Object Detection Using Sim2Real Domain Randomization for Robotic Applications

Authors:
Open Access
Publisher website
Google Scholar
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% $\mathrm{{mAP}}_{50}$ 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.
Funding Information
  • Research on prime exploitation of the potential provided by the industrial digitalisation (ED_18-2-2018-0006)
  • Ministry for Innovation and Technology and the National Research
  • Development and Innovation Office
  • National Lab for Autonomous Systems
  • Application Domain Specific Highly Reliable IT Solutions
  • National Research, Development and Innovation Fund of Hungary (TKP2020-NKA-06)
  • Thematic Excellence Programme (2020-4.1.1.-TKP2020)
  • National Challenges Subprogramme

This publication has 54 references indexed in Scilit: