| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 3.42 MB | Adobe PDF |
Advisor(s)
Abstract(s)
Industrial robot manipulators are widely used for repetitive
applications that require high precision, like pick-and-place. In many
cases, the movements of industrial robot manipulators are hard-coded or
manually defined, and need to be adjusted if the objects being manipulated
change position. To increase flexibility, an industrial robot should
be able to adjust its configuration in order to grasp objects in variable/
unknown positions. This can be achieved by off-the-shelf visionbased
solutions, but most require prior knowledge about each object to
be manipulated. To address this issue, this work presents a ROS-based
deep reinforcement learning solution to robotic grasping for a Collaborative
Robot (Cobot) using a depth camera. The solution uses deep
Q-learning to process the color and depth images and generate a ϵ-
greedy policy used to define the robot action. The Q-values are estimated
using Convolutional Neural Network (CNN) based on pre-trained
models for feature extraction. Experiments were carried out in a simulated
environment to compare the performance of four different pretrained
CNN models (RexNext, MobileNet, MNASNet and DenseNet).
Results show that the best performance in our application was reached by
MobileNet, with an average of 84 % accuracy after training in simulated
environment.
Description
Keywords
Cobots Reinforcement learning Computer vision Pick-and-place Grasping
Citation
Gomes, Natanael Magno; Martins, Felipe N.; Lima, José; Wörtche, Heinrich (2021). Deep reinforcement learning applied to a robotic pick-and-place application. In Pereira, Ana I.; Fernandes, Florbela P.; Coelho, João Paulo; Teixeira, João Paulo; Pacheco, Maria F.; Alves, Paulo; Lopes, Rui Pedro (Eds.) Optimization, learning algorithms and applications: first International Conference, OL2A 2021. Cham: Springer Nature. p. 251-265. ISBN 978-3-030-91884-2
Publisher
Springer Nature