8 papers
The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination
Hooman Tavakoli Ghinani, Tatjana Legler, Martin Ruskowski
While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables. This pape…
OPC UA Shared-Memory: Conceptual Elaboration and Prototypical Implementation Using Iceoryx2
Thomas Barth, Tatjana Legler, Achim Wagner +1
The increasing virtualization of automation software leads to a growing co-location of heterogeneous applications on shared edge devices and fosters modern microservice architectur…
Learning-Based Strategy for Composite Robot Assembly Skill Adaptation
Khalil Abuibaid, Aleksandr Sidorenko, Achim Wagner +1
Contact-rich robotic skills remain challenging for industrial robots due to tight geometric tolerances, frictional variability, and uncertain contact dynamics, particularly when us…
Sustainable Transfer Learning for Adaptive Robot Skills
Khalil Abuibaid, Vinit Hegiste, Nigora Gafur +2
Learning robot skills from scratch is often time-consuming, while reusing data promotes sustainability and improves sample efficiency. This study investigates policy transfer acros…
A Multi-Camera Vision-Based Approach for Fine-Grained Assembly Quality Control
Ali Nazeri, Shashank Mishra, Achim Wagner +3
Quality control is a critical aspect of manufacturing, particularly in ensuring the proper assembly of small components in production lines. Existing solutions often rely on single…
Federated Action Recognition for Smart Worker Assistance Using FastPose
Vinit Hegiste, Vidit Goyal, Tatjana Legler +1
In smart manufacturing environments, accurate and real-time recognition of worker actions is essential for productivity, safety, and human-machine collaboration. While skeleton-bas…