A case-based approach to robot motion planning

The authors present a case-based robot motion planning system. Case-based planning affords on the system good average case performance by allowing it to understand and exploit the tradeoff between completeness and computational cost, and permits it to successfully plan and learn in a complex domain without the need for an extensively engineered and possibly incomplete domain theory. The system automatically classifies motion planning problems according to the solution method that is most appropriate, not by using a fixed classification of problems, but by learning with experience how to map problems to solution methods.<
>