Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Proactivity in Robots / 3994
Jasmin Grosinger

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. In my work I introduce the notion of equilibrium maintenance as a contribution to this understanding. Formal evidence is provided that equilibrium maintenance is conducive to proactive robots, and I demonstrate my approach in a closed loop with a real robot in a smart home.