Camera-based Obstacle Classification for Automated Reach Trucks Using Deep Learning

Konferenz: ISR 2016 - 47st International Symposium on Robotics
21.06.2016 - 22.06.2016 in München, Germany

Tagungsband: ISR 2016

Seiten: 6Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Himstedt, Marian; Maehle, Erik (Institute of Computer Engineering, University of Lübeck, Germany)

This paper focuses on the classification of obstacles that are widely present in warehouse environments using an RGBD camera. Our approach applies depth segmentation to detect obstacles which are classified using a Convolutional Neural Network and a Support Vector Machine. Our system is evaluated on real-world data captured from an automated reach truck in a warehouse environment.