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

Pushing is an essential non-prehensile manipulation skill used for tasksranging from pre-grasp manipulation to scene rearrangement, reasoning aboutobject relations in the scene, and thus pushing actions have been widelystudied in robotics. The effective use of pushing actions often requires anunderstanding of the dynamics of the manipulated objects and adaptation to thediscrepancies between prediction and reality. For this reason, effectprediction and parameter estimation with pushing actions have been heavilyinvestigated in the literature. However, current approaches are limited becausethey either model systems with a fixed number of objects or use image-basedrepresentations whose outputs are not very interpretable and quickly accumulateerrors. In this paper, we propose a graph neural network based framework foreffect prediction and parameter estimation of pushing actions by modelingobject relations based on contacts or articulations. Our framework is validatedboth in real and simulated environments containing different shaped multi-partobjects connected via different types of joints and objects with differentmasses, and it outperforms image-based representations on physics prediction.Our approach enables the robot to predict and adapt the effect of a pushingaction as it observes the scene. It can also be used for tool manipulation withnever-seen tools. Further, we demonstrate 6D effect prediction in the lever-upaction in the context of robot-based hard-disk disassembly.

Object and Relation Centric Representations for Push Effect Prediction