Deep Reinforcement Learning Applied to a Robotic Pick-and-Place Application

Felipe Martins, Heinrich Wörtche, Natanael Gomes (First author), José Lima

Research output: Contribution to conferencePaperAcademic

26 Downloads (Pure)

Abstract

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 vision-based solutions, but most require prior knowledge about each object tobe 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 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 pre-trained CNNmodels (RexNext, MobileNet, MNASNet and DenseNet). Results showthat the best performance in our application was reached by MobileNet,with an average of 84 % accuracy after training in simulated environment.
Original languageEnglish
Number of pages16
Publication statusAccepted/In press - 19 Jul 2021
EventOL2A: International Conference on
Optimization, Learning Algorithms and Applications
- On-line
Duration: 19 Jul 202121 Jul 2021
http://ol2a.ipb.pt/EN_index.html

Conference

ConferenceOL2A: International Conference on
Optimization, Learning Algorithms and Applications
Period19/07/2121/07/21
Internet address

Keywords

  • Cobots
  • reinforcement learning
  • computer vision
  • pick-and-place
  • grasping

Fingerprint

Dive into the research topics of 'Deep Reinforcement Learning Applied to a Robotic Pick-and-Place Application'. Together they form a unique fingerprint.

Cite this