We describe techniques for combining two types of knowledge systems: expert and machine learning. Both the expert system and the learning system represent information by logical decision rules or trees. Unlike the classical views of knowledge-base evaluation or refinement, our view accepts the contents of the knowledge base as completely correct. The knowledge base and the results of its stored cases will provide direction for the discovery of new relationships in the form of newly induced decision rules. An expert system called SEAS was built to discover sales leads for computer products and solutions. The system interviews executives by asking questions, and based on the responses, recommends products that may improve a business' operations. Leveraging this expert system, we record the results of the interviews and the program's recommendations. The very same data stored by the expert system is used to find new predictive rules. Among the potential advantages of this approach are (a) the capability to spot new sales trends and (b) the substitution of less expensive probabilistic rules that use database data instead of interviews.

The author presents an efficient solution to the motion-planning problem for multiple translating robots in the plane. It is shown that careful priority assignment can greatly reduce the average running time of the planner. A priority assignment method is introduced which attempts to maximize the number of robots which can move in a straight line form their start point to their goal point, thereby minimizing the number of robots for which expensive collision-avoiding search is necessary. This prioritization method is extremely effective in sparse workspaces where the moving robots are the primary obstacle.>

A description is given of a robot teaching system for compliant motion strategies, based on recent research in compliant motion planning. The teaching system accepts robot motion commands from a user, and attempts to build a compliant motion strategy from the specified motions. The teaching system has several advantages over previous robot teaching systems. The user is spared many low-level details, such as the specification of conditional tests, compliance parameters, and motion termination conditions. A compliant motion strategy, if found, is guaranteed to work despite uncertainty in the starting configuration of the robot and in robot sensing and control.>