JP2001001284A - Robot control device using information on field of view of operator - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a robot control device using the information on the visual field of an operator operable with reference to the operator irrespective of the skill of the operator of a robot. SOLUTION: This robot control device comprises a monitoring part A having a CCD camera 2 which can calculate the control quantity of a robot R based on the information on the visual field of an operator OP to operate the robot R and acquire the visual field of the operator OP as an image, a recognition part B which treats the image from the monitoring part A, calculates the positional information on the index provided to the robot R, and outputs it as the characteristic quantity, and a control part C to drive an actuator by the control quantity of the actuator of the robot R calculated with reference to the characteristic quantity from the recognition part B.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a robot control device using visual field information of an operator, capable of generating motion information as information for operating the robot from a visual field image of the robot operator. is there.

[0002]

2. Description of the Related Art Today, various robots including industrial robots are widely used in various fields. For example, the robot there is operated by an operation box called a teaching pendant.

[0003]

The manual operation of the robot using the conventional teaching pendant must be performed by operating a button whose moving direction is determined for each coordinate axis fixed to the base or hand of the robot. Therefore, when the operator manually operates the robot while moving around the robot, the button operation is performed while being conscious of the coordinates fixed to the base and the tool of the robot, which requires skill.

Here, the main objects to be solved by the present invention are as follows.

[0005] A first object of the present invention is to provide a robot control device using operator's visual field information, which does not require skill in operation of the robot.

A second object of the present invention is to provide a robot control device using the visual field information of an operator which can easily operate the robot without requiring special knowledge and premise for operation of the robot. It is.

[0007] A third object of the present invention is to provide a robot control device using the visual field information of an operator, which enables robot control based on the operator.

[0008] Other objects of the present invention will become apparent from the description and drawings, and particularly from the description of each claim in the appended claims.

[0009]

In order to solve the above-described problems, the present invention provides a monitoring unit for acquiring a visual field of an operator who operates a robot as an image, and processing the image from the monitoring unit to reduce a feature amount. The control unit calculates the control amount of the actuator of the robot based on the output recognition unit and the feature amount from the recognition unit and an internal variable that defines the operation of the robot, and drives the actuator based on the calculated control amount. And a control unit.

More specifically, in order to solve the above-mentioned problems, the present invention achieves the above object by adopting new characteristic constitution means ranging from a superordinate concept to a subordinate concept listed below. Made for

A first feature of the apparatus of the present invention is a robot control device for controlling a robot based on the field of view of an operator, wherein the monitoring unit acquires an image of the visual field of the operator, and the monitoring unit A recognition unit that processes the obtained image and outputs a feature amount that determines a control amount of the actuator of the robot; and a control amount of the actuator that is calculated from the feature amount by the recognition unit, and the actuator that is calculated based on the calculated control amount. And a control section for driving the robot.

A second feature of the apparatus of the present invention resides in that the monitoring unit in the first feature of the above-described apparatus of the present invention further comprises: a CCD camera disposed in front of the operator's eyeball;
And a display installed in front of the eyeball so as to be able to display the image by a CD camera.

A third feature of the apparatus of the present invention resides in that the control unit in the first or second feature of the above-described apparatus of the present invention is characterized in that the control unit outputs the feature amount output by the recognition unit and the relative amount of the robot to the operator. Another object of the present invention is to adopt a configuration of a robot controller using visual field information of an operator, which is a means capable of calculating the control amount for the actuator from an operation parameter defining a motion.

A fourth feature of the present invention is that the control amount in the third feature of the present invention is such that the control amount of the robot desired by the operator depends on the relationship between the characteristic amount and the operation parameter. An object of the present invention is to adopt a configuration of a robot control device using the visual field information of the operator, which is a predetermined amount of movement.

A fifth feature of the device of the present invention is that the recognition unit in the first, second, third or fourth feature of the device of the present invention is searched with reference to the image from the monitoring unit, Another object of the present invention is to adopt a configuration of a robot control device using field-of-view information of an operator that has a reference image for calculating position information of an index provided in the robot as a feature amount in advance.

According to a sixth feature of the present invention, in the fifth feature of the present invention, the recognizing unit performs a color correlation operation between the image from the monitoring unit and the reference image, and The present invention resides in adopting a configuration of a robot control device using visual field information of an operator, which is a means for calculating a position having a maximum correlation in each of them as a feature amount for the reference image.

[0017]

BRIEF DESCRIPTION OF THE DRAWINGS FIG.
Embodiments of the present invention will be described with reference to an example of an apparatus.

(Example of Apparatus) FIG. 1 is a diagram for explaining a robot control apparatus β using information on the visual field of an operator. The figure also shows an example of a specific implementation.

The robot controller β using the visual field information of the operator comprises: a monitoring unit A for monitoring an image of the visual field of the operator OP; a recognition unit B for calculating a characteristic amount from the video obtained from the monitoring unit A; The control section C is configured to calculate the control amount of the actuator based on the calculated feature amount by the section B and the robot internal variables that define the operation of the robot and to drive the actuator.

Here, the recognition unit B and the control unit C use, for example, a commercially available computer using Windows as an OS, and provide an image processing boat in the computer to provide an environment in which the image processing of the recognition unit B can be performed at high speed. Configuration.

For a specific description, as a specific example, the robot R has two wheels R1 and R2, each of the wheels R1 and R2 has an independent motor as an actuator, and has a rotational speed. It is assumed that a pulse encoder to be detected is completed, and each motor of the robot R has a servo loop of a motor rotation speed that uses a value from the pulse encoder as feedback. Then, the rotation axis speed of the motor is received as a command value from the control unit C outside the robot R via serial communication, and the number of rotations of each motor is controlled to be the command value.

Next, the components of the robot controller β using the visual field information of the operator will be described in detail. When the operator OP wears the immersive head-mounted display 1, the monitoring unit A moves the CCD camera 2 to the position of the eyeball.
Are provided, and the image obtained by the CCD camera 2 (the image D displayed on the head mounted display 1 in FIG. 1) is presented to the immersive head mounted display 1 while the image obtained by the CCD camera 2 is branched. And NTSC
The signal is converted to a signal and transmitted to the recognition unit B. Note that the camera coordinate system 3 in FIG. 1 is not actually imaged.

The recognizing unit B performs a color correlation operation between the image (CCD camera image) from the monitoring unit A and a plurality of reference images registered in advance, and determines the position of the maximum correlation in the CCD camera image. Is calculated as a feature amount for the reference image.

[0024]

[Outside 1]

[0025]

[Table 1]

[0026]

[Outside 2]

For the action determined by Table 1, Table 2
Calculates the rotation speed of the motor shaft provided for each of the wheels R1 and R2 as a command value.
Send to Vd in Table 2 is a command value related to the rotation axis speed of the motor of each axis.

[0028]

[Table 2]

Thus, the robot R receiving the command value
Is controlled so that the rotation speed of each motor becomes a command value. The relationship between the angle θ and the behavior in Table 1 (the behavior rule of the robot R) and the relationship between the behavior and the command value of the motor in Table 2 depend on the relative position and orientation of the robot R and the operator OP. This is determined depending on whether or not a movement is made, and is appropriately determined according to the control content of the robot R.

The control parameters of the robot R to be controlled (corresponding to the command value of each motor in the above)
The number of vectors serving as a reference for the relative position of the marker M is determined by the type and the number thereof.

Although the embodiment of the present invention has been described above, the present invention is not necessarily limited to the above-mentioned matter, and can be appropriately modified and implemented within the scope of achieving the object of the present invention and having the following effects. is there.

[0032]

According to the present invention, the operator OP looks at the marker M provided on the robot through the head mounted display 1, and the operator OP at an arbitrary position is determined by the operation parameters and the marker / motor arrangement. A certain relative movement can be made to the robot. Therefore, the robot operation can be performed mainly on the operator OP, which has not been conventionally performed, and it is possible to improve the work efficiency, and it is possible to easily perform the robot operation without skill.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram of a robot control device using visual field information of an operator according to an embodiment of the present invention.

[Explanation of symbols]

β: Robot controller using operator's visual field information 1… Immersive head mounted display 2… CCD camera 3… Camera coordinate system A… Monitoring unit B… Recognition unit C… Control unit D… Displayed on the immersive head mounted display M… Marker OP… Operator R… Robot R1, R2… Wheel

Claims (6)

[Claims] 1. A robot controller for controlling a robot based on an operator's field of view, comprising: a monitoring unit for acquiring an image of the operator's field of view; and a processor for processing the image acquired by the monitoring unit. A recognition unit that outputs a characteristic amount that determines a control amount of the actuator of the robot; and a control unit that calculates a control amount of the actuator from the characteristic amount by the recognition unit and drives the actuator with the calculated control amount. A robot controller using visual field information of an operator. 2. The monitoring unit according to claim 1, further comprising: a CCD camera arranged in front of the eyeball of the operator; and a display installed in front of the eyeball so as to display the image by the CCD camera. The robot control device using the visual field information of the operator according to claim 1. 3. The control unit, wherein the control unit can calculate the control amount for the actuator from the feature amount output by the recognition unit and an operation parameter that defines a relative motion of the robot with respect to the operator. The robot control device using the visual field information of the operator according to claim 1 or 2, wherein: 4. The method according to claim 1, wherein the control amount is a predetermined amount of motion of the robot desired by the operator according to a relationship between the feature amount and the operation parameter. 4. A robot control device using the visual field information of the operator according to 3. 5. The recognizing unit retrieves a reference image for retrieving based on the image from the monitoring unit and calculating position information of an index included in the robot as a feature amount in advance. The robot control device using the visual field information of the operator according to claim 1, 2, 3, or 4. 6. The recognition unit performs a color correlation operation between the image from the monitoring unit and the reference image, and calculates a position having a maximum correlation in the image as a feature amount for the reference image. The robot control apparatus using the visual field information of the operator according to claim 5, wherein the robot control means is means.