Tiong, Leslie Ching Ow Yoo, Hyuk Jun Kim, Nayeon Kim, Chansoo Lee, Kwan-Young Han, Sang Soo Kim, Donghun 2024-03-13T07:30:18Z 2024-03-13T07:30:18Z 2024-03-13 2024-02 2057-3960 https://pubs.kist.re.kr/handle/201004/149463 Although robot-based automation in chemistry laboratories can accelerate the material development process, surveillance-free environments may lead to dangerous accidents primarily due to machine control errors. Object detection techniques can play vital roles in addressing these safety issues; however, existing detection models still suffer from insufficient accuracy in environments involving complex and noisy scenes. With the aim of improving safety in a surveillance-free laboratory, we report a deep learning (DL)-based object detector, namely, DenseSSD. For the foremost and frequent problem of detecting positions of transparent chemical vessels, DenseSSD achieved a mean average precision (mAP) over 95% based on a complex dataset involving both empty and solution-filled vials, greatly exceeding those of conventional detectors; such high precision is critical to minimizing failure-induced accidents. Additionally, DenseSSD was observed to be generalizable to other laboratory environments, maintaining its high precisions under the variations of solution colors, camera view angles, background scenes, experiment hardware and type of chemical vessels. Such robustness of DenseSSD supports that it can universally be implemented in diverse laboratory settings. This study conclusively demonstrates the significant utility of DenseSSD in enhancing safety within automated material synthesis environments. Furthermore, the exceptional detection accuracy of DenseSSD opens up possibilities for its application in various other fields and scenarios where precise object detection is paramount. English Nature Publishing Group | Shanghai Institute of Ceramics of the Chinese Academy of Sciences (SICCAS) Machine vision-based detections of transparent chemical vessels toward the safe automation of material synthesis Article 10.1038/s41524-024-01216-7 1 npj Computational Materials, v.10, no.1 npj Computational Materials 10 1 Y scie scopus 001167720900001 2-s2.0-85185680331 Chemistry, Physical Materials Science, Multidisciplinary Chemistry Materials Science Article GREEN SYNTHESIS ROBOT