Specifying and achieving goals in open uncertain robot-manipulation domains
This addresses the challenge of reliable robot manipulation in open, uncertain domains, though it appears incremental as it combines existing tools like planning and state-estimation.
The paper tackles the problem of enabling robots to interpret and achieve goals in uncertain environments with occlusion and sensing errors, by developing an integrated system that uses formal specifications, hierarchical planning, and online execution to operate robustly on real robots.
This paper describes an integrated solution to the problem of describing and interpreting goals for robots in open uncertain domains. Given a formal specification of a desired situation, in which objects are described only by their properties, general-purpose planning and reasoning tools are used to derive appropriate actions for a robot. These goals are carried out through an online combination of hierarchical planning, state-estimation, and execution that operates robustly in real robot domains with substantial occlusion and sensing error.