Next Article in Journal
Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages
Next Article in Special Issue
Efficient Reject Options for Particle Filter Object Tracking in Medical Applications
Previous Article in Journal
Testing the Performance of Multi-Frequency Low-Cost GNSS Receivers and Antennas
Previous Article in Special Issue
Toward Smart Traceability for Digital Sensors and the Industrial Internet of Things
Article

A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks

1
Fraunhofer Institute for Manufacturing, Engineering and Automation IPA, Nobelstraße 12, 70569 Stuttgart, Germany
2
Max Planck Institute for Intelligent Systems, Max-Planck-Ring 4, 72076 Tübingen, Germany
3
Institute of Industrial Manufacturing and Management IFF, University of Stuttgart, Allmandring 35, 70569 Stuttgart, Germany
*
Authors to whom correspondence should be addressed.
Academic Editor: Marina Indri
Sensors 2021, 21(6), 2030; https://doi.org/10.3390/s21062030
Received: 29 January 2021 / Revised: 5 March 2021 / Accepted: 10 March 2021 / Published: 13 March 2021
Manual inspection of workpieces in highly flexible production facilities with small lot sizes is costly and less reliable compared to automated inspection systems. Reinforcement Learning (RL) offers promising, intelligent solutions for robotic inspection and manufacturing tasks. This paper presents an RL-based approach to determine a high-quality set of sensor view poses for arbitrary workpieces based on their 3D computer-aided design (CAD). The framework extends available open-source libraries and provides an interface to the Robot Operating System (ROS) for deploying any supported robot and sensor. The integration into commonly used OpenAI Gym and Baselines leads to an expandable and comparable benchmark for RL algorithms. We give a comprehensive overview of related work in the field of view planning and RL. A comparison of different RL algorithms provides a proof of concept for the framework’s functionality in experimental scenarios. The obtained results exhibit a coverage ratio of up to 0.8 illustrating its potential impact and expandability. The project will be made publicly available along with this article. View Full-Text
Keywords: view planning; reinforcement learning; simulation; robotics; smart sensors; automated inspection view planning; reinforcement learning; simulation; robotics; smart sensors; automated inspection
Show Figures

Figure 1

MDPI and ACS Style

Landgraf, C.; Meese, B.; Pabst, M.; Martius, G.; Huber, M.F. A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks. Sensors 2021, 21, 2030. https://doi.org/10.3390/s21062030

AMA Style

Landgraf C, Meese B, Pabst M, Martius G, Huber MF. A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks. Sensors. 2021; 21(6):2030. https://doi.org/10.3390/s21062030

Chicago/Turabian Style

Landgraf, Christian, Bernd Meese, Michael Pabst, Georg Martius, and Marco F. Huber. 2021. "A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks" Sensors 21, no. 6: 2030. https://doi.org/10.3390/s21062030

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop