Decoding Motor Skills of AI and Human Policies: A Study on Humanoid and Human Balance Control

Kai Yuan, Christopher McGreavy, Chuanyu Yang, Wouter J. Wolfslag, Zhibin Li

Research output: Contribution to journalArticlepeer-review

Abstract

From the advancement in computers, computer-aided design for mechanical and electronic engineering, architecture and many other engineering fields emerged. Foreseeing a similar development curve and technology wave, we forecast a new emerging discipline in the near future that uses learning-aided approaches for catalysing control development, alongside other similar applications such as in medicine discovery. In this study, we propose a new paradigm of using a machine learning approach to facilitate a quicker, more efficient and effective control development, as a different approach of leveraging the power of machine learning in addition to other options that intent to use learning directly in real-world applications
Original languageEnglish
Pages (from-to)87 - 101
Number of pages15
JournalIEEE Robotics and Automation Magazine
Volume27
Issue number2
Early online date13 Apr 2020
DOIs
Publication statusPublished - 1 Jun 2020

Keywords

  • Artificial intelligence
  • Humanoid robots
  • Hip
  • Torso
  • Training
  • Control systems

Fingerprint Dive into the research topics of 'Decoding Motor Skills of AI and Human Policies: A Study on Humanoid and Human Balance Control'. Together they form a unique fingerprint.

Cite this