Neocortex – Software with an IQ
Neocortex® is a new form of artificial intelligence that uses sensor information to learn. It discovers patterns in chaotic environments that are relevant to an assigned task. It then analyzes those patterns to understand complexity, improving process. It is based on technology originally co-developed between NASA and Vanderbilt University.
It is unlike any other technology. The software is independent of any hardware, allowing it be used for a host of applications from data analysis to robot and motor control. It uses sensor information to discover multi-dimension patterns in dynamic environments. Those patterns are analyzed to understand complexity and improve process for a range of tasks.
Universal Robotics has been commercializing the Neocortex machine learning/big data platform for three years. As its first application, Neocortex has been applied to handling and moving boxes and objects it has never seen before. Neocortex 3.2 completed testing in early 2013 at a Fortune 200 logistics center as part of the Universal Robotics Unlimited Depalletization Application, and can now be used for on-the-fly automated handling of any carton independent of box variability. This includes size or condition, weight, location or orientation within the work cell, label quantity/type, or box graphics or color.
In addition, Doerfer Companies just announced a partnership with Universal Robotics to integrate Neocortex interactive intelligence and Spatial Vision Robotics 3D software platforms with its custom automation solutions for flexible piece part feeding to industrial automation assembly platforms.
Intelligent – Learns from and reacts to chaotic surroundings
Flexible – Identifies objects and patterns never seen before
ROI – Less than 24 months
“Neocortex artificial intelligence represents a significant breakthrough in perception technology which was needed for robotics to be utilized in warehouses and fulfillment centers”
Roger Christian, VP, Yaskawa America, Inc., Motoman Robotics
Neocortex handles a wide variety of objects in stride. Whether moving multiple bag types from a bin, or unloading a trailer with different case sizes, Neocortex handles every object in real-time. It can differentiate colors, marking, barcodes or SKU numbers. Neocortex distinguishes between normal and arbitrary object traits – such as box flap bent over versus a cardboard edge.
Typical vision systems require pre-configuring in order to later match the object with a CAD drawing, known shape, surface or distinguishing features. Due to processing speed, these vision systems are limited to a dozen or two objects, and can’t identify damaged boxes or new objects.
In contrast, Neocortex provides automated reactive control for machines and robots. For example, Neocortex intelligence was added to Spatial Vision Robotics to create its first application – the Unlimited Depalletization Application. It added the ability to react to a box that moved, find a new box with unique set of labels, and identify damaged cartons without preconfigured images, geometry or details about their unique characteristics.
Neocortex can be used for supply chain and manufacturing throughput analysis, whether manual or automated. Automated material flow is analyzed by tracking physical objects such as reusable pallets and containers, resulting in efficiency gains. Neocortex provides an employee additional information for better decision making such as real time feedback on truck load balancing during manual stacking of a trailer.
Neocortex keeps track of every object it encounters with enough specificity to identify an object’s shape, volume, labels, and damage (if any). Data with this level of granularity is useful for increasing throughput efficiencies in a number of ways. It is used to improve stacking for storage and trailer loading, warehouse throughput sequencing, object damage reporting, and reusable container tracking.
As variation increases, the need for flexible learning also increases. This is the situation with logistics tasks, where nothing is guaranteed to be in its proper place or configuration. This randomness and uncertainty require a new way to approach package/parts handling. When a high degree of flexibility is required, traditional programming approaches fail. Hard-coded programs cannot define repeatable procedures for unanticipated objects in an unstructured environment.
Previous generations of artificial intelligence tend to be brittle and cumbersome. They require pre-established, specific rules of action based on historical trends. This works when enough historical data is available, and when future events mimic previous activities. Greater variations require more and more rules, making artificial intelligence more complex, slower to react in real time, and always a step behind new changes.
Neocortex is a new form of artificial intelligence that uses sensor information to learn. Neocortex discovers patterns in a chaotic environment that are relevant to an assigned task. This cybernetic intuitive learning process is mathematically represented in Neocortex, and is similar to how all mammals learn. It is a dynamic process whereby experience builds fine-tuned understanding.
Sense > Act > Learn
Neocortex Sensory Ego-Sphere
Brains of living beings learn via distributed parallel processing consisting of nodes (modules) and networks consisting of thousands of parallel processes. Also, their learning occurs through the inextricable interaction of their senses with the environment and feedback on the results of their motor coordination. Neocortex’s patented Sensory Ego-Sphere™ (SES) represents this real-time learning that occurs through sensory-motor coordination. With a machine at the origin of the SES virtual geodesic sphere, short-term learning occurs through parallel processing of data on all nodes that are activated by any real object within its sensing proximity.
Though Neocortex does not attempt to biologically model the human cortex, it does mathematically represent the learning pattern of living beings. We as humans learn over time that there is a pattern to success and failure of a task, despite the variety of sensory data and possible ways to complete a task – just like hitting a ball with a bat. In the same way, Neocortex learns to successfully complete tasks by remembering previously successful patterns, and processing real-time sensory/motor control information. It’s the Way the Real World Works™.