Integrating Reactive and Deliberative Planning for Agents
Abstract
Autonomous agents that respond intelligently in dynamic, complex environments need to be both reactive and deliberative. Reactive systems have traditionally fared better than deliberative planers in such environments, but are often hard to code and inflexible. To fill in some of these gaps, we propose a hybrid system that exploits the strengths of both reactive and deliberative systems. We demonstrate how out system controls a simulated household robot and compare our system to a purely reactive one in this domain. We also look at a number of relevant issues in anything planning.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1993
- Accession Number
- ADA267631
Entities
People
- Jim Blythe
- W. S. Reilly
Organizations
- Carnegie Mellon University