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

Acquiring human skills offers an efficient approach to tackle complex taskplanning challenges. When performing a learned skill model for a continuouscontact task, such as robot polishing in an uncertain environment, the robotneeds to be able to adaptively modify the skill model to suit the environmentand perform the desired task. The environmental perturbation of the polishingtask is mainly reflected in the variation of contact force. Therefore,adjusting the task skill model by providing feedback on the contact forcedeviation is an effective way to meet the task requirements. In this study, aphase-modulated diagonal recurrent neural network (PMDRNN) is proposed forforce feedback model learning in the robotic polishing task. The contactbetween the tool and the workpiece in the polishing task can be considered adynamic system. In comparison to the existing feedforward neural networkphase-modulated neural network (PMNN), PMDRNN combines the diagonal recurrentnetwork structure with the phase-modulated neural network layer to improve thelearning performance of the feedback model for dynamic systems. Specifically,data from real-world robot polishing experiments are used to learn the feedbackmodel. PMDRNN demonstrates a significant reduction in the training error of thefeedback model when compared to PMNN. Building upon this, the combination ofPMDRNN and dynamic movement primitives (DMPs) can be used for real-timeadjustment of skills for polishing tasks and effectively improve the robustnessof the task skill model. Finally, real-world robotic polishing experiments areconducted to demonstrate the effectiveness of the approach.

Adaptive Tuning of Robotic Polishing Skills based on Force Feedback Model