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 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.
Neocortex Learns Random Mixed Depalletization
Neocortex has been applied to handling and moving boxes and objects it has never seen before. In this first video (Nov. 2012), Universal Robotics explains this ground-breaking next generation of artificial intelligence that learns from its environment. Watch this to see a robot controlled by Neocortex pick randomly oriented, mixed size boxes, and listen to a description of the technology
Neocortex discovers patterns in chaotic environments that are relevant to an assigned task. It then analyzes those patterns to understand complexity, improving process and completing a task even with unexpected objects in varying locations.
Watch this second video (April, 2012) to see Neocortex increase flexibility in a robot. Listen to the explanation of the technology. The Neocortex-controlled robot picks up randomly oriented, mixed size boxes, as well as reacts to box added at the last minute by a human. This is truly random mixed depalletization.
Flexible Machine Control
Neocortex controls machines and robots to automate tasks, increasing the flexibility of automation. For instance, it can be used to depalletize cartons, even those it has never seen before. It recognizes and moves these cartons regardless of their unique characteristics, or random workcell location.
Operational Efficiency Insight
As a data analysis tool, Neocortex is used for supply chain and manufacturing throughput analysis. The entire material flow can be analyzed to look for improvements. Both existing automated and manual activities can be analyzed for maximum efficiencies. To improve productivity of manual labor, it provides the employee additional information which they cannot perceive on their own.
Benefits of Neocortex
• Enables flexible automation
• Increases throughput via real-time data analysis
• Learns as it experiences variation
• Monitors materials and objects to uncover bottlenecks and flow patterns
• Shares learning from one machine with other connected machines
• Captures intuitive activities important to task success
• Eliminates brain-drain when employees change jobs
• Automatically updates the automation system to new metrics
• Minimizes manual modifications required due to workcell or product changes
• Identifies subtle pattern shifts (defects, deviations, or modifications) not easily diagnosed
• Provides a reliable learning platform with extensive real-world testing
Neocortex handles mixed 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 of a box.
Neocortex identifies the object anywhere within the field of view using 3D sensors and then handles the object as instructed, safely working within the constraints of with work cell.
The flexibility of Neocortex extends to the work cell environment as well. It can recognize partially hidden objects and objects with a range of surfaces including black and Mylar. Sensors and equipment can be configured to accommodate harsh climates, dirty environments and variable lighting conditions.
In the logistics industry, Neocortex is used for supply chain throughput analysis of activities such as trailer loading, pallet stacking, and material handling, whether manual or automated. Neocortex improves the productivity of manual labor by providing additional information that the employee cannot perceive on their own. For example, it can help load balancing during manual stacking of a trailer.
Neocortex can keep 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 can be used to improve stacking for storage and trailer loading, warehouse throughput sequencing, object identification for track and damage reporting, and reusable container tracking.
Simple to Use
Operators interface with Neocortex through a tailored, easy-to-use Graphical User Interface. The GUI has a common look and feel, whether interfacing over Ethernet to a PLC, another computer, or directly to robots and automation equipment. Under the hood, it operates on a Windows 7 platform using an i7 quad core PC equipped with GPUs.
Universal has a successful record of translating state-of-art engineering into practical offerings that feature the least expensive sensor/hardware configuration necessary to improve your logistics efficiency. These solutions provide an attractive ROI by improving utilization of existing assets.
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. For example: loose boxes in the back of a truck need to be unloaded; pallet loads shift during transit so boxes are not in a perfect stack; a forklift damages the corner of a box when it picks it up; and two identical boxes with different shipping labels are loaded into separate trucks with different destinations. 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 per-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 chaotic environments that are relevant to an assigned task. It then analyzes those patterns to understand complexity, improving process.
This method for learning in Neocortex is similar to that of mammals. It is a dynamic process whereby experience builds fine-tuned understanding. The software learns to discern variation in quality and location rendering a fine-tuned decision. It is the equivalent to a human’s intuitive learning process.
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 robot or machine at the origin of the SES virtual geodesic sphere that spatially surrounds it, 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 clear pattern to success and failure of a particular task, despite the variety of sensory input and possible ways to complete a task – just like hitting a ball with a bat. In the same way, despite the complexity of sensory data over time, and despite many behaviors with varying outcomes, 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™.
When Neocortex senses a new object, it determines its attributes and how to best handle it. The software does not require pre-programmed dimensions, models, or reading of labels to recognize the object. Once learned, when the object is encountered again, Neocortex remembers it, delivering efficient performance.