Using Retinanet to determine local graspability for a suction actuator

Master thesis (2021)

Authors

F.A.R. van Tilburg Mechanical Engineering

Contributors

Carlos Hernández Robot Dynamics - Mechanical, Maritime and Materials Engineering (supervisor 1)
M. Wisse Robot Dynamics - Mechanical, Maritime and Materials Engineering (supervisor 1)
J.F.P. Kooij Intelligent Vehicles - Mechanical, Maritime and Materials Engineering (supervisor 2)
M. Imre Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering (supervisor 2)
Faculty
Mechanical Engineering
Copyright: © 2021 Floris van Tilburg
Deep learning Bin-picking Suction gripper Unknown objects Robot vision
More Info
expand_more

Published Date

26-08-2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical Engineering

Abstract

Suction based robotic actuators have potential for the bin-picking industry, but are currently not usable due the needed speed, accuracy and ability to handle novel and adversarial objects. An evaluation of the state of the art grasp pipeline developed by Mahler et al. [1] for detecting grasps on novel objects lead us to split the problem of robotic grasp generation into a global and a local component. The state of the art solution had the ability to fill the role of global evaluator leaving a local evaluator to be developed. This local grasp evaluator was obtained by training a neural network on a suction based grasp dataset, which was created using a newly developed annotation tool. The proposed grasp pipeline obtained by combining these two showed a 95.27% pick success rate for a random setup and a 90.28% success rate for solely novel objects.