| Industry | Automation; Machine Vision; Software |
|---|---|
| Founded | 2001, Commenced Operations 2008 |
| Headquarters | Nashville, Tennessee |
| Key people | David A. Peters, CEO Richard Alan Peters II, Ph.D., CTO |
| Products | Neocortex; Spatial Vision; engineering services |
| Website | http://www.universalrobotics.com |
Universal Robotics, Inc. is a software engineering company headquartered in Nashville, Tennessee.[1][2] Founded in 2008, the company develops software solutions that automate tasks never before possible.[3]
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.[3] 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.[4]
According to the company’s website, Universal also offers Sensor Servoing motion control software[5] and engineering services[6] across a range of industries.
Contents |
Neocortex is a new form of Artificial Intelligence (AI) that allows mobile machines, such as robots, to learn from their experiences in the physical world rather than being programmed to act.[7]
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.[8] 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.[9][10] NVIDIA GPUs are used to speed up processing.[11]
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.[12]
Neocortex technology was developed at Vanderbilt University and NASA, where it was used as “brain” of Robonaut.[13][14] 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.[15]
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.[9]
Universal’s Spatial Vision line of products was created during the development of Neocortex.[7] 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.[16] 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.[4] Spatial Vision provides 0.1 sub pixel accuracy[17] but does not require precision mounting or specialized cameras, which makes it easy to set up[16] and costs a fraction of traditional 3D vision systems.[7]
Spatial Vision provides programmatic interfaces to 3D calibration files for custom C, C++ and MATLAB applications.[17]
Universal has two Spatial Vision product lines – Spatial Vision and Spatial Vision Robotics.[17]
Spatial Vision can be used for tasks ranging from engineering applications to motion capture to improved facial recognition.[11] 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.[4] 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.[18]
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.[9]
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.[1]
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.[4] Spatial Vision Robotics provides real-time vision guidance for random parts picking, pallet sorting, automated kitting and box moving (palletization and depalletization).[19]
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.[1][7]
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.[20]
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.[5]
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:
Universal Robotics was founded and is lead by David Peters, CEO[21] and his brother[13] Dr. Alan Peters, CTO.[22] Dr. Peters is the principal architect of Neocortex and is an Associate Professor at Vanderbilt University in Nashville, Tennessee.[23] Jon Peters serves as the Director of Information Technology.[24] Hob Wubbena is the company’s Director of Marketing,[25][26] and Ross Duncan has been appointed Sales Manager.[27][28]