A simple but robust control law for the grasping manipulation of deformable objects is presented. In the handling of deformable objects, grasping and manipulation must be performed simultaneously despite uncertainties during the handling process. We will propose a control law to perform grasping and manipulation of deformable objects using a realtime vision system.

We use psychophysics to investigate human-centered transparency of grasping in unilateral robot-assisted minimally invasive surgery (RAMIS) without force feedback. Instead of the classical definition of transparency, we define here a human-centered transparency, focusing on natural action and perception in RAMIS. Demonstrating this approach, we assess the effect of gripper scaling on human-cent...

This paper describes an integrated system for dextrous manipulation using a Utah-MIT hand that allows one to look at the higher levels of control in a number of grasping and manipulation tasks. The system consists of a number of low-level system primitives for grasping, integrated hand and robotic arm movement, tactile sensors mounted on the fingertips, sensing primitives to utilize joint posit...

Recently, Holmes et al. (2011b) suggested that grasping is only subject to Weber's Law at early but not late points of a grasping movement. They therefore conclude that distinct visual computations and information may guide early and late portions of grasping. Here, we argue that their results can be explained by an interesting statistical artifact, and cannot be considered indicative of the pr...

There have been many researches on object grasping in cooperating systems assuming no object slippage and stable grasp and the control system is designed to keep the contact force inside the friction cone to prevent the slippage. However undesired slippage can occur due to environmental conditions and many other reasons. In this research, dynamic analysis and control synthesis of a cooperating ...

This paper concerns with the problem of deep learning parameters tuning using a genetic algorithm (GA) in order to improve the performance of deep learning (DL) method. We present a GA based DL method for robot object recognition and grasping. GA is used to optimize the DL parameters in learning procedure in term of the fitness function that is good enough. After finishing the evolution process...

The control system of a robot operating in a human-centered environments should address the problem of motion planning to generate collision-free motions for grasping and manipulation tasks. To deal with the complexity of these tasks in such environments, different motion planning algorithms can be used. We present a motion planning framework for manipulation and grasping tasks consisting of di...