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

State estimation from measured data is crucial for robotic applications asautonomous systems rely on sensors to capture the motion and localize in the 3Dworld. Among sensors that are designed for measuring a robot's pose, or forsoft robots, their shape, vision sensors are favorable because they areinformation-rich, easy to set up, and cost-effective. With recent advancementsin computer vision, deep learning-based methods no longer require markers foridentifying feature points on the robot. However, learning-based methods aredata-hungry and hence not suitable for soft and prototyping robots, as buildingsuch bench-marking datasets is usually infeasible. In this work, we achieveimage-based robot pose estimation and shape reconstruction from camera images.Our method requires no precise robot meshes, but rather utilizes adifferentiable renderer and primitive shapes. It hence can be applied to robotsfor which CAD models might not be available or are crude. Our parameterestimation pipeline is fully differentiable. The robot shape and pose areestimated iteratively by back-propagating the image loss to update theparameters. We demonstrate that our method of using geometrical shapeprimitives can achieve high accuracy in shape reconstruction for a softcontinuum robot and pose estimation for a robot manipulator.

Image-based Pose Estimation and Shape Reconstruction for Robot Manipulators and Soft, Continuum Robots via Differentiable Rendering