The motivation of this project comes from finding visual servoing methods that are free of feature extraction and tracking. For traditional image based visual servoing methods, prominent features are first extracted from the image, and then a controller is designed to make the vector of feature positions converge to a desired value.
Considering the image as sets, we formulate the problem in the non-vector space and design stabilizing controller in this space. The general structure of this approach is shown on the right figure. This approach eliminates the feature extraction and tracking used in traditional image based visual servoing.
- J. Zhao, Y. Jia, N. Xi, W. Li, B. Song, and L. Sun, Visual Servoing Using Non-vector Space Control Theory, 2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Preprint.
- J. Zhao，B. Song, N. Xi, K. Lai, H. Chen, and C. Qu, Compressive Feedback Based Non-vector Space Control, American Control Conference (ACC), Montréal, Canada, 2012. Preprint
- B. Song, J. Zhao, N. Xi, K. Lai, R. Yang, and C. Qu, Non-vector Space Control for Nanomanipulations based on Compressive Feedbacks, IEEE International Conference on Robotics and Automation (ICRA), 2012. PDF
- J. Zhao, B. Song, N. Xi, and K. Lai, Mutation Analysis Models for Visual Servoing in Nanomanipulations, 2011 IEEE Conference on Decision and Control (CDC), December 12-15, 2011, Orlando, FL, pp. 5683-5688. PDF