It's Just Semantics: How to Get Robots to Understand the World the Way We Do

Jen Jen Chung, Julian Förster, Paula Wulkop, Lionel Ott, Nicholas R. J. Lawrance, Roland Siegwart

Abstract: Increasing robotic perception and action capabilities promise to bring us closer to agents that are effective for automating complex operations in human-centered environments. However, to achieve the degree of flexibility and ease of use needed to apply such agents to new and diverse tasks, representations are required for generalizable reasoning about conditions and effects of interactions, and as common ground for communicating with non-expert human users. To advance the discussion on how to meet these challenges, we characterize open problems and point out promising research directions.