Making robots proactive through equilibrium maintenance

Abstract

In order to be proactive, robots should be capable of generating and selecting their own goals, and pursuing activities towards their achievement. Goal reasoning has focused on the former set of cognitive abilities, and automated planning on the latter. Despite the existence of robots that possess both capabilities, we lack a general understanding of how to combine goal generation and goal achievement. This paper introduces the notion of equilibrium maintenance as a contribution to this understanding. We provide formal evidence that equilibrium maintenance is conducive to proactive robots, and demonstrate our approach in a closed loop with a real robot in a smart home.