Abstract
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.
Original language | English |
---|---|
Article number | 42 |
Journal | npj Computational Materials |
Volume | 10 |
Issue number | 1 |
DOIs | |
Publication status | Published - 2024 Dec |
Bibliographical note
Publisher Copyright:© The Author(s) 2024.
ASJC Scopus subject areas
- Modelling and Simulation
- General Materials Science
- Mechanics of Materials
- Computer Science Applications