Abstract: A control system and a control method for controlling physical entities to complete tasks within a shared environment. Use is made of a trained resource safety model to predict whether future resource levels of the physical entities satisfy a safe resource level condition, such as a minimum resource level, given previous resource levels and a selection of behaviours for the physical entities. If a respective physical entity is predicted to have a future resource level which does not satisfy the safe resource level condition, the selected behaviour may be modified or replaced, for example by a behaviour which is predicted by the resource safety model to satisfy the safe resource level condition.

Abstract: A method for training a machine learning model to recognize an object topology of an object from an image of the object. The method includes: obtaining a 3D model of the object; determining a descriptor component value for each vertex of the grid; generating training data image pairs each having a training input image and a target image. The target image is generated by determining the vertex positions in the training input image; assigning the descriptor component value determined for the vertex at the vertex position to the position in the target image; and adapting at least some of the descriptor component values assigned to the positions in the target image or adding descriptor component values to the positions of the target image.

Abstract: A method for operating a multi-agent system including multiple robots. Each robot cyclically carries out the following: starting from an instantaneous system state, ascertaining possible options, the options defining actions via which a transition from an instantaneous system state to a subsequent system state may be achieved; for each possible option, ascertaining action costs for carrying out an action indicated by the option; carrying out an auction, the action cost values ascertained for each option being taken into account by each of the other robots; and executing an action that corresponds to one of the options as a function of all cost values ascertained or received for the option in question, the action costs for an option taking into account an empirical parameter that is a function of costs for past actions, which have already been carried out and which are associated with the option, of the multiple robots.

Abstract: A method for controlling a robot to pick up an object in various positions. The method includes: defining a plurality of reference points on the object; mapping a first camera image of the object in a known position onto a first descriptor image; identifying the descriptors of the reference points from the first descriptor image; mapping a second camera image of the object in an unknown position onto a second descriptor image; searching the identified descriptors of the reference points in the second descriptor image; ascertaining the positions of the reference points in the three-dimensional space in the unknown position from the found positions; and ascertaining a pickup pose of the object for the unknown position from the ascertained positions of the reference points.

Abstract: A device and method for controlling a robotic device. The method includes: training a control model, which includes a parameter model and an object model, including: providing for each initial state-target state pair of a plurality of initial state-target state pairs a control state sequence, including states and transition states, each transition state being assigned a set of task parameters; ascertaining a set of state transition-state-state transition triples, and for each: adapting the parameter model so that the parameter model ascertains a probability distribution for each task parameter from the set of task parameters, which is assigned to the state transition following the state, adapting the object model so that the object model ascertains for each object a probability distribution for the state of the object; and controlling the robotic device with the control model using the trained parameter model and the trained object model.

Abstract: A method for controlling a robot. The method includes providing demonstrations for performing each of a plurality of skills; training from the demonstrations, a robot trajectory model for each skill, each trajectory model is a hidden semi-Markov model having one or more initial states and one or more final states; training, from the demonstrations, a precondition model for each skill comprising, for each initial state, a probability distribution of robot configurations before executing the skill, and a final condition model for each skill comprising, for each final state, a probability distribution of robot configurations after executing the skill; receiving a description of a task, the task includes performing the skills of the plurality of skills in sequence and/or branches; generating a composed robot trajectory model; and controlling the robot according to the composed robot trajectory model to execute the task.

Abstract: A method for controlling a robot device. The method includes providing a selection model and executing multiple instances of a task, including, in each execution, when a function of the robot device needs to be selected to perform the task instance, checking whether the selection model provides a selection of a function and, if yes, controlling the robot device to perform the function selected by the selection model and if no, receiving user input indicating a selection of a function, selecting a function according to the selection indicated by the user input, controlling the robot device to perform the function selected according to the selection indicated by the user input and training the selection model according to the selection indicated by the user input.

Abstract: A method of training a robot system for manipulation of objects, the robot system being able to perform a set of skills, wherein each skill is learned as a skill model, the method comprising: receiving physical input from a human trainer, regarding the skill to be learned by the robot; determining for the skill model a set of task parameters including determining for each task parameter of the set of task parameters if a task parameter is an attached task parameter, which is related to an object being part of said kinesthetic demonstration or if a task parameter is a free task parameter, which is not related to a physical object; obtaining data for each task parameter of the set of task parameters from the set of kinesthetic demonstrations, and training the skill model with the set of task parameters and the data obtained for each task parameter.

Abstract: A method for controlling a robotic device. The method includes providing demonstrations for carrying out a skill by the robot, each demonstration including a robot pose, an acting force as well as an object pose for each point in time of a sequence of points in time, ascertaining an attractor demonstration for each demonstration, training a task-parameterized robot trajectory model for the skill based on the attractor trajectories and controlling the robotic device according to the task-parameterized robot trajectory model.

Abstract: A method for planning a manipulation task of an agent, particularly a robot. The method includes: learning a number of manipulation skills wherein a symbolic abstraction of the respective manipulation skill is generated; determining a concatenated sequence of manipulation skills selected from the number of learned manipulation skills based on their symbolic abstraction so that a given goal specification indicating a given complex manipulation task is satisfied; and executing the sequence of manipulation skills.

Abstract: A method for training a machine learning model to recognize an object topology of an object from an image of the object. The method includes: obtaining a 3D model of the object; determining a descriptor component value for each vertex of the grid; generating training data image pairs each having a training input image and a target image. The target image is generated by determining the vertex positions in the training input image; assigning the descriptor component value determined for the vertex at the vertex position to the position in the target image; and adapting at least some of the descriptor component values assigned to the positions in the target image or adding descriptor component values to the positions of the target image.

Abstract: A method for controlling a robot to pick up an object in various positions. The method includes: defining a plurality of reference points on the object; mapping a first camera image of the object in a known position onto a first descriptor image; identifying the descriptors of the reference points from the first descriptor image; mapping a second camera image of the object in an unknown position onto a second descriptor image; searching the identified descriptors of the reference points in the second descriptor image; ascertaining the positions of the reference points in the three-dimensional space in the unknown position from the found positions; and ascertaining a pickup pose of the object for the unknown position from the ascertained positions of the reference points.

Abstract: A device and method for controlling a robotic device. The method includes: training a control model, which includes a parameter model and an object model, including: providing for each initial state-target state pair of a plurality of initial state-target state pairs a control state sequence, including states and transition states, each transition state being assigned a set of task parameters; ascertaining a set of state transition-state-state transition triples, and for each: adapting the parameter model so that the parameter model ascertains a probability distribution for each task parameter from the set of task parameters, which is assigned to the state transition following the state, adapting the object model so that the object model ascertains for each object a probability distribution for the state of the object; and controlling the robotic device with the control model using the trained parameter model and the trained object model.

Abstract: A method for operating a multi-agent system including multiple robots. Each robot cyclically carries out the following: starting from an instantaneous system state, ascertaining possible options, the options defining actions via which a transition from an instantaneous system state to a subsequent system state may be achieved; for each possible option, ascertaining action costs for carrying out an action indicated by the option; carrying out an auction, the action cost values ascertained for each option being taken into account by each of the other robots; and executing an action that corresponds to one of the options as a function of all cost values ascertained or received for the option in question, the action costs for an option taking into account an empirical parameter that is a function of costs for past actions, which have already been carried out and which are associated with the option, of the multiple robots.

Abstract: A method for determining a movement trajectory (MT) for a movable object (a vehicle) in a rule-based trajectory planning (TP) system, TP being performed based on minimizing overall costs of a cost function (CF), the CF considering violation costs (VC) which arise for each MT section from a potential respective violation of violatable rules as to the section, the rule violation (RV) including a state/transition RV, the state RV indicating a violation of a state rule indicating an impermissible state of the object; the transition RV indicating a violation of a transition rule indicating an impermissible state transition, the state RV being assigned a time-dependent cost amount of the VC, and the transition RV being assigned a fixed, time-independent cost amount of the VC, so that overall costs for a MT for each section violating a violatable rule depend on the time-dependent/fixed cost amount assigned to the violated rule.

Abstract: A method for operating a multi-agent system that includes multiple robots, each of the robots cyclically performing the following: starting from an instantaneous system state, ascertaining possible options, the options defining actions by which a transition may be achieved from an instantaneous system state to a subsequent system state; for each of the possible options, ascertaining action costs for performing an action specified by the option; performing an auction, the action costs values ascertained for each option being taken into consideration by each of the other robots; and performing an action, which corresponds to one of the options, as a function of all cost values ascertained or received for the relevant option, the action costs for a particular option each taking an experience parameter into consideration, which is a function of costs for past actions assigned to the particular option previously carried out by the multiple robots.

Abstract: A method for operating a multi-agent system having a plurality of robots. Each of the robots execute the following method cyclically until a target system state is achieved: starting from an instantaneous system state, determining possible options where progress is made along a path of system states in a predefined, deterministic finite automaton; the options defining actions through which a transition from a current to a subsequent system state can be achieved; determining a cost value for each of the possible options to carry out an action specified by the option; performing an auction, the cost values ascertained for each option being considered by each of the remaining robots; and executing an action, which corresponds to one of the options, as a function of all of the cost values which are determined or received for the respective option.

Abstract: A control system and a control method for controlling physical entities to complete tasks within a shared environment. Use is made of a trained resource safety model to predict whether future resource levels of the physical entities satisfy a safe resource level condition, such as a minimum resource level, given previous resource levels and a selection of behaviours for the physical entities. If a respective physical entity is predicted to have a future resource level which does not satisfy the safe resource level condition, the selected behaviour may be modified or replaced, for example by a behaviour which is predicted by the resource safety model to satisfy the safe resource level condition.

Abstract: A method of training a robot system for manipulation of objects, the robot system being able to perform a set of skills, wherein each skill is learned as a skill model, the method comprising: receiving physical input from a human trainer, regarding the skill to be learned by the robot; determining for the skill model a set of task parameters including determining for each task parameter of the set of task parameters if a task parameter is an attached task parameter, which is related to an object being part of said kinesthetic demonstration or if a task parameter is a free task parameter, which is not related to a physical object; obtaining data for each task parameter of the set of task parameters from the set of kinesthetic demonstrations, and training the skill model with the set of task parameters and the data obtained for each task parameter.

Abstract: A method for planning a manipulation task of an agent, particularly a robot. The method includes: learning a number of manipulation skills wherein a symbolic abstraction of the respective manipulation skill is generated; determining a concatenated sequence of manipulation skills selected from the number of learned manipulation skills based on their symbolic abstraction so that a given goal specification indicating a given complex manipulation task is satisfied; and executing the sequence of manipulation skills.