Control of a Six-Legged Mobile Robot Using the Soar Cognitive Architecture

Abstract

This paper describes the development of the Cognitive Robotic System (CRS) for studying intelligent and autonomous unmanned vehicles. This system uses a multi-threaded software system written using Java to integrate the Soar cognitive architecture with a sixlegged mobile robot and its sensors and motors. The results of experiments in which the Cognitive Robotic System was used to control the hexapod on missions of GPS navigation with obstacle avoidance are described. The CRS was designed so that its capabilities can be expanded in the future through the inclusion of additional software systems and more sophisticated Soar agents.

Biologically-Inspired Spiking Neural Networks with Hebbian Learning for Vision Processing

“…In this case, we were able to first develop a Neuron class, and we could thoroughly debug that piece before moving on to the higher level functions of the code. This approach has worked well for us in other applications as well, for example a flapping wing aerodynamics C++ code [42], a Monte Carlo C++ code for gas dynamics [43], and a Java robotics code [8]. All of these codes would have taken far longer to develop in FORTRAN or C, and would have resulted in unmaintainable code when completed.…”

Vision-Based Target Geolocation and Optimal Surveillance on an Unmanned Aerial Vehicle

“…Papers which discuss architectures for improving the intelligence and autonomy of ground vehicles include Hanford and Long, 3 Hanford et al 4 and Janrathitikarn and Long. 5 One important sensor that many vehicles have is a camera.…”