Gait Control of a Six-Legged Robot on Unlevel Terrain Using a Cognitive Architecture

This paper discusses the use of the Soar cognitive architecture to control gait selection of a six-legged robot using force sensors attached to its feet. The hardware platform also incorporated sonar sensors, a GPS receiver, and a Webcam. The Soar cognitive architecture was used to control the robot, and the Java programming language was used as middleware between Soar and the hardware components. The force sensors were attached and the force profile was examined. Soar productions for controlling the gait were developed. Experiments were performed on terrain which has random holes and obstacles. Two cases were conducted: walking using Soar to select the gait, and using Soar with the chunking turned on for learning.