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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper, a new methodology is proposed to design a learning control for robots. Since, the advanced robots need to work in an unstructured and dynamic environment such as human environment (e.g. assistive robots). They need to learn how to interact with people and manipulate the different objects and payloads. Additionally, due to the nonlinearity, the uncertainty of the parameters, external disturbances, and time-varying effects such as tear and wear, the accurate analytical models are too complex to derive for control applications. In this paper, a learning control is developed by effectively combining the adaptive continuous sliding mode control (ACSMC) presented in [1] with multi-model neural network techniques (MMNN). The controller consists of an online adaptation mechanism and an online learning mechanism. It is shown that learning capability allows to realize the controller with less or no prior information of robot inverse dynamic model. The robustness, performance and learning capability of the control system is demonstrated and evaluated trough simulation study and experimentally, using a two-degrees of freedom robot.

New Methodology to Design Learning Control for Robots Using Adaptive Sliding Mode Control and Multi-Model Neural Networks