INSTALLATION SITE OF A ROBOT MANIPULATOR

Abstract

A method of determining an installation site of a robot manipulator at a workstation, the method including: recording a respective image of the robot manipulator and of the workstation of the robot manipulator, and of a workpiece to be machined at the workstation via a camera unit, wherein the respective image contains spatial information; transmitting the respective image to a computing unit; and determining the installation site of the robot manipulator by applying a non-linear optimization of a predefined cost function and/or of a neural network via the computing unit based on a predefined task for machining the workpiece and based on the spatial information determined by the computing unit from the respective image.

Claims

1. A method of determining an installation site of a robot manipulator at a workstation, the method comprising: recording a respective image of the robot manipulator and of the workstation of the robot manipulator, and of a workpiece to be machined at the workstation via a camera unit, wherein the respective image contains spatial information; transmitting the respective image to a computing unit; and determining the installation site of the robot manipulator by applying a non-linear optimization of a predefined cost function and/or a neural network via the computing unit based on a predefined task for machining the workpiece and based on the spatial information determined by the computing unit from the respective image.

2. The method of claim 1, the method further comprising: outputting information about the installation site as determined, as a suggestion for a user at an output unit; and detecting an input by the user at an input unit, wherein the input includes a correction of the suggestion or a confirmation of the suggestion.

3. The method of claim 1, wherein the cost function of the non-linear optimization is dependent on a type of regulation implemented in a regulator of the robot manipulator and/or a type of generation of a movement command in the regulator and/or parameters of the predefined task, and/or wherein an input variable of the neural network is the type of regulation implemented in the regulator of the robot manipulator and/or the type of generation of the movement command in the regulator and/or parameters of the predefined task.

4. The method of claim 1, wherein images of the robot manipulator and of the workstation are contained in a common photograph.

5. The method of claim 1, the method further comprising, in addition to the installation site, determining an installation orientation of the robot manipulator via the computing unit by determining at least one angle of inclination.

6. The method of claim 1, wherein the installation site of the robot manipulator is determined by geometric modeling of objects at the workstation and/or of the robot manipulator and/or of the workstation in respective geometric bodies.

7. The method of claim 1, wherein the installation site of the robot manipulator is determined based on a simulation with modeled effects of technical mechanics, such that mechanical interactions between the robot manipulator and objects from a vicinity of the robot manipulator are taken into account.

8. The method of claim 2, wherein the robot manipulator comprises two robot arms and the suggestion for the installation site is determined by maximizing a common work space with respect to a respective end effector of a respective robot arm.

9. The method of claim 1, wherein the cost function is a quality function to be maximized, the quality function being determined based on a respective degree of manipulability determined for a large number of poses of the robot manipulator, wherein the respective degree of manipulability is determined based on a Jacobian matrix valid for a respective pose.

10. A system to determine an installation site of a robot manipulator at a workstation, the system comprising: a camera unit configured to record a respective image of the robot manipulator and of the workstation of the robot manipulator and of a workpiece to be machined at the workstation, wherein the respective image contains spatial information, and wherein the camera unit is configured to transmit the respective image; and a computing unit configured to receive the respective image transmitted from the camera unit and further configured to determine the installation site of the robot manipulator via application of a non-linear optimization of a predefined cost function and/or a neural network based a predefined task for machining the workpiece and based on the spatial information determined by the computing unit from the respective image.

11. The system of claim 10, wherein the computing unit is further configured to: output information about the installation site as determined, as a suggestion for a user at an output unit; and detect an input by the user at an input unit, wherein the input includes a correction of the suggestion or a confirmation of the suggestion.

12. The system of claim 10, wherein the cost function of the non-linear optimization is dependent on a type of regulation implemented in a regulator of the robot manipulator and/or a type of generation of a movement command in the regulator and/or parameters of the predefined task, and/or wherein an input variable of the neural network is the type of regulation implemented in the regulator of the robot manipulator and/or the type of generation of the movement command in the regulator and/or parameters of the predefined task.

13. The system of claim 10, wherein images of the robot manipulator and of the workstation are contained in a common photograph.

14. The system of claim 10, wherein the computing unit is further configured to, in addition to the installation site, determine an installation orientation of the robot manipulator by determining at least one angle of inclination.

15. The system of claim 10, wherein the installation site of the robot manipulator is determined by geometric modeling of objects at the workstation and/or of the robot manipulator and/or of the workstation in respective geometric bodies.

16. The system of claim 10, wherein the installation site of the robot manipulator is determined based on a simulation with modeled effects of technical mechanics, such that mechanical interactions between the robot manipulator and objects from a vicinity of the robot manipulator are taken into account.

17. The system of claim 11, wherein the robot manipulator comprises two robot arms and the suggestion for the installation site is determined by maximizing a common work space with respect to a respective end effector of a respective robot arm.

18. The system of claim 10, wherein the cost function is a quality function to be maximized, the quality function being determined based on a respective degree of manipulability determined for a large number of poses of the robot manipulator, wherein the respective degree of manipulability is determined based on a Jacobian matrix valid for a respective pose.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In the drawings:

[0040] FIG. 1 shows a method for determining an installation site of a robot manipulator according to an example embodiment of the invention; and

[0041] FIG. 2 shows a corresponding system for determining the installation site of the robot manipulator according to an example embodiment of the invention.

[0042] The illustrations in the figures are schematic and not to scale.

DETAILED DESCRIPTION

[0043] FIG. 1 shows a method for determining an installation site of a robot manipulator 1 at a workstation 3, wherein the method includes: [0044] recording S1 a respective image of the robot manipulator 1 and of the workstation 3 of the robot manipulator 1 and of a workpiece 5 to be machined at the workstation 3 via a camera unit 7, wherein the respective image contains spatial information; [0045] transmitting S2 the respective image to a computing unit 9; [0046] determining S3 the installation site of the robot manipulator 1 by applying a non-linear optimization of a predefined cost function and/or a neural network via the computing unit 9 based on a predefined task for machining the workpiece 5 and based on the spatial information determined by the computing unit 9 from the respective image; [0047] outputting S4 information about the determined installation site as a suggestion for a user at an output unit 9; and [0048] detecting S5 an input by the user at an input unit 11, the input including a correction of the suggestion or a confirmation of the suggestion.

[0049] This method is carried out on a system 100 for determining the installation site of the robot manipulator 1. The reference symbols and terms mentioned above therefore also relate to the description of FIG. 2, which can also be used here. Further details of the method following this example embodiment are therefore explained in more detail under the description of FIG. 2.

[0050] FIG. 2 shows a system 100 for determining an installation site of a robot manipulator 1 at a workstation 3. The system 100 includes a camera unit 7 and a computing unit 9. The camera unit 9 has a plurality of lens systems and is part of the user's cell phone. The camera unit 9 is capable of capturing multiple images from multiple starting points by using the different lenses and therefore includes spatial information in the image data. The camera unit 9 is also used to record an image of robot manipulator 1 at its initial position at workstation 3. The camera unit 9 is also used to record another image of a workpiece 5 to be machined. These images from camera unit 7 are sent to the computing unit 9 of the robot manipulator 1. The computing unit 9 determines the installation site of the robot manipulator 1 by applying a non-linear optimization of a predefined cost function based on a predefined task for machining the workpiece 5 and based on spatial information determined by the computing unit 9 from the respective image. The cost function is composed of the sum of the squares of the energy required and of the time required for the robot manipulator 1. The energy and time required for the respective execution of the task for the respective installation site is determined by a simulation in which the task is performed virtually for each assumed installation site of the robot manipulator. The various installation sites are selected and evaluated quasi-randomly with the help of an evolution algorithm. In this case, predefined regulator types are evaluated by the computing unit 9. This variation flows directly into the determination of the respective value for the cost function with regard to the respective installation site.

[0051] Although the invention has been further illustrated and described in detail using preferred example embodiments, the invention is not limited by the disclosed examples, and other variations can be derived therefrom by a person skilled in the art without departing from the scope of protection of the invention. It is therefore clear that several possible variations exist. It is also clear that example embodiments are really only examples, which are not to be construed in any way as limiting the scope, applicability, or configuration of the invention. Rather, the foregoing description and description of the figures enable a person skilled in the art to implement the example embodiments, and such person may make various changes based on the knowledge of the disclosed inventive concept, for example with respect to the function or arrangement of individual elements cited in an example embodiment, without departing from the scope as defined by the claims and their legal equivalents, such as a more extensive explanation in the description.

LIST OF REFERENCE NUMERALS

[0052] 1 robot manipulator [0053] 3 workstation [0054] 5 workpiece [0055] 7 camera unit [0056] 9 computing unit [0057] 11 input unit [0058] 13 output unit [0059] 100 system [0060] S1 recording [0061] S2 transmitting [0062] S3 determining [0063] S4 outputting [0064] S5 detecting