GeckoSystems Augments Mobile Robot Navigation Software

Tag : Heat Resistant Wire
ATLANTA, GA, July 30, 2008 (WORLD STOCK WIRE) -- GeckoSystems Intl.Corp. (PINKSHEETS: GCKO) announced today that they have completedthe development and testing of their advanced intelligent mobilerobot navigation software, GeckoNav" 3.7. GeckoSystems is a dynamicleader in the emerging Mobile Service Robot (MSR) industryrevolutionizing their development and usage with mobile robotsolutions for safety, security, and service".

The newly enhanced GeckoNav enables faster, more graceful passagethrough loose crowds of moving people as in public areas. Oursensor loving, fully autonomous and adaptive AI software, GeckoNav,now performs even faster to sense and avoid collisions, withouthuman intervention. GeckoNav now enables even higher patrollingspeeds and faster errand running for greater utility andefficiency. This enables a quicker payback for our end users andOEM partners and increased ROI for our investors, remarked R.Martin Spencer, President/CEO.

GeckoNav accepts sensor reading inputs at over 250Hz and outputssteering and locomotion commands at over 40Hz using a low power500Mhz x86 Mini-ITX computer. GeckoNav has situational awarenesswith numerous emergent, beneficial avoidance behaviors.

GeckoNav's Core Capabilities:
1. Subsumptive software architecture enabling cognizant navigationfor unexpected obstacle (static or dynamic) avoidance while "onpath" with the ability to resume path following.

2. Sensor fusion technology such that the GeckoNav is sensorloving. By utilizing multiple sensor systems (like a blind manlistening and counting steps while using a cane, uses two senses--tactile and hearing-- to routinely navigate known, and unknown,environments) the GeckoNavs AI software architecture enablesdiffering, high count sensor systems synergy.

3. Short term AI memory software such that GeckoSystemsproprietary sensor fused, scanning CompoundedSensorArray may befully utilized. Consequently, total cost for sensor systems cost isdramatically reduced.

4. Emergent behaviors expression (which are not pre-programmed)such as the left/right routine when encountering a dynamic obstaclethat moves to the same side that the robot has chosen to use toavoid the now confounding obstacle. The robustness of this emergentbehavior is apparent as the robot finally, after several left/rightattempts, succeeds in avoiding the dynamic obstacle, and resumespath.

The resultant level of mobile autonomy can be likened to that of a"blind man with a cane in his own home" or loose crowd capable.All GeckoNav source code is in C++ and is not hardware or OScentric.

Some Fundamental Issues of Automatic Self-navigation in DynamicEnvironments

Background:
For any Mobile Service Robot (MSR) to have probable hope ofutility, it must have the intrinsic and timely ability to avoidunforeseen, dynamic obstacles and still reach its desired endpointsor physical locations. Many MSR prototypes are limited by theirnavigation software architecture. Historically, MSR architectureshave been based on either a pre-set path following technique, wherethe sensors are only used to detect failure of the preprogrammedpath, or they have used a purely reactive technique that has noconcept of the larger world that the MSR inhabits and cannot beused for useful tasks.

The path-following techniques suffer from being unable to adapt tochanging conditions quickly or smoothly. The MSR basically travelsblind until it is about to hit something, and once it has detectedan obstacle, the resulting decisions required are very complex. Asa result, the environment must be highly structured to avoidconfusing the MSR so that simple decisions will suffice or a lot ofcomputing power must be available to maintain and compute pathalternatives. Requiring a highly structured environment reduces theusefulness and flexibility of such a MSR in a human environment. Inaddition, the need for a lot of processing power makes MSRs reallyexpensive and their useful "on" time very short due to the powerrequired for the high clock CPU or PC typically on board.

Further, the purely reactive architectures suffer from havinglittle sense of past events, future goals, or of even where exactlythe MSR is within the world. Typically such MSRs have no memory ofthe world that they have traveled and "live" only instant toinstant. They may reach a particular destination, but it is by purechance and the MSR will not be able to recognize that it hasreached the desired destination without providing a modifiedenvironment (e.g. beacon techniques such as the legendary ArctecSystems Gemini, Evolution Robotics ER-1 and others). In its pureform, something seen in many toy robots, this technique is almostuseless for true automatic self-navigation or tasks in a dynamichuman environment. This kind of MSR is typically characterized byits use of binary IF-THEN rules like "If bumped left then turnright". Such an architecture does not scale for the multiplesensors required for Cognizant Navigation. Cognizant Navigation isthe ability to find locations repeatedly upon request withouthitting unexpected obstacles.

Cognizant Navigation is a non-trivial problem that has a number offacets. There must be enough sensor information of the right kindto not hit large obstacles such as walls, furniture, and people.There must also be enough sensor information to avoid smallerobstacles such as toys. Furthermore, the navigation engine must beable to react to quick local changes without losing track of itstask. The MSR must also have a memory of where it is within theworld and be able to repeatedly find locations within that worldeven if there are unexpected obstacles. This means that there mustbe enough processing power and RAM to accomplish this while stillhaving enough battery life to stay active for many hours whileperforming useful tasks like vacuuming or carrying more than atrivial sized load. These important capabilities are the basic,required foundation for useful MSRs in a human environment. Untilthe CareBot, almost all consumer MSRs have fallen short in one ormore of these areas.

Cognizant Navigation is much more than the simple reactive,bump-turn mobile robot behaviors seen in most traditional, orlegacy mobile robots. Such a robot may reach the goal, but isn't"aware" that it is attempting to reach that goal and can'trecognize it when located. Other legacy mobile robots blindlyfollow line segment paths like virtual train tracks and may be"aware" that they are trying to reach a goal, but they haveproblems when reacting to new situations that require deviationfrom the planned route due to their limited sensors and availableCPU power. Typically, these robots cannot sense obstacles untilthey actually run into them!

Are these MSRs cognizant? Cognizant means to be aware or haveconscious knowledge. The word "aware" implies the MSR rememberswhere it is, where it was, where it is "supposed" to be going, aswell as being aware of immediate changes in the environment thatmay require a response. Humanlike short term and long memorymanagement, along with enough sensor information, is the key toresolving this problem. Your existing PC has the raw computingpower, memory, and data storage needed for robust personal MSRcognizant navigation, scheduling of areas to be vacuumed, and much,much more.

GeckoSystemss (GSI) GeckoNav" is different. Its BiologicalHierarchical Architecture provides the benefits of both control andreaction within a single framework without the disadvantages ofeither technique alone. As a result, it is able to respond quicklyand intelligently to short term navigation situations while stillproviding the ability to guide the MSR toward accomplishing usefultasks within a map of the world that the MSR maintains. It turnsout that this approach is synergistic and reduces the complexity oftrying to "force fit" either of the other traditional solutions tosolve the whole problem.

Biological Hierarchical Architecture is a GeckoSystems proprietaryMSR navigation software scheme incorporating several advancedartificial intelligence (AI) methods such that together vote on thebest solution. It should be noted that sufficient sensors fornavigating a home environment while avoiding unexpected obstaclesis a critical prerequisite.

Sensors - Why Other MSRs Bump into Walls, Chairs, Tables, etc.
Many available MSRs are limited by their sensor count, positionand/or interpretation strategy. MSR sensors such as bump switches,feelers, and whiskers have the problem that they cannot sense theirenvironment without actually colliding with the world. Fixed singlesonar and infrared distance (IR) range finders are an improvement,but individually they give very little information about thesurrounding world. They may help avoid running into an obstacledirectly in front of the MSR in one narrow direction, but theyaren't very useful in helping the MSR navigate. There are too manydirections from which unseen problems can approach, and even if theobstacle is detected, it is practically impossible tell the trueextent of the obstacle and what the response should be from thatsingle datapoint.

Even having many different kinds of these sensors does notnecessarily solve this problem. The MSR must be able to assess thecurrent space around the MSR to enable robust navigation, and to dothat the MSR must have enough information of the right kind, notjust many arbitrary sensors. Expensive research MSR manufacturersunderstand this need, and solve this problem through a very costlyarray of multiple sonar and IR sensors or even more expensivemachine vision systems and/or laser rangefinders interpreted byeither CPU intensive computations, or by quicker neural nets thatcan be easily over trained and become brittle in their ability toreliably discern fixed and/or moving, unforeseen obstacles.

GeckoSystemss solution to this problem uses high-data, low costfixed sonars and scanning IR sensors in an array called theCompoundedSensorArray". The CSA can image the surrounding space in250-275 different directions, not just one single direction like asingle fixed sensor. This is actually more advanced than mostresearch MSRs in this respect, which in contrast can generallysense between only 7 to 16 unique obstacle positions on the forwardhalf of the MSR. This is an increase in resolution of 15 to 40times over such MSRs! The reason for this is that such MSRs tend toassume and operate in fairly structured environments, like offices,empty campus hallways and contest mazes and as a result encounterfewer challenges in their environments. In contrast, GSIs basebottechnologies have been designed and tested for typical homeenvironments from the beginning.

About GeckoSystems International Corporation:
In the ten years since founding, the Company has developed a suiteof proprietary, fundamental technologies that enable their robotsto automatically self-navigate the home or workplace using advancedsense and avoid technologies for reliable, unattended collisionavoidance while patrolling, following and/or errand running. Thesescientifically developed, tested, and proven hardware and softwarebreakthroughs enable the practical, low cost manufacture, sale andusage of mobile service robots in a variety of environments.

Their mobile robot solutions are appropriate for the consumer,professional healthcare, commercial security, public safety, anddefense markets. The consumer has needs for family care assistancewith remote monitoring and notification. Professional healthcareneeds night time errand running, portable telemedicine, etc.Homeland Security needs mobile robots patrolling public and/orprivates venues with WMD and small arms weapon detect. Manycommercial and military users desire the elimination of the man inthe loop to enable unmanned ground and air vehicles such asdriverless automobiles (or cybercars), trucks, and drone aircraft-presently teleoperated-- to not require any human intervention.

The Company's mobile robot solutions are appropriate for theconsumer, professional healthcare, commercial security and defensemarkets.

The consumer has needs for family care assistance with remotemonitoring and notification. This is for family care for theelderly, chronically ill, and children. Since GeckoTrak" enablesthe CareBot to automatically follow a designated care receiverusing sensor fusion; it allows the caregiver to remotely see howthey are doing using the onboard wireless webcam. Should thedesignated family member not respond to their CareBots inquiries,GeckoChat" would contact the caregivers forthwith by telephone.

Professional healthcare needs cost effective night time errandrunning, portable telemedicine, etc., enabling specialist nurses tobe more efficient and productive with less work by allowing them tovideo conference (telepresence) doctors for more timely, "on thespot," diagnosis of patients. The CareBotPro" can carry all thespecialized supplies and equipment the IV or wound care nursingspecialists might need. At night the MSR can deliver bedpans,medications, even take vital signs, etc. to those in need while thenight shift nurses are busy with a crisis, or other importantduties on their wing or floor.

Homeland Security needs mobile robots patrolling public venues withWMD and small arms weapon detect. This deployment woulddramatically improve public safety in our post 9/11 world at lowercost and greater efficiencies than human guards only. For example,human guards would tire quickly hauling multiple WMD detectionsystems. GeckoSystems' SecurityBot" MSRs would not.

Commercial and military users desire the elimination of the man inthe loop to enable unmanned ground and air vehicles such asdriverless automobiles, trucks, and drone aircraft to not requireroutine, constant or not infrequent, human control. GeckoSystems'advanced family of hardware and AI software technologies can enableMSRs that can explore urban dwellings with high levels ofsituational awareness due to multiple layers of sensor fusion,while looking for human inhabitants --automatically-- without anyhuman invention or control. This can save lives by placing ourtroops back one or more steps from an unforeseen ambush.

Intelligent mobile service robots are over 80% software. What trulydifferentiates GeckoSystems from the rest of the world is theirincredibly fast, automatic self-navigation software, GeckoNav.Without going into the details of real-time mapping, cognizantnavigation, planned path patrol, sensor fusion, short-term memory,situational awareness, and other "buzz words," GeckoNav makespossible automatic patrolling and navigation in peopled or dynamicenvironments, out of the box automatic learning of surroundings,and safe control of the MSR. GeckoNav is the primary artificialintelligence (AI) engine of all their mobile robot products.Regarding maintenance and technical support, GeckoZap", thediagnostic and compliance software tool provides criticalcalibration and diagnostic capabilities to service personnel in asingle package, further reducing maintenance and support costs.

GeckoChat provides real-time voice synthesis and recognitioncoupled with scheduling, natural language processing and expertsystems to achieve a complete verbal interaction package. Developedfor use in the home environment, especially in the context of eldercare, the benefits of GeckoChat include programming by the family,verbal reminders of past, present, and future events, surrogateshort-term memory, verbal control of the robot, and verbalconfirmation of critical events such as medicine or other medicalregimes. However, GeckoChat can be easily extended to handle nearlyany verbal task for mobile robot control.

GeckoTrak is their real-time color machine vision system withobject tracking, motion vector detection using sensor fusion withsonar range finding, and body heat infrared detection. All thisenables an equipped MSR to, for example, recognize and followindividuals in the home or detect and pursue intruders in a publicsafety or commercial security setting, automatically, without humanintervention.

The CareBot:
For a non technical discussion of what a GeckoSystems' CareBotdoes, the short answer is that it decreases the difficulty andstress for the caregiver that needs to watch over grandma, mom, orother family members most, if not much, of the time day in and dayout due to concerns about their well being, safety, and security.

But, first lets look at some other labor saving, automatic homeappliances most of us use routinely. For example, needing to do twoor more necessary chores and/or activities at the same time, likelaundering clothes and preparing supper.

The automatic washing machine needs no human intervention after thedirty clothes are placed in the washer, the laundry powder pouredin, and the desired wash cycle set. Then, this labor savingappliance runs automatically until the washed clothes are ready tobe placed in another labor saving home appliance, the automaticclothes dryer. While the clothes are being washed and/or dried, thecaregiver prepares supper using several time saving home applianceslike the microwave oven, crock pot, blender, and conventionalstove, with possible convection oven capabilities.

After supper, the dirty pots, pans, and dishes are placed in theautomatic dishwasher to be washed and dried while the familyretires to the den to watch TV, and/or the kids to do homework.Later, perhaps after the kids have gone to bed, the caregiver maythen have the time to fold, sort, and put up the now freshlylaundered clothes.

Much like these useful and cost effective appliances, a CareBothelps the caregiver as a new type of labor saving, time managementautomatic home appliance.

For example, the caregiver frequently feels time stress when theyneed to go shopping for 2 or 3 hours, and are uncomfortable whenthey have to be away for more than an hour or so. Time stress ismuch worse for the caregiver with a frail elderly parent who mustbe reminded to take medications at certain times of the day. Howcan the caregiver be away for 3-4 hours when Grandma must take herprescribed medication every 2 or 3 hours? If the caregiver istrapped in traffic for an hour or two beyond the 2 or 3 theyexpected to be gone, this time stress can be very difficult forthe caregiver to moderate.

Not infrequently, the primary caregiver has a 24 hour, 7 days aweek responsibility. After weeks and weeks of this sometimestedious, if not onerous routine, how does the caregiver get a dayoff? To bring in an outsider is expensive (easily $75-125 per dayfor just 8 hours) and there is the concern that medication will bemissed or the care receiver have an accident requiring immediateassistance by the caregiver, or someone they must designate. Andthe care receiver may be very resistant to a stranger coming into her home and running things.

So what is it worth for a care receiver to have an automatic systemto help take care of Grandma? Just 3 or 4 days a month off on adaylong shopping trip, a visit with friends, or just take in amovie would cost $225-500 per month. And that scenario assumes thatGrandma is willing to be taken care of by a stranger during thoseneeded and appropriate days off.

So perhaps an automatic caregiver, a CareBot, might be prettyhandy, and potentially very cost effective from the primarycaregivers perspective.

The care receiver's perception of a CareBot is much different fromthe caregiver's. Its a new kind of companion that always staysclose to them enabling family and friends to care for them fromafar. It tells them jokes, retells family anecdotes, reminds themto take medication, reminds them that family is coming over soon(or not at all), recites Bible verses, plays favorite songs and/orother music. It alerts them when unexpected visitors, or intrudersare present. It notifies designated caregivers when a potentiallyharmful event has occurred, such as a fall, fire in the home, orjust not found by the CareBot for too long a time. And it respondsto calls for help and notifies those that the caregiver determinedshould be immediately notified when any anticipated event occurs.

The family can customize the personality of the CareBot. Thevoices cadence can be fast or slow. The intonation can be breathy,or abrupt. The voices volume can range from very loud to verysoft. The response phrases from the CareBot for recognized wordsand phrases can be colloquial and/or unique to the familys ownheritage. The personality can range from brassy to timid dependingon how the caregiver, and others appropriate, chooses it to be.

Generally, the care receiver is pleased at the prospect of familybeing able to drop in for a virtual visit using the onboardwebcam and video monitor for at home video conferencing. The carereceiver may feel much more needed and appreciated when their farflung family and friends can look in on them any where in theworld where they can get broadband internet access and simply chatfor a bit.

Why is Grandma really interested in a CareBot? She wants to stay inher home, or her familys home, as long as she possibly can. Whatsthat worth? Priceless. Or, an average nursing home is $4,500 permonth for an environment that is too often the beginning of aspiral downward in the care receivers health. Thats probably$2-3K more per month for them to be placed where they really dontwant to be. Financial payback on a CareBot? Less than a year-Emotional payback for the family to have this new automaticcaregiver? Nearly instantaneous.

Mission Statement:
GeckoSystems' vision is to create practical mobile robot solutionsfor personal, business, and government use. We are committed todeliver service robots of high quality that safe, cost effective,and gratifying for all stakeholders.

Safe Harbor:
Statements regarding financial matters in this press release otherthan historical facts are "forward-looking statements" within themeaning of Section 27A of the Securities Act of 1933, Section 21Eof the Securities Exchange Act of 1934, and as that term is definedin the Private Securities Litigation Reform Act of 1995. Except forhistorical information contained herein, the statements in thisnews release are forward-looking statements that are made pursuantto the safe harbor provisions of the Private Securities LitigationReform Act of 1995. The Company intends that such statements aboutthe Company's future expectations, including future revenues andearnings, technology efficacy and all other forward-lookingstatements be subject to the Safe Harbors created thereby.Forward-looking statements involve known and unknown risks anduncertainties, which may cause a company's actual results,performance and achievement in the future to differ materially fromforecasted results, performance, and achievement. The Company is adevelopment stage firm that continues to be dependent upon outsidecapital to sustain its existence. Since these statements (futureoperational results and sales) involve risks and uncertainties andare subject to change at any time, the Company's actual results maydiffer materially from expected results. The Company undertakes noobligation to publicly release the result of any revisions to theseforward-looking statements that may be made to reflect events orcircumstances after the date hereof, or to reflect the occurrenceof unanticipated events or changes in the Company's plans orexpectations.

Contact:
http://www.GeckoSystems.com
or
Investor Relations: 1-866-227-3268
International: +1 678-413-9236

Source: GeckoSystems Intl. Corp.