Integrating Planning into Reactive High-Level Robot Programs

IndiGolog is a high-level programming language for robots and intelligent agents that supports on-line planning and plan execution in dynamic and incompletely known environments. Programs may perform sensing actions that acquire information at runtime and react to exogenous actions. In this paper, we show how IndiGolog can be used to write robot control programs that combine planning, sensing, and reactivity. Moreover,we present enhancements to IndiGolog in three areas: a more effective replanning mechanism for situations where the environment has changed, an approach to planning in dynamic settings that uses a simulated environment, and a mechanism that allows planning to be done within a larger program that includes reactive threads.