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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The 3D shape of a robot's end-effector plays a critical role in determiningit's functionality and overall performance. Many industrial applications relyon task-specific gripper designs to ensure the system's robustness andaccuracy. However, the process of manual hardware design is both costly andtime-consuming, and the quality of the resulting design is dependent on theengineer's experience and domain expertise, which can easily be out-dated orinaccurate. The goal of this work is to use machine learning algorithms toautomate the design of task-specific gripper fingers. We propose Fit2Form, a 3Dgenerative design framework that generates pairs of finger shapes to maximizedesign objectives (i.e., grasp success, stability, and robustness) for targetgrasp objects. We model the design objectives by training a Fitness network topredict their values for pairs of gripper fingers and their corresponding graspobjects. This Fitness network then provides supervision to a 3D Generativenetwork that produces a pair of 3D finger geometries for the target graspobject. Our experiments demonstrate that the proposed 3D generative designframework generates parallel jaw gripper finger shapes that achieve more stableand robust grasps compared to other general-purpose and task-specific gripperdesign algorithms. Video can be found at https://youtu.be/utKHP3qb1bg.

Fit2Form: 3D Generative Model for Robot Gripper Form Design