Abstract

This work presents a novel and simple approach in the area of manipulation of unknown objects considering both geometric and mechanical constraints of the robotic hand. Starting with an initial blind grasp, our method improves the grasp quality through manipulation considering the three common goals of the manipulation process: improving the hand configuration, the grasp quality and the object positioning, and, at the same time, prevents the object from falling. Tactile feedback is used to obtain local information of the contacts between the fingertips and the object, and no additional exteroceptive feedback sources are considered in the approach. The main novelty of this work lies in the fact that the grasp optimization is performed on-line as a reactive procedure using the tactile and kinematic information obtained during the manipulation. Experimental results are shown to illustrate the efficiency of the approach.

Highlights

  • Object manipulation is a common task in service and industrial robotics

  • Using basic geometry and the information obtained from the tactile sensors and the finger kinematics, the angles β i can be computed as functions of the current contact points Ci, the origin

  • This paper has proposed an approach to manipulate unknown objects based on tactile and kinematic information, using two fingers and pursuing three common manipulation goals: the optimization of the hand configuration, the optimization of grasp quality and the optimization of the object orientation

Read more

Summary

Introduction

Object manipulation is a common task in service and industrial robotics. The development of complex robotics hands has impulsed the search of manipulation strategies to take advantage of this hardware resource [1]. One straightforward way is the use of an exploration method [2] to search for hand configurations that improve a manipulation index, i.e., the fingers are moved following a predefine strategy and if the result improves the grasp (according to any quality index), a new step is done, otherwise the movement is drawn back and a new one is tested. In other words, it is like a blind search in the grasp space.

Proposed Approach
Grasp Modeling
Main Manipulation Algorithm
Manipulation Strategies
Index to be Optimized
Optimization Strategy
System Setup
Experimental Results
Summary and Future Work
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call