Autopilot adjustment using CBR
A ship's autopilot adjustment is a matter of utmost importance since it affects its safety, command as well as fuel and time efficiency. Numerous techniques usually based on models which simulate the weather and loading conditions are used in order to achieve optimum adjustment. Nevertheless, perfect steering is not yet accomplished mainly due to the infinite number of different situations during sea passages. We claim that a CBR approach which selects the best out of a finite, pre-installed set of device configurations using specific criteria can compete with existing methods and continuously improves itself during the ship's life cycle.
Keywords: artificial intelligence, expert systems, case based reasoning, CBR, ship steering, autopilot adjustment