Improvements in robust 2D visual servoing

Abstract

Abstract-A fundamental step towards broadening the use of real world image-based visual servoing is to deal with the important issues of reliability and robustness. In order to address this issue, a closed loop control law is proposed that simultaneously accomplishes a visual servoing task and is robust to a general class of image processing errors. This is achieved with the application of widely accepted statistical techniques of robust M-estimation. Furthermore improvement have been added in the weight computation process: memory, initialization. Indeed, when the error between current visual features and desired ones are large, which occurs when large robot displacement are required, M-estimator may not detect outliers. To address this point, the method we propose to initialize the confidence in each feature is based on the LMedS estimators. Experimental results are presented which demonstrate visual servoing tasks which resist severe outlier contamination.

Feature tracking for visual servoing purposes

“…This tracking approach has been widely used at Irisa to validate modeling aspects and to design new control laws [17,37,43,40]. Furthermore in some critical industrial processes, such a simple approach ensures the required robustness.…”

“…Therefore, in the presented results, we have used a robust control law [40] that allows rejection of miss-tracked points. In Figure 5c, red crosses are the initial points location, blue crosses are their desired locations while the green crosses are the final points location.…”

A Qualitative Visual Servoing to ensure the Visibility Constraint

“…The introduction of an activation matrix within the control law to activate or inactivate some features is also done in [21], [3]. In these two papers, an activation matrix H is used to discard non-satisfactory points or outliers.…”

“…In these two papers, an activation matrix H is used to discard non-satisfactory points or outliers. In [21], outliers are points that are badly tracked. By removing these features from the control law, the visual servoing is less sensitive to tracking errors.…”

Autonomous Surgical Robot using Visual Servoing in the Extended Image Plane

“…general class of image processing errors [10,11]; different approaches that constraint camera movements [12,13,14,15,16] or use the zoom [17] or move the camera backwards along its optical axis [18] to keep all points in the camera field of view during the control task .…”