• français
    • English
    français
  • Login
Help
View Item 
  •   Home
  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)
  • View Item
  • Home
  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Easy grasping location learning from one-shot demonstration

Conférence invitée
Author
BIMONT, Laurent
HELENON, François
THIERY, Stéphane
ccNYIRI, Eric
543315 Laboratoire d’Ingénierie des Systèmes Physiques et Numériques [LISPEN]
ccGIBARU, Olivier

URI
http://hdl.handle.net/10985/17102
Date
2019

Abstract

In this paper, we propose a fast learner grasping pipeline able to grasp objects at a specific location few minutes after being taught by an operator. Our motivation is to ease reconfiguration of robot according to a specific task, without any CAD model, nor existing database, nor simulator. We build a CNN pipeline which performs a semantic segmentation of object, and recognizes authorized and prohibited grasping location shown during demonstration. For that we have simplified the input space, created a data augmentation process and proposed a light CNN architecture allowing learning in less than 5 minutes. Validation on a real 7-DOF robot shown good performances (70 to 100% depending on the object), with only a one-shoot operator’s demonstration. Performances remain good when grasping similar unseen objects, and with several objects in the robot’s workspace using few demonstrations. A video highlighting the main aspects can be found at https://www.youtube.com/watch?v=rYCIk6njBo4

Files in this item

Name:
LISPEN_ICRA2020_2019_bimont.pdf
Size:
2.081Mb
Format:
PDF
View/Open

Collections

  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)

Related items

Showing items related by title, author, creator and subject.

  • A simple and generic CAD/CAM approach for AFM probe-based machining 
    Communication avec acte
    BROUSSEAU, Emmanuel; ARNAL, Benoît; THIERY, Stéphane; ccNYIRI, Eric; ccGIBARU, Olivier (LAMDAMAP, 2015)
    Atomic Force Microscopy (AFM) probe-based machining allows surface structuring at the nano-scale via the mechanical modification of material. This results from the direct contact between the tip of an AFM probe and the ...
  • Towards CNC Automation in AFM Probe-Based Nano Machining 
    Communication avec acte
    BROUSSEAU, Emmanuel; ARNAL, Benoît; THIERY, Stéphane; MAYOR, J.Rhett; ccNYIRI, Eric; ccGIBARU, Olivier (University of Wisconsin-Madison, 2013)
    This paper presents a feasibility study, which aims to demonstrate the applicability of the CNC automation philosophy for the process of AFM probe-based nano machining conducted on commercial AFM instruments. In particular, ...
  • Leap Motion pour la capture de mouvement 3D par spline L1 
    Communication sans acte
    HERNOUX, Franck; ccBEAREE, Richard; ccGAJNY, Laurent; ccNYIRI, Eric; BANCALIN, Julien; ccGIBARU, Olivier (2013)
    Afin d’accroître leur compétitivité les entreprises ont recours de plus en plus à des systèmes robotisés pour realiser différentes tâches complexes. Ces robots sont très attractifs par leur coût mais nécessitent d’introduire ...
  • Fast B-Spline 2D Curve Fitting for unorganized Noisy Datasets 
    Communication sans acte
    EL HAYEK, Nadim; DAMAK, Mohamed; NOUIRA, Hichem; ANWER, Nabil; ccNYIRI, Eric; ccGIBARU, Olivier (2014)
    In the context of coordinate metrology and reverse engineering, freeform curve reconstruction from unorganized data points still offers ways for improvement. Geometric convection is the process of fitting a closed shape, ...
  • On Algebraic Approach for MSD Parametric Estimation 
    Communication avec acte
    OUESLATI, Marouene; THIERY, Stéphane; MORARU, George; ccBEAREE, Richard; ccGIBARU, Olivier (IMAACA, 2011)
    This article address the identification problem of the natural frequency and the damping ratio of a second order continuous system where the input is a sinusoidal signal. An algebra based approach for identifying parameters ...

Browse

All SAMCommunities & CollectionsAuthorsIssue DateCenter / InstitutionThis CollectionAuthorsIssue DateCenter / Institution

Newsletter

Latest newsletterPrevious newsletters

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales