Home Site

    Page 44
16.4 Table of Contents Bottom of Page Site Map
same side that the robot has chosen to use to avoid the now confounding obstacle. The robustness of this emergent behavior is apparent as the robot finally, after several left/right attempts, succeeds in avoiding the dynamic obstacle, and resumes path.There are emergent behaviors possible in the low cost hardware architecture depicted above. Each separate engine can be a low cost new, or used, PC dedicated to specific types of sensory tasks such as seeing, hearing, touching, smelling, and tasting - as biological processors. The cognitive capabilities such as organizing, analyzing, interpreting, synthesizing, and even guessing are now cost effectively contributing to possible higher levels of emergent behaviors. Whatever computational power is needed for a given capability can now satisfy that requirement on an as needed, minimum cost basis.
It is now the beginning
of the twenty-first century and time for the introduction and production of truly cost effective, utilitarian man-rated, servant class mobile robots. This confluence of AI software and low cost hardware solutions is very exciting and we welcome those who share our vision.

R. Martin Spencer, is President/CEO, GeckoSystems, Inc. (www.GeckoSystems.com)

GeckoBrain(TM) Capabilities

Developed within the domain of artificial intelligence mobile robot software:

1. Self-mapping long-term memory with built in curiosity enables complete definition of areas for mobile robot to operate.

2. Efficient path planning algorithms enable Autopilot/Seek of user-selected endpoints in near real time.

3. Subsumptive software architecture enables cognizant navigation for unexpected (or unmapped) obstacle (static or dynamic) avoidance while maintaining the ability to resume path following.

4. Sensor fusion technology is sensor friendly with its AI software architecture enabling differing, high-count sensor system synergy.

5. Short term AI memory software such that its proprietary sensor fused, scanning CompoundedSensorArrayTM may be fully utilized. Consequently, total cost for sensor systems cost is dramatically reduced.

6. The demonstration of emergent behaviors – actions and reactions that were not pre-programmed.

The resultant level of mobile autonomy is analogous to that of a blind man with a cane in his own home. This capability is achieved using 15-20% of an Intel Pentium running at 250-300mhz with Microsoft’s Win98SE. All GeckoBrain source code is in C++ and is not hardware or OS centric.

To Page 43

16.4 Table of Contents
Top of Page

To Page 45

16.4 2002

PC AI Magazine - PO Box 30130 Phoenix, AZ 85046 - Voice: 602.971.1869 Fax: 602.971.2321
e-mail: info@pcai.com - Comments? webmaster@pcai.com