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

Everyday contact-rich tasks, such as peeling, cleaning, and writing, demandmultimodal perception for effective and precise task execution. However, thesepresent a novel challenge to robots as they lack the ability to combine thesemultimodal stimuli for performing contact-rich tasks. Learning-based methodshave attempted to model multi-modal contact-rich tasks, but they often requireextensive training examples and task-specific reward functions which limitstheir practicality and scope. Hence, we propose a generalizable model-freelearning-from-demonstration framework for robots to learn contact-rich skillswithout explicit reward engineering. We present a novel multi-modal sensor datarepresentation which improves the learning performance for contact-rich skills.We performed training and experiments using the real-life Sawyer robot forthree everyday contact-rich skills -- cleaning, writing, and peeling. Notably,the framework achieves a success rate of 100\% for the peeling and writingskill, and 80\% for the cleaning skill. Hence, this skill learning frameworkcan be extended for learning other physical manipulation skills.

Learning Multimodal Contact-Rich Skills from Demonstrations Without Reward Engineering