School of Computer Science, Carnegie Mellon University
AAAI Fall Symposium ``Plan Execution: Problems and Issues'', November, 1996. Pages=61-71.
We have been developing ROGUE, an architecture that integrates
high-level planning with a low-level executing robotic agent. ROGUE is designed as the office gofer task planner for Xavier the robot.
User requests are interpreted as high-level
planning goals, such as getting coffee, and picking up and delivering
mail or faxes. Users post tasks asynchronously and ROGUE controls
the corresponding planning and execution continuous process. This
paper presents the extensions to a nonlinear state-space planning
algorithm to allow for the interaction to the robot executor. We
focus on presenting how executable steps are identified based on the
planning model and the predicted execution performance; how interrupts
from users requests are handled and incorporated into the system; how
executable plans are merged according to their priorities; and how
monitoring execution can add more perception knowledge to the planning
and possible needed re-planning processes. The complete ROGUE
system will learn from its planning and execution experiences to
improve upon its own behaviour with time. We finalize the paper by
briefly discussing ROGUE's learning opportunities.