The first layer let the robot avoid both static and dynamic obstacles. Allen would sit in the middle of the room until approached at which point it would it would scurry away avoid obstacles as it went.
The second layer made the robot randomly wander about. Every 10 seconds or so, a desire to head in a random direction would be generated.
The third layer made the robot look (with it sonars) for distant places and try to head towards them. Progress was monitored by odometry.
Allen was later fitted with a different set of layers. The first layer was the same as before. The second differed in that it made Allen follow walls. The third layer differed also; it examined the sonar data looking for doorways.