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

We propose a closed-loop, multi-instance control algorithm for visuallyguided reaching based on novel learning principles. A control Lyapunov functionmethodology is used to design a reaching action for a complex multi-instancetask in the case where full state information (poses of all potential reachingpoints) is available. The proposed algorithm uses monocular vision andmanipulator joint angles as the input to a deep convolution neural network topredict the value of the control Lyapunov function (cLf) and correspondingvelocity control. The resulting network output is used in real-time as visualcontrol for the grasping task with the multi-instance capability emergingnaturally from the design of the control Lyapunov function.  We demonstrate the proposed algorithm grasping mugs (textureless andsymmetric objects) on a table-top from an over-the-shoulder monocular RGBcamera. The manipulator dynamically converges to the best-suited target amongmultiple identical instances from any random initial pose within the workspace.The system trained with only simulated data is able to achieve 90.3% graspsuccess rate in the real-world experiments with up to 85Hz closed-loop controlon one GTX 1080Ti GPU and significantly outperforms a Pose-Based-Visual-Servo(PBVS) grasping system adapted from a state-of-the-art single shot RGB 6D poseestimation algorithm. A key contribution of the paper is the inclusion of afirst-order differential constraint associated with the cLf as a regularisationterm during learning, and we provide evidence that this leads to more robustand reliable reaching/grasping performance than vanilla regression on generalcontrol inputs.

LyRN (Lyapunov Reaching Network): A Real-Time Closed Loop approach from Monocular Vision