Automatic Generation of 2D Canonical Grasps
نویسنده
چکیده
The concepts of canonical grasp and grasp transformation graph proposed in 10] are useful in grasp planning and dextrous manipulation. However, one critical element, namely the automatic generation of the canonical grasps, is required for the grasp transformation graph to be practical. In this paper, we present an algorithm to generate all canonical grasps in the planar case automatically. To this end, we consider a series of kinematic constraints due to hand and object geometry, which must be satissed for a grasp to be feasible. Once the technique for the kinematic feasibility analysis of a grasp is available, we can then readily construct a system to generate automatically all canonical grasps by rst enumerating possible contact conngurations and then evaluating their feasibility. A graphical simulation system is provided to illustrate the presented algorithm.
منابع مشابه
Exploration of the grasp space using independent contact and non-graspable regions
This report presents the use of independent contact and non-graspable regions to generate the grasp space for 2D and 3D discrete objects. The grasp space is constructed via a sampling method, which provides samples of force-closure or non force-closure grasps, used to compute regions of the graspable or non-graspable space, respectively. The method provides a reliable procedure for an efficient...
متن کاملThe arc-transversal median algorithm: a geometric approach to increasing ultrasonic sensor azimuth accuracy
513 Though a convex polyhedron has been used in the numerical example, the proposed approach is, in fact, adaptable to concave polyhedra, since no special property of a convex polyhedron is used. For a given feasible canonical grasp, in the form of a set of contact pairs, there may be infinite configurations of the grasping system. Consequently, an interesting future research direction is to ex...
متن کاملLearning Grasp Affordances Through Human Demonstration
When presented with an object to be manipulated, a robot must identify the available forms of interaction. How might an agent acquire this mapping from object representation to action? In this paper, we describe an approach that learns a mapping from objects to grasps from human demonstration. For a given object, the teacher demonstrates a set of feasible grasps. We cluster these grasps in term...
متن کاملIdentification of Grasp Quality Based on Learning Method
It is easy to generate a series of possible grasps through a state-of-the-art automatic grasp planner, but it is hard to figure out which grasp is better by the robot itself. A learning-based approach is presented in this paper to solve this problem. In order to develop an algorithm that predicts the quality of a robotic grasp before execution, a large grasp sample data set is collected, includ...
متن کاملGrasp Moduli Spaces
We present a new approach for modelling grasping using an integrated space of grasps and shapes. In particular, we introduce an infinite dimensional space, the Grasp Moduli Space, which represents shapes and grasps in a continuous manner. We define a metric on this space allowing us to formalize ‘nearby’ grasp/shape configurations and we discuss continuous deformations of such configurations. W...
متن کامل