Recent research at the juncture of decision and learning theory are leading to fundamentally new ways of understanding and tackling challenges in sensing, estimation and control problems. This is especially true for human-machine systems, where autonomous machines can efficiently exploit human insights, knowledge and information-gathering capabilitiesto improve robustness and performance in complex, time- and safety-critical situations. To enable seamless human-machine collaboration, the community is striving to solve fundamental questions such as asking human the right question(s) at the right time in the right form and vice-versa; understanding each other’s (human and machine) perspective; fusing soft, imperfect information with hard, sensory data; and adapting to complex and possibly unforeseen environment and situations.
In this context, this workshop aims to bring together experts in the fields of control theory, machine learning, artificial intelligence, and human-machine systems to discuss the fundamentals, state of the art and open questions for the various related topic areas including but are not limited to:value of information and optimization/learning strategies for collaboration.