EP4536447A1 - Erhöhung der greifrate - Google Patents
Erhöhung der greifrateInfo
- Publication number
- EP4536447A1 EP4536447A1 EP23728325.4A EP23728325A EP4536447A1 EP 4536447 A1 EP4536447 A1 EP 4536447A1 EP 23728325 A EP23728325 A EP 23728325A EP 4536447 A1 EP4536447 A1 EP 4536447A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- gripping
- determining
- image
- depth
- probability
- 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.)
- Withdrawn
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
- B25J9/1694—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
-
- 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
- B25J9/1612—Program controls characterised by the hand, wrist, grip 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
- B25J9/1628—Program controls characterised by the control loop
- B25J9/163—Program controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- 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
- G05B2219/39484—Locate, reach and grasp, visual guided grasping
-
- 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
- G05B2219/40053—Pick 3-D object from pile of objects
-
- 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
- G05B2219/40563—Object detection
-
- 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
- G05B2219/40564—Recognize shape, contour of object, extract position and orientation
Definitions
- Claim 11 provides a system for operating and/or monitoring a machine, in particular a multi-axis machine under protection and/or a robot.
- Claim 12 protects a computer program or a computer program product. The subclaims relate to advantageous further training.
- a method for gripping with 6 degrees of freedom, in particular with the aid of a gripping system includes at least one fixed depth camera and at least one gripping device.
- the method includes capturing image data of a scene with the at least one depth camera.
- the method includes determining a depth image based on the image data.
- the method includes determining a 6D pose of at least one known object based on the depth image.
- the at least one known object is an object to be gripped by the gripping system.
- Determining a CAD object representation is intended here in particular to mean inserting, in particular replacing, a CAD object in the place of a (known) object recognized on the basis of the depth image, in particular with the recognized pose.
- the determination includes generating a 3D geometric modeling of the at least one recognized object, in particular all recognized objects (based on the depth image), and is in particular additionally based on the depth image.
- a CAD object representation can contain edge models, surface models, Volume models or the like, in particular a combination of in particular the same and / or different model types (edge models, surface models, volume models or the like).
- a gripping device can be a robotic device.
- a gripping device can preferably be understood herein as a robot with an end effector, in particular a gripper.
- the gripper is designed for workpiece handling and works in particular mechanically, vacuum-based, magnetically and/or adhesively.
- a workpiece in particular an object to be gripped, can be manipulated by the gripping device, in particular by the end effector, in particular via frictional connection, material connection and/or positive connection.
- a “grab probability” should preferably be understood herein as the probability of success (or failure) of the grasp.
- the gripping probability can be a number between zero and one, which in particular can include zero and one.
- the procedure does not apply to purely planar handles.
- the method does not apply to vertical handles with degrees of freedom, especially three Degrees of freedom, in two directions, for example x and y, and a rotation, for example around z.
- the method can in particular carry out a CAD matching (“CAD matching”) or include it in determining the gripping probability.
- CAD matching CAD matching
- the method can be used in one embodiment to select the most promising grip or to decide whether it is possible to grip
- the method may further comprise determining a color image based on the CAD data.
- the method can further include determining textures and/or shadows.
- the determination of the color image, or the textures and/or shadows, can be carried out in one embodiment using ray tracing.
- color image can preferably also refer to a gray image (with gradations of gray tones). The further description of embodiments or examples with color images should not be construed as limiting.
- the method may further comprise: determining a color image if the at least one depth camera is an RGB depth camera based on the image data, in particular determining textures and/or shadows in the color image.
- determining a depth image can additionally be based on the color image.
- more information can advantageously be used to determine a depth image, in particular an improved and/or more detailed depth image can be determined.
- a gripping probability can additionally be determined based on the color image.
- the color image can provide additional information regarding the grip pose or the success of the grip position (grab probability). In one embodiment, this makes it possible for the success of a grip to be determined more precisely and/or better, in particular with greater precision. In this way, in one embodiment it can be achieved that the gripping process to be determined and/or controlled by the method becomes more robust.
- determining the gripping probability may include stacking the depth image and the depth image with the CAD object representation, in particular also the color image, into a tensor (stacked; from English: “to stack”), in particular in such a way that all images have the same height and width.
- a tensor stacked; from English: “to stack”
- five channels are included, in particular 2 depth channels and 3 color channels.
- the depth image and the depth image with CAD object representation can be rendered in just one image with just one depth channel.
- the determination of the depth image, the determination of the CAD object representation and/or the determination of the color image can take place from a perspective of at least one predetermined gripping pose of the gripping device on the object to be gripped.
- predetermined gripping poses can usually be determined using known methods, preferably using grasp sampling, in a step preceding the method.
- the perspective of the at least one predetermined gripping pose of the gripping device usually does not correspond to the camera perspective of the at least one depth camera. This usually results in that for a perspective that deviates from the visual axis of the depth camera, there is usually less depth information in the image data, in other words, fewer points with depth information in a point cloud than if a perspective of the gripping pose corresponds to the visual axis of the depth camera (at least essentially ) matches.
- the method may further comprise gripping the object to be gripped, in particular gripping the object to be gripped with the highest probability of gripping, further in particular comprising gripping and placing the object, in particular the object with the highest probability of gripping.
- this makes it possible for the object to be gripped, in particular the object with the highest probability of gripping, to be selected efficiently and/or more efficiently and in particular for a process of the gripping system to be accelerated and/or improved.
- the method can accelerate a decision for an object to be gripped and thereby in particular optimize the efficiency of a gripping sequence for the objects to be gripped.
- the determination of a gripping probability can further be based on known, in particular tabular, data of the gripping system, the gripping device and/or the object to be gripped.
- this tabular data can include information about at least one gripping pose, a gripping ellipse, in particular its size, and in particular other available information. This advantageously makes it possible for a gripping probability to be determined more precisely and/or better than, in particular, without (known) data. Furthermore, in one embodiment, this makes it possible for a gripping process of the gripping system to be carried out in particular faster and/or more precisely.
- the method may include obtaining images from the perspective of the at least one gripper component.
- the images from the perspective of the at least one gripper component can be determined or rendered from the point cloud of the depth information (image data), in particular from the depth image, and/or the CAD object representation. This makes it possible, in particular in combination with the depth image and/or the CAD object representation and/or the color image, for a surface structure at the gripping position to be assessed more precisely and/or better.
- the method in particular the determination of a gripping probability, can be carried out by a machine learning algorithm, in particular by an artificial neural network.
- a machine learning algorithm in particular by an artificial neural network.
- a system for operating and/or monitoring gripping, in particular gripping and placing, of a multi-axis machine, in particular a robot is provided.
- the gripping system has a gripping device, in particular a multi-axis gripping device.
- the gripping system has at least one fixed depth camera.
- the system is set up to carry out a method as described in the embodiments above and/or has:
- the system or its means has: means for randomly selecting objects, in particular selecting hidden objects that do not relate to the at least one predetermined gripping pose, with no CAD object representation being determined for the randomly selected objects
- the system or its means has: Means for gripping the object with the highest probability of gripping, in particular gripping and placing the object with the highest probability of gripping.
- the means for gripping and in particular depositing can be a gripping device.
- the system or its means has: Means for determining a gripping probability, wherein the gripping probability is further based on a depth image and/or a CAD object representation from the perspective of a gripper component.
- a system and/or a means in the sense of the present invention can be designed in terms of hardware and/or software technology, in particular at least one processing unit, in particular a microprocessor unit, preferably connected to a memory and/or bus system with data or signals, in particular digital processing unit ( CPU), graphics card (GPU) or the like, and/or one or more programs or program modules.
- the processing unit can be designed to process commands that are implemented as a program stored in a memory system, to detect input signals from a data bus and/or to deliver output signals to a data bus.
- a storage system can have one or more, in particular different, storage media, in particular optical, magnetic, solid-state and/or other non-volatile media.
- the program can be designed in such a way that it embodies or is capable of executing the methods described here, so that the processing unit can carry out the steps of such methods and can therefore in particular operate or monitor the machine.
- one or more, in particular all, steps of the method are carried out completely or partially automatically, in particular by the control or its means.
- FIG. 5 is a schematic representation of a machine learning algorithm according to an embodiment of the present invention.
- FIG 3 a scene with CAD object representation or CAD object representations for the objects 5 to be gripped is shown schematically from the perspective of the gripping pose.
- the depth image 30 was used to determine a 6D pose of the objects 5 to be grasped.
- CAD object representations can then be rendered into the scene 31 for or with the existing CAD data from the objects 5 to be grasped.
- the gripping position 20 can in particular be represented more precisely and the determination of a gripping probability can take place on the basis of the depth image and the CAD object representation(s). In this way it can be decided (better) whether a grip at the gripping position 20 is possible, is conditionally possible or is not possible.
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102022205883.6A DE102022205883A1 (de) | 2022-06-09 | 2022-06-09 | Erhöhung der Greifrate |
| PCT/EP2023/063735 WO2023237323A1 (de) | 2022-06-09 | 2023-05-23 | Erhöhung der greifrate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4536447A1 true EP4536447A1 (de) | 2025-04-16 |
Family
ID=86688562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP23728325.4A Withdrawn EP4536447A1 (de) | 2022-06-09 | 2023-05-23 | Erhöhung der greifrate |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP4536447A1 (de) |
| DE (1) | DE102022205883A1 (de) |
| WO (1) | WO2023237323A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102023201407A1 (de) | 2023-02-17 | 2024-08-22 | Kuka Deutschland Gmbh | Verfahren und System zur Verbesserung der Grifferreichbarkeit |
| DE102024111003A1 (de) * | 2024-04-19 | 2025-10-23 | Festo Se & Co. Kg | Greifsystem zur Handhabung von Werkstücken und Verfahren zum Handhaben von Werkstücken |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10766149B2 (en) | 2018-03-23 | 2020-09-08 | Amazon Technologies, Inc. | Optimization-based spring lattice deformation model for soft materials |
| US10977480B2 (en) | 2019-03-27 | 2021-04-13 | Mitsubishi Electric Research Laboratories, Inc. | Detection, tracking and 3D modeling of objects with sparse RGB-D SLAM and interactive perception |
| US11813758B2 (en) * | 2019-04-05 | 2023-11-14 | Dexterity, Inc. | Autonomous unknown object pick and place |
| US11670001B2 (en) | 2019-05-17 | 2023-06-06 | Nvidia Corporation | Object pose estimation |
| US11654564B2 (en) | 2020-09-10 | 2023-05-23 | Fanuc Corporation | Efficient data generation for grasp learning with general grippers |
| DE102020214633A1 (de) | 2020-11-20 | 2022-05-25 | Robert Bosch Gesellschaft mit beschränkter Haftung | Vorrichtung und Verfahren zum Steuern einer Robotervorrichtung |
-
2022
- 2022-06-09 DE DE102022205883.6A patent/DE102022205883A1/de active Pending
-
2023
- 2023-05-23 WO PCT/EP2023/063735 patent/WO2023237323A1/de not_active Ceased
- 2023-05-23 EP EP23728325.4A patent/EP4536447A1/de not_active Withdrawn
Also Published As
| Publication number | Publication date |
|---|---|
| DE102022205883A1 (de) | 2023-12-14 |
| WO2023237323A1 (de) | 2023-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3966731B1 (de) | Maschinelles lernen einer objekterkennung mithilfe einer robotergeführten kamera | |
| DE102017108727B4 (de) | Verfahren zur Erstellung einer Datenbank mit Greiferposen, Verfahren zum Steuern eines Roboters, computerlesbares Speichermedium und Handhabungssystem | |
| DE102015111080B4 (de) | Robotervorrichtung mit maschinellem Sehen | |
| DE102016001174B4 (de) | Robotersystem zum Entnehmen von Werkstücken mit Umrechenfunktion von Position und Orientierung und Verfahren zum Entnehmen von Werkstücken | |
| EP4536447A1 (de) | Erhöhung der greifrate | |
| EP3612355A1 (de) | Verfahren zur erstellung einer datenbank mit greiferposen, verfahren zum steuern eines roboters, computerlesbares speichermedium und handhabungssystem | |
| DE102022203410B4 (de) | Verfahren zum Steuern einer Robotervorrichtung | |
| DE112018007727T5 (de) | Robotersystem | |
| DE102018205669B4 (de) | Aufnehmen von Nutzlasten mittels eines robotergeführten Werkzeugs | |
| DE102022206274B4 (de) | Verfahren zum Steuern eines Roboters zum Manipulieren, insbesondere Aufnehmen, eines Objekts | |
| DE102022207847A1 (de) | Verfahren zum Steuern eines Roboters zum Manipulieren, insbesondere Aufnehmen, eines Objekts | |
| DE102024104640B3 (de) | Betreiben eines Roboters mithilfe einer Datenverarbeitung und Trainieren dieser Datenverarbeitung | |
| EP3870406B1 (de) | Verfahren zum erstellen eines objektmodells zum greifen eines objekts, computerlesbares speichermedium und robotersystem | |
| EP3710900B1 (de) | Verfahren und system zum vorgeben bzw. lernen eines roboterbefehls | |
| EP4063081A1 (de) | Verfahren zum ermitteln von steuerungsdaten für eine greifeinrichtung zum greifen eines gegenstands | |
| WO2024170236A1 (de) | Verfahren und system zur verbesserung der grifferreichbarkeit | |
| DE102020135011B3 (de) | Bilderkennung zum angepassten Ausführen eines Steuerprogramms eines Robotermanipulators | |
| DE102024201098A1 (de) | Verfahren zum Ermitteln, ob ein in einem Eingangsbild dargestelltes Objekt eine Anomalie aufweist | |
| DE102024206901A1 (de) | Verfahren zum Bestimmen eines Bewegungsablaufs für einen Roboter | |
| DE102018204508A1 (de) | Verfahren und System zum Betreiben eines Roboters | |
| WO2024125918A1 (de) | Objektlagedetektion mit automatisierter merkmalsextraktion und/oder merkmalszuordnung | |
| DE102024206903A1 (de) | Verfahren zum Bestimmen einer Greifpose für einen Roboter | |
| DE102022213555A1 (de) | Objektlagedetektion mit automatisierter Merkmalsextraktion und/oder Merkmalszuordnung | |
| EP4141805A1 (de) | Verfahren zum erzeugen, automatisierten annotieren und bereitstellen von trainings-bilddaten | |
| DE102022213562A1 (de) | Greifen mit Verpackungsmaterial |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20241203 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20250717 |