English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The image-based visual servoing without models of system is challenging sinceit is hard to fetch an accurate estimation of hand-eye relationship via merelyvisual measurement. Whereas, the accuracy of estimated hand-eye relationshipexpressed in local linear format with Jacobian matrix is important to wholesystem's performance. In this article, we proposed a finite-time controller aswell as a Jacobian matrix estimator in a combination of online and offline way.The local linear formulation is formulated first. Then, we use a combination ofonline and offline method to boost the estimation of the highly coupled andnonlinear hand-eye relationship with data collected via depth camera. A neuralnetwork (NN) is pre-trained to give a relative reasonable initial estimation ofJacobian matrix. Then, an online updating method is carried out to modify theoffline trained NN for a more accurate estimation. Moreover, sliding modecontrol algorithm is introduced to realize a finite-time controller. Comparedwith previous methods, our algorithm possesses better convergence speed. Theproposed estimator possesses excellent performance in the accuracy of initialestimation and powerful tracking capabilities for time-varying estimation forJacobian matrix compared with other data-driven estimators. The proposed schemeacquires the combination of neural network and finite-time control effect whichdrives a faster convergence speed compared with the exponentially convergeones. Another main feature of our algorithm is that the state signals in systemis proved to be semi-global practical finite-time stable. Several experimentsare carried out to validate proposed algorithm's performance.

Adaptive Finite-Time Model Estimation and Control for Manipulator Visual Servoing using Sliding Mode Control and Neural Networks