Parking assistance device and parking assistance method
The parking assistance device uses driving information from another vehicle to enable memory-based automatic parking in vehicles without a prior teaching drive, addressing the challenge of unfamiliar parking locations by determining feasibility and generating a parking route.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- PANASONIC AUTOMOTIVE SYST CO LTD
- Filing Date
- 2024-12-16
- Publication Date
- 2026-06-09
AI Technical Summary
Memory-type automatic parking systems cannot be executed in vehicles where the driver has not performed a teaching drive, such as when parking at unfamiliar locations for the first time.
A parking assistance device and method that utilizes driving information from another vehicle, including vehicle type and feature point information, to estimate the current location and control automatic parking, even in vehicles without a prior teaching drive.
Enables memory-based automatic parking in vehicles without a prior teaching drive by using driving information from another vehicle to determine feasibility and generate a parking route, ensuring successful parking at unfamiliar locations.
Smart Images

Figure 0007872340000001 
Figure 0007872340000002 
Figure 0007872340000003
Abstract
Description
Technical Field
[0001] The present disclosure relates to a parking assistance device and a parking assistance method.
Background Art
[0002] Conventionally, there is known a parking assistance technology for moving a vehicle by automatic driving when parking the vehicle. As an example, one of the parking assistance technologies is a technology that memorizes a driving route based on a teaching drive by a driver and performs parking assistance using the memorized driving route (hereinafter referred to as memory-type automatic parking). This technology is used, for example, when repeatedly parking at a fixed parking position such as a parking lot at the driver's home or workplace.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] However, in memory-type automatic parking, there is a problem that memory-type automatic parking cannot be executed in a vehicle in which the driver has not performed a teaching drive.
[0005] The present disclosure provides a parking assistance device and a parking assistance method capable of executing memory-type automatic parking even in a vehicle in which the user has not performed a teaching drive.
Means for Solving the Problems
[0006] The parking assistance device according to the present disclosure includes a reception unit, The judgment unit, a position estimation unit, and a control unit. The reception unit receives travel information obtained when another vehicle is parked in a parking space by the driving of a driver. And the vehicle type information of the other vehicles mentioned above The determination unit compares the vehicle type information of its own vehicle with the vehicle type information of the other vehicle. The position estimation unit The aforementionedThe current location information of the vehicle is estimated. Based on the driving information and the current location information, the control unit performs parking control to automatically park the vehicle in the parking space. The driving information includes the training route taken when the other vehicle parked in the parking space and first feature point information based on a first surrounding image taken by the other vehicle while it was training on the training route. The position estimation unit estimates the current location information of the vehicle based on the first feature point information based on the first surrounding image taken by the other vehicle while it was training on the training route and second feature point information based on a second surrounding image taken by the vehicle. If the vehicle type of the vehicle in question is the same as the vehicle type of the other vehicle, the control unit performs parking control to automatically park the vehicle in the parking space based on the driving information.
[0007] The parking assistance method disclosed herein is based on driving information obtained when the driver parks another vehicle in a parking space. And the vehicle type information of the other vehicles mentioned above signal, The vehicle type information of the own vehicle is compared with the vehicle type information of the other vehicle, The system estimates the current location of the vehicle and performs parking control to automatically park the vehicle in the parking space based on the driving information and the current location information. including, The driving information includes the training route when the other vehicle parked in the parking space, and first feature point information based on a first surrounding image taken by the other vehicle while it was driving along the training route. Based on the first feature point information based on the first surrounding image taken by the other vehicle while it was driving along the training route, and the second feature point information based on a second surrounding image taken by the own vehicle, the current position information of the own vehicle is estimated. Furthermore, if the vehicle type of the own vehicle and the vehicle type of the other vehicle are the same, the system performs parking control to automatically park the own vehicle in the parking space based on the driving information. . [Effects of the Invention]
[0008] According to the parking assistance device and parking assistance method described herein, memory-based automatic parking can be performed even in vehicles where the user has not performed a training drive. [Brief explanation of the drawing]
[0009] [Figure 1] Figure 1 is a block diagram showing an example of a vehicle configuration. [Figure 2] Figure 2 is a flowchart showing an example of parking assistance performed by the parking assistance device according to this embodiment. [Figure 3] Figure 3 shows an example of the hardware configuration of the computer included in the parking assistance device according to this embodiment. [Modes for carrying out the invention]
[0010] The embodiments will be described in detail below, with reference to the drawings as appropriate. However, unnecessary details may be omitted. For example, detailed explanations of already well-known matters or redundant explanations of substantially identical configurations may be omitted. This is to avoid the following explanation becoming unnecessarily verbose and to facilitate understanding by those skilled in the art. The accompanying drawings and the following explanation are provided to enable those skilled in the art to fully understand this disclosure and are not intended to limit the subject matter described in the claims.
[0011] (The circumstances leading to the acquisition of the embodiments of this disclosure) This document provides a detailed description of the parking assistance device described in Patent Document 1. The parking assistance device uses a sensor device to store reference data (e.g., driving path data) about the area around the parking space while the driver is parking the vehicle in the parking space. Furthermore, the parking assistance device stores the parking position reached by the vehicle and stores data about the parking position. When performing memory-type automatic parking, the parking assistance device generates a parking path based on the reference data and the vehicle's current position relative to the parking position. In other words, it acquires information such as the driving path during manual parking and assists in subsequent automatic parking by mimicking manual parking.
[0012] However, in the memory-type automatic parking described in Patent Document 1, memory-type automatic parking cannot be performed in vehicles where the driver has not performed a training drive. For example, in a scenario where a user goes to a friend's house for the first time and parks the vehicle in the friend's parking lot for the first time, the user has not performed a training drive in the friend's parking lot, and therefore memory-type automatic parking cannot be performed. The following embodiments describe a parking assistance device and a parking assistance method that enable memory-type automatic parking even in vehicles where the user has not performed a training drive.
[0013] (First embodiment) <Regarding the configuration of the parking assistance device 160> Figure 1 is a block diagram showing an example of the configuration of vehicle 100. Vehicle 100 includes an onboard camera 110, an onboard sensor 120, a steering actuator 130, an engine actuator 140, a brake actuator 150, and a parking assist device 160.
[0014] The on-board camera 110 includes a visible light camera. The vehicle 100 is equipped with a first on-board camera that images the area in front of the vehicle 100, a second on-board camera that images the area behind the vehicle 100, a third on-board camera that images the area to the left of the vehicle 100, and a fourth on-board camera that images the area to the right of the vehicle 100. Hereinafter, unless otherwise specified, the first, second, third, and fourth on-board cameras will simply be referred to as the on-board camera 110. As will be described in more detail later, the on-board camera 110 is used, for example, to detect feature points of objects present around the vehicle 100 and to estimate the current position of the vehicle 100 from the positional relationship between the vehicle 100 and the feature points. The on-board camera 110 outputs the captured image signal to the parking assist device 160. Note that the on-board camera 110 is not limited to a visible light camera, but may also be, for example, a CCD camera or a CMOS camera. Furthermore, the images captured may be still images or videos. Also, the on-board camera 110 may be a camera built into the vehicle 100, or it may be a camera of a drive recorder that is retrofitted to the vehicle 100. In addition, instead of the on-board camera 110, a LiDAR, radar, or ultrasonic sensor may be used as a sensor to estimate the current position of the vehicle 100.
[0015] The on-board sensors 120 include, for example, a steering angle sensor for detecting the steering angle, a yaw rate sensor for detecting the turning angular velocity of the vehicle 100, an acceleration sensor for detecting the acceleration acting on the vehicle 100 in the longitudinal direction, and a wheel speed sensor for measuring the rotational speed of the wheels. The on-board sensors 120 output the sensor information obtained through detection to the parking assist device 160.
[0016] The steering actuator 130 adjusts the steering angle of the vehicle 100 based on the output of the parking assistance device 160. The parking assistance device 160 controls the steering angle by transmitting a target steering angle to the steering actuator 130. The parking assistance device 160 controls the turning curvature during the running of the vehicle 100 by controlling the steering actuator 130. The engine actuator 140 adjusts the supply amounts of fuel and air to the engine based on the output of the parking assistance device 160. The brake actuator 150 adjusts the braking force of the wheels based on the output of the parking assistance device 160.
[0017] Next, the functions of the parking assistance device 160 of the present embodiment will be described. The parking assistance device 160 of the present embodiment receives the driving information obtained when another vehicle is parked in the parking space by the driver's driving, and uses the received driving information to perform parking assistance. Such parking assistance is effective in reducing the driver's parking effort when repeatedly parking at a fixed parking position, such as the driver's home garage, the contract parking position in an apartment building, or the specified parking position in a parking lot at the workplace.
[0018] As shown in FIG. 1, the parking assistance device 160 of the present embodiment includes a vehicle information unit 161, a reception unit 162, an extraction unit 163, a position estimation unit 164, a determination unit 165, a route generation unit 166, and a vehicle control unit 167.
[0019] The vehicle information unit 161 registers vehicle size information such as the vehicle length, vehicle height, and vehicle width of the host vehicle, and vehicle type information including the vehicle manufacturer and model. Further, the vehicle information unit 161 registers performance information indicating the vehicle performance including the minimum turning radius of the host vehicle (for example, the trajectory radius drawn when creeping at the maximum steering angle). The vehicle information unit 161 outputs the vehicle size information, vehicle type information, and performance information to the determination unit 165 described later.
[0020] The receiving unit 162 receives driving information obtained when the driver of another vehicle parks that vehicle in a parking space. The driving in which the driver moves the vehicle from the starting position to the target parking position in the parking space by manual driving is also called a "training drive." The driving information during the training drive is also called "training data." The training data includes information about the target parking position during the training drive, the size of the parking space at the target parking position during the training drive, the speed of the other vehicle during the training drive, the steering angle of the other vehicle during the training drive, the braking action of the other vehicle during the training drive, the driving path during the training drive (hereinafter also referred to as the "training path"), and feature point information extracted from the surrounding image of the parking space captured during the training drive. Here, the information about the driving path during the training drive includes information such as the position coordinates on the path, the path length, the minimum turning radius, and the turning point. Communication between the receiving unit 162 and the other vehicle may be configured to be performed via a network such as the Internet. Alternatively, communication between the vehicle and the other vehicle may be done via a server, wired communication may be used, or wireless communication may be used.
[0021] Furthermore, the receiving unit 162 receives vehicle size information such as the length, height, and width of other vehicles, vehicle type information including the manufacturer and model of other vehicles, and performance information indicating the vehicle performance including the minimum turning radius of other vehicles.
[0022] Furthermore, the memory unit of the other vehicle stores, as training data, the target parking position during the training run, the size of the parking space at the target parking location during the training run, the speed of the other vehicle during the training run, the steering angle of the other vehicle during the training run, the braking action of the other vehicle during the training run, the driving path during the training run, and feature point information extracted from images of the surrounding area of the parking space taken during the training run. In addition, the transmission unit of the other vehicle transmits this training data via a network such as the Internet. The training data may also include, for example, information on the presence or absence of obstacles around the parking space, and distance information between the other vehicle and obstacles. Furthermore, the transmission unit transmits vehicle size information such as the length, height, and width of the other vehicle, vehicle type information including the manufacturer and model of the other vehicle, and performance information indicating the vehicle performance including the minimum turning radius of the other vehicle.
[0023] The extraction unit 163 receives image signals captured by the in-vehicle camera 110. Furthermore, the extraction unit 163 extracts feature points from the surrounding images when the vehicle 100 is driving autonomously. The method used by the extraction unit 163 to extract feature points is not particularly limited, and any known method may be applied. For example, the extraction unit 163 may extract feature points using methods such as FAST (Features from Accelerated Segment Test) or ORB (Oriented FAST and Rotated BRIEF).
[0024] The position estimation unit 164 receives feature points extracted from the extraction unit 163 and feature points stored in the training data of other vehicles received by the receiving unit 162. The position estimation unit 164 compares the feature points extracted from the camera image of the on-board camera 110 with the feature points stored in the training data using pattern matching, feature search, etc. Then, the position estimation unit 164 randomly selects several feature points from the feature points extracted from the camera image of the on-board camera 110 that can be matched with the feature points stored in the training data, and estimates the current position of the vehicle 100 based on the positions of these feature points in the camera image and the three-dimensional positions of these feature points in real space.
[0025] The determination unit 165 compares the vehicle type information of its own vehicle obtained from the vehicle information unit 161 with the vehicle type information of other vehicles obtained from the receiving unit 162 to determine whether the vehicle type of its own vehicle and the vehicle type of the other vehicle are the same. Specifically, the determination unit 165 determines whether the manufacturers and models of the vehicles are the same. If the vehicle type of its own vehicle and the other vehicle are the same, the determination unit 165 determines that it is possible to park in the parking space and outputs a signal to the vehicle control unit 167 indicating that it is possible to park.
[0026] Furthermore, if the vehicle type of the vehicle itself is different from that of the other vehicle, the determination unit 165 compares the size of the parking space included in the training data with the size of the vehicle itself and determines whether the size of the vehicle is less than or equal to the size of the parking space. If the size of the vehicle is less than or equal to the size of the parking space, the determination unit 165 determines that parking is possible in the parking space and outputs a signal to the vehicle control unit 167 indicating that parking is possible. Alternatively, if the vehicle type of the vehicle itself is different from that of the other vehicle, the determination unit 165 may compare the size of the other vehicle obtained from the receiving unit 162 with the size of the vehicle itself and determine that parking is possible in the parking space if the size of the vehicle is less than or equal to the size of the other vehicle. If the size of the vehicle is less than or equal to the size of the other vehicle, the determination unit 165 determines that parking is possible in the parking space and outputs a signal to the vehicle control unit 167 indicating that parking is possible.
[0027] Furthermore, the determination unit 165 determines whether it is possible to control the parking of the vehicle along the teacher route. Specifically, the determination unit 165 compares the minimum turning radius of the vehicle with the minimum turning radius of the route present in the teacher route. If the minimum turning radius of the vehicle is less than or equal to the minimum turning radius of the teacher route, the determination unit 165 determines that parking is possible and outputs a signal to the vehicle control unit 167 indicating that parking assistance is possible. Also, if the minimum turning radius of the vehicle is greater than the minimum turning radius of the teacher route, the determination unit 165 determines that parking assistance along the teacher route is not possible and outputs a signal to the route generation unit 166 to generate the first parking route described later. In addition, the determination unit 165 may also compare the minimum turning radius of the vehicle with the minimum turning radius of other vehicles and determine that parking is possible if the minimum turning radius of the vehicle is less than or equal to the minimum turning radius of other vehicles. Furthermore, the determination unit 165 may determine that parking is possible if the size of the vehicle is less than or equal to the size of the parking space and the minimum turning radius of the vehicle is less than or equal to the minimum turning radius of the training route.
[0028] Furthermore, the determination unit 165 determines whether it is possible to generate a first parking route from the vehicle 100's current position to the target parking position. For example, the determination unit 165 determines that it is possible to generate a first parking route when the route generation unit 166, which has received a signal for generating the first parking route (described later), outputs the first parking route to the vehicle control unit 167.
[0029] When the route generation unit 166 receives a signal from the determination unit 165 for generating a first parking route, it generates a first parking route from the current position of the vehicle 100 to the target parking position. More specifically, the route generation unit 166 generates the first parking route based on information about the target parking position included in the training data, information about the current position of the vehicle 100, information about the presence or absence of obstacles around the parking space, vehicle size information, and performance information. Here, when generating the first parking route, the route generation unit 166 does not use information about the driving route during training driving, such as position coordinates on the route, route length, minimum turning radius, and turning positions, which are included in the training data. The route generation unit 166 transmits the generated first parking route to the vehicle control unit 167. If the route generation unit 166 has been able to generate the first parking route, it may output a signal to the determination unit 165 indicating that the first parking route can be generated. If the route generation unit 166 is unable to generate a first parking route, it may output a signal to the determination unit 165 indicating that it is unable to generate a first parking route.
[0030] The vehicle control unit 167 controls the engine actuator 140, the brake actuator 150, and the steering actuator 130. In other words, the vehicle control unit 167 controls the steering, braking, and acceleration / deceleration of the vehicle 100 to control parking. When the vehicle control unit 167 receives a signal from the determination unit 165 indicating that parking is possible, it controls parking to the target parking position in the parking space based on the training data. Furthermore, if the vehicle 100 deviates from the training path, the vehicle control unit 167 uses feedback control to move the vehicle 100 back to the driving path. For example, the vehicle control unit 167 estimates the difference between the position of the vehicle 100 and the training path based on the current position of the vehicle 100 estimated by the estimation unit, and drives the vehicle 100 to minimize this difference. The reason for performing feedback control is that the position of the vehicle 100 when automatic parking is started may not match the initial position of the training path. The vehicle control unit 167 may also change the training path of the vehicle 100 based on the training data. For example, if an obstacle exists near the training path, the vehicle control unit 167 may temporarily stop the vehicle 100 or modify the driving path to move away from the obstacle. Also, if the vehicle control unit 167 detects an obstacle using the onboard camera 110 or ultrasonic sensor during parking control, it may modify the driving path to include an avoidance path to avoid the detected obstacle. Here, the avoidance path may, for example, be a path that goes around the obstacle from its vicinity and rejoins the driving path.
[0031] Furthermore, when the vehicle control unit 167 receives the first parking route from the route generation unit 166, it performs parking control along the first parking route.
[0032] Next, the flow of the parking assistance process performed by the parking assistance device 160 of this embodiment, configured as described above, will be explained. Figure 2 is a flowchart showing an example of parking assistance performed by the parking assistance device 160 according to this embodiment.
[0033] First, the receiving unit 162 receives driving information obtained when the driver of another vehicle parks that vehicle in a parking space (S300). In addition to the driving information, the receiving unit 162 also receives vehicle size information, vehicle type information, and performance information.
[0034] The determination unit 165 then compares the vehicle type information of its own vehicle with the vehicle type information of the other vehicle to determine whether the vehicle type of its own vehicle and the vehicle type of the other vehicle are the same. If the vehicle type of its own vehicle and the vehicle type of the other vehicle are the same (Yes in S310), the determination unit 165 determines that parking is possible in the parking space and outputs a signal to the vehicle control unit 167 indicating that parking is possible.
[0035] When the vehicle control unit 167 receives a signal from the determination unit 165 indicating that parking is possible, it controls the vehicle to park at the target parking position in the parking space based on the training data (S370). The parking assistance device 160 is also equipped with a notification unit, which may notify the user that memory-type automatic parking will be performed. The notification unit may, for example, notify the user by voice with a message such as "Memory-type automatic parking is available." Alternatively, the notification unit may notify the user by displaying a message such as "Memory-type automatic parking is available" and the training route on the display unit.
[0036] If the vehicle and the other vehicle are not of the same type (No in S310), the determination unit 165 compares the size of the parking space included in the training data with the size of the vehicle and determines whether the size of the vehicle is less than or equal to the size of the parking space.
[0037] If the size of the vehicle is not less than or equal to the size of the parking space (No in S320), the determination unit 165 determines that parking in the parking space is impossible and abandons automatic parking (S330). The notification unit may also notify the user that automatic parking is impossible and the reason why automatic parking was deemed impossible when automatic parking is abandoned. For example, if automatic parking is abandoned, the notification unit may notify the user by voice with a message such as, "Automatic parking cannot be performed because the parking space is smaller than vehicle 100." Alternatively, the notification unit may notify the user by displaying a message such as, "Automatic parking cannot be performed because the parking space is smaller than vehicle 100." In S310, the determination unit 165 may also compare the size of the vehicle with the size of the other vehicle obtained from the receiving unit 162 and determine whether the size of the vehicle is less than or equal to the size of the other vehicle. In this case, the determination unit 165 determines that parking is possible in the parking space if the size of its own vehicle is less than or equal to the size of the other vehicle (corresponding to the Yes process in S320 described later), and determines that parking is impossible in the parking space if the size of its own vehicle is not less than or equal to the size of the other vehicle, and abandons automatic parking (corresponding to No in S320 and the process in S330).
[0038] If the size of the vehicle is less than or equal to the size of the parking space (Yes in S320), the determination unit 165 determines whether it is possible to control the vehicle to park along the teacher path (S340).
[0039] Specifically, the determination unit 165 compares the minimum turning radius of its own vehicle with the minimum turning radius of the paths present in the training route. The determination unit 165 determines that parking is possible if the minimum turning radius of its own vehicle is less than or equal to the minimum turning radius of the training route. Alternatively, the determination unit 165 may compare the minimum turning radius of its own vehicle with the minimum turning radius of other vehicles and determine that parking is possible if the minimum turning radius of its own vehicle is less than or equal to the minimum turning radius of other vehicles. Furthermore, the determination unit 165 may determine that parking is possible if the size of its own vehicle is less than or equal to the size of the parking space AND the minimum turning radius of its own vehicle is less than or equal to the minimum turning radius of the training route.
[0040] If it is possible to control the vehicle to park along the training route (Yes in S340), the determination unit 165 outputs a signal to the vehicle control unit 167 indicating that parking is possible. When the vehicle control unit 167 receives a signal from the determination unit 165 indicating that parking is possible, it controls the vehicle to park at the target parking position in the parking space based on the training data (S370).
[0041] If the vehicle cannot be controlled to park along the designated path (No in S340), the determination unit 165 outputs a signal to the path generation unit 166 for generating a first parking path. When the path generation unit 166 receives a signal from the determination unit 165 for generating a first parking path, it generates a first parking path from the vehicle 100's current position to the target parking position. The path generation unit 166 outputs the generated first parking path to the vehicle control unit 167.
[0042] The determination unit 165 determines whether it is possible to generate a first parking route from the current position of the vehicle 100 to the target parking position (S350). For example, if the first parking route is output from the route generation unit 166 to the vehicle control unit 167, the determination unit 165 determines that it is possible to generate a first parking route.
[0043] If a first parking route can be generated (Yes in S350), the vehicle control unit 167 uses the first parking route to control parking at the target parking position in the parking space (S360). In other words, if the vehicle control unit 167 receives the first parking route from the route generation unit 166 (Yes in S350), it uses the first parking route to control parking at the target parking position in the parking space. The notification unit may also notify the user that parking will be controlled using the first parking route. For example, the notification unit may notify the user by voice with a message such as, "Memory-type automatic parking cannot be performed. Do you want to perform parking using the first parking route?" Alternatively, the notification unit may notify the user by displaying a message such as, "Memory-type automatic parking cannot be performed. Do you want to perform parking using the first parking route?" along with the first parking route on the display unit.
[0044] If the first parking route cannot be generated (No in S350), the determination unit 165 determines that parking in the parking space is impossible and abandons automatic parking (S330). After S330, S360, or S370, the flow shown in Figure 2 ends.
[0045] (Effects and Benefits) The parking assistance device 160 according to this embodiment provides the following effects.
[0046] The parking assist device 160 includes a receiving unit 162 that receives driving information obtained when another vehicle is parked in a parking space by the driver, and a control unit that performs parking control to automatically park its own vehicle in the parking space based on the driving information. The driving information includes the training path when the vehicle is parked in the parking space and feature point information around the parking space. As a result, memory-based automatic parking can be performed even for vehicle 100 in which the user has not yet performed a training drive. More specifically, even in a scenario where the user goes to a friend's house for the first time and parks vehicle 100 in the friend's parking lot for the first time, the parking assist device 160 can perform memory-based automatic parking by acquiring training data.
[0047] The parking assist device 160 further includes a determination unit 165, and the receiving unit 162 further receives vehicle type information of other vehicles. The determination unit 165 compares the vehicle type information of the own vehicle with the vehicle type information of the other vehicle, and if the vehicle type of the own vehicle and the vehicle type of the other vehicle are the same, the control unit performs parking control to automatically park the own vehicle in the parking space based on the driving information. This makes it possible to appropriately determine whether or not memory-type automatic parking is possible before performing automatic parking, based on the vehicle size and vehicle performance.
[0048] The determination unit 165 determines whether the vehicle can park in the parking space if the vehicle type of the vehicle is different from that of the other vehicle. This allows for an appropriate determination of whether or not memory-based automatic parking is possible when the vehicle type of the vehicle is different from that of the other vehicle. For example, it prevents situations where, during memory-based automatic parking, the vehicle is unable to park in the parking space because its size is larger than that of the other vehicle.
[0049] The receiving unit 162 receives the size of the parking space, and the determination unit 165 determines that the vehicle can park in the parking space if the size of the vehicle is less than or equal to the size of the parking space. This prevents the situation from occurring during memory-type automatic parking where the vehicle is unable to park in the parking space because its size is larger than the parking space.
[0050] The determination unit 165 determines that parking is possible in the parking space if the size of its own vehicle is less than or equal to the size of other vehicles. This prevents the situation in which, when performing memory-type automatic parking, the vehicle's size becomes larger than the size of other vehicles and it is unable to park in the parking space midway through the automatic parking process.
[0051] The determination unit 165 determines whether it is possible to control the vehicle's parking along the teacher path. This allows for an appropriate determination of whether memory-based automatic parking is possible before performing automatic parking.
[0052] The determination unit 165 determines that parking control is possible for the vehicle if the vehicle's minimum turning radius is smaller than the minimum turning radius of the training route. This prevents a situation from occurring during memory-based automatic parking where the vehicle's minimum turning radius is larger than the training route's minimum turning radius, making it impossible to control the vehicle to park along the training route.
[0053] The determination unit 165 determines that parking control is possible for its own vehicle if its own vehicle's minimum turning radius is smaller than that of other vehicles. This prevents a situation from occurring during memory-based automatic parking where the vehicle's own minimum turning radius is larger than that of other vehicles, making it impossible to control the parking along the programmed path.
[0054] The system further includes a route generation unit 166. When the determination unit 165 determines that it is not possible to control the vehicle's parking along the teacher route, the route generation unit 166 generates a first parking route based on the location of the parking space. This allows the vehicle to automatically park in a parking space even when it is determined that memory-based automatic parking is difficult, by generating a new parking route to the parking space.
[0055] (modified version) The determination unit 165 may determine whether it is possible to generate a second parking route for controlling the parking of the vehicle based on the teacher route. Here, the determination unit 165 can make this determination based on information about the driving route during the teacher run, such as position coordinates on the route, route length, minimum turning radius, and turning points, which are included in the teacher data. For example, if the minimum turning radius of the vehicle is smaller than the minimum turning radius of the teacher route, it is determined that it is possible to generate a second parking route. The route generation unit 166 generates a second parking route based on information about the driving route during the teacher run, such as information about the target parking position, the current position of the vehicle 100, information about the presence or absence of obstacles around the parking space, vehicle size information, performance information, position coordinates on the route, route length, minimum turning radius, and turning points, which are included in the teacher data. Here, the second parking route is a route that follows the teacher route, but a part of the route may differ from the teacher route. For example, if the current position of vehicle 100 when automatic parking is initiated does not match the initial position of the training route, the route generation unit 166 estimates the difference between the current position of vehicle 100 and the training route based on the current position of vehicle 100, and generates a route for vehicle 100 to merge with the training route. In other words, in this case, the second parking route may include the training route and a route for vehicle 100 to merge with the training route from its current position.
[0056] Furthermore, in general, when driving manually, it is easier to move vehicle 100 out of the garage than to move it in. If such a memory method is used, even if the driver is not good at reversing vehicle 100 into the garage, a driving path for memory-based automatic parking can be generated by a training run in which the driver moves vehicle 100 forward to exit the garage. In this modified example, the case in which the driver moves vehicle 100 forward during the training run was explained as an example, but the driver may also move vehicle 100 in reverse during the training run.
[0057] In the parking assistance device 160 described in this embodiment, each block, such as the vehicle information unit 161, receiving unit 162, extraction unit 163, position estimation unit 164, determination unit 165, route generation unit 166, and vehicle control unit 167, may be individually integrated into a single chip using semiconductor devices such as LSIs, or they may be integrated into a single chip to include some or all of them.
[0058] The processing method performed by the parking assist device 160, the computer program that causes a computer to perform the processing method, and the computer-readable recording medium on which the program is recorded are included in the scope of this disclosure. Examples of computer-readable recording media include flexible disks, hard disks, CD-ROMs, MOs, DVDs, DVD-ROMs, DVD-RAMs, BDs (Blu-ray® Discs), and semiconductor memory.
[0059] Some or all of the processing of each functional block in this embodiment may be implemented by a computer program. Furthermore, each processing of this embodiment may be implemented by hardware, or by software (including cases where it is implemented together with an OS (operating system), middleware, or a predetermined library). Moreover, it may be implemented by a mixed processing of software and hardware.
[0060] Figure 3 shows an example of the hardware configuration of the computer 1000 included in the parking assistance device 160 according to this embodiment. The computer 1000 includes a CPU (Central Processing Unit) 1001, a ROM (Read Only Memory) 1002, a RAM (Random Access Memory) 1003, a storage device 1004 such as a hard disk drive or SSD (Solid State Drive), and a reader 1005 that reads information from the storage device. The above-mentioned parts are connected by a bus 1006. The reader 1005 reads a program from the storage device that records a program for realizing the functions of the above-mentioned parts, and stores it in the storage device 1004. The CPU 1001 copies the program stored in the storage device 1004 to the RAM 1003, and sequentially reads and executes the instructions contained in the program from the RAM 1003. This realizes the functions of the above-mentioned parts. Also, when executing a program, information obtained from the various processes described in each embodiment is stored in the RAM 1003 or the storage device 1004 and used as appropriate.
[0061] The computer program is not limited to one recorded on the above-mentioned recording medium, but may also be transmitted via telecommunication lines, wireless or wired communication lines, networks such as the Internet, etc. Furthermore, the execution order of the processing method according to this embodiment is not necessarily limited to the description of the above embodiment, and the execution order can be changed without departing from the gist of this disclosure. [Explanation of symbols]
[0062] 100 vehicles 110 In-car camera 120 Automotive Sensors 130 Steering Actuator 140 Engine Actuator 150 Brake Actuator 160 Parking assist system 161 Vehicle Information Department 162 Receiving Unit 163 Extraction part 164 Position estimation part 165 Judgment Department 166 Route generation unit 167 Vehicle Control Unit 1000 computers 1001 CPU 1002 ROM 1003 RAM 1004 Storage device 1005 Reader 1006 Bus
Claims
1. A receiving unit that receives driving information obtained when another vehicle is parked in a parking space by the driver, and vehicle type information of the other vehicle, A determination unit that compares the vehicle type information of its own vehicle with the vehicle type information of the other vehicle, A position estimation unit that estimates the current position information of the vehicle, The system includes a control unit that performs parking control to automatically park the vehicle in the parking space based on the aforementioned driving information and the aforementioned current location information, The aforementioned driving information includes the training route taken when the other vehicle parked in the parking space, and first feature point information based on a first surrounding image taken by the other vehicle while it was training along the training route. The position estimation unit estimates the current position information of the vehicle based on the first feature point information based on the first surrounding image captured by the other vehicle during the training run and the second feature point information based on the second surrounding image captured by the vehicle itself. If the vehicle type of the vehicle in question is the same as the vehicle type of the other vehicle, the control unit performs parking control to automatically park the vehicle in the parking space based on the driving information. Parking assist device.
2. The parking assistance device according to claim 1, wherein the determination unit determines whether the vehicle can be parked in the parking space when the vehicle type of the vehicle itself is different from the vehicle type of the other vehicle.
3. The receiving unit receives the size of the parking space, The determination unit determines that the vehicle can be parked in the parking space if the size of the vehicle is less than or equal to the size of the parking space. The parking assistance device according to claim 2.
4. The parking assistance device according to claim 2, wherein the determination unit determines that the vehicle can be parked in the parking space if the size of the vehicle is less than or equal to the size of the other vehicle.
5. The parking assistance device according to any one of claims 1 to 4, wherein the determination unit determines whether it is possible to control the parking of the vehicle along the teacher path.
6. The parking assistance device according to claim 5, wherein the determination unit determines that it is possible to control the parking of the vehicle when the minimum turning radius of the vehicle is less than or equal to the minimum turning radius of the teacher path.
7. The parking assistance device according to claim 5, wherein the determination unit determines that it is possible to control the parking of the vehicle when the minimum turning radius of the vehicle is less than or equal to the minimum turning radius of the other vehicle.
8. It further includes a path generation unit, If the determination unit determines that it is not possible to control the parking of the vehicle along the teacher path, the path generation unit generates a first parking path based on the location of the parking space. The parking assistance device according to claim 5.
9. The parking assistance device according to any one of claims 1 to 4, wherein the determination unit determines whether it is possible to generate a second parking path for controlling the parking of the vehicle based on the teacher path.
10. When the driver parks another vehicle in a parking space, the driving information obtained and the vehicle type information of the other vehicle are received. The vehicle type information of the own vehicle is compared with the vehicle type information of the other vehicle mentioned above. The current location information of the vehicle is estimated, This includes performing parking control to automatically park the vehicle in the parking space based on the aforementioned driving information and the aforementioned current location information, The aforementioned driving information includes the training route taken when the other vehicle parked in the parking space, and first feature point information based on a first surrounding image taken by the other vehicle while it was training along the training route. Based on the first feature point information derived from the first surrounding image captured by the other vehicle during the training run, and the second feature point information derived from the second surrounding image captured by the own vehicle, the current position information of the own vehicle is estimated. If the vehicle type of the said vehicle is the same as the vehicle type of the said other vehicle, the system performs parking control to automatically park the said vehicle in the parking space based on the said driving information. Parking assistance methods.