DE102020206924A1 - Carrying out an application with the aid of at least one robot - Google Patents

Abstract

A method according to the invention for performing an application with the aid of at least one robot (1) comprises the repeatedly repeated steps: determining (S100) a stochastic value of at least one robot parameter and / or at least one environmental model parameter, in particular on the basis of a predetermined stochastic parameter model and / or with the aid of at least one Random generator (3a); and performing (S200) an, in particular multi-stage, simulation of the application on the basis of the determined stochastic value; the steps: training (S200, S500) at least one control agent and / or at least one classification agent using the simulations using machine learning, in particular training a first control agent and / or first classification agent using first stages of the simulations, and at least one further control agent and / or further classification agent with the aid of further stages of the simulations; and performing (S600) the application with the aid of the robot; and at least one of the steps: configuring (S400) a controller of the robot, with which the application is carried out in whole or in part, on the basis of the, in particular the, trained control agent; and / or classification (S700) of the application with the aid of the, in particular the, trained classification agent.

Description

The present invention relates in particular to a method for performing an application using at least one robot, a method for configuring a controller of a robot for performing an application or a predetermined task, a method for training at least one classification agent for classifying a robot application, a method for Carrying out a predetermined task with the aid of at least one robot with an appropriately configured controller and a system and a computer program product for carrying out at least one of these methods.

In order to carry out applications or specified tasks, controls of robots have to be configured accordingly, conventionally by manually creating robot programs or the like.

One object of an embodiment of the present invention is to improve the implementation of an application or a given task with the aid of at least one robot. One object of an embodiment of the present invention is to improve the configuration of a controller of the robot for carrying out the application or the specified task. One object of an embodiment of the present invention is to improve a classification of a robot application. An object of an embodiment of the present invention is to improve a control of a robot with which an application is carried out.

One or more of these objects, the subjects of the independent claims and / or one or more of the methods or means described here, in particular a method with the features of claims 1, 9, 10 and 11, respectively, are achieved. Claims 14, 15 provide a system or computer program product for carrying out a method described here under protection. The subclaims relate to advantageous developments.

• - Konfigurieren einer Steuerung eines Roboters zum Durchführen einer Applikation mithilfe des Roboters (Roboterapplikation);
• - Trainieren wenigstens eines Klassifikations-(KI)Agenten zur Klassifikation einer Roboterapplikation; und/oder
• - Durchführen einer bzw. der (Roboter)Applikation mithilfe wenigstens eines bzw. des Roboters

die mehrfach, in einer Ausführung zyklisch, wiederholten Schritte auf:

• - Ermitteln eines ein- oder mehrdimensionalen stochastischen Wertes wenigstens eines ein- oder mehrdimensionalen Roboterparameters und/oder wenigstens eines ein- oder mehrdimensionalen Umweltmodelparameters, in einer Ausführung auf Basis eines vorgegebenen stochastischen Parametermodells und/oder mithilfe wenigstens eines Zufallsgenerators; und
• - Durchführen einer, in einer Ausführung mehrstufigen, Simulation der Applikation auf Basis des ermittelten stochastischen Wertes.

According to one embodiment of the present invention, a method for

• - Configuring a controller of a robot for performing an application with the aid of the robot (robot application);
• - Training at least one classification (KI) agent to classify a robot application; and or
• - Carrying out one or the (robot) application with the aid of at least one or the robot

the steps repeated several times, cyclically in one execution:

• - Determination of a one-dimensional or multi-dimensional stochastic value of at least one one-dimensional or multi-dimensional robot parameter and / or at least one one-dimensional or multi-dimensional environmental model parameter, in one embodiment on the basis of a predetermined stochastic parameter model and / or with the aid of at least one random generator; and
• - Carrying out a multi-stage simulation of the application on the basis of the determined stochastic value.

The stochastic value for a simulation can be determined before the simulation is carried out and then used in it. Likewise, several stochastic values of the robot and / or the environmental model parameter can also be determined in advance and then one of these stochastic values can be used for or in one of the simulations.

• - Trainieren
  • - wenigstens eines Steuerungs-(KI-)Agenten und/oder
  • - wenigstens eines Klassifikations-(KI)Agenten mithilfe der Simulationen mittels maschinellen Lernens, in einer Ausführung
  • - Trainieren eines ersten Steuerungs-(KI-)Agenten und/oder eines ersten Klassifikations-(KI-)Agenten mithilfe erster Stufen der Simulationen, und
  • - Trainieren wenigstens eines weiteren Steuerungs-(KI-)Agenten und/oder wenigstens eines weiteren Klassifikations-(KI-)Agenten mithilfe weiterer Stufen der Simulationen.

According to one embodiment of the present invention, the method comprises the step:

• - Work out
  • - At least one control (AI) agent and / or
  • - At least one classification (AI) agent using the simulations using machine learning, in one embodiment
  • - Training a first control (KI) agent and / or a first classification (KI) agent using first stages of the simulations, and
  • - Training at least one further control (KI) agent and / or at least one further classification (KI) agent with the aid of further stages of the simulations.

• - ein- oder mehrfaches Durchführen der (realen) Applikation mithilfe des Roboters.

According to one embodiment of the present invention, the method comprises the step:

• - Single or multiple implementation of the (real) application using the robot.

Several control (AI) agents can also use several S (simulation) levels and only one classification (AI) agent using the simulations or several classification (AI) agents using several S (simulation) levels and only a control (AI) agent can be trained using the simulations.

In one embodiment, the robot or environmental model parameter (value) is thus randomized or the simulations are carried out with randomized robot or environmental model parameters (values) and the agent or agents are trained or machine-learned with the aid of these simulations.

As a result, machine learning can be improved in one implementation and more robust and / or faster in one implementation. Additionally or alternatively, an agent trained in this way or on the basis of randomized robot or environmental model parameters (values) can thereby improve the implementation of the (real) application with the aid of the robot, in particular the control of the robot and / or classification of the application, in particular act robustly and / or flexibly.

When an agent is spoken of in the present case, this includes in particular an artificial intelligence agent, in particular a control (AI) agent or a classification (AI) agent.

In one embodiment, determining a stochastic value includes generating the value, in particular numerically and / or physically, and can in particular be generating the value.

The stochastic values on the basis of which the simulations are carried out are, in particular, are determined, in particular generated, in one embodiment with the aid of at least one random generator, in particular pseudo-random number generator, and / or are stochastically or randomly distributed values, in one embodiment random numbers, in particular Pseudo-random numbers, which in one embodiment are determined by the specified stochastic parameter model or which satisfy this model.

In one embodiment, the stochastic parameter model has one or more stochastic parameters, in particular minimum, maximum, expected and / or mean value (s), variance (s), standard deviation (s), measure (s) of dispersion or the like , and / or a probability distribution, for example a Gaussian or normal distribution, a uniform distribution or the like.

For example, a user and / or a user input support or a software assistant can specify a minimum and maximum value for a robot or environmental model parameter as well as a uniform distribution and thus a stochastic parameter model, with the help of a (pseudo) random number generator stochastic (distributed values generated and determined in this way on the basis of this specified stochastic parameter model and with the aid of this (pseudo) random number generator. Likewise, the user and / or the user input support can, for example, specify a specific Gaussian distribution and thus another stochastic parameter model, whereby then with the help of a (pseudo) random number generator again corresponding stochastically (distributed values are generated and in this way on the basis of this other predetermined stochastic parameter model and with the help of this (pseudo) random number generator rs can be determined.

Thus, in one embodiment, the determined stochastic values are (also) determined by the specified stochastic parameter model, for example limited by minimum and / or maximum values, scattered by variance (s) around an expected or mean value or the like.

A simulation is understood to mean, in particular, a simulation run or a numerical simulation of the application or its course over time.

In one embodiment, a multi-stage simulation comprises two or more successive time and / or functional segments or stages of the application that are contiguous in one embodiment, for example the robot-assisted joining of a first gearwheel (first stage) and the subsequent robot-assisted joining of a further gearwheel (further stage) or the like.

In one embodiment, a first control agent using first stages or sections of the simulations and at least one further control agent using further stages or sections of the simulations and / or a first classification agent using the same or different first stages or sections of the Simulations and at least one further classification agent trained using further stages or sections of the simulations, in the above example a first (control or classification) agent for joining the first gear using the first simulation stages or simulations of joining the first gear and a further (control or classification) agent for joining the further gear with the aid of the further simulation stages or simulations of the joining of the further gear.

In one embodiment, an initial state for a later simulation stage is determined or specified on the basis of a final state or result of a previous simulation stage, wherein in one embodiment this initial state also varies, in particular randomized, in particular on the basis of a user input or specification, will or can be. In the above example, for example, a pose of the first gearwheel after its simulated joining can be used as a start value in the further simulation stage and, if necessary, changed and / or randomized by a user.

In this way, a multi-stage application can be carried out particularly advantageously in one embodiment.

• - Konfigurieren einer Steuerung des Roboters zum Durchführen der Applikation, insbesondere einer Steuerung des Roboters, mit der die Applikation durchgeführt wird, auf Basis des bzw. eines oder mehrerer der trainierten Steuerungs-Agenten.

According to one embodiment of the present invention, the method comprises the step:

• - Configuring a controller of the robot to carry out the application, in particular a controller of the robot with which the application is carried out, on the basis of the or one or more of the trained control agents.

Thus, according to one aspect of the present invention, the simulations with stochastic or randomized values are used to machine control of the robot for performing the (real) application with the aid of the robot or to train one or more agents for this purpose.

As a result, in one embodiment, the implementation of the (real) application can be improved with the aid of the robot, in particular the application can be implemented robustly and / or flexibly.

In one embodiment, a control of the robot, with which only part of the application is or is to be carried out, is configured on the basis of the, in particular the, trained control agent.

In particular, the application can have one or more sections that are (should) be carried out with a (different) controller of the robot that is not or is not configured on the basis of the trained control agent (s), as well as one or more sections, which are (should) be carried out with a controller of the robot, which is or is configured on the basis of the trained control agent (s). A controller within the meaning of the present invention can in particular have, in particular be, a control device and / or a computer program, in particular (computer) program module or part.

In particular, it can be useful to configure a (different) control using geometric or dynamic path planning, teaching or the like for transfer sections in which the robot moves a load freely, and for contact, in particular gripping and / or joining sections, in where there is or is environmental contact of the robot, in particular the robot grips or adds a load, to configure a controller based on the trained agent (s).

• - Klassifikation der Applikation mithilfe des bzw. eines oder mehrerer der trainierten Klassifikations-Agenten.

In addition or as an alternative to this aspect, the method according to an embodiment of the present invention has the step:

• - Classification of the application with the aid of the or one or more of the trained classification agents.

Thus, according to one aspect of the present invention, the simulations with stochastic or randomized values are used to learn a classification of the (real) application by machine or to train one or more classification agents for this purpose.

As a result, in one embodiment, the implementation of the (real) application can be improved with the aid of the robot, in particular the application can be monitored robustly and / or flexibly.

In one embodiment, the or one or more of the classification agent (s) has / have machine-learned anomaly detection. Additionally or alternatively, in one embodiment the or one or more of the classification agent (s) has / have machine-learned error detection.

In one embodiment, an anomaly detection comprises a classification of the application (s) carried out into normal (s) and abnormal (s) applications. In one embodiment, the anomaly detection is or is machine learned, in particular only, on the basis of simulated applications labeled as normal and / or the anomaly detection classifies an application as abnormal if it deviates (too much) from the simulated applications labeled as normal.

If, for example, an obstacle not taken into account in the simulations blocks the implementation of the real application with the aid of the robot, the robot's force and / or posture data in particular deviate significantly from the progression in simulated applications labeled as normal, and the agent classifies this real application as abnormal .

In one version, error detection comprises a classification of the application (s) carried out into error-free (s) and faulty (s) applications, and in one version into different error classes. It is or will be learned automatically in an implementation based on simulated applications labeled as error-free and simulated applications labeled as faulty or corresponding to a corresponding error class and / or classifies an application into a (corresponding) error class if it matches the correspondingly labeled simulated applications sufficiently, in particular most strongly, resembles.

For example, in the above example, joining the first gear with the aid of the robot, in particular on the basis of force and / or posture data of the robot, can be classified as error-free, as attached, but not sufficiently deep and / or jammed, or as not joined, if the force or pose data are sufficiently similar to the courses of appropriately labeled simulated applications and the agent classifies this real application into the corresponding error class.

The invention can be used with particular advantage for such classifications of robot applications, since these can only be learned with difficulty by machine using (real) applications carried out with the robot.

In one embodiment, the or one or more of the control agent (s) and / or the or one or more of the classification agent (s) each have at least one artificial neural network; in one embodiment, the control of the Robot configured based on the structure and / or weightings of the trained network.

In this way, a particularly advantageous control can be implemented in one embodiment and / or this can be configured in a particularly advantageous manner.

In one embodiment, the or one or more of the control agent (s) and / or the or one or more of the classification agent (s) is trained with the aid of reinforcement learning, in particular deep reinforcement learning.

This is particularly suitable for configuring a controller for the robot and for classifying, in particular anomaly and / or error detection, of the application.

In one embodiment, the or one or more of the control agent (s) and / or the or one or more of the classification agent (s) are trained, in particular additionally, with the aid of the robot, in one embodiment based on one or more of the several (real) applications carried out with the help of the robot.

As a result, in one embodiment, the corresponding agent can be used particularly advantageously when performing the real application with the aid of the robot and / or machine learning can be (further) improved.

In one embodiment, the or one or more of the control agent (s) and / or the or one or more of the classification agent (s) is / are, based on at least one not measured when performing the application, in a Execution not measurable, state variable trained.

This is based, in particular, on the knowledge or idea that state variables can also be calculated in the simulations, in particular calculated, which are not measured when the application is carried out, and possibly cannot be measured with the existing environment or configuration, in particular measuring equipment , and that such state variables, which arise or are calculable anyway in simulations for (the purpose of) configuring (s) the control, in particular are calculated, can (also) be used particularly advantageously for training or machine learning.

In the above example, it can be the case that the distance between the (first or further) gear and a stop cannot be measured, for example because there is no corresponding sensor or the space between the gear and the stop is not accessible. In the case of a simulation of the joining, however, this distance can be calculated and then used as a state variable for training, in particular in a quality criterion.

In one embodiment, a quality criterion used when training the or one or more of the control agents and / or classification agents, in particular a quality or cost function, is based on at least one not measured when performing the application, in one embodiment with the existing configuration or environment not measurable, state variable determined or depends on this.

As a result, machine learning can be improved in one implementation and more robust and / or faster in one implementation.

In addition or as an alternative to the idea of using state variables for training the or one or more of the agents that are not measured when the application is carried out but are calculated in the simulations, an embodiment of the present invention is based on the knowledge or idea, Simulations that are (anyway) carried out or used to train at least one control agent, on the basis of which the control of the robot with which the (real) application is or should be carried out is configured, also to be used or used for this purpose. use to train one or more classification agents with whose help the (real) application that is carried out with the aid of the robot is or should be classified.

• - Konfigurieren einer Steuerung des Roboters zum Durchführen der Applikation, insbesondere einer Steuerung des Roboters, mit der die Applikation ganz oder teilweise durchgeführt wird, auf Basis des bzw. eines oder mehrerer der trainierten Steuerungs-Agenten;

als auch den Schritt:

• - Trainieren des bzw. eines oder mehrerer der Klassifikations-Agenten, insbesondere Klassifikation der Applikation mithilfe des bzw. eines oder mehrerer der trainierten Klassifikations-Agenten,

wobei in einer Ausführung Steuerungs- und Klassifikations-Agent(en) mithilfe derselben Simulationen trainiert werden bzw. (worden) sind, wobei in einer Weiterbildung der bzw. einer oder mehrere der Klassifikations-Agent(en) mithilfe bereits erfolgter Simulationen, mit deren Hilfe der bzw. einer oder mehrere der Steuerungs-Agent(en) zuvor trainiert worden sind, und/oder synchron mithilfe aktueller Simulationen trainiert werden, mit deren Hilfe der bzw. einer oder mehrere der Steuerungs-Agent(en) gerade trainiert werden.Accordingly, according to one embodiment of the present invention, the method comprises both the step:

• - Configuring a controller of the robot to carry out the application, in particular a controller of the robot with which the application is carried out in whole or in part, on the basis of the or one or more of the trained control agents;

as well as the step:

• - Training the or one or more of the classification agents, in particular classification of the application with the aid of the or one or more of the trained classification agents,

wherein in one embodiment control and classification agent (s) are or have been trained using the same simulations, wherein in a further development the or one or more of the classification agent (s) using simulations that have already been carried out with their help the or one or more of the control agent (s) have been trained beforehand and / or are trained synchronously with the aid of current simulations, with the aid of which the or one or more of the control agent (s) are currently being trained.

In other words, one embodiment of the invention uses simulations on the basis of which, in particular by means of reinforcement learning, the control is configured or with the aid of which the or one or more of the control agent (s) is or are trained, in one embodiment has been or are also used to train at least one machine-learned classification or the or one or more of the classification agents.

In one embodiment, for this purpose, data, in particular state variables, in one embodiment (temporal) state variable curves, in particular trajectories, of the application, in one embodiment of the robot that are or have been calculated in simulations, in one embodiment, simulations, with the help of which the or one or more of the control agent (s) are or have been trained, stored and the or one or more of the classification agent (s) trained with the aid of this stored data, in an execution following these simulations and / or during of these simulations.

In one embodiment, these data include poses of one or more robot-fixed references, in particular an end effector, TCPs, robot-guided tool or piece or the like, joint or axis positions of the robot, internal and / or external forces on the robot, in particular joint and / or Driving forces, frictional forces, contact forces or the like, current variables, in particular voltages and / or currents in the drives of the robot, tracking errors of the robot and / or temporal derivatives of such poses, positions, forces, current variables or tracking errors, in particular speeds and / or accelerations of a or several robot-fixed references, axes or joints, drives, changes in such forces over time, current variables or following errors or the like. Following errors can in particular include force, position and / or speed errors.

In one embodiment, the simulations that have already been carried out in one embodiment become those simulations with the aid of which the or one or more of the control agent (s) are or have been trained, in particular on the basis of the stored data or data is selected in which a quality criterion is met and used to train the anomaly detection, or those simulations or data are sorted into different defect classes on the basis of a quality criterion and used to train the defect detection.

If, for example, traj_i denotes the data of a simulation i, traj = {traj_i} the amount of all data stored during the simulation, in an implementation for machine learning of the anomaly detection, the data {traj_success} of those simulations in which a successful course is generated from this the application was simulated or resulted, or the data {traj_failure_k1}, {traj_failure_ k2}, ... of those simulations in which an error k1, k2, ... was simulated or resulted, selected and then the anomaly detection with the help of {traj_success} or the error detection with the help of {{traj_success}, {traj_failure_k1}, {traj_failure_k2}, ...} learned by machine.

As a result, the machine-learned classification can in each case be improved in one embodiment, in particular learned more quickly and / or classified more precisely, more robustly and / or more reliably.

In one embodiment, the or one or more of the agent (s), in particular the anomaly detection and / or the error detection, classifies the application on the basis of at least one time segment that moves in an execution, in particular moves with it. In one embodiment, in addition to or as an alternative to an evaluation of the complete application, a continuous and / or serial evaluation is carried out and the agent classifies the application on the basis of this continuous or serial evaluation. Particularly suitable this includes recurrent networks, Markov models or autoregressive networks.

As a result, machine learning can be improved in one implementation and more efficient and / or faster in one implementation.

In one embodiment, the or one or more of the agent (s), in particular the anomaly detection and / or the error detection, classifies the application while the application is being carried out.

In one embodiment, this enables a reaction to the result of the classification. Correspondingly, in one embodiment, the currently or currently executed application is changed if necessary on the basis of the classification; Application handled, in particular transported and / or processed, workpiece sorted out or reworked.

In one embodiment, the or one or more of the agent (s), in particular the anomaly detection and / or the error detection, classifies the application after the application has been carried out.

As a result, the application can be classified more precisely in one embodiment.

In one embodiment, the robot parameter has a one-dimensional or multidimensional start pose, one or more one-dimensional or multidimensional intermediate poses and / or a one-dimensional or multidimensional target pose of the application, in particular of the robot. Correspondingly, in one embodiment, the simulations of the application are carried out on the basis of stochastic (distributed or generated start, intermediate and / or target positions. As a result, inaccuracies as a result of previous processes, deviations during travel or the like can be taken into account in one embodiment, and thus machine learning or the trained agent (s) are improved, in particular robust (er) and / or flexible (er).

In one embodiment, especially before performing the simulation, it is checked whether (the stochastic value for) the start pose, intermediate pose (s) and / or target pose can be achieved with the robot, in particular on the basis of a kinematic model of the robot. If the pose or the corresponding stochastic value of the robot parameter cannot be reached, in one embodiment the value is determined again or until (it is determined that) the pose or the value can be reached with the robot, and then this value used as the determined value when performing the simulation of the application. As a result, machine learning can be improved in one implementation and more efficient and / or faster in one implementation.

A pose within the meaning of the present invention can in particular have, in particular be, a one, two or three-dimensional position and / or one, two or three-dimensional orientation.

Additionally or alternatively, in one embodiment the robot parameter has a one- or multi-dimensional force parameter of a robot-internal force, in particular at least one axis and / or at least one end effector stiffness and / or damping. As a result, wear and tear or tolerances between robots of the same model or the like can be taken into account in one embodiment, thereby improving machine learning or the trained agent (s), in particular robust (er) and / or flexible (er) l (er) ), will.

Additionally or alternatively, the robot parameter in one embodiment has a one- or multi-dimensional force parameter of an external force acting on the robot at least, in one embodiment only temporarily, in particular a (stochastic) disturbance or disturbance force, in particular an external force as a result of environmental contact or the like . As a result, real process conditions or random disturbances can be taken into account in an execution and thereby improve machine learning or the trained agent (s), in particular robust (more) and / or flexible (more), will.

A force in the sense of the present invention can in particular have, in particular be, an antiparallel force pair or torque. A force parameter can in particular include a force, but also a stiffness, a damping and / or a coefficient of friction or the like.

Additionally or alternatively, the robot parameter in one embodiment has a one- or multi-dimensional kinematic, in one embodiment dynamic, robot structure parameter, in particular one or multi-dimensional dimension and / or a weight and / or one or multi-dimensional moment of inertia of the robot or individual Structural members or structural member groups, or the like. As a result, tolerances between robots of the same model or the like can be taken into account in one embodiment, thereby improving machine learning or the trained agent (s), in particular robust (er) and / or flexible (er), will.

Additionally or alternatively, the environmental model parameter has in one embodiment a one- or multi-dimensional kinematic, in one embodiment dynamic, environmental, in one embodiment load structure parameter, in particular a one or multi-dimensional pose and / or dimension and / or a weight and / or moment of inertia an environmental structure, in particular a load structure, in particular a tool and / or workpiece or the like used in the application. As a result, tolerances between tools or workpieces of the same model, inaccuracies as a result of previous processes or the like can be taken into account in one embodiment, thereby improving machine learning or the trained agent (s), in particular robust (more) and / or flexible (e) l (er), will.

Additionally or alternatively, in one embodiment the robot parameters and / or the environmental model parameters are determined with the aid of a robot-assisted parameter identification, for example minimum, maximum and / or mean value (s) of or for the stochastic parameter model. In one embodiment, this can improve the correspondence with the real application and thereby improve machine learning or the trained agent (s), in particular robust (more) and / or flexible (more), will.

In one embodiment, in particular, the predetermined stochastic parameter model is predetermined on the basis of a user input and / or application-specifically, in one embodiment it is selected from a plurality of different parameter models made available.

In one embodiment, a user can first select one of several probability distributions, for example a Gaussian distribution, a uniform distribution or another probability distribution, and specify minimum and maximum values or the like for this or here. Likewise, for certain joining applications, for example, a probability distribution, for example a uniform distribution, for certain gripping applications, a different probability distribution, for example a Gaussian distribution, or the like can be selected and application-specific minimum and maximum values or the like can be specified for this or here . Mixed forms are also possible, in particular an application-specific preselection or default value assignment and an input option for the user to change them.

Additionally or alternatively, in one embodiment the robot and / or the environmental model parameters are specified on the basis of a user input and / or application-specific, in one embodiment they are selected from a plurality of different parameters made available.

For example, for inserting a robot-guided workpiece into a recess in a flat surface, a two-dimensional position within the surface and a one-dimensional orientation or angular position around a surface normal can be specified or selected as the target pose for drilling with a robot-guided drill in a flat surface, on the other hand, a one-dimensional distance to the surface along the drill axis as a target or intermediate pose.

In one embodiment, the stochastic parameter model and / or the robot and / or the environmental model parameter is visualized in a, in particular virtual, image of the application through a marked area, in one embodiment through corresponding geometric spaces, in particular bodies such as cuboids, spheres, cones , Cylinders or the like, or, in particular, planar or environment-adapted surfaces.

In the above example, the area within the area in which the target position can (stochastically) be visualized in an image of the application, for example, by a corresponding circular area, the possible orientations or angular positions around the surface normal, for example, by two appropriately rotated cuboids or workpiece avatars in the respective maximum possible deflections.

In one embodiment, a probability distribution of the stochastic parameter model is visualized by a different coloring, in one embodiment different (color) brightness, of the marked area, the respective coloring or brightness (level) depending on the probability that the robot or environmental model parameter has the corresponding value.

In the above example, the area within the area in which the target position can be (stochastically) can be visualized in an image of the application, for example, by a corresponding circular area, areas of the circular area in which the target position is more likely, for example are or will be colored darker or a first area of the circular area in which the target position is located with a first probability, for example is or will be colored with a first color and / or brightness, and at least one other area of the circular area in which the target position lies with a different probability, is or will be colored with a different color and / or brightness.

As a result, in one embodiment, in particular in combination, a particularly suitable parameter model or particularly suitable parameters can be selected, in particular the speed and / or reliability of the input can be improved. User input support by a software assistant described elsewhere is particularly advantageous both for user input for specifying, in particular selection, the stochastic parameter model and user input for specifying, in particular selection, the robot and / or environmental model parameter.

In one embodiment, the configured control of the robot and / or the machine-learned anomaly detection and / or error detection is tested with the aid of at least one further simulation, in particular on the basis of an automated specification or user specification of a value of at least one robot parameter and / or at least one environmental model parameter.

For example, the user can change the pose of a workpiece for the test simulation and then use the test simulation to check whether or how well the configured control or anomaly or error detection (for this) works or performs. Likewise, a test script can automatically carry out further simulation with the trained control agent or agents or trained anomaly and / or error detection and thereby vary the values of at least one robot parameter and / or at least one environmental model parameter.

Additionally or alternatively, in one embodiment, the configured control of the robot and / or the machine-learned anomaly detection and / or error detection, in particular by means of machine learning, in particular reinforcement learning, are trained further with the aid of the robot, in particular on the basis of applications carried out with the aid of the robot.

As a result, a control which is particularly advantageous in practice can be implemented in one embodiment, in particular in combination.

In one embodiment, the stochastic parameter model is, in particular, specified with the aid of machine learning. In particular, a parameter model (KI) agent can be based on previous applications carried out with the aid of the robot, which have been classified with the aid of a classification agent trained according to a method described here and / or in which the control of the robot with which these applications were carried out, have been configured on the basis of a control agent trained according to a method described here, based on the results of the previous applications carried out and the stochastic parameter model used in training this classification or control agent, the stochastic parameter model is specified, which is then specified in a method described here to carry out simulations to train the at least one classification agent, with the help of which a new application is then classified, and / or the at least one control agent is used, with the help of which a control for the durc a new application is configured.

In this way, a particularly advantageous, in particular realistic, stochastic parameter model can be used, preselected in one embodiment, in particular by the user input support or the software assistant. In addition or as an alternative to the earlier applications carried out with the aid of the robot, simulated applications can also be used as earlier applications for machine learning for specifying the stochastic parameter model.

In one embodiment, one or more of the steps of one of the methods described here, in particular the specification, in particular selection, of the stochastic parameter model and / or the robot and / or the environmental model parameter, have user input support from a software assistant, in particular user interface guidance , especially a so-called wizard.

In one embodiment, the robot and / or the environmental model parameter and / or the stochastic parameter model is preselected from a plurality of different parameters or parameter models made available, in particular application-specific and / or by the user input support or the software assistant.

As a result, in one embodiment, in particular in combination, a particularly suitable parameter model or particularly suitable parameters can be selected, in particular the speed and / or reliability of the input can be improved.

Additionally or alternatively, one or more of the steps of one of the methods described here are carried out in a cloud.

As a result, this method can advantageously be carried out in parallel and / or quickly and / or in a distributed manner.

• - Erfassen wenigstens eines ein- oder mehrdimensionalen Roboterparameters und wenigstens eines ein- oder mehrdimensionalen Umweltmodelparameters;
• - Trainieren eines (KI-)Agenten mithilfe einer oder mehrerer Simulationen auf Basis dieses erfassten Roboterparameters und dieses erfassten Umweltmodelparameters mittels maschinellen Lernens auf Basis einer vorgegebenen Kostenfunktion; und
• - Konfigurieren der Steuerung des Roboters auf Basis des trainierten Agenten.

According to one embodiment of the present invention, a method for configuring a controller of a robot for performing a predetermined task has the following steps:

• - Detecting at least one one-dimensional or multi-dimensional robot parameter and at least one one-dimensional or multi-dimensional environmental model parameter;
• - Training an (AI) agent with the help of one or more simulations on the basis of this recorded robot parameter and this recorded environmental model parameter by means of machine learning on the basis of a predetermined cost function; and
• - Configure the control of the robot based on the trained agent.

By training an agent by means of machine learning with the aid of one or more simulations, a controller of a robot for performing a predetermined task can be configured particularly advantageously in one embodiment.

In one embodiment, the robot has a stationary or mobile, in particular mobile, base and / or a robot arm with at least three, in particular at least six, in one embodiment at least seven joints or (movement) axes, in one embodiment swivel joints or axes, on. The present invention is particularly suitable for such robots because of its kinematics, variability and / or complexity.

In one embodiment, the specified task has at least one movement of the robot, in particular at least one scheduled environmental contact of the robot, that is to say in particular can have robot-assisted gripping and / or joining. The present invention is particularly suitable for such tasks because of its complexity.

• - einen ein- oder mehrdimensionalen kinematischen, insbesondere dynamischen, Robotermodellparameter, insbesondere eine oder mehrere Achsabstände, Massen, Massenschwerpunkte, Trägheiten und/oder Steifigkeiten; und/oder
• - einen ein- oder mehrdimensionalen kinematischen, insbesondere dynamischen, Lastmodellparameter, insbesondere eine oder mehrere Abmessungen, Massen, Massenschwerpunkte und/oder Trägheiten; und/oder
• - eine aktuelle Roboterpose, insbesondere eine oder mehrere aktuelle Achs- bzw. Gelenkstellungen; und/oder
• - eine aktuelle Roboterbetriebszeit auf.

In one embodiment, the robot has parameters

• a one or more dimensional kinematic, in particular dynamic, robot model parameter, in particular one or more center distances, masses, centers of gravity, inertia and / or rigidity; and or
• a one or more dimensional kinematic, in particular dynamic, load model parameter, in particular one or more dimensions, masses, centers of mass and / or inertia; and or
• - a current robot pose, in particular one or more current axis or joint positions; and or
• - a current robot operating time.

Additionally or alternatively, in one embodiment the environmental model parameter has a one- or multi-dimensional CAD model parameter and / or a, in particular current, robot positioning in the environmental model and / or is determined with the aid of at least one optical sensor, in particular a camera.

In a further development, this optical sensor is guided, in particular held or carried by a person, in another development by a robot, which in turn, in one embodiment for this purpose, follows a programmed or automatically determined path, in particular by means of collision avoidance, or manually or . is or is guided by forces manually exerted on the robot.

In one embodiment, the agent has an artificial neural network. In a further development, the control of the robot is then configured on the basis of the structure and / or weightings of the trained network, and this structure and / or weightings are transferred in one embodiment to the control of the robot. Additionally or alternatively, the agent is trained in one embodiment with the help of reinforcement learning, preferably deep reinforcement learning.

In one embodiment, after it has been configured in the manner described here, the control of the robot is trained further by means of machine learning, in particular reinforcement learning, preferably deep reinforcement learning, with the aid of the real robot.

In one embodiment, the robot parameter and / or environmental model parameter is, in particular, stored at least temporarily in an administration shell and / or in a data cloud.

According to one embodiment of the present invention, in a method for performing a predetermined task with the aid of at least one robot, a controller of the robot is configured according to a method described here. Correspondingly, in one embodiment, a method according to the invention can have a method described here for configuring a controller of a robot for performing a specified task and the step of performing the specified task with the aid of the robot with the controller configured according to the invention.

According to one embodiment of the present invention, a system, in particular in terms of hardware and / or software, in particular in terms of programming, is set up to carry out one or more methods described here. In one embodiment, it has means for acquiring at least one robot parameter and at least one environmental model parameter; Means for training an agent with the aid of at least one simulation on the basis of the detected robot parameters and environmental model parameters by means of machine learning on the basis of a predetermined cost function; and means for configuring the control of the robot based on the trained agent.

• Mittel zum mehrfach wiederholten Ermitteln eines stochastischen Wertes wenigstens eines Roboterparameters und/oder wenigstens eines Umweltmodelparameters, insbesondere auf Basis eines vorgegebenen stochastischen Parametermodells und/oder mithilfe wenigstens eines Zufallsgenerators; und Durchführen einer, insbesondere mehrstufigen, Simulation der Applikation auf Basis des ermittelten stochastischen Wertes; und

In one implementation, the system comprises:

• Means for repeatedly determining a stochastic value of at least one robot parameter and / or at least one environmental model parameter, in particular on the basis of a predetermined stochastic parameter model and / or with the aid of at least one random generator; and performing an, in particular multi-stage, simulation of the application on the basis of the determined stochastic value; and

Means for training at least one control agent and / or at least one classification agent using the simulations using machine learning, in particular training a first control agent and / or first classification agent using first stages of the simulations, and at least one further control agent and / or further classification agents with the aid of further stages of the simulations.

Additionally or alternatively, in one embodiment the system has means for configuring a control of the robot on the basis of the, in particular the, trained control agent for carrying out the application.

Additionally or alternatively, in one embodiment the system has means for classifying the application with the aid of the, in particular the trained, classification agent.

Additionally or alternatively, in one embodiment the system has means for performing the application with the aid of the robot, with a controller of the robot with which the application is performed in whole or in part being configured and / or based on the, in particular the, trained control agent the application is classified with the aid of, in particular, the trained classification agent.

• eine maschinell gelernte Anomalieerkennung und/oder maschinell gelernte Fehlererkennung und/oder wenigstens ein künstliches neuronales Netz; und/oder Mittel zum Trainieren wenigstens eines Steuerungs-Agenten und/oder wenigstens eines Klassifikations-Agenten mithilfe von Reinforcement Learning und/oder mithilfe des Roboters wird; und/oder

In one embodiment, the system or its means has:

• a machine-learned anomaly recognition and / or machine-learned error recognition and / or at least one artificial neural network; and / or means for training at least one control agent and / or at least one classification agent with the aid of reinforcement learning and / or with the aid of the robot; and or

Means for classifying the application on the basis of at least one, in particular moving, time segment and / or during or after the application is carried out with the aid of the at least one classification agent; and or

Means for training the at least one control agent and / or the at least one classification agent on the basis of at least one state variable that was not measured when the application was carried out; and or

Means for determining the robot parameter and / or the environmental model parameter with the aid of a robot-assisted parameter identification; and / or means for checking whether the starting pose, intermediate pose and / or target pose can be reached with the robot; and or

Means for specifying the stochastic parameter model on the basis of the application and / or a user input, in particular for selecting from a plurality of different parameter models made available; and / or means for visualizing the stochastic parameter model in an image of the application through a marked area; and or

Means for specifying the robot and / or the environmental model parameter on the basis of the application and / or a user input, in particular for selecting from a plurality of different parameters made available; and / or means for visualizing the robot and / or the environmental model parameter in an image of the application through a marked area; and or

Means for testing the configured control of the robot and / or the machine-learned anomaly detection and / or error detection with the aid of at least one further simulation, in particular on the basis of an automated or user specification of a value of at least one robot parameter and / or at least one environmental model parameter; and or

Means for further training the configured control of the robot and / or the machine-learned anomaly detection and / or error detection with the aid of the robot; and or

Means for specifying the stochastic parameter model using machine learning; and or

Means for user input support of at least one of the method steps by a software assistant, in particular a user interface guide; and or

Means for performing at least one of the method steps in a cloud.

A means within the meaning of the present invention can be designed in terms of hardware and / or software, in particular a data or signal-connected, in particular digital, processing, in particular microprocessor unit (CPU), graphics card (GPU), preferably with a memory and / or bus system ) or the like, and / or one or more programs or program modules. The processing unit can be designed to process commands that are implemented as a program stored in a memory system, to acquire input signals from a data bus and / or to output output signals to a data bus. A storage system can have one or more, in particular different, storage media, in particular optical, magnetic, solid-state and / or other non-volatile media. The program can be designed in such a way that it embodies or is able to execute one or more of the methods described here in whole or in part, so that the processing unit can execute steps of such methods and thus in particular configure the controller or classify or execute or execute the application. can operate or control the robot. In one embodiment, a computer program product can have, in particular, a non-volatile storage medium for storing a program or with a program stored on it To carry out a process or one or more of its steps.

In one embodiment, one or more, in particular all, steps of the method are carried out completely or partially in an automated manner, in particular by the system or its means.

In one embodiment, the system has the robot.

In one embodiment, a framework is created that enables motion or task learning to be implemented more efficiently using the reinforcement learning method. In one embodiment, parameters of the robot are simply and efficiently queried and / or the environmental model is recorded. In particular, in order to learn efficiently (more) and quickly (more) and / or not to block the real system, this is not carried out in one embodiment on the real system, but in a cloud simulation environment. This can advantageously enable a parallelization of the learning process and thereby an advantageous increase in speed and, in particular, a more robust model as a result (through randomization of parameters).

• - das Konfigurieren einer Steuerung eines Roboters zum Durchführen einer Applikation mithilfe des Roboters (Roboterapplikation);
• - das Trainieren eines oder mehrerer Klassifikations-(KI)Agenten zur Klassifikation einer Roboterapplikation; und
• - das Durchführen einer bzw. der (Roboter)Applikation mithilfe wenigstens eines bzw. des Roboters

bzw. hierzu eingerichtete Mittel umfasst, insbesondere also (auch) ein Konfigurieren der Steuerung ohne Durchführen der Applikation, ein Trainieren des bzw. der Klassifikations-(KI)Agenten ohne Durchführen der Applikation, insbesondere ein Trainieren des bzw. der Klassifikations-(KI)Agenten zusammen mit dem Konfigurieren der Steuerung, aber ohne Durchführen der Applikation, das Durchführen der Applikation mit bereits konfigurierter Steuerung und/oder trainiertem/-n Klassifikations-(KI)Agenten, d.h. ohne das Konfigurieren und/oder ohne das Trainieren des bzw. der Klassifikations-(KI)Agenten, als auch die Kombination von Konfigurieren und/oder Trainieren mit dem Durchführen bzw. (jeweils) hierzu eingerichtete Mittel. Entsprechend umfasst ein Merkmal des Durchführens der Applikation insbesondere auch, dass das Konfigurieren der Steuerung bzw. Trainieren des bzw. der Klassifikations-(KI)Agenten dazu eingerichtet ist bzw. derart durchgeführt wird, dass dieses Merkmal dann beim Durchführens der Applikation mit der konfigurierten Steuerung bzw. dem bzw. den trainierten Klassifikations-(KI)Agenten verwirklicht ist.It should be emphasized again that the present invention in particular

• the configuration of a controller of a robot for performing an application with the aid of the robot (robot application);
• - the training of one or more classification (KI) agents to classify a robot application; and
• the implementation of a (robot) application with the aid of at least one or the robot

or means set up for this purpose, in particular (also) configuring the controller without performing the application, training the classification (KI) agent or agents without performing the application, in particular training the classification (KI) Agents together with configuring the controller, but without executing the application, executing the application with an already configured controller and / or trained classification (KI) agent, ie without configuring and / or without training the Classification (KI) agents, as well as the combination of configuration and / or training with the implementation or means (each) set up for this purpose. Accordingly, a feature of performing the application also includes, in particular, that the configuration of the controller or training of the classification (KI) agent or agents is set up or performed in such a way that this feature is then used when the application is performed with the configured controller or the trained classification (KI) agent is realized.

• 1: ein System nach einer Ausführung der vorliegenden Erfindung;
• 2: Teile des Systems;
• 3: ein Verfahren nach einer Ausführung der vorliegenden Erfindung;
• 4: ein Verfahren nach einer weiteren Ausführung der vorliegenden Erfindung; und
• 5: eine Visualisierung eines stochastischen Parametermodells und eines Roboterparameters.

Further advantages and features emerge from the subclaims and the exemplary embodiments. For this shows, partly schematically:

• 1 : a system according to an embodiment of the present invention;
• 2 : Parts of the system;
• 3 : a method according to an embodiment of the present invention;
• 4th : a method according to a further embodiment of the present invention; and
• 5 : a visualization of a stochastic parameter model and a robot parameter.

1 Figure 3 shows a system according to an embodiment of the present invention with a robot 1 , a (robot) controller 2 that with the robot 1 and a cloud 4th communicates and a data input / output and processing device, in particular a computer 3 .

• In einem ersten Schritt eines Verfahrens nach einer Ausführung der vorliegenden Erfindung (3: S10) werden ein Roboterparameter und eine Startkonfiguration erfasst. Um das Motion-Learning in einer Simulationsumgebung vorteilhaft durchzuführen, sollten sowohl Parameter des Roboters wie auch das Umweltmodell möglichst exakt in der Cloud-Simulationsumgebung verfügbar sein.

A wizard runs on its user interface that guides a user through one or more of the processes described below:

• In a first step of a method according to an embodiment of the present invention ( 3 : S10 ) a robot parameter and a start configuration are recorded. In order to carry out motion learning advantageously in a simulation environment, both parameters of the robot and the environmental model should be available as precisely as possible in the cloud simulation environment.

With the help of what is known as an asset administration shell (AAS), also known as a digital twin, the robot's status and management data are recorded 1 saved. An OPC UA information model is advantageously used for this. In the administration shell of the robot, data such as the robot model, operating hours, current axis values (to determine a starting position), attached tools, etc. are available and are transferred to the cloud simulation environment. From this, the simulation environment can configure the simulation with regard to the robot (CAD model, dynamic parameters, tools, current axis configuration, possibly changed dynamic parameters due to service life, etc.)

• - Übertragung eines vollständig modellierten CAD Modells inkl. Transformation zum Roboterkoordinatensystem;
• - Erfassung der Umwelt durch eine 3D Kamera, die entweder von einem Menschen handgeführt wird oder am Roboter montiert ist, der
  • - handgeführt wird oder
  • - eine definierte und kollisionsfreie Trajektorie abfährt

In a second step ( 3 : S20 ) the environmental model is recorded. There are several options to choose from in one version:

• - Transfer of a fully modeled CAD model including transformation to the robot coordinate system;
• - Detection of the environment by a 3D camera that is either hand-operated by a human or is mounted on the robot that
  • - is hand-held or
  • - runs a defined and collision-free trajectory

In the case of manual guidance, it is also possible to record areas that are important for the task, for example a joining target, more precisely and from a small distance.

The environmental model generated in this way is now also transferred to the cloud simulation environment. A simple option here is to also store the data in the robot's administration shell.

In a modification, the robot cell has an administration shell 10 (see. 2 ), the environmental model and references to other administration shells involved. This means that the robot itself is interchangeable and the whole thing has a more modular structure than if all the information is in the robot's administration shell itself. The “Cell Manager” can then interact with the subcomponents, the simulation environment 20th (see. 2 ) and regulate the execution of the learning process.

In a third step ( 3 : S30) the learning objective is defined. A cost function is specified so that the reinforcement algorithm knows its goal. In particular, it is possible in the guided wizard to specify the target, for example, by the user guiding the robot to the joining target and repeating this a few times in order to minimize errors.

A manual demonstration is also used in one embodiment, depending on the reinforcement learning algorithm, to initialize the algorithm or to perform inverse reinforcement learning of the cost function. The trajectories of the demonstrations can also be stored in the administration shell.

In a fourth step ( 3 : S40) is in the cloud environment 4th , preferably in parallel, learned the task using the deep reinforcement learning method.

• - Guided Policy Search;
• - Soft Q-Learning;
• - A3C

oder dergleichen.The specific algorithm is advantageous

• - Guided Policy Search;
• - Soft Q-Learning;
• - A3C

or similar.

In order to overcome the simulation-reality gap, the dynamic parameters are randomized in one embodiment. If a vision system is involved, a flexible vision model is learned in an implementation using domain randomization.

A geometric path planner can plan non-contact path elements and in the case of the guided Policy Search initialize the Linear Quadratic Gaussian Controllers.

The result of the algorithm is the structure of the neural network and the trained weights of a neural network. As a modification, progressive nets can be used for later fine-tuning. The results of the simulation are sent back to the robot / edge controller.

In a fifth step ( 3 : S50 ) the model is downloaded to the robot or an edge controller.

The trained model can now be played back. In the administration shell of the simulation instance, parameters of the simulation and the learning algorithm can also be provided (e.g. learning rate, number of iterations, etc., which can later be used for fine tuning). In particular, the ONNX exchange format, for example, can be used for exchanging the computation graph and the weights.

In an optional sixth step ( 3 : S60 ) the model is fine-tuned on the real system.

Depending on the quality of the simulation, the model is immediately ready-to-use or is further fine-tuned on the real system. This means that the reinforcement learning algorithm is trained further on the real system, with initialization using the weights and other parameters of the reinforcement algorithm being advantageous.

In a seventh step ( 3 : S70 ) the learned task can now be executed.

4th FIG. 11 shows a method according to a further embodiment of the present invention, which is carried out with the system of FIG 1 can be executed.

In one step S100 is in each case provided by a random generator provided in this exemplary embodiment and therefore indicated by dashed lines 3a (see. 1 ) a stochastic value of a robot parameter and / or an environmental model parameter, for example a two-dimensional target position of a connector guided by a robot in this exemplary embodiment 1a in a plane 10 (see. 1 ), based on a specified stochastic parameter model, in the exemplary embodiment a Gaussian distribution specified by a user with the aid of the wizard.

5 shows an example of how this robot parameter and this stochastic parameter model are visualized in a mapping of this joining application by a marked area in the form of a circle around the mean or expected value of the Gaussian distribution for the two-dimensional target position in the (mapping of the) surface . The edge of the circle visualizes a maximum value of a deviation from the mean or expected value and the different coloring indicated by different hatching, in one embodiment different (color) brightness, of the marked area the respective probability that the target position is at this point.

In one step S200 a simulation of the application on the basis of the determined stochastic value, ie with a stochastic target position, is performed on the computer 3 or in the cloud 4th accomplished.

A control agent is trained using reinforcement learning.

In one step S300 it is checked whether the control agent has already been trained sufficiently. This is not the case ( S300 : "N"), generated by the random generator 3a a new stochastic target position with which a further simulation is carried out.

Is the control agent sufficiently trained ( S300 : "Y"), the controller 2 of the robot 1 configured on the basis of the trained control agent ( S400 ).

In addition, a classification agent is trained with the help of the simulations carried out, for example anomaly or error detection is learned by machine ( S500 ), ie the simulations carried out when training the control agent are used.

Then the real application is made with the help of the robot 1 with the in step S400 configured control carried out ( S600) and thereby or subsequently classified by the anomaly or error detection ( S700 ). The configured control can be trained further.

Although exemplary embodiments have been explained in the preceding description, it should be pointed out that a large number of modifications are possible. It should also be pointed out that the exemplary designs are only examples that are not intended to restrict the scope of protection, the applications and the structure in any way. Rather, the preceding description provides a person skilled in the art with guidelines for the implementation of at least one exemplary embodiment, with various changes, in particular with regard to the function and arrangement of the components described, being able to be made without departing from the scope of protection as it emerges from the claims and these equivalent combinations of features results.

Claims (15)

A method for performing an application with the aid of at least one robot (1), the method comprising the repeated steps: - Determination (S100) of a stochastic value of at least one robot parameter and / or at least one environmental model parameter, in particular on the basis of a predetermined stochastic parameter model and / or with the aid of at least one random generator (3a); and - Carrying out (S200) a, in particular multi-stage, simulation of the application on the basis of the determined stochastic value; the steps: - Training (S200, S500) at least one control agent and / or at least one classification agent using the simulations using machine learning, in particular training a first control agent and / or first classification agent using first stages of the simulations, and at least one further control agents and / or further classification agents with the aid of further stages of the simulations; and - Execution (S600) of the application with the aid of the robot; as well as having at least one of the steps: - Configuring (S400) a controller of the robot with which the application is carried out in whole or in part, on the basis of the, in particular the, trained control agent; and or - Classification (S700) of the application with the aid of the, in particular the, trained classification agent. Procedure according to Claim 1 , characterized in that the at least one control agent and / or the at least one classification agent has a machine-learned anomaly recognition and / or machine-learned error recognition and / or at least one artificial neural network, in particular the control of the robot based on the structure and / or weightings of the trained network is configured, and / or the at least one control agent and / or the at least one classification agent is trained with the aid of reinforcement learning and / or with the aid of the robot. Method according to one of the preceding claims, characterized in that the at least one classification agent classifies the application on the basis of at least one, in particular moving, time segment and / or during or after the implementation of the application and / or the at least one control agent and / or the at least one classification agent is trained on the basis of at least one state variable that is not measured when the application is carried out. Method according to one of the preceding claims, characterized in that - the robot parameter is a start pose, at least one intermediate pose and / or a target pose of the application and / or a force parameter of a robot-internal and / or an external force acting at least temporarily on the robot and / or a kinematic has, in particular dynamic, robot structure parameters; and / or the environmental model parameter has a kinematic, in particular dynamic, environmental, in particular load structure parameter; and / or - the robot parameter and / or the environmental model parameter is determined with the aid of a robot-assisted parameter identification. Method according to the preceding claim, characterized in that it is checked whether the start pose, intermediate pose and / or target pose can be reached with the robot. Method according to one of the preceding claims, characterized in that the stochastic parameter model is specified based on the application and / or a user input, in particular selected from a plurality of different parameter models made available, and / or visualized in an image of the application by a marked area and / or the robot and / or environmental model parameter is specified on the basis of the application and / or a user input, in particular selected from a plurality of different parameters made available, and / or is visualized in an image of the application by a marked area. Method according to one of the preceding claims, characterized in that the configured control of the robot and / or the machine-learned anomaly detection and / or error detection using at least one further simulation, in particular on the basis of an automated or user specification of a value of at least one robot parameter and / or at least one Environmental model parameters, tested and / or further trained with the aid of the robot. Method according to one of the preceding claims, characterized in that the stochastic parameter model is specified with the aid of machine learning. Method for configuring a controller of a robot (1) for performing an application with the aid of the robot, the method comprising the repeatedly repeated steps of determining (S100) a stochastic value and performing (S200) a simulation and the step of training (S200) at least one control agent according to a method Claim 1 , in particular additionally one or more features of one or more of the Claims 2 until 8th , as well as having the step: configuring (S400) the controller of the robot to carry out the application on the basis of the, in particular the, trained control agent. Method for training at least one classification agent for classifying a robot application, in particular together with configuring a controller of a robot (1) for performing the application according to a method according to the preceding claim, the method for training comprising the repeatedly repeated steps of determining (S100 ) a stochastic value and performing (S200) a simulation and the step of training (S500) at least one classification agent, in particular the step of training (S200, S500) at least one control agent and at least one classification agent, according to a method after Claim 1 , in particular additionally one or more features of one or more of the Claims 2 until 8th , having. A method for performing an application with the aid of at least one robot (1), with the step: performing (S600) the application with the aid of the robot, a control of the robot, with which the application is carried out in whole or in part, according to a method Claim 9 is configured and / or the application is classified with the aid of at least one classification agent, which according to a method according to Claim 10 is trained. Method according to one of the preceding claims, characterized in that at least one of the method steps has user input support by a software assistant, in particular a user interface guide. Method according to one of the preceding claims, characterized in that at least one of the method steps is carried out in a cloud (4). System for carrying out an application with the aid of at least one robot (1), the system being set up for carrying out a method according to one of the preceding claims and / or having: Means for repeatedly determining a stochastic value of at least one robot parameter and / or at least one environmental model parameter, in particular on the basis of a predetermined stochastic parameter model and / or with the aid of at least one random generator (3a), and performing a, in particular multi-stage, Simulation of the application based on the determined stochastic value; and Means for training at least one control agent and / or at least one classification agent using the simulations using machine learning, in particular training a first control agent and / or first classification agent using first stages of the simulations, and at least one further control agent and / or further classification agent with the aid of further stages of the simulations; and / or has: Means for carrying out the application with the aid of the robot, a controller of the robot with which the application is carried out in whole or in part being configured on the basis of the, in particular the, trained control agent and / or the application with the aid of the, in particular the, trained Classification agent is classified; and / or has: Means for configuring a control of the robot on the basis of the, in particular the, trained control agent for carrying out the application; and / or has: Means for classifying the application with the aid of the, in particular the, trained classification agent. Computer program product with a program code, which is stored on a medium that can be read by a computer, for carrying out a method according to one of the preceding claims.

Images