ALT + +→ Schriftgröße anpassen
ALT + /→ Kontrast anpassen
ALT + M→ Hauptnavigation
ALT + Y→ Socials
ALT + W→ Studiengang wählen
ALT + K→ Homenavigation
ALT + G→ Bildwechsel
ALT + S→ Übersicht
ALT + P→ Funktionsleiste
ALT + O→ Suche
ALT + N→ Linke Navigation
ALT + C→ Inhalt
ALT + Q→ Quicklinks
ESC→ Alles zurücksetzen
X
A - keyboard accessible X
A
T

« Overview

26.01.2019

ICRA paper 2019 accepted

Congrats to Thomas Gulde and the whole team.

Our new work on Machine-Vision based articulated indiustrial robot pose estimation will be presented at IEEE International Conference on Robot and Automation (ICRA) conference in Mai in Montreal. We present a pipeline for real-world data production to study and apply further our RoPose framework [Gulde at al 2018]. RoPose is a learning-based AI-framework to estimate robot joints and poses directly from monocular images. This is an important step towards several applications in the industry I4.0 domain.

See you in Montreal at ICRA 2019 May 20-24.

Related work:

Thomas Gulde, Dennis Ludl, Cristóbal Curio: RoPose: CNN-based 2D Pose Estimation of Industrial Robots. 4th IEEE International Conference on Automation Science and Engineering (CASE) 2018, Munich, Germany, August 20-24, 2018: 463-470 PDF