JP2022055774A - Parking support system, parking support device, parking support method, and program - Google Patents

Abstract

To improve the estimation accuracy of the shape of an obstacle.SOLUTION: A parking support system includes: a distance measurement section for acquiring distance information indicating a distance from a movable body to an obstacle by using the reflection of ultrasonic waves; a detection section for detecting a division line showing a parking area; an estimation section for estimating the extension direction of the obstacle on the basis of the distance information and a predetermined direction when the division line is not detected, and for estimating the extension direction of the obstacle on the basis of the distance information and the division line when the division line is detected; and a generation section for generating the movement path of the movable body on the basis of the extension direction estimated by the estimation section.SELECTED DRAWING: Figure 3

Description

The present invention relates to a parking support system, a parking support device, a parking support method, and a program.

In a parking support system that supports the movement of a vehicle when the vehicle is parked in a parking area, the distance from the vehicle to the obstacle is used as a means for detecting an obstacle existing around the vehicle by using an ultrasonic reflected wave. Ultrasonic sensors may be used to measure.

Japanese Patent No. 6479130

When providing parking assistance, it is necessary to estimate the shape of obstacles (for example, other vehicles parked in the adjacent parking area) existing around the target parking area. In particular, it is important to accurately estimate the extension direction of the obstacle (for example, the direction along the side surface of another vehicle) in order to improve the reliability and efficiency of the control. However, when a sensor having a relatively narrow detectable range such as an ultrasonic sensor is used, it is difficult to accurately estimate the shape of a portion far away from the own vehicle.

Therefore, one of the problems of the present invention is to provide a parking support system, a parking support device, a parking support method, and a program capable of improving the estimation accuracy of the shape of an obstacle.

One embodiment of the present invention includes a ranging unit that acquires distance information indicating the distance from a moving object to an obstacle by using the reflection of ultrasonic waves, a detecting unit that detects a lane marking indicating a parking area, and a lane marking. If is not detected, the extension direction of the obstacle is estimated based on the distance information and the predetermined direction, and if the lane marking is detected, the extension direction of the obstacle is estimated based on the distance information and the lane marking. It is a parking support system including an estimation unit and a generation unit that generates a movement path of a moving object based on an extension direction estimated by the estimation unit.

According to the above configuration, when the lane marking is detected by the detection unit, the extension direction of the obstacle is estimated based on the lane marking. As a result, even when an obstacle is detected using ultrasonic waves, the estimation accuracy in the extension direction of the obstacle can be improved, and the reliability and efficiency of the parking support control can be improved. ..

In addition, the parking support system has a calculation unit that calculates the frontage distance that a moving body can pass when entering the parking area based on the extension direction estimated based on the lane marking when the lane marking is detected. Further may be provided.

As a result, the frontage distance can be calculated accurately, and the reliability and efficiency of the parking support control can be improved.

Further, the parking support system performs a process for integrating a plurality of obstacles into one obstacle based on the lane marking when a plurality of obstacles are detected based on the distance information and a lane marking is detected. Further may be provided with an integration unit to perform.

As a result, the recognition accuracy of obstacles can be improved, and the reliability and efficiency of parking support control can be improved.

Further, another embodiment of the present invention is a moving body when the moving body is parked in a parking area based on the distance information indicating the distance from the moving body to the obstacle acquired by utilizing the reflection of ultrasonic waves. It is a parking support device that performs processing to support movement, and when a lane marking indicating a parking area is not detected, the extension direction of the obstacle is estimated based on the distance information and a predetermined direction, and the lane marking is used. It is provided with an estimation unit that estimates the extension direction based on the distance information and the lane marking when is detected, and a generation unit that generates a movement path of the moving object based on the extension direction estimated by the estimation unit. be.

Further, another embodiment of the present invention includes a step of acquiring distance information indicating a distance from a moving body to an obstacle by using reflection of ultrasonic waves, a step of detecting a lane marking indicating a parking area, and a lane marking. When is not detected, the process of estimating the extension direction of the obstacle based on the distance information and the predetermined direction, and when the lane marking is detected, the extension direction is estimated based on the distance information and the lane marking. It is a parking support method including a step and a step of generating a movement path of a moving body based on an estimated extension direction.

Further, another embodiment of the present invention is based on the distance information indicating the distance from the moving body to the obstacle acquired by utilizing the reflection of ultrasonic waves, and the movement of the moving body when the moving body is parked in the parking area. When the lane marking indicating the parking area is not detected by the computer that performs the processing to support the lane marking, the lane marking is detected and the processing for estimating the extension direction of the obstacle based on the distance information and the predetermined direction. In this case, the process of estimating the extension direction based on the distance information and the lane marking and the process of generating the movement path of the moving body based on the estimated extension direction are executed.

FIG. 1 is a plan view showing a configuration of a vehicle equipped with a parking support system according to an embodiment. FIG. 2 is a block diagram showing a configuration of a parking support system according to an embodiment. FIG. 3 is a block diagram showing a functional configuration of the parking support system according to the embodiment. FIG. 4 is a diagram showing an example of a parking lot in which the parking support system according to the embodiment is used. FIG. 5 is a diagram showing an extension direction estimated when a lane marking is detected in the embodiment. FIG. 6 is a diagram showing an extension direction estimated when the lane marking is not detected in the embodiment. FIG. 7 is a flowchart showing processing in the parking support system according to the embodiment. FIG. 8 is a diagram showing a method of calculating the frontage distance according to the embodiment. FIG. 9 is a flowchart showing a process in the frontage distance calculation unit according to the embodiment. FIG. 10 is a diagram showing an example of a detection area that can be detected by an ultrasonic sensor when a vehicle passes through a parking area in the embodiment. FIG. 11 is a diagram showing an example of a detection area that can be detected by an ultrasonic sensor when a vehicle enters a parking area in the embodiment. FIG. 12 is a diagram showing an example of a state in which one obstacle is recognized as two obstacles in the embodiment. FIG. 13 is a diagram showing a process of integrating a plurality of recognition objects into one recognition object when a lane marking is detected in the embodiment. FIG. 14 is a flowchart showing a process in the obstacle integration unit according to the embodiment.

Hereinafter, exemplary embodiments of the present invention will be disclosed. The configurations of the embodiments shown below, as well as the actions, results, and effects produced by such configurations, are examples. The present invention can be realized by a configuration other than the configurations disclosed in the following embodiments, and at least one of various effects based on the basic configuration and derivative effects can be obtained. ..

FIG. 1 is a plan view showing a configuration of a vehicle 10 on which a parking support system according to an embodiment is mounted.

The vehicle 10 is an example of a moving body. The vehicle 10 may be, for example, a vehicle having an internal combustion engine as a drive source (internal combustion engine vehicle), a vehicle having an electric motor as a drive source (electric vehicle, fuel cell vehicle, etc.), or the like. It may be a vehicle (hybrid vehicle) whose drive source is both of the above. The vehicle 10 can be equipped with various transmission devices, and can be equipped with various devices (systems, parts, etc.) necessary for driving an internal combustion engine or an electric motor. The method, number, layout, and the like of the devices involved in driving the wheels 13 in the vehicle 10 can be set in various ways.

As shown in FIG. 1, the vehicle 10 includes a vehicle body 12, four wheels 13, and one or more (four in this embodiment) image pickup devices 14a, 14b, 14c, 14d, and one or more (this). In the embodiment, eight) ultrasonic sensors 16a, 16b, 16c, 16d, 16e, 16f, 16g, 16h, 16i, 16j, 16k, 16l are provided. When it is not necessary to distinguish between the image pickup devices 14a, 14b, 14c, and 14d, the image pickup device 14 is referred to as an image pickup device 14. When it is not necessary to distinguish between ultrasonic sensors 16a, 16b, 16c, 16d, 16e, 16f, 16g, 16h, 16i, 16j, 16k, 16l, it is referred to as an ultrasonic sensor 16.

The vehicle body 12 constitutes a passenger compartment in which an occupant rides. The vehicle body 12 accommodates or holds wheels 13, an image pickup device 14, an ultrasonic sensor 16, and the like.

The four wheels 13 are provided on the front, rear, left and right sides of the vehicle body 12. For example, the two wheels 13 on the front side function as steering wheels, and the two wheels 13 on the rear side function as drive wheels.

The image pickup device 14 is, for example, a digital camera having a built-in image pickup element such as a CCD (Charge Coupled Device) or a CIS (CMOS Image Sensor). The image pickup apparatus 14 outputs moving image or still image data including a plurality of frame images generated at a predetermined frame rate as image pickup data. Each of the image pickup devices 14 has a wide-angle lens or a fisheye lens, and can photograph, for example, a range of 140 ° to 190 ° in the horizontal direction. The optical axis of the image pickup apparatus 14 is set diagonally downward. Therefore, the image pickup device 14 outputs the image pickup data that images the periphery of the vehicle 10 including the surrounding road surface.

The image pickup apparatus 14 is provided on the outer peripheral portion of the vehicle body 12. For example, the image pickup apparatus 14a is provided at the center portion (for example, the front grille) in the left-right direction of the front end portion of the vehicle body 12. The image pickup device 14a generates a captured image of the periphery in front of the vehicle 10. The image pickup apparatus 14b is provided at the center portion in the left-right direction of the rear end portion of the vehicle body 12 (for example, around the back door switch). The image pickup device 14b generates a captured image of the periphery behind the vehicle 10. The image pickup apparatus 14c is provided at the center portion of the left end portion of the vehicle body 12 in the front-rear direction (for example, the left side mirror 12a). The image pickup apparatus 14c generates an image captured by capturing the left periphery of the vehicle 10. The image pickup apparatus 14d is provided at the center portion of the right end portion of the vehicle body 12 in the front-rear direction (for example, the side mirror 12b on the right side). The image pickup apparatus 14d generates an image of the right side of the vehicle 10 as an image.

The ultrasonic sensor 16 is provided on the outer peripheral portion of the vehicle 10, for example, an ultrasonic sensor that transmits ultrasonic waves as detection waves and receives reflected waves reflected by an object (obstacle) existing around the vehicle 10. (Sonar). The ultrasonic sensor 16 acquires (generates) distance information indicating the distance from the vehicle 10 to an obstacle existing around the vehicle 10. For example, the ultrasonic sensor 16 determines the time (TOF: Time Of Flight) from the transmission of the detected wave to the reception of the reflected wave as the distance information for specifying the presence / absence of an obstacle, the distance, the position, the movement, and the like. Get as.

Ultrasonic sensors 16a, 16b, 16c, 16d are also called side sonars and are provided on the left and right sides of the vehicle 10. The ultrasonic sensors 16e and 16f, also called corner sonars, are provided at the rear of the vehicle 10 (for example, near the corners of the vehicle 10) rather than the ultrasonic sensors 16a, 16b, 16c, 16d, and the ultrasonic sensors 16a, 16b, It is directed to the rear (for example, the outside of the rear) from 16c and 16d. The ultrasonic sensors 16g and 16h, also called corner sonars, are provided at the front of the vehicle 10 (for example, near the corners of the vehicle 10) rather than the ultrasonic sensors 16a, 16b, 16c and 16d, and are provided on the ultrasonic sensors 16a and 16b. , 16c, 16d are directed forward (eg, outside the front). The ultrasonic sensors 16i and 16j are also called rear sonars and are provided at the rear end of the vehicle 10. Ultrasonic sensors 16k and 16l, also called front sonars, are provided at the front end of the vehicle 10.

The ultrasonic sensor 16a is provided at a position on the front side of the left side surface of the vehicle 10. The ultrasonic sensor 16a is directed to the left. The ultrasonic sensor 16a acquires distance information regarding an obstacle existing in the detection region on the left side of the front side of the vehicle 10.

The ultrasonic sensor 16b is provided at a position on the rear side of the left side surface of the vehicle 10. The ultrasonic sensor 16b is directed to the left. The ultrasonic sensor 16b acquires distance information regarding an obstacle existing in the detection region on the left side of the rear side of the vehicle 10.

The ultrasonic sensor 16c is provided at a position on the front side of the right side surface of the vehicle 10. The ultrasonic sensor 16c is directed to the right. The ultrasonic sensor 16c acquires distance information regarding an obstacle existing in the detection region on the right side of the front side of the vehicle 10.

The ultrasonic sensor 16d is provided at a position on the rear side of the right side surface of the vehicle 10. The ultrasonic sensor 16d is directed to the right. The ultrasonic sensor 16d acquires distance information regarding an obstacle existing in the detection region on the right side of the rear side of the vehicle 10.

The ultrasonic sensor 16e is provided at a position on the left side of the rear end portion of the vehicle 10. The ultrasonic sensor 16e is directed to the left rear. The ultrasonic sensor 16e acquires distance information regarding an obstacle existing in the detection region on the left rear side of the vehicle 10.

The ultrasonic sensor 16f is provided at a position on the right side of the rear end portion of the vehicle 10. The ultrasonic sensor 16f is directed to the rear right. The ultrasonic sensor 16f acquires distance information regarding an obstacle existing in the detection region on the right rear side of the vehicle 10.

The ultrasonic sensor 16g is provided at a position on the left side of the front end portion of the vehicle 10. The ultrasonic sensor 16g is directed to the left front. The ultrasonic sensor 16g acquires distance information regarding an obstacle existing in the detection area on the left front side of the vehicle 10.

The ultrasonic sensor 16h is provided at a position on the right side of the front end portion of the vehicle 10. The ultrasonic sensor 16h is directed to the front right. The ultrasonic sensor 16h acquires distance information regarding an obstacle existing in the detection region on the right front side of the vehicle 10.

The ultrasonic sensors 16i and 16j are provided at the rear end of the vehicle 10 so as to be spaced apart from each other in the left-right direction between the ultrasonic sensors 16e and 16f. The ultrasonic sensors 16i and 16j are directed to the rear. Ultrasonic sensors 16i and 16j acquire distance information regarding obstacles existing in the detection region behind the vehicle 10.

The ultrasonic sensors 16k and 16l are provided at the front end of the vehicle 10 at a distance in the left-right direction between the ultrasonic sensors 16g and 16h. The ultrasonic sensors 16k and 16l are directed forward. Ultrasonic sensors 16k and 16l acquire distance information regarding obstacles existing in the detection region in front of the vehicle 10.

FIG. 2 is a block diagram showing a configuration of the parking support system 20 according to the embodiment.

The parking support system 20 is mounted on the vehicle 10 and supports the movement of the vehicle 10 when the vehicle 10 is parked in a predetermined parking area by executing automatic driving (including a partial automatic driving).

As shown in FIG. 2, the parking support system 20 includes an image pickup device 14, an ultrasonic sensor 16, a braking system 22, an acceleration system 24, a steering system 26, a speed change system 28, a vehicle speed sensor 30, and a monitor. The device 32, the parking support device 34, and the in-vehicle network 36 are provided.

The braking system 22 controls the deceleration of the vehicle 10. The braking system 22 includes a braking unit 40, a braking control unit 42, and a braking unit sensor 44.

The braking unit 40 includes, for example, a brake, a brake pedal, and the like, and is a device for decelerating the vehicle 10.

The braking control unit 42 is, for example, a computer such as a microcomputer having a hardware processor such as a CPU (Central Processing Unit). The braking control unit 42 controls the braking unit 40 based on the instruction from the parking support device 34, and controls the deceleration of the vehicle 10.

The braking unit sensor 44 is, for example, a position sensor, and when the braking unit 40 is a brake pedal, the braking unit sensor 44 detects the position of the braking unit 40. The braking unit sensor 44 outputs the detected position of the braking unit 40 to the in-vehicle network 36.

The acceleration system 24 controls the acceleration of the vehicle 10. The acceleration system 24 includes an acceleration unit 46, an acceleration control unit 48, and an acceleration unit sensor 50.

The acceleration unit 46 includes, for example, an accelerator pedal and the like, and is a device for accelerating the vehicle 10.

The acceleration control unit 48 is, for example, a computer such as a microcomputer having a hardware processor such as a CPU. The acceleration control unit 48 controls the acceleration unit 46 based on the instruction from the parking support device 34, and controls the acceleration of the vehicle 10.

The acceleration unit sensor 50 is, for example, a position sensor, and when the acceleration unit 46 is an accelerator pedal, the position of the acceleration unit 46 is detected. The acceleration unit sensor 50 outputs the detected position of the acceleration unit 46 to the in-vehicle network 36.

The steering system 26 controls the traveling direction of the vehicle 10. The steering system 26 includes a steering unit 52, a steering control unit 54, and a steering unit sensor 56.

The steering unit 52 is a device that includes, for example, a steering wheel (steering wheel) and the like, and steers the steering wheel of the vehicle 10 to steer the traveling direction of the vehicle 10.

The steering control unit 54 is, for example, a computer such as a microcomputer having a hardware processor such as a CPU. The steering control unit 54 controls the steering unit 52 based on the instruction from the parking support device 34, and controls the traveling direction of the vehicle 10.

The steering unit sensor 56 is an example of a third detection unit, for example, an angle sensor including a Hall element or the like, and detects a steering angle which is a rotation angle of the steering unit 52. The steering unit sensor 56 outputs the detected steering angle of the steering unit 52 to the in-vehicle network 36.

The shifting system 28 controls the gear ratio of the vehicle 10. The speed change system 28 includes a speed change unit 58, a shift control unit 60, and a speed change unit sensor 62.

The transmission unit 58 includes, for example, a shift lever and the like, and is a device for changing the gear ratio of the vehicle 10.

The shift control unit 60 is, for example, a computer such as a microcomputer having a hardware processor such as a CPU. The shift control unit 60 controls the shift unit 58 based on the instruction from the parking support device 34, and controls the gear ratio of the vehicle 10.

The shifting unit sensor 62 is, for example, a position sensor, and when the shifting unit 58 is a shift lever, the shifting unit sensor 62 detects the position of the shifting unit 58. The speed change sensor 62 outputs the detected position of the speed change 58 to the in-vehicle network 36.

The vehicle speed sensor 30 is, for example, a sensor having a Hall element provided in the vicinity of the wheel 13 of the vehicle 10 and detecting the amount of rotation of the wheel 13 or the number of rotations per unit time. The vehicle speed sensor 30 outputs the detected rotation speed or the number of wheel speed pulses indicating the rotation speed to the in-vehicle network 36 as a sensor value for calculating the vehicle speed. The parking support device 34 can calculate the speed (vehicle speed), the amount of movement, and the like of the vehicle 10 based on the sensor values acquired from the vehicle speed sensor 30.

The monitoring device 32 is provided on a dashboard or the like in the vehicle interior of the vehicle 10. The monitor device 32 includes a display unit 64, an audio output unit 66, and an operation input unit 68.

The display unit 64 displays an image based on the image data transmitted by the parking support device 34. The display unit 64 is, for example, a display device such as a liquid crystal display (LCD) or an organic electroluminescent display (OLELD). The display unit 64 displays, for example, an image that receives an operation instruction instructing switching between automatic operation and manual operation.

The voice output unit 66 outputs voice based on the voice data transmitted by the parking support device 34. The audio output unit 66 is, for example, a speaker. The voice output unit 66 outputs, for example, a voice relating to an operation instruction instructing switching between automatic operation and manual operation.

The operation input unit 68 accepts the input of the occupant. The operation input unit 68 is, for example, a touch panel. The operation input unit 68 is provided on the display screen of the display unit 64. The operation input unit 68 is configured to be transparent to the image displayed by the display unit 64. As a result, the operation input unit 68 can make the occupant visually recognize the image displayed on the display screen of the display unit 64. The operation input unit 68 receives the instruction input by the occupant by touching the position corresponding to the image displayed on the display screen of the display unit 64, and transmits the instruction to the parking support device 34. The operation input unit 68 is not limited to the touch panel, and may be a push button type hard switch or the like.

The parking support device 34 is a computer including a microcomputer such as an ECU (Electronic Control Unit), and provides parking support for the vehicle 10.

The parking support device 34 includes a CPU 34a, a ROM (Read Only Memory) 34b, a RAM (Random Access Memory) 34c, a display control unit 34d, a voice control unit 34e, and an SSD (Solid State Drive) 34f. The CPU 34a, ROM 34b and RAM 34c may be integrated in the same package.

The CPU 34a is an example of a hardware processor, reads a program stored in a non-volatile storage device such as a ROM 34b, and executes various arithmetic processes and controls according to the program. The CPU 34a, for example, executes parking support by automatic driving of the vehicle 10.

The ROM 34b stores a program, parameters necessary for executing the program, and the like. The RAM 34c temporarily stores various data used in the calculation in the CPU 34a. The display control unit 34d mainly executes image processing of the image obtained by the image pickup device 14, data conversion of the image for display to be displayed on the display unit 64, and the like among the arithmetic processing in the parking support device 34. The voice control unit 34e mainly executes the voice processing to be output to the voice output unit 66 among the arithmetic processing in the parking support device 34. The SSD 34f is a rewritable non-volatile storage device that maintains data even when the parking support device 34 is turned off.

The in-vehicle network 36 includes, for example, CAN (Controller Area Network), LIN (Local Interconnect Network), and the like. The in-vehicle network 36 includes an acceleration system 24, a braking system 22, a steering system 26, a speed change system 28, an ultrasonic sensor 16, a vehicle speed sensor 30, an operation input unit 68 of a monitor device 32, and a parking support device 34. And connect to each other so that they can send and receive information.

FIG. 3 is a block diagram showing a functional configuration of the parking support system 20 according to the embodiment.

The parking support system 20 includes a distance measuring unit 101, a lane marking detection unit 102 (detection unit), an extension direction estimation unit 103 (estimation unit), a movement route generation unit 104 (generation unit), and a travel control unit 105.

The distance measuring unit 101 acquires distance information indicating the distance from the vehicle 10 to an obstacle by using the reflection of ultrasonic waves. The ranging unit 101 is configured by the cooperation of an ultrasonic sensor 16, a parking support device 34, a program, and the like.

The lane marking detection unit 102 detects the lane marking indicating the parking area. The lane marking detection unit 102 is configured by the cooperation of an image pickup device 14, a parking support device 34, a program, and the like. The lane marking detection unit 102 detects the lane markings existing around the vehicle 10 by image recognition processing for the captured image acquired by the image pickup apparatus 14. The method of detecting the lane marking is not limited to this, and for example, the lane marking is detected based on the information acquired by a LIDAR (Light Detection And Ranging) sensor, a millimeter wave radar, or the like instead of the image pickup apparatus 14. It is also possible to do.

The extension direction estimation unit 103 is based on the distance information acquired by the distance measuring unit 101 and the lane marking information acquired by the lane marking detection unit 102, and the obstacles existing around the vehicle 10, particularly the target parking. Estimate the extension direction of obstacles in the vicinity of the area. The extension direction indicates a part of the shape characteristics of the obstacle, and is the direction in which the relatively long part of the obstacle extends. The extension direction is, for example, a direction along the side surface portion of the vehicle when the obstacle is a vehicle. The lane marking information includes the position, shape, and the like of the lane marking detected by the lane marking detection unit 102. The extension direction estimation unit 103 is configured by the cooperation of the parking support device 34, the program, and the like.

When the lane marking is not detected, the extension direction estimation unit 103 according to the present embodiment is based on the distance information acquired by the distance measuring unit 101 and a predetermined direction (for example, the vehicle width direction of the vehicle 10). Estimate the extension direction. Further, when the lane marking is detected by the lane marking detection unit 102, the extension direction estimation unit 103 estimates the extension direction based on the distance information and the lane marking.

The movement route generation unit 104 generates a movement route of the vehicle 10 based on the extension direction of the obstacle estimated by the extension direction estimation unit 103. The movement route generation unit 104 is configured by the cooperation of a parking support device 34, a program, and the like.

The movement route generation unit 104 according to the present embodiment includes a frontage distance calculation unit 111 and an obstacle integration unit 112.

When the lane marking is detected by the lane marking unit 102, the frontage distance calculation unit 111 can pass when the vehicle 10 enters the parking area based on the extension direction of the obstacle estimated based on the lane marking. Calculate the frontage distance.

When a plurality of obstacles are detected based on the distance information acquired by the distance measuring unit 101 and the lane markings are detected by the lane marking detection unit 102, the obstacle integrating unit 112 has a plurality of obstacles based on the lane markings. Performs processing for integrating obstacles into one obstacle.

The movement route generation unit 104 generates a movement route for the vehicle 10 based on the calculation result by the frontage distance calculation unit 111 and the processing result by the obstacle integration unit 112.

The travel control unit 105 performs processing for automatically traveling the vehicle 10 based on the movement route generated by the movement route generation unit 104. The travel control unit 105 is configured by cooperation of a parking support device 34, a braking system 22, an acceleration system 24, a steering system 26, a speed change system 28, a program, and the like.

FIG. 4 is a diagram showing an example of a parking lot in which the parking support system 20 according to the embodiment is used.

In the parking lot illustrated in FIG. 4, a plurality of parking areas 201 are arranged diagonally (in a staircase pattern). Each parking area 201 is partitioned by a division line 211. In this example, other vehicles 200A and 200B are parked in a parking area adjacent to the parking area 201 where the vehicle 10 (own vehicle) is about to park, and these other vehicles 200A and 200B become obstacles. FIG. 4 shows a situation in which the vehicle 10 travels in the traveling direction Df at a low speed, passes through the target parking area 201 once, and then retreats and enters the garage. In such a situation, the traveling direction Df of the vehicle 10 and the extension direction E of the other vehicles 200A and 200B are not orthogonal to each other.

When the vehicle 10 passes through the parking area 201, the ultrasonic sensor 16 (in this example, the ultrasonic sensors 16c and 16d) acquires distance information indicating the distance from the vehicle 10 to the other vehicles 200A and 200B, and also obtains an image pickup device. The image pickup data (captured image) around the parking area 201 is acquired by the 14 (in this example, the image pickup device 14d). When the lane marking 211 is detected (recognized) from the captured image, the extension direction E of the other vehicles 200A and 200B is estimated based on the distance information and the lane marking 211. On the other hand, when the lane marking 211 is not detected, the extension direction E is estimated based on the distance information and the predetermined direction.

FIG. 5 is a diagram showing an extension direction E estimated when the lane marking 211 is detected in the embodiment.

FIG. 5 shows a case where four ends P1 to P4 of another vehicle 200A are detected by an ultrasonic sensor 16 and a lane marking 211 is detected from an image captured by an image pickup device 14. In such a case, the extension direction estimation unit 103 (see FIG. 3) sets the extension direction E of the other vehicle 200A based on the positions of the ends P1 to P4 obtained from the distance information and the lane marking information regarding the lane marking 211. presume. Specifically, the extension direction E passing through the end portion (end portion P1 in this example) of the other vehicle 200A closest to the target parking area 201 is set to be parallel to the extension direction Es of the lane marking 211. .. In the above, only the other vehicle 200A has been described, but the same applies to the other vehicle 200B. According to such an estimation method, the extension direction E of the other vehicles 200A and 200B can be accurately estimated even in a special parking lot in which a plurality of parking areas 201 are diagonally arranged as shown in FIG.

FIG. 6 is a diagram showing an extension direction E estimated when the division line 211 is not detected in the embodiment.

FIG. 6 shows a case where the ultrasonic sensors 16 detect the four ends P1 to P4 of the other vehicle 200A, and the division line 211 is not detected from the image captured by the image pickup device 14. In such a case, the extension direction estimation unit 103 estimates the extension direction E of the other vehicle 200A based on the positions of the ends P1 to P4 obtained from the distance information and the vehicle width direction W which is a predetermined direction. do. Specifically, the extension direction E passing through the end portion (end portion P1 in this example) of the other vehicle 200A closest to the target parking area 201 is set to be parallel to the vehicle width direction W. In the above, only the other vehicle 200A has been described, but the same applies to the other vehicle 200B. According to such an estimation method, in a parking lot having a special structure as shown in FIG. 4, the estimation accuracy of the extension direction of the other vehicles 200A and 200B is low, but the traveling direction Df and the extension direction E form a right angle. In a parking lot having a normal structure, the extension direction E can be estimated with substantially sufficient accuracy.

FIG. 7 is a flowchart showing processing in the parking support system 20 according to the embodiment.

When the distance measuring unit 101 acquires the distance information (S101), the extension direction estimation unit 103 determines whether or not the lane marking 211 has been detected by the lane marking detection unit 102 (S102). When the lane marking 211 is detected (S102: Yes), the extension direction estimation unit 103 estimates the extension direction E of the obstacle (other vehicles 200A, 200B) based on the distance information and the lane marking 211 (S103). On the other hand, when the lane marking 211 is not detected (S102: No), the extension direction estimation unit 103 estimates the extension direction E of the obstacle based on the distance information and the vehicle width direction W (S104).

The movement route generation unit 104 generates a movement route of the vehicle 10 based on the extension direction E estimated as described above (S105), and the travel control unit 105 controls the vehicle 10 according to the generated movement route (S106). ).

Further, as described above, the movement route generation unit 104 generates a movement route based on the calculation result by the frontage distance calculation unit 111 and the processing result by the obstacle integration unit 112.

FIG. 8 is a diagram showing a method of calculating the frontage distance De according to the embodiment.

The frontage distance De indicates the size of the area that the vehicle 10 can pass through when entering the target parking area 201. As shown in FIG. 8, when the lane marking 211 is detected, the frontage distance De is calculated based on the extension direction E estimated based on the lane marking 211. As a result, the frontage distance De can be accurately calculated even in a parking lot having a special structure as shown in FIG.

FIG. 9 is a flowchart showing the processing in the frontage distance calculation unit 111 according to the embodiment.

The frontage distance calculation unit 111 determines whether or not the lane marking 211 has been detected by the lane marking detection unit 102 (S201). When the lane marking 211 is detected (S201: Yes), the frontage distance calculation unit 111 calculates the frontage distance De based on the extension direction E (see FIGS. 5 and 8) based on the lane marking 211 (S202). On the other hand, when the lane marking 211 is not detected (S201: No), the frontage distance calculation unit 111 calculates the frontage distance De based on the extension direction E (see FIG. 6) of the obstacle based on the vehicle width direction W. (S203). According to the process of step S203, the calculation accuracy of the frontage distance De is low in a parking lot having a special structure as shown in FIG. 4, but a normal parallel structure (a structure in which the traveling direction Df and the extension direction E are at right angles). ) Etc., the extension direction can be estimated with substantially sufficient accuracy.

Hereinafter, the process of integrating a plurality of obstacles will be described with reference to FIGS. 10 to 13.

FIG. 10 is a diagram showing an example of a detection region A1 that can be detected by an ultrasonic sensor 16 when a vehicle 10 passes through a parking region 201 in an embodiment. FIG. 11 is a diagram showing an example of a detection area A2 that can be detected by an ultrasonic sensor 16 when a vehicle 10 enters the parking area 201 in the embodiment.

At the timing shown in FIG. 10, the detection region A1 of the ultrasonic sensor 16 (in this example, the ultrasonic sensors 16c and 16d) is the front end portion of the other vehicle 200A. At the timing shown in FIG. 11, the detection region A2 of the ultrasonic sensor 16 is a side surface portion of another vehicle 200A on the vehicle 10 side. In this way, as the vehicle 10 moves, the detection regions A1 and A2 of the ultrasonic sensor 16 change.

FIG. 12 is a diagram showing an example of a state in which one obstacle is recognized as two obstacles in the embodiment.

In FIG. 12, the recognition object R1 corresponding to the detection area A1 shown in FIG. 10 and the recognition object R2 corresponding to the detection area A2 shown in FIG. 11 are shown. As described above, when the detection areas A1 and A2 of the ultrasonic sensor 16 change with the movement of the vehicle 10, continuity is not recognized in the acquired distance information, and one obstacle (another vehicle 200A in this example) becomes present. It may be recognized as multiple obstacles.

FIG. 13 is a diagram showing a process of integrating a plurality of recognition objects R1 and R2 into one recognition object R when the division line 211 is detected in the embodiment.

When the lane marking 211 is detected, as shown in FIG. 13, the plurality of recognition objects R1 and R2 existing in the predetermined area S are integrated into one recognition object R based on the lane marking 211. The predetermined area S should be appropriately set according to the usage situation and the like, but may be, for example, an area defined based on the size of a general vehicle. In the present embodiment, among the obstacle portions acquired by the ultrasonic sensor 16, a plurality of recognition objects are recognized with reference to the extension direction E that passes through the proximity portion Pn closest to the vehicle 10 and is parallel to the extension direction Es of the lane marking 211. R1 and R2 are integrated into one recognition object R. As a result, the shape of the obstacle can be accurately estimated even in a parking lot having a special structure as shown in FIG.

FIG. 14 is a flowchart showing a process in the obstacle integration unit 112 according to the embodiment.

The obstacle integration unit 112 determines whether or not a plurality of obstacles (recognition objects R1 and R2) are recognized in the predetermined area S (S301). If a plurality of obstacles are not recognized (S301: No), this flow ends. When a plurality of obstacles are recognized (S301: Yes), the obstacle integration unit 112 determines whether or not the lane marking 211 has been detected by the lane marking detection unit 102 (S302).

When the lane marking 211 is detected (S302: Yes), the obstacle integrating unit 112 integrates a plurality of obstacles (recognition objects R1 and R2) into one obstacle (recognition object R) based on the lane marking 211. (S303). On the other hand, when the lane marking 211 is not detected (S302: No), the obstacle integrating unit 112 sets a plurality of obstacles (recognition objects R1 and R2) as one obstacle based on the vehicle width direction W (see FIG. 6). It is integrated into an object (recognition object R) (S304). According to the process of step S304, the estimation accuracy of the shape of the obstacle is low in the parking lot having a special structure as shown in FIG. 4, but the normal parallel structure (traveling direction Df and extension direction E are at right angles). In a parking lot having a structure), the shape of an obstacle can be estimated with substantially sufficient accuracy.

The program for causing the parking support device 34 to execute various processes as described above is a file in an installable format or an executable format, such as a CD-ROM, a CD-R, a memory card, a DVD (Digital Versatile Disk), or a flexible disk (a flexible disk). It may be stored in a computer-readable storage medium such as FD) and provided as a computer program product. Further, the program may be provided by storing it on a computer connected to a network such as the Internet and downloading it via the network. Further, the program may be provided or distributed via a network such as the Internet.

According to the above embodiment, when an obstacle is detected by using ultrasonic waves, or even in a parking lot having a special structure, the estimation accuracy of the shape of the obstacle can be improved, and the parking support control can be performed. Reliability and efficiency can be improved.

Although the embodiments of the present invention have been described above, the above embodiments are presented as examples and are not intended to limit the scope of the invention. This novel embodiment can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. This embodiment and its modifications are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

10 ... Vehicle (moving body), 12 ... Body, 13 ... Wheels, 14 (14a-14d) ... Imaging device, 16 (16a-16l) ... Ultrasonic sensor, 20 ... Parking support system, 34 ... Parking support device, 101 ... Distance measuring unit, 102 ... Section line detection unit (detection unit), 103 ... Extension direction estimation unit (estimation unit), 104 ... Movement route generation unit (generation unit), 105 ... Travel control unit, 111 ... Frontage distance calculation unit (Calculation unit), 112 ... Obstacle integration unit (integration unit), 200A, 200B ... Other vehicles (obstacles), 201 ... Parking area, 211 ... Section line, A1, A2 ... Detection area, Df ... Travel direction, E ... (obstacle) extension direction, Es ... (partition line) extension direction, P1 to P8 ... end, R, R1, R2 ... recognition object, S ... predetermined area, W ... vehicle width direction

Claims (6)

A distance measuring unit that acquires distance information indicating the distance from a moving object to an obstacle using the reflection of ultrasonic waves,
A detector that detects a lane marking indicating a parking area,
When the lane marking is not detected, the extension direction of the obstacle is estimated based on the distance information and a predetermined direction, and when the lane marking is detected, the distance information and the lane marking are used. Based on the estimation unit that estimates the extension direction of the obstacle,
A generation unit that generates a movement path of the moving body based on the extension direction estimated by the estimation unit, and a generation unit.
Parking support system equipped with. When the lane marking is detected, a calculation unit that calculates the frontage distance that the moving body can pass when entering the parking area based on the extension direction estimated based on the lane marking.
The parking support system according to claim 1. An integration unit that performs processing for integrating the plurality of obstacles into one obstacle based on the division line when a plurality of obstacles are detected based on the distance information and the division line is detected.
The parking support system according to claim 1 or 2, further comprising. Based on the distance information indicating the distance from the moving body to the obstacle acquired by using the reflection of ultrasonic waves, the process for supporting the movement of the moving body when the moving body is parked in the parking area is performed. It is a parking support device to perform
When the lane marking indicating the parking area is not detected, the extension direction of the obstacle is estimated based on the distance information and a predetermined direction, and when the lane marking is detected, the distance information and the said An estimation unit that estimates the extension direction of the obstacle based on the lane marking,
A generation unit that generates a movement path of the moving body based on the extension direction estimated by the estimation unit, and a generation unit.
Parking support device equipped with. The process of acquiring distance information indicating the distance from a moving object to an obstacle using the reflection of ultrasonic waves, and
The process of detecting the lane marking indicating the parking area and
When the lane marking is not detected, a step of estimating the extension direction of the obstacle based on the distance information and a predetermined direction, and a step of estimating the extension direction of the obstacle.
When the lane marking is detected, a step of estimating the extension direction of the obstacle based on the distance information and the lane marking, and a step of estimating the extension direction of the obstacle.
A step of generating a movement path of the moving body based on the estimated extension direction, and a step of generating the movement path of the moving body.
Parking assistance methods including. Based on the distance information indicating the distance from the moving body to the obstacle acquired by using the reflection of ultrasonic waves, processing is performed to support the movement of the moving body when the moving body is parked in the parking area. On the computer
A process of estimating the extension direction of the obstacle based on the distance information and a predetermined direction when the lane marking indicating the parking area is not detected.
When the lane marking is detected, a process of estimating the extension direction of the obstacle based on the distance information and the lane marking, and a process of estimating the extension direction of the obstacle.
A process of generating a movement path of the moving body based on the estimated extension direction, and a process of generating the movement path of the moving body.
A program to execute.

Images