The invention generally relates to sortation systems, and relates in particular to robotic and other sortation systems that are intended to be used in dynamic environments requiring the sortation system to accommodate processing a variety of objects in both homogeneous and heterogeneous arrangements.
Many order fulfillment operations achieve high efficiency by employing a process in which orders are picked from warehouse shelves and placed into bins that are sorted downstream. At the sorting stage individual articles are identified, and multi-article orders are consolidated into a single bin or shelf location so that they may be packed and then shipped to customers. The process of sorting these articles has been done by hand. A human sorter picks an article from an incoming bin, finds the barcode on the object, scans the barcode with a handheld or fixed-mount barcode scanner, determines from the scanned barcode the appropriate bin or shelf location for the article, and then places the article in the so-determined bin or shelf location where all articles for that order go.
There remains a need, therefore, for an object identification, sortation, grasp selection, and motion planning system for a robotic system that is able to accommodate the automated identification and processing of a variety of objects in a variety of orientations.
In accordance with an embodiment, the invention provides a sortation system for providing processing of homogenous and non-homogenous objects in both structured and cluttered environments. The sortation system includes a programmable motion device including an end effector, a perception unit for recognizing any of the identity, location, or orientation of an object presented in a plurality of objects, a grasp selection system for selecting a grasp location on the object, the grasp location being chosen to provide a secure grasp of the object by the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination locations, and a motion planning system for providing a motion path for the transport of the object when grasped by the end effector from the plurality of objects to the one of the plurality of destination locations, wherein the motion path is chosen to provide a path from the plurality of objects to the one of the plurality of destination locations.
In accordance with another embodiment, the invention provides a sortation system including a programmable motion device for use in an environment that includes an input area containing objects to be processed, and destination locations at which processed objects are to be placed. The sortation system includes a perception unit for providing data representative of an image of at least a portion of the input area containing objects to be processed, an end effector for engaging objects in the input area, a grasp location selection system for determining a grasp location for grasping an object in the input area containing objects to be processed, and a grasp direction selection system for determining a grasp direction from which to grasp the object in the input area containing objects to be processed.
In accordance with a further embodiment, the invention provides a sortation method of processing objects received at an input area into destination locations. The method includes the steps of providing data representative of an image of at least a portion of the input area, determining a grasp location for grasping an object in the input area, determining a grasp direction from which to grasp the object in the input area, and engaging the object in the input area using an end effector.
The following description may be further understood with reference to the accompanying drawings in which:
The drawings are shown for illustrative purposes only.
In accordance with an embodiment, the invention provides a novel object scanning system, grasp selection and planning system and motion planning system for the purposes of automatically grasping and moving individual objects in a set for a variety of purposes. In applications such as order fulfillment, articles or goods are collected into heterogeneous sets and need to be sorted. Individual objects need to be identified and then routed to object-specific locations. The described system reliably automates the identification of such objects by employing both automated scanners (e.g., barcode scanner) and a robotic arm.
Sorting for order fulfillment is one application for automatically identifying objects from a heterogeneous object stream. Further, scanners have a wide variety of uses including identifying information for the object (such as a barcode, QR code, UPC code, other identification codes, information read from a label on the object, or size, weight and/or shape information), or tracking parcels. The described system may have many uses in the automatic identification and sortation of objects.
Such a system automates part of the sorting process in conjunction with a robotic pick and place system, and in particular, the step of identifying picked articles. A robotic arm, for example, picks an article from a bin, places the article in front of a scanner, and then, having obtained identification information for the article (such as a barcode, QR codes, UPC codes, other identification codes, information read from a label on the object, or size, weight and/or shape information), places the item in the appropriate bin or shelf location. Since certain scanners employ cameras or lasers to scan 1D or 2D symbologies printed on labels affixed to articles, the barcodes must be visible to the scanner's sensors for successful scanning in order to automatically identify items in a heterogeneous stream of arbitrary articles, as in a jumbled set of articles found in a bin.
Further applications for grasping systems of the invention include sortation for a wide variety of applications, including order fulfillment, collection of objects for shipping, and collection of objects for inventory purposes etc. Further, such grasp planning systems of the invention may be used for loading break-packs (organized packages for later breaking apart at a different location), palletization (loading pallets), de-palletization, truck loading, truck unloading etc. As used herein, the term “destination locations” involves the placement of objects at locations for any purpose, not necessarily a final destination, and not necessarily for sortation for order fulfillment.
In accordance with various embodiments, therefore, the invention provides a method for determining the identity of an object from a collection of objects, as well as a method for perceiving the information regarding an object employing one or more perception units (cameras or scanners), and a robotic arm with an end-effector for holding the object. The invention further provides a method for determining a sequence of placements of a robot end-effector so as to minimize the time it takes a configuration of one or more cameras or scanners to successfully scan an object, and a method for scanning the identification information for the object (such as a barcode, QR codes, UPC codes, other identification codes, information read from a label on the object, or size, weight and/or shape information) by employing a scanner as an end-effector on a robotic arm.
An important aspect is the ability to identify identification or mailing information for the objects (such as a barcode, QR codes, UPC codes, other identification codes, information read from a label on the object, or size, weight and/or shape information) by employing a programmable motion device such as a robot arm, to pick up individual objects and place them in front of one or more scanners. In accordance with other embodiments, the programmable motion device may include a parallel arm robot (Delta-type arm) or a linear indexing pick and place system. Automated scanning systems would be unable to see, for example, labels or barcodes on objects that are presented in a way that this information is not exposed or visible.
Important components of an automated identification system in accordance with an embodiment of the present invention are shown in
As further shown in
Again, with reference to
The sortation system 10 may further include a robot or other programmable motion device in the sortation environment, a target station 30 that includes a number of bins 32 into which objects may be placed by the robot after identification and grasping. A central computing and control system 34 may communicate with the perception unit 26 and the image display system 28, as well as with the articulated arm 12 via wireless communication, or, in certain embodiments, the central computing and control system may be provided within the base section 20 of the articulated arm.
The system provides in a specific embodiment, an automated article identification system that includes a robotic pick and place system that is able to pick objects up, move them in space, and place them. The system also includes the set of objects themselves to be identified; the manner in which inbound objects are organized, commonly in a heterogeneous pile in a bin or in a line on a conveyor; the manner in which outbound objects are organized, commonly in an array of outbound bins, or shelf cubbies; the manner in which objects are labeled with barcodes or radio-frequency identification tags; a fixed primary scanner operating above the incoming stream of objects; a scanning station where one or more scanners and illuminators are activated when the object is held at the station; and a central computing and control system determines the appropriate location for placing the object, which is dependent on the object's decoded barcode.
As noted, the robotic pick and place system may include a robotic arm equipped with sensors and computing, that when combined exhibits the following capabilities: (a) it is able to pick objects up from a specified class of objects, and separate them from a stream of heterogeneous objects, whether they are jumbled in a bin, or are singulated on a motorized or gravity conveyor system; (b) it is able to move the object to arbitrary places within its workspace; (c) it is able to place objects in an outgoing bin or shelf location in its workspace; and (d) it is able to generate a map of objects that it is able to pick, represented as a candidate set of grasp points in the workcell, and as a list of polytopes enclosing the object in space.
The allowable objects are determined by the capabilities of the robotic pick and place system. Their size, weight and geometry are assumed to be such that the robotic pick and place system is able to pick, move and place them. These may be any kind of ordered goods, packages, parcels, or other articles that benefit from automated sorting. Each object is associated with a UPC code or other unique object identifier, which identifies the object or its destination.
The invention also provides a robotic system that permits a human worker to assist the robotic system in object sortation, particularly in an environment that presents objects in a non-ordered fashion and in which human workers are also present. As good as a perception unit may be, such an environment almost ensures that the robotic system will encounter some configuration of objects that the robotic system cannot handle. In accordance with various embodiments of the invention, it may be desirable to enable the human worker to assist the robotic system.
In accordance with an embodiment of the invention therefore, the invention provides a method that allows a human worker to look up at an image of a collection of objects as the robotic system perceives the collection of objects, and aid the robotic system by identifying one or more grasp locations for one or more objects. The system may also be used to delete bad grasp locations that the robotic system has identified. In addition, the 2D/3D imagery in conjunction with the human worker selected grasp locations can be used as input to machine learning algorithms to help the robotic system learn how to deal with such cases in the future, thereby reducing the need for operator assistance over time.
As discussed above, the system of an embodiment includes a perception unit 26 that is mounted above a bin of objects to be sorted, looking down into the bin. A combination of 2D and 3D (depth) data is acquired. The system uses this imagery and a variety of algorithms to generate a set of candidate grasp locations for the objects in the bin.
The image also shows two grasp locations 60 that are not good grasp locations, where the perception unit did not correctly perceive the object 54, and in particular, did not perceive that another object 48 is lying on top of the object 54. The object 54 cannot be fully perceived by the detection system, and as result, the perception unit considers the object 54 to be two different objects and has proposed candidate grasps of such two different objects. If the system executes a grasp at either of the grasp locations 60, it will either fail to acquire the object due to a bad grasp point where a vacuum seal will not occur (e.g., on the right), or will acquire the object at a grasp location that is very far from the center of mass of the object (e.g., on the left) and thereby induce a great deal of instability during any attempted transport. Each of these results is undesirable.
As shown in
If a good grasp location is not generated for an object by the robotic system, the human worker may, again using the touch screen interface, select an appropriate grasp location on the touch screen. The sortation system may then queue this human-determined candidate grasp location for that object and execute that grasp location for similar objects during the process of clearing the bin. Every bin image that is modified by a human worker will then be stored and used as input to machine learning algorithms. By identifying bad or good grasp locations on the image, a correlation is established between features in the 2D/3D images and the idea of good or bad grasp locations. Using this data and these correlations as input to machine learning algorithms, the system may eventually learn, for each image presented to it, where to best grasp an object, and where to avoid grasping an object.
In accordance with further embodiments, the system may prompt the human worker with a proposed grasp location, and the person may either confirm that the location is a good selection (e.g., by touching it), or may indicate that the proposed grasp location is not a good location (e.g., by swiping the location—touching and dragging). Following such interaction with a human worker, the system may learn optimal grasp locations for objects that it may come to recognize and know. Further embodiments may involve the use of simulation, either for obtaining feedback from a human worker, or for mapping out various grasp location selections for movement.
As shown in
As shown in
The invention provides therefore in certain embodiments that grasp optimization may be based on determination of surface normal, i.e., moving the end effector to be normal to the perceived surface of the object (as opposed to vertical or “gantry” picks), and that such grasp points may be chosen using fiducial features as grasp points, such as picking on a barcode, given that barcodes are almost always applied to a flat spot on the object. The invention also provides operator assist, where an object that the system has repeatedly failed to grasp has a correct grasp point identified by a human, as well as operator assist, where the operator identifies bad grasp plans, thus removing them and saving the time of the system attempting to execute them.
In accordance with various embodiments therefore, the invention further provides a sortation system that may learn object grasp locations from experience and human guidance. Systems designed to work in the same environments as human workers will face an enormous variety of objects, poses, etc. This enormous variety almost ensures that the robotic system will encounter some configuration of object(s) that it cannot handle optimally; at such times, it is desirable to enable a human operator to assist the system and have the system learn from non-optimal grasps.
The 2D/3D imagery in conjunction with the human-selected grasp points can be used as input to machine learning algorithms, to help the sortation system learn how to deal with such cases in the future, thereby reducing the need for operator assistance over time. A combination of 2D and 3D (depth) data is acquired, the system uses this imagery and a variety of algorithms to generate a set of candidate grasp points for the objects in the bin.
The system optimizes grasp points based on a wide range of features, either extracted offline or online, tailored to the gripper's characteristics. The properties of the suction cup influence its adaptability to the underlying surface, hence an optimal grasp is more likely to be achieved when picking on the estimated surface normal of an object rather than performing vertical gantry picks common to current industrial applications.
In addition to geometric information, the system uses appearance-based features from depth sensors that may not always be accurate enough to provide sufficient information about graspability. For example, the system can learn the location of fiducials such as barcodes on the object, which can be used as indicator for a surface patch that is flat and impermeable, hence suitable for a suction cup. One such example is shipping boxes and bags, which tend to have the shipping label at the object's center of mass and provide an impermeable surface, as opposed to the raw bag material which might be slightly porous and hence not present a good grasp.
Every bin image that is modified by a human operator will then be stored and used as input to machine learning algorithms. By identifying bad or good grasp points on the image, a correlation is established between features in the 2D/3D imagery and the idea of good or bad grasp points; using this data and these correlations as input to machine learning algorithms, the system can eventually learn, for each image presented to it, where to grasp and where to avoid.
This information is added to experience based data the system collects with every pick attempt, successful or not. Over time the robot learns to avoid features that result in unsuccessful grasps, either specific to an object type or to a surface/material type. For example, the robot may prefer to avoid picks on shrink wrap, no matter which object it is applied to, but may only prefer to place the grasp near fiducials on certain object types such as shipping bags.
This learning can be accelerated by off-line generation of human-corrected images. For instance, a human could be presented with thousands of images from previous system operation and manually annotate good and bad grasp points on each one. This would generate a large amount of data that could also be input into the machine learning algorithms to enhance the speed and efficacy of the system learning.
In addition to experience based or human expert based training data, a large set of labeled training data can be generated based on a detailed object model in physics simulation making use of known gripper and object characteristics. This allows fast and dense generation of graspability data over a large set of objects, as this process is not limited by the speed of the physical robotic system or human input.
The method as described thus far focuses on providing data for offline learning algorithms or on real-time correction of the robotic system. There is also the possibility of using this method in response to a robotic system asking for help.
There exists the scenario where a sortation system has emptied all objects out of a bin but one. The system has tried and failed several times to grasp this item. At this point, the robotic system can send for help by transmitting the image from its perception unit to a human operator. That human operator can, by touching the image, identify the grasp point that the system should use to acquire the object, thereby allowing the human to compensate for the inevitable shortcomings of the perception unit.
In accordance with certain embodiments, the system may also choose to “stir” the presented input objects if the system is not able to achieve a successful grasp after a number of attempts, either prior to human interaction or after following the human's guidance. The action of “stirring” objects will re-arrange objects such that a new set of grasps can be computed, which may lead to successful grasp attempts. For example, if an object is standing upright, presenting itself with a surface that the robot is not able to grasp, the robot may choose to knock the object over in order to pick it from the side.
In accordance with a further embodiment of the invention, the system may plan grasp approaches that take into account elements of the environment that may obstruct movement using an optical approach path. For example, and with reference to
As shown in
Systems in accordance with further embodiments of the present invention may also use cameras to check or monitor a grasp.
In further embodiments, the robotic system may also employ motion planning using a trajectory database that is dynamically updated over time, and is indexed by customer metrics. The problem domains contain a mix of changing and unchanging components in the environment. For example, the objects that are presented to the system are often presented in random configurations, but the targets they need to be put into are often fixed and do not change over the entire operation.
One use of the trajectory database is to exploit the unchanging parts of the environment by pre-computing and saving into a database of trajectories that efficiently and robustly move the system through these spaces. Another use of the trajectory database is to constantly improve the performance of the system over the lifetime of its operation. The database communicates with a planning server that is continuously planning trajectories from the various starts to the various goals, to have a large and varied set of trajectories for achieving any particular task.
An advantage of the varied set is robustness to small changes in the environment and to different-sized objects the system might be handling: instead of re-planning in these situations, the system iterates through the database until it finds a trajectory that is collision-free, safe and robust for the new situation. The system may therefore generalize across a variety of environments without having to re-plan the motions.
Another advantage of the varied set is the ability to address several customer metrics without having to re-plan motions. The database is sorted and indexed by customer metrics like time, robustness, safety, distance to obstacles etc. and given a new customer metric, all the database needs to do is to reevaluate the metric on the existing trajectories, thereby resorting the list of trajectories, and automatically producing the best trajectory that satisfies the new customer metric without having to re-plan motions.
Another advantage is that even if a trajectory is invalid due to changes in the environment or customer metrics, the stored trajectories may serve as seeds for trajectory optimization algorithms, thereby speeding up the generation of new trajectories in new situations. A further advantage is that the database offers a mechanism for different systems to share information remotely or over the cloud. By all indexing into the same database, different systems working in different places can have a common infrastructure for sharing information and planned trajectories.
Those skilled in the art will appreciate that numerous modifications and variations may be made to the above disclosed embodiments without departing from the spirit and scope of the present invention.
The present application is a continuation of U.S. patent application Ser. No. 16/775,798, filed Jan. 29, 2020, now U.S. Pat. No. 11,420,329, issued Aug. 23, 2022, which is a continuation of U.S. patent application Ser. No. 15/348,498, filed Nov. 10, 2016, now U.S. Pat. No. 10,625,432, issued Apr. 21, 2020, which claims priority to U.S. Provisional Patent Application Ser. No. 62/255,069, filed Nov. 13, 2015, as well as to U.S. Provisional Patent Application Ser. No. 62/277,234, filed Jan. 11, 2016, the disclosures of which are hereby incorporated by reference in their entireties.
Number | Name | Date | Kind |
---|---|---|---|
2853333 | Littell | Sep 1958 | A |
3005652 | Helm | Oct 1961 | A |
3195941 | Morey | Jul 1965 | A |
3637249 | Kuhl et al. | Jan 1972 | A |
4389064 | Sema | Jun 1983 | A |
4557659 | Scaglia | Dec 1985 | A |
4786847 | Daggett et al. | Nov 1988 | A |
4828304 | Honsha | May 1989 | A |
4896357 | Hatano et al. | Jan 1990 | A |
5207465 | Rich | May 1993 | A |
5244338 | White | Sep 1993 | A |
5752729 | Crozier et al. | May 1998 | A |
5794789 | Payson et al. | Aug 1998 | A |
5865487 | Gore et al. | Feb 1999 | A |
6015174 | Raes et al. | Jan 2000 | A |
6060677 | Ulrichsen et al. | May 2000 | A |
6244640 | LeBricquer et al. | Jun 2001 | B1 |
6721444 | Gu | Apr 2004 | B1 |
6817639 | Schmalz et al. | Nov 2004 | B2 |
7313464 | Perreault | Dec 2007 | B1 |
7474939 | Oda | Jan 2009 | B2 |
7677622 | Dunkmann et al. | Mar 2010 | B2 |
8070203 | Schaumberger | Dec 2011 | B2 |
8132835 | Ban et al. | Mar 2012 | B2 |
8267386 | Schaaf et al. | Sep 2012 | B2 |
8874270 | Ando | Oct 2014 | B2 |
8936291 | Yasuda et al. | Jan 2015 | B2 |
9102053 | Suzuki | Aug 2015 | B2 |
9102055 | Konolige et al. | Aug 2015 | B1 |
9227323 | Konolige | Jan 2016 | B1 |
9259844 | Xu | Feb 2016 | B2 |
9266237 | Nomura | Feb 2016 | B2 |
9283680 | Yasuda | Mar 2016 | B2 |
9486926 | Kawano | Nov 2016 | B2 |
9492923 | Wellman et al. | Nov 2016 | B2 |
9604363 | Ban | Mar 2017 | B2 |
9623570 | Krahn et al. | Apr 2017 | B1 |
9656813 | Dunkmann et al. | May 2017 | B2 |
9687982 | Jules | Jun 2017 | B1 |
9687983 | Prats | Jun 2017 | B1 |
10625432 | Wagner | Apr 2020 | B2 |
11420329 | Wagner | Aug 2022 | B2 |
20010056313 | Osborne, Jr. | Dec 2001 | A1 |
20020147568 | Wenzel et al. | Oct 2002 | A1 |
20030038491 | Schmalz et al. | Feb 2003 | A1 |
20040232716 | Reed et al. | Nov 2004 | A1 |
20080181485 | Beis | Jul 2008 | A1 |
20100109360 | Meisho | May 2010 | A1 |
20100125361 | Mougin et al. | May 2010 | A1 |
20100175487 | Sato | Jul 2010 | A1 |
20100234857 | Itkowitz et al. | Sep 2010 | A1 |
20110320036 | Freudelsperger | Dec 2011 | A1 |
20130054029 | Huang | Feb 2013 | A1 |
20130110280 | Folk | May 2013 | A1 |
20130129464 | Regan et al. | May 2013 | A1 |
20130166061 | Yamamoto | Jun 2013 | A1 |
20130245824 | Barajas | Sep 2013 | A1 |
20130343640 | Buehler | Dec 2013 | A1 |
20130345872 | Brooks et al. | Dec 2013 | A1 |
20140005831 | Naderer et al. | Jan 2014 | A1 |
20140067121 | Brooks et al. | Mar 2014 | A1 |
20140067127 | Gatou | Mar 2014 | A1 |
20140195979 | Branton | Jul 2014 | A1 |
20140298231 | Saito | Oct 2014 | A1 |
20140305847 | Kudrus | Oct 2014 | A1 |
20150057793 | Kawano | Feb 2015 | A1 |
20150073589 | Khodl et al. | Mar 2015 | A1 |
20150081090 | Dong | Mar 2015 | A1 |
20150190925 | Hoffman | Jul 2015 | A1 |
20150224650 | Xu et al. | Aug 2015 | A1 |
20150306634 | Maeda et al. | Oct 2015 | A1 |
20150306770 | Mittal et al. | Oct 2015 | A1 |
20150328779 | Bowman et al. | Nov 2015 | A1 |
20150346708 | Mattern et al. | Dec 2015 | A1 |
20150352717 | Mundt et al. | Dec 2015 | A1 |
20150352721 | Wicks | Dec 2015 | A1 |
20150375398 | Penn et al. | Dec 2015 | A1 |
20150375401 | Dunkmann et al. | Dec 2015 | A1 |
20160075521 | Puchwein et al. | Mar 2016 | A1 |
20160101526 | Saito et al. | Apr 2016 | A1 |
20160136816 | Pistorino | May 2016 | A1 |
20160167227 | Wellman et al. | Jun 2016 | A1 |
20160221187 | Bradski et al. | Aug 2016 | A1 |
20160243704 | Vakanski et al. | Aug 2016 | A1 |
20160271805 | Kuolt et al. | Sep 2016 | A1 |
20160347545 | Lindbo et al. | Dec 2016 | A1 |
20160379076 | Nobuoka et al. | Dec 2016 | A1 |
20170024896 | Houghton et al. | Jan 2017 | A1 |
20170050315 | Sileane | Feb 2017 | A1 |
20170066597 | Hiroi | Mar 2017 | A1 |
20170080566 | Stubbs et al. | Mar 2017 | A1 |
20170106532 | Wellman | Apr 2017 | A1 |
20180085922 | Ooba | Mar 2018 | A1 |
20200189105 | Wen | Jun 2020 | A1 |
20200331144 | Huang | Oct 2020 | A1 |
Number | Date | Country |
---|---|---|
2928645 | Apr 2015 | CA |
102448679 | May 2012 | CN |
102922521 | Feb 2013 | CN |
103157607 | Jun 2013 | CN |
103464383 | Dec 2013 | CN |
103645724 | Mar 2014 | CN |
103963058 | Aug 2014 | CN |
203955558 | Nov 2014 | CN |
3810989 | Aug 1989 | DE |
10121344 | Nov 2002 | DE |
10319253 | Dec 2004 | DE |
102007028680 | Dec 2008 | DE |
102007038834 | Feb 2009 | DE |
102010002317 | Aug 2011 | DE |
102012102333 | Sep 2013 | DE |
0317020 | May 1989 | EP |
1256421 | Nov 2002 | EP |
2233400 | Sep 2010 | EP |
2960024 | Dec 2015 | EP |
769470 | Mar 1995 | JP |
2010201536 | Sep 2010 | JP |
2015044274 | Mar 2015 | JP |
2007182286 | Jul 2019 | JP |
2010034044 | Apr 2010 | WO |
2010099873 | Sep 2010 | WO |
2014166650 | Oct 2014 | WO |
2015035300 | Mar 2015 | WO |
2015118171 | Aug 2015 | WO |
2015162390 | Oct 2015 | WO |
Entry |
---|
Notice on the Second Office Action, along with its English translation, issued by the China National Intellectual Property Administration in related Chinese Patent Application No. 202111071608.X on Jul. 6, 2023, 8 pages. |
Bohg et al., “Data-Driven Grasp Synthesis-A Su,” IEEE Transactions on Robotics, IEEE Service Center, Piscataway, NJ, US, vol. 30, No. 2, Apr. 1, 2014, pp. 289-309. |
Cipolla et al., “Visually guided grasping in unstructured environments,” Robotics and Autonomous Systems, Elsevier Science Publishers, Amsterdam, NL, vol. 19, No. 3-4, Mar. 1, 1997, pp. 337-346. |
Communication pursuant to Article 94(3) EPC issued by the European Patent Office in related European Patent Application No. 16805614.1 on Oct. 14, 2020, 6 pages. |
Communication pursuant to Rules 161(1) and 162 EPC issued by the European Patent Office in related European Patent Application No. 16805614.1 on Jun. 20, 2018, 3 pages. |
Examiner's Report issued by the Innovation, Science and Economic Development Canada (Canadian Intellectual Property Office) in related Canadian Patent Application No. 3,107,257 on Mar. 18, 2022, 6 pages. |
Final Office Action issued by the U.S. Patent and Trademark Office on Mar. 9, 2018 in related U.S. Appl. No. 15/348,498, 25 pages. |
Final Office Action issued by the U.S. Patent and Trademark Office on Jun. 9, 2019 in related U.S. Appl. No. 15/348,498, 26 pages. |
First Office Action, and its English translation, issued by the China National Intellectual Property Administration in related Chinese Patent Application No. 201680066557.2 on Jul. 28, 2020, 20 pages. |
Hebert, et al., “A Robotic Gripper System for Limp Material Manipulation: Hardware and Software Development and Integration,” Proceedings of the 1997 IEEE International Conference on Robotics and Automation, Albuquerque, New Mexico, Apr. 1997, pp. 15-21. |
International Preliminary Report on Patentability issued by the International Bureau of WIPO in related International Application No. PCT/US2016/061414 on May 15, 2018, 10 pages. |
International Search Report and Written Opinion issued by the International Searching Authority, the European Patent Office, in related International Application No. PCT/US2016/061414 on Mar. 22, 2017, 14 pages. |
Klingbeil et al., Grasping with application to an autonomous checkout robot, Robotics and Automation (ICRA), 2011 IEEE Inernational Conference ON, IEEE, May 9, 2011, pp. 2837-2844. |
Liu, et al., “Hand-Arm Coordination for a Tomato Harvesting Robot Based on Commercial Manipulator,” Proceeding of the IEEE, International Conference on Robotics and Biomimetics (ROBIO), Shenzhen, China, Dec. 2013, pp. 2715-2720. |
Non-Final Office Action issued by the U.S. Patent and Trademark Office on Aug. 17, 2017 in related U.S. Appl. No. 15/348,498, 20 pages. |
Non-Final Office Action issued by the U.S. Patent and Trademark Office on Sep. 25, 2018 in related U.S. Appl. No. 15/348,498, 28 pages. |
Non-Final Office Action issued by the United States Patent and Trademark Office in related U.S. Appl. No. 16/775,798 on Nov. 26, 2021, 30 pages. |
Notice of Second Office Action and Second Office Action, along with its English translation, issued by the China National Intellectual Property Administration in related Chinese Patent Application No. 201680066557.2 on Mar. 22, 2021, 17 pages. |
Office Action issued by the Innovation, Science and Economic Development Canada in related Canadian Patent Application No. 3,004,711 on Jun. 17, 2019, 8 pages. |
Office Action issued by the Innovation, Science and Economic Development Canada in related Canadian Patent Application No. 3,004,711 on Mar. 10, 2020, 8 pages. |
Office Action issued by the Innovation, Science and Economic Development Canada in related Canadian Patent Application No. 3,004,711 on Oct. 20, 2020, 5 pages. |
Rembold et al., “Object turning for barcode search,” Proceedings, 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000), Oct. 31-Nov. 5, 2000, vol. 2, Oct. 31, 2000 (Oct. 31, 2000), p. 1267. |
EPO Form 1507N (Communication) and the European Search Report issued by the European Patent Office in related European Patent Application No. 22172900.7 on Oct. 19, 2022, 14 pages. |
Le et al., Learning to grasp objects with multiple contact points, 2010 IEEE International Conference on Robotics and Automation: ICRA 2010; Anchorage, Alaska, USA, May 3-8, 2010, IEEE, Piscataway, NJ, USA, May 3, 2010 (May 3, 2010), pp. 5062-5069, XP031743443, ISBN: 978-1-42445038-1. |
Notice on the First Office Action, along with its English translation, issued by the China National Intellectual Property Administration in related Chinese Patent Application No. 202111071608.X on Dec. 29, 2022, 11 pages. |
Notice on the Third Office Action issued by the China National Intellectual Property Administration in related Chinese Patent Application No. 202111071608.X on Nov. 24, 2023, 9 pages. |
Number | Date | Country | |
---|---|---|---|
20220314447 A1 | Oct 2022 | US |
Number | Date | Country | |
---|---|---|---|
62277234 | Jan 2016 | US | |
62255069 | Nov 2015 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 16775798 | Jan 2020 | US |
Child | 17843666 | US | |
Parent | 15348498 | Nov 2016 | US |
Child | 16775798 | US |