DE102021103126B4 - Method for accelerating a handling machine - Google Patents

Abstract

Method for controlling the movement of a real robot (1) used in a (real) application environment (100) such as a packaging machine (100) by controlling the drives of the relatively movable parts of the robot (1), characterized in thatA ) exemplary movement sections (BA) are created from a large number of exemplary work orders and the order data describing them, for which the optimal movement data in the form of section movement based on at least one predetermined optimization parameter (A6). -Data (ABD) are determined in a pre-calculation process, for which - apart from the start parameters in the form of the start position and start rotational position - and the target parameters in the form of the target position and target rotational position of the tool, as many as possible - Accompanying parameters are provided. (A8)B) the exemplary section movement data (ABD) is entered as training data into an artificial intelligence (AI) with at least one artificial neural network (ANN), - the AI is trained with it, C) in the application - Environment when a work order (AA) appears with one or more movement sections (BA) - the order data is entered into the trained AI as query sizes, - the response sizes received from the AI in response as section movement data (ABD ) or raw section movement data (RABD) can be further used for this at least one movement section (BA), D) the section movement data (ABD) is provided with a temporal and/or local or other start criterion in a data buffer are stored,E) when the start criterion is reached in the order data of a job, in particular of the robot in question, the robot carries out the movement section (BA) by controlling its drives using control commands that are in the section movement data (ABD) are included.

Description

I. Area of application

The invention relates to the control of the movement of one or more robots working together, particularly in packaging technology.

II. Technical background

With the help of the tool attached to a robot, often in the form of a vacuum cleaner, an object is to be grasped at a pick-up point, moved to a storage point and stored there in a defined manner.

The tool - in the following we will only talk about the vacuum cleaner, without restricting the invention to this - can have up to 6 degrees of freedom, so it can generally be moved in the 3 spatial directions X, Y, Z and around the 3 spatial axes A, B, C pivotable.

The robot can be a serial robot with only one robot arm consisting of several arm parts that are articulated one behind the other, i.e. in series, which is attached to a robot base at its rear end and a tool carrier or the tool directly at its front end - hereinafter referred to as the tool unit - carries.

The robot can also be a robot with parallel kinematics, such as a delta robot, in which several, usually 3, robot arms are each attached with their rear end to a usually common robot base and with their front end to a common one Tool unit, which usually includes a tool carrier that carries the tool.

The arm parts arranged one behind the other from the robot base to the tool unit, which also make up the robot arms of this robot type, are connected to one another in an articulated manner with at least one degree of freedom and/or can be moved relative to one another, as is the first arm part on the robot base and the last arm part on the tool unit.

Each of these relative movements is carried out controlled by a drive, with the goal being to complete the robot's desired work order as quickly as possible so that the packaging system - for example a transfer device for products from a product belt into the containers on one Container belt using several robots arranged one behind the other on the belts in the form of a robot line - works as efficiently as possible, i.e. as many work orders as possible in the form of such transfer processes are completed per unit of time.

Since the work orders are known with a time lead before they are carried out - with a robot str. for moving products because a scanner upstream of the transfer area detects the positions and, if necessary, rotational positions of the products on the, usually continuously, running container belt and immediately afterwards the road control system sends the work orders to the respective robots and, if necessary, their robot controls can assign - the movement data for the work orders does not have to be determined and available in real time when the work orders are assigned, but should generally not be longer than 100 ms, preferably not longer than 50 ms, preferably not longer than 30 ms after the work orders are available so as not to cause any delays in the movement sequences of the robot line and the individual robots.

The performance of the packaging machine, in particular the conversion performance of a robot line, limiting parameters are, for example, the load capacity of the bearing points and linear guides, the drive power of the drives, the vibrations generated by the movements in the machine, the load capacity of the object and the speed at which the control determines the ideal movement path and the movement data in the form of control commands for the drives of the individual moving parts involved, in particular the robot - usually based on a known pick-up point and storage point determined by means of a scanner. The ideal movement path does not have to be the straight path from the starting point to the target point, for example of the tool.

Vibrations in the system can have a negative impact on the accuracy of picking up and placing the object as well as the service life of the system.

From the DE 10300606 B4 A method for approaching a gripper to a moving object is described. However, order data from previous work orders is not worked with, this optimal section movement data is not broken down, and artificial intelligence is not trained with this data.

Also the DE 10 2017 008 836 B4 , which is used to control the access of a robot to an object by means of a status observation unit, the positions and position of the objects as well as min At least one state variable is constantly observed does not use these steps.

The DE 11 2019 007 404 T5 Although it calculates parameters for controlling movements of a robot using state variables and evaluates the movements of the robot, in particular with regard to cycle time, only multi-criteria optimization parameters are learned by machine and the aforementioned steps, which are not used in the first two publications, are not used in this case either.

The DE 10 2019 120 663 A1 describes a shovel excavator that, for example, is intended to carry out a gripping movement in both a learning mode and a departure/working mode, whereby the results of the movements carried out in the learning mode are used to optimize the movements in the working mode.

The missing steps mentioned at the beginning are not present here either.

The one further away DE 10 2018 129 528 A1 only addresses the problem of suppressing the vibrations that occur when increasing the operating speed of an industrial robot with an articulated arm.

This is also further away DE 10 2017 113 818 B4 , which abstractly describes the process of moving a moving article and putting it into a moving container using a robot, for example, and does not use the above-mentioned process steps either.

III. Presentation of the invention

a) Technical task

It is therefore the task according to the invention to determine the optimal robot movements with regard to the efficiency of the robot and in particular other optimization parameters such as the service life of the system as quickly and accurately as possible and to generate control commands for the individual drives of the robot as quickly as possible .

b) Solution to the task

This task is solved by the features of claims 1 and 19. Advantageous embodiments result from the subclaims.

In a control method for controlling the movement of a robot used in a real application environment such as a packaging machine, typically a robot line, and is by controlling the drives of its relatively movable parts, such as the arm -Parts that control the robot in its entirety of movements.

In order to solve the existing task, according to step A), the optimized movement paths and movement data are calculated in advance for a large number of possible movement sections of a robot, such as entire work orders, and not in a temporal connection with specific existing ones Work orders to the robot are carried out in a classic deterministic manner in a pre-calculation process, for example calculated using calculation algorithms.

Carrying out this for a large number of example work orders, i.e. movement sections of robots, requires a lot of computing power and a lot of computing time, which is why it is carried out in advance, i.e. usually before the system, i.e. the real application environment, is started up.

The more parameters that can be made available for the calculation of the optimal movement data and can be taken into account when calculating the optimal movement data, the greater the computing effort will be, but the higher will be the degree of optimization of the movement data and thus the Achievable performance of the packaging machine, measured for example in the number of sales processes per unit of time in a transfer device such as a robot line.

As explained using the figures, this results in very fast movements of the robots, but they do not always have to take the assumed shortest route between the start and destination points.

Using the exemplary order data and the optimal movement data calculated therefrom as training data, in step B), an artificial intelligence (AI), which includes at least one artificial neural network (ANN) and a training unit, is trained.

In order to carry out a specific work order present in the application environment in the form of one or more movement sections - the work order can therefore only include a single movement section - for a robot, these order orders are used in accordance with step C). Data is entered into the trained AI as query sizes, which then outputs sectional movement data as response sizes, which is at least can be used as raw section movement data.

This output of the response variables occurs much faster, approximately in 2 to 5 ms, than is required for a deterministic calculation of such optimized movement data using classic deterministic calculation algorithms.

However, the section movement data that is now available is only required at a slightly later point in time, namely when a certain starting criterion for processing this movement section is given - for example the vacuum cleaner of the corresponding robot has reached the corresponding starting point of this movement section - which is why they are according to step D) until then stored and kept in a data buffer.

Only when the start criterion for carrying out this movement section is reached are the corresponding section movement data, which preferably already contain specific control commands for controlling the individual drives of the robot, read out from the data buffer and the movement section is completed according to step E). using the section movement data, in particular the control commands from the robot controller or application controller.

The advantage is that once a work order has been submitted for a robot, the necessary movement data is available so quickly that there is no delay in processing the work orders.

Another advantage is that the pre-calculation process can be carried out outside the application environment and without connection to it, i.e. on separate computers and away from the application environment and, above all, long before the job is carried out in the real application environment.

The pre-calculation process and training of the AI is usually carried out once before the application environment, such as a packaging machine, is put into operation for the first time, as soon as all parameters from the application environment, at least the parameters of the robots, are known.

Accordingly, this usually only needs to be repeated when a tool is exchanged for another type of tool in the application environment, or a robot for another robot, and in any case if the robot is exchanged for a robot of a different type or size is exchanged, but even if it is a robot that is actually identical in construction, the individual differences between two identical robots can be large enough to make a new implementation of the pre-calculation process seem sensible.

Although the advantage of the pre-calculation process is that a high level of computing power and a relatively long computing time are required, exact movement data for an order or movement section - an order can include several movement sections - could be deterministically derived from the order data It makes sense to create even these exemplary data sets, which are only intended as training data for an AI, using a powerful AI.

The movement data would then no longer be determined deterministically and would no longer be correspondingly accurate, but a much larger number of training data could be determined in a short time, but depends very much on the performance of the AI used for this and, above all, its accuracy.

Since the individual drives in a robot require specific control commands, the movement data should already contain such specific control commands.

Control commands can be generated from movement data either in step C) or only in step N described below), i.e. at the latest before the movement data is stored in the data buffer or only afterwards by the control of the application environment, especially the robot.

Since the response sizes received from the AI in the application environment based on the query sizes are not deterministically calculated response sizes, but are also determined by the AI, for example, using interpolation and extrapolation, the response sizes are less precise than deterministically calculated movement data, so they can be used in In practice, the application environment contains movement data that cannot be carried out or contains inaccuracies or even range information.

• Dort werden die möglicherweise noch nicht ausreichend exakten Antwortgrößen nachbearbeitet und in exakte, durchführbare Abschnitts-Bewegungs-Daten umgeformt, die vorzugsweise auch bereits direkt die Steuer-Kommandos für die Antriebe in den Robotern enthalten.

Depending on how large these inaccuracies and/or areas are, a post-processing step N between steps C) and D) may make sense:

• There, the response variables that may not yet be sufficiently precise are post-processed and converted into exact, feasible sectional movement data, which is preferred The control commands for the drives in the robots are already included.

Such post-processing can, for example, take into account existing inconsistencies/discrepancies between the response variables of the AI on the one hand and the real conditions in the application environment or the movement order to be fulfilled or the state of the robot or the application environment on the other hand.

When bridging the inconsistencies/discrepancies, it may be that the circumstances in the application environment cannot be changed and the response variables then have to be adjusted, or both the response variables and the circumstances in the application environment could be changed.

In the latter case, a prioritization or weighting between the two is necessary in order to determine in which sense the post-processing should take place.

The implementation of the individual steps A) to E) can be further improved by the following optional measures:

To step A):

In order to determine optimal movement data, at least one optimization parameter must of course be specified, which is usually the movement time that is required to complete the movement section from its starting point to its destination point, and which should be as short as possible .

Other, especially further, optimization parameters could be minimizing the loads on drive motors, bearings, guides or other parts of the application environment.

If several optimization parameters are specified at the same time, a weighting between the optimization parameters must also be specified and/or a prioritization, in particular a prioritization order, among the several optimization parameters.

In the latter case, optimization is first carried out according to the optimization parameters with the first priority, and if different options arise with regard to the other optimization parameters that change the other optimization parameters differently, optimization is carried out in this order according to the parameter with the second prioritization and then decided according to the parameter with the third prioritization and so on.

A weighting can be represented in different ways, for example by at least a certain relative value, i.e. percentage, or absolute value of a first optimization parameter being achieved from its maximum achievable value in the present situation, but a further increase in favor of optimizing the next lower weighted one parameter should be done.

To determine the section movement data, at least the start parameters in the form of the start position and, if necessary, the start rotational position - if, for example, the products are out of round when viewed from above, the rotational position around a vertical axis - as well as the target parameters in the form of the target position and, if necessary, the target rotational position of the tool, usually a vacuum cleaner.

Position and rotation together result in the spatial position of a component or product.

In order to be able to optimize better, additional accompanying parameters are provided, for example the arrival speed with which the tool is at the start position - i.e. the target position of the previous movement section - based on the movement data of the previous movement section. will arrive and/or from which direction of arrival. Likewise, the departure speed and/or departure direction of the tool from the target position of the movement section is of interest for the tool to move through several movement sections as quickly as possible.

The accompanying parameters can also be environmental properties around the tool, possibly also of the tool itself, which should also be made available to optimize the movement data, for example the elasticity of the robot's drive, i.e. how strong When control commands are entered, the real movement of the robot lags behind these control commands

If the, in particular static, load for certain components, such as bearing points or linear guides, is to be optimized as one of the optimization parameters, load limit values should be specified for these components and points.

If the dynamic load, especially in the form of vibrations, for the robot and / or the system, i.e. machine, i.e. the If the application environment is to be kept optimally low, the vibration behavior of the corresponding part, in particular the robot or the entire system, should be known.

For this purpose, a corresponding model for the application environment, in particular for the static load as well as the vibration behavior, can either be made available for the pre-calculation process, i.e. stored, or can be created for the application environment or its parts in the pre-calculation process based on specified, especially constructive, data from the application environment, which of course further increases the computational effort for creating exemplary movement data.

To step B):

In order to decide when the AI is considered to be sufficiently well trained and the training is ended, a tolerance range can be specified around the movement section data generated deterministically for the example data, which in step A), for example from the order data data were calculated.

The AI can be considered to be sufficiently trained if, when order data is entered from the example data in step A), the AI itself - without resorting to this example data, but using its own artificial intelligence - acts as response variables in the movement section -Provides data that lies within this tolerance range.

To step C):

The AI can be trained in such a way that it can not only provide movement data in the form of a single value as response variables, but also area information, which therefore represents a certain uncertainty in the response variable.

To step D):

Preferably, the section movement data determined in the application environment is stored in the data buffer with a time and/or location advance. The minimum value of this time and/or location lead can be specified, and if necessary also a maximum value for this.

A time advance is understood to mean that section movement data is stored in the data buffer in the transport direction of one of the conveyors, in particular the product belt, when the starting position of this movement section on the conveyor or In relation to the conveyor in the transport direction, at least a defined predetermined lead distance is still away from the current X value, the transport direction of this conveyor, from the corresponding robot.

Local lead means a lead specified in units of length, such as the beginning of an intended movement section from the current position of the component in question, for example the tool of a robot

This ensures that at any time and for each of the robots when the target point of one of its movement sections is reached, the movement data for the next movement section is not only available, but is also read out from the data memory in a timely manner and sent to the system. Control can be provided.

In the event that this is not the case, an optional stop sequence for stopping the tool is preferably included at the end of the data record for the section movement data or during its course, which specifies how quickly and if necessary . in which direction the tool is braked towards the end of the movement section until it comes to a standstill in the target position.

To step E):

If at the end of the movement section in progress there is no section movement data for the immediately following movement section, the robot is preferably stopped at the end of the movement section according to the included stop sequence in order not to cause collisions.

Generally:

In order to facilitate the determination of, in particular, the exemplary movement data in step A) and/or the real movement data generated in step D) for a real work order, for each robot depending on its task in the corresponding application environment one or more basic movement types are defined, whereby the defined movement sections, i.e. their section movement data, preferably of all movement sections, should be subsumable under these or one of these basic movement types, be it in step A) and / or in step D).

This reduces the computing effort in the corresponding step, i.e. in step A) for determining the exemplary movement data and in step D) for determining the real movement data. Data for a movement section of a work order.

Furthermore, the movement speed and direction of movement of the receiving surface and/or storage surface, in a robot line for moving products, usually the product belt and/or the container belt, play an important role in determining movement data of the robot essential role, as this is essential for the robot to access a product at the correct pick-up point and/or to place the product at the correct storage point.

1. a) Entweder wird die Transportgeschwindigkeit bereits bei der Ermittlung der Bewegungs-Daten im Schritt A) als Umgebungs-Parameter mit vorgegeben.

This transport speed - in the example mentioned of belts always running in the same direction, such as a container belt or a product belt, the direction is known and does not change - can be taken into account at different points and steps in the process:

1. a) Either the transport speed is already specified as an environmental parameter when determining the movement data in step A).

Or these exemplary movement data with which the AI is trained does not take the transport speeds into account and then the transport speed is not included in the AI's response variables for a real work order.

Then the transport speed must be taken into account from the response variables of the Kl at the latest when determining the control commands for the drives, i.e. at the latest in step E).

If a recalculation according to step D) takes place in between, this can also be done in this step.

• Zunächst wird gemäß a) die - zu diesem Zeitpunkt nur vermutbare, beispielsweise hochgerechnete - Transportgeschwindigkeit bereits für die Ermittlung der Beispiel-Bewegungs-Daten berücksichtigt und ist dann auch bereits in den Antwortgrößen der KI in der realen Anwendungs-Umgebung enthalten.

In a preferred variant, both occur:

• First of all, according to a), the transport speed - which at this point can only be assumed, for example extrapolated - is already taken into account for the determination of the example movement data and is then already included in the response variables of the AI in the real application environment.

In addition, in the real application environment, the previously only assumed transport speed can be compared with the previously known or now better assumed transport speed of a belt or conveyor and, in the event of a difference that is above a tolerance limit, the movement created based on the originally assumed transport speed. Data, especially control commands, are recalculated taking this difference into account.

A robot application system comprises, on the one hand, an application environment such as a packaging machine with at least one robot and, on the other hand, an application control for controlling the parts of the application environment that are movable relative to one another, in particular the drives of the parts of the at least one robot that are movably connected to one another .

According to the invention, the existing task for such a robot application system is solved in that the robot application system comprises a pre-calculation computer which is able to determine at least one movement section of the robot from exemplary order data and for this to determine optimized section movement data deterministically, i.e. to calculate it.

Such a robot application system also includes a trained artificial intelligence (AI) with at least one artificial neural network (ANN) and in particular a training unit which is able to use the exemplary movement section data for the exemplary movement Sections of the sample jobs to train the AI.

• - ein Arbeits-Auftrags-Generator-Modul (Generator-Modul), welcher in der Lage ist, z.B. aufgrund von Eingaben des Benutzers oder zufallsbedingt, beispielhafte, konkrete Arbeits-Aufträge für jeden einzelnen Roboter zu erstellen und als Anfragegröße in die trainierte KI einzugeben und/oder
• - ein Bewegungs-Daten-Modul (Daten-Modul), welches in der Lage ist, Antwortgrößen der KI entgegenzunehmen und daraus Bewegungs-Daten zu erzeugen, insbesondere mit oder in Form von Steuerkommandos für die Antriebe des Roboters und/oder
• - ein 1. Nachbearbeitungs-Modul (1. Nach-Modul), um die vom Bewegungs-Daten-Modul erzeugten Bewegungs-Daten gegebenenfalls nachzubearbeiten, beispielsweise um Inkonsistenzen mit der realen Anwendungs-Umgebung, insbesondere im betreffenden Bewegungs-Abschnitt, zu beseitigen, und/oder
• - ein Puffer-Referenzwert-Generator-Modul (Ref-Modul), welches in der Lage ist................... und/oder
• - ein Stopp-Sequenz-Generator-Modul (Stopp-Modul), welches in der Lage ist, eine Stopp-Sequenz für einen Bewegungs-Abschnitts-Datensatz zu erzeugen und/oder
• - ein Puffer- Management-Modul (Manage-Modul), welches in der Lage ist, das Einbringen, Abspeichern und gegebenenfalls Sortieren und Ausbringen von Abschnitts-Bewegungs-Daten, insbesondere Datensätzen, im Puffer zu organisieren und/oder
• - ein Puffer- Auslese-Modul (Auslese-Modul), welches in der Lage ist, das Auslesen von Abschnitts-Bewegungs-Daten, insbesondere Datensätzen, aus dem Puffer durchzuführen und/oder
• - ein Förderband-Steuerungs-Modul (F-Steuer-Modul), welches die entsprechenden Förderer für Produkte und/oder Behälter, seiner Förderbänder oder andere Bauformen von Förderer, steuert und/oder
• - Fördergeschwindigkeits-Abschätz-Modul (F-Abschätz-Modul), welches in der Lage ist, die Geschwindigkeit des Förderers zu definierten Zeitpunkten oder Funktionszuständen der Anwendungs-Umgebung in der Zukunft abzuschätzen und/oder
• - ein 2. Nachbearbeitungs-Modul (2. Nach-Modul), um die aus dem Daten-Puffer ausgegebenen oder aus gelesenen Bewegungs-Daten nach zu bearbeiten, insbesondere im Fall einer Differenz zwischen den bei der Erstellung dieser Bewegungs-Daten unterstellten Geschwindigkeit und einer aktuell gemessenen oder nun besser abschätzbaren Fördergeschwindigkeit.

According to the invention, the application control preferably comprises

• - a work order generator module (generator module), which is able to create exemplary, concrete work orders for each individual robot, for example based on user input or randomly, and enter them into the trained AI as a query size and or
• - a movement data module (data module), which is able to receive response variables from the AI and generate movement data from them, in particular with or in the form of control commands for the robot's drives and/or
• - a 1st post-processing module (1st post-module) to post-process the movement data generated by the movement data module if necessary, for example to eliminate inconsistencies with the real application environment, especially in the relevant movement section, and or
• - a buffer reference value generator module (ref module), which is capable of......... and/or
• - a stop sequence generator module (stop module), which is able to generate a stop sequence for a movement section data set and/or
• - a buffer management module (manage module), which is able to organize the insertion, storage and, if necessary, sorting and output of section movement data, in particular data sets, in the buffer and/or
• - a buffer readout module (readout module), which is able to read out section movement data, in particular data sets, from the buffer and/or
• - a conveyor belt control module (F-control module), which controls the corresponding conveyors for products and/or containers, its conveyor belts or other types of conveyors and/or
• - Conveyor speed estimation module (F-estimation module), which is able to estimate the speed of the conveyor at defined times or functional states of the application environment in the future and/or
• - a 2nd post-processing module (2nd post-module) to post-process the movement data output or read from the data buffer, in particular in the case of a difference between the speed and speed assumed when creating this movement data a currently measured or now easier to estimate conveying speed.

• - exakt berechnete optimale Bewegungswege als Trainingsdaten für KI
• - geringerer Rechenaufwand und Datenmenge in der Anwendungs-Umgebung
• - schnelle Ermittlung der realen Bewegungsdaten für die einzelnen Arbeitsaufträge

This means that advantages can be achieved

• - precisely calculated optimal movement paths as training data for AI
• - Lower computing effort and data volume in the application environment
• - Quick determination of real movement data for individual work orders

• Arbeits-Auftrag bedeutet:
  • Beschreibung einer Bewegung und/oder Tätigkeit für einen Roboter Auftrags-Daten bedeutet: Datensatz, der diese Beschreibung in Form von digitalen Daten wiedergibt
• Optimierungs-Parameter bedeutet:
  • der an einem Arbeitauftrag zu optimierende Parameter, beispielsweise die Zeit,
  • die zur Durchführung des Arbeits-Auftrages benötigt wird
• Begleit-Parameter bedeutet:
  • Parameter, die die Begleit-Umstände des Arbeitsauftrages beschreiben und
  • den Arbeitsauftrag selbst beeinflussen
  • Umgebungs-Parameter bedeutet:
  • • Parameter, die die Umgebung, insbesondere Eigenschaften der Umgebung, in der der Arbeitsauftrag durchgeführt wird, beschreiben, beispielsweise die Belastbarkeit oder das Schwingungsverhalten von an dem Arbeitsauftrag beteiligten Teilen, sei es des Roboters oder der Anwendung-Umgebung
• Bewegung bedeutet:
  • (vorgesehene) Bewegung eines Roboters, insbesondere dessen Werkzeuges Bewegungs-Daten bedeutet:
• Datensatz, der diese Beschreibung in Form von digitalen Daten wiedergibt Steuerkommando bedeutet:
  • konkrete an Steuer-Befehle für die einzelnen Antriebe in einem Roboter Roh-Bewegungs-Daten bedeutet:
  • Bewegungsdaten die in dieser Form noch nicht zum festlegen exakter Steuer-kommandos für die Roboter-Antriebe geeignet sind
• Bewegung-Abschnitt bedeutet:
  • Teil einer Bewegung
• Abschnitt-Bewegungs-Daten bedeutet:
  • Datensatz, der diese Beschreibung in Form von digitalen Daten wiedergibt
• Start-Kriterium für Bewegungs-Abschnitt bedeutet:
  • ein meist zeitlich oder örtlich vorgegebenes Kriterium, ab dem ein Bewegung-Abschnitt vollzogen werden soll
• Machine-Learning bedeutet:
  • Trainingsmethoden für eine künstliche Intelligenz, insbesondere dessen künstliches neuronales Netz mittels Trainingsdaten
• Inkonsistenz bedeutet:
  • Widerspruch zwischen der Situation in der Anwendungs-Umgebung zum Ausführungszeitpunkt einer beabsichtigten Bewegung oder eines Bewegung-Abschnitte des und den von der KI hierfür gelieferten Antwortgrößen
• Priorisierung bedeutet:
  • Reihenfolge, in der bestimmte Parameter benutzt werden, insbesondere optimiert werden
• Gewichtung bedeutet:
  • Verhältnis, in dem verschiedene vorhandene Optimierungsparameter relativ zueinander einer Optimierung unterzogen werden sollen
• Position bedeutet:
  • die Stelle, an der sich ein Gegenstand, etwa ein Produkt oder ein Werkzeug, im Raum befindet
• Drehlage bedeutet:
  • die Drehlage, an der sich ein Gegenstand, etwa ein Produkt oder ein Werkzeug, im Raum befindet, insbesondere relativ zu festgelegten Raumachsen
• Raumlage bedeutet:
  • Summe aus Position und Raumlage
• Ankunfts-Richtung bedeutet:
  • diejenige Richtung, aus der sich ein Werkzeug dem Startpunkt für eine vorgesehenen Bewegung des Werkzeuges, also einem Bewegungs-Abschnitt, voraussichtlich nähern wird, falls die vorgesehene Bewegung keine andere Ankunfts-Richtung benötigt
• Ankunfts-Geschwindigkeit bedeutet:
  • diejenige Geschwindigkeit, mit der sich ein Werkzeug dem Startpunkt für eine vorgesehenen Bewegung des Werkzeuges, also einem Bewegungs-Abschnitt, voraussichtlich nähern wird, falls die anschließende Bewegung keine andere Geschwindigkeit erfordert
• Abfahrts-Richtung bedeutet:
  • diejenige Richtung, in die sich ein Werkzeug vom Zielpunkt einer vorgesehenen Bewegung des Werkzeuges, also eines Bewegungs-Abschnitts, voraussichtlich entfernen wird, falls die nachfolgende Bewegung keine andere Abfahrts-benötigt
• Anfahrts-Geschwindigkeit bedeutet:
  • diejenige Geschwindigkeit, mit der sich ein Werkzeug vom Zielpunkt einer vorgesehenen Bewegung des Werkzeuges, also einem Bewegungs-Abschnitt, voraussichtlich entfernen wird, falls die anschließende Bewegung keine andere Geschwindigkeit erfordert
• Schwingungs-Modell bedeutet:
  • mathematisches Modell zur Berechnung des Schwingungsverhaltens eines Bauteil
• Belastungs-Modell bedeutet:
  • mathematisches Modell zur Berechnung auftretender Belastungen an einem Bauteil
• zeitlicher Vorlauf bedeutet:
  • in Zeiteinheiten angegebener Vorlauf, etwa des Beginns eines vorgesehenen Bewegungs-Abschnittes vom momentanen Zeitpunkt aus örtlicher Vorlauf bedeutet:
  • in Längeneinheiten angegebener Vorlauf, etwa des Beginns eines vorgesehenen Bewegungs-Abschnittes vom momentanen Standpunkt des betreffenden Bauteils, beispielsweise des Werkzeuges eines Roboters, aus
• Stopp-Sequenz bedeutet:
  • Teil-Datensatz der das abbremsen eines Bauteils, insbesondere des Werkzeuges des Rabatt das bis zum Stillstand beschreibt von der Geschwindigkeit und Richtung, die das Werkzeug normalerweise am Ende dieses Bewegungs-Abschnittes besitzt; die Stopp-Sequenz ist i.d.R. Teil der Abschnitts-Bewegung-Daten
• Bewequnqs-Grundtyp bedeutet:
  • eine Bewegung die immer aus den gleichen Bewegung-Abschnitten in der gleichen Reihenfolge zusammengesetzt ist, beispielsweise Umsetz-Bewegung: „Anfahren - greifen - Anheben - Querverfahren - Absenken- Loslassen“

Definitions of terms used in this description:

• Work order means:
  • Description of a movement and/or activity for a robot. Order data means: data set that reflects this description in the form of digital data
• Optimization parameters means:
  • the parameter to be optimized in a work order, for example time,
  • which is needed to carry out the work order
• Accompanying parameter means:
  • Parameters that describe the circumstances surrounding the work order and
  • influence the work order itself
  • Environment parameters means:
  • • Parameters that describe the environment, in particular properties of the environment in which the work order is carried out, for example the load capacity or the vibration behavior of parts involved in the work order, be it the robot or the application environment
• Movement means:
  • (intended) movement of a robot, in particular its tool movement data means:
• Data record that reflects this description in the form of digital data. Control command means:
  • concrete control commands for the individual drives in a robot raw movement data means:
  • Movement data that in this form is not yet suitable for determining exact control commands for the robot drives
• Movement section means:
  • Part of a movement
• Section Movement Data means:
  • Data set that reflects this description in the form of digital data
• Start criterion for movement section means:
  • a criterion, usually specified in time or location, from which a movement section should be completed
• Machine learning means:
  • Training methods for an artificial intelligence, in particular its artificial neural network using training data
• Inconsistency means:
  • Contradiction between the situation in the application environment at the time of execution of an intended movement or a movement segment and the response variables provided by the AI for this purpose
• Prioritization means:
  • Order in which certain parameters are used, in particular optimized
• Weighting means:
  • Ratio in which various existing optimization parameters should be subjected to optimization relative to each other
• Position means:
  • the location where an object, such as a product or a tool, is located in space
• Rotation position means:
  • the rotational position at which an object, such as a product or a tool, is located in space, in particular relative to fixed spatial axes
• Spatial position means:
  • Sum of position and spatial position
• Arrival direction means:
  • the direction from which a tool is expected to approach the starting point for an intended movement of the tool, i.e. a movement section, if the intended movement does not require a different arrival direction
• Arrival speed means:
  • the speed at which a tool is expected to approach the starting point for an intended movement of the tool, i.e. a movement section, if the subsequent movement does not require a different speed
• Departure direction means:
  • the direction in which a tool is expected to move away from the target point of an intended movement of the tool, i.e. a movement section, if the subsequent movement does not require any other departure
• Approach speed means:
  • the speed at which a tool is expected to move away from the target point of an intended movement of the tool, i.e. a movement section, if the subsequent movement does not require a different speed
• Vibration model means:
  • mathematical model for calculating the vibration behavior of a component
• Load model means:
  • mathematical model for calculating the loads that occur on a component
• lead time means:
  • Lead time specified in time units, for example the start of a planned movement section from the current point in time. Local lead time means:
  • Lead time specified in units of length, such as the beginning of an intended movement section from the current position of the component in question, for example the tool of a robot
• Stop sequence means:
  • Partial data set that describes the braking of a component, in particular the tool of the discount, until it comes to a standstill from the speed and direction that the tool normally has at the end of this movement section; The stop sequence is usually part of the section movement data
• Bewequnqs basic type means:
  • a movement that is always composed of the same movement sections in the same order, for example transfer movement: “Approach - grab - raise - move transversely - lower - release”

c) Embodiments

• 1a: ein Anwendungs-System mit Robotern in der Aufsicht,
• 1b: das Anwendungs-System der 1a in Transport-Richtung des Produkt-Bandes,
• 2a-d: Prinzip-Darstellungen von Bewegungs-Abschnitten und zugehörigen Bewegungs-Abschnitts-Datensätzen
• 3: ein Ablaufschema für den Vorberechnungs-Prozess,
• 4: ein Ablaufschema für reale Arbeits-Aufträge,
• 5: ein Ablaufschema für reale Arbeits-Aufträge mit Einbringungs-Stellen der Förder-Geschwindigkeit.

Embodiments according to the invention are described in more detail below by way of example. Show it:

• 1a : an application system with robots in supervision,
• 1b : the application system of the 1a in the transport direction of the product belt,
• 2a-d : Principle representations of movement sections and associated movement section data sets
• 3 : a flow chart for the pre-calculation process,
• 4 : a flowchart for real work orders,
• 5 : a flowchart for real work orders with delivery points of the conveying speed.

The 1a, b show a robot application system with a robot road 100, in which several robots are located along the product belt 101, which can be moved in the transport direction 1 are arranged one behind the other in the transport direction X.

The robots 1 should each grab a product P on the container belt 101, lift it off the container belt 101, move to the nest and place it next to it in a predetermined nest of a container such as a box K on a carriage 102 and are controlled for this purpose using the control method according to the invention

In addition to this application environment 100 in the form of a robot road 100, the robot application system includes an application control 100*, which in this case controls both the individual robots 1 and the other moving parts of the robot road 100, in particular Container belt 101 and the carriage 102, controls and is also in data communication with the scanner 103 mounted at a fixed position, for example above the container belt 101, under which the products P pass on the container belt 101 and which of them Position on the container belt 101 still upstream of the transfer area - i.e. the area in the transport direction X in which the transfer robots 1 work - is determined and reported to the application control 100 *.

Serial robots 1 are shown here as robots 1 - which is essential for the implementation of the invention - which are suspended in the middle above the container belt 101 on a crossbar 104 which extends across the container belt 101 in the transverse direction Y with their robot Base 6 are attached. The upper arm 2 of the robot 1 can be pivoted about an upright, in particular vertical, axis 2 'relative to the robot base 6 and at the free end of the upper arm 2, a forearm 3 of the robot 1 is attached so that it can pivot about an upright, in particular vertical pivot axis 3' .

At the free end of the forearm 3 there is a lifting column 4 as a robot hand 4, which can be moved in height relative to the forearm 3, at the lower free end of which a suction device 5 is shown as a tool 5.

The lifting column 4 can be moved in height relative to the forearm 3 and can be pivoted about an upright, in particular vertical, pivot axis 4 '.

The robot 1 is dimensioned so that in the transverse direction Y it can reach both positions on the carriage 102 located in its work area and all transverse positions on the container belt 101.

Furthermore, the robot application system includes a pre-calculation computer (pre-PC) for pre-calculating optimized section movement data, as data sets from given exemplary work orders, in this case conversion processes or movement sections BA from such conversion Occurrence.

For example, with the in 2 In the transfer processes shown, the lifting movement and/or the setting down movement and/or the approximately horizontal displacement movement are each treated as such a separate movement section BA1 to BA3.

The robot application system also includes an artificial intelligence (Kl), which is trained with the exemplary work orders, i.e. movement sections, determined by the pre-calculation computer (pre-PC) and the exemplary optimized movement data calculated for this purpose a robot 1 or all robots 1 of the robot application system.

As in 1b shown, for a transfer process a product P must be lifted from the container belt 101 after being gripped, shifted over the container belt 101 with the help of the robot 1 and there by lowering in one of the application controls 100* predetermined nest, for example in a cardboard box K on a carriage 102 moved in the work area of this robot 1.

The 2a until d show in simplified representations of the principle such a transfer movement in several variants of the movement path used, the transfer movement being divided into several movement sections BA, in the 2a until 2c is divided into three movement sections BA1 to BA3 (lifting, moving, lowering), of which the middle movement section BA2 is an approximately horizontal movement section, which in practice, see in particular 1b , is usually significantly longer compared to raising and lowering.

The arrival of the tool 5 is also shown at the starting point S and at the destination point Z of the entire moving movement, whereby the direction of the arrow corresponds to the arrival direction and the length of the arrow corresponds to the arrival speed - and also at the destination point Z the transfer -Movement the departure of the sucker 5.

In 2a It is assumed that at the starting point S and at the destination point Z of the transfer movement, the suction cup 5 is at rest, and the raising and lowering movements run vertically and the traversing movement runs approximately horizontally.

Above the 2a The associated section movement data ABD1 to ABD3 are symbolically represented in their state stored in the data buffer in such a time order that the subsequent data record, for example AWD2, begins at the time of the regular end of the previous data record, for example ABD1.

A stop sequence is attached to the regular end of each data record ABD1 to ABD3, which is executed if there is no new data record in the data buffer following the end of the regular data record.

Out of 2a It becomes immediately clear that this is not the optimal movement path, simply because of, for example, braking at the end of the lifting movement and then only accelerating in the horizontal direction for the traversing movement in BA2.

When moving according to 2 B This is partially remedied in that the lifting movement merges into the horizontal traversing movement in an arc, i.e. a horizontal acceleration towards the target point Z takes place from the beginning of BA1.

2 B also shows that at the starting point S the vacuum cleaner 5 approaches from the top left, so - depending on, for example, the suction power of the vacuum cleaner 5 - the horizontal movement component of the incoming vacuum cleaner 5 at the starting point S for gripping the product P is not necessarily reduced to zero must be done when the vacuum cleaner 5 moves further to the right from the starting point S.

The same applies at destination point Z.

2c shows a similar situation 2 B , which differs from the fact that the vacuum cleaner 5 approaches its starting point S from the top right before the sales movement begins. In order not to have to completely brake the horizontal movement component of the vacuum cleaner 5 to zero at the starting point S, the vacuum cleaner 5 leaves the starting point S to the left, i.e. in the opposite direction from the target point Z, which may seem nonsensical at first glance, because of the However, the maintained horizontal speed component at the starting point S can bring a time advantage and can result in an overall optimized transfer movement.

2d shows a movement with arrival and departure similar to that 2 B , however, the transition from the raising movement BA1 to the lowering movement BA3 takes place directly and without an intermediate horizontal movement section, which is compared to the movement path according to 2a and 2 B can also bring time advantages.

• Der Vorberechnungs-Rechner (Vor-PC) benötigt als Eingabegrößen beispielhafte Arbeits-Aufträge AA, die u.a. einen zurückzulegenden Bewegungs-Abschnitt BAumfassen, die vorzugsweise von einem Arbeits-Auftrags-Generator-Modul (Beispiel-Generator-Modul) erzeugt werden und dem Vor-PC zur Verfügung gestellt werden.

In the flowchart of the 3 The pre-calculation process through which optimized movement data is calculated is shown:

• The pre-calculation computer (pre-PC) requires exemplary work orders AA as input variables, which include, among other things, a movement section BA to be covered, which are preferably generated by a work order generator module (example generator module) and the pre -PC will be provided.

This determines optimized section movement data ABD for such a movement section BA according to deterministic principles, i.e. usually through classical calculation using concrete calculation algorithms.

Both the description of the movement section BA and the section movement data ABD are entered as training data into the artificial neural network (ANN) of an artificial intelligence (KL) and thus the ANN using the training unit of the AI trained until the AI is in a fully trained state.

4 shows a flowchart in the specific application environment 100, in which the trained AI is then part of the robot application system in addition to the robot application environment 100.

After starting the application control 100*, its real work order generator module (real generator module) - which can be constructed in the same way as the example generator module in the pre-calculation process, i.e. an identical generator - Module can be - based on user input, such as switching on the robot application system 100 with work orders AA stored there, a real work order and enters its movement sections BA as query sizes into the trained AI.

This outputs supposedly optimized raw section movement data RABD as response variables, which flow into a movement data module (data module), which is able, on the one hand, to receive these response variables from the AI and, above all, the desired ones To generate movement data, especially with control commands contained therein or in the form of control commands for the Drives of the robot with which the movement section can be realized.

The data module can forward this raw section movement data RABD to a stop sequence generator module (stop module) in order to generate a stop sequence for the end of the section movement data set.

From the data module, the raw section movement data RABD can be transferred directly to a data buffer - if they are of good enough quality to be used directly as section movement data ABD - or a first post-processing module in between ( 1. Post-module), in which the movement data from the AI is subjected to post-processing, in particular a plausibility check and/or any inconsistencies found compared to the robot application environment 100 are eliminated or inaccuracies are eliminated, and only from there are transferred to the data buffer in which the buffer management module (manage module) stores this section movement data record ABD in the correct order and, if necessary, sorts the data records.

By means of a buffer readout module (readout module), which is preferably also part of the data buffer, the corresponding movement data record ABD is read from the data buffer and the application controller when called up by the application controller 100* 100* handed over for implementation in the application environment 100.

In the practical application of the section movement data ABD to an application environment 100 such as a robot road 100, in which the starting point S and/or the destination point Z of a movement section BA or a larger movement is not at rest, but is constantly moving, such as the product P lying on a permanently running, in particular constantly running, container belt 101 and to be moved in a robot line 100, the transport speed of this, for example, receiving surface must become notorious.

• Das Förderband-Steuer-Modul (F-Steuer-Modul) gibt die bisherige und aktuelle Transport-Geschwindigkeit an ein Förder-Geschwindigkeits-Abschätz-Modul (F-Abschätz-Modul), welches in der Lage ist, die Förder-Geschwindigkeit, also die Transport-Geschwindigkeit, auch für in der Zukunft liegende Zeitpunkte abzuschätzen.

How this is done is shown in the flowchart 5 shown in which the right branch of the flow chart according to 4 is added:

• The conveyor belt control module (F-control module) gives the previous and current transport speed to a conveyor speed estimation module (F-estimation module), which is able to determine the conveyor speed, i.e the transport speed can also be estimated for points in the future.

The F-estimation module forwards these estimates for one or more future points in time to the real generator module, which can already take the estimated transport speed into account when formulating its work orders AA.

The F-estimation module also sends its estimate to the data buffer, in particular its management module and/or its readout module, which outputs the section movement data ABD, in particular including or in the form of control commands.

If these are passed to a 2nd post-processing module (2nd post-module), the 2nd post-module also receives an estimate of the future transport speed from the F-estimation module for the planned time of execution of these control commands , which is now significantly less distant from the time of estimation than in the first estimate

In particular, the 2nd post-module can request a 2nd estimate of the transport speed from the F-estimation module for the now relatively precisely known execution time of the control command.

If this 2nd estimate differs by more than one tolerance value from the 1st estimate of the transport speed originally received from the real generator module, the 2nd subsequent module is able to take this difference into account by appropriately improving the control system. Commands that the second module then passes on to the application controller 100*.

REFERENCE SYMBOL LIST

1

robot

2

upper arm

2'

Pivot axis

3

forearm

3'

Pivot axis

4

Hand, lifting column

4'

Pivot axis

5

Tool, vacuum cleaner

6

Robot base

7 8 9 10

Transport direction

11

Transverse direction

12

vertical

100

Application environment, packaging machine, robot road

100*

Control, application control

101

Product band

102

Sleds

103

scanner

104

Crossbar

105

Travel rail

K

Cardboard box, outer packaging

P

product

AA

Work order

Readout module

Buffer readout module

B.A

Movement section

ABD

Section movement data

Data module

Motion data module

F-control module

Conveyor belt control module

F-estimation module

Conveying speed estimation module

Generator module

Work order generator module

AI

artificial intelligence

KNN

artificial neural network

Post-module

Post-processing module

Ref module

Buffer reference value generator module

Stop module

Stop sequence generator module

Manage module

Buffer management module

Pre-PC

Pre-calculation calculator

S

Starting point

Z

Target point

Claims (20)

Method for controlling the movement of a real robot (1) used in a (real) application environment (100) such as a packaging machine (100) by controlling the drives of the relatively movable parts of the robot (1), characterized in that A) exemplary movement sections (BA) are created from a large number of exemplary work orders and the order data describing them, for which the optimal movement data based on at least one predetermined optimization parameter (A6) is in the form of section sections. Movement data (ABD) are determined in a pre-calculation process, for which - apart from the start parameters in the form of the start position and start rotational position - as well as the target parameters in the form of the target position and target rotational position of the tool many - accompanying parameters are provided. (A8) B) the exemplary section movement data (ABD) is entered as training data into an artificial intelligence (AI) with at least one artificial neural network (ANN), - the AI is trained with it, C) in the application -Environment when a work order (AA) appears with one or more movement sections (BA) - the order data is entered into the trained AI as query variables, - the response variables received by the AI in response as section movement data (ABD ) or raw section movement data (RABD) can be further used for this at least one movement section (BA), D) the section movement data (ABD) is provided with a temporal and/or local or other start criterion in a data buffer are stored, E) when the start criterion is reached in the order data of a job, in particular of the robot in question, the robot carries out the movement section (BA) by controlling its drives using control commands that are in the section movement data (ABD) are included. Procedure according to Claim 1 , characterized in that - the pre-calculation process is carried out outside the application environment in a separate pre-calculation environment (define), - in particular before the first commissioning of the application environment or a new tool or a new robot in the application -Environment, - in particular the pre-calculation process is carried out using machine learning by an AI. Method according to one of the preceding claims, characterized in that the determination of control commands for the drives from the section movement data takes place in step C). Method according to one of the preceding claims, characterized in that between step C) and step D) in a post-processing step N) - the possibly not yet exact response variables are post-processed into exact section movement data (ABD), - in particular in control commands for the drives. Procedure according to Claim 4 , characterized in that the post-processing is carried out taking into account existing inconsistencies between the response variables and the real conditions in the application environment and/or the work order to be fulfilled. Method according to one of the preceding claims, characterized in that in step A) -, the pre-calculation process is carried out deterministically, and/or - as an optimization parameter, the minimization of the movement time required to complete the movement section (BA). , is specified. Method according to one of the preceding claims, characterized in that in step A) when specifying several optimization parameters, a weighting or prioritization is specified among the several optimization parameters. Method according to one of the preceding claims, characterized in that in step A) the accompanying parameters are provided - arrival speed and/or arrival direction of the tool (5) at the starting position (S) and/or - Departure speed and/or departure direction of the tool (5) from the target position (Z). Method according to one of the preceding claims, characterized in that environmental properties are provided as accompanying parameters, such as - elasticity of the drives and/or - vibration behavior of the system, in particular of the robot (1) and/or - load limit values, in particular for Bearing points and linear guides, especially of the robot (1). Procedure according to Claim 9 , characterized in that the vibration behavior is provided by - storing a vibration model for the application environment, or - creating a vibration model for the application environment based on entered, in particular constructive, data of the application environment. Procedure according to one of the Claims 9 or 10 , characterized in that the load limit values are provided by - storing a load model for the application environment, or - creating a load model for the application environment based on entered, in particular constructive, data of the loaded parts of the Application environment. Method according to one of the preceding claims, characterized in that in step B) the AI is considered to be sufficiently trained and the training is ended if - when order data from the example data of step A) is entered as query sizes to the AI, - the response variables received from the AI are within a predetermined tolerance range around the movement section data (ABD) that were calculated from this order data in step A). Method according to one of the preceding claims, characterized in that in step C) the response variables can also contain area information as movement data (ABD). Method according to one of the preceding claims, characterized in that in step D) the section movement data (ABD) is stored in the data buffer with a temporal and/or local advance. Method according to one of the preceding claims, characterized in that in step D) the section movement data (ABD) for a movement section (BA) in the data buffer at the - temporal or local - end an optional stop sequence for stopping the Tool (5) includes. Method according to one of the preceding claims, characterized in that in step E) in the event that there is no movement data for a subsequent movement section (BA) for the end of a movement section (BA) being carried out, the Robot (1) is stopped according to the in the stop sequence contained in the movement data of the movement section (BA) being carried out. Method according to one of the preceding claims, characterized in that - at least one basic movement type is defined as a movement section for the robot in the application environment, - in particular all movement sections (BA) in step A) have one of these basic movement types can be subsumed, - and / or - in particular all the movement sections (BA) described by the movement data generated in step D) can be subsumed under one of these basic movement types. Method according to one of the preceding claims, characterized in that the assumed transport speed of the tapes serving as a pick-up point and/or as a storage point a) either already when determining the movement data in step A) as one of the environmental parameters is taken into account, b) or only after the output variables from the AI in step C), at the latest when determining the control commands for the drives in step E), - in particular according to a) the assumed transport speed is taken into account and at the beginning of the real movement section (BA) is compared with the real transport speed and, if the difference exceeds a tolerance limit, the control commands are recalculated taking the difference into account. Robot application system for carrying out the method according to one of the preceding claims, with - an application environment (100), in particular a packaging machine (100), for example in the form of a robot line (100), comprising - at least one robot (1 ), - an application control (100*) for controlling the movable parts of the application environment (100), in particular the drives of the movably connected parts of the at least one robot (1) relative to one another, characterized by - a pre-calculation computer, in which movement sections (BA) of the robot (1) are defined from exemplary order data and optimized movement data are deterministically calculated - an artificial intelligence (AI) with at least one artificial neural network (ANN) and a training algorithm , which is able to train artificial intelligence (AI) with the help of machine learning models of the exemplary movement sections (BA) and the optimized movement data deterministically calculated from them - in particular according to one of the preceding method claims. Robot application system Claim 19 , characterized in that the application control comprises - a work order generator module (generator module), which is able, for example based on user input or randomly, to create exemplary, concrete work orders (AA). to create each individual robot (1) and enter it into the trained AI as a query size, and/or - a movement data module (data module) which is able to receive response sizes from the AI and use them to create movement data (ABD ), in particular with or in the form of control commands for the drives of the robot, and / or - a 1st post-processing module (post-module) in order to post-process the movement data (ABD) generated by the movement data module if necessary , for example to eliminate inconsistencies with the real application environment, especially in the relevant movement section (BA), and / or - a buffer reference value generator module (ref module and / or - a stop sequence generator -Module (stop module), which is able to generate a stop sequence for a movement section data set (ABD), and / or - a buffer management module (manage module), which is in the Is able to organize the introduction, storage and, if necessary, sorting and output of section movement data (ABD), in particular data sets (ABD), in the buffer, and / or - a buffer readout module (readout module), which is able to read out section movement data (ABD), in particular data setting (ABD), from the buffer, and / or - a conveyor belt control module (F-control module), which controls the corresponding conveyors for products and/or containers, its conveyor belts or other types of conveyor, controls, and/or - conveyor speed estimation module (F-estimation module), which is able to determine the speed of the conveyor at defined times or functional states of the to estimate the application environment in the future, and/or - a 2nd post-processing module (2nd Post-module) to post-process the movement data (ABD) output or read from the data buffer, especially in the case of a difference between the speed assumed when creating this movement data (ABD) and a currently measured or now easier to estimate conveying speed.

Images