Detect-Focus-Track-Servo (DFTS): A vision-based workflow algorithm for robotic image-guided micromanipulation
Name
icra_accepted.pdf
Size
972.84 KB
Format
Adobe PDF
Checksum (MD5)
521381b6cc60b4cb530396b035ea8cde
Author(s)
Yang, Liangjing
Youcef-Toumi, Kamal
Tan, U-Xuan
Date Issued
May 2017
Journal
2017 IEEE International Conference on Robotics and Automation (ICRA)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Yang, Liangjing, Kamal Youcef-Toumi, and U-Xuan Tan. “Detect-Focus-Track-Servo (DFTS): A Vision-Based Workflow Algorithm for Robotic Image-Guided Micromanipulation.” 2017 IEEE International Conference on Robotics and Automation (ICRA) (May 2017).
Version
Author's final manuscript
Abstract
Robotic image-guided micromanipulation contributes towards the ease of operation, speed, accuracy, and repeatability in cell manipulation. However, such technology is not fully exploited because of the challenges in the integration of robotic modules with existing microscope systems, and the difficulty in incorporating robot assistance seamlessly into the workflow. In this paper, we propose a vision-based workflow algorithm termed Detect-Focus-Track-Servo (DFTS). It facilitates easy integration of robotic modules. It also supports user interactions while minimizing the need for manual intervention and disruption to workflow through automatic detection, focusing, tracking and servoing. Experimental results suggest satisfactory detection accuracy of 99.0 % at 70 μm tolerance. The robustness test suggests no difference in the accuracy under blurred and cluttered images. The self-focus algorithm is also demonstrated to bring the tip into focus consistently. The track-servo algorithm achieves low sub-pixel uncertainty. By proposing the DFTS workflow algorithm, we hope that the level of autonomy and ease of deployment in robot and vision modules for micromanipulation can be improved so as to open up new possibilities in the development of robotic image-guided cell manipulation.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICRA.2017.7989636
