The project conducts formal, basic research into the modeling of "intention''. This under-researched and ill-understood concept underlies many applications, including online search, calendars, intelligent dialog systems, security applications, self-driving cars, military applications, and many more. This particular project is concerned with domain-independent, formal models underlying all such applications. 'informational attitudes' such as knowledge and belief which capture the information available to the agent, and 'motivational attitudes' such as goals, preference and utility which capture what the agent cares about, have been studied extensively. In contrast, and despite their importance, "action attitudes" which capture the agent's attitude towards different actions she might take in light of her motivations and the information available to her, have been poorly studied. This is true in particular of intention, perhaps the most basic action attitude, and the focus of this project.
The project is grounded in the Principal Investigator's prior work, in which he laid out a computational point of view, dubbed the "database perspective''. That work, which offered an axiomatic theory of the joint revision of belief and simple ('atomic') action intention, is being extended along multiple dimensions:
-- Modeling complex intentions, using Dynamic Epistemic Logic (DEL). -- Modeling achievement intentions. -- Modeling teleology. -- Developing a quantitative ("probabilistic") theory of intention.
