School of Computer Science, Carnegie Mellon University
ICCBR 95. Pages 169-180
In this paper, we demonstrate our route planning method which retrieves and reuses multiple past routing cases that collectively form a good basis for generating a new routing plan. We briefly present our similarity metric for retrieving a set of similar routes. The metric effectively takes into account the geometric and continuous-valued characteristics of a city map. We then present the replay mechanism and how the planner produces the route plan by analogizing from the retrieved similar past routes. We discuss in particular the strategy used to merge a set of cases and generate the new route. We use illustrative examples and show some empirical results from a detailed online map of the city of Pittsburgh containing over 18,000 intersections and 25,000 street segments.
Also See JETAI for the journal paper.