Resolution-enhanced optical inspection system to examine metallic nanostructures using structured illumination.

We developed a structured illumination-based optical inspection system to inspect metallic nanostructures in real time. To address this, we used post-image-processing techniques to enhance the image resolution. To examine the fabricated metallic nanostructures in real time, a compact and highly resolved optical inspection system was designed for practical industrial use. Structured illumination microscopy yields multiple images with various linear illumination patterns, which can be used to reconstruct resolution-enhanced images. Images of nanosized posts and complex structures reflected in the structured illumination were reconstructed into images with improved resolution. A comparison with wide-field images demonstrates that the optical inspection system exhibits high performance and is available as a real-time nanostructure inspection platform. Because it does not require special environmental conditions and enables multiple systems to be covered in arrays, the developed system is expected to provide real-time and noninvasive inspections during the production of large-area nanostructured components.

Quality-diversity based semi-autonomous teleoperation using reinforcement learning.

Recent successes in robot learning have significantly enhanced autonomous systems across a wide range of tasks. However, they are prone to generate similar or the same solutions, limiting the controllability of the robot to behave according to user intentions. These limited robot behaviors may lead to collisions and potential harm to humans. To resolve these limitations, we introduce a semi-autonomous teleoperation framework that enables users to operate a robot by selecting a high-level command, referred to as option. Our approach aims to provide effective and diverse options by a learned policy, thereby enhancing the efficiency of the proposed framework. In this work, we propose a quality-diversity (QD) based sampling method that simultaneously optimizes both the quality and diversity of options using reinforcement learning (RL). Additionally, we present a mixture of latent variable models to learn multiple policy distributions defined as options. In experiments, we show that the proposed method achieves superior performance in terms of the success rate and diversity of the options in simulation environments. We further demonstrate that our method outperforms manual keyboard control for time duration over cluttered real-world environments.