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

General contact-rich manipulation problems are long-standing challenges inrobotics due to the difficulty of understanding complicated contact physics.Deep reinforcement learning (RL) has shown great potential in solving robotmanipulation tasks. However, existing RL policies have limited adaptability toenvironments with diverse dynamics properties, which is pivotal in solving manycontact-rich manipulation tasks. In this work, we propose Contact-aware OnlineCOntext Inference (COCOI), a deep RL method that encodes a context embedding ofdynamics properties online using contact-rich interactions. We study thismethod based on a novel and challenging non-planar pushing task, where therobot uses a monocular camera image and wrist force torque sensor reading topush an object to a goal location while keeping it upright. We run extensiveexperiments to demonstrate the capability of COCOI in a wide range of settingsand dynamics properties in simulation, and also in a sim-to-real transferscenario on a real robot (Video: https://youtu.be/nrmJYksh1Kc)

COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing