A Layered Heterogeneous Cognitive Robotics Architecture

Alistair Campbell, Debra Burhans

The snarpy cognitive robotics architecture is a new member of the family of GLAIR architectures that performs grounded reasoning and action on real and simulated robots. We employ the SNePS knowledge representation, reasoning, and acting system and the Pyro robotics toolkit. We describe the architecture together with the methodologies used to realize it. With the snarpy architecture, robotic agents can be very easily and quickly constructed having both high-level reasoning skills and low-level acting and sensing abilities on real robotics hardware. Two prototype snarpy agents are presented.

Subjects: 17. Robotics; 4. Cognitive Modeling

Submitted: Jun 1, 2006

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.