Parking assistance method and parking assistance device

Abstract

The parking assistance method involves: detecting the own position of a host vehicle (S1); estimating a detection accuracy of the own position (S2); setting, as a first own position, the own position of a point at which the detection accuracy changes from a state of being equal to or greater than a prescribed accuracy to a state of being smaller than the prescribed accuracy (S13); detecting a relative position relationship between a target parking position and a target that is present around a target parking position when the host vehicle is parked at the target parking position after the first own position is set (S10); storing, in a storage device, the first own position in association with trained target data, which represents the relative position relationship, if the detection accuracy is smaller than the prescribed accuracy when the host vehicle stops at the target parking position (S11); and assisting in parking the host vehicle at the target parking position on the basis of the first own position and the trained target data when the first own position is stored in association with the trained target data(S40-S43).

Description

Parking assistance method and parking assistance device

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

[0002] The following Patent Document 1 describes a parking assistance device that detects the vehicle's own position based on positioning information and provides parking assistance when it determines that the vehicle's own position is approaching a target parking position that has been registered in advance in a storage device.

[0003] International Publication No. 2017 / 072941

[0004] The technology of Patent Document 1 mentioned above may not be able to determine whether a registered target parking position is near the vehicle if the detection accuracy of the vehicle's own position is low. The present invention aims to make it possible to determine whether a registered target parking position is near the vehicle in a location where the detection accuracy of the vehicle's own position is low.

[0005] In one aspect of the parking assistance method of the present invention, the vehicle's own position is detected, the detection accuracy of the self-position is estimated, and the self-position at the point where the detection accuracy changes from a state where it is equal to or greater than a predetermined accuracy to a state where it is less than the predetermined accuracy is set as a first self-position, and the relative positional relationship between the target parking position and targets present around the target parking position when the vehicle is parked at the target parking position after the first self-position is set is detected, and if the detection accuracy is less than the predetermined accuracy when the vehicle is stopped at the target parking position, the first self-position and learned target data, which is data representing the relative positional relationship, are associated and stored in a storage device, and if the first self-position and the learned target data are stored in association with each other, parking of the vehicle at the target parking position is assisted based on the first self-position and the learned target data.

[0006] According to the present invention, it is possible to determine whether or not there is a registered target parking position near the vehicle in a location where the detection accuracy of the vehicle's own position is low.

[0007] FIG. 1 is a diagram showing an example of a schematic configuration of a parking assistance device. FIG. 2 is an explanatory diagram of an example of a process for registering a target parking position. FIG. 3 is an explanatory diagram of an example of a process when parking assistance is being performed. FIG. 4 is a block diagram of an example of a functional configuration of the controller of FIG. 1. FIG. 5 is a schematic diagram of a situation in which the detection accuracy of the vehicle's own position decreases. FIG. 6 is a schematic diagram of a situation in which the detection accuracy of the vehicle's own position decreases. FIG. 7 is an explanatory diagram of a process when parking assistance is being performed to a target parking position. FIG. 8 is an explanatory diagram of a process when parking assistance is being performed to a target parking position. FIG. 9 is a flowchart of an example of a process for storing learned target data. FIG. 10 is a flowchart of an example of a process when parking assistance is being performed.

[0008] Referring to FIG. 1 , the host vehicle 1 is equipped with a parking assistance device 10 that assists in parking the host vehicle 1 at a target parking position. The parking assistance device 10 assists the host vehicle 1 in traveling along a target traveling trajectory from the current position of the host vehicle 1 to the target parking position. For example, the host vehicle 1 may be automatically driven to travel along the target traveling trajectory of the host vehicle 1 to the target parking position (i.e., control of all or part of the steering angle, driving force, and braking force of the host vehicle to automatically perform all or part of traveling along the target traveling trajectory of the host vehicle 1). Parking of the host vehicle 1 may be assisted by displaying the target traveling trajectory and the current position of the host vehicle 1 on a display device visible to the occupant of the host vehicle 1.

[0009] The positioning device 11 measures the vehicle's own position, which is the current location of the vehicle 1. The positioning device 11 may be equipped with a global navigation system (GNSS) receiver such as a global positioning system (GPS) receiver, or may measure the vehicle's own position by receiving position information from a wireless local area network (LAN) access point or a mobile telephone base station. Map data is stored in a map database (map DB) 12. The map data stored in the map DB 12 may be high-precision map data suitable for use as a map for autonomous driving, for example. The human-machine interface (HMI) 13 is an interface device that exchanges information between the parking assistance device 10 and an occupant. The shift switch (shift SW) 14 is a switch used by an occupant (e.g., a driver) of the vehicle 1 or the parking assistance device 10 to switch the shift position of the vehicle 1.

[0010] The external sensor 15 detects objects within a predetermined distance range from the host vehicle 1. The external sensor 15 detects the surrounding environment of the host vehicle 1, such as the relative position of the host vehicle 1 and an object present around the host vehicle 1, the distance between the host vehicle 1 and the object, and the direction in which the object is present. The external sensor 15 may include, for example, a camera that captures the surrounding environment of the host vehicle 1. In the following description, the camera included in the external sensor 15 will be simply referred to as a "camera." The external sensor 15 may include a distance measuring device such as a laser range finder, radar, or LiDAR. The vehicle sensor 16 detects various information (vehicle information) about the host vehicle 1. The vehicle sensor 16 may include, for example, a vehicle speed sensor, a wheel speed sensor, a three-axis acceleration sensor, a steering angle sensor, a turning angle sensor, a gyro sensor, and a yaw rate sensor.

[0011] The controller 17 is an electronic control unit that performs parking assistance control. The controller 17 includes a processor 20 and peripheral components such as a storage device 21. The processor 20 may be, for example, a CPU or an MPU. The storage device 21 may include a semiconductor storage device, a magnetic storage device, an optical storage device, or the like. The functions of the controller 17 are realized, for example, by the processor 20 executing a computer program stored in the storage device 21. The steering actuator 19a controls the steering direction and steering amount of the steering mechanism of the host vehicle 1 in response to a control signal from the controller 17. The accelerator actuator 19b controls the accelerator opening of the drive device, which is an engine or a drive motor, in response to a control signal from the controller 17. The brake actuator 19c activates a braking device in response to a control signal from the controller 17.

[0012] Next, parking assistance control by the parking assistance device 10 will be described. When using parking assistance by the parking assistance device 10, a target parking position where the vehicle 1 should be parked is registered in the parking assistance device 10. Specifically, targets present around the target parking position are extracted and stored in advance in the storage device 21. In the following description, targets around the target parking position stored in the storage device 21 will be referred to as "learned targets." FIG. 2A is an explanatory diagram of an example of a process for registering a target parking position, with circles representing learned targets. When registering a target parking position 30 in the parking assistance device 10, the occupant performs an operation to instruct registration of the target parking position 30 (hereinafter, sometimes referred to as a "registration operation"). The registration operation may be, for example, operation of a "parking position registration switch" provided in the HMI 13.

[0013] For example, when the vehicle 1 is located near the target parking position 30 (for example, when the occupant manually parks the vehicle 1 at the target parking position 30), the parking assistance device 10 detects targets around the vehicle 1 using the external sensor 15 and stores the targets as learned targets. For example, targets may be detected from a surrounding image obtained by capturing an image of the surroundings of the vehicle 1 with a camera. Targets around the vehicle 1 may also be detected using a distance measuring device. The parking assistance device 10 stores learned target data related to the learned targets in the storage device 21. For example, the learned target data includes data representing the feature amounts of the learned targets (hereinafter referred to as "feature amount data"), data on the relative positional relationship between the learned targets and the target parking position (hereinafter referred to as "relative position data"), and coordinate data of the target parking position 30 in a coordinate system (hereinafter referred to as "map coordinate system") that uses a fixed point as the reference point (hereinafter referred to as "target parking position coordinate data").

[0014] As the relative position data, for example, the relative position of the learned target object with respect to the target parking position 30 may be stored. For example, the parking assistance device 10 can acquire the position of the learned target detected when the host vehicle 1 is located at the target parking position 30 as the relative position of the learned target with respect to the target parking position 30. The coordinates of the learned target and the target parking position 30 in a map coordinate system may be stored. As the target parking position coordinate data, the host vehicle 1's own position when the host vehicle 1 is located at the target parking position 30 may be stored. In this case, if the detection accuracy of the positioning device 11 is equal to or higher than a predetermined accuracy, the host vehicle 1's own position measured by the positioning device 11 may be stored, and if the detection accuracy of the positioning device 11 is less than the predetermined accuracy, the host vehicle 1's own position estimated by odometry such as dead reckoning may be stored.

[0015] 2B is an explanatory diagram of an example of processing when parking assistance is performed. The parking assistance device 10 starts parking assistance for the host vehicle 1 when the host vehicle 1 is positioned near a registered target parking position 30 and an occupant performs an operation (hereinafter sometimes referred to as an "activation operation") to instruct activation of parking assistance control of the host vehicle 1 toward the target parking position 30. The activation operation may be, for example, an operation of a "parking assistance activation switch" provided in the HMI 13, or a shift operation for switching between forward and reverse movement of the host vehicle 1.

[0016] The parking assistance device 10 extracts targets around the host vehicle 1 using the external sensor 15. In the following description, targets around the host vehicle 1 extracted when parking assistance is performed are referred to as "surrounding targets." In FIG. 2B, triangular plots represent surrounding targets. The parking assistance device 10 matches the learned targets with the surrounding targets and associates identical feature points. Then, based on the relative positional relationship between the host vehicle 1 and the surrounding targets detected when parking assistance is performed, and the relative positional relationship between the learned targets associated with the surrounding targets and the target parking position 30, the parking assistance device 10 calculates the relative position of the host vehicle 1 with respect to the target parking position 30. For example, the parking assistance device 10 calculates the position of the target parking position 30 in a coordinate system based on the current position of the host vehicle 1 (hereinafter referred to as the "vehicle coordinate system"). In addition, when the coordinates of the learned targets and the target parking position 30 on the map coordinate system are stored in the storage device 21, the coordinates of the target parking position 30 on the map coordinate system may be converted into coordinates on the vehicle coordinate system based on the positions of the surrounding targets detected when parking assistance is performed and the positions of the learned targets in the map coordinate system. The own position of the vehicle 1 on the map coordinate system may be obtained based on the positions of the surrounding targets detected when parking assistance is performed and the positions of the learned targets in the map coordinate system, and the relative position of the vehicle 1 with respect to the target parking position 30 may be calculated from the difference between the coordinates of the vehicle 1 and the coordinates of the target parking position 30 in the map coordinate system.

[0017] The parking assistance device 10 calculates a target driving trajectory 33 from the current position 32 of the vehicle 1 to the target parking position 30 based on the relative position of the vehicle 1 with respect to the target parking position 30. The parking assistance device 10 performs parking assistance control of the vehicle 1 based on the calculated target driving trajectory 33.

[0018] The functional configuration of the controller 17 will be described in detail below with reference to FIG. 3 . When the HMI control unit 40 detects an operation by the occupant to register the target parking position 30, the HMI control unit 40 outputs a map generation command to the map generation unit 45 to store the learned target data in the storage device 21. When the HMI control unit 40 detects an operation to activate parking assist control for the registered target parking position 30, the HMI control unit 40 outputs a control start command to the parking assist control unit 41 to start parking assist control for the target parking position 30. The image conversion unit 42 converts the images captured by the camera into overhead images viewed from a virtual viewpoint directly above the vehicle 1. The image conversion unit 42 converts the captured images into overhead images at predetermined intervals and accumulates the converted overhead images along the driving route of the vehicle 1 to generate a surrounding image, which is an image of the area surrounding the vehicle 1.

[0019] The self-position calculation unit 43 calculates the current position of the vehicle 1 on a map coordinate system as its own position using odometry (e.g., dead reckoning) based on vehicle information output from the vehicle sensor 16. The self-position calculation unit 43 corrects the calculation result of the self-position based on the detection result of the self-position by the positioning device 11. The self-position calculation unit 43 estimates the detection accuracy of the positioning device 11. For example, if the positioning device 11 is equipped with a GNSS receiver, the self-position calculation unit 43 may estimate the detection accuracy of the positioning device 11 based on the number of captured navigation satellites. If the positioning device 11 performs positioning based on position information from wireless LAN access points or mobile telephone base stations, the self-position calculation unit 43 may estimate the detection accuracy of the positioning device 11 based on the number of captured wireless LAN access points or mobile telephone base stations or the reception strength of the position information. The map generation unit 45 and matching unit 47 described below may also estimate the detection accuracy of the positioning device 11 using a similar method. The parking assistance device 10 may detect the own position of the vehicle 1 by using high-precision map data instead of or in addition to the positioning device 11. For example, the parking assistance device 10 may detect targets around the vehicle 1 using the external sensor 15 and detect the own position of the vehicle 1 by map matching between the detected targets and high-precision map data. In this case, the detection accuracy of positioning based on high-precision map data may be estimated based on the accuracy of map matching (e.g., matching error).

[0020] The target detection unit 44 detects targets from the surrounding image output from the image conversion unit 42. The target detection unit 44 may detect the positions of feature points of the targets and their image feature quantities as target data. The target detection unit 44 outputs the positions of the detected feature points and the image feature quantities to the map generation unit 45 and the matching unit 47. Synchronously with the target detection, the map generation unit 45 outputs the vehicle's own position acquired from the vehicle's own position calculation unit 43 to the map generation unit 45 and the matching unit 47. When the map generation unit 45 receives a map generation command from the HMI control unit 40 (i.e., when the target parking position 30 is registered), the map generation unit 45 generates learned target data and stores it in the storage device 21 as map data 46. For example, the map generation unit 45 receives the target data and the vehicle's own position on the map coordinate system synchronized with the target data from the target detection unit 44. The map generation unit 45 acquires position information of the target parking position 30 in the map coordinate system. When the vehicle 1 is located at the target parking position 30, the vehicle's own position calculated by the vehicle's own position calculation unit 43 may be acquired as position information of the target parking position 30. The map generation unit 45 generates relative position data based on the positions of feature points included in the target object data, the position information of the vehicle 1 synchronized therewith, and the position information of the target parking position 30. The map generation unit 45 also acquires feature amount data from the target object data output from the target object detection unit 44. The position information of the target parking position 30 is used as target parking position coordinate data. The learned target object data including the relative position data, feature amount data, and target parking position coordinate data is stored in the storage device 21 as map data 46.

[0021] When the parking assist control unit 41 receives a control start command from the HMI control unit 40, it outputs a parking position calculation command to the matching unit 47. The matching unit 47 receives the target data output from the target detection unit 44 as target data of surrounding targets, and, in synchronization with this, receives the own position of the host vehicle 1 in the map coordinate system. The matching unit 47 determines whether the host vehicle 1 is located near the registered target parking position 30 based on the target parking position coordinate data included in the learned target data stored in the storage device 21. The matching unit 47 may also compare feature amount data included in the learned target data stored in the storage device 21 with the target data of targets around the host vehicle 1 output from the target detection unit 44, and determine whether the host vehicle 1 is located within a range where targets that can match the learned target data near the target parking position 30 are detected. When the vehicle 1 is located near a registered target parking position 30 or when the vehicle 1 is located within a range where a target that can be matched to the learned target data is detected, the matching unit 47 matches the learned target with the surrounding target to associate targets with each other that have the same feature points. The matching unit 47 calculates the relative position of the vehicle 1 with respect to the target parking position 30 based on the relative positional relationship between the surrounding target and the vehicle 1 and the relative positional relationship between the learned target associated with the surrounding target and the target parking position 30. For example, the surrounding target is (x ｉ , y ｉ ) and the surrounding targets (x ｉ , y ｉ ) is the learned target associated with (x ｍｉ , y ｍｉ ) (i=1 to N). The matching unit 47 calculates the affine transformation matrix M ａｆｆｉｎｅ Calculate.

[0022]

[0023] The abutment 47 is a function of the position (targetx) of the target parking position 30 on the map coordinate system stored in the map data 46 according to the following equation: ｍ , target ｍ ) into a position (targetx, targety) in the vehicle coordinate system.

[0024]

[0025] The target trajectory generation unit 48 calculates a target driving trajectory and a target vehicle speed profile from the current position of the host vehicle 1 on the vehicle coordinate system to the target parking position 30. The steering control unit 49a controls the steering actuator 19a so that the host vehicle 1 drives along the target driving trajectory. The vehicle speed control unit 49b controls the accelerator actuator 19b and the brake actuator 19c so that the vehicle speed of the host vehicle 1 changes in accordance with the target vehicle speed profile. When the host vehicle 1 reaches the target parking position 30 and the parking assist control is completed, the parking assist control unit 41 activates the parking brake 18 and switches the shift position to the parking range (P range).

[0026] Next, a process for when the detection accuracy of the vehicle's own position decreases will be described. For example, when the positioning device 11 detects the vehicle's own position using a GNSS receiver, a wireless LAN access point, or the like, the detection accuracy of the vehicle's own position may decrease in an indoor parking lot (e.g., an underground parking lot). When the vehicle's own position is detected using high-precision map data, the detection accuracy of the vehicle's own position may decrease in a location where high-precision map data is not sufficiently available.

[0027] 4A and 4B are schematic diagrams illustrating a situation in which a target parking position 30 is stored in an indoor parking lot 50. In the example of Fig. 4A, the target parking position 30 in a parking space 53n in which the vehicle entered the indoor parking lot 50 from the entrance 51 and then parked along a relatively short travel trajectory 52S is stored, and in the example of Fig. 4B, the target parking position 30 in a parking space 53f in which the vehicle parked along a relatively long travel trajectory 52L is stored.

[0028] If the detection accuracy of the vehicle's own position by the positioning device 11 or high-precision map data is low, the vehicle's own position calculation unit 43 will be unable to correct the vehicle's own position calculated by odometry. Therefore, as the vehicle's travel distance increases, errors accumulate in the calculation results of the vehicle's own position, reducing the position accuracy of the target parking position 30 stored as target parking position coordinate data in the learned target data. Furthermore, the position accuracy of the vehicle's own position at the time of executing parking assist control also decreases. As a result, when executing parking assist control, the matching unit 47 may be unable to determine whether the vehicle 1 is located near the registered target parking position 30.

[0029] Therefore, when the map generation unit 45 determines that the self-location detection accuracy has changed from a state where it is equal to or greater than a predetermined accuracy to a state where it is less than the predetermined accuracy, it sets the self-location detected at the point where the detection accuracy changes to a state where it is less than the predetermined accuracy as the first self-location P1. For example, the self-location detected immediately before the self-location detection accuracy changes from a state where it is equal to or greater than the predetermined accuracy to a state where it is less than the predetermined accuracy may be set as the first self-location P1. For example, the self-location detected immediately before the self-location detection accuracy changes from a state where it is equal to or greater than the predetermined accuracy to a state where it is less than the predetermined accuracy may be temporarily stored as the first self-location P1.

[0030] After setting the first self-position P1, the map generation unit 45 determines whether to generate learned target data and store it in the storage device 21. For example, if the detection accuracy is less than the predetermined accuracy when the vehicle 1 is parked at the target parking position 30, the map generation unit 45 may associate information about the first self-position P1 with the learned target data and store it in the storage device 21. For example, the map generation unit 45 may determine whether the occupant performed a registration operation when the detection accuracy was less than a predetermined accuracy. If the map generation unit 45 determines to generate learned target data and store it in the storage device 21 when the detection accuracy is less than the predetermined accuracy, the map generation unit 45 associates information about the first self-position P1 with the learned target data and stores it in the storage device 21. For example, the map generation unit 45 may determine whether to generate learned target data and store it in the storage device 21 when the detection accuracy of the vehicle 1 at the first self-position P1 changes from a state where the detection accuracy is equal to or greater than the predetermined accuracy to a state where the detection accuracy is less than the predetermined accuracy and continues to be less than the predetermined accuracy. For example, the map generating unit 45 may determine whether the occupant has performed a registration operation in a situation where the detection accuracy continues to be less than a predetermined accuracy. If it is determined that learned target data should be generated and stored in the storage device 21 in a situation where the detection accuracy continues to be less than the predetermined accuracy, the map generating unit 45 may associate information about the first self-position P1 with the learned target data and store them in the storage device 21.

[0031] This allows learned target data of a target parking position 30 registered with a detection accuracy below a predetermined accuracy to be associated with position information (first self-position P1) detected with an accuracy equal to or higher than the predetermined accuracy and stored in the storage device 21. As a result, even in a location where the detection accuracy of the self-position is less than the predetermined accuracy, by checking whether the self-position of the vehicle 1 is near the first self-position P1, it is possible to determine whether a registered target parking position 30 is located near the self-position of the vehicle 1 and read the learned target data from the storage device 21. For example, a point where the detection accuracy of the self-position changes from a state where the detection accuracy is equal to or higher than the predetermined accuracy to a state where the detection accuracy is less than the predetermined accuracy is temporarily stored. When parking assist control is initiated, the learned target data of the registered target parking position 30 can be read by checking the stored point against the first self-position P1. Furthermore, for example, when multiple target parking positions 30 are registered in the storage device 21, it is possible to accurately select a target parking position 30 registered in a location where the detection accuracy of the self-position is less than the predetermined accuracy.

[0032] 5A and 5B are schematic diagrams illustrating a situation in which parking assist control for the target parking position 30 is performed after the target parking position 30 has been registered. The positioning device 11 detects the vehicle's own position (hereinafter, sometimes referred to as the "second own position") P2 of the vehicle 1 after the target parking position 30 has been registered. The second own position P2 may be detected using high-precision map data instead of or in addition to the positioning device 11. The range 54 indicated by the dashed line in FIGS. 5A and 5B indicates the range in which the distance from the first own position P1 is equal to or less than the first threshold value Dt1. When the distance between the second own position P2 and the first own position P1 is equal to or less than the first threshold value Dt1, the matching unit 47 reads out the learned target data stored in association with the first own position P1 from the storage device 21. This allows the vehicle 1 to check whether its own position is near the first own position P1, and read out the learned target data of the target parking position 30 registered in the indoor parking lot 50 from the memory device 21.

[0033] For example, the matching unit 47 may estimate the detection accuracy of the second self-position P2 and determine whether the detection accuracy has changed from a state where it is equal to or greater than a predetermined accuracy to a state where it is less than the predetermined accuracy. When the distance between the second self-position P2 detected immediately before the detection accuracy changes to an accuracy below the predetermined accuracy and the first self-position P1 becomes equal to or less than a first threshold Dt1, the matching unit 47 may read out the learned target data stored in association with the first self-position P1 from the storage device 21. For example, when the detection accuracy of the second self-position P2 changes from a state where it is equal to or greater than a predetermined accuracy to a state where it is less than the predetermined accuracy, the matching unit 47 may determine whether the first self-position P1 stored in the storage device 21 is within a range of the second self-position P2 detected immediately before the detection accuracy changed to an accuracy below the predetermined accuracy within the first threshold Dt1. That is, the matching unit 47 may identify the first self-position P1 that is within a range of the second self-position P2 within the first threshold Dt1. Subsequently, when a parking position calculation command is received (i.e., when the startup operation is accepted), the matching unit 47 may read out the learned target data stored in association with the identified first self-position P1 from the memory device 21.

[0034] For example, the matching unit 47 may temporarily store the second self-position P2 when the detection accuracy of the second self-position P2 changes from a state in which it is equal to or greater than a predetermined accuracy to a state in which it is less than the predetermined accuracy and the distance between the second self-position P2 detected immediately before the detection accuracy changes to an accuracy less than the predetermined accuracy and the first self-position P1 becomes equal to the first threshold value Dt1. After that, when the matching unit 47 receives a parking position calculation command, the matching unit 47 may read from the storage device 21 the learned target data stored in association with the first self-position P1 that is located within the range of the temporarily stored second self-position P2 within the first threshold value Dt1.

[0035] As described above, the self-position calculated by the self-position calculation unit 43 using odometry accumulates calculation errors as the traveling distance of the vehicle 1 increases. Therefore, even if the detection accuracy of the self-position by the positioning device 11 or high-precision map data falls below a predetermined accuracy and the calculation result of the self-position becomes unable to be corrected, the position accuracy of the self-position calculated by the self-position calculation unit 43 can be expected to be high before the traveling distance of the vehicle 1 increases. For example, in the situation shown in FIG. 5A , the traveling distance of the vehicle 1 from when the detection accuracy of the self-position falls below the predetermined accuracy to when the vehicle 1 approaches the registered target parking position 30 is short. Therefore, it is possible to accurately determine whether the vehicle 1 is sufficiently close to the target parking position 30 (i.e., whether the matching unit 47 can match surrounding targets with learned targets of the target parking position 30). On the other hand, in the situation shown in FIG. 5B , the traveling distance until approaching the target parking position 30 is long, and the position accuracy of the self-position calculated by the self-position calculation unit 43 decreases. Therefore, it is not possible to determine whether the vehicle 1 has approached the target parking position 30 sufficiently.

[0036] Therefore, the matching unit 47 may calculate the distance traveled by the host vehicle 1 after the detection accuracy of the second host position P2 changes from a state where it is equal to or greater than a predetermined accuracy to a state where it is less than the predetermined accuracy. If the calculated distance traveled is equal to or less than the second threshold value Dt2, the matching unit 47 may read out learned target data from the storage device 21 based on the host position of the host vehicle 1 calculated from the odometry by the host position calculation unit 43. For example, the matching unit 47 may compare the host position of the host vehicle 1 calculated from the odometry with the target parking position coordinate data of the learned target data stored in the storage device 21, and read out learned target data of a target parking position 30 near the host position of the host vehicle 1 from the storage device 21.

[0037] For example, the matching unit 47 determines whether the host vehicle 1 is located near the registered target parking position 30 by comparing the host vehicle 1's own position calculated from the odometry by the host vehicle position calculation unit 43 with the target parking position coordinate data of the learned target data stored in the storage device 21. When the host vehicle 1 is located near the registered target parking position 30 and a start-up operation by the occupant is accepted, the learned target data of the target parking position 30 near the host vehicle 1 is read from the storage device 21 and parking assistance for the host vehicle 1 is performed.

[0038] On the other hand, if the travel distance after the detection accuracy of the second self-position P2 falls below the predetermined accuracy exceeds the second threshold Dt2, learned target data of targets having feature quantities similar to the feature quantities of surrounding targets around the host vehicle 1 may be read from the storage device 21, among learned target data stored in association with the first self-position P1 within a distance range of the first threshold Dt1 from the second self-position P2 detected immediately before the detection accuracy changed to less than the predetermined accuracy. Specifically, the matching unit 47 compares the feature quantity data of the learned target 57 of the learned target data for the target parking position 30 stored in the storage device 21 in association with the first self-position P1 within a distance range of the first threshold Dt1 from the second self-position P2 with the feature quantities of the surrounding targets 56 detected around the host vehicle 1 when parking assistance is performed. Whether the host vehicle 1 is located near the target parking position 30 is determined based on whether the feature quantity data is similar to the feature quantity data of the surrounding targets. If there are multiple target parking positions 30 stored in the storage device 21 in association with the first self-position P1 within a distance range of the second self-position P2 equal to or less than the first threshold value Dt1, it is determined whether or not the vehicle 1 is located near the target parking position 30 for each of these multiple target parking positions 30. When it is determined that the vehicle 1 is located near the target parking position 30 and a start-up operation by the occupant is accepted, the learned target data for the target parking position 30 near the vehicle 1 is read from the storage device 21, and parking assistance for the vehicle 1 is performed.

[0039] 6 , in step S1, the positioning device 11 detects its own position. In step S2, the map generation unit 45 estimates the detection accuracy of its own position. If the detection accuracy is less than a predetermined accuracy (step S3: Y), the process proceeds to step S4. If the detection accuracy is equal to or greater than the predetermined accuracy (step S3: N), the process proceeds to step S7. In step S4, the map generation unit 45 determines whether the value of the first flag FLG1 is True. The first flag FLG1 is a determination value that is set to True or False in a predetermined step in the flowchart. For example, the value of FLG1 is False in step S6, and the value of FLG1 is True in step S7. If the value of the first flag FLG1 is True (step S4: Y), the process proceeds to step S5. If the value of the first flag FLG1 is False (step S4: N), the process proceeds to step S9.

[0040] In step S5, the map generation unit 45 temporarily stores the self-position detected in step S1 as a first self-position P1. In step S6, the map generation unit 45 sets the value of the first flag FLG1 to False. The process then proceeds to step S9. In step S7, the map generation unit 45 sets the value of the first flag FLG1 to True. In step S8, the map generation unit 45 erases the first self-position P1 stored in step S5. The process then proceeds to step S9.

[0041] In step S9, the HMI control unit 40 determines whether the occupant has performed a registration operation. If the occupant has performed a registration operation (step S9: Y), the process proceeds to step S10. If the occupant has not performed a registration operation (step S9: N), the process returns to step S1. In step S10, the target detection unit 44 detects targets around the target parking position 30. In step S11, the map generation unit 45 generates learned target data and stores it in the storage device 21. In step S12, the map generation unit 45 determines whether the value of the first flag FLG1 is False. If the value of the first flag FLG1 is False (step S12: Y), the process proceeds to step S13. If the value of the first flag FLG1 is True (step S12: N), the process ends. In step S13, the map generation unit 45 associates the information on the first self-position P1 temporarily stored in step S5 with the learned target data stored in step S11 and stores the information in the storage device 21. Thereafter, the processing ends.

[0042] 7 . In step S20, the positioning device 11 detects the second self-position P2. In step S21, the matching unit 47 estimates the detection accuracy of the second self-position P2. If the detection accuracy is less than a predetermined accuracy (step S22: Y), the process proceeds to step S23. If the detection accuracy is equal to or greater than the predetermined accuracy (step S22: N), the process proceeds to step S29. In step S23, the matching unit 47 determines whether the value of the second flag FLG2 is True. The second flag FLG2 is a determination value that is set to True or False in a predetermined step in the flowchart. For example, the value of FLG2 becomes False in step S28, and the value of FLG2 becomes True in step S29. If the value of the second flag FLG2 is True (step S23: Y), the process proceeds to step S24. If the value of the second flag FLG2 is False (step S23: N), the process proceeds to step S32.

[0043] In step S24, the matching unit 47 determines whether the distance between the second self-position P2 and the first self-position P1 is equal to or less than the first threshold Dt1. If the distance between the second self-position P2 and the first self-position P1 is equal to or less than the first threshold Dt1 (step S24: Y), the process proceeds to step S25. If the distance between the second self-position P2 and the first self-position P1 is not equal to or less than the first threshold Dt1 (step S24: N), the process proceeds to step S27. In step S25, the matching unit 47 temporarily stores the second self-position P2. In step S26, the matching unit 47 sets the value of the third flag FLG3 to True. The third flag FLG3 is a determination value that is set to True or False in a predetermined step in the flowchart. For example, the value of FLG3 is True in step S26, and the value of FLG3 is False in steps S27 and S31. The process then proceeds to step S28. In step S27, the matching unit 47 sets the value of the third flag FLG3 to False. The process then proceeds to step S28. In step S28, the matching unit 47 sets the value of the second flag FLG2 to False. The process then proceeds to step S32.

[0044] In step S29, the matching unit 47 sets the value of the second flag FLG2 to True. In step S30, the matching unit 47 erases the second self-position P2 previously stored in step S25. In step S31, the matching unit 47 sets the value of the third flag FLG3 to False. The process then proceeds to step S32. In step S32, the target detection unit 44 detects surrounding targets present around the host vehicle 1. In step S33, the HMI control unit 40 determines whether the occupant has performed an activation operation. If the occupant has performed an activation operation (step S33: Y), the process proceeds to step S34. If the occupant has not performed an activation operation (step S33: N), the process returns to step S20.

[0045] In step S34, the matching unit 47 determines whether the value of the second flag FLG2 is False. If the value of the second flag FLG2 is False (step S34: Y), the process proceeds to step S36. If the value of the second flag FLG2 is True (step S34: N), the process proceeds to step S35. In step S35, the matching unit 47 reads out learned target data for a registered target parking position 30 near the second self-position P2, which is the current position of the vehicle 1, from the storage device 21. Thereafter, the process proceeds to step S40. In step S36, the matching unit 47 determines whether the value of the third flag FLG3 is True. If the value of the third flag FLG3 is True (step S36: Y), the process proceeds to step S37. If the value of the third flag FLG3 is False (step S36: N), the process ends.

[0046] In step S37, the matching unit 47 determines whether the travel distance after the detection accuracy of the second self-position P2 falls below the predetermined accuracy is equal to or less than the second threshold Dt2. If the travel distance is equal to or less than the second threshold Dt2 (step S37: Y), the process proceeds to step S38. If the travel distance is not equal to or less than the second threshold Dt2 (step S37: N), the process proceeds to step S39. In step S38, the matching unit 47 reads learned target data from the storage device 21 based on the self-position calculated by the self-position calculation unit 43 using odometry. Then, the process proceeds to step S40. In step S39, the matching unit 47 reads learned target data of targets having feature quantities similar to the feature quantities of the surrounding targets from the learned target data stored in association with the first self-position P1 within a distance range equal to or less than the first threshold Dt1 from the second self-position P2 stored in step S25. Then, the process proceeds to step S40. In step S40, the matching unit 47 matches the surrounding targets with the learned target data to calculate the relative position of the vehicle 1 with respect to the target parking position 30. In step S41, the target trajectory generation unit 48 calculates a target driving trajectory and a target vehicle speed profile. In step S42, the steering control unit 49a and the vehicle speed control unit 49b control the steering actuator 19a, accelerator actuator 19b, and brake actuator 19c based on the target driving trajectory and the target vehicle speed profile. In step S43, when the parking assist control is completed, the parking assist control unit 41 activates the parking brake 18 and switches the shift position to P range. The processing then ends.

[0047] (Effects of the Embodiments) (1) According to the parking assistance method of claim 1, even in a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy, it is possible to determine whether there is a registered target parking position near the vehicle 1 and read out learned target data from the storage device. According to the parking assistance method of claim 2, even in a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy, it is possible to assist the vehicle 1 in parking at the target parking position using learned target data of the registered target parking position. According to the parking assistance method of claim 3, even in a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy, it is possible to assist the vehicle 1 in parking at the target parking position using learned target data of the registered target parking position. (2) According to the parking assistance method of claim 4, it is possible to read out learned target data from the storage device even if parking assistance control is started after the vehicle enters a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy. According to the parking assistance method of claim 5, it is possible to read out learned target data from the storage device even if parking assistance control is started after the vehicle enters a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy.

[0048] (3) According to the parking assistance method of claim 6, it is possible to efficiently read out learned target data from the storage device when the distance traveled after entering a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy is relatively short. (4) According to the parking assistance method of claim 7, it is possible to read out learned target data from the storage device even when the distance traveled after entering a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy is relatively long. (5) According to the parking assistance method of claim 8, it is possible to accurately select learned target data of a target parking position registered in a location where the detection accuracy of the vehicle's own position is less than a predetermined accuracy.

[0049] 1... Vehicle, 10... Parking assistance device, 17... Controller

Claims

1. A parking assistance method comprising: detecting a vehicle's own position; estimating the detection accuracy of the own position; setting the own position at a point where the detection accuracy changes from a state where it is equal to or greater than a predetermined accuracy to a state where it is less than the predetermined accuracy as a first own position; detecting a relative positional relationship between the target parking position and targets present around the target parking position when the vehicle is parked at the target parking position after the first own position is set; if the detection accuracy is less than the predetermined accuracy when the vehicle is stopped at the target parking position, associating the first own position with learned target data which is data representing the relative positional relationship and storing it in a storage device; and if the first own position and the learned target data are stored in association with each other, assisting the vehicle in parking at the target parking position based on the first own position and the learned target data.

2. Detecting a second self-position, which is the self-position of the host vehicle at a time later than the learning time point, which is the time point when the learned target data was stored; When the distance between the second self-position and the first self-position becomes equal to or less than a first threshold, reading out the learned target data stored in association with the first self-position from the storage device; Detecting the positions of surrounding targets, which are targets that exist around the host vehicle at a time later than the learning time point; Calculating a relative positional relationship between the target parking position and the current position of the host vehicle based on the learned target data and the positions of the surrounding targets; Calculating a driving trajectory from the current position of the host vehicle to the target parking position based on the relative positional relationship between the target parking position and the current position of the host vehicle; and Assisting the host vehicle in parking at the target parking position based on the driving trajectory.

3. The parking assistance method according to claim 2, characterized in that the detection accuracy of the second self-position is estimated, and when the detection accuracy of the second self-position changes from a state where it is equal to or greater than the specified accuracy to a state where it is less than the specified accuracy and the distance between the second self-position and the first self-position becomes equal to or less than the first threshold, the learned target data stored in association with the first self-position is read out from the storage device.

4. The parking assistance method according to claim 3, characterized in that, when the detection accuracy of the second self-position changes from a state where it is equal to or greater than the specified accuracy to a state where it is less than the specified accuracy, the first self-position that is within a range from the second self-position within the first threshold value is identified, and when an operation to instruct the detection of the target parking position is received from the occupant, the learned target data stored in association with the identified first self-position is read out from the storage device.

5. Detect a second self-position, which is the self-position of the host vehicle at a time point later than the learning time point at which the learned target object data was stored, and store the second self-position when the detection accuracy of the second self-position changes from a state where it is equal to or greater than the predetermined accuracy to a state where it is less than the predetermined accuracy and the distance between the second self-position and the first self-position becomes equal to or less than a first threshold value; when an operation instructing detection of the target parking position is received from the occupant, read out from the storage device the learned target object data stored in association with the first self-position that is within a distance range equal to or less than the first threshold value from the stored second self-position; detect the positions of surrounding targets that are targets present around the host vehicle at a time point later than the learning time point; calculate a relative positional relationship between the target parking position and the current position of the host vehicle based on the learned target object data and the positions of the surrounding targets; calculate a driving trajectory from the current position of the host vehicle to the target parking position based on the relative positional relationship between the target parking position and the current position of the host vehicle; 2. The parking assistance method according to claim 1, wherein the parking assistance step includes assisting the host vehicle to park at the target parking position based on the travel trajectory.

6. The parking assistance method described in claim 2, characterized in that the learned target data includes position data of the target parking position, the detection accuracy of the second self-position is estimated, and if the distance traveled by the vehicle after the detection accuracy of the second self-position changes from a state where it is equal to or greater than the specified accuracy to a state where it is less than the specified accuracy is equal to or less than a second threshold, the learned target data is read from the storage device based on the self-position of the vehicle estimated from the odometry of the vehicle.

7. The parking assistance method described in claim 2, characterized in that the learned target data includes data on the features of targets present around the target parking position, the detection accuracy of the second self-position is estimated, and if the distance traveled by the vehicle after the detection accuracy of the second self-position changes from a state where it is equal to or greater than the specified accuracy to a state where it is less than the specified accuracy is greater than a second threshold, the learned target data stored in association with the first self-position and having features similar to the features of the surrounding targets is read from the storage device.

8. A parking assistance method as described in any one of claims 2 to 7, characterized in that the learned target data of the plurality of target parking positions is stored in the storage device, and when the distance between the second self-position and the first self-position becomes equal to or less than a first threshold, the learned target data stored in association with the first self-position among the plurality of target parking positions is read out from the storage device.

9. A parking assistance device comprising: a storage device; and a controller that executes the following processes: a process of acquiring position information obtained by positioning the host vehicle's own position, which is its current position; a process of estimating the detection accuracy of the own position; a process of setting the host vehicle's own position at a point where the detection accuracy changes from a state where it is equal to or greater than a predetermined accuracy to a state where it is less than the predetermined accuracy as a first host position; a process of detecting the relative positional relationship between the target parking position and targets present around the target parking position when the host vehicle is parked at the target parking position after the first self-position is set; a process of associating the first self-position with learned target data, which is data representing the relative positional relationship, and storing them in the storage device when the first self-position and the learned target data are stored in association with each other; and a process of assisting the host vehicle in parking at the target parking position based on the first self-position and the learned target data when the first self-position and the learned target data are stored in association with each other.

Images