Grasping skill is a major ability that a wide number of real-life applications require for robotisation. Stateof-the-art robotic grasping methods perform prediction of object grasp locations based on deep neural networks which require huge amount of labeled data for training and prove impracticable in robotics. In this paper, we propose to generate a large scale synthetic dataset with ground tr...

Although, in the task of grasping via a data-driven method, closed-loop feedback and predicting 6 degrees freedom (DoF) grasp rather than conventionally used 4DoF top-down are demonstrated to improve performance individually, few systems have both. Moreover, sequential property that is hardly dealt with, while approaching motion necessarily generates series observations. Therefore, this paper s...

As a first step towards transferring human grasping capabilities to robots, we analyzed the grasping behavior of human subjects. We derived a taxonomy in order to adequately represent the observed strategies. During the analysis of the recorded data, this classification scheme helped us to obtain a better understanding of human grasping behavior. We will provide support for our hypothesis that ...

This paper presents a novel approach to visuo-haptic perception of grasping/manipulative tasks. The proposed approach is founded on a hierarchical Bayesian model which integrates the visual information with the haptic data to reach a reasonable percept of what is happening in grasping tasks. The primary goal of the approach is to identify what type of grasping behaviour is being performed by th...

We measure grasping and resultant forces and reveal that the grasping force is kept stable while subjects shake objects. Then, we propose a new method to feedback grasping and resultant forces for multi-finger object manipulation. While shaking an object, the proposed method keeps the grasping force and eliminates the influence of the resultant force to the distance between fingers. We do an ex...

The Smeets and Brenner view on grasping is simple: grasping is in fact pointing. In our comments we examine the model beyond the reach-to-grasp task, namely, by grasping (without reaching) of moving objects and eating. The model fits the data of both tasks. Although generalization of a model to different tasks usually strengthens its acceptance, in the present case it reveals its shortcomings, ...