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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

One of the typical purposes of using lower-limb exoskeleton robots is toprovide assistance to the wearer by supporting their weight and augmentingtheir physical capabilities according to a given task and human motionintentions. The generalizability of robots across different wearers in multipletasks is important to ensure that the robot can provide correct and effectiveassistance in actual implementation. However, most lower-limb exoskeletonrobots exhibit only limited generalizability. Therefore, this paper proposes ahuman-in-the-loop learning and adaptation framework for exoskeleton robots toimprove their performance in various tasks and for different wearers. To suitdifferent wearers, an individualized walking trajectory is generated onlineusing dynamic movement primitives and Bayes optimization. To accommodatevarious tasks, a task translator is constructed using a neural network togeneralize a trajectory to more complex scenarios. These generalizationtechniques are integrated into a unified variable impedance model, whichregulates the exoskeleton to provide assistance while ensuring safety. Inaddition, an anomaly detection network is developed to quantitatively evaluatethe wearer's comfort, which is considered in the trajectory learning procedureand contributes to the relaxation of conflicts in impedance control. Theproposed framework is easy to implement, because it requires proprioceptivesensors only to perform and deploy data-efficient learning schemes. This makesthe exoskeleton practical for deployment in complex scenarios, accommodatingdifferent walking patterns, habits, tasks, and conflicts. Experiments andcomparative studies on a lower-limb exoskeleton robot are performed todemonstrate the effectiveness of the proposed framework.

Learning to Assist Different Wearers in Multitasks: Efficient and Individualized Human-In-the-Loop Adaption Framework for Exoskeleton Robots