Characterisation of Grasp Quality Metrics

ArXiv, 2018

Current robotic manipulation requires reliable methods to predict whether a certain grasp on an object will be successful or not prior to its execution. Different methods and metrics have been developed for this purpose but there is still work to do to provide a robust solution. In this article we combine different metrics to evaluate real grasp executions. We use different machine learning algorithms to train a classifier able to predict the success of candidate grasps. Our experiments are performed with two different robotic grippers and different objects. Grasp candidates are evaluated in both simulation and real world. We consider 3 different categories to label grasp executions: robust, fragile and futile. Our results shows the proposed prediction model has success rate of 76\%.

2018

1 Increasing the flexibility and general-purpose applicability of robots is a longstanding goal. 2 Several avenues of research are addressing these goals, ranging from integration of multi3 ple sensors to allow robots to perceive their surroundings and adapt accordingly, to more 4 sophisticated control algorithms that enable robots to re-plan based on current status, to 5 development of more dexterous means of manipulating objects. As part of the manipula6 tion thrust, there has been a recent increase in the development of robotic hands. Inspired 7 by nature, these end effectors hold potential for allowing robots to pick up and manipulate 8 a broader range of objects, without requiring customized end-of-arm tooling or grippers. 9 With this rapidly-growing number of robot hands with diverse designs, there is a need to 10 capture their individual competencies and characteristics under a unified framework. In 11 addition to knowledge of basic hand characteristics such as the number of ...

In this paper, a new Multi-Aspect Grasp (MAG) performance index is presented for evaluating grasp quality during an object manipulation task. The position of grasp points, the configuration of cooperative manipulators, and the kinetic aspects of manipulating arms and the grasped object are considered in the MAG index. The MAG index is used to evaluate the candidate points to choose the best grasp point and to select the most effective branch of the inverse kinematics solution, with respect to the given task. Simulation results, which are validated with analytical solutions, show the merits of the proposed index. According to these results, the MAG index indicates that in planar object manipulation tasks without rotation, the best grasp point is the object center of the mass, which is physically meaningful.

2012 IEEE International Conference on Robotics and Automation, 2012

Grasp quality metrics which analyze the contact wrench space are commonly used to synthesize and analyze preplanned grasps. Preplanned grasping approaches rely on the robustness of stored solutions. Analyzing the robustness of such solutions for large databases of preplanned grasps is a limiting factor for the applicability of data driven approaches to grasping. In this work, we will focus on the stability of the widely used grasp wrench space epsilon quality metric over a large range of poses in simulation. We examine a large number of grasps from the Columbia Grasp Database for the Barrett hand. We find that in most cases the grasp with the most robust force closure with respect to pose error for a particular object is not the grasp with the highest epsilon quality. We demonstrate that grasps can be reranked by an estimate of the stability of their epsilon quality. We find that the grasps ranked best by this method are successful more often in physical experiments than grasps ranked best by the epsilon quality.

Tehnicki Vjesnik-technical Gazette, 2022

Predicting the quality of the robot end-effector grasp quality during an industrial robot manipulator operation can be an extremely complex task. As is often the case with such complex tasks, Artificial Intelligence methods may be applied to attempt the creation of a model -if sufficient data exists. The presented dataset uses a publicly available dataset, consisting of 992632 measurements of position, torque, and velocity -for each of the three joints of three fingers of the simulated end-effector. The dataset is first analyzed and pre-processed to prepare it for model training. The duplicate values are removed from the dataset, as well as the statistical outliers. Then, a multilayer perceptron (MLP) machine learning algorithm is applied to 80% of the data contained in the dataset, using the Grid Search algorithm to determine the best combination of MLP hyperparameters. As the dataset consists of torque, velocity, and speed measurements for separate joints and fingers of the tested end-effector the testing is performed to see if a subset of the inputs may be used to regress the robustness of the given grip. The normalization of the dataset is also applied, and its effect on the regression quality is tested. The results, evaluated with the coefficient of determination, show that while the best model is achieved using all the possible inputs, a satisfactory result can be obtained using only velocity and torque.The results also show that the normalization of the dataset improves the regression quality in all the observed cases.

2005 International Symposium on Computational Intelligence in Robotics and Automation

We propose a new and efficient approach to compute task oriented quality measures for dextrous grasps. Tasks can be specified as a single wrench to be applied, as a rough direction in form of a wrench cone, or as a complex wrench polytope. Based on the linear matrix inequality formalism to treat the friction cone constraints we formulate respective convex optimization problems, whose solutions give the maximal applicable wrench in the task direction together with the needed contact forces. Numerical experiments show that application to complex grasps with many contacts is possible.

This paper describes a practical approach to the robot grasping problem. An approach that is composed of two different parts. First, a vision-based grasp synthesis system implemented on a humanoid robot able to compute a set of feasible grasps and to execute any of them. This grasping system takes into account gripper kinematics constraints and uses little computational effort.

2006

This paper addresses a new approach to the problem of selecting contact locations for grasping in the presence of shape and contact location uncertainty. Focusing on twodimensional planar objects and two-finger grasps for simplicity, we present a principled approach for selecting contact points by minimizing the risk of force-closure failure. The key contribution of the paper is the risk measure defined on grasp plans. The risk measure successfully distinguishes grasps that are equivalent without uncertainty, and we illustrate the properties of the measure with simulation experiments in two classes of objects.

Lecture Notes in Mechanical Engineering, 2020

This work presents grasp planning on everyday objects using vision. The hand considered is a one degree-of-freedom parallel jaw gripper of Mitsubishi Movemaster robot. Candidate grasping points are chosen on the object and a grasp matrix is computed for the grasp. The grasp matrix can be used to computationally determine a force-closure grasp feasibility. For selecting the candidate grasping points, image of the object is used. Three quality metrics based on different physical notions of quality of grasp are computed. The first quality measure tells how far a grasp is from violating the friction limits, the second gives the worst case performance of the force-closure for all external wrenches, and the third tells how well the object is enclosed from all directions. The main contribution of the paper is to compare grasps based on different quality measures and understand their physical interpretation.

2010

Humans are adept at grasping different objects robustly for different tasks. Robotic grasping has made significant progress, but still has not reached the level of robustness or versatility shown by human grasping. It would be useful to understand what parameters (called grasp measures) humans optimize as they grasp objects, how these grasp measures are varied for different tasks, and whether they can be applied to physical robots to improve their robustness and versatility. This paper demonstrates a new way to gather human-guided grasp measures from a human interacting haptically with a robotic arm and hand. The results revealed that a human-guided strategy provided grasps with higher robustness on a physical robot even under a vigorous shaking test (91%) when compared with a state-of-the-art automated grasp synthesis algorithm (77%). Furthermore, orthogonality of wrist orientation was identified as a key human-guided grasp measure, and using it along with an automated grasp synthesis algorithm improved the automated algorithm's results dramatically (77% to 93%).