JP2019139696A - Vehicle control device - Google Patents

Abstract

To provide a vehicle control device that effectively achieves correct grasp of an actual location related to a vehicle during its automatic traveling in a parking area when map data capacity is relatively small.SOLUTION: A vehicle control device includes a plurality of computers that include an image recognition device, a location estimation device, and a traveling control device. Among the plurality of computers, a first computer providing the image recognition device and a second computer providing the traveling control device are different from each other, and a third computer providing the location estimation device and the second computer providing the traveling control device are identical with each other.SELECTED DRAWING: Figure 5

Description

  Embodiments described herein relate generally to a vehicle control device.

  In recent years, after an occupant gets off from a vehicle in a predetermined getting-off area in a parking lot, the automatic parking in which the vehicle automatically moves from the getting-off area to an empty parking area according to a predetermined instruction, and the automatic parking is completed. After that, a technique for realizing automatic valet parking including a vehicle that leaves a parking area in response to a predetermined call and automatically moves to a predetermined boarding area and stops is being studied.

JP2015-41348A

  In the technology that is based on the premise of automatic traveling such as automatic valet parking as described above, it is important to accurately grasp the current position (actual position) of the vehicle during automatic traveling. With respect to this point, conventionally, a method (so-called odometry) for estimating the actual position of the vehicle using a detection value of a wheel speed sensor or the like is known. However, in this method, as the moving distance of the vehicle increases, errors in the estimation results accumulate and increase, so that the actual position of the vehicle may not be accurately grasped.

  On the other hand, the image which acquires the data (for example, road marking data regarding the road marking of a parking lot) used as the basis of estimation of the real position of a vehicle from the image data obtained with the vehicle-mounted camera which images the surrounding condition of a vehicle A recognition function, a position estimation function for estimating the actual position of the vehicle by comparing data acquired by the image recognition function with predetermined data (for example, map data of a parking lot), and the position estimation function It is conceivable to realize an accurate grasp of the actual position of the vehicle during automatic traveling by providing the vehicle control device with a traveling control function for performing traveling control of the vehicle based on the actual position.

  In the configuration in which the vehicle control apparatus includes a plurality of computers, it is possible to appropriately share the above-described functions among the plurality of computers based on the performance of the computer required to realize the above-described functions. In addition, it is possible to efficiently realize an accurate grasp of the actual position of the vehicle during automatic traveling.

  For example, since the travel control function relates to the behavior of the vehicle, a computer that realizes the travel control function is required to have a high processing capacity (processing speed). On the other hand, since the image recognition function handles a relatively large amount of data such as image data, a computer that realizes the image recognition function is required to have a certain processing speed. Ability to handle is required.

  Here, when the map data has a relatively small capacity, the computer that realizes the position estimation function is not required to have the ability to handle a large amount of data.

  Based on the above, one of the problems of the embodiment is vehicle control capable of efficiently realizing accurate grasp of the actual position of the vehicle during automatic traveling when the map data has a relatively small capacity. Is to provide a device.

  The vehicle control device according to the embodiment includes an image data acquisition unit that acquires image data obtained by an in-vehicle camera that captures a situation around the vehicle, and a parking area where the vehicle travels by performing an image recognition process based on the image data. A road marking data acquisition unit that acquires road marking data related to the road markings installed on the road surface of the parking lot, an image recognition device that includes the map data acquisition unit that acquires map data of the parking lot including the absolute position of the road markings, and A position estimation unit including a position estimation unit that estimates the actual position of the vehicle by comparing the road marking data acquired by the road marking data acquisition unit and the map data acquired by the map data acquisition unit, and the vehicle A route acquisition unit that acquires a travel route to be traced by automatic driving, a travel route acquired by the route acquisition unit, and an actual position estimated by the position estimation unit And a travel control unit that performs automatic travel based on the travel route by controlling the travel state of the vehicle based on the travel control device. The first computer that implements the apparatus and the second computer that implements the travel control apparatus are different from each other, and the third computer that implements the position estimation apparatus and the second computer that implements the travel control apparatus are the same.

  According to the vehicle control device having such a configuration, the travel control device that requires high processing capability and the image recognition device that requires the ability to handle large amounts of data are separated from each other by computers. Can be realized. In addition, when the map data is relatively small, a position estimation device that does not require much capacity to handle large volumes of data is required to have a high processing capacity (that is, the ability to handle large volumes of data is not so much). (Not required) can be realized by the same computer as the travel control device. As a result, when the map data has a relatively small capacity, it is possible to share processing with multiple computers according to the required performance, so it is efficient to accurately grasp the actual position of the vehicle during automatic driving. Can be realized.

  The vehicle control device described above is a control device provided corresponding to a parking lot, and includes a communication device that holds map data and communicates with a control device that generates a travel route according to the situation in the parking lot. Furthermore, the map data acquisition unit of the position estimation device acquires map data from the control device via the communication device, and the route acquisition unit of the travel control device acquires the travel route from the control device via the communication device. According to such a structure, map data and a driving | running route can be easily acquired from the outside by communication.

  Further, in the vehicle control device described above, the automatic traveling is performed in a parking lot including the getting-off area, the getting-on area, and the parking area, and after the passenger gets off from the vehicle in the getting-off area, Automatic parking to automatically move to the parking area and park, and after the automatic parking has been completed, the automatic delivery of the vehicle from the parking area in response to a predetermined call, automatically moving to the boarding area and stopping, including. According to such a configuration, it is possible to efficiently realize an accurate grasp of the actual position of the vehicle during automatic running of automatic valet parking.

Drawing 1 is an exemplary and typical figure showing an example of automatic parking in an automatic valet parking system concerning an embodiment. FIG. 2 is an exemplary schematic diagram illustrating an example of automatic delivery in the automatic valet parking system according to the embodiment. FIG. 3 is an exemplary schematic block diagram illustrating a hardware configuration of the control device according to the embodiment. FIG. 4 is an exemplary schematic block diagram illustrating a system configuration of the vehicle control system according to the embodiment. FIG. 5 is an exemplary schematic block diagram illustrating functional configurations of the control device and the vehicle control device according to the embodiment. FIG. 6 is an exemplary schematic diagram illustrating a specific example of a situation in which the vehicle control device according to the embodiment estimates the actual position of the vehicle. FIG. 7 is an exemplary and schematic sequence diagram illustrating a flow of processing executed by the control device and the vehicle control device according to the embodiment during automatic parking. FIG. 8 is an exemplary and schematic sequence diagram illustrating a flow of processing executed by the control device and the vehicle control device according to the embodiment at the time of automatic delivery. FIG. 9 is an exemplary and schematic flowchart illustrating a schematic flow of an actual position estimation process executed by the vehicle control device according to the embodiment during automatic traveling. FIG. 10 is an exemplary and schematic flowchart illustrating a detailed flow of an actual position estimation process executed by the vehicle control device according to the embodiment during automatic traveling.

  Hereinafter, embodiments will be described with reference to the drawings. The configuration of the embodiment described below, and the operation and result (effect) brought about by the configuration are merely examples, and are not limited to the following description.

<Embodiment>
First, with reference to FIG. 1 and FIG. 2, the outline of the automatic valet parking system concerning embodiment is demonstrated. Here, the automatic valet parking system refers to automatic valet parking including automatic parking and automatic delivery as described below in a parking lot P having one or more parking areas R partitioned by a lane marking L such as a white line. It is a system to realize. In addition to the parking area R, the parking lot P according to the embodiment has a getting-off area P1 and a boarding area P2.

  FIG. 1 is an exemplary schematic diagram illustrating an example of automatic parking in the automatic valet parking system according to the embodiment, and FIG. 2 illustrates an example of automatic delivery in the automatic valet parking system according to the embodiment. It is an exemplary and schematic diagram.

  As shown in FIG. 1 and FIG. 2, in the automatic valet parking, after the occupant X gets out of the vehicle V in the predetermined getting-off area P1 in the parking lot P, the vehicle V gets out of the getting-off area P1 Automatic parking (see arrow C1 in FIG. 1) that automatically moves from the parking space to an empty parking area R, and after the automatic parking is completed, the vehicle V leaves the parking area R in response to a predetermined call. Automatic delivery (see arrow C2 in FIG. 2) that automatically moves to a predetermined boarding area P2 and stops is executed. The predetermined instruction and the predetermined call are realized by the operation of the terminal device T by the occupant X.

  As shown in FIGS. 1 and 2, the automatic valet parking system includes a control device 101 provided in the parking lot P and a vehicle control system 102 mounted on the vehicle V. The control device 101 and the vehicle control system 102 are configured to be able to communicate with each other by wireless communication.

  The control device 101 is configured to manage (including hold) the map data of the parking lot P. The map data includes information for specifying the (regular) absolute position of a road marking fixedly installed on the road surface of the parking lot P, such as the lane marking L described above and a marker M (see FIG. 6) described later. Contains. The absolute position referred to here is a concept that can include the directionality (absolute direction) of the road marking. In other words, when the road marking includes a linear marking having a predetermined direction (direction), the map data includes not only the absolute position where the road marking is provided, but also the linear marking included in the road marking. The absolute orientation represented by the marking can also be specified.

  In addition, the control apparatus 101 receives image data obtained from one or more monitoring cameras 103 that capture the situation in the parking lot P, and data output from various sensors (not shown) provided in the parking lot P. By receiving, the situation in the parking lot P is monitored, and the parking area R is managed based on the monitoring result. Below, the information which the control apparatus 101 receives in order to monitor the condition in the parking lot P may be named generically and may be described as sensor data.

  In the embodiment, the number and arrangement of the getting-off area P1, the boarding area P2, and the parking area R in the parking lot P are not limited to the examples shown in FIGS. The technology of the embodiment can be applied to a parking lot having various configurations different from the parking lot P shown in FIGS. 1 and 2.

  Next, with reference to FIG. 3 and FIG. 4, the structure of the control apparatus 101 and the vehicle control system 102 concerning embodiment is demonstrated. The configurations shown in FIGS. 3 and 4 are merely examples, and the configurations of the control device 101 and the vehicle control system 102 according to the embodiment can be set (changed) in various ways.

  First, a hardware configuration of the control device 101 according to the embodiment will be described with reference to FIG.

  FIG. 3 is an exemplary schematic block diagram illustrating a hardware configuration of the control device 101 according to the embodiment. As shown in FIG. 3, the control device 101 according to the embodiment has the same computer resources as a general information processing device such as a PC (Personal Computer).

  In the example illustrated in FIG. 3, the control device 101 includes a processor 301, a memory 302, a communication device 303, an input / output interface (I / F) 304, and a storage 305. These hardwares are connected to each other via a data bus 350.

  The processor 301 is configured by, for example, a CPU (Central Processing Unit) and controls the control device 101 in an integrated manner. The processor 301 reads various control programs (computer programs) stored in the memory 302, the storage 305, and the like, and realizes various functions according to instructions defined in the various control programs.

  The memory 302 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), and the like, and stores data necessary for various processes executed by the processor 301 and provides a work area for the processor 301. To do.

  The communication device 303 realizes communication between the control device 101 and an external device. For example, the communication device 303 realizes transmission / reception of signals by wireless communication between the control device 101 and the vehicle V (vehicle control system 102).

  The input / output interface 304 is an interface that realizes connection between the control device 101 and an external device. As the external device, for example, an input / output device used by an operator of the control device 101 can be considered.

  The storage 305 is an auxiliary storage device configured by, for example, an HDD (Hard Disk Drive) or an SSD (Solid State Drive).

  Next, a system configuration of the vehicle control system 102 according to the embodiment will be described with reference to FIG.

  FIG. 4 is an exemplary schematic block diagram illustrating a system configuration of the vehicle control system 102 according to the embodiment. As shown in FIG. 4, the vehicle control system 102 includes a braking system 401, an acceleration system 402, a steering system 403, a transmission system 404, an obstacle sensor 405, a traveling state sensor 406, and a communication device 407. A vehicle-mounted camera 408, a monitor device 409, a vehicle control device 410, and a vehicle-mounted network 450.

  The braking system 401 controls the deceleration of the vehicle V. The braking system 401 includes a braking unit 401a, a braking control unit 401b, and a braking unit sensor 401c.

  The braking unit 401a is a device for decelerating the vehicle V including a brake pedal, for example.

  The braking control unit 401b is an ECU (Electronic Control Unit) configured by a computer having a hardware processor such as a CPU, for example. The braking control unit 401b controls an amount of deceleration of the vehicle V by driving an actuator (not shown) based on an instruction from the vehicle control device 410 and operating the braking unit 401a.

  The brake unit sensor 401c is a device for detecting the state of the brake unit 401a. For example, when the brake unit 401a includes a brake pedal, the brake unit sensor 401c detects the position of the brake pedal or the pressure acting on the brake pedal as the state of the brake unit 401a. The braking unit sensor 401c outputs the detected state of the braking unit 401a to the in-vehicle network 450.

  The acceleration system 402 controls the acceleration of the vehicle V. The acceleration system 402 includes an acceleration unit 402a, an acceleration control unit 402b, and an acceleration unit sensor 402c.

  The acceleration part 402a is an apparatus for accelerating the vehicle V including an accelerator pedal etc., for example.

  The acceleration control unit 402b is an ECU configured by a computer having a hardware processor such as a CPU, for example. The acceleration control unit 402b controls an acceleration degree of the vehicle V by driving an actuator (not shown) based on an instruction from the vehicle control device 410 and operating the acceleration unit 402a.

  The acceleration unit sensor 402c is a device for detecting the state of the acceleration unit 402a. For example, when the acceleration unit 402a includes an accelerator pedal, the acceleration unit sensor 402c detects the position of the accelerator pedal or the pressure acting on the accelerator pedal. The acceleration unit sensor 402c outputs the detected state of the acceleration unit 402a to the in-vehicle network 450.

  The steering system 403 controls the traveling direction of the vehicle V. The steering system 403 includes a steering unit 403a, a steering control unit 403b, and a steering unit sensor 403c.

  The steering unit 403a is a device that steers steered wheels of the vehicle V including, for example, a steering wheel and a handle.

  The steering control unit 403b is an ECU configured by a computer having a hardware processor such as a CPU, for example. The steering control unit 403b controls an advancing direction of the vehicle V by driving an actuator (not shown) based on an instruction from the vehicle control device 410 and operating the steering unit 403a.

  The steering unit sensor 403c is a device for detecting the state of the steering unit 403a. For example, when the steering unit 403a includes a steering wheel, the steering unit sensor 403c detects the position of the steering wheel or the rotation angle of the steering wheel. When the steering unit 403a includes a handle, the steering unit sensor 403c may detect the position of the handle or the pressure acting on the handle. The steering unit sensor 403c outputs the detected state of the steering unit 403a to the in-vehicle network 450.

  The transmission system 404 controls the transmission ratio of the vehicle V. The transmission system 404 includes a transmission unit 404a, a transmission control unit 404b, and a transmission unit sensor 404c.

  The transmission unit 404a is a device for changing the transmission ratio of the vehicle V including a shift lever, for example.

  The shift control unit 404b is an ECU configured by a computer having a hardware processor such as a CPU, for example. The shift control unit 404b drives an actuator (not shown) based on an instruction from the vehicle control device 410 and operates the shift unit 404a to control the transmission ratio of the vehicle V.

  The transmission unit sensor 404c is a device for detecting the state of the transmission unit 404a. For example, when the transmission unit 404a includes a shift lever, the transmission unit sensor 404c detects the position of the shift lever or the pressure acting on the shift lever. The transmission unit sensor 404c outputs the detected state of the transmission unit 404a to the in-vehicle network 450.

  The obstacle sensor 405 is a device for detecting information related to obstacles that may exist around the vehicle V. The obstacle sensor 405 includes a distance measuring sensor such as a sonar that detects the distance to the obstacle. The obstacle sensor 405 outputs the detected information to the in-vehicle network 450.

  The traveling state sensor 406 is a device for detecting the traveling state of the vehicle V. The running state sensor 406 is, for example, a wheel speed sensor that detects the wheel speed of the vehicle V, an acceleration sensor that detects acceleration in the front-rear direction or the left-right direction of the vehicle V, and a gyro that detects the turning speed (angular velocity) of the vehicle V. Includes sensors. The traveling state sensor 406 outputs the detected traveling state to the in-vehicle network 450.

  The communication device 407 realizes communication between the vehicle control system 102 and an external device. For example, the communication device 407 transmits / receives a signal (data) by wireless communication between the vehicle control system 102 and the control device 101 and a signal (data) by wireless communication between the vehicle control system 102 and the terminal device T. Realize transmission and reception.

  The in-vehicle camera 408 is a device for imaging the situation around the vehicle V. For example, a plurality of in-vehicle cameras 408 are provided so as to image a region including the road surface in front, rear, and side (both left and right) of the vehicle V. The image data obtained by the in-vehicle camera 408 is used for monitoring the situation around the vehicle V (including detection of obstacles). The in-vehicle camera 408 outputs the obtained image data to the vehicle control device 410. Hereinafter, the image data obtained from the in-vehicle camera 408 and the data obtained from the various sensors provided in the vehicle control system 102 may be collectively referred to as sensor data.

  The monitor device 409 is provided on a dashboard in the passenger compartment of the vehicle V. The monitor device 409 includes a display unit 409a, an audio output unit 409b, and an operation input unit 409c.

  The display unit 409a is a device for displaying an image in response to an instruction from the vehicle control device 410. The display unit 409a is configured by, for example, a liquid crystal display (LCD: Liquid Crystal Display), an organic EL display (OELD: Organic Electroluminescent Display), or the like.

  The sound output unit 409b is a device for outputting sound in response to an instruction from the vehicle control device 410. The audio output unit 409b is configured by a speaker, for example.

  The operation input unit 409c is a device for receiving an input from an occupant in the vehicle V. The operation input unit 409c is configured by, for example, a touch panel provided on the display screen of the display unit 409a, a physical operation switch, or the like. The operation input unit 409c outputs the received input to the in-vehicle network 450.

  The vehicle control device 410 has a plurality of ECUs 400 for comprehensively controlling the vehicle control system 102. The plurality of ECUs 400 are physically provided independently of each other, and each is configured as a computer having hardware such as a processor 400a and a memory 400b. The plurality of ECUs 400 are connected to each other via a vehicle-mounted network 450 so as to communicate with each other. In the embodiment, a group of a plurality of physically independent ECUs 400 is merely defined as the vehicle control device 410 for convenience. That is, in the embodiment, one large physical unit called the vehicle control device 410 is not assumed.

  The processor 400a is constituted by, for example, a CPU and controls the vehicle control device 410 in an integrated manner. The processor 400a reads various control programs (computer programs) stored in the memory 400b or the like, and implements various functions according to instructions defined in the various control programs.

  The memory 400b includes, for example, a ROM and a RAM, and realizes storage of data necessary for various processes executed by the processor 400a, provision of a work area for the processor 400a, and the like.

  In FIG. 4, only the processor 400a and the memory 400b are representatively exemplified as hardware included in the ECU 400, but the ECU may include other hardware (for example, storage). Needless to say. FIG. 4 illustrates a configuration in which the in-vehicle camera 408 and the monitor device 409 are connected to one of the plurality of ECUs 400. However, this configuration is merely an example. In the embodiment, the connection relationship between the plurality of ECUs 400 and the in-vehicle camera 408 can be set (changed) as appropriate, and the connection relationship between the plurality of ECUs 400 and the monitor device 409 can also be set (changed) as appropriate.

  The in-vehicle network 450 includes a braking system 401, an acceleration system 402, a steering system 403, a transmission system 404, an obstacle sensor 405, a traveling state sensor 406, a communication device 407, and an operation input unit 409c of the monitor device 409. And the vehicle control device 410 are communicably connected.

  By the way, in the technology based on the premise of automatic traveling, such as the automatic valet parking system described above, it is important to accurately grasp the current position (actual position) of the vehicle V during automatic traveling. With respect to this point, conventionally, a method (so-called odometry) for estimating the actual position of the vehicle V using a detection value of a wheel speed sensor or the like is known. However, in this method, as the moving distance of the vehicle V increases, errors in estimation results accumulate and increase, and thus the actual position of the vehicle V may not be accurately grasped.

  On the other hand, an image recognition function for acquiring data (for example, road marking data related to the road marking of the parking lot P) from which the actual position of the vehicle V is estimated from the image data obtained by the in-vehicle camera 408, and A position estimation function for estimating the actual position of the vehicle V by comparing data acquired by the image recognition function with predetermined data (for example, map data of the parking lot P), and an actual position estimated by the position estimation function. Considering that the vehicle control device 410 has a traveling control function for performing traveling control of the vehicle V in consideration, it is possible to realize an accurate grasp of the actual position of the vehicle V during automatic traveling.

  In the configuration as in the embodiment in which the vehicle control device 410 includes a plurality of ECUs 400, each function described above is assigned to the plurality of ECUs 400 based on the performance of the ECU 400 required to realize each function described above. If it can be appropriately shared, accurate grasp of the actual position of the vehicle during automatic traveling can be efficiently realized.

  For example, since the travel control function relates to the behavior of the vehicle V, the ECU 400 that realizes the travel control function is required to have a high processing capacity (processing speed). On the other hand, since the image recognition function handles a relatively large amount of data such as image data, the ECU 400 that realizes the image recognition function is required to have a certain processing speed. Ability to handle is required.

  Here, when the map data has a relatively small volume, the ECU 400 that realizes the position estimation function is not required to have a large capacity for handling a large volume of data.

  Based on the above, the embodiment assigns each of the functions described above to a plurality of ECUs 400 as follows, so that when the map data has a relatively small capacity, the actual position of the vehicle V during the automatic travel is accurately determined. Efficient grasping.

  FIG. 5 is an exemplary and schematic block diagram illustrating a functional configuration of the control device 101 and the ECU 400 included in the vehicle control device 410 according to the embodiment. The functional module group shown in FIG. 5 is realized by cooperation of software and hardware. That is, in the example shown in FIG. 5, the functional module group of the control device 101 is realized as a result of the processor 301 reading and executing a predetermined control program stored in the memory 302 or the like. The group is realized as a result of the processor 400a of each ECU 400 reading and executing a predetermined control program stored in the memory 400b or the like. In the embodiment, a part or all of the functional module group shown in FIG. 5 may be realized only by dedicated hardware (circuit).

  As shown in FIG. 5, the control device 101 according to the embodiment includes, as a functional configuration, a communication processing unit 501, a sensor data acquisition unit 502, a parking lot data management unit 503, a guidance route generation unit 504, have.

  The communication processing unit 501 controls wireless communication performed with the vehicle control device 410. For example, the communication processing unit 501 authenticates the vehicle control device 410 by transmitting and receiving predetermined data to and from the vehicle control device 410, and outputs from the vehicle control device 410 when automatic parking and automatic delivery are completed. The predetermined completion notification is received, map data of the parking lot P, a guidance route described later, and the like are transmitted to the vehicle control device 410 as necessary.

  The sensor data acquisition unit 502 acquires the above-described sensor data from the monitoring camera 103 and various sensors (not shown) provided in the parking lot P. The sensor data (particularly image data obtained from the monitoring camera 103) acquired by the sensor data acquisition unit 502 can be used, for example, for grasping the vacant state of the parking area R.

  The parking lot data management unit 503 manages data (information) related to the parking lot P. For example, the parking lot data management unit 503 manages the map data of the parking lot P, the availability of the parking area R, and the like. For example, when the automatic parking is performed, the parking lot data management unit 503 selects one parking area R from the vacant parking areas R, and selects the selected parking area R of the vehicle V in the automatic parking. Designate as the target parking area that is the destination goal. In addition, when the vehicle V moves again after the automatic parking is completed and the parking area R is changed, the parking lot data management unit 503 changes the changed data based on the sensor data acquired from the sensor data acquisition unit 502. The parking area R is specified.

  The guidance route generation unit 504 generates a guidance route that instructs the vehicle control device 410 when automatic parking and automatic delivery are performed. More specifically, when automatic parking is performed, the guidance route generation unit 504 generates a schematic route from the getting-off area P1 to the target parking area as a guidance route, and when automatic delivery is performed, A rough route from the target parking area (a parking area R where the vehicle V is currently parked when the vehicle V is moving after automatic parking) to the boarding area P2 is generated as a guidance path.

  Here, as shown in FIG. 5, in the embodiment, the position estimation device 520 as a logical (functional) unit responsible for the position estimation function described above and the logical unit responsible for the travel control function described above. The travel control device 530 is realized by the same ECU 412, and the image recognition device 510 as a logical unit responsible for the image recognition function described above is realized by an ECU 411 different from the ECU 412. As a result, when the map data handled by the position estimation device 520 has a relatively small capacity, the ECU 411 is responsible for processing that mainly requires the ability to handle large volumes of data, and has the ability to handle large volumes of data. Since it is possible to cause another ECU 412 to perform processing that is not required, the efficiency can be improved. Although only two ECUs 411 and 412 are illustrated in FIG. 5, the vehicle control device 410 according to the embodiment may include an ECU 400 other than the ECUs 411 and 412.

  Hereinafter, functional configurations of the image recognition device 510, the position estimation device 520, and the travel control device 530 will be specifically described.

  The image recognition device 510 includes an image data acquisition unit 511 and a road marking data acquisition unit 512 as functional configurations. Note that the image recognition device 510 is realized by an ECU 411 that is different from the ECU 412 that realizes the position estimation device 520 and the travel control device 530, but the ECU 411 and the ECU 412 can communicate with each other via the in-vehicle network 450. Therefore, the image recognition device 510 can communicate with the position estimation device 520 and the travel control device 530.

  The image data acquisition unit 511 acquires image data obtained by the in-vehicle camera 408. This image data shall contain the information showing the condition of the road surface of the parking lot P.

  The road marking data acquisition unit 512 performs an image recognition process based on the image data acquired by the image data acquisition unit 511, and thereby the lane marking L (see FIG. 1) and the marker M (see FIG. 6) described later. The road marking data related to the road marking installed on the road surface of the parking lot P is acquired. The road marking data is data indicating a position (which may include an orientation) of the road marking on the image data. From this road marking data, a relative position (which may include a relative direction) of the road marking with respect to the vehicle V on the image data can be calculated.

  The position estimation device 520 includes a map data acquisition unit 521 and a position estimation unit 522.

  The map data acquisition unit 521 acquires the map data of the parking lot P from the control device 101 via the communication device 407. As described above, it is possible to specify the (normal) absolute position of the road marking from this map data.

  The position estimation unit 522 collates the road marking data acquired by the road marking data acquisition unit 512 of the image recognition device 510 with the map data acquired by the map data acquisition unit 521, so that the actual position of the vehicle V Is estimated. More specifically, the position estimation unit 522 calculates a relative position (which may include a relative direction) of the road marking with respect to the vehicle V based on the road marking data, and the vehicle estimated based on the relative position and odometry. Based on the actual position for calculating V, an absolute position (which may include an absolute direction) for calculating the road marking is calculated. Then, the position estimation unit 522 compares the calculated absolute position of the road marking calculated based on the road marking data with the (regular) absolute position of the road marking specified based on the map data. Thus, the (regular) actual position of the vehicle V is estimated.

  The travel control device 530 includes a route acquisition unit 531 and a travel control unit 532. Since travel control device 530 is realized by the same ECU 412 as position estimation device 520, position estimation device 520 and travel control device 530 can communicate with each other.

  The route acquisition unit 531 acquires a guidance route as a travel route to be followed by the automatic travel of the vehicle V from the control device 101 via the communication device 407.

  The travel control unit 532 controls the braking system 401, the acceleration system 402, the steering system 403, the speed change system 404, and the like, thereby starting control from the dismounting area P1 and traveling control from the dismounting area P1 to the parking area R (parking). Control), running control from the parking area R to the boarding area P2 (including delivery control), stop control to the boarding area P2, etc., and various kinds of running control for realizing automatic parking and automatic delivery. Thus, the traveling state of the vehicle V is controlled.

  More specifically, the travel control unit 532 travels the vehicle V based on the guidance route acquired by the route acquisition unit 531 and the actual position of the vehicle V estimated by the position estimation unit 522 of the position estimation device 520. By controlling the state, automatic traveling based on the guidance route is performed. The traveling control unit 532 can also use image data obtained by the in-vehicle camera 408, data output from various sensors provided in the vehicle control system 102, and the like for control. This makes it possible to adjust the guidance route according to the situation.

  With the configuration as described above, the vehicle control device 410 according to the embodiment estimates the current position of the vehicle V by odometry while the vehicle V is automatically traveling. Then, the vehicle control device 410 corrects the estimation result by the odometry so as to cancel the accumulated error based on the image data obtained by the in-vehicle camera 408 and the map data acquired from the control device 101, and automatically travels. The current position (actual position) of the vehicle V inside is estimated.

  That is, the vehicle control apparatus 410 according to the embodiment first detects road marking data related to road markings located around the vehicle V from the image data obtained by the in-vehicle camera 408 during the automatic running. The relative position on the image data of the road marking with respect to the vehicle V is calculated. Then, the vehicle control device 410 calculates the absolute position of the road marking calculated based on the relative position of the road marking, and the normal absolute position of the road marking specified from the map data acquired from the control device 101. Based on the difference, the estimation result based on odometry is corrected, and the corrected value is set as a normal estimated value of the current position (actual position) of the vehicle V.

  For example, as in the example described below, the vehicle control device 410 according to the embodiment is configured such that when the vehicle V is traveling automatically on a road surface on which a lane marking L and a marker M are installed as road markings, Based on the side image data which is the image data representing the situation on the side of V, road marking data relating to the positions of the end portion E and the marker M on the side close to the vehicle V in the lane marking L is detected. Then, the vehicle control device 410 calculates a relative position representing the positions of the end E of the lane marking L and the marker M with reference to the vehicle V based on the detected road marking data. Then, the vehicle control device 410 determines the lane line identified from the absolute position of the lane line L and the marker M calculated based on the relative positions of the lane line L and the marker M and the map data of the parking lot P. The actual absolute position of the vehicle V during automatic traveling is estimated based on the collation result.

  FIG. 6 is an exemplary schematic diagram illustrating a specific example of a situation in which the vehicle control device 410 according to the embodiment estimates the actual position of the vehicle V. In the example shown in FIG. 6, the vehicle V is traveling by automatic traveling in a direction intersecting with the three lane markings L61 to L63 located on the left side of the vehicle V. In the example shown in FIG. 6, a marker M61 is installed between the end E61 of the lane marking L61 and the end E62 of the lane marking L62, and the end E62 of the lane marking L62 and the end of the lane marking L63. A marker M62 is also provided between the two parts.

  In the example shown in FIG. 6, the imaging range of the in-vehicle camera 408 provided on the left side of the vehicle V (for example, a side mirror) includes an end E61 of the lane marking L61, a marker M61, and an end E62 of the lane marking L62. , Corresponding to region A61. Therefore, the vehicle control device 410 performs an image recognition process such as a white line detection process on one side image data obtained by the vehicle-mounted camera 408 provided on the left side of the vehicle V, so that the end of the lane marking L61 Each road marking data of E61, marker M61, and end E62 of lane marking L62 is acquired.

  Then, the vehicle control device 410 uses the acquired road marking data, and each of the lane line L61 (the end portion E61), the marker M61, and the lane line L62 (the end portion E62) based on the vehicle V. , And using the calculated relative position and the estimation result based on odometry, each of the marking line L61 (the end E61), the marker M61, and the marking line L62 (the end E62) Specifies the absolute position in the calculation of.

  Then, the vehicle control device 410 acquires map data from the control device 101, and from the map data, each of the lane marking L61 (end E61), the marker M61, and the lane marking L62 (end E62) is normalized. Specify the absolute position of. Then, the vehicle control device 410 takes the difference between the calculated absolute position and the regular absolute position, corrects the deviation of the estimation result by odometry based on the difference, and uses the corrected value as the actual value of the vehicle V. Estimated as position. In this way, accurate estimation of the actual position of the vehicle V during automatic traveling is realized.

  In the example shown in FIG. 6 described above, the three road markings of the lane markings L61 and L62 and the marker M61 are used for estimating the actual position of the vehicle V. However, the number of road markings used for estimating the actual position of the vehicle V may be two or less, or may be four or more. In the embodiment, the actual position of the vehicle V may be estimated based on road markings other than the lane marking L and the marker M.

  Next, with reference to FIGS. 7-10, the process performed with the automatic valet parking system concerning embodiment is demonstrated.

  FIG. 7 is an exemplary and schematic sequence diagram illustrating a flow of processing executed by the control device 101 and the vehicle control device 410 according to the embodiment during automatic parking. The processing sequence shown in FIG. 7 is started when the occupant X operates the terminal device T in the getting-off area P1 to give a predetermined instruction that triggers automatic parking.

  In the processing sequence shown in FIG. 7, first, in S701, the control device 101 and the vehicle control device 410 establish communication. In S701, authentication based on transmission / reception of identification information (ID), transfer of operation authority for realizing automatic traveling under the monitoring of the control device 101, and the like are executed.

  When communication is established in S701, the control device 101 (communication processing unit 501) transmits the map data of the parking lot P to the vehicle control device 410 in S702.

  In S703, the control device 101 (parking data management unit 503) confirms the vacant parking area R and designates one vacant parking area R as a target parking area to be given to the vehicle V.

  Then, in S704, the control device 101 (guidance route generation unit 504) generates a guidance route from the getting-off area P1 to the target parking area designated in S703, which the vehicle V should follow in automatic parking.

  In step S <b> 705, the control device 101 (communication processing unit 501) transmits the guidance route generated in step S <b> 704 to the vehicle control device 410.

  On the other hand, the vehicle control device 410 (position estimation device 520) estimates the initial position in the dismounting area P1 in S706 after the map data transmitted from the control device 101 in S702 is received via the communication device 407. . The initial position is the current position (actual position) of the vehicle V in the getting-off area P1, which is the starting point for starting from the getting-off area P1. For the estimation of the initial position, the result of the image recognition process of the image recognition apparatus 510 based on the image data obtained by the in-vehicle camera 408 can be used, as in the above-described estimation of the actual position during automatic traveling. In the example illustrated in FIG. 7, the process of S706 is performed before the process of S705, but the process of S706 may be performed after the process of S705.

  When the initial position is estimated in S706, and the guidance route transmitted from the control device 101 in S705 is received via the communication device 407, the vehicle control device 410 (travel control device 530), in S707, in S706. Based on the estimated initial position and the like, a travel route based on the guidance route to be followed in actual automatic parking is generated.

  In step S708, the vehicle control device 410 (travel control device 530) executes start control from the getting-off area P1.

  In step S709, the vehicle control device 410 (travel control device 530) executes travel control along the travel route generated in step S707. This travel control is executed with the estimation of the actual position by the position estimation device 520 using the result of the image recognition processing by the image recognition device 510 as described above. Note that the flow of processing executed at the time of estimating the actual position will be described in detail later with reference to another drawing, and thus further description is omitted here.

  Then, the vehicle control device 410 (travel control device 530) executes parking control to the target parking area in S710.

  When the parking control in S710 is completed, the vehicle control device 410 (travel control device 530) transmits a parking completion notification to the control device 101 via the communication device 407 in S711.

  As described above, automatic parking in automatic valet parking is realized.

  FIG. 8 is an exemplary and schematic sequence diagram illustrating a flow of processing executed by the control device 101 and the vehicle control device 410 according to the embodiment at the time of automatic delivery. The processing sequence shown in FIG. 8 is started when the occupant X operates the terminal device T in the boarding area P2 to make a predetermined call that triggers automatic shipping.

  In the processing sequence shown in FIG. 8, first, in S801, the control device 101 and the vehicle control device 410 establish communication. In S801, as in S701 of FIG. 7 described above, authentication by transmission / reception of identification information (ID), transfer of operation authority for realizing automatic traveling under the control of the control device 101, and the like are executed. .

  When communication is established in S801, the control device 101 (communication processing unit 501) transmits the map data of the parking lot P to the vehicle control device 410 in S802.

  In step S803, the control device 101 (parking lot data management unit 503) checks the parking area R in which the vehicle V on which the communication partner vehicle control device 410 is mounted is currently located. In the embodiment, the process of S803 is executed based on image data obtained by the monitoring camera 103 or the like.

  Then, in S804, the control device 101 (guidance route generation unit 504) generates a guidance route from the parking area R confirmed in S803 to the boarding area P2 that the vehicle V should follow in the automatic delivery.

  In step S805, the control device 101 (communication processing unit 501) transmits the guidance route generated in step S804 to the vehicle control device 410.

  On the other hand, the vehicle control device 410 (position estimation device 520) determines that the parking area R in which the vehicle V is currently stopped in S806 after the map data transmitted from the control device 101 in S802 is received via the communication device 407. Estimate the delivery position in the house. The delivery position is the current position (actual position) of the vehicle V in the parking area R, which is the starting point for delivery from the parking area R. For the estimation of the delivery position, the result of the image recognition processing of the image recognition apparatus 510 based on the image data obtained by the in-vehicle camera 408 can be used as in the above-described estimation of the actual position during automatic traveling. In the example illustrated in FIG. 8, the process of S806 is performed before the process of S805, but the process of S806 may be performed after the process of S805.

  When the delivery position is estimated in S806, and the guidance route transmitted from the control device 101 in S805 is received via the communication device 407, the vehicle control device 410 (travel control device 530), in S807, in S806. Based on the estimated delivery position and the like, a travel route is generated based on the guidance route to be traced in actual automatic delivery.

  Then, the vehicle control device 410 (travel control device 530) executes the exit control from the parking area R in S808.

  In step S809, the vehicle control device 410 (travel control device 530) executes travel control along the travel route generated in step S807. This travel control is also executed with the estimation of the actual position by the position estimation device 520 using the result of the image recognition processing by the image recognition device 510 as described above, similarly to the travel control in S709 of FIG.

  Then, vehicle control device 410 (travel control device 530) executes stop control to boarding area P2 in S810.

  Then, when the stop control in S810 is completed, the vehicle control device 410 (travel control device 530) transmits a notification of completion of delivery to the control device 101 via the communication device 407 in S811.

  As described above, automatic delivery in automatic valet parking is realized.

  FIG. 9 is an exemplary and schematic flowchart showing a schematic flow of an actual position estimation process executed by the vehicle control device 410 according to the embodiment during automatic traveling. The processing flow shown in FIG. 9 is repeatedly executed during the automatic traveling of the vehicle V in S709 shown in FIG. 7, S809 shown in FIG.

  In the processing flow shown in FIG. 9, first, in step S <b> 901, the vehicle control device 410 (image recognition device 510) acquires image data from the in-vehicle camera 408.

  In S902, the vehicle control device 410 (image recognition device 510) executes an image recognition process including a white line recognition process, so that the position of the road marking on the image data is obtained from the image data acquired in S901. To obtain road marking data.

  In step S <b> 903, the vehicle control device 410 (position estimation device 520) collates the road marking data with the map data, and estimates the actual position of the vehicle V. Then, the process ends.

  Hereinafter, the content of the actual position estimation process executed in S903 of FIG. 9 will be described in more detail.

  FIG. 10 is an exemplary and schematic flowchart illustrating a detailed flow of an actual position estimation process executed by the vehicle control device 410 according to the embodiment during automatic traveling.

  In the processing flow shown in FIG. 10, first, in S1001, the vehicle control device 410 (position estimation device 520) estimates the previous estimated value related to the actual position of the vehicle V based on the amount of change based on the sensor data, that is, odometry. By adding the amount of change in the position of the vehicle V, the actual position of the vehicle V based on odometry is calculated.

  In S1002, the vehicle control device 410 (position estimation device 520) compares the road marking relative to the actual position calculated in S1001 based on the road marking data obtained as a result of the image recognition processing of the image recognition device 510. Calculate the position. By using the relative position of the road marking calculated in S1002 and the actual position of the vehicle V calculated in S1001, the absolute position in calculation of the road marking can be specified.

  In step S <b> 1003, the vehicle control device 410 (position estimation device 520) specifies the normal absolute position of the road marking based on the map data acquired via the communication device 407. For example, the vehicle control apparatus 410 (position estimation apparatus 520) is close to the absolute position in calculation of the road marking specified by using the calculation result of S1002 from the absolute positions of all road markings included in the map data. Is extracted, the normal absolute position of the road marking that is the target of calculating the difference from the calculated absolute position in the processing of the next S1004 is specified.

  In S1004, the vehicle control device 410 (position estimation device 520) determines the absolute position in calculation of the road marking specified based on the calculation result in S1002 and the normal absolute position of the road marking specified in S1003. , And based on the difference, the calculated value of S1001, that is, the calculated value of the actual position of the vehicle V based on odometry is corrected.

  In step S1005, the vehicle control device 410 (position estimation device 520) estimates the corrected value in step S1004 as a normal actual position of the vehicle V. In the embodiment, based on the estimation result of S1005, various parameters (vehicle speed, rudder angle, traveling direction, etc.) required when the vehicle V is automatically driven by the traveling control device 530 are set.

  As described above, the vehicle control device 410 according to the embodiment includes the plurality of ECUs 400 that realize the image recognition device 510, the position estimation device 520, and the travel control device 530. The image recognition device 510 and the travel control device 530 are realized by different ECUs 400, and the position estimation device 520 and the travel control device 530 are realized by the same ECU 400.

  According to the embodiment, based on the above configuration, the traveling control device 530 that requires high processing capability and the image recognition device 510 that requires the ability to handle large amounts of data are separated from each other. Can be realized. Further, when the map data has a relatively small capacity, the position estimation device 520 that does not require the ability to handle large volumes of data is required to have a high processing capacity (that is, the ability to handle large volumes of data is not so much). (Not required) can be realized by the same ECU 400 as the traveling control device 530. As a result, when the map data has a relatively small capacity, the processing can be shared by a plurality of computers according to the required performance, so that an accurate grasp of the actual position of the vehicle V during automatic traveling can be obtained. Can be realized efficiently.

  Further, in the embodiment, the position estimation device 520 and the travel control device 530 realized by the same ECU 412 respectively acquire map data and a travel route from the control device 101 via the communication device 407. According to such a configuration, the map data and the travel route are acquired from the control device 101 to the ECU 412 via the communication device 407 (and the in-vehicle network 450) through the same route, so that the efficiency of data transmission / reception is improved. be able to.

<Modification>
In the above-described embodiment, the case where the technology of the present invention is applied to an automatic valet parking system is illustrated. However, the technology of the present invention can be applied to parking systems other than the automatic valet parking system as long as an appropriate road marking is installed in the parking lot and data on the absolute position of the road marking can be acquired. is there.

  Moreover, in embodiment mentioned above, the structure which acquires map data from the control apparatus 101 by communication is illustrated. However, as a modification, a configuration in which map data is stored in advance in the vehicle control device 410 is also conceivable.

  Similarly, in the above-described embodiment, a configuration in which a travel route (guidance route) is acquired from the control device 101 by communication is illustrated. However, as a modified example, a configuration in which a travel route is appropriately generated only on the vehicle control device 410 side based on information acquired from various sensors provided in the in-vehicle camera 408 or the vehicle V is also conceivable.

  As mentioned above, although embodiment and the modification of this invention were described, embodiment and the modification which were mentioned above are an example to the last, Comprising: It is not intending limiting the range of invention. The above-described novel embodiments and modifications can be implemented in various forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. The above-described embodiments and modifications are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

101 Control device 400 ECU (computer)
407 Communication device 408 In-vehicle camera 410 Vehicle control device 411 ECU (first computer)
412 ECU (second computer, third computer)
510 image recognition device 511 image data acquisition unit 512 road marking data acquisition unit 520 position estimation device 521 map data acquisition unit 522 position estimation unit 530 travel control device 531 route acquisition unit 532 travel control unit L, L61 to L63 lane markings (road markings) )
M, M61, M62 Marker (road marking)
P Parking lot P1 Alighting area P2 Boarding area R Parking area V Vehicle

Claims (3)

An image data acquisition unit that acquires image data obtained by an in-vehicle camera that captures the situation around the vehicle, and an image recognition process based on the image data, and is installed on a road surface of a parking lot where the vehicle travels A road marking data acquisition unit that acquires road marking data related to road markings, and an image recognition device including:
The map data acquisition unit for acquiring map data of the parking lot including the absolute position of the road marking, the road marking data acquired by the road marking data acquisition unit, and the map data acquired by the map data acquisition unit A position estimation unit that estimates the actual position of the vehicle by comparing
A travel state of the vehicle based on a route acquisition unit that acquires a travel route to be traced by automatic traveling of the vehicle, the travel route acquired by the route acquisition unit, and the actual position estimated by the position estimation unit A travel control unit that performs the automatic travel based on the travel route by controlling
Equipped with multiple computers
Of the plurality of computers, a first computer that realizes the image recognition device and a second computer that realizes the travel control device are different from each other, and a third computer that realizes the position estimation device and the travel control device are realized. The second computer is identical to each other,
Vehicle control device. A control device provided corresponding to the parking lot, further comprising a communication device that holds the map data and communicates with a control device that generates the travel route according to the situation in the parking lot,
The map data acquisition unit of the position estimation device acquires the map data from the control device via the communication device,
The route acquisition unit of the travel control device acquires the travel route from the control device via the communication device;
The vehicle control device according to claim 1. The automatic traveling is performed in the parking lot including a dismounting area, a boarding area, and a parking area. Automatic parking for automatically moving to and parking, and after the automatic parking is completed, the vehicle exits from the parking area in response to a predetermined call, and automatically exits to the boarding area and stops automatically ,including,
The vehicle control device according to claim 1 or 2.

Images