WO2025002895A1 - Verfahren und system zum betreiben eines roboters - Google Patents
Verfahren und system zum betreiben eines roboters Download PDFInfo
- Publication number
- WO2025002895A1 WO2025002895A1 PCT/EP2024/066867 EP2024066867W WO2025002895A1 WO 2025002895 A1 WO2025002895 A1 WO 2025002895A1 EP 2024066867 W EP2024066867 W EP 2024066867W WO 2025002895 A1 WO2025002895 A1 WO 2025002895A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- robot
- pose
- target
- data
- basis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1628—Program controls characterised by the control loop
- B25J9/163—Program controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1656—Program controls characterised by programming, planning systems for manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1656—Program controls characterised by programming, planning systems for manipulators
- B25J9/1664—Program controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1694—Program controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Program-control systems
- G05B19/02—Program-control systems electric
- G05B19/42—Recording and playback systems, i.e. in which the program is recorded from a cycle of operations, e.g. the cycle of operations being manually controlled, after which this record is played back on the same machine
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/39—Robotics, robotics to robotics hand
- G05B2219/39298—Trajectory learning
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/39—Robotics, robotics to robotics hand
- G05B2219/39391—Visual servoing, track end effector with camera image feedback
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/40—Robotics, robotics mapping to robotics vision
- G05B2219/40519—Motion, trajectory planning
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/40—Robotics, robotics mapping to robotics vision
- G05B2219/40532—Ann for vision processing
Definitions
- the present invention relates to a method for operating a robot, which comprises multiple predictions of a robot target pose by means of data processing based at least partially on machine learning, in particular by means of a regression method and/or at least one artificial neural network, on the basis of provided image data, a method for training the data processing, and a system and a computer program or computer program product for carrying out a method described here.
- One object of the present invention is to improve the operation of a robot and/or data processing therefor based at least partially on machine learning, in one embodiment its training. This object is achieved by a method with the features of claim 1 and 6, respectively.
- a robot has at least one robot arm.
- the robot preferably the or one or more of the robot arms, has at least three, preferably at least six, in one embodiment at least seven, joints or (movement) axes, preferably rotary joints or axes, which are adjusted by, preferably motor-driven, in one embodiment electric-driven, drives of the robot or are designed to do so.
- a method for operating the robot comprises the steps: a1) providing start image data of an environment of the robot, which are assigned to a robot start pose, in one embodiment in or for which the robot start pose is generated using at least one camera and/or image processing; 2022P00048WO 2/41 Kuka Kunststoff GmbH c1) predicting a first robot target pose by means of data processing based at least partially on machine learning, in one embodiment by means of a regression method and/or at least one, preferably deep, artificial neural network (“(deep) artificial neural network”), on the basis of the provided start image data, in particular using the provided start image data as input to the data processing; d1) determining a robot target movement based on the first target pose; and e1) controlling drives of the robot to execute this robot target movement.
- the method comprises the following steps, repeated several times in one embodiment until a termination condition is reached or occurs, preferably a (sufficiently accurate) reaching of a current target pose or a detection of an error, for example a detection of inaccessibility or (insurmountable) blockage, a predetermined maximum number of attempts or the like: (each) a2) providing new image data of a, preferably the same, environment of the robot, which are assigned to a current robot pose, in one embodiment in or for the current robot start pose are generated using at least one, preferably the at least one, camera and/or image processing, this provision taking place during the execution of the (previous or most recently determined, possibly most recently updated) robot target movement; c2) predicting an updated robot target pose by means of the data processing on the basis of these provided new image data; d2) updating the robot target movement based on this updated target pose; and e2) controlling, preferably the, drives of the robot to execute the updated robot target movement, in particular instead of the previous or most recently determined robot
- the approach to the target pose is broken down into two sub-problems or sub-tasks and, during the movement of the robot, continuously, in one embodiment in parallel and/or with different clock rates, - by a (suitably trained) artificial intelligence or data processing based at least partially on machine learning, preferably a regression method and/or at least one, preferably deep, artificial neural network, current image data (and, as explained below, possibly previous image data and/or other data, in particular kinematics and/or environmental data) is taken as input, which outputs a, preferably most probable, target pose; and - by a further function, the (updated) target pose predicted by this artificial intelligence or data processing (and, as explained below, possibly kinematics data) is taken as input, which in turn outputs an (updated) robot target movement as output.
- a (suitably trained) artificial intelligence or data processing based at least partially on machine learning, preferably a regression method and/or at least one, preferably deep, artificial neural network
- current image data and, as explained below
- the robot can be moved reactively, preferably over large parts of a free workspace, for example half a meter or a whole meter.
- explicit (prior) knowledge about variable environmental conditions can be taken into account by the method, preferably the artificial intelligence or data processing, and/or (expensive) force-torque sensors can be dispensed with and/or the robot can be used or operated without expert knowledge.
- the first or updated robot target pose can in particular be a final or robot end pose that the robot should have at the end of a task or application to be carried out by it, for example at the end of a start-up process for picking up a load, at the end of a load transfer, at the end of a processing path or the like.
- the method comprises, preferably in addition to or particularly preferably instead of steps a2) - e2), the steps following steps a1) - e1), several times in one execution until a termination condition is reached or occurs, preferably a sufficiently small change in the respectively predicted new target pose compared to a previously 2022P00048WO 4/41 Kuka Kunststoff GmbH predicted new target pose or detection of an error case, for example detection of inaccessibility or (insurmountable) blockage, reaching a predetermined maximum number of attempts or the like, repeated steps: (each) a3) providing new image data of a, preferably the same, environment of the robot, which are assigned to a current robot pose, in one embodiment in which or for the current robot start pose(s) are generated using at least one, preferably the at least one, camera and/or image processing, this provision taking place in one embodiment before or after or particularly preferably during the execution of the (previous or most recently determined
- the first robot target pose or one or more of the new robot target poses can in particular be (each) a robot target pose of a next path section or time step, in particular control cycle or the like, wherein the robot approaches the first robot target pose and one or more of the new robot target poses successively one after the other in order to carry out a task or application, for example a start-up process for picking up a load, a transfer of a load, a processing path or the like.
- the present invention comprises in particular two different aspects, which are described together here and can advantageously be implemented in combination with one another or particularly advantageously also independently: A) an (appropriately trained) artificial intelligence or data processing based at least partially on machine learning, preferably a 2022P00048WO 5/41 Kuka Kunststoff GmbH regression method and/or at least one, preferably deep, artificial neural network, outputs a, preferably final or end or target pose; or B) a (correspondingly trained) artificial intelligence or data processing based at least partially on machine learning, preferably a regression method and/or at least one, preferably deep, artificial neural network, outputs a target pose for one or more next time step(s) or path section(s), preferably during a movement of the robot.
- various, preferably arbitrary, movements can advantageously be carried out during data recording for training the data processing, for example zigzag-like, spiral-like or the like, whereby a more diverse database can advantageously be obtained, since here only the end pose is important, so to speak, and the data processing or artificial intelligence is trained to predict it.
- the robot can advantageously continue to move anyway based on the last forecast.
- the forecast of the target pose can be used in particular to move the robot directly to the target pose.
- the forecast can also be used to deliberately avoid a target pose, for example if the target pose is a variable obstacle or the like.
- the data processing in one embodiment does not learn how the robot should move, but only where the target pose is.
- the data processing in one embodiment, when data is recorded to train the data processing, the movements are carried out in the way the robot should later move. If, in aspect B), the provision of new image data during operation fails in the meantime, the robot will remain stationary in one embodiment.
- the data processing advantageously learns how the robot should move.
- the method comprises steps a1), optionally b1), c1), d1) and e1) as well as the subsequent, repeatedly repeated steps a2), optionally b2), c2), d2) and e2) and 2022P00048WO 6/41 Kuka Kunststoff GmbH according to another embodiment of the present invention or aspect B), the method comprises steps a1), optionally b1), c1), d1) and e1) as well as the subsequent, repeatedly repeated steps a3), optionally b2), c3), d3) and e3) (the step of providing updated kinematics data explained below is uniformly referred to as step b2) for both aspects A), B) for a more compact presentation).
- step c1) a sequence with the first robot target pose and one or more (respectively) subsequent robot target poses is predicted by means of data processing on the basis of the provided start image data and in step d1) the robot target movement is determined on the basis of this sequence and/or in step c3) a sequence with the new robot target pose and one or more (respectively) subsequent robot target poses is predicted by means of data processing on the basis of the provided new image data and in step d3) the new robot target movement is determined on the basis of this sequence.
- yi designates a robot target pose
- yi designates a robot target pose
- the robot target movement is determined on the basis of this sequence ⁇ yi, yi+1, yi+2, ... ⁇ , preferably in such a way that the robot approaches these robot target poses one after the other.
- y can include, in particular be, the end effector pose x explained below and/or the joint coordinates q explained below.
- the updated robot target pose is predicted by means of data processing on the basis of a group or history of at least some of the previously provided image data, in a further development chronologically.
- the new robot target pose, in a further development the sequence is predicted by means of data processing on the basis of a, 2022P00048WO 7/41 Kuka Kunststoff GmbH in a further development chronological, group or history of at least some of the previously provided image data. In one embodiment, this can improve the accuracy and/or reliability of the forecast.
- step e2) new movement commands for controlling drives of the robot are determined several times (and these drives are controlled on the basis of these movement commands) before step c2) is carried out again.
- (the) drives of the robot are controlled at a higher clock rate or higher frequency compared to an update of the robot target pose on the basis of new image data, preferably also controlled at a higher clock rate or higher frequency compared to a provision of new image data.
- Control in the sense of the present invention can generally include, in particular be, regulation or control on the basis of target and fed-back actual values.
- an advantageous, for example smoother, robot target movement can be carried out and/or the execution or control of the robot target movement, in particular its precision, speed and/or reliability, can be improved.
- start kinematics data that indicate the robot start pose and/or at least one time derivative thereof, in particular a robot start speed and/or acceleration
- updated kinematics data that indicate a current robot pose and/or at least one time derivative thereof, in particular a current robot speed and/or acceleration
- the first robot target pose is predicted by means of data processing on the basis of the start kinematics data provided.
- the updated robot target pose is predicted by means of data processing on the basis of the updated kinematics data provided, in a further development on the basis of a group or history, in particular a chronological one, of at least some of the previously provided kinematics data; or - in step c3) the new robot target pose, in a further development the sequence, is predicted by means of data processing on the basis of the updated kinematics data provided, in a further development on the basis of a group or history, in particular a chronological one, of at least some of the previously provided kinematics data.
- step d1) the robot target movement is determined on the basis of the start kinematics data provided.
- the robot target movement is updated on the basis of the updated kinematics data provided, in particular on the basis of a, in particular chronological, group or history of at least some of the previously provided kinematics data; or - in step d3) the new robot target movement is determined on the basis of the updated kinematics data provided, in particular on the basis of a, in particular chronological, group or history of at least some of the previously provided kinematics data.
- steps b2), d2) and e2) are repeated several times before step c2 is carried out again, in an embodiment of steps a2) and c2), or several times - updated kinematics data which indicate the current robot pose and/or at least one time derivative thereof are provided (step b2)); 2022P00048WO 9/41 Kuka Kunststoff GmbH - the robot target movement is updated on the basis of the most recently updated target pose and also the kinematic data provided (in particular compared to this most recently updated target pose), in particular on the basis of a group of the previously provided kinematic data, in particular a chronological group (step d2)); and - (the) drives of the robot are controlled to execute this updated robot target movement (step e2)), before again - a (new) updated robot target pose is predicted by means of data processing on the basis of new image data provided (step c2)); - and if necessary, this new image data of an environment of the robot assigned to a (now
- steps b2), d3) and e3) are repeated several times in an embodiment of steps a3) and c3) before step c3) is carried out again.
- the robot target movement is updated at a higher clock rate or higher frequency on the basis of new kinematics data of the robot compared to an update of the robot target pose on the basis of new image data, possibly also compared to a provision of the new image data, and used to control the robot's drives, or the new robot target movement is determined at a higher clock rate or higher frequency on the basis of new kinematics data of the robot compared to a determination of the new robot target pose on the basis of new image data, possibly also compared to a provision of the new image data, and used to control the robot's drives.
- new image data can also be provided during the higher frequency updating of the robot target movement or determination of the new robot target movement, but preferably the updating of the robot target pose or determination of the new robot target pose, in a further development of the determination of the sequence, preferably takes place at a lower frequency than the updating of the robot target movement or determination of the new robot target movement.
- an advantageous, for example smoother, robot target movement can be carried out and/or the execution or control of the robot target movement, in particular its precision, speed and/or reliability, can be improved.
- the first robot target pose is predicted by means of data processing on the basis of, in particular, previously specified environmental data; and/or - in step c2) the updated robot target pose is predicted by means of data processing on the basis of, in particular, previously specified environmental data, preferably the environmental data used in step c1), or in step c3) the new robot target pose, in a further development the sequence, is predicted by means of data processing on the basis of, in particular, previously specified environmental data, preferably the environmental data used in step c1).
- Such predetermined environmental data can in particular comprise geometries of the environment, in particular geometries and/or poses of workpieces to be approached or transported, obstacles to be avoided or the like.
- this can improve the accuracy and/or reliability of the forecast.
- the first robot target pose is forecast by means of data processing on the basis of environmental data recorded by sensors, preferably in or for the start pose; and/or - in step c2) the updated robot target pose is forecast by means of data processing on the basis of environmental data recorded by sensors, preferably in or for the current robot pose, in particular on the basis of a group or history, in particular a chronological group, of at least some of the environmental data recorded previously by sensors, or in step c3) the new robot target pose, in a further development the sequence by means of which 2022P00048WO 11/41 Kuka Kunststoff GmbH Data processing based on environmental data recorded by sensors, preferably in or for the current robot pose, in particular on the basis of a group or history, in particular chronological, of at least some of the environmental data previously recorded by sensors.
- Such environmental data recorded by sensors can in particular include poses of workpieces to be approached or transported and/or obstacles to be avoided and/or joint and/or drive loads of the robot and/or audio data or the like.
- the sensors for (sensory) recording of the environmental data can in particular include force and/or torque sensors, distance sensors, radar sensors, microphones and the like, whereby a combination of two or more sensors or a combination of environmental data recorded (by sensors) using different sensors can be particularly advantageous. In one embodiment, this can improve the accuracy and/or reliability of the forecast.
- one or more of the robot target movements are determined taking into account constraints that can be parameterized or parameterized in a further development, in one embodiment one or more, preferably parameterized or parameterized, safety areas and/or collision avoidance, in particular self- and/or external collision avoidance. In one embodiment, the operation of the robot can thereby be improved. Additionally or alternatively, in one embodiment, one or more of the robot target movements (each) are determined on the basis of a numerical kinematic model of the robot. In one embodiment, advantageous path planning algorithms can thereby be used.
- one or more of the robot target movements are determined by means of data processing that is also at least partially based on machine learning, in a further development using Gaussian Processes, Gaussian Mixture Models, Bayesian Learning and/or at least one additional artificial neural network. In this way, advantageous movements can be carried out in one embodiment. Additionally or alternatively, in one embodiment, one or more of the robot target movements (each) comprise movement commands in an axis or joint coordinate space, in particular axis or joint angle space, of the robot, wherein in an advantageous further development, hardware limits and/or (self-)collisions and/or other restrictions such as safety areas (“safety spaces”) are taken into account.
- safety spaces safety areas
- movements can be advantageously determined or controlled and/or the determination and/or control can be improved, in particular simplified and/or accelerated.
- the robot target movements determined in step d1) and/or one or more of the robot target movements updated in step d2) (each) comprise a displacement of an end effector of the robot by at least 10 cm, preferably by at least 25 cm, in particular by at least 50 cm.
- the robot can be moved over large parts of a free workspace, for example half a meter or a whole meter, reactively or by updating the target pose.
- the provided start kinematics data and/or the updated kinematics data (each) comprise one, preferably one, two or 2022P00048WO 13/41 Kuka Kunststoff GmbH three-dimensional position and/or a, preferably one-, two- or three-dimensional, orientation of an end effector of the robot, in particular corresponding, preferably one-, two- or three-dimensional, position and/or, preferably one-, two- or three-dimensional, orientation data, hereinafter referred to as x t without restriction of generality.
- the provided start kinematics data and/or the updated kinematics data comprise joint positions of the robot, in particular corresponding joint position data or coordinates, the dimension of which preferably corresponds to the number of degrees of freedom or joints or (motion) axes of the robot, hereinafter referred to as q t without restriction of generality.
- the provided start kinematics data and/or the updated kinematics data comprise first and/or higher time derivatives of the aforementioned variables, in particular translational and/or rotational speeds and/or accelerations of the end effector and/or the joints.
- the first robot target pose and/or the updated or new robot target pose(s), in a further development the robot target poses of the sequence, comprise a, preferably one-, two- or three-dimensional, position and/or a, preferably one-, two- or three-dimensional, orientation of one or the end effector of the robot, in particular corresponding, preferably one-, two- or three-dimensional, position and/or, preferably one-, two- or three-dimensional, orientation data, hereinafter referred to without restriction of generality as x* or x i or x i+1 , ....
- the first robot target pose and/or the updated or new robot target pose(s), in a further development the robot target poses of the sequence comprise (each) joint positions of the robot, in particular corresponding joint position data or coordinates, the dimension of which preferably corresponds to the number of degrees of freedom or joints or (motion) axes of the robot, hereinafter referred to as q* or qi or qi+1, without loss of generality, .... 2022P00048WO 14/41 Kuka Kunststoff GmbH
- robot target movements can be determined particularly advantageously, in particular advantageous algorithms can be used to determine corresponding robot target movements.
- robot target poses can be determined particularly advantageously; they are particularly suitable as (part of) an input of such a target pose-predicting artificial intelligence or data processing.
- the robot start pose and/or the (respective) current robot pose is a position of the robot, in particular its joints or (motion) axes. Accordingly, in one embodiment, the start image data is assigned to a start position of the robot and/or the current robot pose is assigned to a current position of the robot (respectively).
- the robot start pose and/or the (respective) current robot pose is a, preferably one-, two- or three-dimensional, position and/or, preferably one-, two- or three-dimensional, orientation of its end effector.
- the start image data is assigned to a start position and/or orientation of the end effector and/or the current robot pose is (respectively) assigned to a current position and/or orientation of the end effector of the robot.
- steps b2) respectively updated kinematic data indicating a (respective) current robot pose and/or at least one time derivative thereof can be provided.
- the robot target movement is updated on the basis of the target pose updated most recently or in the most recently performed step c2) and also on the basis of the kinematic data updated most recently or in the most recently performed step b2), before the target pose is updated again in a new step c2) on the basis of kinematic data provided in a preceding step b2), which are preferably also used to update the robot target movement, and thus at a lower frequency than the robot target movement.
- the new robot target movement is updated in several steps d3) on the basis of the new target pose predicted last or in the last step c3) and on the basis of the kinematic data updated last or in the last step b2), before the new target pose is predicted in a new step c3) on the basis of kinematic data provided in a preceding step b2), which are preferably also used to determine the new robot target movement, and is thus determined at a lower frequency than the new robot target movement.
- the two sub-problems "prediction/updating the target pose" and "determining the target movement” can thus be solved at different frequencies and thus particularly advantageously, preferably in parallel and/or synchronized.
- the data processing is based on the image data and, if applicable, kinematic and/or environmental data.
- 2022P00048WO 16/41 Kuka Kunststoff GmbH - in step c1) at least one, preferably first, time derivative of the first robot target pose is additionally predicted and in step d1) the robot target movement is determined on the basis of this time derivative(s); and/or - in step c2) at least one, preferably first, (updated) time derivative of the updated robot target pose is additionally predicted and in step d2) the robot target movement is updated on the basis of this (updated) time derivative(s) or in step c3) at least one, preferably first, (new) time derivative of the new robot target pose, in a further development at least one, preferably first, time derivative of the robot target poses of the sequence is predicted and in step d3) the robot target movement is determined on the basis of this (new) time derivative(s).
- a time derivative of a robot target pose can in particular include, in particular be, a translational and/or rotational speed of the end effector and/or joints or axes of the robot.
- the data processing is trained according to a method described here.
- the method for operating a robot according to an embodiment of the present invention can therefore comprise a method described here for training a data processing based at least partially on machine learning for predicting robot target poses on the basis of image data or its steps.
- the training comprises the steps of: - successively carrying out movements of the robot or a demonstrator, in particular a loose end effector, end effector dummy, pointing device or the like, in each case - from a start pose to reach a, preferably into a, target pose; or 2022P00048WO 17/41 Kuka Kunststoff GmbH - from a target pose to reach a, preferably into a, start pose with - different movement trajectories; and/or - under different environmental conditions; and/or - at least once from a start pose to reach a target pose and at least once from a target pose to reach a start pose, preferably several times from a start pose to reach a target pose, preferably from different start poses to reach the same or different target pose(s), and/or several times from a target
- the demonstrator has a, preferably integrated, sensor system, with which, in a further development, poses and, in one embodiment, (assigned) time stamps are recorded. Additionally or alternatively, the pose of the demonstrator and, in one embodiment, (assigned) time stamps can be recorded using an external sensor system, in particular a tracking system or the like.
- One embodiment of the present invention is based on the idea of continuously collecting image data during (the execution of) such movements and using it to train the (target pose) artificial intelligence or target pose-predicting data processing.
- the training can at least partially take place while (further) movements are being carried out to collect (further) image data and target poses, which can improve and, in particular, accelerate training.
- One or more movements from a target pose to a start pose or against a path direction running through in normal operation can in particular improve approaching a target pose in the inventive operation of the robot in the regular path direction and/or controlling the training movements, in particular simplifying them and/or increasing precision.
- the start pose and/or the target pose are specified for one or more of the movements, preferably entered by means of an operator input (separately or in addition to assuming the pose).
- kinematics data indicating this robot pose and/or at least a time derivative thereof are collected for several of the poses assumed by the robot or demonstrator during this movement and assigned to the corresponding image data, preferably in terms of time, in one embodiment by means of corresponding time stamps or the like, and the data processing is trained on the basis of this collected kinematics data, which is preferably assigned in time to the corresponding poses or image data.
- environmental data is specified for one or more of these movements; in a further development, as already mentioned elsewhere, geometries of the environment, in particular geometries and/or poses of workpieces to be approached or transported, obstacles to be avoided or the like, and the data processing is also trained on the basis of these specified environmental data.
- environmental data is recorded by sensors; in a further development, as already mentioned elsewhere, poses of workpieces to be approached or transported and/or poses of obstacles to be avoided or the like and/or joint and/or drive loads of the robot and/or audio data or the like, and the data processing is also trained on the basis of these (sensor-) recorded environmental data, preferably temporally assigned to the corresponding poses or image data. 2022P00048WO 19/41 Kuka Kunststoff GmbH In one embodiment, this can improve the accuracy and/or reliability of the forecast.
- the start poses are identical for two or more of the movements used or utilized to train the data processing.
- the target poses are identical for two or more of the movements used or utilized to train the data processing.
- the accuracy and/or reliability of the forecast can be improved due to the different motion trajectories and/or different environmental conditions. In one embodiment, this can improve the accuracy and/or reliability of the forecast. In one embodiment, this can improve the accuracy and/or reliability of the forecast. In one embodiment, this can improve the accuracy and/or reliability of the forecast.
- the starting poses are identical and the target poses are identical, but the movements in between are different (from each other). In one embodiment, the accuracy and/or reliability of the prediction can be improved by the different movement trajectories and/or different environmental conditions.
- the robot or demonstrator reaches the respective target pose in one or more of the movements performed.
- positive examples are used to train the data processing. 2022P00048WO 20/41 Kuka Kunststoff GmbH Additionally or alternatively, in one embodiment the robot or demonstrator does not reach the respective specified target pose for one or more of the movements performed.
- negative examples are (also) used to train the data processing. This can improve the accuracy and/or reliability of the forecast in one embodiment.
- the robot or demonstrator is hand-guided for one or more of the movements performed or used to train the data processing by forces exerted on it manually; in a further development the robot is controlled accordingly.
- the robot carries out one or more of the movements used to train the data processing automatically, in a further development - with the help of automated path planning based on environmental recognition; and/or - with the help of a, in particular automated, variation - of a movement previously guided or controlled by a user; or - an automatically planned path; and/or 2022P00048WO 21/41 Kuka Kunststoff GmbH in a work assignment, in further training in a productive or production company.
- training can be improved, in particular many movements can be used and the accuracy and/or reliability of the forecast can be improved.
- the data processing is advantageously (also) (further) trained in the assignment.
- a duplicate of the forecast is further trained on the basis of the movements carried out automatically in a work assignment, in further training in a productive or production company, or the data collected during this, and it is checked whether this further trained duplicate achieves a better result than the forecast used in the work assignment, and, in one embodiment by a user, a decision is made as to whether the further trained duplicate will be used as the new forecast for further work assignments instead of the forecast previously used.
- the start and/or the new image data are generated using at least one camera guided by the robot and/or using at least one camera on the environment side and/or using image processing.
- providing image data in step a1) and/or in step a2) or a3) includes such generation.
- one or more robots are (each) equipped with at least one camera and at least one further robot moves to the corresponding pose.
- Robot-guided cameras can be used to use more significant perspectives, while cameras on the environment side can advantageously use calmer and/or more global perspectives, whereby an environment-side camera can itself be fixed in the environment or can be moved and/or rotated by a movement device separate from the robot.
- Image processing can be used to generate image data that is particularly advantageous for data processing.
- predicting a target pose includes predicting one or the one of several target poses that has the highest probability.
- the data processing in one execution determines 2022P00048WO 22/41 Kuka Kunststoff GmbH different target poses each have a probability that it is an actual (desired) target pose, and selects the one with the highest probability as the predicted target pose.
- predicting a target pose comprises outputting a target pose on the basis of an input or with an input, wherein this input or this input comprises image data, in a further development additionally kinematic data and/or environmental data.
- a system in particular hardware and/or software, in particular program technology, is set up to carry out a method described here.
- a or the system has: - means for providing start image data of an environment of the robot assigned to a robot start pose, in particular comprising at least one camera and/or image processing; - Means for predicting a first robot target pose by means of data processing based at least partially on machine learning, in particular by means of a regression method and/or at least one artificial neural network, on the basis of the provided start image data, in particular comprising the data processing; - Means for determining a robot target movement on the basis of the first target pose; and - Means for controlling drives of the robot to execute the robot target movement; and - Means for subsequently providing new image data of an environment of the robot, assigned to a respective current robot pose, repeatedly, in a further development during the execution of the robot target movement, in particular comprising the at least one camera and/or image processing; - Means for subsequently providing new image data of an environment of the robot, assigned
- a or the system additionally or alternatively comprises: - means for, when movements of the robot or a demonstrator are carried out one after the other, in each case - from a start pose to reaching a target pose; or - from a target pose to reach a start pose with different movement trajectories and/or under different environmental conditions and/or at least once from a start pose to reach a target pose and at least once from a target pose to reach a start pose, for at least one of these movements for several poses of the robot or demonstrator assumed during this movement, collecting in each case: - image data of an environment assigned to this pose; and - the respective target pose, in a further development of the sequence, for machine learning of the forecasting, in particular a corresponding (filled) data storage or a corresponding amount of data; and - means for training the data processing on the basis of these collected, mutually assigned image data and target poses.
- a system and/or a means in the sense of the present invention can be designed in terms of hardware and/or software, in particular at least one, preferably data- or signal-connected, especially digital, processing unit, especially microprocessor unit (CPU), graphics card (GPU) or the like, and/or one or more programs or program modules.
- the processing unit can be designed to execute commands that are stored as a 2022P00048WO 24/41 Kuka Kunststoff GmbH
- the program can be designed in such a way that it embodies or is capable of carrying out the methods described here, so that the processing unit can carry out the steps of such methods and thus in particular operate the robot or train the data processing.
- a computer program product can have, in particular be, a storage medium, in particular a computer-readable and/or non-volatile one, for storing a program or instructions or with a program or instructions stored thereon.
- execution of this program or these instructions by a system or a controller, in particular a computer or an arrangement of several computers causes the system or the controller, in particular the computer(s), to carry out a method described here or one or more of its steps, or the program or the instructions are set up for this purpose.
- one or more, in particular all, steps of a method described here are fully or partially computer-implemented or one or more, in particular all, steps of the method are carried out fully or partially automatically, in particular by the system or its means.
- the system has the robot and/or the data processing and/or the at least one camera and/or image processing.
- the robot preferably moves continuously during several steps e2) or e3) carried out one after the other.
- the robot's drives are continuously controlled to execute the robot's target movement, while this is continuously updated on the basis of a target pose that is continuously updated using artificial intelligence or data processing, or is already updated during the approach to a last 2022P00048WO 25/41 Kuka Kunststoff GmbH, at least one new target pose is predicted and a path section to this is planned.
- Fig. 1 shows a system according to an embodiment of the present invention
- Fig. 2 a method according to an embodiment of the present invention
- Fig. 3 an information flow in the system or method according to an embodiment of the present invention
- Fig. 1 shows a system according to an embodiment of the present invention, which has a robot with a controller 1 and a robot arm 10 with an end effector 11 and at least one camera 20 guided by the robot and/or at least one camera 21 on the environment.
- the camera 20 or 21 can be omitted and/or additional cameras guided by the robot and/or cameras on the environment can be provided and/or the robot arm can have a different configuration, for example more or fewer than the six joints or (movement) axes shown.
- Fig. 1 shows a system according to an embodiment of the present invention, which has a robot with a controller 1 and a robot arm 10 with an end effector 11 and at least one camera 20 guided by the robot and/or at least one camera 21 on the environment.
- the camera 20 or 21 can be
- a robot start pose is shown in solid lines and a robot target pose is shown in dashed lines
- a movement of the robot based on a "LIN" movement command that causes a straight line of a TCP of the robot indicated in Fig. 1 by coordinate systems in Cartesian space is shown in a dash-dotted line
- a movement of the robot based on a "CIRC” movement command that causes a circular path of the TCP in Cartesian space is shown in dash-double-dotted lines
- a movement of the robot based on a "PTP" movement command is shown in double-dash lines.
- Fig. 2 shows a method according to an embodiment of the present invention.
- step S10 For training a data processing based at least partially on machine learning to predict robot target poses based on 2022P00048WO 26/41 Kuka Kunststoff GmbH
- environmental data for example known geometries of workpieces to be handled by the robot 10 and/or obstacles to be avoided or the like, are specified for the image data.
- step S20 a movement of the robot 10 or of a demonstrator, for example only the loose end effector 11, is carried out from a starting pose to reach a target pose. Additionally or alternatively, movements from a target pose to reach a starting pose can also be carried out. The movement is carried out with different movement trajectories (cf. Fig. 1) and/or under different environmental conditions.
- step S20 for several poses assumed by the robot or demonstrator during the respective movement, image data of an environment 30 and the respective target pose are collected for machine learning of the forecasting.
- these poses or image data are temporally assigned, preferably via time stamps or the like, kinematic data that indicate the respective robot pose, and/or environmental data recorded by sensors, for example sensor data from force-torque sensors, joint torque sensors, radar sensors, audio microphones, tracking systems 22 for detecting obstacles 31 or the like, are collected.
- sensor data from force-torque sensors, joint torque sensors, radar sensors, audio microphones, tracking systems 22 for detecting obstacles 31 or the like are collected.
- S25: "Y” sensor data from force-torque sensors, joint torque sensors, radar sensors, audio microphones, tracking systems 22 for detecting obstacles 31 or the like
- the training can also take place at least partially in parallel with the collection of further data on the basis of further movements carried out.
- environmental data for example known geometries of workpieces or the like to be handled by the robot 10
- start-up data are specified in a step S110.
- a robot target pose is predicted by means of the trained data processing on the basis of the provided environmental data, start image data and start kinematic data, in a step S140 a robot target movement is determined on the basis of this first target pose, and in a step S150 drives of the robot 10 are controlled to execute the robot target movement, of which three drives are provided with the reference number 12 as an example.
- step S150 current kinematics data are provided several times, analogously to step S110, the robot target movement is updated on the basis of the first target pose and this current kinematics data, analogously to step S140, and then the drives 12 of the robot 10 are controlled to execute this updated robot target movement instead of the previously executed robot target movement.
- step S210 While the robot target movement is still being executed, in a step S210, as previously in step S110, updated kinematics data indicating the current robot pose are provided, in a step S220, as previously in step S120, new image data of the environment of the robot 10 associated with this current robot pose and sensor-detected environmental data are provided, in a step S230, as previously in step S130, an updated robot target pose is predicted by means of the trained data processing on the basis of the environmental data provided, new image data and updated kinematics data, in a step S240 the robot target movement is updated on the basis of this updated target pose, and in a step S250, as previously in step S150, the drives 12 of the robot 10 are now controlled to execute this updated robot target movement.
- step S250 current kinematics data are provided several times, analogous to step 150 or S210, the robot target movement is provided on the basis of the target pose updated in step S230, and 2022P00048WO 28/41 Kuka Kunststoff GmbH this current kinematic data and then the drives 12 of the robot 10 are controlled to execute this updated robot target movement.
- S255: "N" no termination condition is met
- S255: "Y” the system or method returns to step 210, otherwise (S255: "Y") the method is terminated (step S260).
- steps S10, S20 environmental data are specified and movement of the robot 10 or a demonstrator is carried out and image data of the environment 30 and the respective target pose are collected for machine learning of the prediction, whereby the target pose here is not the final target or end pose but the target pose approached in a next time step or a sequence with several consecutive such target poses is collected.
- these poses or image data can be temporally associated with kinematic data, preferably via time stamps or the like, which indicate the respective robot pose, and/or environmental data recorded by sensors, for example sensor data from force-torque sensors, joint torque sensors, radar sensors, audio microphones, 2022P00048WO 29/41 Kuka Kunststoff GmbH tracking systems 22 for detecting obstacles 31 or the like.
- step S30 the or, if applicable, further data processing is trained on the basis of these collected, associated image data and target poses and, if applicable, kinematics and/or environmental data, but not to predict the final target or end pose, but rather the target pose(s) to be approached in the next time step(s).
- step S100 environmental data, for example known geometries of workpieces to be handled by the robot 10 or the like, are specified in step S100, start kinematics data indicating the robot start pose are provided in a step S110, start image data of an environment 30 of the robot 10 associated with this robot start pose and sensor-detected environmental data, for example sensor data from force-torque sensors, joint torque sensors, radar sensors, audio microphones, tracking systems 22 for detecting obstacles 31 or the like (not shown) are provided in a step S120, a first robot target pose is predicted by means of the trained data processing on the basis of the environmental data, start image data and start kinematics data provided in a step S130, a robot target movement is determined on the basis of this first target pose in a step S140, and drives of the robot 10 for executing the Robot target movement is controlled, of which three drives are provided with the reference number 12 by way of example.
- start kinematics data indicating the robot start pose are provided in a step S110
- step S210 updated kinematics data indicating the current robot pose are provided
- step S220 new image data of the environment of the robot 10 associated with this current robot pose and environmental data recorded by sensors are provided
- step S230 new image data of the environment of the robot 10 associated with this current robot pose and environmental data recorded by sensors
- step S230 new image data of the environment of the robot 10 associated with this current robot pose and environmental data recorded by sensors
- step S230 new image data of the environment of the robot 10 associated with this current robot pose and environmental data recorded by sensors
- step S230 as previously in step S130
- a new robot target pose to be approached in the next time step or several consecutive such robot target poses (to be approached in successive time steps) are predicted by means of the trained data processing on the basis of the environmental data provided, new image data and updated kinematics data, in a step S240, as previously in step S150, 2022P00048WO 30/41 Kuka Kunststoff GmbH previously in step S140, a new robot target movement is determined on the basis of these new target pose(s),
- step S250 analogously to step 150 or S210, current kinematics data are provided several times, analogously to step S240, a new robot target movement is determined on the basis of the new target pose determined in step S230 and this current kinematics data, and then the drives 12 of the robot 10 are controlled to execute this new robot target movement.
- S255: "N" no termination condition is met
- the system or method returns to step 210, otherwise (S255: "Y") the method is terminated (step S260).
- the artificial intelligence or data processing predicts the current pose as the new target pose, so that the robot stops automatically.
- “has an X” does not generally imply an exhaustive list, but is a short form of “has at least one X” and also includes “has two or more X” and “has Y in addition to X”.
- the kinematic data used can also have time derivatives (dqt/dt, dxt/dt, d 2 qt/dt 2 , d 2 xt/dt 2 ,,,,).
- the respective data with a time stamp is then also collected and used in the training process.
- the exemplary embodiments are merely examples that are not intended to limit the scope of protection, the applications and the structure in any way.
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
Abstract
Description
Claims
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP24734872.5A EP4731393A1 (de) | 2023-06-26 | 2024-06-18 | Verfahren und system zum betreiben eines roboters |
| CN202480043288.2A CN121443425A (zh) | 2023-06-26 | 2024-06-18 | 用于操作机器人的方法和系统 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102023206009.4A DE102023206009B3 (de) | 2023-06-26 | 2023-06-26 | Verfahren und System zum Trainieren einer wenigstes teilweise auf maschinellem Lernen basierenden Datenverarbeitung zum Prognostizieren von Roboter-Zielposen und/oder zum Betreiben eines Roboters |
| DE102023206009.4 | 2023-06-26 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025002895A1 true WO2025002895A1 (de) | 2025-01-02 |
Family
ID=91616465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/EP2024/066867 Ceased WO2025002895A1 (de) | 2023-06-26 | 2024-06-18 | Verfahren und system zum betreiben eines roboters |
Country Status (4)
| Country | Link |
|---|---|
| EP (1) | EP4731393A1 (de) |
| CN (1) | CN121443425A (de) |
| DE (1) | DE102023206009B3 (de) |
| WO (1) | WO2025002895A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102024104640B3 (de) * | 2024-02-20 | 2025-05-15 | Kuka Deutschland Gmbh | Betreiben eines Roboters mithilfe einer Datenverarbeitung und Trainieren dieser Datenverarbeitung |
| DE102024129503A1 (de) * | 2024-10-11 | 2026-04-16 | Kuka Deutschland Gmbh | Steuern eines Roboters |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160243704A1 (en) * | 2013-10-25 | 2016-08-25 | Aleksandar Vakanski | Image-based trajectory robot programming planning approach |
| US20200086483A1 (en) * | 2018-09-15 | 2020-03-19 | X Development Llc | Action prediction networks for robotic grasping |
| US20210276188A1 (en) * | 2020-03-06 | 2021-09-09 | Embodied Intelligence Inc. | Trajectory optimization using neural networks |
| DE102021109332A1 (de) * | 2021-04-14 | 2022-10-20 | Robert Bosch Gesellschaft mit beschränkter Haftung | Vorrichtung und Verfahren zum Steuern eines Roboters zum Einsetzen eines Objekts in eine Einsetzstelle |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6644191B1 (ja) | 2018-12-26 | 2020-02-12 | 三菱電機株式会社 | ロボット制御装置、ロボット制御学習装置、及びロボット制御方法 |
| DE102019205651B3 (de) | 2019-04-18 | 2020-08-20 | Kuka Deutschland Gmbh | Verfahren und System zum Ausführen von Roboterapplikationen |
| DE102021204846B4 (de) | 2021-05-12 | 2023-07-06 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zum Steuern einer Robotervorrichtung |
| US12017355B2 (en) | 2021-06-08 | 2024-06-25 | Fanuc Corporation | Grasp learning using modularized neural networks |
| DE102021209646B4 (de) | 2021-09-02 | 2024-05-02 | Robert Bosch Gesellschaft mit beschränkter Haftung | Robotervorrichtung, Verfahren zum computerimplementierten Trainieren eines Roboter-Steuerungsmodells und Verfahren zum Steuern einer Robotervorrichtung |
| DE102022202142B3 (de) | 2022-03-02 | 2023-06-15 | Robert Bosch Gesellschaft mit beschränkter Haftung | Vorrichtung und Verfahren zum Trainieren eines maschinellen Lernmodells zum Ableiten eines Bewegungsvektors für einen Roboter aus Bilddaten |
-
2023
- 2023-06-26 DE DE102023206009.4A patent/DE102023206009B3/de active Active
-
2024
- 2024-06-18 WO PCT/EP2024/066867 patent/WO2025002895A1/de not_active Ceased
- 2024-06-18 EP EP24734872.5A patent/EP4731393A1/de active Pending
- 2024-06-18 CN CN202480043288.2A patent/CN121443425A/zh active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160243704A1 (en) * | 2013-10-25 | 2016-08-25 | Aleksandar Vakanski | Image-based trajectory robot programming planning approach |
| US20200086483A1 (en) * | 2018-09-15 | 2020-03-19 | X Development Llc | Action prediction networks for robotic grasping |
| US20210276188A1 (en) * | 2020-03-06 | 2021-09-09 | Embodied Intelligence Inc. | Trajectory optimization using neural networks |
| DE102021109332A1 (de) * | 2021-04-14 | 2022-10-20 | Robert Bosch Gesellschaft mit beschränkter Haftung | Vorrichtung und Verfahren zum Steuern eines Roboters zum Einsetzen eines Objekts in eine Einsetzstelle |
Also Published As
| Publication number | Publication date |
|---|---|
| DE102023206009B3 (de) | 2024-08-01 |
| EP4731393A1 (de) | 2026-04-29 |
| CN121443425A (zh) | 2026-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3623116B1 (de) | Verfahren und vorrichtung zur kollisionsfreien bewegungsplanung eines manipulators | |
| WO2025002895A1 (de) | Verfahren und system zum betreiben eines roboters | |
| EP3523168B1 (de) | Verfahren und vorrichtung zur fahrdynamikregelung für ein kraftfahrzeug | |
| DE102019205651B3 (de) | Verfahren und System zum Ausführen von Roboterapplikationen | |
| DE102019006725B4 (de) | Steuereinrichtung und Steuersystem | |
| DE102008062622A1 (de) | Verfahren und Vorrichtung zur Befehlseingabe in eine Steuerung eines Manipulators | |
| EP3771952B1 (de) | Verfahren zur automatischen bewegung eines arbeitsgeräts sowie arbeitsgerät | |
| EP3037219B1 (de) | Sicherer roboter mit bahnfortschrittsvariablen | |
| WO2016087590A1 (de) | Verfahren zur bewegungssimulation eines manipulators | |
| EP0508202A1 (de) | Einrichtung zur Führung des Endeffektors eines Roboters längs einer Sollbahn | |
| EP2208584B1 (de) | Verfahren zur Steuerung von Industrierobotern | |
| EP3771522A1 (de) | Verfahren und manipulationssystem zur manipulation eines objekts durch einen roboter mittels vektorfelder | |
| EP3313627B1 (de) | Abfahren einer vorgegebenen bahn mit einem roboter | |
| EP3752327A1 (de) | Koordinierungsanlage, handhabungseinrichtung und verfahren | |
| DE69207018T2 (de) | Verfahren zur Führung eines Roboterarmes durch definieren von Ersatzstrecken | |
| EP2671691A2 (de) | Verfahren und Vorrichtung zum Steuern einer Manipulatoranordnung | |
| WO2019201873A1 (de) | Verfahren zur erkennung einer intention eines partners gegenüber einer mehrgliedrigen aktuierten kinematik | |
| DE102022207800A1 (de) | Verfahren zum Trainieren einer Steuerungsrichtlinie zur Steuerung eines technischen Systems | |
| DE102024104640B3 (de) | Betreiben eines Roboters mithilfe einer Datenverarbeitung und Trainieren dieser Datenverarbeitung | |
| EP3710900B1 (de) | Verfahren und system zum vorgeben bzw. lernen eines roboterbefehls | |
| EP3720663B1 (de) | Betreiben eines roboters | |
| DE102020103852B4 (de) | Erzeugen und Optimieren eines Steuerprogramms für einen Robotermanipulator | |
| WO2024008232A1 (de) | Verfahren zur dynamischen erkennung von ratcheting bei einem kollaborativen roboter mittels künstlicher intelligenz und dynamischer kompensation der trajektorien | |
| DE102023210548B3 (de) | Steuern eines Roboters | |
| EP3712724A1 (de) | Automatisierungsanordnung, verfahren zum betrieb der automatisierungsanordnung sowie computerprogramm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24734872 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2024734872 Country of ref document: EP Effective date: 20260126 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024734872 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024734872 Country of ref document: EP Effective date: 20260126 |
|
| ENP | Entry into the national phase |
Ref document number: 2024734872 Country of ref document: EP Effective date: 20260126 |