Vehicle behavior prediction device

Abstract

The present disclosure relates to a vehicle behavior prediction device. A vehicle behavior prediction unit (10) predicts that a target vehicle (T2) enters a lane (L) in which a vehicle (V) is traveling from a road area (L1) adjacent to the lane (L) in which the vehicle (V) is traveling. The vehicle behavior prediction unit (10) includes: a target vehicle detection unit (11) for detecting the target vehicle (T2); a distance acquisition unit (12) for acquiring a front distance (C) as the distance between the target vehicle (T2) and a target vehicle (T1) located in front of the target vehicle (T2); a turning radius estimation unit (13) for estimating the turning radius of the target vehicle (T2); and an entry prediction unit (14) for predicting whether the target vehicle (T2) can avoid the target vehicle (T1) and enter the lane (L) based on the front distance and the turning radius.

Description

Technical Field

[0001] The present disclosure relates to a vehicle behavior prediction device. Background Art

[0002] For example, Patent Document 1 describes a device that predicts the start of parked vehicles around the host vehicle and controls the vehicle based on the prediction results. This device predicts the start of parked vehicles based on factors such as the presence of a driver in the parked vehicle, the lighting status of the brake lights, the lighting status of the hazard lights, and the lighting status of the turn signals.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2021-009440

[0006] For example, a target vehicle may attempt to exit a row of parallel-parked vehicles. In this case, depending on the size of the space between the target vehicle and the vehicle in front of it, the target vehicle may exit the row directly or be unable to exit the row without turning back. Therefore, even if one attempts to predict the entry or exit of a target vehicle based solely on the direction indicators, as described in Patent Document 1, accurate prediction may be impossible depending on the space in front of the target vehicle. Summary of the Invention

[0007] Therefore, the present disclosure describes a vehicle behavior prediction device that can accurately predict the entry of a target vehicle from a road area adjacent to a lane in which the vehicle is traveling into the vehicle's own lane.

[0008] One embodiment of the present disclosure is a vehicle behavior prediction device that predicts the entry of a target vehicle into a lane in which the target vehicle is traveling from a road area adjacent to the target vehicle's lane, the target vehicle comprising: a target vehicle detection unit that detects the target vehicle present in the road area; a distance acquisition unit that acquires a front distance that is the distance between the target vehicle and an obstacle present in front of the target vehicle; a turning radius estimation unit that estimates the turning radius of the target vehicle; and an entry prediction unit that predicts whether the target vehicle can avoid the obstacle and enter the target lane based on the acquired front distance and the estimated turning radius.

[0009] This vehicle behavior prediction device uses the length of the clear space ahead of the target vehicle (front distance) and the target vehicle's turning radius to predict whether the target vehicle can avoid obstacles and enter its own lane. In other words, the vehicle behavior prediction device can predict whether the target vehicle can physically enter its own lane by turning. This allows the vehicle behavior prediction device to accurately predict the target vehicle's entry into its own lane from a road area adjacent to the vehicle's own lane.

[0010] In the above-mentioned vehicle behavior prediction device, the turning radius estimating unit may estimate the turning radius based on the steering angle of the target vehicle's tires. In this case, the entry prediction unit can more accurately predict the target vehicle's entry into the host lane based on the actual steering angle of the tires.

[0011] Alternatively, the vehicle behavior prediction device may further include a storage unit that stores turning radius information in which a minimum turning radius is associated with each vehicle type. The turning radius estimating unit may extract the minimum turning radius associated with the type of the target vehicle based on the turning radius information stored in the storage unit, and estimate the turning radius of the target vehicle based on the extracted minimum turning radius. In this case, the vehicle behavior prediction device can more accurately predict the target vehicle's entry into its own lane based on the type of the target vehicle.

[0012] In the aforementioned vehicle behavior prediction device, the entry prediction unit can also predict whether the target vehicle can enter the host lane based on the target vehicle's lateral position within the road area. For example, even if the distance ahead is the same, depending on the target vehicle's lateral position, the target vehicle may be able to enter the host lane, while other times, it may be blocked by an obstacle ahead. Therefore, by further using the target vehicle's lateral position for prediction, the entry prediction unit can more accurately predict the target vehicle's entry into the host lane.

[0013] In the aforementioned vehicle behavior prediction device, the entry prediction unit can also predict whether the target vehicle can enter the host lane based on the target vehicle's inclination relative to the direction in which the host lane extends. For example, even if the distance ahead remains the same, depending on the target vehicle's inclination, the target vehicle may be able to enter the host lane in some cases, while in other cases, it may be blocked by an obstacle ahead and unable to enter the host lane. Therefore, by further using the target vehicle's inclination in its prediction, the entry prediction unit can more accurately predict the target vehicle's entry into the host lane.

[0014] In the aforementioned vehicle behavior prediction device, the entry prediction unit may also predict the amount of protrusion of the target vehicle into the host lane if the target vehicle is unable to enter the host lane by avoiding an obstacle. In this manner, even if the target vehicle is unable to enter the host lane, the vehicle behavior prediction device can calculate the protrusion amount and use it for various control purposes.

[0015] Effects of the Invention

[0016] According to one aspect of the present disclosure, it is possible to accurately predict the entry of a target vehicle into a lane in which the host vehicle is traveling from a road area adjacent to the lane in which the host vehicle is traveling. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a block diagram showing an example of a driving assistance device according to an embodiment.

[0018] Figure 2 A diagram for explaining a scenario in which driving assistance is performed.

[0019] Figure 3 (a)~ Figure 3 (c) is a diagram for explaining whether or not a target vehicle enters the own lane.

[0020] Figure 4 (a) and Figure 4 (b) is a diagram for explaining whether or not a target vehicle enters the own lane.

[0021] Figure 5 This is the first half of the flowchart showing the flow of a process for driving assistance for the target vehicle entering the own lane, which is performed by the driving assistance ECU.

[0022] Figure 6 This is the second half of the flowchart showing the flow of the driving assistance processing for the target vehicle entering the own lane, which is performed by the driving assistance ECU.

[0023] Description of reference numerals:

[0024] 3: Storage unit, 10: Vehicle behavior prediction unit (vehicle behavior prediction device), 11: Target vehicle detection unit, 12: Distance acquisition unit, 13: Turning radius estimation unit, 14: Entry prediction unit, L: Current lane, L1: Road area, T, T1, T3: Target vehicle, T2: Target vehicle (obstacle), V: Current vehicle. DETAILED DESCRIPTION

[0025] Hereinafter, exemplary embodiments will be described with reference to the accompanying drawings. It should be noted that in each figure, the same or corresponding elements are denoted by the same reference numerals, and repeated descriptions are omitted.

[0026] like Figure 1 As shown, the driving assistance device 100 performs driving assistance for the host vehicle V. Figure 2 As shown, the driving assistance device 100 in this embodiment predicts that the target vehicle T enters the lane L from a road area L1 adjacent to the lane L in which the host vehicle V is traveling, and performs driving assistance for the host vehicle V based on the prediction result.

[0027] It should be noted that in Figure 2 In the illustrated example, target vehicles T, namely, target vehicles T1 to T3, are arranged in a line on a road area L1. The target vehicles T are located in the road area L1 adjacent to the lane L in which the host vehicle V is traveling. The road area L1 may be an adjacent lane adjacent to the host lane L or a parking space (a space for parallel parking adjacent to the driving lane).

[0028] The target vehicle T may be a vehicle parked in the road area L1 or a vehicle in a traffic jam traveling in the road area L1.

[0029] like Figure 1 As shown, the driving assistance device 100 includes an external sensor 1 , an actuator 2 , a storage unit 3 , and a driving assistance ECU (Electronic Control Unit) 4 .

[0030] The external sensor 1 is a detection device that detects the external environment of the host vehicle V. The external sensor 1 includes at least one of a camera and a radar sensor.

[0031] The camera is a device that captures images of the environment outside the vehicle V. The camera is located behind the front windshield of the vehicle V and captures images of the area in front of the vehicle. The camera transmits captured information about the environment outside the vehicle V to the driving support ECU 4. The camera can be either a monocular camera or a stereo camera.

[0032] A radar sensor is a detection device that uses radio waves (such as millimeter waves) or light to detect objects around the vehicle V. Radar sensors include, for example, millimeter wave radars or laser radars (LIDAR: Light Detection and Ranging). The radar sensor detects objects by transmitting radio waves or light to the periphery of the vehicle V and receiving the radio waves or light reflected by the objects. The radar sensor transmits object information related to the detected objects to the driving assistance ECU 4. In addition to other vehicles, objects also include fixed objects such as guardrails and poles installed on the road, billboards, etc.

[0033] The actuator 2 is a device for controlling the travel of the vehicle V. The actuator 2 includes at least a drive actuator, a brake actuator, and a steering actuator. The drive actuator controls the amount of air supplied to the engine (throttle opening) based on a control signal from the driving assistance ECU 4, thereby controlling the driving force of the vehicle V. It should be noted that, in the case where the vehicle V is a hybrid vehicle, in addition to the amount of air supplied to the engine, a control signal from the driving assistance ECU 4 is input to the motor serving as a power source to control the driving force. In the case where the vehicle V is an electric vehicle, a control signal from the driving assistance ECU 4 is input to the motor serving as a power source to control the driving force. The motor serving as a power source in these cases constitutes the actuator 2.

[0034] The brake actuator controls the braking system based on control signals from the driving assistance ECU 4, thereby controlling the braking force applied to the wheels of the host vehicle V. For example, a hydraulic brake system can be used as the braking system. The steering actuator controls the driving of the assist motor in the electric power steering system, which controls the steering torque, based on control signals from the driving assistance ECU 4. Thus, the steering actuator controls the steering torque of the host vehicle V.

[0035] The storage unit 3 stores turning radius information associated with the minimum turning radius for each vehicle type. Vehicle types can refer to sizes such as large, medium, and small vehicles, or types such as sedans, vans, and trucks. The minimum turning radius is predetermined for each vehicle type.

[0036] The driving assistance ECU 4 is an electronic control unit that includes a CPU (Central Processing Unit), ROM (Read Only Memory), and RAM (Random Access Memory). The driving assistance ECU 4 implements various functions by, for example, loading programs stored in the ROM into the RAM and executing them on the CPU. The driving assistance ECU 4 may also be composed of multiple electronic units.

[0037] The driving assistance ECU 4 functionally includes a vehicle behavior prediction unit (vehicle behavior prediction device) 10 and a driving assistance unit 20. The vehicle behavior prediction unit 10 performs processing to predict the entry of the target vehicle T into the host lane L. The driving assistance unit 20 performs driving assistance processing for the host vehicle V based on the prediction results of the vehicle behavior prediction unit 10.

[0038] More specifically, the vehicle behavior prediction unit 10 includes a target vehicle detection unit 11 , a distance acquisition unit 12 , a turning radius estimation unit 13 , and an entry prediction unit 14 .

[0039] The target vehicle detection unit 11 detects a target vehicle T present in the road area L1. The target vehicle detection unit 11 detects a vehicle present in the road area L1 as the target vehicle T using a well-known technique, for example, based on the detection results of the external sensor 1. Furthermore, the target vehicle detection unit 11 detects the lateral position of the target vehicle T in the road area L1 using a well-known technique based on the detection results of the external sensor 1. The lateral position of the target vehicle T in the road area L1 refers to a direction perpendicular to the direction along the extension direction of the road area L1 (in the direction perpendicular to the extension direction of the road area L1). Figure 2 The position of the target vehicle T is shown in the direction of arrow A).

[0040] Furthermore, the target vehicle detection unit 11 detects the inclination of the target vehicle T relative to the extending direction of the own lane L (the direction of the target vehicle T) using a well-known technique based on the detection result of the external sensor 1. Figure 2 In the example shown, when the target vehicle T2 is in the state shown by the solid line, the target vehicle T2 is not inclined with respect to the extending direction of the host lane L. For example, Figure 2 In the example shown, when the target vehicle T2 is in the state indicated by the dotted line, the target vehicle T2 is inclined by an angle θ with respect to the extending direction B of the host lane L. In this embodiment, the target vehicle detection unit 11 detects the lateral position and inclination of each of the target vehicles T1 to T3.

[0041] The distance acquisition unit 12 acquires the front distance, which is the distance between the target vehicle T and an obstacle located in front of the target vehicle T. Specifically, the distance acquisition unit 12 acquires the length of the clear space in front of the target vehicle T. Obstacles here include not only other vehicles located in front of the target vehicle T but also fixed objects such as guardrails and poles installed on the road, billboards, and the like. In this embodiment, the distance acquisition unit 12 acquires the front distance for each of the target vehicles T1 to T3.

[0042] exist Figure 2 In the example shown, the obstacle in front of target vehicle T2 is target vehicle T1. Therefore, distance acquisition unit 12 acquires, for example, the distance C between target vehicle T2 and target vehicle T1 as the distance in front of target vehicle T2. This distance in front can be, for example, the length along the direction of the host lane L (road area L1). It should be noted that distance acquisition unit 12 can acquire the distance in front using well-known techniques based on the detection results of external sensor 1.

[0043] The turning radius estimating unit 13 estimates the turning radius of the target vehicle T. The turning radius here refers to the radius of the driving trajectory for the target vehicle T, which is located in the road area L1, to enter the host lane L. The turning radius estimating unit 13 can estimate the turning radius of the target vehicle T based on the detection results of the external sensor 1. In this embodiment, the turning radius estimating unit 13 estimates the turning radius for each of the target vehicles T1 to T3.

[0044] Specifically, for example, the turning radius estimating unit 13 detects the steering angle of the tires of the target vehicle T based on the detection results of the external sensor 1. Here, the turning radius estimating unit 13 detects the steering angle of the front tire, which serves as the steering wheel, for example. For example, the turning radius estimating unit 13 detects the steering angle of the tire based on detection results of the tire's circular deformation or the inclination of the wheel surface. In this case, the turning radius estimating unit 13 can detect the steering angle of the tire based on, for example, images captured by a camera or detection results from a radar sensor, which serves as the external sensor 1.

[0045] Then, the turning radius estimating unit 13 estimates the turning radius of the target vehicle T based on the detected tire steering angle. Here, the larger the tire steering angle, the smaller the turning radius.

[0046] Furthermore, the turning radius estimating unit 13 can also estimate the turning radius based on the turning radius information stored in the storage unit 3. For example, when the steering angle of the tires of the target vehicle T cannot be detected based on the detection results of the external sensor 1, the turning radius estimating unit 13 can use the turning radius information to estimate the turning radius. Specifically, the turning radius estimating unit 13 identifies the type of the target vehicle T based on the detection results of the external sensor 1. The turning radius estimating unit 13 extracts the minimum turning radius corresponding to the type of the target vehicle T based on the turning radius information stored in the storage unit 3. The turning radius estimating unit 13 estimates the turning radius of the target vehicle T based on the extracted minimum turning radius. It should be noted that, for example, the turning radius estimating unit 13 can identify the type of the target vehicle T based on pattern matching, such as pattern matching based on camera images. Alternatively, for example, the turning radius estimating unit 13 can estimate the extracted minimum turning radius as the turning radius of the target vehicle T.

[0047] The entry prediction unit 14 predicts whether the target vehicle T can avoid the obstacle ahead (avoid the obstacle) and enter the host lane L (whether it is possible to enter). Here, the entry prediction unit 14 can predict whether the target vehicle T can enter the host lane L without interfering with the obstacle ahead when the target vehicle T enters the host lane L in the current state of the target vehicle T. Figure 2In the example shown, the obstacle ahead of target vehicle T2 is, for example, target vehicle T1 ahead of target vehicle T2. For example, the obstacle ahead of target vehicle T3 is target vehicle T2 ahead of target vehicle T3. For example, the obstacle ahead of target vehicle T1 may be another vehicle (not shown) or a fence, billboard, or pole installed in road area L1. Alternatively, there may be no obstacles within a predetermined distance ahead.

[0048] More specifically, the entry prediction unit 14 predicts whether the target vehicle T can avoid a forward obstacle and enter the host lane L based on the forward distance acquired by the distance acquisition unit 12 and the turning radius estimated by the turning radius estimation unit 13. Here, the entry prediction unit 14 estimates the driving trajectory of the target vehicle T based on the turning radius. Then, based on the forward distance to the forward obstacle, the entry prediction unit 14 predicts whether the target vehicle T can enter the host lane L without interfering with the obstacle while traveling along the estimated driving trajectory.

[0049] Furthermore, the entry prediction unit 14 predicts the amount of protrusion of the target vehicle T into the host lane L if the target vehicle T is unable to avoid a forward obstacle and enter the host lane L. Here, the entry prediction unit 14 predicts the amount of protrusion of the target vehicle T into the host lane L if the target vehicle T travels as far as possible until it interferes with the forward obstacle. This protrusion can be set to the widthwise length of the host lane L. For example, the left front end of the target vehicle T may interfere with a forward obstacle, making it impossible for the target vehicle T to avoid the obstacle, but the right front end of the target vehicle T may protrude into the host lane L. The entry prediction unit 14 predicts, for example, the amount of protrusion of the right front end of the target vehicle T into the host lane L in such a situation.

[0050] Specifically, for example, Figure 3 As shown in (a), if the distance C ahead of the target vehicle T2 is short, that is, if the space between the target vehicle T2 and the target vehicle T1 is narrow, the estimated driving trajectory K of the target vehicle T2 will interfere with the target vehicle T1. In this case, the entry prediction unit 14 predicts that the target vehicle T2 will not be able to separate from the vehicle column in the road area L1 and will not be able to enter the host lane L.

[0051] For example, Figure 3 As shown in (b), when the distance C ahead of the target vehicle T2 is long, that is, when the space between the target vehicle T2 and the target vehicle T1 is wide, the estimated driving trajectory K of the target vehicle T2 will not interfere with the target vehicle T1. In this case, the entry prediction unit 14 predicts that the target vehicle T2 can separate from the vehicle column in the road area L1 and enter the host lane L.

[0052] It should be noted that, for example, when the steering angle of the tires of the target vehicle T2 is small, the turning radius of the target vehicle T2 estimated based on the steering angle of the tires is large. Figure 3 If the distance C ahead is long, as shown in (c), the estimated driving trajectory K may interfere with the target vehicle T1. In this case, the entry prediction unit 14 predicts that the target vehicle T2 cannot separate from the vehicle column in the road area L1 and cannot enter the host lane L.

[0053] In this manner, the entry prediction unit 14 predicts the possibility of each target vehicle T entering the own lane L by using the front distance and the turning radius.

[0054] Furthermore, the entry prediction unit 14 can also predict whether the target vehicle T can enter the host lane L based on the lateral position of the target vehicle T within the road area L1. Specifically, the entry prediction unit 14 predicts whether the target vehicle T can enter the host lane L based on the forward distance C acquired by the distance acquisition unit 12, the turning radius estimated by the turning radius estimation unit 13, and the lateral position of the target vehicle T within the road area L1 detected by the target vehicle detection unit 11.

[0055] Specifically, for example, Figure 4 As shown in (a) of FIG. 2 , even when the distance C ahead of the target vehicle T2 is short, the target vehicle T2 may be able to separate from the vehicle column in the road area L1 without interfering with the target vehicle T1 within its driving trajectory K, depending on the lateral position of the target vehicle T2. Therefore, the entry prediction unit 14 considers the lateral position of the target vehicle T2 in addition to the distance C ahead and the turning radius to predict whether the target vehicle T2 can enter the host lane L.

[0056] Furthermore, the entry prediction unit 14 can also predict whether the target vehicle T can enter the host lane L based on the inclination of the target vehicle T with respect to the extending direction of the host lane L. That is, the entry prediction unit 14 predicts whether the target vehicle T can enter the host lane L based on the front distance C acquired by the distance acquisition unit 12, the turning radius estimated by the turning radius estimation unit 13, and the inclination of the target vehicle T detected by the target vehicle detection unit 11.

[0057] Specifically, for example, Figure 4As shown in (b), even when the distance C ahead of the target vehicle T2 is short, the target vehicle T2 may be able to separate from the vehicle column in the road area L1 without interfering with the target vehicle T1 through its driving trajectory K, depending on the inclination of the target vehicle T2. Therefore, the entry prediction unit 14 considers the inclination of the target vehicle T2 in addition to the distance C ahead and the turning radius to predict whether the target vehicle T2 can enter the host lane L.

[0058] Note that the entry prediction unit 14 can also predict whether the target vehicle T can enter the host lane L based on the front distance, the turning radius, the lateral position of the target vehicle T, and the inclination of the target vehicle T.

[0059] The driving assistance unit 20 provides driving assistance for the host vehicle V based on the prediction results of the vehicle behavior prediction unit 10. The driving assistance unit 20 can provide various driving assistance when it is predicted that the target vehicle T can enter the host lane L. For example, this driving assistance may include notification to the driver of the host vehicle V via an HMI (Human Machine Interface), control to slow down or stop the host vehicle V by instructing the actuator 2, or control to shift the lateral position of the host vehicle V away from the road area L1 by instructing the actuator 2.

[0060] Furthermore, even when it is predicted that the target vehicle T will not be able to enter the host lane L, the driving assistance unit 20 can provide driving assistance for the host vehicle V based on the amount of protrusion of the target vehicle T into the host lane L. For example, the driving assistance unit 20 can perform the aforementioned notification to the driver, control the deceleration or stop of the host vehicle V, and control the lateral position shift of the host vehicle V when the amount of protrusion of the target vehicle T exceeds a reference threshold.

[0061] That is, when the target vehicle T is predicted to be unable to enter the host lane L, the driving assistance unit 20 does not provide driving assistance for the target vehicle T to dive out (enter the host lane L). However, even when the target vehicle T is predicted to be unable to enter the host lane L, the driving assistance unit 20 can provide driving assistance for the target vehicle T to dive out if the dive amount of the target vehicle T exceeds the reference threshold.

[0062] Next, use Figure 5 and Figure 6 , the flow of the driving assistance processing for the target vehicle T entering the own lane L by the driving assistance ECU 4 will be described. Figure 5 and Figure 6The processing shown starts when the host vehicle V is in a state where it can travel. Furthermore, when the processing reaches "End," it restarts from "Start" after a predetermined time. That is, the driving assistance ECU 4 repeatedly predicts whether the target vehicle T in the road area L1 can enter the host lane L at a predetermined time.

[0063] like Figure 5 As shown, the target vehicle detection unit 11 detects a target vehicle T in the road area L1 (S101). If the target vehicle T is not present (S101: NO), the driving assistance ECU 4 restarts the process from "Start" after a predetermined time. If the target vehicle T is present (S101: YES), the distance acquisition unit 12 acquires the front distance, which is the distance between the target vehicle T and an obstacle in front of the target vehicle T (S102). The target vehicle detection unit 11 also detects the lateral position and inclination of the target vehicle T (S103).

[0064] The turning radius estimating unit 13 detects the steering angle of the tires of the target vehicle T based on the detection results of the external sensor 1 (S104). If the steering angle of the tires is detected (S104: Yes), the turning radius estimating unit 13 estimates the turning radius of the target vehicle T based on the steering angle of the tires (S105). On the other hand, if the steering angle of the tires cannot be detected (S104: No), the turning radius estimating unit 13 determines the type of the target vehicle T (S106). The turning radius estimating unit 13 then estimates the turning radius of the target vehicle T based on the determined type of the target vehicle T and the turning radius information stored in the storage unit 3 (S107).

[0065] After estimating the turning radius in S105 or S107, the entry prediction unit 14 estimates the driving trajectory of the target vehicle T based on the turning radius, the lateral position of the target vehicle T, and its inclination (S108). The entry prediction unit 14 then predicts whether the target vehicle T will interfere with the obstacle if traveling along the estimated driving trajectory based on the forward distance to the obstacle ahead (S109). If the target vehicle T will not interfere with the obstacle (S109: No), the entry prediction unit 14 predicts that the target vehicle T can avoid the obstacle ahead and enter the host lane L (S110). The driving assistance unit 20 then performs driving assistance to prevent the target vehicle T from escaping into the host lane L (S111).

[0066] On the other hand, if there is a possibility of interference with an obstacle (S109: Yes), the entry prediction unit 14 predicts that the target vehicle T will not be able to avoid the obstacle ahead and enter the host lane L (S112). Then, the entry prediction unit 14 predicts the amount of protrusion of the target vehicle T into the host lane L (S113). The driving assistance unit 20 determines whether the predicted protrusion of the target vehicle T is greater than the reference threshold (S114). If the protrusion is greater than the reference threshold (S114: Yes), the driving assistance unit 20 performs driving assistance for the protrusion of the target vehicle T (S115). On the other hand, if the protrusion is less than the reference threshold (S114: No), the driving assistance unit 20 does not perform driving assistance. Then, the driving assistance ECU 4 starts processing again from "Start" after a predetermined time.

[0067] As described above, the vehicle behavior prediction unit 10 of the driving assistance device 100 uses the length of the clear space ahead of the target vehicle T (the distance ahead) and the turning radius of the target vehicle T to predict whether the target vehicle T can avoid the obstacle ahead and enter the host lane L. In other words, the vehicle behavior prediction unit 10 can predict whether the target vehicle T can enter the host lane L by turning. As a result, the vehicle behavior prediction unit 10 can accurately predict the target vehicle T's entry into the host lane L from the road area L1 adjacent to the host lane L in which the host vehicle V is traveling.

[0068] The driving assistance unit 20 then provides driving assistance for the host vehicle V based on the prediction results of the vehicle behavior prediction unit 10. This prevents, for example, the driving assistance unit 20 from providing driving assistance to prevent the target vehicle T from escaping into the host lane L even though the target vehicle T is unable to enter the host lane L without turning back. Consequently, the driving assistance device 100 can prevent unnecessary driving assistance and thus minimize inconvenience for the driver of the host vehicle V.

[0069] In the vehicle behavior prediction unit 10 , the turning radius estimation unit 13 can estimate the turning radius based on the tire steering angle of the target vehicle T. In this case, the entry prediction unit 14 can more accurately predict the entry of the target vehicle T into the host lane L based on the actual tire steering angle.

[0070] In the vehicle behavior prediction unit 10, the turning radius estimation unit 13 can estimate the turning radius of the target vehicle T based on the minimum turning radius corresponding to the type of the target vehicle T, based on the turning radius information stored in the storage unit 3. In this case, the vehicle behavior prediction unit 10 can more accurately predict the target vehicle T's entry into the host lane L according to the type of the target vehicle T.

[0071] For example, a target vehicle T may separate from the line of vehicles while parked in a parallel parking situation with a narrow distance between vehicles. In such cases, the target vehicle T often backs up as far as possible and attempts to separate from the line of vehicles by turning while parked (steering while stationary) with the minimum turning radius. In such cases, estimating the turning radius using the minimum turning radius for each type of target vehicle T is particularly effective.

[0072] In the vehicle behavior prediction unit 10, the entry prediction unit 14 also predicts whether the target vehicle T can enter the host lane L based on the lateral position of the target vehicle T within the road area L1. For example, even if the distance ahead is the same, depending on the lateral position of the target vehicle T, the target vehicle T may be able to enter the host lane L, while other times the target vehicle T may be blocked by a forward obstacle and unable to enter the host lane L. Therefore, by further using the lateral position of the target vehicle T, the entry prediction unit 14 can predict the target vehicle T's entry into the host lane L with higher accuracy.

[0073] In the vehicle behavior prediction unit 10, the entry prediction unit 14 also predicts whether the target vehicle T can enter the host lane L based on the inclination of the target vehicle T. For example, even if the distance ahead is the same, depending on the inclination of the target vehicle T, the target vehicle T may be able to enter the host lane L in some cases, or may be blocked by a forward obstacle and unable to enter the host lane L in other cases. Therefore, by further using the inclination of the target vehicle T in the prediction, the entry prediction unit 14 can more accurately predict the target vehicle T's entry into the host lane L.

[0074] In the vehicle behavior prediction unit 10, the entry prediction unit 14 predicts the amount of the target vehicle T's protrusion into the host lane L if the target vehicle T is unable to enter the host lane L by avoiding an obstacle. Thus, even in cases where the target vehicle T is unable to enter the host lane L, the amount of protrusion calculated by the vehicle behavior prediction unit 10 can be used for various control purposes. In this embodiment, the driving assistance unit 20 provides driving assistance for the host vehicle V based on the amount of protrusion of the target vehicle T into the host lane L. Thus, even in cases where the target vehicle T is unable to enter the host lane L, the driving assistance device 100 can provide driving assistance to address protrusion even if the amount of protrusion into the host lane L is large.

[0075] In this manner, the driving assistance device 100 can detect whether the target vehicle T can avoid the obstacle ahead and enter the host lane L. Furthermore, if the target vehicle T cannot enter the host lane L, the device can quantitatively detect the maximum amount of protrusion of the target vehicle T into the host lane L. Consequently, the driving assistance device 100 can suppress excessive driving assistance for the host vehicle V, thereby reducing annoyance for the driver of the host vehicle V and providing effective driving assistance tailored to the behavior of the target vehicle T.

[0076] In particular, in a situation where the distance between vehicles in parallel parking is narrow, the target vehicle T may make multiple turns when it breaks away from the vehicle line. Even in such a situation, the driving assistance device 100 can accurately predict whether the target vehicle T can break away from the vehicle line, thereby appropriately providing driving assistance for the host vehicle V.

[0077] Furthermore, even when the target vehicle T is separated from a congested vehicle column, the driving assistance device 100 can predict the possibility of the target vehicle T entering the host lane L and provide driving assistance for the host vehicle V. In this case, the driving assistance device 100 can also predict the possibility of the target vehicle T entering the host lane L by taking into account the vehicle speed of the host vehicle V and / or the speed of the vehicle ahead of the host vehicle V.

[0078] The embodiments of the present disclosure have been described above, but the present invention is not limited to the above-mentioned embodiments. For example, the vehicle V is not limited to a car. For example, the vehicle V may also be a bicycle, a two-wheeled motorbike, an electric motorcycle, etc. In this case, the prediction result of the behavior of the target vehicle T in the vehicle behavior prediction unit 10 can also be used in a warning system for bicycles, etc. For example, in the case where a bicycle overtakes a parked vehicle that is parked on the shoulder of the road, it is particularly effective to report whether the parked vehicle can break away from the line of parked vehicles. In addition, the prediction result of the behavior of the target vehicle T in the vehicle behavior prediction unit 10 can also be applied to a warning system for pedestrians. In this case, for example, the behavior of the target vehicle T can be predicted in the same way as described above using information from external sensors mounted on glasses worn by pedestrians.

[0079] It should be noted that, for example, on a slope, a vehicle may be parked with the steering wheel turned toward the shoulder. In this case, the driving assistance device 100 may not estimate the driving trajectory, but may simply predict whether the parked vehicle is likely to enter the host lane based on the tire angle.

Claims

1. A vehicle behavior prediction device for predicting the entry of a target vehicle from a road area adjacent to a lane in which a vehicle is traveling into the lane, the vehicle behavior prediction device comprising: a target vehicle detecting unit configured to detect the target vehicle existing in the road area; a distance acquisition unit that acquires a front distance that is a distance between the target vehicle and an obstacle that exists in front of the target vehicle; a turning radius estimating unit for estimating a turning radius of the target vehicle; as well as an entry prediction unit, which predicts whether the target vehicle can avoid the obstacle and enter the host lane based on the acquired front distance and the estimated turning radius, The vehicle further includes a storage unit that stores turning radius information in which the minimum turning radius is associated with each vehicle type. The turning radius estimating unit extracts the minimum turning radius corresponding to the type of the target vehicle based on the turning radius information stored in the storage unit, and estimates the turning radius of the target vehicle based on the extracted minimum turning radius.

2. The vehicle behavior prediction device according to claim 1, wherein: The entry prediction unit further predicts whether the target vehicle can enter the host lane based on the lateral position of the target vehicle in the road area.

3. The vehicle behavior prediction device according to claim 1 or 2, wherein: The entry prediction unit further predicts whether the target vehicle can enter the host lane based on the inclination of the target vehicle with respect to the extending direction of the host lane.

4. The vehicle behavior prediction device according to claim 1 or 2, wherein: The entry prediction unit predicts an amount of protrusion of the target vehicle into the host lane when the target vehicle cannot avoid the obstacle and enter the host lane.

Images