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

Bimanual activities like coffee stirring, which require coordination of dualarms, are common in daily life and intractable to learn by robots. Adoptingreinforcement learning to learn these tasks is a promising topic since itenables the robot to explore how dual arms coordinate together to accomplishthe same task. However, this field has two main challenges: coordinationmechanism and long-horizon task decomposition. Therefore, we propose theMixline method to learn sub-tasks separately via the online algorithm and thencompose them together based on the generated data through the offlinealgorithm. We constructed a learning environment based on the GPU-acceleratedIsaac Gym. In our work, the bimanual robot successfully learned to grasp, holdand lift the spoon and cup, insert them together and stir the coffee. Theproposed method has the potential to be extended to other long-horizon bimanualtasks.

Mixline: A Hybrid Reinforcement Learning Framework for Long-horizon Bimanual Coffee Stirring Task