Object Detection Using Sim2Real Domain Randomization for Robotic Applications

Horváth, Dániel; Erdős, Gábor; Istenes, Zoltán; Horváth, Tomáš; Földi, Sándor

Abstract

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% mAP50 scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints.

Citation

Horváth, D., Erdős, G., Istenes, Z., Horváth, T., & Földi, S. (2023). Object Detection Using Sim2Real Domain Randomization for Robotic Applications. IEEE Transactions on Robotics, 39(2), 1225-1243. https://doi.org/10.1109/tro.2022.3207619

• Journal Article Type: Article
• Acceptance Date: Aug 24, 2022
• Online Publication Date: Oct 12, 2022
• Publication Date: 2023-04
• Deposit Date: Mar 27, 2024
• Publicly Available Date: Mar 27, 2024
• Journal: IEEE Transactions on Robotics
• Print ISSN: 1552-3098
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Volume: 39
• Issue: 2
• Pages: 1225-1243
• DOI: https://doi.org/10.1109/tro.2022.3207619
• Keywords: Computer vision for automation, deep learning in robotics and automation, localization, sim2real knowledge transfer
• Public URL: http://researchrepository.napier.ac.uk/Output/3577467