane 3 which is the oncoming lane of the first driving lane 2 in which the host vehicle 1 is traveling. The intersecting passage detection unit 43 detects an intersecting passage 5 that intersects the second driving lane 3 in front of the host vehicle 1.

[0133] The intersecting passage detecting unit 43 determines whether the other vehicle 4a is located within a predetermined range R1, which is a range from the intersection position 6 of the intersecting passage 5 and the second driving lane 3 to a point that is away from the intersection position 6 by a predetermined distance in a direction opposite to the advancing direction of the vehicle in the second driving lane 3. The stopping determining unit 42 determines whether the other vehicle 4a is in any state of a stopped state or a decelerated state.

[0134] When the other vehicle 4 a is within the predetermined range R1 and the other vehicle 4 a is in either a stopped state or a decelerated state, the entry prediction unit 44 predicts that there is a possibility that the moving object may enter the first driving lane 2 from the intersection 5 .

[0135] In this way, by predicting the possibility that a moving object may enter the first driving lane 2 from the intersection 5, evasive action can be taken in advance, thereby avoiding the situation where the moving object entering the first driving lane 2 from the intersection 5 is too close to the vehicle 1 and the moving object and the vehicle 1 suddenly decelerate.

[0136] In addition, when other vehicles 4a are not in a stopped state or decelerated state within a predetermined range R1 on the front side relative to the intersection position 6, it is possible to predict that there are no other moving objects entering from the intersection passage 5, so the prediction accuracy of the possibility of other moving objects entering the driving lane in which the host vehicle is traveling can be improved. As a result, since unnecessary deceleration and stopping can be reduced, for example, a target driving trajectory and speed curve with high fuel consumption efficiency can be generated in automatic driving control.

[0137] (2) When determining that the intersection 5 has entered the blind spot 7 when viewed from the host vehicle, the entry prediction unit 44 predicts whether there is a possibility that the moving object will enter the first driving lane 2 from the intersection 5 .

[0138] Thus, even if the intersection 5 enters the blind spot 7 , it is possible to predict whether there is a possibility that a moving object will enter the first driving lane 2 from the intersection 5 based on the behavior of the other vehicle 4 a .

[0139] (3) When determining that the intersection 5 is a crosswalk, the entry prediction unit 44 predicts that there is a possibility that the moving object will enter the first driving lane 2 from the intersection 5 .

[0140] When the intersection 5 is a pedestrian crossing and the moving object is a pedestrian or a two-wheeled vehicle, the other vehicle 4a gives way to the pedestrian or the two-wheeled vehicle, and sometimes the pedestrian or the two-wheeled vehicle crosses the first driving lane 2 in a somewhat urgent manner. By predicting the possibility of the pedestrian or the two-wheeled vehicle entering the first driving lane 2 in advance, it is possible to avoid the situation where the host vehicle 1 is too close to the pedestrian or the two-wheeled vehicle and the host vehicle 1 or the two-wheeled vehicle decelerates suddenly.

[0141] (4) When determining that the intersection 5 is a branch road or a private land exit, the entry prediction unit 44 predicts that there is a possibility that the vehicle 8 a as a moving object may enter the first driving lane 2 from the intersection 5 .

[0142] When the cross passage 5 is a fork or a private land exit and the moving body is the vehicle 8a, other vehicles 4a may give way to the vehicle 8a, and the vehicle 8a may enter the first driving lane 2 somewhat hastily. By predicting the possibility of the vehicle 8a entering the first driving lane 2 in advance, it is possible to avoid the situation where the host vehicle 1 and the vehicle 8a are too close to each other and the host vehicle 1 and the vehicle 8a decelerate suddenly.

[0143] (5) When the width W of the intersection passage 5 is smaller than a predetermined value, the possibility estimation unit 53 predicts that the possibility of the moving object entering the first driving lane 2 from the intersection passage 5 is high.

[0144] When the width W of the intersection 5 is less than a predetermined value, the possibility that other vehicles 4a will give way to the moving object to avoid passing the moving object on the intersection 5 increases. Therefore, it is possible to more accurately predict that the moving object is likely to enter the first driving lane 2, thereby avoiding the situation where the host vehicle 1 and the moving object are too close and the host vehicle and the moving object decelerate suddenly.

[0145] (6) When determining that there is no other vehicle within the predetermined distance range R2 ahead of the host vehicle 1 in the first travel lane 2 , the possibility estimation unit 53 predicts that the possibility of the moving object entering the first travel lane 2 from the intersection 5 is high.

[0146] This is because: when there is no vehicle and space is left ahead of the first driving lane 2, the moving object can easily enter the first driving lane 2, so the possibility of other vehicles 4a giving way to the moving object increases. Therefore, it is possible to more accurately predict that the moving object is likely to enter the first driving lane 2, thereby avoiding the situation where the host vehicle 1 and the moving object are too close and the host vehicle and the moving object decelerate suddenly.

[0147] (7) When it is determined that the stop time of the other vehicle 4 a is longer than the predetermined time, the possibility estimation unit 53 predicts that the possibility of the moving object entering the first driving lane 2 from the intersection 5 is low.

[0148] When the parking time is long, it is considered that the other vehicle 4a stops for reasons other than the moving body intending to enter from the intersection 5. In this case, it is predicted that the possibility of the moving body entering the first driving lane 2 from the intersection 5 is low, thereby improving the prediction accuracy of the possibility of the other moving body entering the driving lane in which the host vehicle is traveling. As a result, unnecessary deceleration, parking, etc. can be reduced.

[0149] (Second Embodiment)

[0150] Figure 7 The other vehicle 4a is shown to be in a stopped state or decelerated state within a predetermined range R1 on the front side relative to the intersection position 6, and the direction indicator for indicating the intention to turn to the intersection 5 is lit. In this case, it is considered that the other vehicle 4a that intends to move toward the intersection 5 is stopped or decelerated on the front side of the intersection 5, which means that there is an object on the intersection 5 that blocks the entry, or there is a possibility that the vehicle is giving way to another moving body entering from the intersection 5.

[0151] Therefore, when the other vehicle 4a is in a stopped state or a decelerated state within a specified range R1 on the front side relative to the intersection position 6, and the direction indicator for indicating the intention to turn toward the intersection 5 is lit (that is, the direction indicator of the other vehicle 4a indicates the intention to proceed toward the intersection), the behavior prediction unit 36 ​​predicts that there is a possibility that another moving object will enter the first driving lane 2 from the intersection 5.

[0152] Reference Figure 8 The controller 18 of the second embodiment has the same functional configuration as that of the controller 18 of the first embodiment, and the same components are denoted by the same reference numerals.

[0153] The behavior prediction unit 36 ​​includes a flashing light detection unit 45 .

[0154] The flashing light detection unit 45 detects the lighting of the direction indicator of the other vehicle 4a on the second driving lane 3, which indicates the intention to turn to the cross passage 5. In addition, for example, the object sensor 11 includes a camera that captures the surroundings of the vehicle, and the flashing light detection unit 45 can detect the lighting of the direction indicator by detecting the presence of a yellow flashing (flashing of the direction indicator) area on the image captured by the camera. Alternatively, the lighting of the direction indicator can be detected by receiving a signal indicating the lighting of the direction indicator from the other vehicle 4a through inter-vehicle communication or the like. The method of detecting the lighting of the direction indicator of the other vehicle 4a is not particularly limited.

[0155] When another vehicle 4a is in a stopped state or a decelerated state within a specified range R1 on the front side relative to the intersection position 6 and has turned on the direction indicator to indicate the intention to turn to the intersection 5, the entry prediction unit 44 predicts that there is a possibility that another moving body will enter the first driving lane 2 from the intersection 5.

[0156] For example, when another vehicle 4a is in a stopped state or a decelerated state within a specified range R1 on the front side relative to the intersection position 6, and the direction indicator for indicating the intention to turn to the intersection 5 is lit, it is considered that the other vehicle 4a that wants to enter the intersection 5 is in a stopped state or a decelerated state on the front side of the intersection 5, and the other vehicle 4a is giving way to the vehicle 8a entering from the intersection 5.

[0157] For example, when another vehicle 4a stops at the entrance of the intersection 5 while changing its posture by turning nearly 90 degrees, it is considered that there is a high possibility that a pedestrian is crossing the intersection 5 or that the intersection 5 is congested and cannot enter. However, when another vehicle 4a stops at the entrance of the intersection 5 while leaving the entrance of the intersection 5 without turning, it is considered that there is a possibility that the vehicle 8a wants to enter from the intersection 5 and is giving way to the vehicle.

[0158] In this situation, the vehicle 8a that has been given up the way may enter the cross passage 5 quickly to allow the other vehicle 4a to start again, and the vehicle 8a may enter the cross passage 5 suddenly. In this way, when the vehicle 8a suddenly appears in the driving lane 2 of the host vehicle 1, there is a possibility that the host vehicle 1 and the vehicle 8a are closer than expected. In this case, the host vehicle 1 and the vehicle 8a need to decelerate suddenly.

[0159] By predicting such a scenario in advance using the entry prediction unit 44 , the vehicle can be decelerated and driven slowly on the front side of the intersection 5 , thereby avoiding sudden deceleration.

[0160] On the other hand, when the other vehicle 4 a has not turned on the direction indicator indicating the intention to turn onto the intersection 5 , the entry prediction unit 44 predicts that there is no possibility that the other moving body will enter the first driving lane 2 from the intersection 5 .

[0161] As a result, it is possible to predict that there is no other moving object entering from the intersection 5 , and thus it is possible to improve the accuracy of prediction of the possibility that another moving object will enter the lane in which the host vehicle is traveling.

[0162] Reference Fig. 9 The following describes the moving body behavior prediction routine of the second embodiment. The processing of step S30 and step S31 is similar to Figure 5 The processing of steps S10 and S11 is the same.

[0163] In step S32, the stop determination unit 42 determines whether the other vehicle 4a is in a stopped state or a decelerated state. If the other vehicle 4a is in a stopped state or a decelerated state (S32: "Yes"), the process proceeds to step S33. If the other vehicle 4a is not in a stopped state or a decelerated state (S32: "No"), the process proceeds to step S36.

[0164] In step S33, the flashing light detection unit 45 determines whether the other vehicle 4a on the second driving lane 3 has turned on the direction indicator for indicating the intention to turn to the intersection 5. If the other vehicle 4a has turned on the direction indicator for indicating the intention to turn to the intersection 5 (step S33: "Yes"), the process proceeds to step S34. If the other vehicle 4a has not turned on the direction indicator for indicating the intention to turn to the intersection 5 (step S33: "No"), the process proceeds to step S36.

[0165] The processing of steps S34 to S36 is Figure 5 The processing of steps S13 to S15 is the same.

[0166] (Effects of the Second Embodiment)

[0167] When detecting that the direction indicator of the other vehicle 4 a indicates an intention to proceed toward the intersection 5 , the entry prediction unit 44 predicts that there is a possibility that the moving body will enter the first driving lane 2 from the intersection 5 .

[0168] In this way, by predicting the possibility that a moving object may enter the first driving lane 2 from the intersection 5, evasive action can be performed in advance, thereby avoiding the situation where the moving object entering the first driving lane 2 from the intersection 5 is too close to the vehicle 1 and the moving object and the vehicle 1 suddenly decelerate.

[0169] In addition, since it is possible to predict that there is no other moving object entering from the intersection 5 when the other vehicle 4a does not light up the direction indicator for indicating the intention to turn to the intersection 5, the prediction accuracy of the possibility of other moving objects entering the driving lane in which the host vehicle is traveling can be improved. As a result, since unnecessary deceleration and stopping can be reduced, for example, a target driving trajectory and speed curve with high fuel consumption efficiency can be generated in automatic driving control.

[0170] (Third Embodiment)

[0171] Fig.10 The other vehicle 4a is shown to be in a stopped state or decelerated state within a predetermined range R1 on the front side relative to the intersection position 6, and is flashing or double flashing its headlights (passing). Such behavior is an expression of the other vehicle 4a's intention to give way to other moving bodies. For example, if the intersection 5 is a fork or a private land exit, it is considered that the vehicle 8a as a moving body intends to enter the first driving lane 2 or the second driving lane 3 after exiting the intersection 5.

[0172] In addition, for example Fig.11As shown, when the intersection 5 is a crosswalk 60 crossing the first driving lane 2 and the second driving lane 3 , it is assumed that a pedestrian or a two-wheeled vehicle (hereinafter referred to as “pedestrians etc.”) as a moving object intends to cross the crosswalk 60 .

[0173] Therefore, when the behavior prediction unit 36 ​​detects that another vehicle 4a is in a parked state or a decelerated state within a specified range R1 on the front side relative to the intersection position 6, and that the other vehicle 4a is flashing its headlights (or performing double flashes), it predicts that there is a possibility that another moving object will enter the first driving lane 2 from the intersection passage 5.

[0174] Reference Fig.12 The controller 18 of the third embodiment has the same functional configuration as that of the controller 18 of the first embodiment, and the same components are denoted by the same reference numerals.

[0175] The behavior prediction unit 36 ​​includes a headlight detection unit 46 .

[0176] The headlight detection unit 46 detects the flashing or double flashing of the headlights of other vehicles 4a. In addition, for example, the object sensor 11 includes a camera that captures the surroundings of the vehicle, and the headlight detection unit 46 can detect the flashing or double flashing of the headlights by detecting an area with a large brightness change (on and off of the headlights) in the image captured by the camera. Alternatively, the flashing or double flashing of the headlights can be detected by receiving a signal indicating the flashing or double flashing of the headlights from other vehicles 4a through inter-vehicle communication or the like. The method of detecting the flashing or double flashing of the headlights of other vehicles 4a is not particularly limited.

[0177] When the other vehicle 4a is stopped or decelerated within a predetermined range R1 ahead of the intersection position 6 and is flashing or hazard-proofing its headlights, the entry prediction unit 44 predicts that another moving object may enter the first driving lane 2 from the intersection passage 5 .

[0178] For example, when another vehicle 4a is stopped or decelerated within a specified range R1 in front of the intersection position 6 and has its headlights flashing or hazard lights on, it is considered that the vehicle 8a as described above wants to enter the first driving lane 2, or that pedestrians want to cross the crosswalk 60.

[0179] In this situation, the vehicle 8a or pedestrian that has been given up the way may want to quickly make the other vehicle 4a start again, and the vehicle 8a or pedestrian may suddenly enter or cross the crosswalk 60 from the intersection 5. In this way, when the vehicle 8a or pedestrian suddenly appears in the driving lane 2 of the host vehicle 1, there is a possibility that the vehicle 8a or pedestrian is closer to the host vehicle 1 than expected. In this case, the host vehicle 1, the vehicle 8a, and the two-wheeled vehicle need to decelerate suddenly.

[0180] By predicting such a situation in advance using the entry prediction unit 44 , the vehicle can be decelerated and driven slowly on the front side of the intersection 5 , thereby avoiding sudden deceleration.

[0181] On the other hand, when the other vehicle 4 a does not flash or hazard lights, the entry prediction unit 44 predicts that there is no possibility that the other moving object will enter the first driving lane 2 from the intersection 5 .

[0182] As a result, it is possible to predict that there is no other moving object entering from the intersection 5 , and thus it is possible to improve the accuracy of prediction of the possibility that another moving object will enter the lane in which the host vehicle is traveling.

[0183] Reference Fig.13 The moving body behavior prediction routine of the third embodiment is described below. Figure 5 The processing of steps S10 and S11 is the same.

[0184] In step S42, the stop determination unit 42 determines whether the other vehicle 4a is in a stopped state or a decelerated state. If the other vehicle 4a is in a stopped state or a decelerated state (S42: "Yes"), the process proceeds to step S43. If the other vehicle 4a is not in a stopped state or a decelerated state (S42: "No"), the process proceeds to step S46.

[0185] In step S43, the headlight detection unit 46 determines whether the other vehicle 4a in the second driving lane 3 is flashing or strobing the headlights. If the other vehicle 4a is flashing or strobing the headlights (step S43: Yes), the process proceeds to step S44. If the other vehicle 4a is not flashing or strobing the headlights (step S43: No), the process proceeds to step S46.

[0186] The processing of steps S44 to S46 is Figure 5 The processing of steps S13 to S15 is the same.

[0187] (Effects of the Third Embodiment)

[0188] When the other vehicle 4 a is detected to be flashing or hazard-hiding its headlights, the entry prediction unit 44 predicts that there is a possibility that the moving object will enter the first driving lane 2 from the intersection 5 .

[0189] In this way, by predicting the possibility that a moving object may enter the first driving lane 2 from the intersection 5, evasive action can be performed in advance, thereby avoiding the situation where the moving object entering the first driving lane 2 from the intersection 5 is too close to the vehicle 1 and the moving object and the vehicle 1 suddenly decelerate.

[0190] In addition, since it is possible to predict that there is no other moving object entering from the cross passage 5 when the other vehicle 4a does not flash or hazard lights, the prediction accuracy of the possibility of other moving objects entering the driving lane of the host vehicle can be improved. As a result, since unnecessary deceleration and stopping can be reduced, for example, a target driving trajectory and speed curve with high fuel consumption efficiency can be generated in automatic driving control.

[0191] The purpose of all examples and conditional terms recorded herein is to educate, so as to help readers understand the present invention and the concepts given by the inventor for the development of technology, and should be interpreted as not limited to the above examples and conditions specifically recorded and the structures of the examples related to the superiority and inferiority of the present invention in this specification. Although the embodiments of the present invention are described in detail, it should be understood that various changes, substitutions and modifications can be applied thereto without departing from the spirit and scope of the present invention.

[0192] Description of Reference Numerals

[0193] 1: This vehicle; 10: Driving assistance device; 11: Object sensor; 12: Vehicle sensor; 13: Positioning device; 14: Map database; 15: Communication device; 16: Notification device; 17: Speed ​​reduction mechanism; 18: Controller; 20: Processor; 21: Storage device; 30: Object detection unit; 31: This vehicle position estimation unit; 32: Map acquisition unit; 33: Detection integration unit; 34: Object tracking unit; 35: In-map position calculation unit; 36: Behavior prediction unit; 37: This vehicle path generation unit; 38: Vehicle control unit; 40: Lane determination unit; 41: Oncoming vehicle determination unit; 42: Stop determination unit; 43: Cross-passage detection unit; 44: Entry prediction unit; 45: Flashing light detection unit; 46: Headlight detection unit; 50: Road width determination unit; 51: Front vehicle determination unit; 52: Stop time determination unit; 53: Possibility estimation unit.

Claims

1. A method for predicting the behavior of a mobile object, characterized in that: Determine the position of the vehicle; determining the position of another vehicle in a second driving lane which is an oncoming lane of the first driving lane in which the host vehicle is traveling; detecting an intersecting passage that intersects the second driving lane in front of the host vehicle and has an exit, the exit facing the second driving lane, and a moving object entering the intersecting passage from the exit of the intersecting passage from outside the second driving lane; The intersection position of the intersection passage and the second driving lane is set as a position that becomes a reference, and the reference is used to determine whether the body of the other vehicle obstructs the forward path of the moving body that wants to enter the second driving lane from the intersection passage, and whether the other vehicle is located within a prescribed range and the other vehicle is in any one of a stopped state and a decelerated state, wherein the prescribed range is a range from the intersection position to a point that is away from the intersection position by a prescribed distance in a direction opposite to the forward direction of the vehicle on the second driving lane; as well as When the other vehicle is within the specified range and is in any of a parking state and a decelerating state, and the intersection has entered a blind spot of the vehicle, it is predicted that there is a possibility that the moving object will enter from the exit of the intersection and enter the first driving lane.

2. The behavior prediction method according to claim 1, characterized in that: When it is detected that the direction indicator of the other vehicle indicates an intention to proceed toward the intersecting passage, it is predicted that there is a possibility that the moving object will enter the first driving lane from the intersecting passage.

3. The behavior prediction method according to claim 1, characterized in that: When the flashing of the headlights of the other vehicle is detected, it is predicted that there is a possibility that the moving object will enter the first driving lane from the intersecting passage.

4. The behavior prediction method according to claim 1, characterized in that: When it is determined that the intersecting passage is a branch road or a private land exit, it is predicted that there is a possibility that the vehicle as the moving object will enter the first driving lane from the intersecting passage.

5. The behavior prediction method according to claim 1, characterized in that: When the width of the intersection passage is smaller than a predetermined value, it is predicted that the possibility that the moving object will enter the first driving lane from the intersection passage is high.

6. The behavior prediction method according to claim 1, characterized in that: When it is determined that there is no other vehicle within a predetermined distance ahead of the host vehicle in the first driving lane, it is predicted that there is a high possibility that the moving object will enter the first driving lane from the intersection.

7. The behavior prediction method according to claim 1, characterized in that: When it is determined that the stop time of the other vehicle is equal to or longer than a predetermined time, it is predicted that the possibility that the moving object will enter the first driving lane from the intersection is low.

8. A mobile behavior prediction device, characterized in that: A controller is provided to perform the following processing, wherein: Determine the position of the vehicle; determining the position of another vehicle in a second driving lane which is an oncoming lane of the first driving lane in which the host vehicle is traveling; detecting an intersecting passage that intersects the second driving lane in front of the host vehicle and has an exit, the exit facing the second driving lane, and a moving object entering the intersecting passage from the exit of the intersecting passage from outside the second driving lane; The intersection position of the intersection passage and the second driving lane is set as a position that becomes a reference, and the reference is used to determine whether the body of the other vehicle obstructs the forward path of the moving body that wants to enter the second driving lane from the intersection passage, and whether the other vehicle is located within a prescribed range and the other vehicle is in any one of a stopped state and a decelerated state, wherein the prescribed range is a range from the intersection position to a point that is away from the intersection position by a prescribed distance in a direction opposite to the forward direction of the vehicle on the second driving lane; as well as When the other vehicle is within the specified range and is in any of a parking state and a decelerating state, and the intersection has entered a blind spot of the vehicle, it is predicted that there is a possibility that the moving object will enter from the exit of the intersection and enter the first driving lane.

9. A vehicle, characterized in that: have: The behavior prediction device according to claim 8; a deceleration mechanism for decelerating the vehicle; and a notification device for notifying an occupant of the vehicle of information, When the controller predicts that there is a possibility that the moving object will enter the first driving lane from the intersection, the controller activates the notification device to warn the occupant or activates the deceleration mechanism to decelerate the vehicle.

Images