Intent Inference for Collaborative Tasks: Papers from the AAAI Fall Symposium
Benjamin Bell and Eugene Santos, Cochairs
As decision support systems become more capable of autonomous performance, they must engage more fully with human operators (and other autonomous entities), negotiating task assignments, anticipating near-term needs, and proactively providing information, analysis, and alerts. A body of work in intent inference has shed much light on how automation systems can be given some measure of understanding of their users' tasks and needs. But decision support systems are seldom limited to a single operator, and research into team intent-inference is therefore assuming greater importance.
Understanding team-level intent requires a multidisciplinary approach informed by team dynamics and workflow, workplace procedures, cognitive task analysis, reasoning under uncertainty, and intelligent collaborative agents. By bringing together researchers from the intent inference community, those engaged in the study of collaboration, and prominent players in the application domains, this symposium will help foster the emerging discipline of team intent inference and promote the development of intent-aware decision support for multi-operator complex systems.