Massively parallel support for case-based planning

The Caper case-based planner uses the massive parallelism of the Connection Machine to quickly retrieve cases and plans from a large, unindexed memory. The system can retrieve cases and plans based on any feature of the target problem, including abstractions of target features. By controlling which features are part of the retrieval probe and their level of abstraction, a wide range of queries can be issued. The more specific the query, the closer the retrieved cases are to the current problem. Unlike serial planners, Caper can afford to retrieve several plans to achieve different parts of the target problem, and then merge them into a composite plan that solves most of the target goals with less adaptation. We are testing Caper's case-retrieval components in two domains: car assembly and transportation logistics.<
>