Jump to content

Universal Robotics

Add links
From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by Swco2dude (talk | contribs) at 21:48, 26 September 2017 (fixed problems). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.
Universal Logic, Inc.
IndustryAutomation; machine vision; software; artificial intelligence; big data; cybernetics
Founded2001, commenced operations 2008
HeadquartersNashville, Tennessee
Key people
David A. Peters, CEO
Hob Wubbena, VP
ProductsNeocortex Goods to Robot Cells, Neocortex, Spatial Vision, Unlimited Depalletization, 3D Inspection, engineering services
Websitehttp://www.universallogic.com

Universal Logic, Inc. , formerly Universal Robotics, Inc., is an artificial intelligence software engineering and robotics integration company headquartered in Nashville, Tennessee.[1][2][3][4]The company offers supply chains complete material handling systems for high-mix, high-volume applications. The systems integrate artificial intelligence with vision, grasping, and motion control to give machines flexibility at high speed.[5][6]

Founded in 2008, the company specializes in complex or chaotic processes not previously automated.[7] The technology was funded by DARPA and NASA, and was originally co-developed through a 7-year[8] partnership between NASA and Vanderbilt University[7] and is employed in NASA’s Robonaut.[5] In 2015, the company received its first million-dollar contract.[9]

NASA Robonaut

Products and services

Universal offers a family of flexible robot cells and two modular software product families: Neocortex Goods to Robot Cells, Neocortex real-time artificial intelligence software, and Spatial Vision 3D sensing, vision guidance and inspection.[10][11] Applications[12] include robotic order fulfillment, random bin picking, random bag picking, 3D inspection, part induction, robotic kitting, machine tending, box moving, and robotic depalletizing.[13][14]

Neocortex Goods to Robot (G2R) Cells: Flexible Robot Cells

Universal introduced a family of artificial intelligence-based robot cells in August, 2016. The cells, called Neocortex Goods to Robot (G2R) Cells, provide flexible piece-picking for order fulfillment, random bin picking, machine tending, line loading, or part induction.[15] Average robotic cell pick rates average from 600 to 1400 per hour, with peaks to 27 per minute.[16] Reliability of the cells average 99.1% to 99.98%, with 3D accuracy from 0.25mm to 12mm. SKU pick accuracy can be 100% verified.[17] Each cell includes an industrial 6-axis robot with gripper, an industrial PC with a human/machine interface, artificial intelligence software (Neocortex), 3D vision guidance software (Spatial Vision), sensors, safety barriers, and communication interface. It also includes interface to WMS software. The Cell handles sensor connections, calibration, PLC and robot communication, path planning, obstacle avoidance, vision guidance, inspection, database management, and learning. [18][19] Each cell comes on a moveable forklift skid and can be operating in less than a day.[20][21]They require power, compressed air, and a hard-wired internet connection.[22]

Neocortex: Artificial Intelligence Software

Neocortex is a form of Artificial Intelligence (AI) that allows machines, such as robots, to learn from their experiences in the physical world rather than being programmed to act.[23] It provides object recognition, robot path planning, and grasp analysis.[24] It resides on a client computer in the robot cell, and may also reside as a server in the cloud or in a computer room.

Neocortex is based on the pattern of learning in nature which is common to all creatures.[25] The patent-protected software allows a robot to recognize a wide range of objects, with or without models.[7][26] NVIDIA GPUs are used to speed up processing.[27] Neocortex also uses a range of tools and techniques from deep learning to neural networks to improve probabilities of success by coupling the software's previous experiences with current observations.[28][29]

Neocortex responds dynamically to change with real-time sensory input and matches what is known with what it is learning.[30] Its database is aggregated over time, increasing what is known. Neocortex enables a robot to pick different items such as cartons, bottles, tubes, bags, cans for a given task.[31][32]

Neocortex technology was developed at Vanderbilt University and NASA, where it was used as “brain” of Robonaut.[33][34]

Spatial Vision: 3D Vision Software

Universal’s Spatial Vision software was created during the development of Neocortex.[23] It provides 3D vision guidance and vision inspection.[35] It also provides sensor connection, calibration of sensors and robot, PLC & robot communication, robot path planning, obstacle avoidance, and database management.[36]

Spatial Vision software processes images from a mix of off-the-shelf webcam, single camera, camera pairs (stereopsis), multiple cameras, time-of-flight sensor, structured light sensor, infrared sensor, and LIDAR to generate a multi-dimensional scan.[37][38][30] The sensors can be mounted in a fixed location, on the robot arm, or both. It provides 3D vision guidance by recognizing and tracking objects relative to its surroundings.[39][40]

Spatial Vision provides 3D inspection of objects up to the size of a pallet.[41] In the case of pallets, it identifies a wide range of defects such as raised nails, damaged wood, split or loose boards, or missing wood.[42][43]

In 2011, Spatial Vision provided the first industrial application using the Microsoft Kinect structured light sensor to provide real-time 3D. Then, in 2012, it was the first industrial application using four simultaneous Microsoft Kinect structured light sensors.[44]

In 2011, as part of an ongoing collaboration with Motoman Robotics, a division of Yaskawa America, Inc., Universal launched MotoSight 3D Spatial Vision, a 3D vision system for cost-effective, flexible and scalable real-time guidance for Motoman robots.[2][23] The system determines six degrees of object position and pose information (X, Y, Z, Rx, Ry, Rz) and is accurate within 2–4 mm with off-the-shelf Logitech 9000 webcams.[45]

Note: Universal’s Autonomy software is motion control software that automates robot programming[33] for moving a robot at high speed using a variety of sensor inputs. It provides real-time autonomous reaction for robots as well as motion planning and collision avoidance.

Applications

Airline Beverage Replenishment

Universal collaborated with NextGen Robotics in 2017 to introduce a Neocortex G2R Cell for replenishing airline drink cans located in trolley cart drawers in an airline hub catering kitchen between flights.[46][47] Neocortex determines which cans are empty, partially used, or unopened as well as the brand of drink and sorts them accordingly. Then it reuses unopened cans and supplements the drawer as needed.[48] [49]

E-Commerce Consumer Goods Order Fulfillment

In 2016, Universal introduced the Neocortex Goods to Robot (G2R) Cell for order fulfillment. It picks a mix of SKUs or objects at 800 to 1,400 per hour. It identifies bottles, tubes, bags in various colors with or without labels. It can pick from totes, bins, trays or cases, and place into shipping bags, boxes or cartons. Barcode scanners are optionally available for read the SKU code for 100% verfication to order when picking. The skid-mounted cell includes artificial intelligence software, 3D vision guidance software, 6-axis robot with EOAT (end of arm tool), safety barriers, communication interface to a PLC and WMS, panel-mounted operator interface. The Cell is maintained through remote diagnostics and software upgrades via Universal.[50][51][52]

Pharmaceutical Order Fulfillment

In 2015, Universal formed a strategic partnership with R/X Automation Solutions and Yaskawa America - Motoman Robotics to deliver a robotic pharmacy order fulfillment system.[53] In 2016, the partnership introduced a RX Unit Pick Workcell that is a fully automated robotic pharmacy order fulfillment system capable of handling thousands of different pre-packaged medicine with 100% verification for mail order delivery.[54][55]

Random Bin Picking

The Random Bin Picking application enables a robot to automatically move a number of randomly placed parts, regardless of their orientation in bins up to 48 inches deep.[56] It picks parts at up to 1,400 per hour. Whether loosely or tightly packed, either on the floor, conveyor or bin/container, the parts can be in any orientation. It provides 3D position and pose to the robot regardless of the presence or type of labels, the object material type, and whether the parts are in a single layer or randomly packed.

Box Moving & Depalletizing

The Random Box Moving application moves or de-palletizes up to 500 - 900 cases per hour of cartons in any orientation with any combination of labels.[57] The application handles box sizes from 6 to 48 inches, any dimension, and pallets up to 60 inches in height (72" high optional). The boxes can also be in any random orientation or location. It unloads partial, mixed, or full pallets of loosely or tightly packed boxes – regardless of the number of layers, as well as determines single double picks on the fly. It moves boxes from floor to conveyor, table to pallet, pallet to conveyor, truck to conveyor, or assembly line to staging area.[58][59] Neocortex assists proper identification of mixed-size boxes.[7][60]

Random Bag Picking

The Random Bag Picking application enables a robot to automatically move a number of randomly placed bags at 700 - 1,000 bags per hour, regardless of their orientation or how many layers are ‘piled’ together up to 60 inches deep. The application dynamically provides 3D guidance to the robot for bags regardless of labels or material type..[61][62][63]

3D Inspection

The Universal 3D pallet inspection[64] replicates manual inspection of both sides of a pallet through an automated 3D vision system. It identifies a wide range of defects, including raised nails, and wood damage – whether split, loose, or missing – at production line speed. CHEP, the global leader in pallet and container pooling services, uses this for automated 3D pallet inspection.[42]

Engineering

Universal’s engineering team works in technologies related to sensing, manipulation and artificial intelligence. The company offers customers engineering services in the following areas:

Leadership

Universal Robotics was founded and is led by David Peters, CEO[66] and his brother[33] Dr. Alan Peters, CTO.[67] Dr. Peters is the principal architect of Neocortex and is an Associate Professor at Vanderbilt University in Nashville, Tennessee.[68] Hob Wubbena is the company’s Vice President of Strategic Planning and Marketing.[69][70]

References

  1. ^ "Universal Robotics Announces Expansion of Artificial Intelligence Robot Cells and a New Corporation, Universal Logic". PRWeb. Retrieved 2017-08-31.
  2. ^ a b "Universal Robotics, Inc". Bloomberg Businessweek. Retrieved 8 June 2011.
  3. ^ Hogan, Hank. (November/December 2010). "Universal Robotics' 3D Vision." Robotics Business Review: 23-25.
  4. ^ "Universal Robotics Announces Expansion of Artificial Intelligence Robot Cells and a New Corporation, Universal Logic". PRWeb. Retrieved 2017-09-26.
  5. ^ a b Universal Robotics Introduces Neocortex, "Software with an IQ." Yahoo! Finance. Retrieved 8 June 2011.
  6. ^ "Universal Robotics". Universal Robotics. Retrieved 2017-09-26.
  7. ^ a b c d "Universal Robotics Introduces 'Software with an IQ'". Robotics Trends. Retrieved 15 June 2011.
  8. ^ http://www.robotics.org/content-detail.cfm/Industrial-Robotics-Featured-Articles/Robotics-Vision-at-a-Glance-The-Dos-Don-ts-and-Applications/content_id/4189
  9. ^ Universal Logic (2017-05-19), Universal Introduction with CEO David Peters, retrieved 2017-09-26
  10. ^ Fifer, Rolf. (1999). "Understanding Intelligence." The MIT Press.
  11. ^ http://www.universalrobotics.com/products
  12. ^ http://www.universalrobotics.com/urapplications
  13. ^ "Applications". Universal Robotics. 2015-06-29. Retrieved 2017-09-26.
  14. ^ Universal Logic (2016-04-10), Robotic Random Straw Picking, retrieved 2017-09-26
  15. ^ Universal Logic (2017-02-28), Neocortex G2R Cells: Flexibility @ Speed, retrieved 2017-09-26
  16. ^ "Products". Universal Robotics. 2016-10-27. Retrieved 2017-09-26.
  17. ^ "Applications". Universal Robotics. 2015-06-29. Retrieved 2017-09-26.
  18. ^ "New robotic Neocortex G2R Cell quickly clears and restocks airline beverage trays - The Robot Report". The Robot Report. 2017-02-25. Retrieved 2017-09-26.
  19. ^ "Neocortex Goods to Robot Cell Fuses Best of Collaborative and Industrial Robots for Order Fulfillment and Material Handling Applications | RoboticsTomorrow". Retrieved 2017-09-26.
  20. ^ Universal Logic (2017-03-06), Neocortex G2R Cell Rapid Deployment, retrieved 2017-09-26
  21. ^ Universal Logic (2016-10-24), Neocortex G2R Robot Cell: Order Fulfillment, retrieved 2017-09-26
  22. ^ "Products". Universal Robotics. 2016-10-27. Retrieved 2017-09-26.
  23. ^ a b c "Teaching Robots New Tricks". Canadian Manufacturing. Retrieved 15 June 2011.
  24. ^ Universal Logic (2017-05-19), Universal Introduction with CEO David Peters, retrieved 2017-09-26
  25. ^ Fifer, Rolf. (1999). "Understanding Intelligence." The MIT Press.
  26. ^ "Neocortex® G2R Cells are Easy to Both Deploy & Re-Deploy". Universal Robotics. 2017-03-06. Retrieved 2017-09-26.
  27. ^ "Emerging Companies Review: Universal Robotics". Nvidia. Retrieved 15 June 2011.
  28. ^ "What's Hot in Robotics?". Universal Robotics. 2015-06-18. Retrieved 2017-09-26.
  29. ^ Universal Logic (2017-05-19), Universal Introduction with CEO David Peters, retrieved 2017-09-26
  30. ^ a b http://www.robotics.org/userassets/riauploads/file/TH_RIA_David_Peters.pdf
  31. ^ http://www.universalrobotics.com/neocortex
  32. ^ "Products". Universal Robotics. 2016-10-27. Retrieved 2017-09-26.
  33. ^ a b c "Robots Can't Learn if They're Tied Down". The Global Transition. Retrieved 15 June 2011.
  34. ^ Ambrose, Rob (July 2000). "Robotnaut: NASA's space humanoid." IEEE Intelligent Systems 15 (4): 57-63.
  35. ^ "Universal Robotics Overview of Products". Retrieved 20 December 2012.
  36. ^ "Applications". Universal Robotics. 2015-06-29. Retrieved 2017-09-26.
  37. ^ "Articulating Motion". Motion System Design. Retrieved 15 June 2011.
  38. ^ Universal Logic (2017-05-19), Universal Introduction with CEO David Peters, retrieved 2017-09-26
  39. ^ "Universal Robotics Launches Spatial Vision and Spatial Vision Robotics". Inspect. Retrieved 8 June 2011.
  40. ^ "3D Spatial Vision Intelligence". Universal Robotics. Retrieved 15 June 2011.
  41. ^ Universal Logic (2015-12-10), 3D Pallet Quality Inspection, retrieved 2017-09-26
  42. ^ a b "CHEP Selects Universal Robotics to Provide Innovative Pallet Inspection System". CHEP Inc. Retrieved 12 December 2012.
  43. ^ "CHEP Selects Universal Robotics to Provide Innovative Pallet Inspection System". Packaging Revolution. Retrieved 12 December 2012.
  44. ^ http://www.universalrobotics.com/urcompany
  45. ^ "Motoman Robotics announces MotoSight 3D Spatial Vision". Automation. Retrieved 15 June 2011.
  46. ^ Universal Logic (2017-07-03), Neocortex Automated Airline Beverage Replenishment 2017-5-29, retrieved 2017-09-26
  47. ^ "Neocortex Goods to Robot Cell for Replenishing Airline Beverages is Now Available". PRWeb. Retrieved 2017-09-26.
  48. ^ "Too Many Robots in the Kitchen – Or Not Enough?". apex.aero. Retrieved 2017-09-26.
  49. ^ "New robotic Neocortex G2R Cell quickly clears and restocks airline beverage trays - The Robot Report". The Robot Report. 2017-02-25. Retrieved 2017-09-26.
  50. ^ "Neocortex Goods to Robot Cell Fuses Best of Collaborative and Industrial Robots for Order Fulfillment and Material Handling Applications". PRWeb. Retrieved 2017-09-26.
  51. ^ Universal Logic (2015-09-10), Neocortex Bin Picking for Order Fulfillment, retrieved 2017-09-26
  52. ^ Universal Logic (2015-03-19), Goods to Robot, retrieved 2017-09-26
  53. ^ Div., Yaskawa America, Inc.- Motoman Robotics. "Yaskawa Motoman, R/X Automation Solutions and Universal Robotics Announce Strategic Partnership". www.motoman.com. Retrieved 2017-09-26.{{cite web}}: CS1 maint: multiple names: authors list (link)
  54. ^ Universal Logic (2016-05-11), Neocortex Pharmaceutical Handling, retrieved 2017-09-26
  55. ^ Div., Yaskawa America, Inc.- Motoman Robotics. "Robotic Pharmaceutical Unit Pick Workcell". www.motoman.com. Retrieved 2017-09-26.{{cite web}}: CS1 maint: multiple names: authors list (link)
  56. ^ http://www.universalrobotics.com/random-bin-picking
  57. ^ http://www.universalrobotics.com/random-box-mover
  58. ^ http://www.prweb.com/releases/neocortex-box-moving/unlimited-depalletizing/prweb10899645.htm
  59. ^ Universal Logic (2014-09-18), Neocortex Unstructured Multi-Pick Depalletizing, retrieved 2017-09-26
  60. ^ "iRobot: A Robot that Learns.". Nashville Technology Council: Catalyst. 2010.
  61. ^ http://www.universalrobotics.com/random-bag-picking
  62. ^ Universal Logic (2011-11-07), Universal Robotics Random Bag Picking, retrieved 2017-09-26
  63. ^ Universal Logic (2014-12-01), Robotic Snack Bag Moving Demo, retrieved 2017-09-26
  64. ^ http://www.universalrobotics.com/3D-inspection
  65. ^ "Engineering". Universal Robotics. Retrieved 8 June 2011.
  66. ^ "David Peters". Universal Robotics. Retrieved 15 June 2011.
  67. ^ "Alan Peters". Universal Robotics. Retrieved 15 June 2011.
  68. ^ "Richard Alan Peters III, PH.D." Vanderbilt School of Engineering. Retrieved 15 June 2011.
  69. ^ "Robotics Software Firm Hires Marketer". Nashville Post. Retrieved 15 June 2011.
  70. ^ "Hob Wubbena". Universal Robotics. Retrieved 15 June 2011.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Universal_Robotics&oldid=802549764"