A gripper design algorithm for grasping a set of parts in manufacturing lines

Sintov, Avishai; Menassa, Roland; Shapiro, Amir

doi:10.1016/j.mechmachtheory.2016.06.015

Cited by 11 publications

(12 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synthesis of an adaptive gripper with robotic applications was formulated mathematically and solved by Galabov et al [7]. Sintov et al [8] proposed an algorithm called 3D-OCOG (3-Dimensional Objects Common Grasp Search) with the goal of making a gripper similar to robotic arm capable of grasping various objects. The feasibility of the algorithm was validated by the results obtained from simulations and experiments.…”

Section: Introductionmentioning

confidence: 99%

Optimal kinematic design of a single-DOF planar grasper based on metaheuristic optimization

Eqra

Taghvaei

Vatankhah

2019

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

A method is proposed for optimal synthesis of a grasper mechanism for circular objects. A single-DOF linkage-type grasper is developed considering the geometry of the target objects. The mechanism consists of successive coupled four-bar linkages and is capable of grasping circular objects with desirable range of diameter. The synthesis problem is formulated as a constraint optimization problem, while adaptive inertia weight particle swarm optimization (AIW-PSO) approach is used to carry out the solutions. Biomechanical and industrial applications for the mechanism are suggested and investigated by simulations as case studies. To demonstrate the effectiveness of AIW-PSO on the problem, a comparison with two other well-known metaheuristic algorithms namely PSO and genetic algorithm is done. The results show the efficiency of the proposed algorithm and the performance of the mechanism.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimal kinematic design of a single-DOF planar grasper based on metaheuristic optimization

Eqra

Taghvaei

Vatankhah

2019

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…In this section, we discuss a grasp representation based on previous work proposed by Sintov et al (2014Sintov et al ( , 2016). An n-finger grasp of object O can be defined by a set of n contact points,…”

Section: Grasp Representationmentioning

confidence: 99%

“…Similar to the planar case, we divide the parameterization vector into constraints for the shape and size, and the ones that define the contact normals. An n-vertex polyhedron requires 3n − 6 constraints to define its shape and size (Sintov et al, 2016). Here also, we may paramterize some of the triangles forming the polyhedron and their respected posture.…”

Section: Grasp Representationmentioning

confidence: 99%

Simple Kinesthetic Haptics for Object Recognition

Sintov¹,

Ben-David²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Object recognition is an essential capability when performing various tasks. Humans naturally use either or both visual and tactile perception to extract object class and properties. Typical approaches for robots, however, require complex visual systems or multiple high-density tactile sensors which can be highly expensive. In addition, they usually require actual collection of a large dataset from real objects through direct interaction. In this paper, we propose a kinesthetic-based object recognition method that can be performed with any multifingered robotic hand in which the kinematics is known. The method does not require tactile sensors and is based on observing grasps of the objects. We utilize a unique and frame invariant parameterization of grasps to learn instances of object shapes. To train a classifier, training data is generated rapidly and solely in a computational process without interaction with real objects. We then propose and compare between two iterative algorithms that can integrate any trained classifier. The classifiers and algorithms are independent of any particular robot hand and, therefore, can be exerted on various ones. We show in experiments, that with few grasps, the algorithms acquire accurate classification. Furthermore, we show that the object recognition approach is scalable to objects of various sizes. Similarly, a global classifier is trained to identify general geometries (e.g., an ellipsoid or a box) rather than particular ones and demonstrated on a large set of objects. Full scale experiments and analysis are provided to show the performance of the method.

show abstract

“…β is the maximum offset between the gripper front edge and the effective grasping region. It is chosen based on the clearance constraint between the tool and the wall as seen in figure (1). γ is the radius of the biggest circle that can fit inside the grasp region.…”

Section: A Robot Coordinate Systemmentioning

confidence: 99%

“…In [1], Sintov presented a gripper design process for picking and placing objects of different geometry by proposing an algorithm that analyze the geometry of an object and build a library of best grasping points utilizing a 3-fingered robotic gripper. Multi-finger grippers can simulate human grasping especially if they are coupled with force/torque feedback [5] or tactile accurate sensing [6].…”

Section: Introductionmentioning

confidence: 99%

A novel gripper design for multi hand tools grasping under tight clearance constraints and external torque effect

Shaqura

Shamma

2017

2017 IEEE International Conference on Mechatronics and Automation (ICMA)

View full text Add to dashboard Cite

CitationShaqura M, Shamma JS (2017) Abstract-A robotic multi tool gripper design and implementation is presented in this paper. The proposed design targets applications where an actuation task is performed using a wide selection of standard hand tools. The manipulation motion is assumed to be rotational which requires a firm grip to account for external torque on the grasped tool. The setup is assumed to be a conventional workshop panel with hand tools being hanged close to each other, which constraints lateral clearance around the target, and near the wall of the panel, which constraints the depth clearance. Off the shelf grippers are mostly heavy and bulky which make them unsuitable for these requirements. Moreover, they are not optimized in terms of power consumption, simplicity and compactness. These generic grippers are mostly designed for pick and place tasks where no external torques other than those caused by the object weight affects the gripper. The design challenge involves building a gripper that is capable of operating in limited clearance space, firmly grip a variety of standard hand tools with different sizes and shapes. The proposed design is optimized for these objectives and offers a low cost and power consumption solution. The design has been validated in lab and outdoor experiments and has been deployed in real operating platform used in an international robotics competition.

show abstract

A gripper design algorithm for grasping a set of parts in manufacturing lines

Cited by 11 publications

References 43 publications

Optimal kinematic design of a single-DOF planar grasper based on metaheuristic optimization

Optimal kinematic design of a single-DOF planar grasper based on metaheuristic optimization

Simple Kinesthetic Haptics for Object Recognition

A novel gripper design for multi hand tools grasping under tight clearance constraints and external torque effect

Contact Info

Product

Resources

About