Parking assistance method and parking assistance device

Abstract

In the parking assistance method of the present invention, the marker objects around the vehicle and the relative position of the marker objects relative to the vehicle, i.e., the marker object position (S2) are detected, and the known marker objects pre-stored in a specified storage device and the relative position relationship between the known marker objects and the target parking position are read from the storage device (S3). Based on the marker object position detected by the sensor and the relative position relationship between the known marker object and the target parking position, the relative position of the target parking position relative to the current position of the vehicle is estimated (S5). Based on the estimated relative position, the target driving trajectory from the current position of the vehicle to the relative position of the target parking position is calculated (S8), and the estimation accuracy of the estimated relative position is determined (S6). When the estimation accuracy is low, the speed limit of the moving speed of the vehicle along the target driving trajectory is limited to a speed lower than that when the estimation accuracy is high (S10).

Description

Technical Field

[0001] The invention relates to a parking assistance method and a parking assistance device. Background Art

[0002] Patent document 1 described below discloses a technique for identifying and storing feature points around a target parking position, calculating the relative position of the target parking position relative to the vehicle based on the relative position of the vehicle relative to the stored feature points, and automatically moving the vehicle to the target parking position based on the calculated relative position.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2017-138664

[0006] Problems to be Solved by the Invention

[0007] However, if the calculation accuracy of the relative position between the target parking position and the host vehicle is low, there is a possibility that the occupants may feel uncomfortable when the host vehicle is moved based on the relative position. Summary of the invention

[0008] An object of the present invention is to reduce the discomfort caused to the occupants when moving the vehicle to the target parking position based on the known relative position relationship between the marker object detected by the sensor mounted on the vehicle and the target parking position and the marker object.

[0009] In a parking assistance method of one embodiment of the present invention, a sensor mounted on the vehicle detects marker objects around the vehicle and the relative position of the marker objects relative to the vehicle, i.e., the marker object position, and reads out known marker objects pre-stored in a specified storage device and the relative position relationship between the known marker objects and the target parking position from a storage device. Based on the marker object position detected by the sensor and the relative position relationship between the known marker object and the target parking position, the relative position of the target parking position relative to the current position of the vehicle is estimated. Based on the estimated relative position, a target driving trajectory from the current position of the vehicle to the relative position of the target parking position is calculated, and the estimation accuracy of the estimated relative position is determined. When the estimation accuracy is low, the speed limit of the moving speed of the vehicle along the target driving trajectory is limited to a speed lower than that when the estimation accuracy is high.

[0010] Effects of the Invention

[0011] According to the present invention, when the host vehicle is moved to the target parking position based on the known relative position relationship between the marker object and the target parking position detected by the sensor mounted on the host vehicle, the discomfort caused to the occupants can be reduced.

[0012] The objects and advantages of the present invention are realized by using the elements and combinations thereof shown in the scope of the claims.The above general description and the following detailed description are only exemplary and illustrative and should not be construed as limiting the present invention in the manner of the scope of the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a diagram showing an example of a schematic configuration of a parking assist device according to an embodiment.

[0014] Figure 2A This is an illustration of an example of a learning completed landmark object.

[0015] Figure 2B This is an explanatory diagram of an example of a parking assistance method.

[0016] Figure 3 yes Figure 1 A block diagram showing an example of the functional structure of a controller in FIG.

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

[0018] (structure)

[0019] Figure 1 1 is a diagram showing an example of a schematic structure of a parking assistance device according to an embodiment. A vehicle 1 is provided with a parking assistance device 10 for assisting the vehicle 1 in parking at a target parking position. In the parking assistance of the parking assistance device 10, a target driving trajectory from the current position of the vehicle 1 to the target parking position is calculated. Then, the automatic driving of the vehicle 1 is controlled so that the vehicle 1 travels to the target parking position along the target driving trajectory. The parking assistance device 10 includes a positioning device 11, an object sensor 12, a vehicle sensor 13, a controller 14, and an actuator 15.

[0020] The positioning device 11 measures the current position of the host vehicle 1. The positioning device 11 may include, for example, a global positioning system (GNSS) receiver. The GNSS receiver is, for example, a global positioning system (GPS) receiver, and measures the current position of the host vehicle 1 by receiving radio waves from a plurality of navigation satellites.

[0021] The object sensor 12 detects an object within a predetermined distance range (e.g., a detection area of ​​the object sensor 12) from the host vehicle 1. The object sensor 12 detects the surrounding environment of the host vehicle 1, such as the relative position of the object existing around the host vehicle 1 and the host vehicle 1, the distance between the host vehicle 1 and the object, and the direction in which the object exists. The object sensor 12 may include, for example, a camera that captures the surrounding environment of the vehicle 1. The object sensor 12 may include a distance measuring device such as a laser range finder (LRF), a radar, or a laser radar such as a LiDAR (Light Detection and Ranging).

[0022] The vehicle sensor 13 detects various information (vehicle information) obtained from the host vehicle 1. The vehicle sensor 13 may include, for example, a vehicle speed sensor for detecting the travel speed (vehicle speed) of the host vehicle 1, a wheel speed sensor for detecting the rotation speed of each tire of the host vehicle 1, a three-axis acceleration sensor (G sensor) for detecting the acceleration (including deceleration) of the host vehicle 1 in the three-axis direction, a steering angle sensor for detecting the steering angle (including the steering angle), a gyro sensor for detecting the angular velocity generated by the host vehicle 1, and a yaw rate sensor for detecting the yaw rate.

[0023] The controller 14 is an electronic control unit (ECU) that performs parking assist control of the vehicle 1. The controller 14 includes peripheral components such as a processor 14a and a storage device 14b. The processor 14a may be a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit). The storage device 14b may include a semiconductor storage device, a magnetic storage device, an optical storage device, etc.

[0024] The functions of the controller 14 described below are realized by, for example, the processor 14a executing a computer program stored in the storage device 14b. The controller 14 may be formed by hardware dedicated to executing each information processing described below.

[0025] The actuator 15 operates the steering wheel, accelerator opening, and brake device of the vehicle 1 according to the control signal from the controller 14 to generate the vehicle behavior of the vehicle 1. The actuator 15 includes a steering actuator, an accelerator opening actuator, and a brake control actuator. The steering actuator controls the steering direction and steering amount of the steering wheel of the vehicle 1. The accelerator opening actuator controls the accelerator opening of the vehicle 1. The brake control actuator controls the braking action of the brake device of the vehicle 1.

[0026] Next, an example of parking assist control by the parking assist device 10 according to the embodiment will be described.

[0027] Reference Figure 2AWhen the driver utilizes the parking assistance of the parking assistance device 10, first, the driver stores the marker objects existing near the target parking position 2, which is the target position for parking the vehicle 1, and the relative positional relationship between these marker objects and the target parking position 2, in the storage device 14b. The marker objects are ground objects used as marks for determining the current position of the vehicle 1, and may be, for example, road markings (lane boundary lines 3a, stop lines 3b, road signs, etc.), road boundaries (curbstones 3c to 3e, guardrails, etc.), obstacles (houses 3f, fences 3g, objects 3h, etc.) drawn on the road surface.

[0028] Thus, in the following description, the data formed by combining the known landmark objects stored in the storage device 14b and the relative positional relationship between these known landmark objects and the target parking position 2 is expressed as "parking assist data".

[0029] In order to store the parking assist data in the storage device 14 b , the operation mode of the parking assist device 10 is set to the “landmark object learning mode.” Then, the driver parks the host vehicle 1 at the target parking position 2 by manual driving.

[0030] While the host vehicle 1 is parked at the target parking position 2 by manual driving, the parking assist device 10 detects the landmark objects around the host vehicle 1 and the relative positions of the landmark objects with respect to the host vehicle 1 , ie, the landmark object positions, through the object sensor 12 .

[0031] For example, the parking assist device 10 detects a road marking (in Figure 2A In the example, lane boundary line 3a, stop line 3b), road boundary (in Figure 2A In the example, the grounding part of the curbstones 3c to 3e), obstacles (in Figure 2A In the example, the edge or corner portion of a landmark object such as a house 3f, a wall 3g, or a grounding site of an object 3h is used as a feature point.

[0032] In addition, the parking assist device 10 calculates the feature amount of the detected feature point. Here, the feature amount may be, for example, vector data calculated from the vicinity of the feature point on the image. The detection of feature points and the calculation of feature amounts may be performed using methods such as SIFT, SURF, ORB, BRIAK, KAZE, and AKAZE.

[0033] Furthermore, the parking assist device 10 calculates the relative position of the feature point with respect to the host vehicle 1 based on the position of the feature point on the image and camera information related to the installation state of the camera on the host vehicle 1 (installation position, optical axis angle, and viewing angle).

[0034] The parking assist device 10 may also detect feature points of point group information obtained by a laser range finder, a radar, or a LiDAR. In this specification, an example of detecting feature points from a captured image is described.

[0035] Next, the parking assist device 10 finds the relative positional relationship between the marker object (feature point) detected by the object sensor 12 and the target parking position 2. For example, the parking assist device 10 estimates the current position of the host vehicle 1 in the fixed coordinate system when the marker object is detected by the object sensor 12, and calculates the position of the marker object in the fixed coordinate system based on the estimated current position and the relative position of the object relative to the host vehicle 1. Here, the fixed coordinate system refers to a coordinate system (such as a map coordinate system) with a specific location as the coordinate origin. Next, the parking assist device 10 detects the position of the host vehicle 1 when the host vehicle 1 is located at the target parking position 2 as the position of the target parking position 2 in the fixed coordinate system. By determining the position of the marker object and the position of the target parking position 2 in the fixed coordinate system, the relative positional relationship between the marker object and the target parking position 2 is determined.

[0036] The current position of the host vehicle 1 in the fixed coordinate system can be estimated, for example, by the positioning device 11, the odometry method, or the dead reckoning method. The current position of the host vehicle 1 in the fixed coordinate system can also be estimated based on the map mapping of the marker object detected by the object sensor 12, the known marker object position, and the high-precision map information in which the marker object position is pre-stored.

[0037] Furthermore, the parking assist device 10 may determine the relative positional relationship between the landmark object and the target parking position 2 based on the landmark object position detected by the object sensor 12 when the host vehicle 1 is located at the target parking position 2 .

[0038] The parking assist device 10 stores parking assist data composed of information of the marker object (i.e., the feature amount of the feature point), the marker object, the target parking position 2, and the relative position relationship in the storage device 14b. As the data of the relative position relationship, the position of the marker object and the position of the target parking position 2 in the fixed coordinate system may be stored, or the position of the marker object in the fixed coordinate system with the target parking position 2 as the coordinate origin may be stored. Hereinafter, the marker object stored in the storage device 14b is referred to as a "learning completed marker object".

[0039] Figure 2A The circle icon represents the learning completion mark object stored in the storage device 14b.

[0040] The parking assist device 10 may store parking assist data for performing parking assist at each of a plurality of different target parking positions in the storage device 14 b .

[0041] When the parking assist data is stored in the storage device 14b, parking assist can be performed using the parking assist device 10. In order to utilize parking assist, the operation mode of the parking assist device 10 is set to the "parking assist mode".

[0042] In the parking assist mode, the parking assist device 10 reads parking assist data from the storage device 14b. When parking assist data is stored for each of a plurality of different target parking positions, the parking assist data stored for the target parking position at which the host vehicle 1 is to be parked is selected and read.

[0043] For example, the parking assist device 10 can read parking assist data corresponding to the current position of the host vehicle 1 measured by the positioning device 11. For example, the parking assist data stored about the target parking position closest to the current position of the host vehicle 1 can be read.

[0044] Alternatively, attribute data of parking assistance data (eg, "parking lot at home" or "parking lot at work") may be stored in the storage device 14b, and the occupant (eg, driver) may select parking assistance data to be read from the storage device 14b based on the attribute data.

[0045] Figure 2B The circle icon represents the learning completion mark object read from the storage device 14b in the parking assist mode.

[0046] The parking assist device 10 detects the landmark objects around the host vehicle 1 and the relative positions of the landmark objects with respect to the host vehicle 1, that is, the landmark object positions, through the object sensor 12. The landmark objects and the landmark object position detection method are the same as those in the landmark object learning mode.

[0047] The landmark objects detected by the object sensor 12 in the parking assist mode are indicated by triangular icons. Figure 2B In the example shown in FIG. 1 , the lane boundary line 3 a , the curbstones 3 c and 3 e , and the corner portions of the fence 3 g are detected as feature points of the landmark objects.

[0048] The parking assist device 10 makes each marker object (triangular icon) detected by the object sensor 12 in the parking assist mode correspond to the same marker object among the learning completed marker objects (circle icons) stored in the storage device 14b. For example, the parking assist device 10 may determine that marker objects having feature points with the same or similar feature quantities are the same marker object. Figure 2B In the example of FIG. 1 , the lane boundary line 3 a , the curbstones 3 c and 3 e , and the corner portions of the fence 3 g are corresponded to each other.

[0049] The parking assist device 10 calculates the relative position of the target parking position 2 with respect to the current position of the host vehicle 1 based on the relative positional relationship between each marker object (triangular icon) detected in the parking assist mode and the host vehicle 1, and the relative positional relationship between the learning completion marker object (circle icon) corresponding to these marker objects (triangular icon) and the target parking position 2. For example, the parking assist device 10 may calculate the position of the target parking position 2 on a relative coordinate system (hereinafter referred to as "vehicle coordinate system") based on the current position of the host vehicle 1. Alternatively, the current position of the host vehicle 1 on the fixed coordinate system may be calculated based on the relative positional relationship between each marker object (triangular icon) detected in the parking assist mode and the host vehicle 1, and the learning completion marker object (circle icon) on the fixed coordinate system. By determining the position of the host vehicle 1 and the position of the target parking position 2 in the fixed coordinate system, the relative position of the target parking position 2 with respect to the current position of the host vehicle 1 is determined.

[0050] The parking assist device 10 calculates a target driving trajectory from the current position of the host vehicle 1 to the target parking position 2 based on the relative position of the target parking position 2 with respect to the current position of the host vehicle 1. The parking assist device 10 controls the automatic driving of the host vehicle 1 so that the host vehicle 1 travels to the target parking position along the calculated target driving trajectory.

[0051] In this way, the relative position of the target parking position 2 with respect to the host vehicle 1 (hereinafter, also referred to as the relative position of the target parking position 2) is estimated based on the known relative position relationship between the landmark object and the target parking position 2 detected by the sensor mounted on the host vehicle 1, and if the host vehicle 1 is controlled so as to travel to the target parking position 2, this may sometimes cause discomfort to the occupants. For example, if the estimation accuracy of the relative position of the target parking position 2 is low, the control accuracy of causing the host vehicle 1 to travel to the target parking position 2 is reduced, and this may cause discomfort to the occupants.

[0052] Therefore, the parking assist device 10 determines the estimation accuracy of the relative position of the target parking position 2, and when the estimation accuracy is low, limits the speed limit of the moving speed of the host vehicle 1 along the target driving trajectory to a lower speed than when the estimation accuracy is high. Thus, when the estimation accuracy of the relative position of the target parking position 2 is low, the moving speed to the target parking position 2 becomes low, so that the discomfort caused to the occupant can be suppressed.

[0053] Next, the functional structure of the controller 14 will be described in detail. Figure 3The controller 14 functions as an image conversion unit 40 , a self-position calculation unit 41 , a feature point detection unit 42 , a map generation unit 43 , a relative position estimation unit 45 , an estimation accuracy determination unit 46 , a target trajectory generation unit 47 , a steering control unit 48 , and a vehicle speed control unit 49 .

[0054] The image conversion unit 40 converts the image captured by the camera of the object sensor 12 into Figure 2A and 2B The bird's-eye view image (surround view monitor image) as shown is observed from a virtual viewpoint directly above the vehicle 1. Hereinafter, the bird's-eye view image converted by the image conversion unit 40 may be referred to as a "surrounding image". Figure 2A is the surrounding image in the landmark object learning mode, Figure 2B It is the surrounding image in parking assist mode.

[0055] The own position calculation unit 41 calculates the current position of the own vehicle 1 on the fixed coordinate system based on the dead reckoning method based on the vehicle information output from the vehicle sensor 13. The own position calculation unit 41 can also correct the calculated current position by mapping the landmark object detected by the object sensor 12 with the known landmark object position and high-precision map information.

[0056] The feature point detection unit 42 detects feature points of landmark objects around the vehicle 1 based on the surrounding image output from the image conversion unit 40, and calculates feature values ​​of the feature points. The feature point detection unit 42 outputs the detected feature points and their feature values ​​together with the current position of the vehicle 1 received from the own position calculation unit 41 to the map generation unit 43 and the relative position estimation unit 45.

[0057] In the landmark object learning mode, the map generating unit 43 stores feature point information including feature points output from the feature point detecting unit 42 while the driver is manually driving the host vehicle 1 to park at the target parking position 2, the current position of the host vehicle 1 synchronized therewith, and feature amounts of the feature points in the storage device 14b as parking assist data 44. The positions of the feature points on the fixed coordinate system may be calculated based on the current position of the host vehicle 1 and stored as the feature point information.

[0058] When the current position of the host vehicle 1 reaches the target parking position 2, the map generation unit 43 receives the current position of the host vehicle 1 on the fixed coordinate system from the positioning device 11 or the own position calculation unit 41, and stores the target parking position 2 in the storage device 14b as parking assistance data 44. For example, the driver can operate the human-machine interface (not shown) of the parking assistance device 10 to indicate that the current position of the vehicle 1 is the target parking position 2. As a result, the storage device 14b stores the relative positional relationship between the position of the feature point detected in the landmark object learning mode and the position of the target parking position 2, and the feature amount of the feature point as parking assistance data 44 in the storage device 14b. In addition, as the parking assistance data 44 stored in the storage device 14b, it is sufficient to include at least the relative positional relationship between the position of the feature point and the position of the target parking position 2, and it is not necessarily necessary to include the feature amount of the feature point. Hereinafter, the position of the feature point or information including the position and feature amount of the feature point is also described as feature point information.

[0059] When the operation mode of the parking assist device 10 is switched to the parking assist mode, the relative position estimating unit 45 reads the parking assist data 44 from the storage device 14b. The relative position estimating unit 45 calculates the feature point information ( Figure 2A ), and feature point information ( Figure 2B The triangular icon in the figure is used to match the feature point information detected for the same landmark object so that the feature point information detected for the same landmark object corresponds to each other.

[0060] The relative position estimation unit 45 estimates the relative position of the target parking position 2 relative to the current position of the vehicle 1 based on the relative position relationship between the feature points (triangle icons) detected in the parking assistance mode and the vehicle 1, and the relative position relationship between the feature point information (circle icon) of the learning completion mark object corresponding to these feature points (triangle icons) and the target parking position 2.

[0061] For example, the feature points detected in the parking assist mode are recorded as (x i ,y i ), will be combined with the feature point (x i ,y i ) respectively correspond to the feature points of the learning completed landmark objects and are recorded as (x mi ,y mi )(i=1 to N). For example, the relative position estimation unit 45 may calculate the affine transformation matrix M by the following equation based on the least squares method: affine .

[0062] (Equation 1)

[0063]

[0064] in,

[0065]

[0066] We can also use the weighted least squares method to calculate the column vector (a 1 , a 2 , a 3 , a 4 ) T .

[0067] (Formula 2)

[0068] W=diag(w 1 … w N )

[0069]

[0070] The relative position estimating unit 45 calculates the position (target x) of the target parking position 2 on the fixed coordinate system stored in the parking assist data 44 according to the following equation: m , targety m ) is transformed into the position (targetx, targety) of the vehicle coordinate system.

[0071] (Equation 3)

[0072]

[0073] Instead, the relative position estimating unit 45 assumes that the position (x mi ,y mi )(i=1~N), respectively calculate the feature points (x i ,y i ), and feature points (x i ,y i ) corresponds to the learning of the feature points of the landmark object (x mi ,y mi ) i (i.e. position error), so that the average S of the distance di = (d 1 +d 2 +…d N ) / N is minimized, and the position of the feature point of the learning completion mark object in the vehicle coordinate system is determined.

[0074] The relative position estimation unit 45 can calculate the position (targetx, targety) of the target parking position 2 in the vehicle coordinate system based on the position of the feature point of the learning completion mark object in the determined vehicle coordinate system and the relative position relationship between the position of the feature point of the learning completion mark object and the target parking position 2.

[0075] The estimation accuracy determination unit 46 determines the estimation accuracy of the relative position of the target parking position 2 with respect to the current position of the host vehicle 1 estimated by the relative position estimation unit 45 .

[0076] For example, the estimation accuracy determination unit 46 may determine that the estimation accuracy is lower when there are fewer feature points detected in the parking assist mode than when there are more feature points. For example, the estimation accuracy may be determined to be lower as fewer feature points are detected in the parking assist mode.

[0077] For example, the estimation accuracy determination unit 46 may determine that the estimation accuracy is lower when there are fewer learning completion marker objects than when there are more learning completion marker objects. For example, the estimation accuracy may be determined to be lower as fewer learning completion marker objects are present.

[0078] That is, when the number of feature points or learning completion marker objects detected in the parking assist mode is small, the number of learning completion marker objects corresponding to the feature points detected in the parking assist mode decreases, and there is a possibility that the estimation accuracy of the target parking position 2 relative to the current position of the host vehicle 1 decreases. Therefore, the estimation accuracy may be estimated on the assumption that the feature points or learning completion marker objects detected in the parking assist mode, whichever is smaller, all correspond to the other, and the estimation accuracy is determined to be lower as the number of the feature points or learning completion marker objects detected in the parking assist mode decreases.

[0079] In addition, for example, the estimation accuracy determination unit 46 may determine that the estimation accuracy is lower when the number of learning completion marker objects corresponding to the feature points detected in the parking assist mode is small than when the number of learning completion marker objects is large. For example, the fewer the learning completion marker objects corresponding to the feature points detected in the parking assist mode are, the lower the estimation accuracy may be determined.

[0080] For example, the estimation accuracy determination unit 46 may calculate the distance (position error) d between the position of the marker object detected in the parking assist mode and the position of the feature point of the learned marker object after matching (aligning) the marker object detected in the parking assist mode with the feature point of the learned marker object. i The average S = (d 1 +d 2 +…d N) / N is large, it is determined that the estimation accuracy is lower than when the minimum value of the average S is small. It can be determined that the larger the average S is, the lower the estimation accuracy is.

[0081] In addition, for example, the estimation accuracy determination unit 46 may calculate the affine transformation matrix M based on the least squares method. affine When the residual is large, it is determined that the estimation accuracy is lower than when the residual is small. It can be determined that the larger the residual, the lower the estimation accuracy.

[0082] The target trajectory generating unit 47 generates a target driving trajectory from the current position of the host vehicle 1 on the vehicle coordinate system (i.e., the coordinate origin) to the position (targetx, targety) of the target parking position 2 on the vehicle coordinate system. In addition, the target driving trajectory can be generated by connecting the current position of the host vehicle 1 to the target parking position 2 with a clothoid curve, for example.

[0083] In addition, the target trajectory generation unit 47 calculates a moving speed plan (moving speed curve) that sets the moving speed of each position on the target driving trajectory from the current position of the host vehicle to the target parking position 2. For example, the target trajectory generation unit 47 calculates the moving speed of each position on the target driving trajectory so that the host vehicle is accelerated from a stationary state at the current position to a specified speed limit at a specified acceleration, and then decelerated from the speed limit at a specified deceleration and stopped at the target parking position 2. The target trajectory generation unit 47 may set a lower moving speed at a location with a larger curvature of the target driving trajectory.

[0084] The steering control unit 48 controls the steering actuator of the actuator 15 so that the host vehicle 1 travels along the target travel trajectory.

[0085] The vehicle speed control unit 49 controls the accelerator actuator and the brake actuator of the actuator 15 so as to change the vehicle speed of the vehicle 1 according to the moving speed plan calculated by the target trajectory generation unit 47. Thus, the vehicle 1 is controlled to travel along the target travel trajectory.

[0086] When the estimation accuracy of the relative position of the target parking position 2 determined by the estimation accuracy determination unit 46 is low, the vehicle speed control unit 49 sets the speed limit for causing the host vehicle 1 to travel along the target travel trajectory to a speed lower than when the estimation accuracy is high. For example, the lower the estimation accuracy, the lower the speed limit is set.

[0087] For example, the vehicle speed control unit 49 can calculate the corrected moving speed plan by correcting the moving speed of the position where a moving speed higher than the speed limit set based on the estimated accuracy is set to the speed limit in the moving speed plan calculated by the target trajectory generation unit 47. The vehicle speed control unit 49 can control the accelerator actuator and the brake actuator of the actuator 15 to change the vehicle speed of the host vehicle 1 according to the corrected moving speed plan.

[0088] In addition, when the vehicle speed control unit 49 controls the speed of the host vehicle 1 according to the moving speed plan calculated by the target trajectory generation unit 47, it can also determine whether the moving speed of the host vehicle 1 detected by the vehicle speed sensor of the vehicle sensor 13 is higher than the speed limit set according to the estimation accuracy. When the moving speed of the host vehicle 1 is higher than the speed limit, the moving speed of the host vehicle can also be controlled to be lower than the speed limit.

[0089] In addition, the vehicle speed control unit 49 may also determine whether the distance from the host vehicle 1 to the obstacle around the host vehicle 1 is less than a predetermined threshold value, and stop the host vehicle 1 when the distance from the host vehicle 1 to the obstacle is less than the predetermined threshold value. For example, the distance information from the host vehicle 1 to the obstacle around the host vehicle 1 may be detected by the object sensor 12.

[0090] In addition, the target trajectory generation unit 47 may calculate the target driving trajectory only once when the parking assistance device 10 starts parking assistance, or may regenerate the target driving trajectory to update the target driving trajectory after the vehicle 1 starts traveling along the target driving trajectory toward the target parking position 2. For example, the target trajectory generation unit 47 may repeatedly update the target driving trajectory at a predetermined period.

[0091] When updating the target driving trajectory, the feature point detection unit 42 detects feature points of objects around the host vehicle 1 from an image captured by the camera of the object sensor 12 after the host vehicle 1 starts traveling toward the target parking position 2 .

[0092] After starting to travel toward the target parking position 2, the relative position estimating unit 45 re-estimates the relative position of the target parking position 2 relative to the current position of the host vehicle 1 by matching the feature points detected by the feature point detecting unit 42 with the feature points of the learning completion marker object stored as the parking assistance data 44. In addition, the estimation accuracy determining unit 46 determines the estimation accuracy of the re-estimated relative position of the target parking position 2. Generally, the closer the host vehicle 1 is to the target parking position 2, the more the number of marker objects that can be detected and matched with the learning completion marker object increases, and thus there is a tendency for the estimation accuracy to be higher.

[0093] The target trajectory generation unit 47 regenerates the target driving trajectory from the current position of the host vehicle 1 to the target parking position 2 based on the re-estimated relative position of the target parking position 2. In addition, the target trajectory generation unit 47 updates the moving speed plan based on the regenerated target driving trajectory. At this time, the target trajectory generation unit 47 sets the current vehicle speed of the host vehicle 1 detected by the vehicle sensor 13 as the moving speed (initial value) of the current position.

[0094] The steering control unit 48 controls the steering actuator so that the host vehicle 1 travels along the regenerated target travel trajectory. The vehicle speed control unit 49 controls the actuator 15 so that the vehicle speed of the host vehicle 1 is changed according to the updated travel speed plan.

[0095] The vehicle speed control unit 49 limits the speed limit of the host vehicle 1 along the target travel trajectory to a lower speed than when the estimation accuracy is high, based on the estimation accuracy of the re-estimated relative position of the target parking position 2 , if the estimation accuracy is low.

[0096] (action)

[0097] Figure 4 This is a flowchart of an example of the operation of the parking assist device 10 in the parking assist mode.

[0098] In step S1 , the positioning device 11 measures the current position of the host vehicle 1 on the fixed coordinate system.

[0099] In step S2 , the object sensor 12 detects feature points of landmark objects around the host vehicle 1 .

[0100] In step S3 , the relative position estimating unit 45 of the controller 14 reads the parking assist data corresponding to the current position of the host vehicle 1 from the storage device 14 b .

[0101] In step S4 , the relative position estimating unit 45 determines the correspondence relationship between the feature points of the landmark object detected in step S2 and the feature points of the known landmark object in the parking assist data read in step S3 .

[0102] In step S5, the relative position estimation unit 45 estimates the relative position of the target parking position 2 relative to the vehicle 1 based on the relative position of the feature point of the marker object detected in step S2 relative to the vehicle 1, and the relative position relationship between the feature point of the known marker object corresponding to the feature point of the marker object detected in step S2 and the target parking position 2.

[0103] In step S6 , the estimation accuracy determination unit 46 determines the estimation accuracy of the relative position in step S5 .

[0104] In step S7 , when the estimation accuracy determined in step S6 is low, the vehicle speed control unit 49 limits the speed limit for causing the host vehicle 1 to travel to the target parking position 2 to a speed lower than when the estimation accuracy is high.

[0105] In step S8 , the target trajectory generation unit 47 generates a target travel trajectory for causing the host vehicle 1 to travel from the current position of the host vehicle 1 to the target parking position 2 based on the relative position of the target parking position 2 with respect to the host vehicle 1 estimated in step S5 .

[0106] In step S9 , the target trajectory generation unit 47 calculates a moving speed plan in which the moving speed at each position on the target travel trajectory is set.

[0107] In step S10 , the vehicle speed control unit 49 limits the travel speed plan calculated in step S9 to the speed limit set in step S7 .

[0108] In step S11, the steering control unit 48 controls the steering angle so that the vehicle 1 travels along the target travel trajectory generated in step S8. The vehicle speed control unit 49 controls the moving speed of the host vehicle 1 according to the moving speed plan limited in step S10. When the host vehicle 1 reaches the target parking position 2, the process ends.

[0109] (Effects of Embodiments)

[0110] (1) The object sensor 12 detects the marker objects around the host vehicle 1 and the relative position of the marker objects relative to the host vehicle 1, i.e., the marker object positions. The controller 14 reads out the known marker objects and the relative position relationship between the known marker objects and the target parking position pre-stored in the specified storage device 14b from the storage device 14b, estimates the relative position of the target parking position relative to the current position of the host vehicle 1 based on the marker object positions detected by the object sensor 12 and the relative position relationship between the known marker objects and the target parking position, calculates the target driving trajectory from the current position of the host vehicle 1 to the relative position of the target parking position based on the estimated relative position, determines the estimation accuracy of the estimated relative position, and in the case of low estimation accuracy, limits the speed limit of the moving speed of the host vehicle 1 along the target driving trajectory to a speed lower than that in the case of high estimation accuracy.

[0111] Thus, when the estimation accuracy of the relative position of the target parking position 2 is low, the moving speed to the target parking position 2 becomes low, so that the discomfort caused to the occupants can be suppressed. That is, for example, when the estimation accuracy of the relative position of the target parking position 2 is low, the calculation accuracy of the target driving trajectory from the current position of the host vehicle 1 to the relative position of the target parking position also becomes low, and there is a possibility that the optimal target driving trajectory cannot be generated. In this case, if the moving speed of the host vehicle 1 is fast, it is possible that the driver will feel uncomfortable, but by reducing the moving speed, the discomfort caused to the occupants can be suppressed.

[0112] (2) When the number of marker objects detected by the object sensor 12 is small, the controller 14 may determine that the estimation accuracy is lower than when the number of marker objects is large.

[0113] When the number of known landmark objects stored in the storage device 14 b is small, the controller 14 may determine that the estimation accuracy is lower than when the number of known landmark objects is large.

[0114] The controller 14 can also estimate the relative position of the target parking position with respect to the current position of the vehicle 1 by making the marker object detected by the object sensor 12 correspond to the known marker objects stored in the storage device 14b, and can also, when the number of known marker objects corresponding to the marker objects detected by the object sensor 12 is small, determine that the estimation accuracy is lower than when there are more known marker objects.

[0115] The controller 14 may also estimate the relative position of the target parking position with respect to the current position of the vehicle 1 by reducing the average value of the respective distances between multiple marker objects detected by the object sensor 12 and multiple known marker objects stored in the storage device 14b, and when the average value is large, the estimated accuracy is judged to be lower than when the average value is smaller.

[0116] Thereby, the estimation accuracy of the relative position of the target parking position with respect to the current position of the host vehicle 1 can be determined.

[0117] (3) The controller 14 calculates a moving speed plan that sets the moving speed of each position on the target driving trajectory from the current position of the vehicle 1 to the target parking position, and calculates a corrected moving speed plan by correcting the moving speed of the position set with a moving speed higher than the speed limit to the speed limit in the moving speed plan. Based on the corrected moving speed plan, the controller 14 controls the moving speed of the vehicle 1 along the target driving trajectory.

[0118] As a result, the moving speed of the host vehicle 1 traveling along the target travel trajectory can be limited according to the estimation accuracy of the relative position.

[0119] (4) The vehicle sensor 13 detects the moving speed of the host vehicle 1. When the moving speed of the host vehicle 1 traveling along the target travel trajectory is higher than the speed limit, the controller 14 may control the moving speed of the host vehicle 1 to be lower than the speed limit.

[0120] As a result, the moving speed of the host vehicle 1 traveling along the target travel trajectory can be limited according to the estimation accuracy of the relative position.

[0121] (5) The distance from the host vehicle 1 to the obstacle around the host vehicle 1 may be detected by the object sensor 12, and the host vehicle may be stopped when the detected distance is smaller than a predetermined distance.

[0122] This can reduce the discomfort felt by the occupants due to the host vehicle 1 being too close to an obstacle.

[0123] All examples and conditional terms described herein are intended for the purpose of teaching in order to help readers understand the present invention and the concepts provided by the inventors for technological advancement, and should be interpreted as not being limited to the above examples and conditions specifically described, as well as the structure of the examples of this specification related to the superiority and deterioration of the present invention. Although the embodiments of the present invention have been 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.

[0124] Explanation of symbols

[0125] 1: own vehicle, 2: target parking position, 3a: lane boundary line, 3b: stop line, 3c-3e: curb, 3f: house, 3g: fence, 3h: object, 10: parking assistance device, 11: positioning device, 12: object sensor, 13: vehicle sensor, 14: controller, 14a: processor, 14b: storage device, 15: actuator, 40: image conversion unit, 41: own position calculation unit, 42: feature point detection unit, 43: map generation unit, 44: parking assistance data, 45: relative position estimation unit, 46: estimation accuracy determination unit, 47: target trajectory generation unit, 48: steering control unit, 49: vehicle speed control unit.

Claims

1. A parking assistance method, characterized in that: The sensor mounted on the vehicle detects the landmark objects around the vehicle and the relative position of the landmark objects relative to the vehicle, i.e., the landmark object positions. Reading out from a storage device a known marker object pre-stored in a predetermined storage device and a relative position relationship between the known marker object and a target parking position, The relative position of the target parking position relative to the current position of the host vehicle is estimated based on the position of the marker object detected by the sensor and the relative positional relationship between the known marker object and the target parking position. Based on the estimated relative position, a target driving trajectory from the current position of the host vehicle to the relative position of the target parking position is calculated; determining the estimation accuracy of the estimated relative position, When the estimation accuracy is low, the speed limit of the moving speed of the host vehicle traveling along the target traveling trajectory is limited to a speed lower than that when the estimation accuracy is high.

2. The parking assistance method according to claim 1, characterized in that: When the number of the marker objects detected by the sensor is small, it is determined that the estimation accuracy is lower than when the number of the marker objects is large.

3. The parking assistance method according to claim 1 or 2, characterized in that: When the number of the known landmark objects stored in the storage device is small, it is determined that the estimation accuracy is lower than when the number of the known landmark objects is large.

4. The parking assistance method according to claim 1 or 2, characterized in that: By making the marker object detected by the sensor correspond to the known marker object stored in the storage device, the relative position of the target parking position with respect to the current position of the host vehicle is estimated, When the number of the known marker objects corresponding to the marker objects detected by the sensor is small, it is determined that the estimation accuracy is lower than when the number of the known marker objects is large.

5. The parking assistance method according to claim 1 or 2, characterized in that: The relative position of the target parking position with respect to the current position of the host vehicle is estimated so that the average value of the respective distances between the plurality of the marker objects detected by the sensor and the plurality of the known marker objects stored in the storage device becomes smaller, When the average value is large, it is determined that the estimation accuracy is lower than when the average value is small.

6. The parking assistance method according to claim 1 or 2, characterized in that: calculating a moving speed plan that sets moving speeds for respective positions on the target driving trajectory from the current position of the host vehicle to the target parking position, The corrected moving speed plan is calculated by correcting the moving speed of the position where a moving speed higher than the speed limit is set in the moving speed plan to the speed limit, Based on the corrected completed moving speed plan, the moving speed of the host vehicle is controlled so as to travel along the target travel trajectory.

7. The parking assistance method according to claim 1 or 2, characterized in that: detecting the moving speed of the vehicle, When the moving speed of the host vehicle traveling along the target traveling trajectory is higher than the speed limit, the moving speed of the host vehicle is controlled to be equal to or lower than the speed limit.

8. The parking assistance method according to claim 1 or 2, characterized in that: The sensor detects a distance from the host vehicle to an obstacle around the host vehicle, and stops the host vehicle when the detected distance is less than a predetermined distance.

9. A parking assistance device, characterized in that: have: A sensor mounted on the vehicle to detect a marker object around the vehicle and a relative position of the marker object relative to the vehicle, i.e., a marker object position; A storage device storing known marker objects and a relative position relationship between the known marker objects and a target parking position; A controller that estimates the relative position of the target parking position with respect to the current position of the host vehicle based on the position of the marker object detected by the sensor and the relative position relationship between the known marker object and the target parking position, calculates a target driving trajectory from the current position of the host vehicle to the relative position of the target parking position based on the estimated relative position, determines an estimation accuracy of the estimated relative position, and, if the estimation accuracy is low, limits the moving speed of the host vehicle along the target driving trajectory to a speed lower than that when the estimation accuracy is high.

Images