Path planning for robust image-based control

Abstract

To cite this version:Youcef Mezouar, François Chaumette. Path planning for robust image-based control. IEEE Transactions on Robotics and Automation, Institute of Electrical and Electronics Engineers (IEEE), 2002, 18 (4), pp.534-549. <inria-00352101> 534 IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 18, NO. 4, PP. 534-549, AUGUST 2002 Path Planning for Robust Image-based Control Youcef Mezouar and François Chaumette, Member, IEEE Abstract-Vision feedback control loop techniques are efficient for a large class of applications but they come up against difficulties when the initial and desired robot positions are distant. Classical approaches are based on the regulation to zero of an error function computed from the current measurement and a constant desired one. By using such approach, it is not obvious to introduce any constraint in the realized trajectories and to ensure the convergence for all the initial configurations. In this paper, we propose a new approach to resolve these difficulties by coupling path planning in image space and image-based control. Constraints such that the object remains in the camera field of view or the robot avoids its joint limits can be taken into account at the task planning level. Furthermore, by using this approach, current measurements always remain close to their desired value and a control by image-based servoing ensures the robustness with respect to modeling errors. The proposed method is based on the potential field approach and is applied when object shape and dimensions are known or not, and when the calibration parameters of the camera are well or badly estimated. Finally, real time experimental results using an eye-in-hand robotic system are presented and confirm the validity of our approach.

Point-based and region-based image moments for visual servoing of planar objects

“…In that case, the interaction matrix related to x n , y n , and a n is again given by (20), but with:…”

“…Finally, we recall that the interaction matrices (20) and (22) have nice expected forms only when the object is parallel to the image plane. In Section V, we will see that, when the desired object position is parallel to the image plane, satisfactory results are obtained even if the initial position is far away from this configuration.…”

“…However, as soon as the error is large, problems may appear such as reaching local minimum or a task singularity [3]. To overcome these problems, combining path planning and visual servoing is a first approach, since tracking planned trajectories allows the error to always remain small [20], [7], [34]. A second approach is to use the measures to build particular visual features that will ensure expected properties to the control scheme.…”

Robot motion control from a visual memory

“…1 R 2 and 1 t 2 (up to a factor) can be extracted from this collineation matrix [6]. It is also possible to determine the ratio ρ j , defined for each couple of projection between the depth Z j of the 3D point and d 2 [17]:…”

Visual Servoing from Spheres with Paracatadioptric Cameras

“…The partitioned approach has been coupled with a potential function in a control scheme to keep the features in the image boundary. Potential functions can also be used in path planning in the image space to keep the features in the field of view [7]. Similarly, navigation functions can be combined with a global diffeomorphism from a visible set of rigid-body configurations of a special target to an image space, to construct global, dynamical visual servoing systems that guarantees the visibility of the features all times [8].…”