We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
We present a method for improved release of whole-hand virtual grasps. It addresses the problem of objects “sticking” during release after the user’s (real) fingers interpen...
The autonomous execution of mobile manipulation tasks in unstructured, dynamic environments requires the consideration of various motion constraints. The task itself imposes constr...
— In this paper we develop a theory of metamodules and an associated distributed asynchronous planner which generalizes previous work on metamodules for lattice-based modular rob...
Daniel J. Dewey, Michael P. Ashley-Rollman, Michae...