Robert Boschgmbh

Philipp Christian Schillinger

Mathias Buerger

Andras Gabor Kupcsik

Miroslav Gabriel

Leonel Rozo

Markus Spies

Zohar Feldman

Anh Vien Ngo

Nicolai Waniek

Alexander Kuss

Marco Todescato

Meng Guo

Patrick Kesper

Hanna Ziesche

Markus Giftthaler

Christian Graf

Henning Schlueter

Akshay Dhonthi Ramesh Babu

A method of controlling a robotic device. The method includes generating a robot control model for performing a task, wherein the robot control model comprises parameters which influence the performance of the task, adjusting the parameters of the robot control model by optimizing a target function which evaluates the adherence to at least one condition with respect to the temporal progression of at least one continuous sensor signal when performing the task, and controlling the robotic device according to the robot control model in order to perform the task using the adjusted parameters.

Method for controlling a robotic device

A method for picking up an object by means of a robotic device. The method includes obtaining at least one depth image of the object; determining, for each of a plurality of points of the object, the value of a measure of the scattering of surface normal vectors in an area around the point of the object; supplying the determined values to a neural network configured to output, in response to an input containing measured scattering values, an indication of object locations for pick-up; determining a location of the object for pick-up from an output which the neural network outputs in response to the supply of the determined values; and controlling the robotic device to pick up the object at the determined location.

Method for picking up an object by means of a robotic device

A method for controlling a robot for manipulating, in particular picking up, an object. The method includes: creating an image which depicts the object; generating a manipulation-quality image from the image, in which, for each pixel which represents a point on the surface of the object, the pixel value of the pixel provides an assessment of how well the object may be manipulated at the point; recording descriptors of points of the object which should be used during the manipulation and/or of points which should be avoided during the manipulation; mapping the image onto a descriptor image; generating a manipulation-preference image by comparing the recorded descriptors of points to the descriptor image; selecting a point for manipulating the object taking into account the pixel values of the manipulation-quality image and the pixel values of the manipulation-preference image; and controlling the robot to manipulate the object at the selected point.

Method for controlling a robot for manipulating, in particular picking up, an object

A method for ascertaining object information from image data. The method includes training an agent with the aid of reinforcement learning, successively recording images according to actions that are output by the agent, after each recording, the agent obtaining information, generated from the previously recorded images, concerning the location of surface points of an object as state information, and ascertaining the object information from the recorded images with the aid of the machine learning model.

Method for ascertaining object information with the aid of image data

A robot device, a method for training a robot control model, and a method for controlling a robot device. The method for training includes: supplying an image showing object(s), to a first and second prediction model to produce a first and second pickup prediction that has, for each pixel of the image, a first and second pickup robot configuration vector with an assigned first and second success probability; supplying the first and second pickup prediction to a blending model of the robot control model to produce a third pickup prediction that has, for each pixel of the image: a third pickup robot configuration vector that is a weighted combination of the first and second pickup robot configuration vector, and a third success probability that is a weighted combination of the first and second success probability; and training the robot control model by adapting the first and second weighting factors.

Robot device, method for the computer-implemented training of a robot control model, and method for controlling a robot device

A device and a method for controlling one or more robots. The method includes: for each robot of the one or more robots, determining a labeled Markov decision process for each skill of one or more skills which the robot is able to implement, each labeled Markov decision process having a labeling function which indicates for each state of the labeled Markov decision process, whether one or more control conditions of a plurality of predetermined control conditions is/are satisfied; providing a control mission defined by a mission specification, the mission specification having a time sequence over a subset of the plurality of predetermined control conditions; and controlling the one or more robots to execute the control mission in such a way that the control conditions of states of the one or more robots contained in the mission specification are satisfied.

Device and method for controlling one or more robots

A method for controlling a robotic device, in which a composite robot trajectory model made up of robot trajectory models of the movement skills is generated for a sequence plan for a task to be carried out by the robot including a sequence of movement skills and primitive actions to be carried out, and the robot is controlled, if after one movement skill according to the sequence plan one or multiple primitive action(s) is/are to be executed before the next movement skill, by interrupting the control of the robot according to the composite robot trajectory model after carrying out the movement skill, and by executing the one or multiple primitive action(s) and then resuming the control of the robot according to the composite robot trajectory model.

Method for controlling a robotic device and robot control unit

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.

Apparatus and method for training a machine learning model to recognize an object topology of an object from an image of the object

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.

Method for operating a robot in a multi-agent system, robot, and multi-agent system

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.

Device and method for controlling a robot to pick up an object in various positions

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.

Method and system for robot manipulation planning

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.

Method for trajectory planning of a movable object

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.

Method for operating a robot in a multi-agent system, robot and multi-agent system

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.

A method for controlling a plurality of agents to complete a mission, including deriving a decomposition set of decomposition states in a set of possible states of an automaton, wherein the automaton characterizes the mission, deriving a sequence of actions to be carried out by the plurality of agents depending on the decomposition set, where each action is to be carried out by at most one of the plurality of agents.

Growing community of inventors

Renningen-Malmsheim, Germany

Philipp Christian Schillinger