JP3210649B2 - Autonomous mobile robot - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an autonomous mobile robot, and more particularly to, for example, a guide robot or a security robot in an exhibition hall, which determines the direction of surrounding people.
A new autonomous mobile robot.

[0002]

2. Description of the Related Art When a robot walking around an exhibition hall explains a nearby exhibit to a visitor who meets in the venue, the robot needs to determine not only the position of the visitor and the exhibit but also the orientation of the visitor. . This is because the instructions to the visitor are different between the case where the visitor is walking with his / her back to the robot and the case where he is walking toward the robot. For example, if there is an exhibit on the right side of the robot and the visitor is walking with the robot behind, the robot can say "There is an exhibit on the right side", but the visitor is walking toward the robot Then the robot needs to say, "There is an exhibit on the left."

[0003] For this reason, conventionally, a camera is mounted on a robot, and a photographed image is processed to determine the orientation of a visitor around the robot.

[0004]

However, in order to determine the orientation of a visitor, it is necessary to detect the visitor before that. In the prior art, the detection of the visitor was also performed by image processing. For this reason, it takes time until the guide message is issued to the visitor, and there is also a problem in the detection accuracy of the visitor before that.

[0005] Therefore, a main object of the present invention is to provide an autonomous mobile robot capable of accurately determining the direction of the face of a person in the vicinity in a short time.

[0006]

According to the present invention, there is provided a detecting means for detecting the presence of a person by using a high-frequency signal from a transmitting source carried by a person, and transmitting the signal when the detecting means detects a person.
Direction changing means for changing the direction of the robot to the direction of the source, direction
The orientation of the robot by can changing means comprises determining means for determining the orientation of a human face based on the image captured by the photographing unit to photograph between human <br/> come to have been changed, and the imaging means, the autonomous mobile robot It is.

[0007]

A high frequency signal is output from a transmission source carried by a human. The detecting means detects the presence of a human in the surroundings based on the high-frequency signal. When the presence of a human is detected, the direction changing means changes the direction of the robot to the source of the robot.
The direction is changed to the direction of the person, the photographing means photographs the person, and the determining means determines the direction of the human face based on the photographed image.

[0008] The determination means is preferably a face area detection means,
It includes a skin color region extracting unit, a ratio calculating unit, and a direction determining unit. The face area detection means detects a human face area based on the captured image, and the skin color area extraction means extracts a skin color area from the face area. The ratio calculating means calculates the ratio of the skin color area to the face area, and the direction determining means determines the direction of the person based on the calculated ratio.

[0009]

According to the present invention, the presence of a human is detected by a signal from a transmitter carried by the human, and the determination of the orientation of the human face is made based on the photographed image of the human. Therefore, the direction of the person around the face can be accurately determined in a short time.

The above objects, other objects, features and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

[0011]

FIG. 1 is a front view showing an autonomous mobile robot 10 according to one embodiment of the present invention. Referring to FIG. 1, the autonomous mobile robot of this embodiment (hereinafter simply referred to as “robot”)
That. 10) includes a main body or a housing 12 and a housing 1
A wheel 14 is provided at the lower part of the wheel 2 so as to be rotatable around a shaft 16.
The wheels 14, ie, the shaft 16, are driven by a motor 36 (FIG. 2), which allows the robot 10 to move in any direction.

Although not shown, a power transmission mechanism, such as a differential gear, capable of independently controlling the left and right wheels is incorporated in connection with the shaft 16 or the wheels 14. Further, two motors may be used to independently control the left and right wheels 14. Since such a drive system itself does not have a characteristic, other configurations of the drive system are conceivable.

The housing 12 is formed in a substantially rectangular plane, and high-frequency sensors 18 are arranged on four side surfaces thereof. When each high-frequency sensor 18 detects a high-frequency signal of a predetermined frequency, it outputs a detection signal to a microcomputer 24 (FIG. 2) described later.
Output to The microcomputer 24 detects the presence of the high-frequency transmitter in the surroundings based on the detection signal. An image sensor 20 having, for example, a CCD camera is provided on the front surface of the housing 12. Image sensor 2
In the case of 0, an object ahead is photographed by the CCD camera, and a photographed image signal is output to the microcomputer 24. A speaker 22 is provided on the upper surface of the housing 12. The speaker 24 captures the synthesized voice data generated by the microcomputer 24 and emits a corresponding synthesized voice.

Referring to FIG. 2, a microcomputer 24 is provided in housing 12 of FIG. Although one microcomputer 24 is shown in FIG. 2, a plurality of microcomputers may be provided as necessary, and tasks such as image processing, sound processing, and drive control may be shared among the microcomputers. However, in the following description, one or more microcomputers are represented by the microcomputer 24 for convenience.

The microcomputer 24 includes the high-frequency sensor 18 and the image sensor 2 described with reference to FIG.
It receives the input from 0 and gives the synthesized voice data to the speaker 22. Although not shown in FIG. 1, the robot 10 is further provided with an encoder 30 and a compass 32. The encoders 30 are individually provided for the left and right wheels 14, and input pulse signals of a number corresponding to the number of rotations of each wheel 14 to the microcomputer 26. The microcomputer 24 counts the pulse signals from each of the enders 30 and calculates the speed at which the robot 10 is moving and the position that changes every moment. The compass 32 is for knowing the azimuth (moving direction) of the robot 10.

Here, as shown in FIG. 3, the room used by the inventors for the experiment on the robot 10 is a substantially square room of 4 m square, and the room is divided into four blocks. The door part starts, the destination is set at a diagonal position, and the exhibit 40 is placed in the upper right block.
A person 38 carrying a high-frequency transmitter 38a is walking around the room.

The map data of the room (indicating the destination and the exhibit) is stored in the RAM 28 of the microcomputer 24 in advance, and the robot 10 receives the map data and inputs from the encoder 32 and the compass 34 described above. You can know the current location. The RAM 28 also stores travel route data, and the robot 10
Moves in the room according to the movement route data.
The stored travel route is indicated by an arrow in FIG. on the other hand,
The ROM 26 stores a main program for autonomous movement and an interrupt processing program executed in response to a detection signal from the high frequency sensor 18.

Referring to FIG. 4, the operation of the microcomputer 24 when processing the interrupt processing program will be described. When a detection signal indicating the detection of a high-frequency signal is given from the high-frequency sensor 18, the direction of the robot 10 is first changed to the direction of the source of the high-frequency signal in step S 1, and then the captured image signal from the image sensor 20 is changed in step S 3. take in. By changing the direction of the robot 10, the captured image signal includes an image of the person 38 carrying the high-frequency transmitter 38a.

In step S5, a whole body image of the human 38 is extracted from the captured image by the background subtraction method. In step S7, a face area is recognized from the extracted whole body image.
The face area is recognized through a contour line extraction process from the whole body image and a feature point detection process from the contour line. Subsequently, in step S9, a skin color area is extracted from the face area, and in step S11, the ratio of the skin color area to the face area is calculated. Step S
In 13, the orientation of the face of the human 38 is determined based on the calculated ratio of the skin color region and the position of the skin color region.

That is, if the skin color area occupies most of the face area, it is determined that the face is facing in the direction facing the robot 10, and if there is almost no skin color area, the face is in the same direction as the robot 10. It is determined that it is suitable. When the skin color area occupies about half of the face area and the skin color area is located on the right side of the face area, it is determined that the face is facing the front right of the robot 10, and conversely, the skin color area is If the face is located on the left side of the area, it is determined that the face is facing the front left of the robot 10.

In step S15, the position of the exhibit 40 is specified based on the map data stored in advance. In step S17, guidance according to the relationship between the position and orientation of the person 38 and the position of the exhibit 40 is provided by the speaker 22. Emanates from. In other words, when the exhibit 40 exists behind the human 38, "there is an exhibit behind", and when the exhibit 40 exists in front of the human 38, "there is an exhibit ahead." To tell. Also, when the exhibit 40 is on the right side of the human 38, it says "there is an exhibit on the right", and when the exhibit 40 is on the left of the human 38, it is "there is an exhibit on the left." To tell.

Referring to FIG. 3, human 38
When walking from the front left to the front right, the robot 10 detects the presence of the human 38 based on the high-frequency signal. Then, the robot 10 captures a whole body image of the human 38, and determines that the human 38 is facing right front based on the captured image. The robot 10 further specifies the position of the exhibit 40 based on the map data. And human 3
8 and the position of the exhibit 40,
Say "There is an exhibit on the left."

According to this embodiment, the robot first detects the presence of a human in the vicinity by using a frequency signal from a transmitter carried by the human. Then the robot
Photographing is performed in the direction in which a human exists, and the direction of the human is determined based on the captured image. As described above, the detection of the position of the human is performed by the high-frequency signal, and the image processing is performed on the captured image including the human image without fail. Therefore, as compared with the related art, the accuracy of detecting a person is improved, and the time required for image processing is reduced.

When the above-mentioned robot is placed in the exhibition hall, a method of giving a card with a built-in high-frequency transmitter to a visitor who visits the exhibition hall at the time of entry can be considered.
Here, register the visitor data such as the name of the visitor and what field you are interested in on the card, transmit it together with the high-frequency signal, and make the robot output a voice message related to the visitor data It may be. As a voice message, "**, on your left
○ is on display ”, and“ △△, □□ on your right are also interested in the same field as you ”.

In this embodiment, a high-frequency signal from a transmitter carried by a human is detected by a high-frequency sensor.
Thus, the presence of a human in the vicinity is detected. However, a signal used for detecting the presence of a human may be an infrared signal or an ultrasonic signal other than the high-frequency signal.
In this case, a human needs to carry an infrared transmitter or an ultrasonic transmitter, and the robot needs to be provided with an infrared sensor or an ultrasonic sensor.

[Brief description of the drawings]

FIG. 1 is an illustrative front view showing a robot according to an embodiment of the present invention;

FIG. 2 is a block diagram showing a configuration of the robot of the embodiment in FIG. 1;

FIG. 3 is an illustrative view showing an outline of a room used in the experiment;

FIG. 4 is a flowchart showing a part of the operation of the embodiment in FIG. 1;

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 10 ... Robot 14 ... Wheel 18 ... High frequency sensor 20 ... Image sensor 22 ... Speaker 24 ... Microcomputer 30 ... Encoder 32 ... Compass 34 ... Motor

────────────────────────────────────────────────── ─── Continuing on the front page (72) Inventor Shiro Takada 5th Sanriya, Seiya-cho, Seika-cho, Kyoto, Japan No. 5, Hiratani, Seiya-cho, Gunma-cho, Japan A / T R & D Co., Ltd. (72) Inventor Ryuichi Nishimura Ritsuichi Nishimura, No. 5, Sanya-ya, Seika-cho, Kyoto, Soraku-gun, Kyoto A.T. Inside the Intelligent Video Communication Research Laboratory (72) Inventor Haruo Noma Kyoto, Sagara-gun, Seika-cho, 5th Inuiya small character Sanraya, 5th A.T.R., Inc.Intellectual Video Communication Research Laboratory (72) Inventor Toshiaki Sugihara, Kyoto, Japan Seikacho, Inaya, Sub-section, Sanraya, 5 AIT Co., Ltd. In-house (72) Inventor Tsutomu Miyazato 5 in Saniya, Saika-cho, Kyoto Prefecture, Japan No. 5 Mihiraya Inside ATR Intelligent Video Communications Laboratory (56) References JP-A-4-76698 (JP, A) JP-A-6-274584 (JP, A) JP-A-8-138024 (JP, A) JP-A-2000-268180 (JP, A) Tetsuo Ono (Two others), Creation of Relationships in Social Communication of Robots Symbiotic with Humans, IPSJ Research Report, October 1998 2nd, Vol. 98, No. 90, p43-49 (58) Fields investigated (Int. Cl. ⁷ , DB name) B25J 13/08 B25J 5/00 G06T 1/00 340 G06T 7/60 150 JICST file (JOIS)

Claims (2)

(57) [Claims] 1. A detecting means for detecting the presence of a human being by a high-frequency signal from a transmitting source carried by a human, and in the direction of the transmitting source when the detecting means detects a human being.
Direction changing means for changing the orientation of the robot, the orientation imaging means for imaging between humans can and <br/> the orientation of the robot is changed by the changing means, and the human face based on the image captured by the imaging means An autonomous mobile robot comprising a determination unit for determining an orientation. 2. A face area detecting means for detecting a human face area based on the photographed image, a skin color area extracting means for extracting a skin color area from the face area, and the skin color area occupying the face area. The autonomous mobile robot according to claim 1, further comprising: a ratio calculating unit that calculates a ratio of the moving object; and a direction determining unit that determines a direction of a human based on the ratio.