[en] Recycling is a promising way to prevent the use of
raw material and reduce energy consumption, air pollution and
waste. However, the process of recycling has to be economically
efficient in order to be adopted by industrial manufacturers.
One way to achieve this goal is to improve the recycling rate.
We propose a novel method to design a machine learningbased controller to improve the efficiency of a recycling line by
throwing waste into buckets instead of picking and dropping
them. Our proof-of-concept is demonstrated on stones, because
of their simple and uniform shapes. The method enables an
ABB IRB 340 robot to throw objects to buckets with an
empirical success rate of 99%.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Marlier, Norman ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Laboratoire des Systèmes Multicorps et Mécatroniques
Louppe, Gilles ; Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Big Data
Bruls, Olivier ; Université de Liège - ULiège > Département d'aérospatiale et mécanique ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Laboratoire des Systèmes Multicorps et Mécatroniques
Dislaire, Godefroid ; Université de Liège - ULiège > Urban and Environmental Engineering ; Université de Liège - ULiège > Département ArGEnCo > Géoressources minérales & Imagerie géologique
Language :
English
Title :
Robotic throwing controller for accelerating a recycling line
Publication date :
2019
Event name :
3rd Robotix-Academy Conference on for Industrials Robotics
Event date :
5 juin 2019
By request :
Yes
Audience :
International
Main work title :
Proceedings of the Robotix Academy Conference for Industrial Robotics (RACIR) 2019