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

Soft object manipulation tasks in domestic scenes pose a significantchallenge for existing robotic skill learning techniques due to their complexdynamics and variable shape characteristics. Since learning new manipulationskills from human demonstration is an effective way for robot applications,developing prior knowledge of the representation and dynamics of soft objectsis necessary. In this regard, we propose a pre-trained soft object manipulationskill learning model, namely SoftGPT, that is trained using large amounts ofexploration data, consisting of a three-dimensional heterogeneous graphrepresentation and a GPT-based dynamics model. For each downstream task, agoal-oriented policy agent is trained to predict the subsequent actions, andSoftGPT generates the consequences of these actions. Integrating these twoapproaches establishes a thinking process in the robot's mind that providesrollout for facilitating policy learning. Our results demonstrate thatleveraging prior knowledge through this thinking process can efficiently learnvarious soft object manipulation skills, with the potential for direct learningfrom human demonstrations.

SoftGPT: Learn Goal-oriented Soft Object Manipulation Skills by Generative Pre-trained Heterogeneous Graph Transformer