Plan Generation and Execution For Robotics

Abstract

Applicability of existing industrial robot systems is limited; truly flexible automation must make use of significant sensory feedback to respond appropriately to each new stimulus. This requires fundamental research in problem solving and the monitoring of plan execution. A number of problems in this area requiring further research are discussed, including dealing with time, planning for parallel execution, planning for information gathering, planning for planning, learning, interactive planning, dynamic plan repair, and distributed robotics.

This paper was prepared for the NSF-sponsored workshop on the research needed to advance the state of robotics, to be held April 15-17, 1980.