Universal Robotics
Encyclopedia
Universal Robotics, Inc. is a software engineering company headquartered in Nashville, Tennessee. Founded in 2008, the company develops software solutions that automate tasks never before possible.
Universal’s flagship technology, Neocortex, which was created at Vanderbilt University
with funding from DARPA and NASA
and developed using NASA’s Robonaut
, enables robots to perform tasks too costly, dangerous or impossible for humans to undertake. Its 3D machine vision
products – Spatial Vision and Spatial Vision Robotics – are software solutions that turn a pair of webcams into accurate, cost-effective, easy-to-calibrate and install 3D vision systems.
According to the company’s website, Universal also offers Sensor Servoing motion control software and engineering services across a range of industries.
(AI) that allows mobile machines, such as robots, to learn from their experiences in the physical world rather than being programmed to act.
Traditional AI gives robots programmed actions corresponding to variables, leading to failure each time an unprogrammed variable is encountered. Neocortex is based on the pattern of learning in nature which is common to all creatures. The patent-protected software allows a machine to develop its own understanding from sensing and acting in the physical world, using information from up to 50 channels of sensor data. NVIDIA
GPUs
are used to speed up processing.
With Neocortex, machines learn from their experiences. It enables robots to perform nearly any task that requires adaptive human input. Neocortex allows a machine to determine its actions by remembering what worked and failed in past attempts. Its database compounds over time allowing for adaptation. With enough experience, Neocortex can enable a machine draw correlations to attempt an entirely new solution to a given task.
Neocortex technology was developed at Vanderbilt University and NASA, where it was used as “brain” of Robonaut. Today, Neocortex is enabling machines to perform highly specialized, automated tasks that require them to react and adapt to their environments and has the potential to increase productivity, profitability and worker safety across industries worldwide.
Universal is initially launching Neocortex in the materials handling
industry where the software will palletize and depalletize mixed-size boxes using industrial robots. Efforts to use traditional AI in applications with many variables – such as mixed-size box handling – have been unsuccessful because of the inability to program for every circumstance.
The Spatial Vision software combines the images from two, off-the-shelf USB webcams to determine a point’s 3D coordinates. This 3D data can be used to measure, identify objects, and calibrate and help guide robots.
3D vision systems have many benefits over 2D, including better accuracy and object identification, but adoption has been slow in many markets because traditional systems are costly and difficult to maintain. Spatial Vision provides 0.1 sub pixel accuracy but does not require precision mounting or specialized cameras, which makes it easy to set up and costs a fraction of traditional 3D vision systems.
Spatial Vision provides programmatic interfaces to 3D calibration files for custom C, C++ and MATLAB applications.
Universal has two Spatial Vision product lines – Spatial Vision and Spatial Vision Robotics.
Spatial Vision can be used for tasks ranging from engineering applications to motion capture
to improved facial recognition
. The system also can be used to measure situations such as in-store foot traffic patterns as well as scientific applications requiring object tracking and visual analytics. In March 2011, Universal launched Spatial Vision 2.0, which added support for GigE
Allied Vision cameras, improved user interfaces and enhanced accuracy tools, such as snap-to-corner measurement assistance and accuracy calculator displays.
Spatial Vision can be deployed in any setting where a pair of cameras can be installed, including manufacturing lines, warehouses, laboratories, office buildings and department stores.
Universal partnered with Logitech
to launch the Spatial Vision Logitech Bundle, which includes the Spatial Vision software, two webcams and a pair of 3D glasses.
Spatial Vision Robotics, which is specially engineered to guide robots, tracks moving machinery being controlled with Spatial Vision’s 3D data relative to its surroundings and objects of interest. Spatial Vision Robotics provides real-time vision guidance for random parts picking, pallet sorting, automated kitting and box moving (palletization and depalletization).
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 that delivers cost-effective, flexible and scalable real-time 3D vision guidance for Motoman robots.
As with other Spatial Vision products, MotoSight™ 3D Spatial Vision is easier to install and has a lower price-point than traditional 3D vision systems. The system determines six degrees of object position and pose information (X, Y, Z, Rx, Ry, Rz) and is accurate within 2-4mm with off-the-shelf Logitech 9000 webcams. Accuracy can be improved by substituting webcams with GigE cameras.
Universal’s flagship technology, Neocortex, which was created at Vanderbilt University
Vanderbilt University
Vanderbilt University is a private research university located in Nashville, Tennessee, United States. Founded in 1873, the university is named for shipping and rail magnate "Commodore" Cornelius Vanderbilt, who provided Vanderbilt its initial $1 million endowment despite having never been to the...
with funding from DARPA and NASA
NASA
The National Aeronautics and Space Administration is the agency of the United States government that is responsible for the nation's civilian space program and for aeronautics and aerospace research...
and developed using NASA’s Robonaut
Robonaut
Robonaut is a humanoid robotic development project conducted by the Dextrous Robotics Laboratory at NASA's Johnson Space Center in Houston, Texas...
, enables robots to perform tasks too costly, dangerous or impossible for humans to undertake. Its 3D machine vision
Machine vision
Machine vision is the process of applying a range of technologies and methods to provide imaging-based automatic inspection, process control and robot guidance in industrial applications. While the scope of MV is broad and a comprehensive definition is difficult to distil, a "generally accepted...
products – Spatial Vision and Spatial Vision Robotics – are software solutions that turn a pair of webcams into accurate, cost-effective, easy-to-calibrate and install 3D vision systems.
According to the company’s website, Universal also offers Sensor Servoing motion control software and engineering services across a range of industries.
Neocortex
Neocortex is a new form of Artificial IntelligenceArtificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
(AI) that allows mobile machines, such as robots, to learn from their experiences in the physical world rather than being programmed to act.
Traditional AI gives robots programmed actions corresponding to variables, leading to failure each time an unprogrammed variable is encountered. Neocortex is based on the pattern of learning in nature which is common to all creatures. The patent-protected software allows a machine to develop its own understanding from sensing and acting in the physical world, using information from up to 50 channels of sensor data. NVIDIA
NVIDIA
Nvidia is an American global technology company based in Santa Clara, California. Nvidia is best known for its graphics processors . Nvidia and chief rival AMD Graphics Techonologies have dominated the high performance GPU market, pushing other manufacturers to smaller, niche roles...
GPUs
Graphics processing unit
A graphics processing unit or GPU is a specialized circuit designed to rapidly manipulate and alter memory in such a way so as to accelerate the building of images in a frame buffer intended for output to a display...
are used to speed up processing.
With Neocortex, machines learn from their experiences. It enables robots to perform nearly any task that requires adaptive human input. Neocortex allows a machine to determine its actions by remembering what worked and failed in past attempts. Its database compounds over time allowing for adaptation. With enough experience, Neocortex can enable a machine draw correlations to attempt an entirely new solution to a given task.
Neocortex technology was developed at Vanderbilt University and NASA, where it was used as “brain” of Robonaut. Today, Neocortex is enabling machines to perform highly specialized, automated tasks that require them to react and adapt to their environments and has the potential to increase productivity, profitability and worker safety across industries worldwide.
Universal is initially launching Neocortex in the materials handling
Material handling equipment
Material handling equipment is all equipment that relates to the movement, storage, control and protection of materials, goods and products throughout the process of manufacturing, distribution, consumption and disposal...
industry where the software will palletize and depalletize mixed-size boxes using industrial robots. Efforts to use traditional AI in applications with many variables – such as mixed-size box handling – have been unsuccessful because of the inability to program for every circumstance.
Spatial Vision
Universal’s Spatial Vision line of products was created during the development of Neocortex. This software allows any pair of webcams to be turned into a 3D vision system.The Spatial Vision software combines the images from two, off-the-shelf USB webcams to determine a point’s 3D coordinates. This 3D data can be used to measure, identify objects, and calibrate and help guide robots.
3D vision systems have many benefits over 2D, including better accuracy and object identification, but adoption has been slow in many markets because traditional systems are costly and difficult to maintain. Spatial Vision provides 0.1 sub pixel accuracy but does not require precision mounting or specialized cameras, which makes it easy to set up and costs a fraction of traditional 3D vision systems.
Spatial Vision provides programmatic interfaces to 3D calibration files for custom C, C++ and MATLAB applications.
Spatial Vision can be used for tasks ranging from engineering applications to motion capture
Motion capture
Motion capture, motion tracking, or mocap are terms used to describe the process of recording movement and translating that movement on to a digital model. It is used in military, entertainment, sports, and medical applications, and for validation of computer vision and robotics...
to improved facial recognition
Facial recognition system
A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source...
. The system also can be used to measure situations such as in-store foot traffic patterns as well as scientific applications requiring object tracking and visual analytics. In March 2011, Universal launched Spatial Vision 2.0, which added support for GigE
GigE vision
GigE Vision is an interface standard introduced in 2006 for high-performance industrial cameras. It provides a framework for transmitting high-speed video and related control data over Ethernet networks. The standard was initiated by a group of 12 companies and the committee has since grown to...
Allied Vision cameras, improved user interfaces and enhanced accuracy tools, such as snap-to-corner measurement assistance and accuracy calculator displays.
Spatial Vision can be deployed in any setting where a pair of cameras can be installed, including manufacturing lines, warehouses, laboratories, office buildings and department stores.
Universal partnered with Logitech
Logitech
Logitech International S.A. is a global provider of personal peripherals for computers and other digital platforms headquartered in Romanel-sur-Morges, Switzerland. The company develops and markets products like peripheral devices for PCs, including keyboards, mice, microphones, game controllers...
to launch the Spatial Vision Logitech Bundle, which includes the Spatial Vision software, two webcams and a pair of 3D glasses.
Spatial Vision Robotics, which is specially engineered to guide robots, tracks moving machinery being controlled with Spatial Vision’s 3D data relative to its surroundings and objects of interest. Spatial Vision Robotics provides real-time vision guidance for random parts picking, pallet sorting, automated kitting and box moving (palletization and depalletization).
As part of an ongoing collaboration with Motoman Robotics, a division of Yaskawa America, Inc.
Yaskawa Electric Corporation
The is a Japanese manufacturer of servos, machine controllers, AC Motor drives, switches and robots.Their Motoman robots are heavy duty industrial robots used for example in car manufacturing....
, Universal launched MotoSight™ 3D Spatial Vision, a 3D vision system that delivers cost-effective, flexible and scalable real-time 3D vision guidance for Motoman robots.
As with other Spatial Vision products, MotoSight™ 3D Spatial Vision is easier to install and has a lower price-point than traditional 3D vision systems. The system determines six degrees of object position and pose information (X, Y, Z, Rx, Ry, Rz) and is accurate within 2-4mm with off-the-shelf Logitech 9000 webcams. Accuracy can be improved by substituting webcams with GigE cameras.
Sensor Servoing
Universal’s Sensor Servoing is motion control software 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. Sensor Servoing couples Spatial Vision Robotics with robot kinematics to allow a robot to react dynamically to changes in object positioning. For example, the software will allow a paint-spraying robot to maintain a consistent distance from an assembly line part swaying on a moving cable, which reduces over-spray.Engineering
Universal’s engineering team has engineering expertise in technologies related to sensing, manipulation and artificial intelligence. The company offers customers world class engineering services in the following areas:- Sensor Applications: 2/3D Vision (including object recognition), Force, InfraredInfraredInfrared light is electromagnetic radiation with a wavelength longer than that of visible light, measured from the nominal edge of visible red light at 0.74 micrometres , and extending conventionally to 300 µm...
, and AccelerationAccelerometerAn accelerometer is a device that measures proper acceleration, also called the four-acceleration. This is not necessarily the same as the coordinate acceleration , but is rather the type of acceleration associated with the phenomenon of weight experienced by a test mass that resides in the frame... - Reactive Robotics: KinematicsKinematicsKinematics is the branch of classical mechanics that describes the motion of bodies and systems without consideration of the forces that cause the motion....
, End-of-tool Design, and High Speed Control - Machine Learning: Pattern ExtractionPattern recognitionIn machine learning, pattern recognition is the assignment of some sort of output value to a given input value , according to some specific algorithm. An example of pattern recognition is classification, which attempts to assign each input value to one of a given set of classes...
, Path PlanningMotion planningMotion planning is a term used in robotics for the process of detailing a task into discrete motions....
, Hierarchical ControlHierarchical control systemA Hierarchical control system is a form of Control System in which a set of devices and governing software is arranged in a hierarchical tree. When the links in the tree are implemented by a computer network, then that hierarchical control system is also a form of Networked control system.-...
, Closed Loop Control, Supervised/Unsupervised learningUnsupervised learningIn machine learning, unsupervised learning refers to the problem of trying to find hidden structure in unlabeled data. Since the examples given to the learner are unlabeled, there is no error or reward signal to evaluate a potential solution...
, Reinforcement learningReinforcement learningInspired by behaviorist psychology, reinforcement learning is an area of machine learning in computer science, concerned with how an agent ought to take actions in an environment so as to maximize some notion of cumulative reward...
, Sensori-Motor coordination, Programming by DemonstrationProgramming by demonstrationIn computer science, programming by demonstration is an End-user development technique for teaching a computer or a robot new behaviors by demonstrating the task totransfer directly instead of programming it through machine commands.... - Middleware: CUDACUDACUDA or Compute Unified Device Architecture is a parallel computing architecture developed by Nvidia. CUDA is the computing engine in Nvidia graphics processing units that is accessible to software developers through variants of industry standard programming languages...
and CORBACommon Object Request Broker ArchitectureThe Common Object Request Broker Architecture is a standard defined by the Object Management Group that enables software components written in multiple computer languages and running on multiple computers to work together .- Overview:CORBA enables separate pieces of software written in different...