Investors: Press Release

GeckoSystems Improves AI Savant Management Due to Elder Care Robot Trials

CONYERS, Ga., Apr. 26, 2010 -- GeckoSystems Intl. Corp. (PINKSHEETS: GCKO) -- -- reported today that they have advanced the capabilities of their uppermost GeckoSavant™, the GeckoSuper™. GeckoSystems is a dynamic leader in the emerging mobile robotics industry revolutionizing their development and usage with "Mobile Robot Solutions for Safety, Security, and Service™".

"Real world testing and development enables automotive manufacturers such as Ford, GM, Chrysler, Honda, BMW, and others to improve the reliability and performance of their mainstream product lines. Mobile robot development, especially personal companion robot development, is no different," remarked Martin Spencer, President/CEO, GeckoSystems.

"As we continue our world's first in home elder care robot trials, we keep on learning more from these real world tests, just as NASCAR racing participation enables domestic manufacturers to design more efficient engines, better brakes, improved handling, and greater safety. Since we are pioneers in this emerging marketplace, these trials have given us important insights and numerous ideas as to how to improve the cost effective utility and benefit to the care giver and care receiver. Our now fourth generation GeckoSuper in the last five years is substantive testimony as to the many technological barriers we have demonstrably solved since our founding over twelve years ago," continued Spencer.

GeckoSuper is an AI/expert system responsible for system-wide orchestrated subsumption. At its simplest, subsumption means organizing various simple behaviors into layers. Low-level layers contain the most basic behaviors (eg. avoid an obstacle), while high-level layers can be thought of as more abstract behaviors (eg explore the surroundings). This is a bottom-up approach; low-level layers can override the high-level layers as necessary. The end result is an approach where high-level layers provide an overall goal for the AI system to achieve whereas the low-level layers provide the means.

This approach summarizes GeckoSuper perfectly. Its ability to receive data from other GeckoSavants and make decisions based upon that data means that GeckoSuper can provide a general directive for the robot to currently execute without having to actually worry about how it is carried out. This frees up GeckoSuper to instead focus on prioritization; given two or more inputs, GeckoSuper can determine the order in which they need to be addressed. Depending upon the circumstances, this could be interpreted as a form of common sense on the part of the robot.

The inclusion and utilization of so many specialized GeckoSavants running in parallel and mediated by GeckoSuper allows the CareBot to perform comparatively complex tasks in a timely and efficient manner. In GeckoSystems terminology, a GeckoSavant is an AI/expert system that is responsible for and excels at one particular task or group of related tasks. An example would be GeckoScheduler™. Version 2.0 has recently been completed to improve the user experience. GeckoScheduler stores the when and frequency of upcoming verbal reminders to waypoint commands, and it will see to it that they are executed at the desired time. How these tasks are carried out is not GeckoScheduler's burden, it only needs to ensure that the appropriate commands are sent when they are needed.

No one GeckoSavant is necessarily the star of the show, however. The nature of subsumption architecture means that various beneficial emergent behaviors can arise. For example, the CareBot can be commanded to move toward a waypoint that is in the middle of a table. The robot will do its best to go there, but its collision avoidance programming will repel it. The end result is that the CareBot circles around the table "looking" for a way to its programmed destination. This means that it is really the combination of multiple savants that allows the CareBot to behave in a complex, intelligent manner. More GeckoSavants mean more opportunities for emergent behaviors. GeckoSuper is built to recognize this advantage, and its extensibility allows it to easily take in more data with which to make actionable decisions. Combined with its prioritization, GeckoSuper allows the robots to not simply react to stimuli, but gain actionable situational awareness of its surroundings.

This has striking parallels to sensor fusion, another feature that appears in GeckoSystems' suite of mobile service robot technologies. Sensor fusion is the combination of two or more sensory inputs (such as sight and hearing) to achieve greater awareness of the surroundings. For example, you don't just see oncoming cars when you cross the street, you also frequently hear them. Possessing two or more independent inputs not only gives you more information about your environment, but also increased redundancy. For example, if you are temporarily blinded, you can still hear, smell and feel your way around. Similarly, GeckoSuper is able to take data from multiple inputs and use it to paint a portrait of its environment. More independent sensory data sources means a more complete picture and understanding of the environment, whether static or dynamic.

In other words, the end result of GeckoSuper's redesign is numerous applications, including persistent surveillance for monitoring the well being of the elderly, security, etc. In addition, many, if not most, of these actions can be done autonomously with little or no intervention necessary, unless otherwise desired.

"To many, the foregoing GeckoSuper discussion may well be 'techno-babble.' Unfortunately the terminology evolves slower than the new technology it describes, as evident with early planes called flying machines and early cars called horseless carriages. Initially personal computer descriptions and explanations were equally obscure. The benefits of and technology behind personal companion robots is difficult to communicate in present every day vernacular. These are still the 'early days' of mobile service robot sales and usage," opined Mark Peele, Vice President, R&D, GeckoSystems.

"GeckoSuper provides the umbrella for our suite of GeckoSavants with the disparate, functional benefits needed to cost effectively provide utility to families for remote care taking of their members and other loved ones, by making them more personal and uniquely adapted, and addressed to the particular person to be assisted. Not only does this capability enable new forms of social interaction and community for families --even when dispersed geographically--, just as 'racing improves the breed,' our in home elder care robot trials are teaching us what we need to know to expand our marketplace and increase ROI for our investors," concluded Spencer.

Download Full-Text PDF