Stable pinching by controlling finger relative orientation of robotic fingers with rolling soft tips

Psomopoulou, Efi; Karashima, Daiki; Doulgeri, Zoe; Tahara, Kenji

doi:10.1017/s0263574717000303

Cited by 12 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventional grasping controllers are designed using analytic models based on the feedback of actuator torques and positions [14]- [17], but subject to limited adaptive ability, especially in grasping objects with various physical properties.…”

Section: A Analytic Methodsmentioning

confidence: 99%

Learning Adaptive Grasping From Human Demonstrations

Wang¹,

Hu²,

Sun³

et al. 2022

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

This work studied a learning-based approach to learn grasping policies from teleoperated human demonstrations which can achieve adaptive grasping using three different neural network (NN) structures. To transfer human grasping skills effectively, we used multi-sensing state within a sliding time window to learn the state-action mapping. By teleoperating an anthropomorphic robotic hand using human hand tracking, we collected training datasets from representative grasping of various objects, which were used to train grasping policies with three proposed NN structures. The learned policies can grasp objects with varying sizes, shapes, and stiffness. We benchmarked the grasping performance of all policies, and experimental validations showed significant advantages of using the sequential history states, compared to the instantaneous feedback. Based on the benchmark, we further validated the best NN structure to conduct extensive experiments of grasping hundreds of unseen objects with adaptive motions and grasping forces.

show abstract

Section: A Analytic Methodsmentioning

confidence: 99%

Learning Adaptive Grasping From Human Demonstrations

Wang¹,

Hu²,

Sun³

et al. 2022

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

show abstract

“…As shown in Figure 7 , this grasper is underactuated; tendon-driven; and consists of two flexible fingers, whose configuration could be changed according to the object’s shape. The grasping state is detected through rolling soft fingertips, and the grasping force and the grasper pose are changed by adjusting the control parameters [ 55 ]. However, there also exist some constraints—such as contact reachability, object restraint, force control, etc.—for a specific manipulating task.…”

Section: Geometric-uncertain Objectsmentioning

confidence: 99%

Feature Sensing and Robotic Grasping of Objects with Uncertain Information: A Review

Wang

Zhang

Zang

et al. 2020

Sensors

View full text Add to dashboard Cite

As there come to be more applications of intelligent robots, their task object is becoming more varied. However, it is still a challenge for a robot to handle unfamiliar objects. We review the recent work on the feature sensing and robotic grasping of objects with uncertain information. In particular, we focus on how the robot perceives the features of an object, so as to reduce the uncertainty of objects, and how the robot completes object grasping through the learning-based approach when the traditional approach fails. The uncertain information is classified into geometric information and physical information. Based on the type of uncertain information, the object is further classified into three categories, which are geometric-uncertain objects, physical-uncertain objects, and unknown objects. Furthermore, the approaches to the feature sensing and robotic grasping of these objects are presented based on the varied characteristics of each type of object. Finally, we summarize the reviewed approaches for uncertain objects and provide some interesting issues to be more investigated in the future. It is found that the object’s features, such as material and compactness, are difficult to be sensed, and the object grasping approach based on learning networks plays a more important role when the unknown degree of the task object increases.

show abstract

“…However, the contribution of tangential forces is not taken into account owing to the assumption of rigid point contact with the classical DAE-2 formulation [18], given that it still depends on the friction cone. In [27][28][29][30][31], the manipulation of a circular object using redundant SD-fingers is showed. In [32], grasping and manipulation using redundant SDfingers considering the gravity effect was presented.…”

Section: Introductionmentioning

confidence: 99%

In-hand manipulation of a circular dynamic object by soft fingertips without angle measurement

García-Rodríguez

Parra-Vega

2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

A multi-fingered robotic hand with curved fingertips enables contact re-positioning without reattaching at the expense of fingertip rolling. This rolling stands for a characteristic that facilitates dexterous manipulation but results in an algebraically complex dynamic model subject to such constraints. The hemispherical shape of fingertips allows a dexterous manipulation when controlling the tangent forces, which are essential to rotate object. However, the measurement of the object angle in practice requires tactile-optical sensing. In this paper, considering robotic fingers with curved soft tips, we propose a feedback control that ensures optimal dynamical grasping of a circular rigid object. It is shown that the collaboration of the contact forces, to get a minimum pose of internal forces, and the tangential forces, to induce the conditions for assuring the grasp closure, is necessary to get a skillful manipulation. In this case, the orientation control of a circular object to the desired angle while avoiding direct measurement of the object angle is presented. Stability conditions of the system are presented in the sense of stability-in-the-manifold. Finally, representative simulations are shown and discussed.

show abstract

Stable pinching by controlling finger relative orientation of robotic fingers with rolling soft tips

Cited by 12 publications

References 47 publications

Learning Adaptive Grasping From Human Demonstrations

Learning Adaptive Grasping From Human Demonstrations

Feature Sensing and Robotic Grasping of Objects with Uncertain Information: A Review

In-hand manipulation of a circular dynamic object by soft fingertips without angle measurement

Contact Info

Product

Resources

About