Planning with Dynamic Goals for Robot Execution

摘要

We have been developing ROGUE, an architecture that integrates high-level planning with a low-level execut-ing 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 get-ting coffee, and picking up and delivering mail or faxes. Users post tasks asynchronously and RoauE controls the corresponding planning and execution continuous process. This paper presents the extensions to a non-linear state-space planning algorithm to allow for the interaction to the robot executor. We focus on pre-senting how executable steps are identified based on the planning model and the predicted execution per-formance; how interrupts from users requests are han-dled and incorporated into the system; how executable plans are merged according to their priorities; and how monitoring execution can add more perception knowl-edge to the planning and possible needed re-plannlng 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. 1.