Using perception to plan incremental adaptations

Abstract

A robot system operating in an environment in which there is uncertainty and change needs to combine the ability to react with the ability to plan ahead. In a previous paper we proposed a solution to the problems of integrating planning and reaction: cast planning as adaptation of a reactive system. The planner, asynchronously tuning the reactor, decides on the appropriate parts of the reactor to be modified based on perceptions: information gathered in the reactor for the express purpose to inform the planner. In this paper, we show the benefits of using perception to adapt the reactor where it needs to be updated most and present our first experimental results from the planner-reactor architecture.<>