System and method of automating a process

Abstract

The present disclosure relates to a computer-implemented method (100) of automating a process of at least a first subsystem for implementation in a robot, the method comprising. Obtaining (101) process-steps indicative of an operation of said at least first subsystem. Further, translating (102) said process-steps to a current data set comprising generalized 5 parameters and obtaining (103), from a data source, previous data sets of generalized parameters associated with said process-steps. Moreover, the method determines (104) at least one robot resource required to perform said process-steps and provides (105) an automated process model. The process model being configured for implementation in a robot comprising said at least one robot resource. Wherein said automated process model is based 10 on said current data set and previous data sets, wherein said automated process model is, when executed in said robot, configured to: cause the robot to perform said process-steps.

Description

[0001] SYSTEM AND METHOD OF AUTOMATING A PROCESS

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to a system and method of automating a process of at least a first subsystem for implementation in a robot.

[0004] BACKGROUND ART

[0005] Generally robots that are adapted to perform specific processes are mainly directed to perform a predefined set of tasks. Thus, their operation can usually only be varied within the set of tasks.

[0006] To allow a robot to perform a particular process or action, they are conventionally programmed by guiding or off-line programming. Some industrial robots are programmed by guiding a robot point to point through the phases of an operation, with each point stored in the robotic control system.

[0007] Even though programming robots for processes is a conventional task, there is recently a desire to automate and prepare processes obtained from at least a first robot or device for implementation in a second robot in an efficient manner. This requires a system to take in information from at least one other device / robot and be able to in an efficient manner prepare it for implementation into another suitable system.

[0008] In order to automate and prepare tasks obtained from different types of devices / robots for implementation into another system, there is a need of a solution that can handle a large variety of devices / robots of different types (e.g. linear robot movements, tools, cameras, lights or different types of sensors) and in an efficient manner automate and prepare the processes for implementation in a robot that is suitable to perform the process.

[0009] Thus, there is room for systems for automation processes in the present art to explore the domain of providing an improved system that allows for the automation and preparation of tasks of at least a first device / robot for implementation into a second robot in an efficient manner, specifically there is a need of flexibility and efficiency of such a system. Even though some currently known solutions work well in some situations it would be desirable to provide a system that fulfils requirements relating to flexibility and efficiency when automating and preparing tasks for implementation in another system.

[0010] SUMMARY

[0011] It is therefore an object of the present disclosure to provide a method and a system to mitigate, alleviate or eliminate one or more of the above-identified deficiencies and disadvantages.

[0012] This object is achieved by means of a method and a system as defined in the appended claims.

[0013] In accordance with the disclosure there is provided a method and a system according to claim 1 and claim 13.

[0014] The present disclosure provides a computer-implemented method of automating a process of at least a first subsystem for implementation in a (preferably an industrial robot) robot, the method comprising the steps of obtaining process-steps indicative of an operation of said at least first subsystem. Further, the method translates / transforms said process-steps to a current data set (i.e. a data set of generalized parameters) comprising generalized parameters. Moreover the method obtains, from a data source, previous data sets of generalized parameters associated with said process-steps. Further, the method determines at least one robot resource required to perform said process-steps. Furthermore an automated process model is provided for implementation in a robot comprising said at least one robot resource, wherein said process model is based on said current data set and previous data sets and when the automated process model is executed in said robot, it's configured to cause the robot to perform said process-steps (which it can then do without the need of any interaction from users / operators). Thus, it's configured to cause the robot to perform said process-steps in an automated manner.

[0015] A benefit of the method in accordance with the present disclosure is that it allows for automating processes performed by subsystems for implementation in a robot that can perform these. Thus, the method provides an efficient and convenient way to obtain and automate process steps from a subsystem, and provide it for implementation in a robot. Further, by translating process steps the method functions in a model-based manner allowing it to operate with different kind of subsystems in an efficient manner.

[0016] The process-steps may be obtained from at least a first and a second subsystem. The process steps may be values indicative of process-steps. Thus, the method may obtain process steps from several different sub-systems, automate these, and provide it to a robot. Further, the automated process model may coordinate the process-steps of the at least first and the second subsystem. In other words, the method may be provided such that process-steps of at least a first and a second subsystem are performed in a coordinated manner i.e. so that the robot they are implemented in performs them cooperatively. The process steps may be in the form of e.g. a source code, sensor data (e.g. photo time-stamp data and photo settings of a camera stored in a memory thereof) or any other form.

[0017] Preceding / during the step of providing an automated process model, the method may execute a simulation for said process model, the simulation performing said process-steps over a time period and upon f u If i II i ng / com pleti ng / finishi ng the execution of said simulation, provide said automated process model for implementation in a robot.

[0018] Thus, the method may simulate (either virtually or live) and upon fulfilling the simulation the automated process model may be provided for implementation in the robot. A benefit of this is that it allows for testing and verifying that the process model works and can be implemented in a robot.

[0019] Further, a simulation may be executed for a plurality of process models, wherein after the step of fulfilling, the method evaluates each of said plurality of process models subject to at least one predetermined parameter and selects, based on the evaluation, one of said plurality of process models for implementation in a robot. In other words, the method may identify the best matching simulation for the process to be automated and selects said best matching simulation. The parameters may be for instance time to fulfill simulation, power of robot required to fulfil simulation, or any other suitable parameter. Thus, the method may provide a plurality of process models, simulate these and choose the most appropriate one based on how the simulation is performed subject to said predetermined parameters. An advantage of this is that the automated process model will be chosen depending on its performance in simulation. The step of translating / transforming may comprise matching said process-steps towards previous data sets to determine the generalized parameters. Thus, the method may obtain process steps from a subsystem (or an intermediary system), match them towards previous data sets of e.g. other process-steps previously performed and upon matching, the method may determine what type or process-steps that are obtained and these process-steps may subsequently be translated to generalized parameters. The translation may be performed in a translating module configured to obtain process-steps of a plurality of pre-determined formats and transform said process steps to generalized parameters. A benefit of translating processsteps to generalized parameters is that previously stored (i.e. previous data sets) parameters may be utilized in order to optimize a new process to be automated.

[0020] Preceding the step of translating, the method may comprise the steps of classifying the process-steps. Moreover the method may input the process steps into a corresponding translating module of a plurality of translating modules, depending on the classification of the process-steps. The step of classifying allows the method to in an efficient manner sort the steps to improve the efficiency in the translating process and to generate generalized parameters for a variety of subsystems of different types.

[0021] The generalized parameters may comprise coordinates projected in a coordinate system, matrices, distances or images. Thus, the method may utilize different types of generalized parameters alone or in combination.

[0022] The method may further comprise the step of transmitting the automated process model to a robot for implementation in said robot.

[0023] The step of providing may be performed by an orchestrating unit providing logical functions for each of said process-steps, preferably Boolean functions. Thus, the logical functions may allow a robot which executes the automated process model to perform said process steps autonomously.

[0024] The at least one robot resource may be a robotic arm with one degree of freedom, a robotic arm with two degrees of freedom, a robotic arm with three degrees of freedom, a robotic arm with four degrees of freedom, a robotic arm with five degrees of freedom, a robotic arm with six degrees of freedom, a measurement device for measuring a physical quantity, a sensing device, an automated guided vehicle or any other suitable robot resource. In other words, the method may be able to cause any of the mentioned robot resources to perform the process-steps in an automated manner.

[0025] There is also provided a computer-readable storage medium storing one or more programs configured to be executed by one or more control circuitry of an electronic device, the one or more programs including instructions for performing the method according to the present disclosure. The electronic device may be a robot.

[0026] Further, there is provided a system for automating a process of at least a first subsystem for implementation in a robot, the system comprising control circuitry and at least one robot comprising at least one robot resource. The control circuitry is configured to: obtain process-steps indicative of an operation of at least a first subsystem; translate said process-steps to a current data set comprising generalized parameters; obtain, from a data source, previous data sets of generalized parameters associated to said process-steps; determine at least one robot resource required to perform said process-steps; provide an automated process model for implementation in one of said robots comprising said at least one robot resource, wherein said process model is based on said current data set and previous data sets, wherein said automated process model is, when executed in said robot, configured to: cause the robot to perform said process-steps.

[0027] The system and the method of the present disclosure allows for a model-based coordination of subsystems for controlling and manoeuvring robot resources automatically. Thus, the system and method in accordance with the disclosure can enable a robot to perform operations in a flexible and optimized manner. Further, by utilizing generalized parameters in a model-based manner, the system can be utilized even if an operation to be automated is new to the system. The general manner of providing automated process models allows for an improved way of providing automated process models for any type of process-steps.

[0028] BRIEF DESCRIPTION OF THE DRAWINGS In the following, the disclosure will be described in a non-limiting way and in more detail with reference to exemplary embodiments illustrated in the enclosed drawings, in which:

[0029] Figure 1 illustrates schematically a computer-implemented method 100 of automating a process / operation of at least a first subsystem for implementation in a robot in accordance with some implementations of the disclosure;

[0030] Figure 2 illustrates schematically a computer-implemented method 100 of automating a process / operation of at least a first subsystem for implementation in a robot in accordance with some implementations of the disclosure;

[0031] Figure 3 schematically illustrates a system 1 in accordance with some implementations of the present disclosure;

[0032] Figure 4 illustrates schematically and sequentially providing an automated process model to a robot from at least a first subsystem;

[0033] Figure 5 illustrates schematically in an exemplary manner the translating step 102 of the method 100 in accordance with some aspects of the translating step 102; and

[0034] Figure 6 illustrates schematically a first and a second simulation 15, 16 in an exemplary manner;

[0035] DETAILED DESCRIPTION

[0036] In the following detailed description, some embodiments of the present disclosure will be described. However, it is to be understood that features of the different embodiments are exchangeable between the embodiments and may be combined in different ways, unless anything else is specifically indicated. Even though in the following description, numerous specific details are set forth to provide a more thorough understanding of the provided disclosure, it will be apparent to one skilled in the art that the embodiments in the present disclosure may be realized without these details. In other instances, well known constructions or functions are not described in detail, so as not to obscure the present disclosure. In the following description of example embodiments, the same reference numerals denote the same or similar components.

[0037] Figure 1 illustrates a computer-implemented method 100 of automating a process / operation of at least a first subsystem for implementation in a robot, the method 100 comprising the steps of obtaining 101 process-steps indicative of an operation of said at least first subsystem. Further, the method comprise the step of translating 102 said process-steps to a current data set comprising generalized parameters. Further, the method comprises obtaining 103, from a data source, previous data sets of generalized parameters associated with said process-steps. The step of obtaining 103, may be performed simultaneously as the step of translating 102, or preceding the step of translating 102. Thus, in some aspects, the method may obtain 103 previous sets of generalized parameters associated with said process-steps so to allow for a more efficient translating based on the previous sets. Further, determining 104 at least one robot resource required to perform said process-steps. Further, providing 105 an automated process model for implementation in a robot comprising said at least one robot resource, wherein said automated process model is based on said current data set and previous data sets, wherein said automated process model is, when executed in said robot, configured to cause the robot to perform said process-steps.

[0038] The method 100 may obtain process-steps from at least a first category of subsystem and a second category of subsystem. A first type may be e.g. a gripper and a second type may be an imaging device. The different categories may be defined by having different functions / hardware.

[0039] The term "process-steps" may refer to a set of or a plurality of process-steps that jointly form an operation.

[0040] The term "data source" may refer to a collection of data stored and accessible from an electronic device. The data source (shown in Figure 3) in accordance with the present disclosure may be a data base or a cloud data source ran on a cloud computing platform, the data source may also be a local data source. The previous data sets may be a training data set.

[0041] The term "subsystem" may refer to any parts of devices that can be controlled e.g. arms, grippers, imaging devices etc. The term "robot" may refer to a programmable machine comprising robot resources.

[0042] The term "robot resource" may refer to at least one subsystem connected to / operable by a robot.

[0043] The term "generalized parameter" may refer to parameters that are compatible with an internal model(s) utilized in the method 100 to provide automated process models. Thus, the method 100 translates / transforms the obtained process-steps into generalized parameters to allow for input into the internal model(s) so to provide a desired output, which within the context of the present disclosure is an automated process model.

[0044] The term "automated process model" may refer to a model that is configured to, when implemented in a robot, cause the robots resources to automatically (and e.g. jointly) perform a process, or be prepared to automatically perform a process.

[0045] The generalized parameters may comprise coordinates projected in a coordinate system, functions, matrices, distances, images or any other suitable type of generalized parameters. By translating / transforming obtained process-steps into generalized parameters the method 100 is allowed to make use of stored (and trained) data (previous data sets) gained from previously provided automated process models when providing an automated process model for a current data set. Thus, the method 100 is constantly improved in terms of efficiency, speed and accuracy. Further, the method 100 is allowed to be compatible with a plurality of different types of subsystems having different functions.

[0046] The generalized parameters are also stored in said data source in the form of previous data sets. The previous data sets may be trained previous data sets e.g. trained by a learning algorithm.

[0047] The process-steps may be obtained from at least a first and a second subsystem. Thus, the method 100 may coordinate processes of at least a first and a second subsystem. The first and second subsystems may be of different types. Further, the subsystems may be independent subsystems of different devices, or in the same device.

[0048] Figure 2 schematically illustrates the method 100 in accordance with some implementations of the present disclosure. Figure 2 illustrates that preceding / during the step of providing 105 an automated process model, the method 100 may form 104a at least one automated process model and execute 104b a simulation for said process model. The simulation performs said process-steps over a time-period, and upon fulfilling (Le. successfully completing / validating the simulation), the execution of said simulation, the method 100 may provide said automated process model for implementation in a robot. Thus, after the simulation is completed the automated process model may be implemented in a robot. If the simulation is not successfully completed then the method 100 may re-iterate the step of forming 104a. The execution of the simulation may be performed virtually or live.

[0049] As also shown in Figure 2, in some implementations of the present disclosure, the method 100 may execute 104b the simulation for a plurality of process models. After fulfilling said simulation, the method 100 may evaluate 104c each of said plurality of process models subject to at least one predetermined parameter and select 104d, based on the evaluation, one of said plurality of process models for implementation in a robot. The predetermined parameter may be e.g. time. In other words, the method 100 may select the process model that executed the simulation in the shortest time.

[0050] As further shown in Figure 2, the step of translating 102 may comprise matching 102a said process-steps towards previous data sets of generalized parameters to determine generalized parameters of the process-steps. Thus, the method 100 may be configured to match the process-steps towards previous data sets and identify the best matching data sets relative the obtained process-steps. Further, the process-steps may be translated / transformed to generalized parameters.

[0051] Figure 2 further illustrates that preceding / during the step of translating 102, the method 100 may comprise the steps of classifying 101a the process-steps and depending on the classification of the process-steps inputting 101b the process-steps into a corresponding translating module depending on the classification of the process steps. Thus, depending on the classification of the process-steps the process-steps may be inputted into a corresponding translating module that is configured to translate process-steps of a specific type. For example, there may be robot process-steps and device process-steps that may be inputted 101b into a robot translating module and a device translating module respectively. Each module may then utilize specific translation functions or models in order to translate the process-steps into generalized parameters. Thus, by classifying the process-steps it improves the matching process to obtain the generalized parameters. Each module may be directed to translate a specific predetermined type of format.

[0052] Figure 2 also illustrates that the method 100 may further comprise the step of transmitting 106 the automated process model to said robot for implementation in said robot.

[0053] The step of providing 105 may be performed by an orchestrating unit (shown in Figure 3) providing logical functions for each of said process-steps, preferably Boolean functions.

[0054] The at least one robot resources may be a robotic arm with one degree of freedom, a robotic arm with two degrees of freedom, a robotic arm with three degrees of freedom, a robotic arm with four degrees of freedom, a robotic arm with five degrees of freedom, a robotic arm with six degrees of freedom, a measurement device for measuring a physical quantity, a sensing device, an imaging device, an industrial tool or any other suitable robot resource. A robot resource may further in some implementations be several subsystems combined.

[0055] Figure 3 schematically illustrates a system 1 for automating a process of at least a first subsystem for implementation in a robot 2, the system 1 comprising, control circuitry 3 and at least one robot 2 comprising at least one robot resource 4. The control circuitry 3 is configured to: obtain process-steps indicative of an operation of at least a first subsystem; translate said process-steps to a current data set comprising generalized parameters; obtain, from a data source, previous data sets of generalized parameters associated to said process-steps; determine at least one robot resource 4 required to perform said process-steps; provide an automated process model for implementation in one of said robots 2 comprising said at least one robot resource 4, wherein said process model is based on said current data set and previous data sets, wherein said automated process model is, when executed in said robot 2, configured to: cause the robot 2 to perform said process-steps.

[0056] As illustrated in Figure 3, the control circuitry 3 may comprise one or more memory devices 5, an orchestrating unit 7 and at least one translating module 8. The orchestrating unit 7 may provide logical functions and the translating module 8 may translate process steps to generalized parameters. The control circuitry 3 may further comprise other modules / components for carrying out the method 100 in accordance with any aspect of the present disclosure such as a machine learning component (not shown).

[0057] The memory device 5 may comprise any form of volatile or non-volatile computer readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by each associated control circuitry 3. Each memory device 5 may store any suitable instructions, data or information, including a computer program, software, an application including one or more of logic, rules, code, tables, etc. and / or other instructions capable of being executed by the control circuitry 3 and, utilized. Memory device 5 may be used to store any calculations made by control circuitry 3 and / or any data set having generalized parameters or any data received via the translating modules of the present disclosure. In some embodiments, each control circuitry 3 and each memory device 5 may be considered to be integrated. The previous data sets may be retrieved to the memory device 5 by means of wireless communication or be stored on the memory device 5. The control circuitry 3 may be integrated with the robot 2.

[0058] Further, the control circuitry 3 may be integrated in an electronic device (e.g. see Fig.4) such as a computer, tablet device, or any other integrated device configured to provide and transmit an automated process model to the robot 2. It should be noted that the system 1 of the present disclosure may comprise additional modules for carrying out the method 100, e.g. a classifying module, a matching module, a obtaining module, transmitting module etc. Further, different modules may be integrated.

[0059] Each memory device 5 may also store data that can be retrieved, manipulated, created, or stored by the control circuitry 3. The data may include, for instance, previous data sets, current data sets, generalized parameters, training data, trained learning algorithms (and / or internal models, components, or any data utilized in said trained learning algorithms). The control circuitry 3 may comprises a machine learning (not shown) component that based on previous data sets and current data sets may implement a trained learning algorithm for providing, by the orchestrating unit 7, an automated process model in accordance with any embodiment of the present disclosure. Any data obtained from the control circuitry 3 may be stored in one or more data sources 6. The one or more data sources 6 can be connected to the control circuitry by a high bandwidth field area network (FAN) or wide area network (WAN), or through any other type of communication network. The data source 6 and the memory unit 5 may be integrated in some implementations.

[0060] The circuitry 3 may include, for example, one or more central processing units (CPUs), graphics processing units (GPUs) dedicated to performing calculations, and / or other processing devices. The memory device 5 may comprise one or more computer-readable media and can store information accessible by the control circuitry 3, including instructions / programs that can be executed by the control circuitry 3.

[0061] The instructions, which may be executed by the control circuitry 3, may comprise instructions for implementing the method 100 according to any aspects of the present disclosure.

[0062] The network may be any type of communication network, such as a local area network (e.g. intranet), wide area network (e.g. Internet), cellular network, or some combination thereof. Communication between control circuitry 3, memory device 5, robot 2, data sources and remote entities can be carried via a network interface (not shown) using any type of wired and / or wireless connection, using a variety of communication protocols (e.g. TCP / IP, HTTP, SMTP, FTP), encodings or formats (e.g. HTMF, XMF), and / or protection schemes (e.g. VPN, secure HTTP, SSF).

[0063] Figure 4 illustrates in an exemplary manner at least a part of the method 100 and the system 1 in accordance with some implementations of the present disclosure. Figure 4 illustrates that a first subsystem 8 and a second subsystem 8' (of different types) perform an operation / process. Namely the first subsystem 1 is configured to move boxes from a first container to a second container, further the second subsystem 8' captures images of the first container to determine the number of boxes left in the first container.

[0064] In accordance with the process performed by said first and second subsystem 8, 8', the method 100 disclosed in Figure 1, may be performed by an electronic device 9 so to obtain the process-steps performed by said first and second subsystem 8, 8'. The electronic device 9 may obtain the process-steps by manual input from a user or by electronic communication e.g. with control circuitry of said subsystem or any combination thereof. Further, said electronic device 9 may translate said process-steps to generalized parameters. Further, the electronic device 9 may obtain from a data source 6 previous data sets of generalized parameters associated to said process-steps. Moreover, the electronic device 9 provides an automated process model for implementation in a robot 2 comprising the required at least one robot resource 4 for performing the process-steps, wherein said automated process model is based on said current data set and previous data sets. Thus, in Figure 4, the automated process model is implemented 110 in a robot 2 comprising both the first and the second subsystem 8, 8' as resource 4, wherein said process-steps for each subsystem 8, 8' are coordinated to be performed in a cooperative / joint manner by said robot 2. Accordingly, the method 100 may allow a process to be automated and implemented 110 in a second robot 2.

[0065] Figure 5 illustrates in an exemplary manner at least a part of the method 100 and the system 1 in accordance with some implementations of the present disclosure showing the step of translating 102. Figure 5 shows that the electronic device 9 obtains process-steps (current data sets 12) from a first and a second subsystem 8, 8', the process steps being of different types, namely type A and type B which may be classified by the electronic device 9. Further, the electronic device 9 matches 102a the process-steps towards previous data sets 13 of the same or corresponding classification to determine / form generalized parameters. The step of classification 102 and matching 102a may be performed in a translating module (see Fig.4) or different translating modules each configured for a specific classification of process-steps.

[0066] Upon generating generalized parameters, the electronic device 9 may provide the automated process model based on the current data set 12 and previous data sets 13. Thus, the previous data sets may facilitate the forming of an automated process model. In other words, the step of providing (step 105 in the method shown in Figure 1) may combine the current data set and previous data sets to provide an optimized automated process model. The term "optimized" may refer to generating the automated process model having the most functional / effective form as possible. A trained learning algorithm may preferably be incorporated in the step of providing. Figure 6 illustrates a first and a second simulation 15, 16 in an exemplary manner. Preceding / during the step forming 104a (shown in Fig.2) at least one automated process model the method may execute simulations 15, 16 for a two of process models. After fulfilling the simulation for at least one of said plurality of process models, the method 100 may evaluate 104c each of said plurality of process models subject to at least one predetermined parameter and select 104d, based on the evaluation, one of said plurality of process models for implementation in a robot. Thus, if e.g. the predetermined parameter is time for moving the boxes from the first container to the other, then the automated process model associated to the second simulation 16 may be chosen since the second simulation 16 moves the boxes faster in-between the containers (gripping two boxes at a time). The different simulations may be formed from combining the current and previous data sets. The previous data sets may have previously similar process-steps that have been performed in a different manner, thus knowledge / functions from previous data may be utilized when providing new automated process models.

[0067] It should be noted that the Figures 4-6 have the purpose of further describing the disclosure as presented herein accompanied with advantages thereof. It should be noted that the Figures 3- 6 are based on embodiments for a disclosing purpose, however it is not limited to said embodiments and may be varied within the present disclosure.

Claims

CLAIMS1. A computer-implemented method (100) of automating a process of at least a first subsystem for implementation in a robot, the method comprising the steps of: obtaining (101) process-steps indicative of an operation of said at least first subsystem; translating (102) said process-steps to a current data set comprising generalized parameters; obtaining (103), from a data source, previous data sets of generalized parameters associated with said process-steps; determining (104) at least one robot resource required to perform said process-steps; providing (105) an automated process model for implementation in a robot comprising said at least one robot resource, wherein said automated process model is based on said current data set and previous data sets, wherein said automated process model is, when executed in said robot, configured to: cause the robot to perform said process-steps.

2. The method (100) according to claim 1, wherein the process-steps are obtained from at least a first and a second subsystem.

3. The method (100) according to claims 2, wherein, said automated process model coordinates the process-steps of the at least first and the second subsystem.

4. The method according to any one of the claims 1-3, wherein preceding the step of providing (105) an automated process model, the method (100): forms (104a) at least one automated process model; executes (104b) a simulation for said at least one process model, the simulation performing said process-steps over a time period; and upon fulfilling the execution of said simulation, provide said automated process model for implementation in a robot.The method (100) according to claim 4, wherein the simulation is executed for a plurality of process models, wherein after fulfilling the simulation for at least one of said plurality of process models, the method (100): evaluates (104c) each of said plurality of process models subject to at least one predetermined parameter; selects (104d), based on the evaluation, one of said plurality of process models for implementation in a robot. The method (100) according to any one of the claims 1-6, wherein the step of translating (102) comprises matching (102a) said process-steps towards previous data sets to determine the generalized parameters. The method according to any one of the claims 1-7, wherein preceding the step of translating, the method comprises the steps of; classifying (101a) the process-steps; inputting (101b) the process steps into a corresponding translating module depending on the classification of the process-steps. The method (100) according to any one of the claims 1-8, wherein the generalized parameters comprises coordinates projected in a coordinate system, matrices, distances or images. The method (100) according to any one of the claims 1-8, further comprising the step of: transmitting (106) the automated process model to said robot for implementation in said robot. The method (100) according to any one of the claims 1-9, wherein the step of providing (105) is performed by an orchestrating unit providing logical functions for each of said process-steps, preferably Boolean functions.1711. The method (100) according to any one of the claims 1-10, wherein said at least one robot resources are a robotic arm with one degree of freedom, a robotic arm with two degrees of freedom, a robotic arm with three degrees of freedom, a robotic arm with four degrees of freedom, a robotic arm with five degrees of freedom, a robotic arm with six degrees of freedom, a measurement device for measuring a physical quantity, a sensing device, an imaging device, an industrial tool or any other suitable robot resource.

12. A computer-readable storage medium storing one or more programs configured to be executed by one or more control circuitry (3) of an electronic device, the one or more programs including instructions for performing the method (100) of any of claims 1-11.

13. A system (1) for automating a process of at least a first subsystem for implementation in a robot (2), the system (1) comprising: control circuitry (3); at least one robot (2) comprising at least one robot resource (4); wherein the control circuitry (3) is configured to: obtain process-steps indicative of an operation of at least a first subsystem; translate said process-steps to a current data set comprising generalized parameters; obtain, from a data source (6), previous data sets of generalized parameters associated to said process-steps; determine at least one robot resource (4) required to perform said process-steps; provide an automated process model for implementation in one of said robots (2) comprising said at least one robot resource (4), wherein said process model is based on said current data set and previous data sets, wherein said automated process model is, when executed in said robot (2), configured to: cause the robot (2) to perform said process-steps.

Images