Many tasks require humans to manipulate dynamically complex objects and maintain appropriate safety margins, such as placing a cup of coffee on a coaster without spilling. This study examined how humans learn such safety margins and how they are shaped by task constraints and changing variability with improved skill. Eighteen subjects used a manipulandum to transport a shallow virtual cup conta...

The present experiment investigated the sensitivity for end-state comfort in a bimanual object manipulation task. Participants were required to simultaneously reach for two bars and to place the objects' ends into two targets on the table. The design of the experiment allowed to dissociate the relative roles of initial means (e.g., the selection of grips) and final postures (e.g., the anticipat...

This paper describes formulation and management of constraints that, combined with a nonlinear optimization algorithm, enable interactive geometrically aware manipulation of articulated objects. Going beyond purely kinematic or dynamic approaches, our solution method directly employs geometric constraints to ensure noninterpenetration during object manipulation. We present the formulation of th...

• E The rope is tied around a cylindrical pole by dual 6 D.O.F direct drive manipulators. • E The manipulators confirm that the rope is grasped by both hands using the force sensor. • E A flexible object model and a CCD camera vision system are used to recognize the shape of the rope.

This paper introduces, motivates, and illustrates a new approach to the model-ing of lexicon base. This lexicon is used in the process of scene generation, described in terms of sentences in Persian. The lexicon base is rich enough to handle scene expressions. It contains not only case frame information, but also it helps to determine the following (a) meaning of spatial propositions; (b) the p...

We aim to enable robot to learn tabletop object manipulation by imitation. Given external observations of demonstrations on object manipulations, we believe that two underlying problems to address in learning by imitation is 1) segment a given demonstration into skills that can be individually learned and reused, and 2) formulate the correct RL (Reinforcement Learning) problem that only conside...