In this work, we present a general approach to task planning based on contingent planning and run-time sensing, which forms part of a robot task planning framework called KVP. Using the general-purpose PKS planner, we model information-gathering actions at plan time that have multiple possible outcomes at run time. As a result, perception and sensing arise as necessary preconditions for manipulation, rather than being hard-coded as a task itself. We demonstrate the effectiveness of our approach on two simple scenarios covering visual and force sensing, and discuss its applicability to more general tasks in automation and mobile manipulation, involving arbitrary numbers of sensors and manipulators.
|Title of host publication||ICRA 2013 Workshop on Combining Task and Motion Planning|
|Number of pages||4|
|Publication status||Published - 1 May 2013|