François Chaumette

Zane Zake, François Chaumette, Nicolò Pedemonte et al.

Cable-Driven Parallel Robots (CDPRs) are a kind of parallel robots that have cables instead of rigid links. Implementing vision-based control on CDPRs leads to a good final accuracy despite modeling errors and other perturbations in the system. However, unlike final accuracy, the trajectory to the goal can be affected by the perturbations in the system. This paper proposes the use of trajectory tracking to improve the robustness of 2 1/2 D visual servoing control of CDPRs. Lyapunov stability analysis is performed and, as a result, a novel workspace, named control stability workspace, is defined. This workspace defines the set of moving-platform poses where the robot is able to execute its task while being stable. The improvement of robustness is clearly shown in experimental validation.

Quentin Bateux, Eric Marchand, Jürgen Leitner et al.

We present a deep neural network-based method to perform high-precision, robust and real-time 6 DOF visual servoing. The paper describes how to create a dataset simulating various perturbations (occlusions and lighting conditions) from a single real-world image of the scene. A convolutional neural network is fine-tuned using this dataset to estimate the relative pose between two images of the same scene. The output of the network is then employed in a visual servoing control scheme. The method converges robustly even in difficult real-world settings with strong lighting variations and occlusions.A positioning error of less than one millimeter is obtained in experiments with a 6 DOF robot.