The Thinking
Cap (TC) is a system for autonomous robot navigation based
on fuzzy logic which has been implemented and validated on several mobile
platforms. Parts of the TC were previously reported in a series of papers. The main ingredients of TC are:
- a library of fuzzy behaviors for indoor navigation, like
obstacle avoidance, wall following, and door crossing;
- a context-depending blending mechanism that combines the
recommendations from different behaviors into a tradeoff control;
- a set of perceptual routines, including sonar-based feature
extraction, and detection of closed doors and blocked corridors;
- an approximate map of the environment, together with a
positioning mechanism based on natural landmarks;
- a navigation planner that generates a behavior combination
strategy, called a B-plan, that achieves the given
navigation goal; and
- a monitor that reinvokes the planner whenever the current
B-plan is no more adequate to the current goal.
Fig. 1: the TC architecture.
