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

Learning from demonstration (LfD) provides a convenient means to equip robotswith dexterous skills when demonstration can be obtained in robot intrinsiccoordinates. However, the problem of compounding errors in long and complexskills reduces its wide deployment. Since most such complex skills are composedof smaller movements that are combined, considering the target skill as asequence of compact motor primitives seems reasonable. Here the problem thatneeds to be tackled is to ensure that a motor primitive ends in a state thatallows the successful execution of the subsequent primitive. In this study, wefocus on this problem by proposing to learn an explicit correction policy whenthe expected transition state between primitives is not achieved. Thecorrection policy is itself learned via behavior cloning by the use of astate-of-the-art movement primitive learning architecture, Conditional NeuralMotor Primitives (CNMPs). The learned correction policy is then able to producediverse movement trajectories in a context dependent way. The advantage of theproposed system over learning the complete task as a single action is shownwith a table-top setup in simulation, where an object has to be pushed througha corridor in two steps. Then, the applicability of the proposed method tobi-manual knotting in the real world is shown by equipping an upper-bodyhumanoid robot with the skill of making knots over a bar in 3D space. Theexperiments show that the robot can perform successful knotting even when thefaced correction cases are not part of the human demonstration set.

Bimanual rope manipulation skill synthesis through context dependent correction policy learning from human demonstration