Flexible Task Execution and Cognitive Control in Human-Robot Interaction

A robotic system that interacts with humans is expected to flexibly execute structured cooperative tasks while reacting to unexpected events and behaviors. In this thesis, these issues are faced presenting a framework that integrates cognitive control, executive attention, structured task execution and learning. In the proposed approach, the execution of structured tasks is guided by top-down (task-oriented) and bottom-up (stimuli-driven) attentional processes that affect behavior selection and activation, while resolving conflicts and decisional impasses. Specifically, attention is here deployed to stimulate the activations of multiple hierarchical behaviors orienting them towards the execution of finalized and interactive activities. On the other hand, this framework allows a human to indirectly and smoothly influence the robotic task execution exploiting attention manipulation. We provide an overview of the overall system architecture discussing the framework at work in different applicative contexts. In particular, we show that multiple concurrent tasks/plans can be effectively orchestrated and interleaved in a flexible manner; moreover, in a human-robot interaction setting, we test and assess the effectiveness of attention manipulation and learning processes.