Grounding Predicates through Actions
Toki Migimatsu,Jeannette Bohg,Toki Migimatsu,Jeannette Bohg
Symbols representing abstract states such as “dish in dishwasher” or “cup on table” allow robots to reason over long horizons by hiding details unnecessary for high-level planning. Current methods for learning to identify symbolic states in visual data require large amounts of labeled training data, but manually annotating such datasets is prohibitively expensive due to the combinatorial number of...
