Final report for contract N00014-91-J-1577 (Yale University)
Abstract
The object of the Yale Knowledge-Based Planning project is to find a unified theory of robot planning and sensing. We achieved several results in this direction, including the development of an architecture for a reactive planner, the implementation and testing of a theory of map making by a mobile robot, the development of an algorithm for reasoning about constraints on image hypotheses, and preliminary work on high-speed visual tracking. Our overall model of planning is this: An agent must be continuously executing plans in order to make progress on its goals. These plans are driven by sensors, and can normally cope with deviations from expected results without intervention from the planner. When intervention is required, the planner starts from scratch, generating plans and then revising them on the basis of their projected results. The projector contains a probabilistic model of the world that allows the planner to forecast probable errors. our work on sensing has focused on these areas: (1) Theoretical foundations for set-based decision-making algorithms; (2) Visual tracking and vision-based control of servo systems; and (3) Comparison of set-based and statistically-based estimation
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1994
- Accession Number
- ADA281505
Entities
People
- Drew McDermott
- Gregory D. Hager
Organizations
- Yale University