EP4200106A1 - Verfahren und system zum handhaben einer lastanordnung mit einem robotergreifer - Google Patents
Verfahren und system zum handhaben einer lastanordnung mit einem robotergreiferInfo
- Publication number
- EP4200106A1 EP4200106A1 EP21758708.8A EP21758708A EP4200106A1 EP 4200106 A1 EP4200106 A1 EP 4200106A1 EP 21758708 A EP21758708 A EP 21758708A EP 4200106 A1 EP4200106 A1 EP 4200106A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- robot
- load
- gripper
- load arrangement
- lifting
- 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.)
- Pending
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
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J15/00—Gripping heads and other end effectors
- B25J15/06—Gripping heads and other end effectors with vacuum or magnetic holding means
- B25J15/0616—Gripping heads and other end effectors with vacuum or magnetic holding means with vacuum
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/0096—Program-controlled manipulators co-operating with a working support, e.g. work-table
-
- 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
- B25J9/1602—Program controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- 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
- B25J9/1638—Program controls characterised by the control loop compensation for arm bending/inertia, pay load weight/inertia
-
- 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
- B25J9/1653—Program controls characterised by the control loop parameters identification, estimation, stiffness, accuracy, error analysis
-
- 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
- G05B2219/39107—Pick up article, object, measure, test it during motion path, place it
Definitions
- the present invention relates to a method for handling a load arrangement with a robot and a system and computer program product for carrying out the method.
- a robot gripper with a plurality of suction elements is known from DE 10 2016220 643 A1.
- An object of an embodiment of the present invention is to improve the handling of load arrangements with a robot (gripper), preferably to eliminate unintentional lifting of too many and/or wrong loads or objects.
- a method for handling a load arrangement with a robot comprises the following steps, which are carried out in one embodiment in succession:
- a machine-learned model(s) in one embodiment classifying (still) during a movement of the lifted load arrangement (by or with the help of the robot(s )) and/or classification (while the lifted load arrangement is still) over an, in particular predetermined or limited, receiving area in which the load arrangement for lifting was located, in particular has been lifted, in one embodiment over a receiving area of a receiving station and/ or above or in a receiving container (located, in particular moved), in particular classifying during a movement of the raised load arrangement (by or with the help of the robot(s)) (still) above the receiving area; and at least one of the steps:
- the method includes the step of: performing a third process with the robot if the load assembly classifies into a third class or has been assigned to a third class, in a further development the method comprises the step of: Executing a fourth process with the robot if the load arrangement is classified into a fourth class or has been assigned to a fourth class.
- one or more additional classes can be provided, with a corresponding, class-specific additional process being carried out with the robot if the load arrangement is assigned to an additional (this) class(es).
- a normal picking of a lifted object can take place (first process), if the load arrangement is or is classified as a load arrangement with (only) one (single) object, a two-stage, sequential picking of two lifted objects can take place (second process), if the load arrangement is classified as a load arrangement with (exactly) two objects, and a three-stage, sequential picking of three lifted objects takes place (third process) if the load arrangement is or is classified as a load arrangement with (exactly) three objects.
- the raised load arrangement can be handed over, in particular over the pick-up area (second or third process), without being picked in the process or as a result, if the load arrangement is a load arrangement is classified with the wrong number of objects.
- picking of a lifted object can occur (first process) if the load assembly is classified as a load assembly with an object of the correct type, and delivery of the lifted load assembly over the receiving area can occur (second process) without the this is thereby or thereby picked if the load arrangement is or is classified as a load arrangement with the wrong object type.
- the object can also be picked at a second picking station (second process) if the load arrangement is or is classified as a load arrangement with an object of a second type.
- the robot has a robot arm with at least three, in particular at least six, in one embodiment at least seven joints, in particular rotary joints, on whose (end) flange the gripper is arranged, in one embodiment releasably fastened.
- the present invention is particularly advantageous for this purpose, in particular due to the flexible possible uses of such robots.
- activation of a lifting state includes switching to an operating mode in which the gripper can lift loads or objects or exerts a corresponding gripping force on one or more loads or objects.
- the gripper is a pneumatic gripper with one or more suckers
- activating its lifting state in one embodiment includes activating, in particular generating a vacuum, of one or more, preferably all, suckers.
- the gripper is additionally or alternatively a mechanical gripper with one or more movable, in particular pivotable, gripping jaws
- activating its lifting state includes closing the or one or more, preferably all, gripping jaws in one embodiment.
- a deactivation includes a deactivation of suckers or opening of gripping jaws.
- an embodiment of the present invention is particularly suitable for eliminating unintentional lifting of too few and/or, particularly advantageously, too many loads or objects.
- the first and second as well as possibly third, fourth and/or further class(es) differ in the number of loads or objects lifted by the gripper, which are of the same type in one embodiment.
- the first class is a class with only a single object or only a single load ("single grip 1 ").
- the second and/or third and/or fourth class (each) is a class with multiple objects or loads (“multiple grip 1 ”) and/or one of the second and possibly third and possibly fourth class is a class without an object or load (“mistake”).
- the second class is a class with more than one object or the second class is a class with exactly two objects and the third class is a class with more than two objects.
- the load arrangement lifted by the gripper is classified in the class without object or load or, for more compact purposes, if the gripper is empty after activation of a lifting state, it is generally referred to as a load arrangement lifted by the gripper, which then has no object or corresponds to the empty set.
- the present invention can therefore be used in one embodiment for lifting load arrangements with a different number of objects or loads that are of the same type in one embodiment, but is not limited to this.
- the first, second or possibly third and/or fourth process can also be carried out depending on the classified type of the loads lifted by the gripper.
- the first class can be a class of a first type of objects or loads and the second class can be a class of other (types of) objects, in one embodiment a second type of objects or loads, in which case in a further development the first process a transfer movement of the raised load arrangement using the robot to a first picking station and the second process a different picking or transfer movement of the raised load arrangement using the robot to one second picking station or a deactivation of the lifting status of the gripper over the pick-up area and a new lifting attempt (of the correct object or load type).
- the distribution or position(s) relative to, in particular on, the gripper first, second or optionally third and/or fourth process are carried out.
- the first class can be a class with a first load that is sucked together by a subset of a set of several suckers of the gripper and a second load that is sucked in by one or more other suckers of the gripper
- the second class can be a class with the first and second loads , which are or will be sucked in by the suction cups in a different constellation
- the first process may include a deactivation of the other suction cup(s) and the second process may include a partial deactivation different from this in a further development, in which also at least one deactivating the sucker while one or more suckers identified as carrying the first load remain activated.
- the machine-learned model identifies the distribution or position(s) of the lifted loads relative to, in particular on, the gripper, with different lifting devices, in particular suckers, then being used in a targeted manner in the first, second and possibly third and possibly fourth process.
- the grapple may be deactivated to deliver one or more of those loads while at least one other of the lift devices identified as carrying a load remains activated.
- the classes differ in one embodiment in the number, distribution and/or type of loads lifted by the gripper.
- the gripper has two or more lifting devices in one embodiment, and two or more, preferably at least three, suction devices in a further development. Since unintentional lifting of too many loads or objects can occur (more) frequently with such suction grippers, the present invention is particularly advantageous for this.
- the at least one sensor is arranged on the gripper, between the gripper and one or the robot arm to which it is attached, or on the robot arm.
- the sensor is a force and/or moment sensor and/or is arranged on the robot arm flange or between the gripper and the robot arm or on one of the joints of the robot (arm).
- the one-dimensional or multidimensional force variable depends on at least one, in one embodiment vertical, load arrangement-dependent force component and/or at least one load arrangement-dependent torque component, in particular this force or torque component(s) can have, in particular be. These are particularly advantageous for the classification of lifted load arrangements.
- the one-dimensional or multi-dimensional time profile of the load arrangement-dependent force variable is recorded in one embodiment with the sensor(s) and/or extends in one embodiment over at least 0.5 seconds, in particular at least 1 second, in one embodiment at least 2 seconds. In one embodiment, it is sampled at a sampling rate of at least 0.01 kHz.
- the one-dimensional or multi-dimensional parameter of the time profile has the time profile itself, and can in particular be the time profile. Additionally or alternatively, it can also have one or more variables or values derived from the time profile, in one embodiment signal analysis technology and/or numerically, in particular be one or more variables of a frequency or Fourier analysis, integration and/or differentiation of the time profile , mean and/or extreme values, or the like.
- the load arrangement lifted by the gripper is determined using the machine-learned model based on the determined parameters of the time profile of the load arrangement-dependent force variable and other determined actual values, in one embodiment using at least one sensor of the robot determined and / or kinematic actual values, in one version axis positions, speeds and/or accelerations or the like, in one embodiment time histories thereof.
- the load arrangement can be classified particularly advantageously, in particular precisely, quickly and/or reliably, using a machine-learned model.
- the first process includes a transfer movement of the lifted load arrangement using the robot, in one embodiment out of the receiving area or container and/or to a (first) picking station, in a further development the delivery of the lifted load arrangement to the (first) Picking station can consist of this in particular.
- the second process includes a complete deactivation or a partial deactivation of the lifting state of the gripper, in particular a deactivation of one or more of its lifting devices. In one embodiment, this deactivation does not take place at the (first) picking station, in one embodiment at no picking station.
- the third process includes a complete deactivation or a partial deactivation, in particular different from the second process, of the lifting state of the gripper, in particular a deactivation of another group of its lifting devices. In one embodiment, this deactivation does not take place at the (first) picking station, in one embodiment at no picking station.
- the second and/or third process includes the (complete or partial) deactivation of the lift state over the recording area.
- the second process comprises picking that differs from the first process and is sequential in one embodiment, in particular the delivery of a first part of the lifted load arrangement to the (first) picking station and the delivery of another part of the lifted load arrangement to another picking station or at the same (first) picking station after further processing, in particular removal, of the delivered first part.
- the third process includes a different, in one embodiment sequential, picking from the first and/or second process, in particular the delivery of a first part of the lifted load arrangement at the (first) picking station, the delivery of a second part of the lifted load arrangement at the other picking station or at the same (first) picking station after further processing, in particular removal, of the delivered first part, as well as delivering another part of the lifted load arrangement to the other or the same (first) picking station after further processing, in particular removal, of the delivered part second part.
- the second process can also include picking that is different from the first process, in particular sequential
- the third process can include deactivating the lifting state of the gripper over the receiving area, so that in one embodiment (only) two objects or loads are lifted sequentially picked and more than two lifted objects or loads are delivered in the pick-up area.
- the second and/or third process comprises a placement movement of the lifted load arrangement using the robot, which guides or continues to carry the load arrangement (“guided placement movement of the lifted load arrangement”), in particular in the receiving area and/or in front Hub state deactivation.
- Guided placement movement of the lifted load arrangement (“guided placement movement of the lifted load arrangement”)
- lifted objects or loads can be protected when the lifting status is deactivated.
- objects or loads can be dropped by deactivating the lifting state, thereby saving process time in particular.
- partially disabling the lift state of the grapple in the second and/or third process includes disabling at least one of the lift devices while at least another one of the lift devices identified as load-carrying remains activated.
- the classes differ in the distribution of loads lifted by the grapple relative to or on the grapple, such that in one embodiment, all but one of the lifters identified as load-bearing, or a group of the same, of the lifters of the grapple are targeted Load common bearing identified of lifting devices is disabled.
- specific lifting devices in particular suckers, can advantageously be deactivated in a targeted manner in order to continue to handle only a desired number or type of objects or loads with the robot.
- the load assembly lifted by the gripper is classified using the machine learned model (also) based on a sensed movement of the lifted load assembly using the robot. It has been found that the additional consideration of the detected movement of the lifted load arrangement in the classification using machine-learned models can be particularly advantageous, in particular improving the precision, reliability and/or speed of the classification.
- the model has at least one artificial neural network, in a further development a network with 1D convolutions.
- Such machine-learned models are particularly advantageous for the present classification, in particular because of their learning behavior and/or their precision, reliability and/or speed.
- the model is, in particular, learned by machine by lifting one or more load arrangements with the gripper of the robot, which is/are referred to here without loss of generality as learning load arrangement(s), in a further development the class of this at least one learning load arrangement entered manually or automatically, in one embodiment using automated identification, for example by image processing or evaluation or the like, or by only partial activation of the gripper, in one embodiment activating only one of its lifting devices, is specified, in particular. Additionally or alternatively, in one embodiment, the model may be machine learned using lifting multiple different learning load assemblies with the robot's gripper.
- machine learning can be greatly improved in one embodiment, in particular in a combination of two or more of these features.
- a system for handling a load arrangement with a robot in particular hardware and/or software, in particular programming, is set up to carry out a method described here and/or has:
- system or its means(s) has:
- a means within the meaning of the present invention can be hardware and/or software, in particular a processing unit, in particular a microprocessor unit (CPU), graphics card (GPU) preferably connected to a memory and/or bus system for data or signals ) 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 output 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.
- a computer program product can have, in particular be a, in particular non-volatile, storage medium for storing a program or with a program stored thereon, with the execution of this program causing a system or a controller, in particular a computer, to carry out the method described here or one or more of its steps.
- 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 includes the robot.
- "Over a capture area” in one implementation in a manner conventional in the art, refers to a position horizontally (seen) at least partially within (an outer boundary) of the capture area.
- An embodiment of the present invention is particularly advantageous for gripping unknown object types whose weight is also not known in advance, or is used for this purpose.
- Fig. 1 a system according to an embodiment of the present invention.
- Figure 2 a method according to an embodiment of the present invention.
- FIG. 1 shows a system performing a method according to an embodiment of the present invention.
- a robot 10 has a multi-axis robot arm 11 and a gripper 12 with three suction cups 12.1-12.3, for example, and is intended to pick up objects or loads 21 from a receiving container 20 and pick them individually at a picking station 30 into packaging 31 provided there.
- a robot controller 13 carries out the method outlined in Fig. 2:
- a step S110 the robot 10 moves its gripper 12 into the receiving container 20 and activates its lifting status or all suckers 12.1-12.3. In this way, at least one of the objects 21 can be gripped (pneumatically) with a high degree of probability.
- a second step S120 the robot 10 lifts the gripper 12 with the load arrangement raised.
- a force-torque sensor 14 between the gripper 12 and the robot arm 11 continuously or at discrete intervals detects a vertical force component that depends on the load arrangement being lifted.
- the sequence of the corresponding measurement signals of the sensor 14 forms a (parameter of a) Time course of a load arrangement dependent force variable.
- force and/or torque components can be additionally or alternatively detected and/or sensors on the axes or joints of the robot arm and/or one or more strain gauges on the gripper 12 can be used in addition or as an alternative to the force-torque sensor 14 and /or in addition or as an alternative to the time profiles themselves, for example frequency analyzes or mean values of the time profiles or the like can be used as parameters.
- axis positions of the robot can also be detected by sensors in step S120, with the artificial neural network 13.1 then classifying the load arrangement lifted by the gripper on the basis of these actual values as well.
- the robot performs a transfer movement of the lifted load arrangement from the receiving area to the picking station 30 and releases the object or the load arrangement into the packaging 31 provided by deactivating all suction devices 12.1-12.3 (S141).
- the controller 13 deactivates all but one of the suction cups 12.1 in a step S142 -12.3, while the gripper is still in or above the receiving container 20, so that the object gripped too much falls back into it, and then, as in step S141, picks the one object held by this sucker that is still active(ed) into the one provided packaging 31
- suckers 12.1-12.3 can also be deactivated in step S142 while the gripper is still in or above the receiving container 20, so that all gripped objects fall back into it, and then a new attempt can be carried out analogously to step S140, only one grab object.
- step S142 as in step S141, the provided packaging 31 can first be approached and only some of the suction cups can be deactivated via this, in particular the suction cups that have been identified as carrying the same load, while the other suction cups are still active(s) are, so that only one object is commissioned into the packaging 31 provided, and then, after the packaging has been transported away and the next packaging has been provided, the other suckers are deactivated, so that the second object is commissioned into the newly provided packaging.
- the procedure can be analogous (step S143) if the load arrangement has been assigned to the third class, i.e. it is determined on the basis of the (parameter of) the time profile of the load arrangement-dependent force variable that more than two objects are lifted (S130: "3").
- the second class objects that have been picked up too much can be dropped in or above the receiving container 20 or picked sequentially, or all objects can be dropped and a new attempt to pick them up can be carried out.
- step S10 for the respective object or load type, with either the fact that only a single object is present ( and is also being lifted), or if it is confirmed by an operator or by image recognition that only a single object is being lifted, it is certain that only a single object is being lifted. In this way, machine learning can be improved. Additionally or alternatively, in step S10, several different objects can also be lifted sequentially, preferably individually, with the gripper 12 and the artificial neural network 13.1 can be trained as a result or in the process.
- steps S140 and/or S143 can be omitted, in one embodiment the only object can be picked normally (S141 - first process) if the lifted load arrangement has been classified in the "single handle" class (S130: “1") and otherwise all suction cups 12.1-12.3 are still deactivated in or above the receptacle 20 (S142 - second process), if the raised load arrangement has been classified in the "multiple handle” class (S130: “2"), in a further development also with a classification a new lifting attempt can be started directly in the "Mistake” class (S130: “0” or S140 - third process), whereby in a further development a new lifting attempt can also be started directly with a classification in the "Mistake” class (S130: “0” or S140 - third process) or an empty gripper or incorrect grip can also be recognized or treated in another way, in particular without a corresponding class or classification tion.
- the type of objects lifted can also be classified and type-specific processes can be carried out on this basis.
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102020210537.5A DE102020210537A1 (de) | 2020-08-19 | 2020-08-19 | Verfahren und System zum Handhaben einer Lastanordnung mit einem Robotergreifer |
| PCT/EP2021/072498 WO2022038040A1 (de) | 2020-08-19 | 2021-08-12 | Verfahren und system zum handhaben einer lastanordnung mit einem robotergreifer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4200106A1 true EP4200106A1 (de) | 2023-06-28 |
Family
ID=77447919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21758708.8A Pending EP4200106A1 (de) | 2020-08-19 | 2021-08-12 | Verfahren und system zum handhaben einer lastanordnung mit einem robotergreifer |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US12583102B2 (de) |
| EP (1) | EP4200106A1 (de) |
| KR (1) | KR20230051533A (de) |
| CN (1) | CN116323108A (de) |
| DE (1) | DE102020210537A1 (de) |
| WO (1) | WO2022038040A1 (de) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102021208769B8 (de) | 2021-08-11 | 2023-02-23 | Kuka Deutschland Gmbh | Verfahren und System zur Analyse eines Betriebs eines Roboters |
Family Cites Families (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE2704670C3 (de) * | 1977-02-04 | 1981-11-19 | Kernforschungsanlage Jülich GmbH, 5170 Jülich | Greifer zum Heben schwerer Lasten |
| US5136687A (en) | 1989-10-10 | 1992-08-04 | Edelman Gerald M | Categorization automata employing neuronal group selection with reentry |
| DE102012001265A1 (de) | 2012-01-23 | 2013-07-25 | Weber Maschinenbau Gmbh Breidenbach | Vorrichtung und Verfahren zur Ermittlung des Gewichts einer Aufnahmevorrichtung |
| JP5616478B1 (ja) * | 2013-04-18 | 2014-10-29 | ファナック株式会社 | ワークを搬送するロボットを備えるロボットシステム |
| NL2011625C2 (nl) | 2013-10-16 | 2015-04-20 | Bosch Sprang Beheer B V | Matrijssysteem voor een thermovormmachine, thermovormmachine en werkwijze voor het thermovormen van een product. |
| US9205558B1 (en) | 2014-07-16 | 2015-12-08 | Google Inc. | Multiple suction cup control |
| DE102016009030B4 (de) * | 2015-07-31 | 2019-05-09 | Fanuc Corporation | Vorrichtung für maschinelles Lernen, Robotersystem und maschinelles Lernsystem zum Lernen eines Werkstückaufnahmevorgangs |
| KR101980603B1 (ko) * | 2016-05-20 | 2019-05-22 | 구글 엘엘씨 | 오브젝트(들)를 캡처하는 이미지(들)에 기초하는 그리고 환경에서의 미래 로봇 움직임에 대한 파라미터(들)에 기초하여 로봇 환경에서의 오브젝트(들)의 모션(들)을 예측하는 것과 관련된 머신 학습 방법들 및 장치 |
| JP2018027581A (ja) * | 2016-08-17 | 2018-02-22 | 株式会社安川電機 | ピッキングシステム |
| DE102016220643A1 (de) | 2016-10-20 | 2018-04-26 | Kuka Systems Gmbh | Robotergreifer mit beweglichen Hilfssaugelementen |
| CN110785268B (zh) * | 2017-06-28 | 2023-04-04 | 谷歌有限责任公司 | 用于语义机器人抓取的机器学习方法和装置 |
| JP2019084601A (ja) * | 2017-11-02 | 2019-06-06 | キヤノン株式会社 | 情報処理装置、把持システムおよび情報処理方法 |
| DE102018208126A1 (de) | 2018-05-23 | 2019-11-28 | Trumpf Werkzeugmaschinen Gmbh + Co. Kg | Verfahren zum Hantieren eines Werkstücks mit Hilfe eines Entnahmewerkzeugs und Maschine zur Durchführung des Verfahrens |
| DE202018103922U1 (de) | 2018-07-09 | 2018-08-06 | Schunk Gmbh & Co. Kg Spann- Und Greiftechnik | Greifsystem als intelligentes Sensor-Aktor-System |
| JP2020062707A (ja) | 2018-10-16 | 2020-04-23 | 株式会社東芝 | 情報処理装置 |
| EP3871172A1 (de) * | 2018-10-25 | 2021-09-01 | Berkshire Grey, Inc. | Systeme und verfahren zum lernen zur extrapolation optimaler zielrouting- und handhabungsparameter |
| AT521997B1 (de) * | 2018-11-21 | 2021-11-15 | Tgw Logistics Group Gmbh | Optimierungsverfahren zur Verbesserung der Zuverlässigkeit einer Warenkommissionierung mit einem Roboter |
| US11839983B2 (en) * | 2018-11-27 | 2023-12-12 | Ocado Innovation Limited | Systems and methods for robotic grasp verification |
| US20200270069A1 (en) * | 2019-02-27 | 2020-08-27 | Walmart Apollo, Llc | Flexible automated sorting and transport arrangement (fast) robotic arm |
| US11312581B2 (en) * | 2019-04-16 | 2022-04-26 | Abb Schweiz Ag | Object grasp system and method |
| US10576630B1 (en) | 2019-05-31 | 2020-03-03 | Mujin, Inc. | Robotic system with a robot arm suction control mechanism and method of operation thereof |
| US11213953B2 (en) * | 2019-07-26 | 2022-01-04 | Google Llc | Efficient robot control based on inputs from remote client devices |
| US20230356387A1 (en) * | 2019-07-29 | 2023-11-09 | Nimble Robotics, Inc. | Storage Systems and Methods for Robotic Picking |
| US11345029B2 (en) * | 2019-08-21 | 2022-05-31 | Mujin, Inc. | Robotic multi-gripper assemblies and methods for gripping and holding objects |
| CN112405570A (zh) * | 2019-08-21 | 2021-02-26 | 牧今科技 | 用于夹持和保持物体的机器人多夹持器组件和方法 |
| JP7282703B2 (ja) * | 2020-02-10 | 2023-05-29 | 株式会社東芝 | ロボットシステムおよびプログラム |
| US11478942B1 (en) * | 2020-06-03 | 2022-10-25 | Amazon Technologies, Inc. | Robotic picking assemblies configured to grasp multiple items |
-
2020
- 2020-08-19 DE DE102020210537.5A patent/DE102020210537A1/de active Pending
-
2021
- 2021-08-12 EP EP21758708.8A patent/EP4200106A1/de active Pending
- 2021-08-12 WO PCT/EP2021/072498 patent/WO2022038040A1/de not_active Ceased
- 2021-08-12 CN CN202180068974.1A patent/CN116323108A/zh active Pending
- 2021-08-12 US US18/042,051 patent/US12583102B2/en active Active
- 2021-08-12 KR KR1020237008588A patent/KR20230051533A/ko active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| US12583102B2 (en) | 2026-03-24 |
| US20230302635A1 (en) | 2023-09-28 |
| CN116323108A (zh) | 2023-06-23 |
| WO2022038040A1 (de) | 2022-02-24 |
| DE102020210537A1 (de) | 2022-02-24 |
| KR20230051533A (ko) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102015005908B4 (de) | System zum Transportieren eines Werkstücks mit einer Funktion zur Überwachung einer externen Kraft | |
| DE102016001174B4 (de) | Robotersystem zum Entnehmen von Werkstücken mit Umrechenfunktion von Position und Orientierung und Verfahren zum Entnehmen von Werkstücken | |
| DE102014005758B4 (de) | Robotersystem, aufweisend einen Roboter zur Beförderung eines Werkstücks | |
| DE102009011300B4 (de) | Beladung von Lademitteln mit Paketen mittels Manipulator | |
| DE102018112360B3 (de) | Bereichsabhängige Kollisionsdetektion für einen Robotermanipulator | |
| DE112018007727B4 (de) | Robotersystem | |
| DE102014005434A1 (de) | Steuerungseinrichtung für einen Roboter zur Beförderung eines Werkstücks | |
| AT519452A4 (de) | Verfahren und Vorrichtung zum Kommissionieren von Waren | |
| DE102021125068A1 (de) | Ladesystem und Informationsverarbeitungsvorrichtung | |
| EP2952296A2 (de) | Vorrichtung zum automatisierten entnehmen von in einem behälter angeordneten werkstücken | |
| WO2014205475A1 (de) | Verfahren zum robotergestützten stapeln von gegenständen | |
| DE112018007729B4 (de) | Maschinelle Lernvorrichtung und mit dieser ausgestattetes Robotersystem | |
| EP3625157B1 (de) | Handhabungseinrichtung zum handhaben von zumindest abschnittsweise ebenen gütern, verfahren zum betreiben einer derartigen handhabungseinrichtung | |
| DE102018112370B4 (de) | Richtungsabhängige Kollisionsdetektion für einen Robotermanipulator | |
| DE102017002354B4 (de) | Transportieren von Objekten, insbesondere Kommissionieren von Waren, mithilfe eines Roboters | |
| DE102019102470A1 (de) | Einlernvorgang für ein Robotersystem bestehend aus zwei Robotermanipulatoren | |
| DE102020107385B4 (de) | Betriebseinstellvorrichtung zum einstellen des betriebs einer robotervorrichtung | |
| WO2022038040A1 (de) | Verfahren und system zum handhaben einer lastanordnung mit einem robotergreifer | |
| DE102018205669B4 (de) | Aufnehmen von Nutzlasten mittels eines robotergeführten Werkzeugs | |
| DE102016120809B4 (de) | Verfahren zum robotergestützten Einpassen eines männlichen Bauteils in ein weibliches Bauteil | |
| DE102021214721B3 (de) | Verfahren und System zum Betreiben eines Roboters | |
| DE102019200930A1 (de) | Vorrichtung und Verfahren zum automatischen Handhaben von Lagereinheiten | |
| EP3710900B1 (de) | Verfahren und system zum vorgeben bzw. lernen eines roboterbefehls | |
| DE102013022533B3 (de) | Verfahren zum robotergestützten Stapeln von Gegenständen | |
| DE102021210749B3 (de) | Verfahren und Vorrichtung zur Überwachung einer Füll- und/oder Verschließanlage und/oder Nachverarbeitungsanlage |
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: 20230213 |
|
| 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 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) | ||
| P01 | Opt-out of the competence of the unified patent court (upc) registered |
Effective date: 20240508 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20251208 |