JPH10151591A - Discriminating device and method, position detecting device and method, and robot device and color sampling device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide simple constitution to reliably discriminate a moving object or other object by providing a discriminating means to discriminate a moving object having a photographed discrimination object, based on a detecting result for the color pattern of a photographed discrimination body and stored color pattern information classified by each moving object. SOLUTION: A solid discriminating part 30 inputs an image signal S1 from a camera 16 to color sampling parts 31A-31U and samples a picture element of a given color from images based on the image signal S1. A color pattern detecting part 32 effects scanning in a state that images based on feeding sampling signals S10 are overlapped with each other and detects a part where three colors are juxtaposed and decides it as a discriminating body. A color pattern, a position in an image, and a diameter of a picture element forming a unit are fed to a comparing and computing part 33 as a discriminating information signal S11 and ID of a photographing discriminating body is detected. Further, a distance to the discriminating body is calculated, and a result is fed to a CPU 36 as a discriminating body detecting signal S12 based on a distance and a discriminating information signal S11 and the position of other robot is recognized.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[Table of Contents] The present invention will be described in the following order.

[0002] 2. Description of the Related Art [0002] Problems to be Solved by the Invention Means for Solving the Problems Embodiments of the Invention (1) First Embodiment (1-1) Individual Identification System According to First Embodiment (FIGS. 1 to 4) (1-2) Configuration of Color Extraction Unit (FIGS. 1 to 6) (1-3) Operation and Effect of First Embodiment (FIGS. 1 to 4) (2) Second Embodiment (2-1) Overall Configuration of Individual Identification System According to Second Embodiment (FIGS. 1 to 12) (2-2) Operation and Effect of Second Embodiment (FIGS. 1 to 12) (3) Third Embodiment (3-1) Overall Configuration of Position Detection System According to Third Embodiment (FIGS. 13 to 15) (3-2) Operation and Effect of Third Embodiment (FIGS. 13 to 1)
5) (4) Fourth Embodiment (4-1) Principle (FIG. 16) (4-2) Overall Configuration of Position Detection System According to Fourth Embodiment (FIGS. 14, 17 and 18) (4-3) Operation and effects of the fourth embodiment (FIGS. 17 and 1)
8) (5) Fifth Embodiment (5-1) Overall Configuration of Position Detection System According to Fifth Embodiment (FIGS. 17, 19 to 21) (5-2) Operation and Effect of Fifth Embodiment (FIG. 19 to 2
1) (6) Sixth Embodiment (6-1) Overall Configuration of Position Detection System According to Sixth Embodiment (FIGS. 19, 22 to 24) (6-2) Operation and Effect of Sixth Embodiment (FIG. 22 to FIG.
4) (7) Seventh Embodiment (7-1) Overall Configuration of Position Detection System According to Seventh Embodiment (FIGS. 14, 25 to 27) (7-2) Operation and Effect of Seventh Embodiment (FIG. 25 to 2
7) (8) Eighth Embodiment (8-1) Overall Configuration of Position Detection System According to Eighth Embodiment (FIGS. 17, 28 and 29) (8-2) Operation and Effect of Eighth Embodiment (FIG. 28 and FIG.
9) (9) Other Embodiments (FIGS. 1 to 36) Effects of the Invention

[0003]

[0001] The present invention relates to an identification apparatus and method,
The present invention relates to a position detecting device and method, a robot device, and a color extracting device, which are suitable for application to, for example, an autonomous mobile robot.

[0004]

2. Description of the Related Art In recent years, as one of mobile robots, a so-called autonomous mobile system has been developed in which information about the surrounding environment is sequentially taken in, and an action can be determined by himself / herself based on the obtained information. Research on mold robots is ongoing.

[0005]

As a method for such a mobile robot to identify other mobile robot individuals (for example, the first mobile device, the second mobile device,..., Etc.), radio waves are transmitted to each robot. A first method of generating a special signal for identification such as infrared rays or sound waves, a second method of applying a predetermined color different from each other to each robot, and identifying the robot based on the color, and a second method of identifying each robot. A third method of writing symbols or bar codes for identification on the surface may be considered.

However, in the first method, a special device for transmitting or receiving a signal is required, and a desired signal is transmitted due to restrictions by radio laws and influences on other devices existing in the vicinity. There are problems that may not be possible.

In the second method, if only a small number of robots are to be identified, there is no problem since it is sufficient to prepare colors that can be easily identified by the number of robots, but there is no problem in identifying a large number of robots. There is a problem that the image processing must be complicated and that the image processing is liable to be affected by lighting conditions and the like.

Further, the third method has a problem that a symbol or the like cannot be observed depending on the direction and posture of the robot.

On the other hand, as a method for enabling a mobile robot to detect its own position in a moving area,
A first method in which a sign such as a color pattern or a symbol is written on the floor of the moving area, and the robot visually reads the mark, and a radio wave, an infrared ray, or a sound wave on the floor or the corner of the moving area. A second method of installing a transmitting device such as a transmitting device, and detecting a position based on a signal from the transmitting device; and providing a position of the robot at the time of starting the robot to the robot by some means, and setting a driving state of the moving device. A third method may be considered in which the moving distance and the moving direction are obtained from (for example, the number of rotations of the wheel) and the current position is detected by integrating the moving distance and the moving direction.

[0010] In this case, the first method is to make the camera disposed on the robot sometimes face downward to capture an image of the floor surface,
Alternatively, this can be realized by separately preparing a camera for monitoring the floor surface.

However, if the first method is to be realized by the former method, while the robot is facing downward to detect its own position, the robot cannot fully see its surroundings, and the other robots cannot be seen. If the first method is to be realized by the latter method, a camera for floor surveillance is separately prepared,
There are problems that the manufacturing cost is increased, the weight of the robot is increased, or the configuration of the robot is complicated.

In the second method, when the transmitting device is placed on the floor of the moving area, there is a problem that the transmitting device itself becomes an obstacle to the robot's action.

Further, the third method has a problem that the error of the current position to be measured becomes large due to the limitation of the measuring accuracy of the moving distance and the moving direction of the robot. In particular, when the robot moves a long distance while frequently changing its direction, errors accumulate and increase, making it difficult to correctly detect the current position.

The present invention has been made in view of the above points, and provides a simple identification apparatus and method and a robot apparatus capable of reliably identifying a moving object or another object, and a moving object or its own position in an area. The present invention is to propose a position detecting device and method and a robot device which can accurately detect a color, and a color extracting device which can accurately extract a desired color.

[0015]

According to the present invention, there is provided an identification device, comprising: an identification unit having a different color pattern provided on each moving body;
An image pickup means provided on each of the moving objects, for picking up an image of an identification object having a different color pattern for each of the moving objects disposed on the other moving objects, and an image pickup device based on the first image information supplied from the image pickup means. A color pattern detecting means for detecting a color pattern of the identified object, and an identification object imaged by the imaging means based on the detection result and color pattern information of the identified object for each moving object stored in advance. Identification means for identifying a moving object having the same.

As a result, the individual of each mobile object can be easily and reliably identified.

According to the present invention, in the identification device, the image pickup means is provided for each moving object and picks up an image of the identification object having a different color pattern for each of the moving objects disposed on the other moving objects. A color pattern detecting means for detecting a color pattern of the imaged object based on the supplied first image information; and a detection result and color pattern information of the object stored for each moving object stored in advance. And based on
An identification means for identifying a moving object having an identification object imaged by the imaging means is provided.

As a result, the individual of each moving object can be easily and reliably identified.

Further, according to the present invention, in the identification method, the first step of providing each of the moving bodies with an identification body having a different color pattern from each other and the image pickup means provided for each of the moving bodies can be used to identify other moving bodies. A second step of imaging the identification object, a third step of detecting a color pattern of the imaged identification object based on the first image information output from the imaging means, and a color pattern of the detected identification object. ,
A fourth step is provided for identifying the imaged identification object based on the color pattern information of each identification object stored in advance.

As a result, the individual of each moving object can be easily and reliably identified.

Further, in the present invention, an image pickup means for picking up an image of an identification object having a different color pattern provided on each of the other objects in the robot apparatus, and an identification image picked up based on image information supplied from the image pickup means. Color pattern detection means for detecting the color pattern of the body; identification means for identifying the imaged identification object based on the detection result by the color pattern detection means and the color pattern information of each identification object stored in advance. It was provided.

As a result, the robot can easily and reliably identify another object.

Further, in the present invention, in the identification device, an image pickup means for picking up an image of the entire area, and each movement given to a predetermined position of each moving body based on the first image information outputted from the image pickup means. Color pattern detection means for detecting a different color pattern for each body, and identification means for identifying each moving body based on the detection result and prestored information on the color pattern assigned to each moving body. Is provided.

As a result, the individual of each moving object can be easily and reliably identified.

Further, in the present invention, in the identification method, a first step of arranging an image pickup means for picking up an image of the entire area at a predetermined position and giving different color patterns to predetermined positions of each moving body, and A second step of detecting a color pattern of each moving object based on the first image information output from the means, a result of the detection, and a previously stored color pattern assigned to each moving object. And a third step for identifying each moving object based on the information of the third embodiment.

As a result, the individual of each moving object can be easily and reliably identified.

Further, according to the present invention, in the position detecting device, a plurality of wall surfaces of different colors provided along the periphery of the area, an image pickup means provided on the moving body and imaging the corresponding predetermined wall surface, The first output from the imaging means
Based on the image information, the color and relative position detection means for detecting the color of the wall surface imaged by the imaging means and the relative position with respect to the wall surface, and the detection results of the color and relative position detection means, and are stored in advance. And position detecting means for detecting the position of the moving object in the area based on the colors of all the wall surfaces and the map information.

As a result, the position of each moving body in the area can be detected easily and reliably.

Further, in the present invention, in the position detecting device, of a plurality of wall surfaces of different colors provided along the periphery of the area, an imaging means for imaging a corresponding predetermined wall surface, and an image output from the imaging means. A color and relative position detecting means for detecting a color of the wall surface imaged by the imaging means and a relative position with respect to the wall surface, based on the first image information, and detection results of the color and relative position detecting means; Position detecting means for detecting the position of the moving object in the area based on the stored color and map information of each wall surface is provided.

As a result, the position of each mobile unit in the area can be detected easily and reliably.

Further, according to the present invention, in the position detecting method, the first step of providing a plurality of walls of different colors along the periphery of the area and the imaging means provided on the moving body image the walls. A second step of detecting the color of the wall surface imaged by the first imaging means and the relative position with respect to the wall surface based on the obtained first image information, and storing these detection results in advance. And a third step of detecting the position of the moving body in the area based on the colors of all the wall surfaces and the map information.

As a result, the position of each mobile unit in the area can be detected easily and reliably.

Further, according to the present invention, in the robot apparatus, of the plurality of wall surfaces of different colors provided along the periphery of the region, the imaging means for imaging the corresponding predetermined wall surface, and the image is outputted from the imaging means. Based on the first image information, a color and relative position detecting means for detecting a color of the wall surface imaged by the imaging means and a relative position with respect to the wall surface, and respective detection results of the color and relative position detecting means, and are stored in advance. And position detecting means for detecting the position of the moving body in the area based on the color of each wall surface and the map information.

As a result, the robot can easily and reliably detect its own position in the area.

Further, according to the present invention, based on a luminance signal and a color difference signal of a supplied image signal, level detecting means for sequentially detecting a luminance level and a color difference level of each pixel in an image based on the image signal, Determining means for determining whether or not each pixel has a predetermined color based on the detected luminance level and color difference level of the pixel, and an upper limit value and a lower limit value of a color difference level for each luminance level stored in advance. Was provided.

As a result, a pixel of a desired color can be reliably extracted.

[0037]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below in detail with reference to the drawings.

(1) First Embodiment (1-1) Overall Configuration of Individual Identification System According to First Embodiment In FIG. 1, reference numeral 1 denotes an individual identification system to which the present invention is applied as a whole. Robots 3
A to 3C are arranged. In the following description, it is assumed that the region 2 has a flat rectangular shape, a direction parallel to a predetermined side is the X direction (arrow x), and a direction perpendicular thereto is the Y direction (arrow y) and the region 2 The vertical direction is defined as a Z direction (arrow z).

In each of the robots 3A to 3C, as shown in FIG.
The head 12 is disposed via the thigh 13 and the shin 14 at the front, rear, left and right corners of the lower surface of the body 10.
Right front leg 15A, left front leg 15B, right hind leg 1
5C and the left rear leg 15D (hereinafter, these are collectively referred to as respective legs 15A to 15D) are provided.

In this case, a camera 16 is attached to the head 12, and a microphone 17 (FIG. 3) is attached to a predetermined position of the head 12, and the head 12, body 10 and each leg 15A are attached. A plurality of contact sensors 18A to 18Z (FIG. 3) are respectively attached to the surfaces of to 15D.

Further, a control section 19 (FIG. 3) is provided in the body section 10, and the control section 19 transmits the image signal S1 supplied from the camera 16 and the microphone 17 as shown in FIG. Based on the supplied audio signal S2 and the sensor signals S3A to S3Z supplied from the contact sensors 18A to 18Z, the surrounding state is recognized, and based on the recognition result, each of the constituent units (the head 12, the neck 11, the body) is recognized. Actuator 21 in each of joints 20A to 20J (FIG. 2) for connecting section 10, each thigh 13 and each shin 14).
A to 21J are respectively driven as needed.

Thus, in each of the robots 3A to 3C, each component unit can be driven freely under the control of the control unit 19, and thus the action according to the surrounding environment can be autonomously taken. It has been made possible.

In addition to this configuration, the individual identification system 1
In the case of (1), as is clear from FIG. 2 (A), the rear end of the upper surface of the body 10 of each of the robots 3A to 3C is color-coded in a different pattern for each of the robots 3A to 3C via the support rod 22. A spherical discriminator 23 is attached.

As shown in FIG. 2 (B), each discriminator 23 applies predetermined three colors from among a plurality of types of colors on the surface of the sphere, respectively, in a direction perpendicular to the moving direction of the robots 3A to 3C (ie, Z direction). Direction) and applied in a strip shape.

The control unit 19 of each of the robots 3A to 3C.
In FIG. 3, an individual identification unit 30 as shown in FIG. 4 is provided to identify individuals of the other robots 3 </ b> A to 3 </ b> C moving in the area 2 based on the identification object 23.

That is, in the individual identification section 30, the same number (for example, 16) of color extraction sections 3 as the colors used for identification are used.
1A to 31U, and inputs an image signal S1 supplied from the camera 16 to each of the color extracting units 31A to 31U.

Each color extracting section 31 extracts a pixel of a predetermined color from the image based on the image signal S1, and a portion corresponding to the pixel rises to a logical “1” level, and a portion corresponding to the other pixels. Sends the color extraction signals S10A to S10U falling to the logical "0" level to the color pattern detection unit 32, respectively. In addition, each color extraction part 31A ~
31U extracts pixels of mutually different colors from a plurality of colors used for identification.

The color pattern detecting section 32 is provided for each color extracting section 31.
Each of the color extraction signals S10 supplied from A to 31U, respectively.
By superimposing and scanning the images obtained based on A to S10U, a portion in which three colors are arranged in a substantially circular shape in the Z direction in the image is detected. The color pattern of the identifier 23, the position in the image, and the diameter in pixel units are sent to the comparator / arithmetic unit 33 as an identifier information signal S11.

The comparison / arithmetic unit 33 calculates the color pattern of the imaged identification object 23 obtained based on the supplied identification object information signal S11 and the color of each identification object 23 stored in the first memory 34 in advance. The identification object 2 captured by the camera 16 based on the pattern and the table relating to the ID.
3 (that is, the robots 3A to 3C).

The comparing / calculating section 33 is provided with the imaged identification object 2 obtained based on the supplied identification object information signal S11.
The diameter (Dpic) in pixels in the image of 3 and the second
The reference value (camera 1) stored in advance in the memory 35
6 when the discriminator 6 and the discriminator 23 are separated by 1 [m]
3 based on the diameter (Dstd) in pixels)

[0051]

(Equation 1)

By executing the operation of the above, the identifier 2
The distance L1 to 3 is calculated.

Further, the comparing / calculating section 33 calculates the ID of the detected discriminator 23, the distance L1 to the discriminator 23 obtained by the calculation of the equation (1), and the image obtained based on the discriminator information signal S11. And the position of the discriminating body 23 within the robot as the discriminating body detection signal S12 to the uppermost CPU 36 which controls the actions of the robots 3A to 3C as a whole.

In this way, in the robots 3A to 3C, the CPU 36 can recognize the positions of the other robots 3A to 3C on the basis of the identification object detection signal S12, and thus, based on the recognition result, the surrounding situation. It is possible to take action according to.

(1-2) Configuration of Color Extraction Unit Generally, each color in an image based on an image signal is represented by two color difference signals (RY, B-Y) included in the image signal.
Y), the signal level U of one of the first color difference signals is
On the axis, the signal level V of the other second color difference signal can be represented as a point on the UV plane taken on the Y axis. However, even on the same color, the position on the UV plane slightly changes depending on the lighting conditions and the like.

Therefore, as shown in FIG. 5, a rectangular area 40 in the UV plane is considered, and when the first and second color difference levels U and V of a pixel enter the area 40, the pixel attempts to extract it. Is determined to be a certain color, and the luminance level Y of the pixel is determined so as to correspond to a change in lighting conditions and the like.
Accordingly, by moving the area 40, the pixel of the corresponding color in the image based on the image signal can be accurately extracted.

In this case, to specify the area 40, the first
And the upper limit values a ₁ and b ₁ and the lower limit values a ₂ and b ₂ of the second color difference levels U and V may be determined according to the color to be extracted.
In order to move the area 40 by the luminance level Y, the upper and lower limits a ₁ and b ₁ and the lower and upper limits a ₂ and b ₂ of the first and second color difference levels U and V are set in advance for each of the luminance levels Y. A table is created by calculation and determination, and based on the table and the luminance level Y of the actual pixel, the upper and lower limits a ₁ , b ₁ and a ₂ , of the first and second color difference levels U, V,
The b ₂ may be to change.

In consideration of the above points, each robot 3A to 3C
Each of the color extraction units 31A to 31U of the individual identification unit 30 of FIG.
It is configured as shown in FIG.

That is, in the color extraction units 31A to 31U, the image signal S1 supplied from the camera 16 is input to the separation circuit 41, and the separation circuit 41 outputs the image signal S1.
To the luminance signal S20 and two color difference signals (RY, B-
Y) Separate into S21A and S21B.

In this case, the luminance signal S20 is sampled in the analog / digital conversion circuit 42 at a predetermined first cycle, and is sequentially converted into luminance data D1 corresponding to each pixel. 4 are supplied to the memories 44A to 44D.

The first color difference signal S21A of one of the two color difference signals S21A and S21B is sampled by the analog / digital conversion circuit 43A at the above-described first cycle, so that the first color difference signal S21A corresponds to each pixel. After being sequentially converted into one color difference data D2A, the data is supplied to the first and second comparison circuits 45A and 45B, and the other second color difference signal S21B is supplied to the analog / digital conversion circuit 43B by the above-mentioned first color difference signal S21B. By being sampled periodically, the data is sequentially converted to second color difference data D2B corresponding to each pixel, and then supplied to the third and fourth comparison circuits 45C and 45D.

At this time, the first and second memories 44A, 44A,
4B, the value of the first color difference data D2A (that is, the first color difference data D2A) for each value of the luminance data D1 (that is, the luminance level Y) of the pixel is associated with the color to be extracted by the color extraction units 31A to 31U. with an upper limit value a ₁ or the lower limit value a ₂ of the chrominance level U) is stored as a table, third and fourth memory 44C, the 44D, second color difference data for each respective value of the luminance data D1 of the pixel upper limit value b ₁ or the lower limit value b ₂ values D2B (i.e. second chrominance level V) is stored as a table. Note that these upper limit values a
₁ , b ₁ and the lower limits a ₂ , b ₂ are the luminance levels Y of the pixels.
And an address bus 46 and a data bus 47
Is set by the highest-level CPU 36 described above.

The first to fourth memories 44A to 44D
Is configured to output a corresponding set value from a table stored in advance using the value of the supplied luminance data D1 as an address.

Thus, in the color extraction units 31A to 31U, the first upper limit a of the first color difference level corresponding to the value of the luminance data D1 is set for each pixel from the first and second memories 44A to 44D. with ₁ or the lower limit value a ₂ is output, the third and fourth memory 44C, the upper limit value b ₁ of the second color difference level set in advance corresponding to the value of the luminance data D1 for each pixel from each of 44D And lower limit b ₂
And these are supplied to the corresponding first to fourth comparison circuits 45A to 45D.

In the first to fourth comparison circuits 45A to 45D, the outputs of the corresponding first to third or fourth memories 44A to 44D and the first supply for each pixel which are sequentially supplied are respectively provided.
Alternatively, the values of the second color difference data D2A and D2B are sequentially compared with each other, and the comparison results are sequentially sent to the determination circuit.

The decision circuit 48 has, for example, an AND circuit configuration, and its pixels are stored in the first to fourth memories 44A to 44D based on the outputs of the first to fourth comparison circuits 45A to 45D.
D is within the area 40 (FIG. 5) determined by the upper limit values a ₁ and b ₁ or the lower limit values a ₂ and b ₂ of the first or second color difference levels U and V respectively stored in D. It is determined whether it is included or not, and “1” is stored in a position corresponding to the pixel in the frame memory 49 if not.

Thus, the frame memory 49 outputs the color extraction signals S10A to S10U in which only the portions corresponding to the pixels of the color to be extracted by the color extraction units 31A to 31U rise to the logical "1" level. .

As described above, each of the color extracting units 31A to 31U
Can extract the pixels of the corresponding color from the image based on the image signal S1, and send the color extraction signals S10A to S10U thus obtained to the color pattern detection unit 32 (FIG. 4) as described above. It has been made to be.

(1-3) Operation and Effect of First Embodiment In the above configuration, in the case of this individual identification system 1,
Each of the robots 3A to 3C identifies the color pattern of the identification object 23 captured by the camera 16, the position in the image based on the image signal S1 supplied from the camera 16, and the diameter in units of pixels. And the color pattern of the identified object 23 detected by the color extracting units 31A to 31U and the color pattern detecting unit 32, the color pattern of each identified object 23 stored in the first memory 34, and the ID thereof. The ID (individual robots 3A to 3C) of the imaged object 23 detected based on the table is detected, the diameter of the imaged object 23 detected by the color pattern detection unit 32 as a unit, and the second memory 35. The distance L1 to the identification object 23 is calculated based on the reference value stored in the ID, the detected ID of the identification object 23, the distance L1 to the identification object 23, As the uppermost governs the position and the behavior of the robot 3A~3C respective identification member 23 C to definitive
Send to PU36.

Accordingly, in the individual identification system 1, the top CPU of each robot 3A to 3C has the other robots 3A to 3C located therearound, and the distance L1 and direction to the robots 3A to 3C. Can be accurately recognized.

Further, in this individual identification system 1, since the identification body 23 of each of the robots 3A to 3C can be manufactured by painting a color such as a ping-pong ball, it can be constructed extremely inexpensively. it can.

Further, in this individual identification system 1, since each robot 3A to 3C does not use a special signal as means for identifying each individual robot 3A to 3C, peripheral devices are adversely affected. And are not subject to regulations based on radio regulations.

Further, in the individual identification system 1, the identification body 23 is spherical as described above, and a plurality of identification colors are painted in a strip shape in a direction perpendicular to the moving direction of the robots 3A to 3C. Area 2 where 3A to 3C move
Can be seen in the same shape and the same color pattern in any direction, as long as the robot 3A is substantially flat, so that each of the robots 3A to 3C can be seen from the other robot 3A.
〜3C individuals can be easily and reliably identified.

Further, in the individual identification system 1, since the discriminating bodies 23 of the robots 3A to 3C are configured so that the surface is painted in a plurality of colors instead of a single color, a large number of robots are determined according to the combination of colors. 3A to 3C can be identified. In this case, the number of combinations can be increased by using only colors with greatly different shades, such as primary colors, as identification colors. There is an advantage that is hard to receive.

According to the above configuration, each of the robots 3A to 3A
C, the identification bodies 23 having different color patterns from each other are attached to each of the robots 3A to 3C. At each position and diameter, and the detection result,
Based on the color pattern of each identifier 23 and a table relating to the ID stored in advance in the first memory 34, the ID of the captured identifier 23 is detected, and within the image based on the detected image signal S1. The diameter of the identification body 23 of
By calculating the distance L1 to the discriminator 23 based on the reference value stored in the second memory 35, each robot 3A to 3C can easily identify the other robot 3A to 3C, respectively. In addition, it is possible to realize an individual identification system and a robot having a simple configuration, which can identify the robots 3A to 3C reliably and can surely recognize the individuals of the robots 3A to 3C.

(2) Second Embodiment (2-1) Overall Configuration of Individual Identification System According to Second Embodiment FIGS. 7 and 8 show an individual identification system 5 according to the second embodiment.
0, and the robots 51A to 51A have the same reference numerals as in FIG. 2A, as shown in FIG.
Identification seals 52 are attached to the upper surface of the body 10 of C, respectively.

In this case, as shown in FIG. 10, the identification seals 52 of the robots 51A to 51C each have a predetermined number (for example, six) of strip-shaped areas 52A whose surfaces are successively adjacent to each other.
To 52F, and each of these band-shaped regions 52A to 52F
Are colored in any one of a plurality of colors selected for identification. The combination of colors (color pattern) for coloring each of the band-shaped regions 52A to 52F on the surface of the identification seal 52 is determined by the identification
A different pattern is selected for each of the robots 51A to 51A based on the color pattern of the identification seal 52.
51C individuals can be identified.

On the other hand, as is clear from FIGS. 7 and 8,
A camera 53 is provided above the area 2 so that the entire area 2 can be photographed in one screen.
Is supplied to the individual identification unit 54 provided outside the area 2.

In this case, as shown in FIG. 11 in which the same reference numerals are assigned to the parts corresponding to FIG. 4, the individual identification unit 54 has a number (16 colors) corresponding to the number of colors for identification. Color extraction units 31A to 31U are provided.
Color extraction signals S10A respectively output from A to 31U
To S10U are sent to the color pattern detection unit 55.

The color pattern detecting section 55 scans the images based on the supplied color extraction signals S10A to S10U in a superimposed manner, thereby detecting a portion where a predetermined number of colors for identification are arranged in a band in the image. The identification label is determined as the identification label 52 of the robots 51A to 51C, and the color pattern of the identification label 52 and the position in the image in units of pixels are identified by the identification label detection signal S31.
Is sent to the comparison / calculation unit 56. In this case, the identification seals 52 are detected by the number of the robots 51A to 51C located in the area 2, and the color pattern of each identification seal 52 and the position in the image are sent to the comparison / calculation unit 56, respectively.

The comparison / calculation unit 56 calculates the color pattern of each identification seal 52 obtained based on the supplied identification seal detection signal S31, the color pattern of each identification seal 52 stored in the memory 57 in advance, and its ID. The ID of each identification seal 52 in the image based on the image signal S30 from the camera 53 (that is, the individual of each of the robots 51A to 51C) is detected based on the table and the ID of each identification seal 52 thus obtained. The transmitting unit 58 uses the position information in the area 2 as the robot position detection signal S32.
Robots 51A to 51C moving in the area 2 through the
To be transmitted by radio waves.

In each of the robots 51A to 51C, the radio wave transmitted from the transmitting section 58 of the individual identification section 54 is received via the antenna 60 as shown in FIG. The ID of each identification seal 52 received and obtained by the unit 61 (that is, each robot 51
The position information in the area 2 is transmitted to the control unit 62 as a reception signal S33.

At this time, the control unit 62 is supplied with the image signal 1 from the camera 16, the audio signal S 2 from the microphone 17, and the contact sensors 18 A to 18 A.
Sensor signals S3A to S3Z are supplied from 8Z.

Thus, the control unit 62 determines the surrounding environment and the robots 51A to 51A including the self in the area 2 based on the supplied image signal S1, sound signal S2, sensor signals S3A to 3Z and received signal S33. 51C, and can determine its own action based on the recognition result. Based on the determination result, the corresponding actuators 21A to 21A-2 correspond to each other.
Drive 1J.

In this way, each of the robots 51A to 51C
Is capable of recognizing the surrounding environment and the positions of all the robots 51A to 51C including itself moving in the area 2, and acting autonomously based on the recognition result.

(2-2) Operation and Effect of Second Embodiment In the above configuration, in the individual identification system 50,
The entire area 2 is imaged from above by the camera 53, and based on the obtained image signal S30, the individual identification unit 54 disposed outside the area 2 is used to identify each of the identification seals 52 in the image based on the image signal S30. The position is determined for each color extraction unit 31A-3
Each of the identification labels 52 in the image is detected based on the detection result and the color pattern information of each of the identification labels 52 stored in the memory 57.
And the detection result is transmitted to each of the robots 51A to 51C in the area 2 via the transmission unit 58.

On the other hand, in each of the robots 51A to 51C, each of the robots 51A to 51
The position information in the region 2 of 51C, the image signal S1 supplied from the camera 16, the audio signal S2 supplied from the mylophone 17, and the sensor signals S3A to S3Z respectively supplied from the contact sensors 18A to 18Z. The robot recognizes the surrounding situation and the positions of the robots 51A to 51C based on the recognition result, and acts autonomously based on the recognition result.

Therefore, in the individual identification system 50, each of the robots 51A to 51C can surely recognize the other robots 51A to 51C and the absolute position of itself in the area 2.

Further, in the individual identification system 50, since only the antenna 60 and the receiving section 61 are provided and the identification seal 52 is attached to the robots 51A to 51C, only the robots 51A to 51C are required.
To 51C are replaced with the robots 3A to 3C of the first embodiment.
This can be more simplified than (FIG. 2A).
In addition, the entire system requires a camera 53 and an individual identification unit 54 for imaging the entire area 2, but this can be a single set regardless of the number of the robots 51 </ b> A to 51 </ b> C. Thus, the configuration can be simplified.

Also, in this individual identification system 50, since the surface of the identification seal 52 is painted in a plurality of colors instead of a single color, a large number of robots 51A to 51C can be easily identified by the combination of colors. Can be In this case, even if a color with a large difference in color, such as the primary color, is used as the color for identification, the number of combinations can be increased, so that individual identification is performed using subtle color differences using a single color. Therefore, there is an advantage that it is hardly affected by lighting conditions and the like.

Further, in the individual identification system 50, since the ID and the position of each of the robots 51A to 51C in the area 2 can be intensively recognized in the individual identification section 54, this is stored. Each robot 51A
Each of the robots 51A to 51C as a record of the actions of
Can be used for evaluation and improvement of a program that controls each of them.

Further, in this individual identification system 50, since the vision of each of the robots 51A to 51C is not used,
There is also an advantage that the present invention can be applied to the case where the robots 51A to 51C have low visual processing capability or the case where each of the robots 51A to 51C has no vision.

According to the above configuration, the robots 51A to 51A-5
The entire action area 2 of 1C is imaged from above by the camera 53, the position of each identification seal 52 in the image based on the obtained image signal S30 is detected, and the detection result and each of the identification seals 52 stored in the memory 57 are detected. The ID and position of each identification seal 52 in the image are detected from the color pattern information of the identification seal 52, and the detection result is used as each robot 51A in the area 2.
To 51C, the absolute positions of the robots 51A to 51C moving in the area 2 can be accurately detected, and thus the robots 51A to 51C in the action area 2 can be reliably detected. An individual identification system and a robot having a simple configuration that can be identified can be realized.

(3) Third Embodiment (3-1) Overall Configuration of Position Detection System According to Third Embodiment FIG. 13 in which parts corresponding to those in FIG.
1 shows a position detection system 70 to which the present invention is applied, in which a wall 72 having a predetermined height is provided along the periphery of the action area 2 of the robot 71.

In this case, the inner wall surface 72A of the wall 72 is
Each of the wall surfaces 72AA to 72AD along each side is painted with a different color, and the wall surfaces 72AA to 72AD are determined based on the painted color.
７２72 AD can be easily determined.

On the other hand, the robot 71 is provided in the control unit 19 (FIG. 3) of the robots 3A to 3C (FIGS. 2A and 3) of the first embodiment instead of the individual identification unit 30 (FIG. 4) in FIG. Except that a wall identification unit 80 as shown in FIG.
It is configured similarly to the robots 3A to 3C of the embodiment.

In this case, the wall discriminating section 80 is provided with the color extracting sections 31A to 31D as many as the number of the wall surfaces 72AA to 72AD (four sides) along each side of the area 2.
The image signal S1 supplied from the color extraction units 31A to 31
D, respectively.

As a result, from each of the color extracting sections 31A to 31D, a portion corresponding to the pixel of the corresponding color among the pixels in the image based on the image signal S1 rises to the logical "1" level, and the pixels of the other colors Are extracted to the logic "0" level.
0D is output and supplied to the wall detection unit 81. In addition, each color extraction part 31A-31D is each wall surface 72A.
Only one different color is extracted from a plurality of colors for identification applied to A to 72AD.

[0099] The wall detecting section 81 includes the color extracting sections 31A to 31A.
D respectively supplied with color extraction signals S10A to S10
By scanning the images based on D in a superimposed manner, a substantially horizontal elongated region of the same color can be formed on any of the wall surfaces 72AA to 72AA.
72AD and its wall surfaces 72AA-72A
D is detected, and the heights of the wall surfaces 72AA to 72AD in the image based on the image signal S1 are detected in units of pixels.
The colors of A to 72AD and the height in the image are sent to the comparison / calculation unit 82 as a wall detection signal S40.

The comparing / calculating section 82 calculates the colors of the wall surfaces 72AA to 72AD obtained based on the wall detection signal S40 and the wall surfaces 72AA stored in the first memory 83 in advance.
The IDs of the wall surfaces 72AA to 72AD are searched based on the respective colors of .about.72AD and the table relating to their IDs.

The comparing / calculating section 82 outputs the wall detection signal S4
The height (referred to as Hpic) in the image of the wall surfaces 72AA to 72AD obtained on the basis of 0 and a reference value (the robot 71 corresponds to the wall surface 72AD) stored in advance in the second memory 84.
Based on the height (Hstd) in pixels of the wall surfaces 72AA to 72AD in the image at a distance of 1 [m] from AA to 72AD,

[0102]

(Equation 2)

By executing the above, the distance L2 from the camera 16 to the wall surfaces 72AA to 72AD is calculated.

Further, the comparison / calculation unit 82 determines that the camera 16 is to move its wall (hereinafter referred to as a first wall) 72
After being directed to a wall surface different from AA to 72AD (hereinafter referred to as a second wall surface) 72AA to 72AD, the same processing is executed to execute the second wall surface 72AA to 72AD.
And the distance L3 to the second wall surfaces 72AA to 72AD are calculated.

Further, thereafter, the comparison / calculation unit 82 determines the I / O of the first wall surfaces 72AA to 72AD obtained as described above.
D and the distance L to the first wall surfaces 72AA to 72AD.
2, the IDs of the second wall surfaces 72AA to 72AD, the distance L3 to the second wall surfaces 72AA to 72AD, and each wall surface 72AA along each side of the area 2 stored in the third memory 85 in advance. The position of the robot 71 in the area 2 is detected based on the map information of the area 2 including the positions of .about.72AD, and this is detected as a position detection signal S41.
Is sent to the highest-order CPU 36 which controls the above operation.

As a result, in the robot 71,
The CPU 36 can recognize its own position in the area 2 based on the position detection signal S41, and can autonomously take an action according to the surrounding situation based on the recognition result.

(3-2) Operation and Effect of Third Embodiment In the above configuration, in this position detection system 70,
The robot 71 outputs an image signal S1 output from the camera 16.
Based on the first and second surrounding wall surfaces 72AA-72
The color applied to the AD and the height Hpic of the first and second wall surfaces 72AA to 72AD in the image based on the image signal S1 are detected, and the detection result and the first memory 83 are detected.
Based on the colors and the IDs of the wall surfaces 72AA to 72AD stored in advance, the reference value Hstd stored in advance in the second memory 84, and the map information stored in advance in the third memory 85. To detect its own position in the area 2.

Therefore, in this position detecting system 70, 2
Of two wall surfaces 72AA to 72AD and these wall surfaces 72A
Robot 7 from height Hpic in the images of A-72AD
1 can easily and accurately recognize its own position in the area 2.

In the position detecting system 70, each of the wall surfaces 72AA to 72AD arranged along each side of the area 2 is provided.
Since it is only necessary to apply different colors to each other, the system can be constructed extremely easily.

Further, since the position detecting system 70 does not use a method of transmitting a special signal such as a radio wave, the position detecting system 70 can be used without considering the influence on peripheral devices and radio regulations. Since there is no need to install a signal generator on the floor of No. 2, there is no possibility that the movement of the robot 71 will be hindered.

Further, in this position detection system 70, since a method of not writing a sign or a sign on the floor of the action area 2 of the robot 71 is not used, paint or the like can be applied to the floor for another purpose.

Further, in the position detecting system 70, the camera 16 of the robot 71 is oriented in a substantially horizontal direction, so that the front wall surfaces 72AA to 7AA of the robot 71 are provided.
Since 2AD can be imaged by the camera 16,
The robot 71 does not need to point the camera 16 in a predetermined direction in order to detect its own position in the area 2, and can detect its own position in the area 2 while capturing the other robots 71 with the camera 16. There are advantages too.

According to the above configuration, the wall surfaces 72AA to 72AD are respectively formed along the sides of the action area 2 of the robot 71.
And apply different colors to the wall surfaces 72AA to 72AD, respectively, while the robot 71 detects at least two or more wall surfaces 72A imaged by the camera 16 based on the image signal S1 output from the camera 16.
The colors of A to 72AD and the height Hpic of each of the wall surfaces 72AA to 72AD in the image based on the image signal S1 are detected, and the detection result and each of the wall surfaces 72AA stored in the first memory 83 in advance are detected. Identification color of ~ 72AD and its ID
And the reference value Hstd stored in the second memory 84 in advance.
The robot 71 can detect its own position in the area 2 by detecting its own position in the area 2 based on the map information of the area 2 stored in the third memory 85 in advance. Thus, it is possible to realize a position detection system and a robot capable of detecting the position of the object itself in the area 2 with good accuracy.

(4) Fourth Embodiment (4-1) Principle In general, a color can be represented using three attributes of hue (Hue), saturation (Saturation) and lightness (Intensity).

In this case, the relationship between the hue, saturation (also referred to as saturation) and lightness is obtained when an arbitrary point on the plane is set as the origin O as shown in FIGS. 16 (A) and 16 (B). , The hue is the angle around the origin O in this plane, the saturation is the distance from the origin O in this plane,
In addition, the brightness can be represented by polar coordinates, which are distances from the origin O in a direction perpendicular to this plane. FIG.
The vertices of the hexagon shown in (B) are R (red),
They correspond to Y (yellow), G (green), C (cyan), B (blue) and M (magenta).

By the way, for example, the object (identifier 23 in the first embodiment, identification mark 52 in the second embodiment, and wall 72 in the third embodiment) as in the first to third embodiments.
In a system for identifying an object based on a difference in color applied to the AA to 72AD), the appearance of a color changes depending on a change in illumination conditions, a direction in which the object is viewed, and the like, even for the same color. Therefore, for example, in the first to third embodiments, this change is dealt with by giving a range to the condition for determining the color.

However, even if such a measure is taken, depending on how to select the color for painting the object, when a lighting condition or the like changes, the appearance of one color captured by the robot can be changed to another color. If the color falls within the determination condition and is recognized as a different color, the object painted with that color may not be correctly identified.

As one method of preventing such a situation, for example, as a combination of colors used for identification, colors that are far apart in a predetermined color space are used in advance. The format of the output image signal may be converted into the format of the color space to perform color identification.

That is, for example, a color is defined as a hue,
A color space represented by using three attributes of saturation and lightness (hereinafter, referred to as a color space)
This is called an HSI space), a plurality of colors whose hues are separated by a predetermined angle (for example, 60 °) or more are selected, and the image format of the image signal output from the camera inside the robot is represented by the hue (H). Is converted into a format (hereinafter, referred to as an HSI format) represented by the saturation (S) and the lightness (I), and the color is identified from the hue based on the image signal thus obtained. It can be considered that the influence of a change in the lighting condition or the like can be reduced at times, and erroneous determination of color identification can be efficiently avoided.

(4-2) Configuration of the Position Detecting System According to the Fourth Embodiment FIG. 17 in which parts corresponding to those in FIG.
FIG. 9 shows a position detection system 90 according to a fourth embodiment, in which different unique colors are applied to the region 2 and the wall surfaces 72AA to 72AD of the wall 72 along each side of the region 2 respectively.

In this case, the region 2 and each of the wall surfaces 72AA to 72
As the colors to be applied to the AD, respectively, five colors (for example, R, Y,
G, C and B) have been selected.

On the other hand, in the robot 91, the position detector 80 (FIG. 1) is provided in the robot 71 (FIG. 14) of the third embodiment.
Instead of 5), the configuration is the same as that of the robot 71 except that a position detecting unit 92 as shown in FIG.

In this case, the position detection unit 92 is provided with an image format conversion unit 93 and the same number of color extraction units 94A to 94D as the number of the wall surfaces 72AA to 72AD. Is converted into an HSI format image signal S50, which is sent to each of the color extraction units 94A to 94D.

Each of the color extraction units 94A to 94D respectively determines the hue information of each pixel contained in the image signal S50 based on the hue information.
A pixel having a hue within a predetermined angle from the hue designated in the polar coordinates shown in FIG. 16B is detected as a pixel of a color to be extracted, and a portion corresponding to the pixel of the color to be extracted is determined based on the detection result. It generates color extraction signals S51A to S51D in which a portion corresponding to a pixel of another color has fallen to a logic “0” level while rising to a logic “1” level, and sends it to the wall detection section 81. In addition, each color extraction part 94A-94D
Extracts pixels of predetermined colors different from each other from a plurality of colors applied to the wall surfaces 72AA to 72AD, respectively.

As a result, as described above with reference to FIG.
Based on the color extraction signals S51A to S51D, the colors of the wall surfaces 72AA to 72AD imaged by the camera 16 and
The height hpic in the image of the wall surfaces 72AA to 72AD in pixels is detected by the wall detection unit 81, and based on the detection result, the comparison and calculation unit 82 performs the same operation as in the third embodiment. The position of the robot 91 in the area 2 is detected, and the detection result is sent as a position detection signal S41 to the highest-order CPU 36 that controls the action of the robot 91.

As a result, in this robot 91,
The CPU 36 can recognize its own position in the area 2 based on the position detection signal S41, and can autonomously take an action according to the surrounding situation based on the recognition result.

(4-3) Operation and Effect of Fourth Embodiment In the above configuration, the position detecting system 90
Similar to the position detection system 70 (FIG. 14) of the third embodiment, the robot 91 detects the surrounding first and second wall surfaces 72AA to 7 based on the image signal S1 output from the camera 16.
The color of 2AD and the height Hpic of the first and second wall surfaces 72AA to 72AD in the image based on the image signal S1 are detected, and the detection results and each of the values stored in the first memory 83 in advance are detected. Colors and IDs of the wall surfaces 72AA to 72AD
And the reference value Hstd stored in the second memory 84 in advance.
And its own position in the area 2 based on the map information stored in the third memory 85 in advance.

Therefore, according to the position detecting system 90, the same functions and effects as those of the position detecting system 70 of the third embodiment can be obtained.

In addition, in the position detection system 90, the hue is 60 in the HSI space as the color applied to each of the wall surfaces 72AA to 72AD of the wall 72 and the region 2.
An image signal S1 output from the camera 16 as an internal process of the robot 91 is used.
After the image format is converted to the HSI format, the color identification is performed.
Even when the lighting conditions for .about.72AD are changed, it is possible to reduce the influence of the color discrimination in the robot 91 when it is changed.

According to the above configuration, each wall 72 of the wall 72 is different from the position detection system 70 (FIG. 14) of the third embodiment.
AA-72AD and a color whose hue is separated by 60 ° or more in the HSI space are used as colors to be applied to the area 2 and the camera 6 as internal processing of the robot 91, respectively.
After converting the image signal S1 output from the image signal S1 into an image signal S50 of the HSI format, the color identification is performed based on the image signal S50.
1 can efficiently avoid erroneous determination of color identification. In this way, it is possible to avoid erroneous recognition of an object inside the robot 91, and thus to realize a position detection system and a robot device capable of detecting its own position in the area with higher accuracy.

(5) Fifth Embodiment (5-1) Configuration of Position Detecting System According to Fifth Embodiment FIG. 19 in which parts corresponding to those in FIG.
This shows a position detection system 100 according to a fifth embodiment, in which H is applied to each of the wall surfaces 72AA to 72AD of the wall 72.
In the SI space, different unique colors having hues separated by 60 ° or more are painted.

In this case, as shown in FIG. 20, the color of each of the wall surfaces 72AA to 72AD is lowest at one end in the longitudinal direction of each of the wall surfaces 72AA to 72AD, and the saturation (saturation degree) increases from the one end to the other end. ) Increases linearly, i.e., the saturation of the color at one end of the wall surfaces 72AA-72AD is S _min , the saturation at the other end is S _max and the wall surface 72AA-72AD.
When the length in the longitudinal direction of AA to 72AD is M, the saturation S _x of the color at a position of a distance x from one end of the wall surfaces 72AA to 72AD is expressed by the following equation.

[0133]

(Equation 3)

It is painted so as to satisfy the following.

On the other hand, in the robot 101, the position detector 92 (FIG. 1) is added to the robot 91 (FIG. 17) of the fourth embodiment.
The configuration is the same as that of the robot 91, except that a position detecting unit 102 as shown in FIG.

In this case, the position detection unit 102 is provided with the same number of color extraction units 94A to 94D as the number of the wall surfaces 72AA to 72AD along each side of the area 2, and the number of color extraction units 94A to 94D of the image signal S1 output from the camera 16 is After converting the image format into the HSI format in the image format conversion unit 93, the image signal S50 thus obtained is converted into the respective color extraction units S50.
51A to 51D.

In each of the color extracting sections S51A to S51D, a pixel of a predetermined color is extracted from the image based on the image signal S50, and a portion corresponding to the pixel rises to a logic "1" level, and the other colors are extracted. The color extraction signals S51A to S51D in which the portion corresponding to the pixel has fallen to the logical “0” level are sent to the wall detection unit 103, respectively.

The wall detecting section 103 includes color extracting sections 94A-9A.
Color extraction signals S51A to S5 respectively supplied from 4D
By superimposing and scanning images based on 1D,
A substantially horizontal elongated area of the same color is used for any of the wall surfaces 72AA.
７２72AD, and the detection result is a wall detection signal S60.
Is given to the uppermost CPU 36 which controls the robot.

At this time, the CPU 36 moves the direction of the camera 16 (that is, the head of the robot 101) in the left-right direction by driving the actuators of the corresponding joints. On the basis of the signal S60, the wall surface having the largest number of pixels in the image based on the image signal S50 (that is, the closest wall surface) 7
2AA to 72AD, and the wall surface 72AA
The direction of the camera 16 is adjusted so that the upper end or the lower end in the images of ~ 72AD is horizontal (that is, the optical axis of the camera 16 is perpendicular to the wall surfaces 72AA ~ 72AD).

Then, the wall surface 7 where the optical axis of the camera 16 is closest
In the state of being vertically aligned with 2AA to 72AD, the wall detection unit 103 detects the colors of the wall surfaces 72AA to 72AD based on the color extraction signals S51A to S51D supplied from the color extraction units 94A to 94D, respectively. At the same time, based on the image signal S50 supplied from the image format converter 93, the wall surfaces 72AA to 72A at the center of the image based on the image signal S50.
D, the saturation S _{x of} the color applied to the wall surface is detected, and the detected colors of the wall surfaces 72AA to 72AD and the saturation S of the color applied to the wall surfaces 72AA to 72AD at the center of the image are detected.
_x as a color and saturation detection signal S61
04.

The comparing / calculating section 104 has the wall surfaces 72AA to 72AD obtained based on the color and saturation detection signal S61.
And the table of the colors and the IDs of the wall surfaces 72AA to 72AD stored in the first memory 105 in advance, and detects the IDs of the wall surfaces 72AA to 72AD.

[0142] The comparison and calculation unit 104, and saturation S _x of the wall 72AA~72AD in the image central portion obtained based on the color and saturation signal S61, advance the second memory 1
06, the respective saturations S _min and S _max at one end and the other end of each of the wall surfaces 72AA to 72AD, and the respective wall surfaces 7AA to 72AD.
By calculating back the formula (3) based on the length M of 2AA to 72AD, the own position in the direction parallel to the wall surfaces 72AA to 72AD is detected.

Further, comparing / calculating section 105 thereafter sets CP
Under the control of U36, the camera 16 is rotated by 90 [°], and the wall surfaces 72AA to 72AD different from the wall surfaces 72AA to 72AD (hereinafter, referred to as first wall surfaces 72AA to 72AD).
After being directed to 2AD (hereinafter, referred to as second wall surfaces 72AA to 72AD), the same processing is executed to obtain the IDs of the second wall surfaces 72AA to 72AD and the second wall surfaces 72AA to 72AD. Detect your position in the parallel direction.

Further, the comparing / calculating section 104 thereafter calculates the IDs of the first wall surfaces 72AA to 72AD obtained as described above, the position in the direction parallel to the first wall surfaces 72AA to 72AD, and the second I on the walls 72AA-72AD
D and the position in the direction parallel to the second wall surfaces 72AA to 72AD, and the map information of the region 2 including the positions of the wall surfaces 72AA to 72AD stored in the third memory 107 in advance. It detects its own position and sends the detection result to the CPU 36 as a position detection signal S62.

As a result, in the robot 101, the CPU 36 operates the area 2 based on the position detection signal S62.
The user is able to recognize his / her own position in the vehicle and take autonomous action according to the surrounding situation based on the recognition result.

(5-2) Operation and Effect of Fifth Embodiment In the above configuration, in the position detection system 100, the robot 101 controls the first and second surroundings based on the image signal S1 output from the camera 16. Wall surface 72AA ~
The color of 72AD and the saturation _{Sx at} the center of the image based on the image signal S1 of these colors are detected, and these detection results and each of the wall surfaces 72A stored in the first memory 105 are detected.
A to 72AD colors and their IDs, and the second memory 106
, The color saturations S _min and S _max at one end and the other end of each of the wall surfaces 72AA to 72AD, and the map information stored in the third memory 107. To detect its own position in the area 2 based on

Therefore, in this position detection system 100,
The robot 101 can easily and accurately recognize its position in the area 2 based on the colors of the two wall surfaces 72AA to 72AD and the change in the saturation of these colors.

In the position detecting system 100, each of the wall surfaces 72AA to 72A arranged along each side of the area 2 is provided.
Since it is only necessary to apply different colors to D while changing the saturation in the horizontal direction, a system can be constructed extremely easily.

Further, in this position detection system 100,
No special signal transmission method such as radio waves is used, so it can be used without considering the effects on peripheral devices and radio regulations, and it is necessary to install a signal generator on the floor of the area There is no possibility that the action of the robot 101 is hindered.

Further, in this position detection system 100,
Since the method is not a method of writing a sign, a sign, or the like on the floor of the action area 2 of the robot 101, paint or the like can be applied to the floor for another purpose.

Further, in this position detection system 100,
By turning the camera 16 of the robot 101 in a substantially horizontal direction, the wall surface 72A on the front of the robot 101 is moved.
Since the A to 72AD can be imaged by the camera 16, the robot 101 does not need to turn the camera 16 in a predetermined direction to detect its own position in the area 2, and the other robots can be captured by the camera 16. There is also an advantage that one's own position in the area 2 can be detected.

According to the above configuration, each of the wall surfaces 72AA to 7AA
A different color is applied to the 2AD, while changing the saturation in the horizontal direction, and the robot 102 uses the colors of the two wall surfaces 72AA to 72AD and the wall surfaces 72AA to 72AD.
When the AD is captured vertically, the saturation S _x at the center of the image of the color is detected, and the detection result and each of the wall surfaces 72AA to 7AA stored in the first memory 105 are detected.
The 2AD color and its ID, the length M of each of the wall surfaces 72AA to 72AD stored in the second memory 106, and the color saturations S _min and S _max at one end and the other end of each of the wall surfaces 72AA to 72AD. By detecting its own position in the area 2 based on the map information stored in the third memory 107, the robot 101 can accurately detect its own position in the area 2. Thus, it is possible to realize a position detection system and a robot that can accurately detect the position of the user in the area 2.

(6) Sixth Embodiment (6-1) Configuration of Position Detecting System According to Sixth Embodiment FIG. 22 in which parts corresponding to those in FIG.
This shows a position detection system 110 according to a sixth embodiment, in which H is applied to each of the wall surfaces 72AA to 72AD of the wall 72.
In the SI space, different unique colors having hues separated by 60 ° or more are applied.

Each of the wall surfaces 72AA to 72AD is formed so as to extend from near the lower end of one end to near the upper end of the other end.
In the HSI space, a diagonal line 102 is indicated using a hue of each color applied to each of the wall surfaces 72AA to 72AD and a color separated by 60 ° or more.

On the other hand, in the robot 111, the position detecting unit 92 (FIG. 1) is added to the robot 91 (FIG. 17) of the fourth embodiment.
The configuration is the same as that of the robot 91, except that a position detecting unit 113 as shown in FIG.

In this case, the position detection unit 113 is provided with one more color extraction units 94A to 94E than the number of the wall surfaces 72AA to 72AD along each side of the area 2, and is output from the camera 16. After converting the image format of the image signal S1 into the HSI format in the image format converter 93, the image signal S50 thus obtained is sent to each of the color extracting units 94A to 94E.

In each of the color extracting sections 94A to 94E, a pixel of a predetermined color corresponding to each pixel is extracted from the image based on the image signal S50, and a portion corresponding to the pixel rises to a logic "1" level. The color extraction signals S51A to S51E in which the portion corresponding to the color pixel falls to the logical “0” level are sent to the wall detection unit 114, respectively. Note that each color extraction unit 114 is provided with a corresponding one of the wall surfaces 72AA to 72A.
Pixels of mutually different colors are extracted from the color applied to D and the shaded line 112.

[0158] The wall detecting section 114 includes the color extracting sections 94A to 94A.
4E respectively supplied with color extraction signals S51A to S5.
By superimposing and scanning the images based on 1E,
A substantially horizontal elongated area of the same color is used for any of the wall surfaces 72AA.
７２72AD, and the detection result is a wall detection signal S60.
As the highest CPU controlling the behavior of this robot 111
Give to 36.

At this time, the CPU 36 moves the direction of the camera 16 (that is, the head of the robot 111) in the left-right direction by driving the actuators of the corresponding joints. On the basis of the signal S60, the wall surface having the largest number of pixels in the image based on the image signal S50 (that is, the closest wall surface) 7
2AA to 72AD, and the wall surface 72AA
Camera 16 so that the upper end or the lower end in the image of .about.72AD is horizontal (that is, the optical axis of the camera 16 is perpendicular to the nearest wall surfaces 72AA to 72AD).
Adjust the orientation of.

Then, the wall surface 7 where the optical axis of the camera 16 is closest
In a state where the wall detection unit 114 is vertically aligned with respect to 2AA to 72AD, the wall detection unit 114 detects the wall surface 7 in the center of the image.
And the longitudinal length U _x of the upper part than the hatched 112 2AA～72AD, detects a length L _x of the lower part of the pixel units respectively than the hatched 112, detected in the wall 72AA~72AD these the length L _x of length U _x and the lower portion of the upper part than hatching 112, the wall surface 72AA~72
The color of AD is sent to the comparison / calculation unit 115 as a color and length detection signal S70.

The comparing / calculating section 115 has the wall surfaces 72AA to 72AD obtained based on the color and length detection signal S70.
Of the wall surfaces 72AA to 72AD stored in the first memory 116 in advance and the table of the colors and IDs of the wall surfaces 72AA to 72AD are detected.

The comparing / calculating section 115 has the wall surfaces 72AA to 72AA obtained based on the color and length detection signal S70.
Than AD hatched 112 based on the length L _x of length U _x and the lower portion of the upper part following formula

[0163]

(Equation 4)

By executing the operation given by
Based on the image signal S50, the ratio R _x1 of the vertical length U _x above the oblique line 112 to the height (= U _x + L _x ) of the wall surfaces 72AA to 72AD at the center of the image is calculated.

The comparing / calculating section 115 calculates the result of this calculation, the length M of each of the wall surfaces 72AA to 72AD stored in the second memory 117 in advance, and the respective wall surfaces 72AA to 72A.
D, the ratio R of the vertical length of the portion above the oblique line 112 to the height of the wall surfaces 72AA to 72AD at one end of D
_a1 and the ratio R _b1 of the length of the portion above the oblique line 112 to the height of the wall surface 72AA to 72AD at the other end of each of the wall surfaces 72AA to 72AD,

[0166]

(Equation 5)

By performing the operation given by
From one end of the wall surfaces 72AA to 72AD, the wall surface 72A
A distance x to a portion of the image taken at the center of the image of A to 72AD (from one end of the wall surface 72AA to 72AD in a direction parallel to the wall surface 72AA to 72AD, the robot 1
11).

The hatched line 1 at one end of each of the wall surfaces 72AA to 72AD with respect to the height of the wall surface 72AA to 72AD.
As shown in FIG. 23, the ratio R _a1 of the length of the portion above 12 is U _{a1 where} the length of the portion above the oblique line 112 of the wall surfaces 72AA to 72AD at one end of each of the wall surfaces 72AA to 72AD is U _a1 , Assuming that the length below the oblique line 112 is _La1 ,

[0169]

(Equation 6)

Each wall 72AA-72A
The ratio R _b1 of the length above the oblique line 112 to the height of the wall surfaces 72AA to 72AD at the other end of D is the wall surface 72AA at the other end of the wall surfaces 72AA to 72AD.
The length of the portion above the oblique line 112 of AA to 72AD is U _b1
And the length below the oblique line is L _b1 and the following equation

[0171]

(Equation 7)

Is given by

Further, comparing / calculating section 115 subsequently outputs CP
Under the control of U36, the camera 16 is rotated by 90 [°], and the wall surfaces 72AA to 72AD different from the wall surfaces 72AA to 72AD (hereinafter, referred to as first wall surfaces 72AA to 72AD).
After being directed to 2AD (hereinafter, referred to as second wall surfaces 72AA to 72AD), the same processing is executed to obtain the IDs of the second wall surfaces 72AA to 72AD and the second wall surfaces 72AA to 72AD. Detect your position in the parallel direction.

Further, the comparing / calculating section 115 thereafter calculates the IDs of the first wall surfaces 72AA to 72AD obtained as described above, the position in the direction parallel to the first wall surfaces 72AA to 72AD, and the second I on the walls 72AA-72AD
D and the position in the direction parallel to the second wall surfaces 72AA to 72AD and the map information of the region including the positions of the wall surfaces 72AA to 72AD stored in the third memory 118 in advance. It detects its own position and sends the detection result to the CPU 36 as a position detection signal S71.

As a result, in the robot 111, the CPU 36 operates the area 2 based on the position detection signal S71.
The user is able to recognize his / her own position in the vehicle and take autonomous action according to the surrounding situation based on the recognition result.

(6-2) Operation and Effect of Sixth Embodiment In the above configuration, in the position detection system 110, the robot 111 controls the first and second surroundings based on the image signal S1 output from the camera 16. Wall surface 72AA ~
Each of the colors 72AD and the ratio R _x1 of the length U _x above the oblique line 112 to the height of each of the wall surfaces 72AA to 72AD at the center of the image based on the image signal S1 are detected. , The first memory 116
Of the wall surfaces 72AA to 72AD stored in advance in the second memory 117, the length M of each wall surface 72AA to 72AD stored in advance in the second memory 117, and the wall surface 72AA
Walls 72A at one end and the other end of AA-72AD
The ratios R _a1 and R _b1 of the lengths U _a1 and U _b1 above the oblique line 112 to the heights of A to 72AD, and the third memory 11
8 to detect its own position in the area 2 based on the map information stored in advance.

Therefore, in this position detection system 110,
The colors of the two wall surfaces 72AA to 72AD and these wall surfaces 72
The robot 111 can easily and accurately recognize its own position in the area 2 based on the diagonal lines 112 indicated by AA to 72AD.

In the position detecting system 110, each of the wall surfaces 72AA to 72A arranged along each side of the area 2 is provided.
D is coated with a different color from each other.
Since only 12 is required, the system can be constructed extremely easily.

Further, in this position detection system 110,
Since no special signal transmission method such as radio waves is used, it can be used without considering the effects on peripheral devices and radio regulations, and a signal generator is installed on the floor of area 2. Since there is no need, there is no possibility that the action of the robot 111 is hindered.

Further, in this position detecting system 110,
Since this is not a method of writing a sign, a sign, or the like on the floor of the action area 2 of the robot 111, paint or the like can be applied to the floor for another purpose.

Further, in this position detection system 110,
By turning the camera 16 of the robot 111 in a substantially horizontal direction, the wall surface 72A on the front surface of the robot 111 is moved.
Since the A to 72AD can be imaged by the camera 16, it is not necessary for the robot 111 to turn the camera 16 in a predetermined direction to detect its own position in the area 2, and the other robots can be captured by the camera 16. There is also an advantage that one's own position in the area 2 can be detected.

According to the above configuration, each of the wall surfaces 72AA to 7AA
While different colors are applied to the 2AD and the oblique lines 112 are indicated on the respective wall surfaces 72AA to 72AD, the robot 111 uses the colors of the two wall surfaces 72AA to 72AD,
When the wall surfaces 72AA to 72AD are vertically imaged, the ratio R _x1 of the vertical length U _x of the portion above the oblique line 112 at the center of the image is detected, and these detection results and the first memory The colors and IDs of the wall surfaces 72AA to 72AD stored in the memory 116 in advance and the wall surfaces 72AA to 72A stored in the second memory 117 in advance.
The ratio of the length U _a1 , U _b1 of the length M above the oblique line 112 to the height of the wall surface 72AA to 72AD at one end and the other end of each of the wall surfaces 72AA to 72AD, and R _a1 , R _b1 ; The robot 111 can accurately detect its own position in the area 2 by detecting its own position in the area 2 based on the map information stored in advance in the memory 118 of the third area. Thus, it is possible to realize a position detection system and a robot that can accurately detect the position of the user in the area 2.

(7) Seventh Embodiment (7-1) Configuration of Position Detecting System According to Seventh Embodiment FIG. 25 in which parts corresponding to those in FIG.
This shows a position detection system 120 according to a seventh embodiment, in which H is applied to each of the wall surfaces 72AA to 72AD of the wall 72.
In the SI space, colors of different hues separated by 60 ° or more are assigned.

That is, on each of the wall surfaces 72AA to 72AD,
As shown in FIG. 26, a virtual line K1 extending from near the lower end of one end to near the upper end of the other end in the longitudinal direction is used as a boundary.
A color having a high saturation and a predetermined hue is applied to a portion above the virtual line K1 of each of the wall surfaces 72AA to 72AD, and a color having a low saturation and the same hue as the upper portion is applied to a portion below the virtual line K1. I have.

On the other hand, in the robot 121, the position detector 92 (FIG. 1) is added to the robot 91 (FIG. 17) of the fourth embodiment.
The configuration is the same as that of the robot 91 except that a position detection unit 122 as shown in FIG. 27 is provided instead of 8) corresponding to that of FIG.

In this case, the position detection unit 122 is provided with the same number of color extraction units 94A to 94D as the number of the wall surfaces 72AA to 72AD along each side of the region 2, and the image signal S1 output from the camera 16 is provided. Is converted into the HSI format in the image format conversion unit 93, and the image signal S50 thus obtained is sent to each of the color extraction units 94A to 94D and the wall detection unit 123.

As described above, each of the color extraction units 94A to 94D determines the hue within a predetermined angle from the hue designated on the polar coordinates shown in FIG. 16B based on the hue information of each pixel included in the image signal S50. Is detected as a pixel of a color to be extracted, and a portion corresponding to the pixel of the color to be extracted rises to the logical logic “1” level based on the detection result, and a portion corresponding to the pixel of the other color is a logical Generate color extraction signals S51A to S51D falling to the “0” level,
This is sent to the wall detection unit 123.

The wall detecting section 123 is provided with the respective color extracting sections 94A.
To the color extraction signals S51A to 94D supplied from
By superimposing and scanning the image based on S51D, an almost horizontal elongated region of the same hue is detected as one of the wall surfaces 72AA to 72AD, and the detection result is used as a wall detection signal S80 to control the behavior of the robot 121. To the CPU 36.

At this time, the CPU 36 moves the direction of the camera (ie, the head of the robot) in the left-right direction by driving the actuator of the corresponding joint, and the wall detection signal S80 supplied from the wall detection unit 123. , The wall surface having the largest number of pixels in the image based on the image signal S50 (that is, the closest wall surface) 72AA-
72AD, and the wall surfaces 72AA to 72A.
The direction of the camera 16 is adjusted so that the upper end or the lower end in the image of D is horizontal (that is, the optical axis of the camera 16 is perpendicular to the wall surfaces 72AA to 72AD).

The wall surface 7 where the optical axis of the camera 16 is closest
In the state where the wall detection unit 123 is vertically oriented to 2AA to 72AD, the wall detection unit 123 outputs the color extraction signals S51A to S51D provided from the color extraction units 94A to 94D and the pixels included in the image signal S50 provided from the image format conversion unit 93. Based on the chroma information of the image signal S50, a portion of the center portion of the image based on the image signal S50 on which the color with the larger chroma of the wall surfaces 72AA to 72AD is applied (that is, the virtual line K
The upper part than 1 hereafter, this is called wall surface 72AA-72AD
Of the vertical direction H _x (FIG. 26)
And a portion of the wall 72AA-72AD at the center of the image where the color with the smaller saturation is applied (i.e., a portion below the virtual line K1; hereinafter, this is referred to as the wall 72A-72A).
D _x (referred to as low-saturation portion of D) in the vertical direction (FIG. 26)
DOO respectively detect the pixel as a unit, the length H _x of the high saturation of these detected walls 72AA～72AD, the hue of the length L _x and the wall surface thereof 72AA～72AD low chroma portion of the wall surface 72AA～72AD To the wall detection signal S8
The value is sent to the comparison / calculation unit 124 as 1.

The comparison / arithmetic unit 124 generates the wall detection signal S8
1 and the hue of the wall surfaces 72AA to 72AD obtained based on the first and second wall surfaces 7AA to 72AD stored in the first memory 125 in advance.
The IDs of the wall surfaces 72AA to 72AD are detected based on the hues of 2AA to 72AD and the table relating to the IDs.

The comparing / calculating section 124 determines whether or not the wall 7 at the center of the image obtained based on the wall detection signal S81.
Based on the lengths H _x and L _x of the high chroma portion and the low chroma portion of 2AA to 72AD,

[0193]

(Equation 8)

The ratio R _x2 of the vertical length of the high-saturation portion to the height of the wall surface at the center of the image calculated in this way is stored in the second memory 126 in advance. Each wall surface 72AA-72
The ratio R _a2 of the length of the high chroma portion to the height of the wall surfaces 72AA to 72AD at one end of the AD, each wall surface 72AA
Walls 72AA to 72AD at the other end of.
Based on the ratio R _b2 of the length of the high chroma portion to the height of the surface and the length M of each of the wall surfaces 72AA to 72AD.

[0195]

(Equation 9)

By executing the operation given by
From one end of the wall surfaces 72AA to 72AD, the wall surface 72A
A distance x to a portion of the image taken at the center of the image of A to 72AD (from one end of the wall surface 72AA to 72AD in a direction parallel to the wall surface 72AA to 72AD, the robot 1
(Equivalent to the distance to 21).

[0197] Note that the ratio R _a2 longitudinal length of the high-chroma portions with respect to the height of the wall 72AA~72AD at one end of each wall 72AA~72AD, as shown in FIG. 26, at one end of the wall surface 72AA~72AD the length of the high saturation portions and H _a2, the following equation the length of the low saturation part as L _a2

[0198]

(Equation 10)

Is given by In addition, each wall 72AA ~
Ratio R _b2 length of the high-chroma portions with respect to the height of the wall 72AA~72AD at the other end of 72AD is the length of the high saturation portions at the other end of the wall 72AA~72AD and H _b2, the length of the low saturation part _Where L _b2 is

[0200]

[Equation 11]

Given by

Further, after this, the comparison / calculation unit 124
Under the control of U36, the camera 16 is rotated by 90 [°], and the wall surfaces 72AA to 72AD different from the wall surfaces 72AA to 72AD (hereinafter, referred to as first wall surfaces 72AA to 72AD).
After being directed to 2AD (hereinafter, referred to as second wall surfaces 72AA to 72AD), the same processing is executed to obtain the IDs of the second wall surfaces 72AA to 72AD and the second wall surfaces 72AA to 72AD. Detect your position in the parallel direction.

Further, the comparison / calculation unit 124 thereafter calculates the IDs of the first wall surfaces 72AA to 72AD obtained as described above, the position in the direction parallel to the first wall surfaces 72AA to 72AD, and the second I on the walls 72AA-72AD
D and the position in the direction parallel to the second wall surfaces 72AA to 72AD and the map information of the region including the positions of the respective wall surfaces 72AA to 72AD stored in the third memory 127 in advance. It detects its own position and sends the detection result to the CPU 36 as a position detection signal S82.

As a result, in the robot 121, the CPU 36 operates the area 2 based on the position detection signal S82.
The user is able to recognize his / her own position in the vehicle and take autonomous action according to the surrounding situation based on the recognition result.

(7-2) Operation and Effect of Seventh Embodiment In the above configuration, in the position detection system 120, the robot 121 uses the first and second surroundings based on the image signal S1 output from the camera 16. Wall surface 72AA ~
And color 72AD, detects the ratio R _x2 of length H _x of the high saturation portions definitive central portion of the image based on the image signal S1 of each wall 72AA~72D to height, and these detection results, the first memory Each wall 72 stored in 125
AA-72AD colors and their IDs and the second memory 12
6, the length M of each of the wall surfaces 72AA to 72AD stored in
And the ratio R _a2, R _b2 length H _a2, H _b2 high saturation portion with respect to the height of the wall 72AA～72AD at one end and the other end of each wall 72AA～72AD, third memory 12
7 to detect its own position in the area 2 based on the map information stored in the area 7.

Accordingly, in this position detection system 120,
The hues of the two wall surfaces 72AA to 72AD and
Robot 1 based on the high saturation portion of 2AA to 72AD
21 can easily and accurately recognize its own position in the area 2.

In the position detecting system 120, each of the wall surfaces 72AA to 72A arranged along each side of the area 2 is provided.
Since it is only necessary to apply two colors having different hues and greatly different saturations in a predetermined pattern to D, a system can be constructed extremely easily.

Further, in this position detection system 120,
Since no special signal transmission method such as radio waves is used, it can be used without considering the effects on peripheral devices and radio regulations, and a signal generator is installed on the floor of area 2. Since there is no need, there is no possibility that the action of the robot 121 will be hindered.

Further, in this position detection system 120,
Since the method is not a method of writing a sign, a sign, or the like on the floor of the action area 2 of the robot 121, paint or the like can be applied to the floor for another purpose.

Further, in this position detection system 120,
By turning the camera 16 of the robot 121 in a substantially horizontal direction, the wall surface 72A on the front of the robot 121 is moved.
Since the A to 72AD can be imaged by the camera 16, the robot 121 does not need to turn the camera 16 in a predetermined direction to detect its own position in the area 2, and the other robots are captured by the camera 16 There is also an advantage that one's own position in the area 2 can be detected.

According to the above configuration, each of the wall surfaces 72AA to 7AA
By using different hues for each 2AD, each of these wall surfaces 7
The robot 121 applies two colors of the same hue and different saturation in a predetermined pattern to the 2AA to 72AD, and the robot 121 applies the hue of the two wall surfaces 72AA to 72AD and the wall surfaces 72AA to 72AD.
Longitudinal length and H _x detects respective high saturation portion with respect to the height of the wall 72AA~72AD the image central portion in the case where the captured vertically by the camera 16 and 72AD, and these detection results, the first memory 125 And the color of each wall surface 72AA-72AD stored in the
Each wall surface 72AA- stored in the second memory 126
The length M of the 72AD and the ratio R _a2 , R _b2 of the lengths Ha ₂ and H _b2 of the high chroma portion to the height of the wall surfaces 72AA to 72AD at one end and the other end of each of the wall surfaces 72AA to 72AD;
By detecting its own position in the area 2 based on the map information stored in the third memory 127, the robot 121 can accurately detect its own position in the area 2. Thus, it is possible to realize a position detection system and a robot that can accurately detect the position of the user in the area 2.

(8) Eighth Embodiment (8-1) Configuration of Position Detection System According to Eighth Embodiment FIG. 28 in which the same reference numerals are assigned to parts corresponding to FIG.
FIG. 14 shows a position detection system 130 according to an eighth embodiment, in which each wall surface 131A provided along each side of the area 2;
The configuration is the same as that of the position detection system 90 (FIG. 17) of the fourth embodiment, except that A to 131AD are each configured by a panel surface of a plurality of liquid crystal panels 132.

In this case, as shown in FIG. 29, each of the liquid crystal panels 132 has the same color along the same side of the region 2 and has a hue of 60 [ [°]] is controlled by the control unit 133 so as to emit light of different colors separated from each other toward the region 2.

Thus, in the position detecting system 130, the position detecting system 90 (FIG. 1) of the fourth embodiment is used.
As in the case of 7), the robot 91 has the wall surfaces 131AA to 13A.
The wall surface 131AA to 131AD based on the color of 1AD
Can be easily identified.

(8-2) Operation and Effect of Eighth Embodiment In the above configuration, in the position detection system 130, the robot 91 is based on the image signal S1 output from the camera 16 as described above with reference to FIG. And the colors of the surrounding first and second wall surfaces 131AA to 131AD,
Its first and second in the image based on the image signal S1
The height of the wall surfaces 131AA to 131AD is detected, the detection result, the color and ID of each of the wall surfaces 131AA to 131AD stored in the first memory 83 in advance, and the second
The reference value Hstd stored in advance in the memory 84 of the
Of the user in the area 2 on the basis of the map information stored in the memory 85 in advance.

Therefore, according to the position detecting system 130, the same functions and effects as those of the position detecting system 90 (FIG. 17) of the fourth embodiment can be obtained.

In addition, in the position detecting system 130, since each of the wall surfaces 131AA to 131AD emits a predetermined color by itself, for example, as in the fourth embodiment, each of the wall surfaces 72AA
When performing color discrimination inside the robot 91, it is possible to reduce the influence of the external environment such as illumination as compared with the case of using the reflection of light at -72AD.

In the position detection system 130, since the wall surfaces 131AA to 131AD are constituted by the panel surface of the liquid crystal panel 132, the robot 91
Of each wall 131AA-131 according to the type of
There is also an advantage that the color of AD can be freely switched.

According to the above configuration, each of the wall surfaces 131AA to 131AD of each of the regions 2 is formed by a plurality of liquid crystal panels 132 in the position detection system 90 (FIG. 17) of the fourth embodiment. At the same time, those liquid crystal panels 132 that are the same color along the same side of region 2 are
In addition, by controlling the light along different sides of the region 2 to emit light of different colors having a hue of 60 ° or more apart in the HSI space toward the region 2, the inside of the robot 91 is controlled. Can be made less susceptible to changes in the external environment in the color discrimination in
A position detection system and a robot that can accurately detect the position of the user in the vehicle can be realized.

(9) Other Embodiments In the above-described first to eighth embodiments, the present invention relates to autonomous mobile robots 3A to 3C, 51A to 51C, 71,
The case where the present invention is applied to 91, 101, 111, and 121 has been described, but the present invention is not limited to this, and can be applied to various other robots or other moving objects.

In the first embodiment described above, FIG.
As shown in (A), the case where the identification body 23 is attached to each of the robots 3A to 3C via the support rod 22 has been described. However, the present invention is not limited to this. May be arranged on the head 12 of the robot 140. The point is that the identification body 23 is located at a position that is easy to see from the other robots 3A to 3C with respect to the robots 3A to 3C.
Is attached, various other positions can be applied as the attachment position of the identification body 23.

Further, in the above-described first embodiment, the case where the discriminating body 23 is formed in a spherical shape has been described. However, the present invention is not limited to this. For example, an elliptical rotating body as shown in FIG. The shape may be various other shapes such as a column shape as shown in FIG. However, the shape of the identification body 23 is selected as a rotating body having a central axis perpendicular to the moving direction of the robots 3A to 3C, and the surface thereof is divided into a plurality of belt-like regions parallel to the moving direction of the robots 3A to 3C. By coloring each band-shaped region in a predetermined color with the color pattern described above, the identifier can be viewed in the same shape and the same color pattern in any direction when the region 2 is flat. In addition, individual identification of the identification body can be facilitated.

Further, in the first embodiment described above, the case where the surface of the discriminating body 23 is colored in three colors has been described. However, the present invention is not limited to this. May be. Further, in the above-described first embodiment, a case has been described in which 16 colors are prepared as colors for identification, but the present invention is not limited to this, and other numbers may be used.

Further, in the above-described first embodiment, the camera 16 is applied as an image pickup means for picking up an image of the identification body 23 having a different color pattern for each of the robots 3A to 3C provided in the other robots 3A to 3C. However, the present invention is not limited to this, and various other imaging means can be applied.

Further, in the above-described first embodiment, the color pattern detecting means for detecting the color pattern of the identification body 23 imaged by the camera 16 based on the image information (image signal S1) supplied from the camera 16 is provided. 6, a case has been described in which a plurality of color extraction units 31A to 31U and a color pattern detection unit 32 are configured as shown in FIG. 6. However, the present invention is not limited to this. Applicable.

Further, in the first embodiment described above, the color pattern of the discriminator 23 detected by the color pattern detector 32, the color pattern information of the discriminator 23 for each of the robots 3A to 3C stored in advance, and Based on the camera 16
Robots 3A to 3C having an identification body 23 captured by
Identification means for identifying the individual of the comparison / calculation unit 33, the first
Has been described, the present invention is not limited to this, and various other configurations can be applied. In this case, various other storage means can be applied in place of the first memory 34.

Further, in the above-described first embodiment, size detecting means for detecting the diameter of the identification body 23 (or the size of another portion) in an image based on the image signal S1 supplied from the camera 16. To a plurality of color extraction units 31
Although a case has been described in which the configuration is made up of A to 31U and the color pattern detection unit 32, the present invention is not limited to this, and various other configurations can be applied.

Further, in the first embodiment described above, the camera 16 is determined based on the size of the discriminator 23 detected by the color pattern detecting section 32 and a reference value stored in advance.
Calculating means for calculating the distance L1 from the object to the identification body 23,
Although the case has been described in which the configuration is made up of the comparison / calculation unit 33 and the second memory 35, the present invention is not limited to this, and various other configurations can be applied. In this case, various other storage means can be applied instead of the second memory 35.

Further, in the first embodiment, the reference value for calculating the distance L1 from the camera 16 to the discriminating object 23 is set to the discriminating object when the camera 16 and the discriminating object 23 are separated by 1 [m]. Although the case where the diameter is selected in units of 23 pixels has been described, the present invention is not limited to this, and various other values can be applied.

Further, in the above-described first embodiment, a case has been described in which each identification body 23 is simply colored in a unique color pattern with a plurality of colors. However, the present invention is not limited to this. Each of the 23 color patterns is stored in a predetermined color space (for example, the HSI space described with reference to FIG.
An RGB space representing colors in red, green and blue levels,
Alternatively, a color is formed by a combination of a plurality of colors separated by a predetermined first distance in a luminance level and a YUV space represented by first and second color difference levels (that is, in a predetermined color space as a color for identification). (A color separated by a first distance) may be used.

In this case, instead of the color extracting sections 31A to 31U, the individual identifying section 30 of each of the robots 3A to 3C converts the image signal S1 supplied from the camera 16 into an image format image signal corresponding to its color space. Conversion means for conversion (for example, the image format conversion unit 93 of the fourth embodiment) and a plurality of color extractions for extracting pixels of designated colors different from each other from an image based on an image signal output from the conversion means Means (for example, each color extracting unit 94 of the fourth embodiment)
A to 94D), and the color of the identification body 23 captured by the camera 16 by the color pattern detecting means constituted by the converting means, the plurality of color extracting means, and the color pattern detecting section 32 (FIG. 4). What is necessary is just to make it detect a pattern. By doing so, the robot 3
It is possible to avoid erroneous determination of the color of the identification body 23 in A to 3C beforehand, and the robots 3A to 3C can be more accurately performed.
An individual identification system and a robot capable of identifying the individual C can be realized. In this case, if the image format of the image signal S1 output from the camera 16 conforms to the above-described color space, the conversion means can be omitted.

Further, in this case, the combination of colors applied to the discriminator 23 may be selected so that adjacent colors are separated by a second distance larger than the first distance in the above-described color space. By doing so, it is possible to realize an individual identification system and a robot that can identify the robots 3A to 3C with higher accuracy.

Further, in the above-described first embodiment, a case has been described in which an object that does not emit light is used as the discriminator 23. However, the present invention is not limited to this.
For example, a light emitting unit such as a light bulb is accommodated in a transparent spherical shell, and the surface of the spherical shell is colored with a corresponding color pattern so that the identifier 23 emits light of the corresponding color pattern. By doing so, it is possible to reduce the probability of occurrence of erroneous identification in the color identification by the identification means, and more accurately, the robots 3A to 3D.
An individual identification system and a robot capable of identifying an individual of 3C can be realized.

Further, in the second embodiment described above, FIG.
Although the case where the color pattern is formed by color-coding the surface of the identification seal 52 like 0 has been described, the present invention is not limited to this, and the color of the surface of the identification seal 52 is color-coded as shown in FIG. In other words, if the surface of the identification seal 52 is color-coded with a plurality of colors,
Various other shapes can be applied as the shape of the color pattern.

In this case, for example, as shown in FIG. 33, a color pattern is formed by coloring a plurality of concentric annular regions 141A to 141C using a predetermined number of colors from a plurality of types of identification colors. You may do it.

In addition to this, for example, FIG.
(C) A linear region 141D colored in a predetermined color extending in a predetermined radial direction of each of the annular regions 141A to 141C as shown in FIG.
Alternatively, a region such as an uncolored rectangular region 141E or a fan-shaped region 141F may be provided. In this case, regions of a predetermined shape such as the linear region 141D, the rectangular region 141E, or the fan-shaped region 141F are the robots 51A to 51A.
The robot 51 is set in advance so as to face the front or the rear of C, so that the robot 51 can be controlled based on the orientation of the area.
The direction of A to 51C can also be detected.

Further, in the above-described second embodiment, a case is described in which the identification seal 52 whose surface is color-coded with a predetermined color pattern is attached to each of the robots 51A to 51C as means for giving a different color pattern. However, the present invention is not limited to this.
Each of the robots 5 is directly painted on the upper surface of the robot 51C (or another predetermined position that can be imaged by the camera 53).
Different predetermined color patterns may be assigned to 1A to 51C, and various other methods may be applied as means for assigning different predetermined color patterns to the robots 51A to 51C.

In this case, for example, each of the robots 51A to 51C
Light emitting means for emitting light having different color patterns from each other (for example, a light emitting body such as a light bulb is provided below the transparent film and colored with a color pattern corresponding to the transparent film) may be provided. By doing so, it is possible to reduce the probability that erroneous identification will occur in the color identification by the identification means, and the robot 3 will be more accurately accordingly.
An individual identification system and a robot capable of identifying individuals A to 3C can be realized.

Further, in the above-described second embodiment, based on the position of the color pattern of each of the robots 51A to 51C in the image based on the image information (image signal S1) supplied from the camera 53, Robot 51
Although a case has been described where the position detection means for detecting the positions of A to 51C is configured by the comparison / calculation unit 56 and the memory 57, the present invention is not limited to this, and various other configurations can be applied. In this case, various other storage means can be applied instead of the memory 57.

Further, in the above-described second embodiment, the case has been described in which the positions of the robots 51A to 51C detected by the individual identification unit 54 are transmitted to the robots 51A to 51C by radio waves. The present invention is not limited to this, and other wireless means such as infrared rays or other various transmission means such as wires can be applied.

Further, in the above-described second embodiment, a case has been described in which each identification seal 52 is simply colored by a plurality of colors into a unique color pattern. However, the present invention is not limited to this. Each of the 52 color patterns is formed by a combination of a plurality of colors separated by a predetermined first distance in a predetermined color space (for example, an HSI space, an RGB space, or a YUV space) (that is, a predetermined color as a color for identification). (A color separated by a first distance in a color space may be used).

In this case, the individual identifying section 54 includes the color extracting section 3
A conversion unit (for example, an image format conversion unit 93 of the fourth embodiment) for converting the image signal S30 supplied from the camera 53 into an image signal of an image format corresponding to the color space, instead of 1A to 31U; A plurality of color extracting means (for example, each of the color extracting units 94A to 94D of the fourth embodiment) for extracting pixels of a designated color different from each other from an image based on an image signal output from the means. Each identification sticker 5 imaged by the camera 53 by the color pattern detecting means constituted by the means and a plurality of color extracting means and the color pattern detecting section 55 (FIG. 11).
The second color pattern may be detected. By doing so, an erroneous determination of the color of the identification seal 52 in the individual identification section 54 can be avoided beforehand, and an individual identification system that can identify the robots 51A to 51C more accurately by that amount. realizable. In this case as well, if the image format of the image signal S1 output from the camera 16 conforms to the above-described color space, the conversion means can be omitted.

Further, in this case, the combination of colors applied to the identification seal 52 may be selected so that adjacent colors are separated by a second distance larger than the first distance in the above-described color space. By doing so, an individual identification system that can identify the robots 51A to 51C with higher accuracy can be realized.

Further, in the third embodiment described above, a case has been described in which the color applied to each of the wall surfaces 72AA to 72AD along each side of the region 2 is changed, but the present invention is not limited to this. Each wall surface 72A along each side of the area 2
A to 72AD may be divided into a plurality of regions parallel to the Z direction, and the color to be applied may be changed for each of the regions.

Further, in the above-described first to third embodiments, the case where the color extracting units 31A to 31U are configured as shown in FIG. 6 has been described. However, the present invention is not limited to this. Separating means for separating the supplied image signal into a luminance signal and a chrominance signal (in the embodiment, a separating circuit 41, and based on the luminance signal and the chrominance signal, determine the luminance level and chrominance level of each pixel in the image based on the image signal. Level detecting means (analog / digital conversion circuits 42, 43A, 43B in the embodiment) for sequentially detecting, the luminance level and color difference level of the pixel detected by the level detecting means, and the color difference level for each luminance level stored in advance. (For example, the first to fourth memories 44 </ b> A to 44 </ b> A in this embodiment) determine whether or not each pixel has a predetermined color based on the upper limit and the lower limit.
D, if the first to fourth comparison circuits 45A to 45D and the determination circuit 48) are provided, various other configurations can be applied to the configuration of the color extraction unit.

Further, in the above-described third to eighth embodiments, a plurality of wall surfaces 72AA to 72AD, 131AA to 131A of different colors provided along the periphery of the region 2 are provided.
D, corresponding predetermined wall surfaces 72AA to 72AD, 1
31AA-131AD (that is, the front wall surface 72AA-
72AD, 131AA to 131AD), the case where the camera 16 is applied as the imaging means for imaging is described. However, the present invention is not limited to this, and various other imaging means can be applied.

Further, in the above third to eighth embodiments, the image information (image signal S
Based on 1), the colors of the wall surfaces 72AA to 72AD and 131AA to 131AD imaged by the camera 16 and the wall surfaces 72AA to 72AD, 131AA to 131AD.
Relative to (the wall surfaces 72AA to 72AD, 13
Distance L2 from 1AA to 131AD or its wall surface 72A
The wall surfaces 72AA to 72AD, 131AA to 13 in a direction parallel to A to 72AD and 131AA to 131AD.
The color and relative position detecting means for detecting the distance x) from one end of the 1AD are provided by a plurality of color extracting units 31A to 31D, 94A to
94E, wall detectors 8, 103, 114, 123, comparison
Arithmetic units 82, 104, 115, 124 and first and second memories 83, 84, 105, 106, 116, 11
7, 125, and 126 have been described, but the present invention is not limited to this, and various other configurations can be applied. In this case, the first and second memories 83,
84, 105, 106, 116, 117, 125, 12
Instead of 6, various other storage means can be applied.

In the third to eighth embodiments, the wall surfaces 72AA to 72A captured by the camera 16 are used.
D, colors of 131AA to 131AD and the corresponding wall surface 72AA
-72AD, relative positions with respect to 131AA-131AD, and all the previously stored wall surfaces 72AA-72A
D, colors of 131AA-131AD and all wall surfaces 72A
A position detecting means for detecting its own position in the area 2 based on the map information of the area 2 including the positions of A to 72AD and 131AA to 131AD,
4, 115, 124 and third memories 85, 107, 1
18 and 127, the present invention is not limited to this, and the third memory 85, 1
Various other storage means can be applied in place of 07, 118, and 127.

Further, in the third to eighth embodiments, the robots 71, 91, 101, 111, and 121 have two robots.
Wall surfaces 72AA-72AD, 131AA-131AD
Has described the case where the user's own position in the area 2 is detected, but the present invention is not limited to this, and the user's own position in the area 2 is detected from three or more wall surfaces 72AA to 72AD and 131AA to 131AD. You may do it.

Further, in the above-described fourth to eighth embodiments, the colors for identification in FIG.
The angle around the origin O in the polar coordinates shown in (B) is 60 [°]
The above description has been given of the case where the colors separated from each other are selected. However, the present invention is not limited to this, and the colors around the origin O in polar coordinates shown in FIG. You may do it. Also, as a color for identification, H
Colors separated by a predetermined distance in a color space other than the SI space (such as an RGB space or a YUV space) may be used.

Further, in the above-described fourth to eighth embodiments, in the HSI space, only colors for identification are used.
The angle around the origin O in the polar coordinates shown in FIG.
Although the case where a color separated by [°] or more is selected has been described, the present invention is not limited to this. For example, adjacent walls may be separated by 60 ° or more in the HSI space (or another color space). Colors are assigned (for example, in FIG. 16B, the wall surface 72AA is yellow (Y), the wall surface 72AB is cyan (C), the wall surface 72AC is red (R), and the wall surface 72AD).
May be coated with blue (B). By doing so, the robots 91, 101, 11
Wall surfaces 72AA to 72AD131 inside 1, 121
It is possible to avoid erroneous discrimination when discriminating the colors of AA to 131AD beforehand, and to construct a position detection system and a robot apparatus that can more accurately detect one's own position in the area 2.

In the fifth embodiment, the case where the saturation (saturation) of the color applied to each of the wall surfaces 72AA to 72AD is linearly changed has been described. However, the present invention is not limited to this. , May be changed non-linearly. However, in this case, one wall surface 72AA to 72A
It is necessary to make sure that there is no part with the same degree of saturation in D.

Further, in the fifth embodiment described above, as the predetermined data relating to the change in the degree of saturation of each of the wall surfaces 72AA to 72AD, the length M of each of the wall surfaces 72AA to 72AD, and one end and the other end of each of the wall surfaces 72AA to 72AD. Has been described in the case where the saturations S _min and S _max are stored in the second memory 106, but the present invention is not limited to this.
In short, the data, comparison and calculation section 104 on the basis of the saturation S _x color applied to the wall surface 72AA~72AD at the center of the image based on the image signal S50 detected by the wall detection unit 103 If the data can detect its own position in the area 2, the second
Other data can be applied to the data stored in the memory 106.

In the sixth embodiment, the oblique lines 112 are formed on the wall surfaces 72AA to 72AD so as to extend from the vicinity of the lower end of one end of the wall surfaces 72AA to 72AD to the vicinity of the upper end of the other end.
Has been described, but the present invention is not limited to this. For example, as shown in FIG.
The oblique line 112 may be written on each of the wall surfaces 72AA to 72AD from the lower end of one end of A to 72AD to the upper end of the other end, or the diagonal line may be written in other forms.

Further, in the above-described sixth embodiment, the wall surfaces 72AA to 72AD at the wall surfaces 72AA to 72AD are used.
As the predetermined data relating to the change in the ratio of the portion above the oblique line 112 with respect to the height, the length M of each of the wall surfaces 72AA to 72AD, and the portions above and below the oblique line 112 at one end and the other end of each wall surface 72AA to 72AD. Length U _a1 ,
The case where U _b1 , L _a1 , and L _b1 are stored in the second memory 117 has been described. However, the present invention is not limited to this. In short, the data and the data detected by the wall detection unit 115 are used. Based on the image signal S50, based on the ratio _{Rx of the} upper part (or lower part) of the oblique line 112 to the height of the wall surfaces 72AA to 72AD at the central part of the image at the central part of the image, the comparing / calculating part 115 If the data can be detected in the second memory 117, other data can be applied as the data stored in the second memory 117.

In the seventh embodiment, the imaginary line K1 separating the upper part and the lower part of the wall surfaces 72AA to 72AD passes through the vicinity of the lower end of one end of the wall surfaces 72AA to 72AD and the vicinity of the upper end of the other end. I mentioned the case,
The present invention is not limited to this. For example, as shown in FIG. 36, the imaginary line K1 (or may be a diagonal line) has the wall surfaces 72AA to 72A.
Each wall 7 passes through the lower end of one end of D and the upper end of the other end.
The 2AA to 72AD may be divided into an upper portion and a lower portion, and a virtual line K1 or a diagonal line may be selected or described in other forms.

Further, in the seventh embodiment, the length H of the high chroma portion with respect to the height of the wall surfaces 72AA to 72AD is determined.
_Although the case where the ratio _Rx of _x changes linearly has been described, the present invention is not limited to this, and may change nonlinearly. However, also in this case, the wall surfaces 72AA to 72AD are formed on one wall surface 72AA to 72AD.
The ratio R _x high chroma portion of the length H _x it is necessary to make no portion to be the same to the height of the.

Further, in the seventh embodiment, the wall surfaces 72AA to 72AD at the wall surfaces 72AA to 72AD are used.
As the predetermined data relating to the change in the ratio R _x high chroma portion of the length H _x for height, each wall 72AA~72AD
The length M of the length H _a2 of high-chroma portions and low chroma portion at one end and the other end of each wall 72AA~72AD, L _a2,
Although the case where H _b2 and L _b2 are stored in the second memory 126 has been described, the present invention is not limited to this, and the point is that the data and the image signal S50 detected by the wall detection unit 123 are stored. Wall 7 at the center of the image based on
The length H _x of the high chroma portion for the height of 2AA to 72AD
If the comparison / calculation unit 124 can detect its own position in the area 2 based on the ratio _Rx of the data, other data to be stored in the second memory 126 Applicable.

Further, in the third and eighth embodiments, the wall surfaces 72AA to 72A are provided inside the robot 91.
D, distances from the wall surfaces 72AA to 72AD and 131AA to 131AD are detected as relative positions with respect to 131AA to 131AD, and in the fourth to eighth embodiments, the wall surfaces 72A inside the robots 101, 111, and 121 are detected.
The wall surface 72AA as a relative position with respect to A to 72AD.
The corresponding wall surfaces 72AA to 7 in a direction parallel to 72AD.
Although the case where the distance from one end of 2AD is detected has been described, the present invention is not limited to this, and other relative positions may be detected.

In the eighth embodiment, each of the wall surfaces 131AA to 131AD is connected to the liquid crystal panel display 1.
Although the description has been given of the case where the panel is constituted by 32 panel surfaces, the present invention is not limited to this, and each wall surface 131AA to
131AD may be configured with a display surface of a display other than the liquid crystal panel display 132 (for example, a CRT (Cathode Ray Tube)). Further, for example, a concave portion is provided in the normal wall surfaces 72AA to 72AD (FIG. 13), a film of a predetermined color is attached so as to cover the concave portion, and a light source is disposed in the concave portion.
The light of the color assigned to 2AA to 72AD may be emitted toward the area 2. In short, the light emitting means for emitting the light 2 of the color assigned to the wall toward the area constitutes the wall. Alternatively, if the light emitting means is provided on the wall surface, various other structures can be applied as the structure of the light emitting means.

Further, in the above-described eighth embodiment, each liquid crystal panel display 132 is simply formed by each of the wall surfaces 131AA to 131A.
Although the case where different colors of light are emitted for each 131AD has been described, the present invention is not limited to this. For example, the colors and diagonal lines assigned to each liquid crystal panel display 132 as in the fifth to seventh embodiments are described. May be displayed, and the robot 91 may be configured as in the fifth to seventh embodiments.

In the fourth to seventh embodiments, the image format converter 93 is provided for converting the image format of the image signal S1 output from the camera 16 into an image format corresponding to the HSI space. Although the case has been described, the present invention is not limited to this. For example, the image format of the image signal S1 output from the camera 16 may be an image format corresponding to the color space used when selecting the colors of the wall surfaces 72AA to 72AD. In some cases, the image format converter 93 may be omitted.

[0263]

As described above, according to the present invention, in a discriminating apparatus and method for identifying a moving object moving in a predetermined area or another object in the area, and a robot apparatus, each moving object or other object is provided. In each of the moving objects or the robot apparatus, an identification unit having a different color pattern is provided, and an imaging unit provided in each of the moving units or the robot apparatus captures an image of an identification unit of another moving object or another object. Based on the first image information, the color pattern of the identification object imaged by the imaging unit is detected, and the image is imaged by the imaging unit based on the detection result and the color pattern information of each identification object stored in advance. By identifying an identification object or another object, a simple identification device and method capable of reliably identifying a moving object and a robot device having a simple configuration capable of reliably identifying another object are realized. Kill.

[0264] In the identification device and method for identifying a plurality of moving objects moving in a predetermined area, an imaging means for imaging the entire area is arranged at a predetermined position, and different colors are provided at predetermined positions of the moving objects. Pattern,
Based on the first image information output from the imaging unit, the color pattern of each moving body is detected, and the detection result and the previously stored color pattern information provided for each moving body are detected. Based on the identification of each moving object, a simple identification device and a simple identification method capable of reliably identifying the moving object can be realized.

Further, in a position detection and method and a robot apparatus for detecting the position of a moving body moving within a predetermined area or the position of the moving object itself within the area, a plurality of wall surfaces of different colors are provided along the periphery of the area. Capturing an image of a wall surface by an imaging unit provided in the moving object or the robot device, detecting a color of the imaged wall surface based on the obtained first image information and a relative position of the moving object or the robot with respect to the wall surface, By detecting the position of the moving object or the robot device in the area based on the detection result, it is possible to realize a position detecting device and method and a robot device that can accurately detect the position of the moving object or the robot in the area. .

Further, based on the luminance signal and the color difference signal of the image signal, level detecting means for sequentially detecting the luminance level and the color difference level of each pixel in the image based on the image signal, and A determination unit is provided for determining whether or not each pixel has a predetermined color based on the luminance level and the color difference level, and the upper limit value and the lower limit value of the color difference level for each luminance level stored in advance. This makes it possible to realize a color extraction device that can accurately extract a desired color.

[Brief description of the drawings]

FIG. 1 is a plan view showing the overall configuration of an individual identification system according to a first embodiment.

FIG. 2 is a schematic side view showing a configuration of a robot and a configuration of an identification body according to a first embodiment.

FIG. 3 is a schematic block diagram showing a configuration of a robot according to the first embodiment.

FIG. 4 is a block diagram illustrating a configuration of an individual identification unit according to the first embodiment.

FIG. 5 is a schematic diagram used for describing a configuration of a color extraction unit.

FIG. 6 is a block diagram illustrating a configuration of a color extraction unit.

FIG. 7 is a plan view showing the overall configuration of an individual identification system according to a second embodiment.

FIG. 8 is a plan view showing the overall configuration of an individual identification system according to a second embodiment.

FIG. 9 is a schematic perspective view showing a configuration of a robot according to a second embodiment.

FIG. 10 is a plan view for explaining an identification seal.

FIG. 11 is a block diagram illustrating a configuration of an individual identification unit according to a second embodiment.

FIG. 12 is a schematic block diagram showing a configuration of a robot according to a second embodiment.

FIG. 13 is a perspective view showing an overall configuration of a position identification system according to a third embodiment.

FIG. 14 is a plan view showing an overall configuration of a position identification system according to a third embodiment.

FIG. 15 is a block diagram illustrating a configuration of a position detection unit according to a third embodiment.

FIG. 16 is a schematic diagram used for describing an HSI space.

FIG. 17 is a plan view showing an overall configuration of a position identification system according to a fourth embodiment.

FIG. 18 is a block diagram illustrating a configuration of a position detection unit according to a fourth embodiment.

FIG. 19 is a plan view showing an overall configuration of a position identification system according to a fifth embodiment.

FIG. 20 is a schematic diagram illustrating a state of each wall surface in the fifth embodiment.

FIG. 21 is a block diagram showing a configuration of a position detection unit according to a fifth embodiment.

FIG. 22 is a plan view showing the overall configuration of a position identification system according to a sixth embodiment.

FIG. 23 is a schematic diagram illustrating a state of each wall surface in the sixth embodiment.

FIG. 24 is a block diagram showing a configuration of a position detector according to a sixth embodiment.

FIG. 25 is a plan view showing the overall configuration of a position identification system according to a seventh embodiment.

FIG. 26 is a schematic diagram showing a state of each wall surface in the seventh embodiment.

FIG. 27 is a block diagram showing a configuration of a position detector according to a seventh embodiment.

FIG. 28 is a plan view showing an overall configuration of a position identification system according to an eighth embodiment.

FIG. 29 is a plan view for describing the configuration of a position identification system according to an eighth embodiment.

FIG. 30 is a schematic side view showing another embodiment.

FIG. 31 is a side view and a perspective view showing another embodiment.

FIG. 32 is a plan view showing another embodiment.

FIG. 33 is a plan view showing another embodiment.

FIG. 34 is a plan view showing another embodiment.

FIG. 35 is a plan view showing another embodiment.

FIG. 36 is a plan view showing another embodiment.

[Explanation of symbols]

1, 50 ... individual identification system, 2 ... area, 3A-3
C, 51A to 51C, 71, 91, 101, 111, 1
21: robot, 16, 53: camera, 23: identification body, 30, 54: individual identification unit, 31A to 31U, 9
4A to 94E: color extraction unit, 32, 55 ... color pattern extraction unit, 33, 56, 82, 104, 115, 124 ...
... Comparison / calculation units, 34, 35, 44A to 44D, 57,
83-85, 105-107, 116-118, 125
127, a memory, 36, a CPU, 41, a separation circuit, 42, 43A, 43B, an analog / digital conversion circuit, 45A to 45D, a comparison circuit, 48, a determination circuit, 49, a frame memory, 52 identification seal, 5
8 ... transmitting unit, 70 ... wall, 72AA to 72AD, 13
1AA to 131AD: wall surface, 80, 102, 113,
122: Position detecting unit, 81, 103, 114, 123
... Wall detection unit, 93 image format conversion unit, 13
2 ... liquid crystal panel, 133 ... control unit, D1 ... brightness data, D2A, D2B ... color difference data, S1, S30,
S50 ... Image signal, S10A to S10U, S51A to
S51D: color extraction signal; S11: identification body information signal;
S12: identification object detection signal, S20: luminance signal, S2
1A, S21B ... color difference signal, S31 ... identification seal detection signal, S32 ... robot position detection signal, S40 ...
Wall detection signal, S41, S62, S71, S82 ... Position detection signal.

 ────────────────────────────────────────────────── ─── Continued on the front page (72) Inventor Makoto Inoue 6-35 Kita Shinagawa, Shinagawa-ku, Tokyo Inside Sony Corporation

Claims (55)

[Claims] 1. An identification device for identifying a moving object that moves within a predetermined area, comprising: an identifying object having a different color pattern provided on each of the moving objects; Imaging means for imaging the identification object disposed on the moving body; and detecting the color pattern of the identification object imaged by the imaging means based on first image information supplied from the imaging means. A color pattern detection unit; and the identification object imaged by the imaging unit based on a detection result by the color pattern detection unit and color pattern information of the identification object for each moving object stored in advance. An identification device, comprising: identification means for identifying the moving object. 2. A size detecting means for detecting a size of the identification object in an image based on the first image information supplied from the imaging means, and a detection result by the detecting means, The identification device according to claim 1, further comprising: a calculating unit that calculates a distance to the identification object based on the reference value. 3. The discriminating body is a rotating body having a center axis perpendicular to the moving direction of the moving body, the surface of which is divided into a plurality of belt-like regions parallel to the moving direction of the moving body. The identification device according to claim 1, wherein each of the band-shaped regions is colored in a predetermined color by the color pattern. 4. Each of said color patterns is formed by a combination of a plurality of colors separated from each other by a predetermined first distance in a predetermined color space, and said color pattern detection means is provided by said imaging means supplied from said imaging means. After converting the first image information into the second image information corresponding to the corresponding color space, detecting the color pattern of the identification object imaged by the imaging means based on the second image information. The identification device according to claim 1, wherein: 5. The color pattern is formed by selecting a combination of the colors such that adjacent colors are separated from each other by a second distance larger than the first distance in the color space. The identification device according to claim 4, wherein 6. The identification apparatus according to claim 1, wherein each of said identification bodies emits light of said corresponding color pattern. 7. An identification device for identifying a moving body moving in a predetermined area, wherein a different color pattern is provided for each of the moving bodies and is different for each of the moving bodies disposed on the other moving bodies. Imaging means for imaging a body; color pattern detection means for detecting the color pattern of the identification object imaged by the imaging means based on first image information supplied from the imaging means; Means for identifying the moving object having the identification object imaged by the imaging means, based on the detection result by the means and color pattern information of the identification object for each of the moving objects stored in advance. An identification device characterized by comprising: 8. A size detection means for detecting a size of the identification object in an image based on the first image information supplied from the imaging means, and a detection result obtained by the detection means, 8. The identification device according to claim 7, further comprising a calculating unit that calculates a distance to the identification object based on the reference value. 9. The discriminating body is a rotating body having a central axis perpendicular to the moving direction of the moving body, and its surface is divided into a plurality of band-shaped regions parallel to the moving direction of the moving body, The identification device according to claim 7, wherein each of the band-shaped regions is colored in a predetermined color by the color pattern. 10. Each color pattern is formed by a combination of a plurality of colors separated from each other by a predetermined first distance in a predetermined color space, and said color pattern detection means is supplied from said imaging means. After converting the first image information into the second image information corresponding to the corresponding color space, detecting the color pattern of the identification object imaged by the imaging means based on the second image information. The identification device according to claim 7, characterized in that: 11. A method for identifying a moving object moving in a predetermined area, comprising: a first step of providing an identifying object having a different color pattern to each of the moving objects; A second step of taking an image of the identification object of the other moving body by the taken imaging means, and a first step of imaging the identification object taken by the imaging means based on the first image information output from the imaging means. A third step of detecting the color pattern; a color pattern of the detected identification object; and a color pattern information of each identification object stored in advance, the identification object captured by the imaging unit. And a fourth step of identifying the information. 12. A detection step for detecting the size of the identification object in an image based on the first image information output from the imaging means, and the detected size of the identification object are stored in advance. 12. The identification method according to claim 11, further comprising an operation step of calculating a distance to the identification object based on the reference value. 13. The discriminating body is a rotating body having a center axis perpendicular to the moving direction of the moving body, the surface of which is divided into a plurality of belt-like regions parallel to the moving direction of the moving body. The identification method according to claim 11, wherein each of the band-shaped regions is colored in a predetermined color by the color pattern. 14. Each of the color patterns is formed by a combination of a plurality of colors separated by a predetermined first distance in a predetermined color space. In the third step, the color pattern supplied from the imaging means is provided. The second image information corresponding to the color space corresponding to the second
12. The identification method according to claim 11, wherein the color pattern of the identification object imaged by the imaging unit is detected based on the second image information after the conversion into the image information. 15. The color pattern according to claim 1, wherein said color combination is selected and formed such that adjacent colors are separated by a second distance greater than said first distance in said color space. 15. The identification method according to claim 14, wherein the identification method is used. 16. The apparatus according to claim 11, wherein each of said discriminators emits light of the corresponding color pattern.
Identification method described in. 17. An image pickup means for picking up an identification object having a different color pattern provided on each of other objects, and said image pickup means picked up by said image pickup means based on first image information supplied from said image pickup means. A color pattern detection unit that detects the color pattern of the identification object; a detection result obtained by the color pattern detection unit; and a color image information captured by the imaging unit based on color pattern information of each identification object stored in advance. A robot apparatus comprising: identification means for identifying an identification object. 18. A size detection means for detecting a size of the identification object in an image based on the first image information supplied from the imaging means, and a detection result obtained by the detection means, 18. The robot apparatus according to claim 17, further comprising a calculating unit that calculates a distance to the identification object based on the reference value. 19. Each of the color patterns is formed by a combination of a plurality of colors separated by a predetermined first distance in a predetermined color space, and the color pattern detecting means is provided by the imaging means. After converting the first image information into the second image information corresponding to the corresponding color space, detecting the color pattern of the identification object imaged by the imaging means based on the second image information. 18. The robot device according to claim 17, wherein 20. An identification device for identifying a plurality of moving objects moving in a predetermined area, comprising: an image pickup means for picking up an image of the entire area; and a first image information output from the image pickup means. A color pattern detection unit that detects a different color pattern for each of the moving bodies respectively assigned to a predetermined position of the moving body; a detection result of the color pattern detection unit; An identification unit for identifying each of the moving objects based on the information on the color pattern provided. 21. A position of each of the moving objects in the area based on a position of the color pattern of each of the moving objects in an image based on the first image information supplied from the imaging means. 21. The identification device according to claim 20, further comprising a position detection unit. 22. The color pattern according to claim 20, wherein each of the color patterns is formed by coloring a plurality of concentric annular regions by using a predetermined number of colors from among a plurality of types of predetermined colors. Identification device. 23. The identification device according to claim 20, wherein each of said color patterns has a region extending in a radial direction of said annular region. 24. Each of the color patterns is formed by a combination of a plurality of colors separated by a predetermined first distance in a predetermined color space, and the color pattern detection means is provided by the image pickup means. After converting one image information into a second image information corresponding to the corresponding color space, detecting the color pattern of each of the moving objects based on the second image information. Item 21. The identification device according to Item 20. 25. Each of the color patterns is formed by selecting a combination of the colors so that the adjacent colors are separated from each other by a second distance larger than the first distance in the color space. The identification device according to claim 24, wherein: 26. The identification apparatus according to claim 20, further comprising a light emitting means provided on each of said moving bodies to emit light of the corresponding color pattern. 27. An identification method for identifying a plurality of moving objects moving within a predetermined area, wherein an imaging means for imaging the entire area is arranged at a predetermined position, and different from each other at a predetermined position of each moving object. A first step of providing a color pattern; a second step of detecting the color pattern of each of the moving objects based on the first image information output from the imaging means; and a second step of detecting the color pattern of each of the moving objects. And a third step of identifying each of the moving objects based on the detection result in step (1) and the color patterns provided for each of the moving objects stored in advance. 28. A position of each of the moving objects in the area based on a position of the color pattern of each of the moving objects in an image based on the first image information supplied from the imaging means. 28. The identification method according to claim 27, further comprising a detection step. 29. A method according to claim 27, wherein each of said color patterns is obtained by coloring a plurality of concentric annular regions using a predetermined number of colors from among a plurality of types of predetermined colors. Identification method. 30. The identification method according to claim 27, wherein each of said color patterns has a region extending in a radial direction of said annular region. 31. Each of the color patterns is formed by a combination of a plurality of colors separated by a predetermined first distance in a predetermined color space, and in the second step, the color pattern supplied from the imaging means is provided. After converting the first image information into the second image information corresponding to the corresponding color space,
28. The color pattern of each of the moving objects is detected based on the second image information.
Identification method described in. 32. Each of the color patterns is formed by selecting a combination of the colors such that adjacent colors are separated from each other by a second distance larger than the first distance in the color space. The identification device according to claim 31, characterized in that: 33. A position detecting device for detecting a position of a moving body moving in a predetermined area in the area, comprising: a plurality of wall surfaces of different colors provided along the periphery of the area; Imaging means for imaging the corresponding predetermined wall surface, and the color of the wall surface imaged by the imaging means and the movement with respect to the wall surface based on first image information output from the imaging means. A color and relative position detecting means for detecting a relative position of the body; a detection result of the color and relative position detecting means; a color of each of the wall surfaces and a position of each of the wall surfaces stored in advance. A position detecting device for detecting a position of the moving body in the area based on the map information of the area. 34. A color separated by a predetermined first distance from each other in a predetermined color space as the color of each of the wall surfaces, and the color and relative position detection means are supplied from the imaging means. After converting the first image information into second image information corresponding to the corresponding color space, detecting a color of the wall surface imaged by the imaging unit based on the second image information. The position detecting device according to claim 33, wherein: 35. The color of each of the wall surfaces is selected such that the colors of adjacent wall surfaces are separated from each other by a second distance larger than the first distance in the color space. Item 35. The position detection device according to Item 34. 36. The position detecting device according to claim 33, wherein each of said wall surfaces emits light of the corresponding color toward said area. 37. A position detecting device for detecting a position of a moving body moving in a predetermined area in the area, wherein a plurality of different colors provided on the moving body and provided along the periphery of the area. Imaging means for imaging the corresponding predetermined wall surface among the wall surfaces, and the color of the wall surface imaged by the imaging means and A color and relative position detecting means for detecting a relative position of the moving body, a detection result of the color and relative position detecting means, a color of all the wall surfaces stored in advance, and a position of all the wall surfaces, And a position detecting means for detecting a position of the moving body in the area based on the map information of the area. 38. A color separated by a predetermined first distance from each other in a predetermined color space as the color of each of the wall surfaces, and the color and relative position detection means are supplied from the imaging means. After converting the first image information into second image information corresponding to the corresponding color space, detecting a color of the wall surface imaged by the imaging unit based on the second image information. The position detecting device according to claim 37, wherein 39. Each of the wall surfaces is colored so that the degree of saturation of the color changes in the longitudinal direction of the wall surface, and the color and relative position detecting means is provided in an image based on the first image information. The distance from one end of the wall of the moving body in a direction parallel to the wall as the relative position of the moving body with respect to the wall based on the saturation of the color of the wall. Item 38. The position detection device according to Item 37. 40. An oblique line is drawn on each of the wall surfaces from one end to the other end in the longitudinal direction of the wall surface, and the color and relative position detecting means is provided in an image based on the first image signal. Based on the ratio of the length of the portion above or below the oblique line of the wall to the height of the wall, as the relative position of the mobile with respect to the wall, the moving body in a direction parallel to the wall The position detecting device according to claim 37, wherein a distance from one end of the wall surface is detected. 41. Each of said wall surfaces is bounded by an oblique line or an imaginary line from one end to the other end in the longitudinal direction of said wall surface.
The upper part and the lower part of the oblique line or the imaginary line are colored with the same hue and the different colors with the same hue, respectively, and the color and relative position detection unit detects the wall surface in the image based on the first image signal. Based on the ratio of the length of the upper portion or the lower portion of the oblique line or the imaginary line of the wall with respect to the height, as the relative position of the moving body with respect to the wall, the direction in a direction parallel to the wall. The position detecting device according to claim 37, wherein a distance from one end of the wall surface of the moving body is detected. 42. A position detecting method for detecting a position of a moving body moving in a predetermined area in the area, comprising: a first step of providing a plurality of wall surfaces of different colors along the periphery of the area. Capturing an image of the wall surface by an imaging unit disposed on the moving body, and detecting a color of the wall surface captured by the imaging unit and a relative position with respect to the wall surface based on the obtained first image information; A second step, a color of the wall surface detected in the second step and a relative position with respect to the wall surface, and an area including a color of each of the wall surfaces and a position of each of the wall surfaces stored in advance. A third step of detecting the position of the moving body in the area based on the map information. 43. Colors separated from each other by a predetermined first distance in a predetermined color space are selected as the colors of the wall surfaces, and in the second step, the colors supplied from the image pickup means are selected. The second image information corresponding to the color space corresponding to the second
43. The position detecting method according to claim 42, wherein after converting the image information into the image information, the color of the wall surface imaged by the imaging unit is detected based on the second image information. 44. The color of each of said wall surfaces is selected such that said color of adjacent said wall surfaces is separated by a second distance greater than said first distance in said color space. The position detection method according to 1. 45. Each of the wall surfaces is colored so that the degree of saturation of the color changes in the longitudinal direction of the wall surface. In the second step, the wall surface in an image based on the first image information is provided. Based on the saturation of the above color,
43. A distance between one end of the wall and the moving body in a direction parallel to the wall as the relative position of the moving body with respect to the wall.
The position detection method according to 1. 46. A diagonal line is drawn on each of the wall surfaces from one end to the other end in the longitudinal direction of the wall surface, and in the second step, in the image based on the first image signal, Based on the ratio of the length of the upper or lower part of the wall above the oblique line to the height of the wall,
43. The position detecting method according to claim 42, wherein a distance from one end of the wall of the moving body in a direction parallel to the wall is detected as the relative position of the moving body with respect to the wall. 47. Each of said wall surfaces is bounded by an oblique line or an imaginary line extending from one end to the other end in the longitudinal direction of said wall surface.
The upper part and the lower part of the oblique line or the imaginary line are colored with the same hue and different colors, respectively. In the second step, the height of the wall surface in the image based on the first image signal is adjusted. Based on the ratio of the length of the upper portion or the lower portion of the wall relative to the oblique line or the imaginary line, as the relative position of the moving body with respect to the wall surface, the moving body in a direction parallel to the wall surface 43. The position detecting method according to claim 42, wherein a distance from one end of the wall surface is detected. 48. The position detecting method according to claim 42, wherein each of said wall surfaces emits the corresponding color toward said region. 49. A robot apparatus movable in a predetermined area, comprising: imaging means for imaging the corresponding predetermined wall surface among a plurality of wall surfaces of different colors provided along the periphery of the area; A color and relative position detector for detecting a color of the wall surface captured by the imager and a relative position to the wall based on first image information output from the imager; Detecting the position of the moving body in the area based on each detection result of the means and map information of the area including the colors of all the walls and the positions of all the walls stored in advance. A robot device comprising: a position detecting means. 50. A color separated by a predetermined first distance from each other in a predetermined color space as the color of each of the wall surfaces, and the color and relative position detection means are supplied from the imaging means. After converting the first image information into second image information corresponding to the corresponding color space, detecting a color of the wall surface imaged by the imaging unit based on the second image information. 50. The robot apparatus according to claim 49, wherein 51. A color separated by a predetermined first distance from each other in a predetermined color space as the color of each of the wall surfaces, and the color and relative position detection means are supplied from the imaging means. After converting the first image information into second image information corresponding to the corresponding color space, detecting a color of the wall surface imaged by the imaging unit based on the second image information. 50. The robot apparatus according to claim 49, wherein 52. Each of said wall surfaces is colored so that the degree of saturation of said color changes in the longitudinal direction of said wall surface, and said color and relative position detecting means is provided in an image based on said first image information. The distance from one end of the wall of the moving body in a direction parallel to the wall as the relative position of the moving body with respect to the wall based on the saturation of the color of the wall. 50. The robot apparatus according to item 49. 53. A diagonal line is drawn on each of the wall surfaces from one end to the other end in the longitudinal direction of the wall surface, and the color and relative position detecting means is provided in an image based on the first image signal. Based on the ratio of the length of the portion above or below the oblique line of the wall to the height of the wall, as the relative position of the mobile with respect to the wall, the moving body in a direction parallel to the wall 50. The robot apparatus according to claim 49, wherein a distance from one end of the wall surface is detected. 54. Each of said wall surfaces is bounded by an oblique line or an imaginary line extending from one end to the other end in the longitudinal direction of said wall surface.
The upper part and the lower part of the oblique line or the imaginary line are colored with the same hue and the different colors with the same hue, respectively, and the color and relative position detection unit detects the wall surface in the image based on the first image signal. Based on the ratio of the length of the upper portion or the lower portion of the oblique line or the imaginary line of the wall with respect to the height, as the relative position of the moving body with respect to the wall, the direction in a direction parallel to the wall. 50. The robot apparatus according to claim 49, wherein a distance from one end of the wall surface of the moving body is detected. 55. A separating means for separating a supplied image signal into a luminance signal and a color difference signal, and a luminance level and a color difference for each pixel in an image based on the image signal based on the luminance signal and the color difference signal. Level detecting means for sequentially detecting a level; the luminance level and the color difference level of the pixel detected by the level detecting means; and an upper limit value and a lower limit value of the color difference level for each of the luminance levels stored in advance. And a determination means for determining whether or not each of the pixels has a predetermined color based on the above.