Guiding a robotic gripper by visual feedback for object manipulation tasks

Abstract

This paper presents a novel object manipulation technique that could be adopted by any advanced mechatronic platform in order to perform demanding pick and place tasks.The ultimate goal of a robotics researcher is to provide an appli cable manipulation solution that minimizes user's involvement.It has been shown that the best solution to this problem is provided by the introduction of sensors that allow an automatic or, at least, semi-automatic grasping of the targets. The proposed method relies on a vision-based framework that is responsible for several vital tasks that affect directly the manipulation process. The contribution of the paper incorporates a shape retrieval technique accompanied with classification and clustering algorithms that are utilized during the objects' pose estimation process. The experimental results obtained confirm the validity of the presented approach.

Human skill capture: A Hidden Markov Model of force and torque data in peg-in-a-hole assembly process

“…Generally, manipulation tasks contain gross motion states and fine motion states. For the design of a robotic solution, a gross motion such as approaching a workpiece can be controlled using vision feedback [2] whilst a fine motion needs to rely on force and torque (F/T) feedback. Some intermediate passive solutions such as using a compliant * The authors acknowledge support from the EPSRC Centre for Innovative Manufacturing in Intelligent Automation, in undertaking this research work under grant reference number EP/IO33467/ 1. gripper have been proposed [3], but they cannot sufficiently address the uncertainties in very complex situations.…”

What, Where and How? Introducing pose manifolds for industrial object manipulation

“…The adequate implementation of robotic manipulation tasks necessitates the accurate estimation of the 6 DoF pose of the testing object (Kouskouridas, Amanatiadis, & Gasteratos, 2011;Kouskouridas, Charalampous, & Gasteratos, 2014;Popovic et al, 2010;Sansoni et al, 2014). The simplicity along with facile training sessions render template matching methods as one of the most widely used solutions for object detection tasks (Ferrari, Tuytelaars, & Van Gool, 2006;Hinterstoisser et al, 2011;Ma, Chung, & Burdick, 2011;Rios-Cabrera & Tuytelaars, 2013;Tejani et al, 2014).…”

Perancangan Sistem Kendali pada Lengan Assistive Social Robot menggunakan Kamera

“…Salah satu penelitian lain tentang lengan robot lain dengan menggunakan platform lengan robot STAIR (STanford AI Robots), telah dikembangkan oleh Saxena [10] pada aplikasi untuk meletakkan berbagai macam peralatan makan pada rak dengan berbasis visual menggunakan kamera untuk menentukan lokasi bendanya. Sebuah metodologi yang berbasis umpan balik visual untuk melakukan tugas mengambil dan meletakkan benda juga telah dikembangkan oleh Kouskouridas [11]. Dalam mengestimasi posisi objek melibatkan hubungan antara gambar dalam bidang 2D.…”