CN108340367A - Machine learning method for mechanical arm crawl - Google Patents
Machine learning method for mechanical arm crawl Download PDFInfo
- Publication number
- CN108340367A CN108340367A CN201711324287.3A CN201711324287A CN108340367A CN 108340367 A CN108340367 A CN 108340367A CN 201711324287 A CN201711324287 A CN 201711324287A CN 108340367 A CN108340367 A CN 108340367A
- Authority
- CN
- China
- Prior art keywords
- crawl
- cargo
- machine learning
- mechanical arm
- unit
- 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—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme 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
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/04—Viewing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G61/00—Use of pick-up or transfer devices or of manipulators for stacking or de-stacking articles not otherwise provided for
Abstract
The invention discloses the machine learning methods captured for mechanical arm, including：Mechanical arm carries out grasping manipulation according to the control instruction of control unit；Camera obtains the image of crawl process, and sends the image to image processing unit；Image processing unit judges crawl result according to described image, and will determine that result is sent to machine learning unit；Training dataset is added in the control instruction and the judging result by machine learning unit, and adjusts control parameter according to training result；And it is read by control unit after preserving the control parameter after adjustment.Provided by the present invention for the machine learning method of mechanical arm crawl, the parameter of mechanical arm crawl can be optimized by machine learning, improve the success rate of crawl, the versatility to increase the automated machines such as unstacker lays the first stone.
Description
Technical field
The present invention relates to technical field of mechanical automation, more particularly to are used for the machine learning method of mechanical arm crawl.
Background technology
Logistics labour in for the ease of cargo packing and transporting, it will usually now cargo is packed together, then to cargo into
Row is redistributed.De-stacking, turn pile, stacking belongs to plant produced, the essential step of logistics transportation, in traditional handicraft
In, usually carries out de-stacking by artificial, turns pile, stacking, this process not only waste of manpower but also inefficiency.Due to labour at
This rising and market competition etc., require that enterprise must improve production efficiency, by manually turning to automation.
Now, it although there is some equipment that the operations such as de-stacking, stacking may be implemented, is all confined to fixed place and is directed to
Specific cargo is operated, and can not be moved and be further increased the bottleneck of logistic efficiency with not high become of versatility, hinder general
Property this realization a factor be can not determine crawl mechanical arm crawl orientation and strength, cause mechanical arm capture at
The low problem of power.
Invention content
In order to solve the above problem, the present invention is provided to the machine learning methods of mechanical arm crawl.Use provided by the invention
In the machine learning method of mechanical arm crawl, including：
Mechanical arm carries out grasping manipulation according to the control instruction of control unit；
Camera obtains the image of crawl process, and sends the image to image processing unit；
Image processing unit judges crawl result according to described image, and will determine that result is sent to machine learning
Unit；
Training dataset is added in the control instruction and the judging result by machine learning unit, and according to training result
Adjust control parameter；And it is read by control unit after preserving the control parameter after adjustment.
Preferably,
The crawl including capturing with crawl as a result, successfully fail.
Preferably,
The crawl failure, including cross and capture and owe crawl；
Described cross captures, to cause goods packing to deform more than the first preset value after mechanical arm crawl；
The deficient crawl, to fall off after mechanical arm crawl or goods packing is after being crawled opposite sliding with mechanical arm.
Preferably,
Described image processing unit is additionally operable to obtain the volume of cargo according to described image, and by the volume of the cargo
It is sent to machine learning unit；
Training data is added in the volume of the cargo, the control instruction and the judging result by machine learning unit
Collection, and control parameter is adjusted according to training result；And it is read by control unit after preserving the control parameter after adjustment.
Preferably,
The mechanical arm, including support portion and crawl section；
The support portion is used to move crawl section to specified position,
The crawl section is for capturing cargo；
The crawl section is equipped with force snesor, for detecting grasp force；
The support portion is equipped with motion sensor, the movable information for detecting support portion, the motion sensor packet
It includes one or more in acceleration transducer, foil gauge；
General Porcess Unit, for obtaining the quality of cargo according to the movable information；
The machine learning unit obtains the quality of the grasp force and the cargo, and by the grasp force, the goods
Training dataset is added in the quality of object, the control instruction and the judging result, and adjusts control parameter according to training result；
And it is read by control unit after preserving the control parameter after adjustment.
Preferably,
The movable information of the support portion, is also obtained by following manner,
Camera shoots the picture of support portion, and the picture of the support portion is sent to image processing unit；
Image processing unit is according to the picture of the support portion of different time, the movement speed in the portion that is supported using calculus of finite differences
Degree, and moving displacement and acceleration of motion are obtained according to the movement velocity.
Preferably,
The General Porcess Unit is additionally operable to obtain the rigidity of cargo according to the movable information；
The method for obtaining cargo rigidity is the system for being reduced to be connected with spring between 2 mass blocks by cargo, and
General Porcess Unit is handled to obtain the quality and spring of 2 mass blocks according to 2DOF vibration equation to vibration data
Rigidity；
The machine learning unit obtains the quality and rigidity of the grasp force and the cargo, and by the grasp force,
Training dataset is added in the quality and rigidity of the cargo, the control instruction and the judging result, and according to training result
Adjust control parameter；And it is read by control unit after preserving the control parameter after adjustment.
The present invention some advantageous effects may include：
Provided by the present invention for the machine learning method of mechanical arm crawl, mechanical arm can be optimized by machine learning
The parameter of crawl improves the success rate of crawl, and the versatility to increase the automated machines such as unstacker lays the first stone.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The purpose of the present invention and other advantages can be by the explanations write
Specifically noted structure is realized and is obtained in book, claims and attached drawing.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Description of the drawings
Attached drawing is used to provide further understanding of the present invention, and a part for constitution instruction, the reality with the present invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings：
Fig. 1 is the flow chart of the machine learning method for mechanical arm crawl in the embodiment of the present invention.
Specific implementation mode
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
Fig. 1 is the flow chart of the machine learning method for mechanical arm crawl in the embodiment of the present invention.As shown in Figure 1, packet
It includes：
Provided by the present invention for the machine learning method of mechanical arm crawl, including：
Step S101, mechanical arm carries out grasping manipulation according to the control instruction of control unit；
Step S102, camera obtains the image of crawl process, and sends the image to image processing unit；
Step S103, image processing unit judges crawl result according to described image, and will determine that result is sent
To machine learning unit；
Step S104, training dataset, and root is added in the control instruction and the judging result by machine learning unit
Control parameter is adjusted according to training result；And it is read by control unit after preserving the control parameter after adjustment.
Since the size and weight of the outer packing of cargo are usually different, therefore, it is difficult to be obtained by fixed programming
Suitable crawl position and crawl strength, therefore the degree of de-stacking automation is limited, and the present invention utilizes machine learning (depth
Study) versatility, it may be determined that the crawl parameter of a variety of cargos, with improve crawl success rate, to for increase unstacker
The versatility of equal automated machines lays the first stone.
In order to simplify the cost of machine learning, the dimension for reducing training dataset is needed, in one embodiment of the present of invention
In,
The crawl including capturing with crawl as a result, successfully fail.
Training dataset, which excessively simplifies, in order to prevent causes grasp force to cross conference damage cargo, needs to concentrate in training data
Including the case where excessive equal crawls of grasp force fail, in one embodiment of the invention,
The crawl failure, including cross and capture and owe crawl；
Described cross captures, to cause goods packing to deform more than the first preset value after mechanical arm crawl；
The deficient crawl, fall off for cargo after mechanical arm crawl or goods packing is after being crawled have with mechanical arm it is relatively sliding
It is dynamic.
When the grasp force of mechanical arm is more than the first preset value, goods packing can be caused to deform after mechanical arm crawl cargo.
In order to be applicable in various sizes of cargo, need to concentrate the size for including cargo in training data, the one of the present invention
In a embodiment,
Described image processing unit is additionally operable to obtain the volume of cargo according to described image, and by the volume of the cargo
It is sent to machine learning unit；
Training data is added in the volume of the cargo, the control instruction and the judging result by machine learning unit
Collection, and control parameter is adjusted according to training result；And it is read by control unit after preserving the control parameter after adjustment.
In order to be applicable in the cargo of different weight, need to concentrate the weight for including cargo in training data, the one of the present invention
In a embodiment,
The mechanical arm, including support portion and crawl section；
The support portion is used to move crawl section to specified position,
The crawl section is for capturing cargo；
The crawl section is equipped with force snesor, for detecting grasp force；
The support portion is equipped with motion sensor, the movable information for detecting support portion, the motion sensor packet
It includes one or more in acceleration transducer, foil gauge.
After getting movable information, General Porcess Unit, for obtaining the quality of cargo according to the movable information.By
It is known in the weight (quality), material (Young's modulus, Poisson's ratio etc.) and shape of mechanical arm, foil gauge collects deformation,
Moment of flexure is calculated according to elastic deformation theory, the anti-quality for releasing cargo；Or rigidity mass ratio is calculated according to the frequency of vibration,
Due to rigidity (being determined by the material and shape of mechanical arm) it is known that the anti-quality for releasing cargo counter can be released；
The machine learning unit obtains the quality of the grasp force and the cargo, and by the grasp force, the goods
Training dataset is added in the quality of object, the control instruction and the judging result, and adjusts control parameter according to training result；
And it is read by control unit after preserving the control parameter after adjustment.
In order to simplify the hardware cost of equipment, the movable information of support portion can be judged by machine vision, without
The data for wanting motion sensor, to save the cost of motion sensor and relevant data acquisition equipment, the present invention's
In one embodiment,
The movable information of the support portion can also be obtained by following manner,
Camera shoots the picture of support portion, and the picture of the support portion is sent to image processing unit；
Image processing unit is according to the picture of the support portion of different time, the movement speed in the portion that is supported using calculus of finite differences
Degree, and moving displacement and acceleration of motion are obtained according to the movement velocity.
Since the article in cargo may not be an entirety, the weight of object can be caused to identify using whole this hypothesis
Mistake in order to be suitable for such case needs that the dynamic characteristic of cargo is identified, most important of which is that the matter of object
Amount and coupling stiffness, since two degree freedom system is the better approximation to real system, and its calculation amount is not high, at this
In one embodiment of invention,
The General Porcess Unit is additionally operable to obtain the rigidity of cargo according to the movable information；
The method for obtaining cargo rigidity is the system for being reduced to be connected with spring between 2 mass blocks by cargo, and
General Porcess Unit is handled to obtain the quality and spring of 2 mass blocks according to 2DOF vibration equation to vibration data
Rigidity；
The machine learning unit obtains the quality and rigidity of the grasp force and the cargo, and by the grasp force,
Training dataset is added in the quality and rigidity of the cargo, the control instruction and the judging result, and according to training result
Adjust control parameter；And it is read by control unit after preserving the control parameter after adjustment.
Provided by the present invention for the machine learning method of mechanical arm crawl, mechanical arm can be optimized by machine learning
The parameter of crawl improves the success rate of crawl, and the versatility to increase the automated machines such as unstacker lays the first stone.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, the present invention can be used in one or more wherein include computer usable program code computer
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (7)
1. for the machine learning method of mechanical arm crawl, including：
Mechanical arm carries out grasping manipulation according to the control instruction of control unit；
Camera obtains the image of crawl process, and sends the image to image processing unit；
Image processing unit judges crawl result according to described image, and will determine that result is sent to machine learning list
Member；
Training dataset is added in the control instruction and the judging result by machine learning unit, and is adjusted according to training result
Control parameter；And it is read by control unit after preserving the control parameter after adjustment.
2. the method as described in claim 1, which is characterized in that
The crawl including capturing with crawl as a result, successfully fail.
3. method as claimed in claim 2, which is characterized in that
The crawl failure, including cross and capture and owe crawl；
Described cross captures, to cause goods packing to deform more than the first preset value after mechanical arm crawl；
The deficient crawl, to fall off after mechanical arm crawl or goods packing is after being crawled opposite sliding with mechanical arm.
4. the method as described in claim 1, which is characterized in that
Described image processing unit is additionally operable to obtain the volume of cargo according to described image, and the volume of the cargo is sent
To machine learning unit；
Training dataset is added in the volume of the cargo, the control instruction and the judging result by machine learning unit, and
Control parameter is adjusted according to training result；And it is read by control unit after preserving the control parameter after adjustment.
5. the method as described in claim 1, which is characterized in that
The mechanical arm, including support portion and crawl section；
The support portion is used to move crawl section to specified position,
The crawl section is for capturing cargo；
The crawl section is equipped with force snesor, for detecting grasp force；
The support portion is equipped with motion sensor, the movable information for detecting support portion, and the motion sensor includes adding
It is one or more in velocity sensor, foil gauge；
General Porcess Unit, for obtaining the quality of cargo according to the movable information；
The machine learning unit obtains the quality of the grasp force and the cargo, and by the grasp force, the cargo
Training dataset is added in quality, the control instruction and the judging result, and adjusts control parameter according to training result；And it will
Control parameter after adjustment is read after preserving by control unit.
6. method as claimed in claim 5, which is characterized in that
The movable information of the support portion, is also obtained by following manner,
Camera shoots the picture of support portion, and the picture of the support portion is sent to image processing unit；
Image processing unit is according to the picture of the support portion of different time, the movement velocity in the portion that is supported using calculus of finite differences, and
Moving displacement and acceleration of motion are obtained according to the movement velocity.
7. such as method described in claim 5 or 6, which is characterized in that
The General Porcess Unit is additionally operable to obtain the rigidity of cargo according to the movable information；
The method for obtaining cargo rigidity is the system for being reduced to be connected with spring between 2 mass blocks by cargo, and general
Processing unit handles vibration data according to 2DOF vibration equation to obtain the rigidity of the quality and spring of 2 mass blocks；
The machine learning unit obtains the quality and rigidity of the grasp force and the cargo, and by the grasp force, described
Training dataset is added in the quality and rigidity of cargo, the control instruction and the judging result, and is adjusted according to training result
Control parameter；And it is read by control unit after preserving the control parameter after adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711324287.3A CN108340367A (en) | 2017-12-13 | 2017-12-13 | Machine learning method for mechanical arm crawl |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711324287.3A CN108340367A (en) | 2017-12-13 | 2017-12-13 | Machine learning method for mechanical arm crawl |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108340367A true CN108340367A (en) | 2018-07-31 |
Family
ID=62963062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711324287.3A Pending CN108340367A (en) | 2017-12-13 | 2017-12-13 | Machine learning method for mechanical arm crawl |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108340367A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109093599A (en) * | 2018-09-07 | 2018-12-28 | 中科新松有限公司 | A kind of crawl teaching method and system |
| CN109333536A (en) * | 2018-10-26 | 2019-02-15 | 北京因时机器人科技有限公司 | A kind of robot and its grasping body method and apparatus |
| CN109376664A (en) * | 2018-10-29 | 2019-02-22 | 百度在线网络技术（北京）有限公司 | Machine learning training method, device, server and medium |
| CN109483534A (en) * | 2018-11-08 | 2019-03-19 | 腾讯科技（深圳）有限公司 | A kind of grasping body methods, devices and systems |
| CN110782038A (en) * | 2019-09-27 | 2020-02-11 | 深圳蓝胖子机器人有限公司 | Method and system for automatically marking training sample and method and system for supervised learning |
| CN111975764A (en) * | 2019-05-24 | 2020-11-24 | 京瓷办公信息系统株式会社 | Robot device and holding method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013052490A (en) * | 2011-09-06 | 2013-03-21 | Mitsubishi Electric Corp | Workpiece takeout device |
| CN106078748A (en) * | 2016-06-13 | 2016-11-09 | 北京理工大学 | A kind of robot based on hands, eye, arm coordinated manipulation captures the control method of object |
| CN106393102A (en) * | 2015-07-31 | 2017-02-15 | 发那科株式会社 | Machine learning device, robot system, and machine learning method |
| CN106671112A (en) * | 2016-12-13 | 2017-05-17 | 清华大学 | Judging method of grabbing stability of mechanical arm based on touch sensation array information |
| US20170157767A1 (en) * | 2015-12-07 | 2017-06-08 | Fanuc Corporation | Machine learning device, laminated core manufacturing apparatus, laminated core manufacturing system, and machine learning method for learning operation for stacking core sheets |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN107000208A (en) * | 2014-12-16 | 2017-08-01 | 亚马逊技术股份有限公司 | The robot crawl of article in inventory system |
| US20170252922A1 (en) * | 2016-03-03 | 2017-09-07 | Google Inc. | Deep machine learning methods and apparatus for robotic grasping |
-
2017
- 2017-12-13 CN CN201711324287.3A patent/CN108340367A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013052490A (en) * | 2011-09-06 | 2013-03-21 | Mitsubishi Electric Corp | Workpiece takeout device |
| CN107000208A (en) * | 2014-12-16 | 2017-08-01 | 亚马逊技术股份有限公司 | The robot crawl of article in inventory system |
| CN106393102A (en) * | 2015-07-31 | 2017-02-15 | 发那科株式会社 | Machine learning device, robot system, and machine learning method |
| US20170157767A1 (en) * | 2015-12-07 | 2017-06-08 | Fanuc Corporation | Machine learning device, laminated core manufacturing apparatus, laminated core manufacturing system, and machine learning method for learning operation for stacking core sheets |
| US20170252922A1 (en) * | 2016-03-03 | 2017-09-07 | Google Inc. | Deep machine learning methods and apparatus for robotic grasping |
| CN106078748A (en) * | 2016-06-13 | 2016-11-09 | 北京理工大学 | A kind of robot based on hands, eye, arm coordinated manipulation captures the control method of object |
| CN106671112A (en) * | 2016-12-13 | 2017-05-17 | 清华大学 | Judging method of grabbing stability of mechanical arm based on touch sensation array information |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 毛君: "《机械振动学》", 31 January 2016 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109093599A (en) * | 2018-09-07 | 2018-12-28 | 中科新松有限公司 | A kind of crawl teaching method and system |
| CN109333536A (en) * | 2018-10-26 | 2019-02-15 | 北京因时机器人科技有限公司 | A kind of robot and its grasping body method and apparatus |
| CN109376664A (en) * | 2018-10-29 | 2019-02-22 | 百度在线网络技术（北京）有限公司 | Machine learning training method, device, server and medium |
| CN109376664B (en) * | 2018-10-29 | 2021-03-09 | 百度在线网络技术（北京）有限公司 | Machine learning training method, device, server and medium |
| CN109483534A (en) * | 2018-11-08 | 2019-03-19 | 腾讯科技（深圳）有限公司 | A kind of grasping body methods, devices and systems |
| CN111975764A (en) * | 2019-05-24 | 2020-11-24 | 京瓷办公信息系统株式会社 | Robot device and holding method |
| CN111975764B (en) * | 2019-05-24 | 2023-06-27 | 京瓷办公信息系统株式会社 | Robot device and holding method |
| CN110782038A (en) * | 2019-09-27 | 2020-02-11 | 深圳蓝胖子机器人有限公司 | Method and system for automatically marking training sample and method and system for supervised learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108340367A (en) | Machine learning method for mechanical arm crawl | |
| CN111655433B (en) | Method for operating a robot | |
| CN110329710B (en) | Robot system with robot arm adsorption control mechanism and operation method thereof | |
| KR102517457B1 (en) | Update of local features model based on correction to robot action | |
| US10987807B2 (en) | Robotic system with object identification and handling mechanism and method of operation thereof | |
| JP6140204B2 (en) | Transport robot system with 3D sensor | |
| JP6873941B2 (en) | Robot work system and control method of robot work system | |
| DE102019130048B4 (en) | A robotic system with a sack loss management mechanism | |
| CN102189550B (en) | Robot having learning control function | |
| US9233469B2 (en) | Robotic system with 3D box location functionality | |
| CN108621125A (en) | Object manipulation device and its calibration method | |
| WO2020086619A1 (en) | Machine learning methods and apparatus for automated robotic placement of secured object in appropriate location | |
| US20150217975A1 (en) | Apparatus for controlling a mobile platform | |
| WO2019167765A1 (en) | Simulation device, method, and program | |
| WO2021178873A1 (en) | Imaging process for detecting failure modes | |
| JP2022108283A (en) | Robot system equipped with gripping mechanism | |
| WO2020222135A1 (en) | A logistic device | |
| CN112171664B (en) | Production line robot track compensation method, device and system based on visual identification | |
| KR102303521B1 (en) | Vibration damping method of multi-unloading manipulator for cargo | |
| US11059171B2 (en) | Method and apparatus for optimizing a target working line | |
| EP3753681A1 (en) | End manipulator for package picking and placing, corresponding machine and method for operating a machine | |
| JP2016221647A (en) | Grip control device, grip control method, and program | |
| CN108341273A (en) | Full-automatic de-stacking system | |
| CN117657756A (en) | Workpiece stirring system and robot | |
| CN117657754A (en) | Workpiece grabbing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180731 |