JP2017121865A - Automatic drive vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the convenience of the user of an automatic drive vehicle.SOLUTION: An automatic drive vehicle (1) includes: an imaging part (13) for imaging at least a part of surroundings of a vehicle itself; a storage part (12) for pre-storing user image information related to a user of the vehicle and gesture image information related to one or plural gestures representing a given vehicular action; and control parts (11, 12) for collating at least an image imaged by the imaging part with the user image information, identifying a user gesture from the image imaged by the imaging part and the gesture image information under a condition that a user exists nearby the vehicle, and automatically controlling the vehicle so as to perform a vehicular action represented by the identified gesture.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a technical field of an autonomous driving vehicle that performs autonomous driving.

  As this type of vehicle, a vehicle that is remotely operated by a mobile terminal possessed by a user has been proposed (see Patent Document 1). In particular, it is disclosed that the delivery position is determined based on the parking position of the host vehicle and the position of the user who is scheduled to board the host vehicle, and the host vehicle automatically moves to the determined exit position. ing.

JP 2013-177128 A

  The technique described in Patent Document 1 has room for improvement in terms of user convenience.

  This invention is made | formed in view of the said fact, and makes it a subject to provide the autonomous driving vehicle which can improve a user's convenience.

  In order to solve the above-described problem, an autonomous driving vehicle according to the present invention includes an imaging unit that images at least a part of the periphery of the vehicle, user image information regarding a user of the vehicle, and one or a plurality of predetermined vehicle operations. A storage unit that preliminarily stores gesture image information related to the gesture, and an image captured by at least the image capturing unit and the user image information, and on the condition that the user exists in the vicinity of the vehicle A control unit that identifies the user's gesture from the image captured by the imaging unit and the gesture image information, and automatically controls the vehicle so that the vehicle operation indicated by the identified gesture is executed; Prepare.

  The self-driving vehicle of the present invention specifies a user's gesture from an image captured by the imaging unit, and automatically executes a vehicle operation indicated by the identified gesture. From the user's viewpoint, the user can remotely control the vehicle by making a predetermined gesture. Therefore, according to the present invention, the convenience of the user can be improved as compared with, for example, a case where the vehicle is remotely operated by a portable terminal.

  In one aspect of the autonomous driving vehicle of the present invention, the vehicle further includes a receiving unit that receives a radio signal transmitted from an electronic key corresponding to the vehicle, and the control unit receives the radio signal when the receiving unit receives the radio signal. The image captured by the image capturing unit is collated with the user image information.

  According to this aspect, when the receiving unit receives the radio signal of the electronic key corresponding to the vehicle (that is, when the user is within a certain range from the vehicle), the captured image and the user image Verification with information is performed (that is, user recognition is performed). For this reason, for example, the power consumption of the vehicle in standby can be suppressed.

  The effect | action and other gain of this invention are clarified from the form for implementing demonstrated below.

It is a block diagram which shows the structure of the autonomous driving vehicle which concerns on embodiment. It is a flowchart which shows a part of process which the automatic driving vehicle which concerns on embodiment performs. It is a flowchart which shows the remote operation process which concerns on embodiment.

  An embodiment according to the autonomous driving vehicle of the present invention will be described with reference to FIGS. 1 to 3. The self-driving vehicle according to the present embodiment is configured to automatically move within a predetermined range (for example, several meters to several tens of meters) in accordance with the recognized gesture when the gesture of the user outside the vehicle can be recognized. Has been. The self-driving vehicle can perform parking and unloading with a gesture, particularly when the parking space is relatively narrow and it is difficult to get on and off in the state where the parking space is parked. That is, the user can remotely control the autonomous driving vehicle by a relatively simple method called gesture.

  Below, the outline | summary of an autonomous driving vehicle is demonstrated first, and the remote control process is demonstrated next, giving the example of leaving an autonomous driving vehicle from a parking space first.

(Vehicle configuration)
The configuration of the autonomous driving vehicle according to the embodiment will be described with reference to FIG. Note that the autonomous driving vehicle according to the present embodiment may be a vehicle including only an engine as a drive source (a so-called conventional vehicle), a hybrid vehicle, or an electric vehicle. .

  In FIG. 1, an automatic driving vehicle 1 includes a control personal computer (hereinafter referred to as “control PC” as appropriate) 11, a recognition personal computer (hereinafter referred to as “recognition PC” as appropriate) 12, and automatic operation. Transmission from a camera 13 that captures at least a part of the periphery of the vehicle 1, a camera 14 that captures at least a part of the interior of the autonomous driving vehicle 1, a map database 15, and an electronic key 20 corresponding to the autonomous driving vehicle 1. Receivers 16a to 16d that can receive the received radio wave signal, a vehicle speed sensor 17, and an object detection sensor 18 such as Lidar (Light Detection and Ranging), for example.

  The control PC 11 issues the automated driving vehicle 1 based on a predetermined delivery program according to an instruction from the user of the autonomous driving vehicle 1 (details will be described later).

  The recognition PC 12 stores in advance user image information including a face image of the user of the autonomous driving vehicle 1 and gesture image information related to a gesture indicating a vehicle behavior related to the leaving program, such as a hard disk or a nonvolatile memory. A storage unit (not shown) is included.

  The gesture image information includes a gesture corresponding to “GO” (for example, raising one hand, beckoning, etc.) indicating execution of the exit program, and a gesture (for example, pointing up) corresponding to “STOP” indicating emergency stop. Etc.). The gesture image information is not limited to “GO” and “STOP”, and may include three or more gestures, or may include only one gesture.

  Since various existing aspects can be applied to the components other than the control PC 11 and the recognition PC 12, a detailed description thereof will be omitted. Each of the cameras 13 and 14 is not limited to one camera and may be composed of a plurality of cameras.

(Processing when parking)
Next, processing executed when the control PC 11 is parked in the parking space will be described with reference to the flowchart of FIG. The control PC 11 and the receiving units 16a to 16d are supplied with minute electric power from a battery (not shown) even when the autonomous driving vehicle 1 is parked (that is, when the ignition is off).

  In FIG. 2, the control PC 11 detects the approach of the user of the autonomous driving vehicle 1 (here, the person holding the electronic key 20) (step S101). Specifically, the control PC 11 estimates the distance between the autonomous driving vehicle 1 and the user based on the reception intensity of the radio signal transmitted from the electronic key 20 in at least one of the receiving units 16a to 16d. To do. The control PC 11 determines that the approach of the user has been detected when the estimated distance is within a predetermined distance.

  If the approach of the user is not detected in the process of step S101 (step S101: No), the control PC 11 once ends the process, and executes the process of step S101 again after a predetermined time.

  On the other hand, when the approach of the user is detected in the process of step S101 (step S101: Yes), the control PC 11 moves the user based on the time change of the reception intensity of the radio signal transmitted from the electronic key 20. A speed is obtained and it is determined whether or not the obtained moving speed is equal to or higher than a certain speed (step S102).

  As a result of the determination in step S102, when it is determined that the determined moving speed is equal to or higher than a certain speed (step S102: Yes), the control PC 11 once ends the process, and after a predetermined time, performs the process in step S101 again. Run. This is because there is a high possibility that the user will pass around the autonomous driving vehicle 1.

  On the other hand, as a result of the determination in step S102, when it is determined that the obtained moving speed is less than the constant speed (step S102: No), the control PC 11 turns on the power of the autonomous driving vehicle 1 (step S103). . As a result of the processing in step S103, power is supplied to the recognition PC 12, the cameras 13 and 14, and the like.

  Here, “turning on the power” means a state in which main electrical components can be started and the engine can be started in a so-called conventional vehicle, and in a hybrid vehicle or an electric vehicle, the vehicle can be driven. (So-called ready state).

(Remote operation processing)
Next, the remote operation process executed after the process of step S103 described above will be described with reference to the flowchart of FIG. In the present embodiment, an example is given in which the autonomous driving vehicle 1 is left from a parking space by remote control.

1. Recognition PC operation (1)
In FIG. 3, the recognition PC 12 determines the position of the electronic key 20 (for example, centering on the autonomous driving vehicle 1 based on the reception intensity of the radio signal transmitted from the electronic key 20 received by each of the receiving units 16 a to 16 d. And the like, the distance from the autonomous driving vehicle 1, etc.) are specified (step S211). Since the existing technique can be applied to the method for specifying the position of the electronic key 20, a detailed description thereof will be omitted.

  Next, the recognition PC 12 includes the image corresponding to the position of the electronic key 20 specified in the process of step S211 among the images captured by the camera 13 and the user image information stored in advance in the storage unit. The face image to be checked is collated (step S212).

  Next, the recognition PC 12 determines whether or not a driver (here, a user holding the electronic key 20) has been identified (step S213). Specifically, the recognition PC 12 collates the image captured by the camera 13 with the face image included in the user image information (that is, performs face authentication based on the face image), and there is a corresponding person. It is determined that the driver has been identified. On the other hand, when there is no corresponding person, the recognition PC 12 determines that the driver is not specified.

  Note that “there is no corresponding person” is not limited to the case where there is no user indicated by the user image information. For example, the user cannot be clearly imaged due to some obstacle such as another person or a building, and face authentication cannot be performed. Including cases.

  As a result of the determination in step S213, when it is determined that the driver is not specified (step S213: No), the recognition PC 12 once ends the process, and executes the process of step S211 again after a predetermined time.

  On the other hand, if it is determined that the driver has been specified as a result of the determination in step S213 (hereinafter, “user holding the electronic key 20” is referred to as “driver” as appropriate) (step S213: Yes), the recognition PC 12 The driver image included in the image captured by the camera 13 is stored in the storage unit (hereinafter referred to as “stored specific driver image”).

  The recognition PC 12 further collates the driver image included in the image captured by the camera 13 with the gesture image information stored in advance in the storage unit. Specifically, for example, the recognition PC 12 extracts feature points from the driver image, and performs pattern matching using the extracted feature points and gesture image information.

  Subsequently, the recognition PC 12 determines whether or not the driver's gesture has been recognized (that is, whether or not the driver's gesture has been identified) based on the collation result (step S214).

  As a result of the determination in step S214, if it is determined that the driver's gesture is not recognized (step S214: No), the recognition PC 12 may end the process once and execute the process in step S211 again after a predetermined time. . In the process of step S214, typically, when a gesture is not recognized within a predetermined recognition period after the driver is specified, it is determined that “the gesture is not recognized”. Therefore, the recognition PC 12 collates the driver image included in the images sequentially captured by the camera 13 within the recognition period with the gesture image information.

  On the other hand, if it is determined as a result of the determination in step S214 that the driver's gesture has been recognized (step S214: Yes), the recognition PC 12 determines whether or not the driver is intentionally performing the gesture (that is, remote to the driver). It is determined whether or not there is an intention to operate (step S215).

  Specifically, for example, the recognition PC 12 specifies (i) the driver's line-of-sight direction from the image captured by the camera 13, and whether the specified line-of-sight direction is the direction of the autonomous driving vehicle 1, and (Ii) It is determined from the image captured by the camera 13 whether or not the driver continues the gesture recognized in the process of step S214. In the recognition PC 12, the direction of the identified driver's line of sight is the direction of the autonomous driving vehicle 1 (that is, the driver is looking at the autonomous driving vehicle 1), and the driver continues the recognized gesture. Then, it is determined that the driver has the will of remote control.

  As a result of the determination in step S215, if it is determined that the driver does not intend to perform remote operation (step S215: No), the recognition PC 12 ends the process once, and executes the process in step S211 again after a predetermined time. Also good.

  On the other hand, if it is determined as a result of the determination in step S215 that the driver is willing to perform remote control (here, it is assumed that the driver is performing a gesture corresponding to “GO” meaning execution of the exit program). (Step S215: Yes), the recognition PC 12 transmits a signal indicating an instruction to leave the autonomous driving vehicle 1 to the control PC 11 (Step S216).

2. Operation of control PC (1)
The control PC 11 that has received the signal indicating the exit instruction from the recognition PC 12 blinks a hazard lamp or the head, for example, to notify the driver (and the surrounding people) that the autonomous driving vehicle 1 moves. A light is turned on (step S231).

  Subsequently, the control PC 11 uses a steering mechanism (not shown), based on signals from various sensors including the vehicle speed sensor 17 so that the autonomous driving vehicle 1 moves to a delivery position preset by the delivery program. A drive mechanism (not shown) and a braking mechanism (not shown) are each controlled (step S232).

  Here, the exit position and the route of the autonomous driving vehicle 1 to the exit position are the position of the autonomous driving vehicle 1 recognized by, for example, GPS (Global Positioning System) (not shown), the map database 15, and the camera 13. And the detection result of obstacles around the autonomous driving vehicle 1 by the object detection sensor 18. The delivery position is typically set to a position (for example, a position at which the door can be opened at least about 60 degrees) that can secure a space where the driver can get into the autonomous driving vehicle 1 with a margin. For specific examples of the delivery position and the course, see the above-mentioned Patent Document 1.

  Further, during the movement of the autonomous driving vehicle 1, the control PC 11 causes the autonomous driving vehicle 1 to temporarily stop (further change the course) according to the obstacle detection result by the camera 13 or the object detection sensor 18. Control the braking mechanism. For example, when the autonomous driving vehicle 1 is temporarily stopped, the control PC 11 may be configured to blink the headlight to notify the driver that the vehicle is temporarily stopped.

  When the autonomous driving vehicle 1 is a so-called conventional vehicle, the engine is automatically started in the process of step S232. Further, when the autonomous driving vehicle 1 is a hybrid vehicle, the engine is automatically started as necessary.

3. Operation of PC 12 for recognition (2)
The PC 12 for recognition collates the image of the driver included in the image captured by the camera 13 with the gesture image information while the autonomous driving vehicle 1 is moving (that is, after the processing in step S216 described above). Then, it is determined whether or not a gesture corresponding to “STOP” meaning an emergency stop has been performed (step S217).

  As a result of the determination in step S217, if it is determined that the driver does not perform a gesture corresponding to STOP (step S217: No), the recognition PC 12 determines whether or not the automatic driving vehicle 1 has stopped at a predetermined delivery position. Is determined (step S218). It is determined based on a signal output from the control PC 11 whether or not the automatic driving vehicle 1 has stopped at a predetermined delivery position.

  As a result of the determination in step S218, when it is determined that the autonomous driving vehicle 1 is not stopped (moving) at the predetermined leaving position (step S218: No), the recognition PC 12 executes the process of step S217. To do. That is, the recognition PC 12 always monitors the driver's gesture while the autonomous driving vehicle 1 is moving.

  In addition, when the driver interrupts the gesture during the movement of the automatic driving vehicle 1 or when the driver's line of sight is different from the direction of the automatic driving vehicle 1 (that is, in the process of step S215 described above, the driver If the condition for determining that the user is willing to perform remote operation is not satisfied), the recognition PC 12 may transmit a signal indicating that the driver does not intend to perform remote operation to the control PC 11. In this case, the control PC 11 may stop the automatic driving vehicle 1 at a safe position while confirming the situation around the automatic driving vehicle 1.

  As a result of the determination in step S217, if it is determined that the driver has made a gesture corresponding to STOP (step S217: Yes), the recognition PC 12 transmits a signal indicating STOP to the control PC 11. Thereafter, the recognition PC 12 executes a process of step S219 described later.

4). Operation of control PC 11 (2)
In parallel with the processing of steps S217 and S218 described above, the control PC 11 determines whether or not the driver has made a gesture corresponding to STOP (step S233). When receiving the signal indicating STOP from the recognition PC 12, the control PC 11 determines that the driver has made a gesture corresponding to the STOP.

  As a result of the determination in step S233, if it is determined that the driver has made a gesture corresponding to STOP (step S233: Yes), the control PC 11 controls the braking mechanism so that the autonomous driving vehicle 1 immediately stops ( Step S236), the process of step S237 described later is executed.

  On the other hand, as a result of the determination in step S233, if it is determined that the driver does not perform a gesture corresponding to STOP (step S233: No), the control PC 11 determines whether the automatic driving vehicle 1 has moved to a predetermined delivery position. It is determined whether or not (step S234).

  As a result of the determination in step S234, when it is determined that the autonomous driving vehicle 1 has not moved to the predetermined leaving position (step S234: No), the control PC 11 executes the process in step S233. Whether or not the vehicle has moved to a predetermined delivery position may be determined based on, for example, the position of the autonomous driving vehicle 1 recognized by the GPS and the map database 15.

  On the other hand, as a result of the determination in step S234, when it is determined that the automatic driving vehicle 1 has moved to the predetermined delivery position (step S234: Yes), the control PC 11 sets the braking mechanism so that the automatic driving vehicle 1 stops. Control is performed (step S235). At this time, the control PC 11 transmits a signal indicating the stop of the autonomous driving vehicle 1 to the recognition PC 12.

  Subsequently, the control PC 11 blinks the headlight, for example, and notifies the driver that the autonomous driving vehicle 1 has stopped (step S237).

5. PC operation for recognition (3)
As a result of the determination in step S218 described above, when it is determined that the automatic driving vehicle 1 has stopped (that is, when the recognition PC 12 receives a signal indicating the stop of the automatic driving vehicle 1 from the control PC 11) (step S218). : Yes), or when it is determined that the driver has made a gesture corresponding to STOP (step S217: Yes), the recognition PC 12 receives the image captured by the camera 14 and the stored specific driver image described above. To recognize the passenger of the autonomous driving vehicle 1 (step S219).

  Subsequently, the recognition PC 12 determines whether or not the passenger is the same as the user specified as the driver in the process of step S213 described above (step S220). As a result of the determination in step S220, when it is determined that they are the same (step S220: Yes), the recognition PC 12 transmits a signal indicating the same to the control PC 11 (step S221), and the processing Exit.

  On the other hand, as a result of the determination in step S220, when it is determined that they are not the same (step S220: No), the recognition PC 12 transmits a signal indicating that they are not the same to the control PC 11, and ends the process.

Note that the recognition PC 12 determines that the board for the automatic driving vehicle 1 is not detected even after a predetermined time (for example, several minutes) has elapsed since the automatic driving vehicle 1 is stopped after the delivery program is executed. A signal indicating that there is no boarding may be transmitted. In this case, the control PC 11
If the automatic driving vehicle 1 is a so-called conventional vehicle, the engine may be stopped, and if the automatic driving vehicle 1 is a hybrid vehicle or an electric vehicle, the ready-off state may be set. If possible, the recognition PC 12 may notify the user specified as the driver in the above-described processing of step S213 by e-mail or the like, for example.

6). Operation of control PC (3)
After the process of step S237 described above, the control PC 11 determines whether or not the passenger is the same as the user specified as the driver in the process of step S213 described above (step S238).

  If the control PC 11 receives a signal indicating that it is the same from the recognition PC 12, it determines that they are the same (step S 238: Yes), maintains the current state of the autonomous driving vehicle 1, and ends the process. To do.

  On the other hand, if the control PC 11 receives a signal indicating that it is not the same from the recognition PC 12, it determines that they are not the same (step S238: No), and stops the engine if the autonomous driving vehicle 1 is a so-called conventional vehicle. If the autonomous driving vehicle 1 is a hybrid vehicle or an electric vehicle, the ready-off state is set (step S239), and the process is terminated.

(effect)
According to the remote operation process described above, a gesture performed by the user is recognized, and a predetermined delivery program is executed in accordance with the recognized gesture. In other words, as long as the user performs a predetermined gesture, the user can move the automatic driving vehicle 1 to a predetermined delivery position. That is, the user can remotely operate the autonomous driving vehicle 1 by a relatively simple method.

  The “recognition PC 12” and the “camera 13” according to the embodiments are examples of the “storage unit” and the “imaging unit” according to the present invention, respectively. The “control PC 11” and the “recognition PC 12” according to the embodiment are examples of the “control unit” according to the present invention.

  In the above-described embodiment, the example in which the autonomous driving vehicle 1 is delivered by the delivery program is described. However, for example, the automatic driving vehicle 1 may be parked at a predetermined parking position by the parking program.

  The present invention is not limited to the above-described embodiment, and can be appropriately changed without departing from the gist or concept of the invention that can be read from the claims and the entire specification. Is also included in the technical scope of the present invention.

  DESCRIPTION OF SYMBOLS 1 ... Self-driving vehicle, 11 ... Personal computer for control, 12 ... Personal computer for recognition, 13, 14 ... Camera, 15 ... Map database, 16a-16d ... Reception part, 17 ... Vehicle speed sensor, 18 ... Object detection sensor

Claims (2)

An imaging unit that images at least a part of the periphery of the vehicle;
A storage unit that stores in advance user image information related to a user of the vehicle and gesture image information related to one or more gestures indicating a predetermined vehicle operation;
At least the image captured by the imaging unit and the user image information are collated, and on the condition that the user exists around the vehicle, from the image captured by the imaging unit and the gesture image information, A control unit that identifies the user's gesture and automatically controls the vehicle so that the vehicle operation indicated by the identified gesture is executed;
An automatic driving vehicle comprising: A receiver for receiving a radio signal transmitted from an electronic key corresponding to the vehicle;
The self-driving vehicle according to claim 1, wherein the control unit collates an image captured by the imaging unit with the user image information when the reception unit receives the radio signal.

Images