A procedural knowledge approach to task-level control

Effective task-level control is critical for robots that are to engage in purposeful activity in real-world environments. This paper describes PRS-Lite, a task-level controller grounded in a proce-dural knowledge approach to action description. The controUer embodies much of the philosophy that underlies the Procedural Reasoning System (PRS) but in a minimalist fashion. Several fea-tures of PRS-Lite distinguish it from its predeces-sor, including a richer goal semantics and a gener-alized control regime. Both of these features are critical for supporting the management of con-tinuous processes employed in current-generation robots. PRS-Lite has been used extensively as a task-level controller for a robot whose underlying behaviors are implemented as fuzzy rules. Tasks to which it has been applied include vision-based tracking, autonomous exploration, and complex delivery scenaxios