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

To adopt the soft hand exoskeleton to support activities of daily livings, itis necessary to control finger joints precisely with the exoskeleton. Theproblem of controlling joints to follow a given trajectory is called thetracking control problem. In this study, we focus on the tracking controlproblem of a human finger attached with thin McKibben muscles. To achieveprecise control with thin McKibben muscles, there are two problems: one is thecomplex characteristics of the muscles, for example, non-linearity, hysteresis,uncertainties in the real world, and the other is the difficulty in accessing aprecise model of the muscles and human fingers. To solve these problems, weadopted DreamerV2, which is a model-based reinforcement learning method, butthe target trajectory cannot be generated by the learned model. Therefore, wepropose Tracker, which is an extension of DreamerV2 for the tracking controlproblem. In the experiment, we showed that Tracker can achieve an approximately81% smaller error than PID for the control of a two-link manipulator thatimitates a part of human index finger from the metacarpal bone to the proximalbone. Tracker achieved the control of the third joint of the human index fingerwith a small error by being trained for approximately 60 minutes. In addition,it took approximately 15 minutes, which is less than the time required for thefirst training, to achieve almost the same accuracy by fine-tuning the policypre-trained by the user's finger after taking off and attaching thin McKibbenmuscles again as the accuracy before taking off.

Tracker: Model-based Reinforcement Learning for Tracking Control of Human Finger Attached with Thin McKibben Muscles