Date of Award
December 2020
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Mechanical Engineering
Committee Member
Laine Mears
Committee Member
Oliver Myers
Committee Member
Brian Riley
Abstract
Visual servoing is a control technique that uses image data as feedback in a motion control loop. This technique is useful in tasks that require robots or other automated motion systems to automatically inspect parts or structures in motion. One specific method of visual servoing is Image Based Visual Servoing (IBVS), a method that simply minimizes the differences between an observed image orientation and a desired one. This method works well for orientations where the differences are small, but in the case where the desired orientation is more difficult to reach, the system can become unstable, either driving to infinity through a phenomenon known as camera retreat or following non-optimal and non-repeatable trajectories. This work attempts to address camera retreat and other non-optimal paths by applying dynamic programming, an optimal control method that can determine an optimal trajectory by partitioning possible trajectories into multiple smaller trajectories. Using a cost function to penalize undesirable sub trajectories, the optimal overall trajectory can be determined and initiated. This work attempts to explore an optimized portioned approach using dynamic programming to address camera retreat. The motivation for this is to create a high precision visual servoing sequence suitable for high tolerance automated processes; specifically, quality inspection of airplane wire harnesses.
Recommended Citation
Allen, Mark S., "Optimal Control of Image Based Visual Servoing (IBVS) for High Precision Visual Inspection Applications" (2020). All Theses. 3439.
https://tigerprints.clemson.edu/all_theses/3439