Making large-scale support vector machine learning practical
Advances in kernel methods
Digital Image Processing
Evaluating the Role of Force Feedback for Biomanipulation Tasks
VR '06 Proceedings of the IEEE conference on Virtual Reality
CAD Model-based Tracking and 3D Visual-based Control for MEMS Microassembly
International Journal of Robotics Research
Hi-index | 0.00 |
One of the key challenges of microsystem- and nanotechnologies is the automation of robot-based nanomanipulation. However, there is limited sensor feedback due to lack of appropriate sensors. Sensor feedback is required for repeatable actuator movements from macro- down to the nanoscale. This complicates the design of reliable automation processes. In this paper, the development of an automated robot-based toolbox for cell injection and handling is presented. This toolbox includes several sensor methods, bridging several orders of magnitude as feedback for automation. A non-linear support vector machine (SVM) is applied for classification of the viability of cells as feedback for quality control. A visual servoing algorithm for position tracking of the injection needle as well as an injection force sensor have been developed. First automation results and the control system are explained.