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

Dexterous manipulation with anthropomorphic robot hands remains a challengingproblem in robotics because of the high-dimensional state and action spaces andcomplex contacts. Nevertheless, skillful closed-loop manipulation is requiredto enable humanoid robots to operate in unstructured real-world environments.Reinforcement learning (RL) has traditionally imposed enormous interaction datarequirements for optimizing such complex control problems. We introduce a newframework that leverages recent advances in GPU-based simulation along with thestrength of imitation learning in guiding policy search towards promisingbehaviors to make RL training feasible in these domains. To this end, wepresent an immersive virtual reality teleoperation interface designed forinteractive human-like manipulation on contact rich tasks and a suite ofmanipulation environments inspired by tasks of daily living. Finally, wedemonstrate the complementary strengths of massively parallel RL and imitationlearning, yielding robust and natural behaviors. Videos of trained policies,our source code, and the collected demonstration datasets are available athttps://maltemosbach.github.io/interactive_ human_like_manipulation/.

Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations