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

Contact-rich manipulation tasks are commonly found in modern manufacturingsettings. However, manually designing a robot controller is considered hard fortraditional control methods as the controller requires an effective combinationof modalities and vastly different characteristics. In this paper, we firstlyconsider incorporating operational space visual and haptic information intoreinforcement learning(RL) methods to solve the target uncertainty problem inunstructured environments. Moreover, we propose a novel idea of introducing aproactive action to solve the partially observable Markov decision processproblem. Together with these two ideas, our method can either adapt toreasonable variations in unstructured environments and improve the sampleefficiency of policy learning. We evaluated our method on a task that involvedinserting a random-access memory using a torque-controlled robot, and we testedthe success rates of the different baselines used in the traditional methods.We proved that our method is robust and can tolerate environmental variationsvery well.

Proactive Action Visual Residual Reinforcement Learning for Contact-Rich Tasks Using a Torque-Controlled Robot