T2: Towards a Unified Framework for Intelligent Robotics
 

Honghai Liu
Institute of Industrial Research, University of Portsmouth
Naoyuki Kubota
Tokyo Metropolitan University, Japan

Abstract:
This tutorial consists of state of the art in intelligent robotics with a focus on fuzzy systems and a fuzzy qualitative framework proposed by the speaker's group. It overviews fuzzy approaches to intelligent robotics including navigation, human robot interaction and control. The second part of the talk is focused on a theoretical framework based on approximation reasoning, it includes fuzzy qualitative robotics and its applications. The framework is intended to provide a foundation towards a unified representation by gluing hybrid robotic representations. The framework has been adapted into applied applications with substantial results such as human motion analysis, robot fault diagnosis and multifingered robot manipulation.

 

Vitas: http://userweb.port.ac.uk/~liuh/

Honghai Liu is a Reader in Intelligent Systems in the Institute of Industrial Research at the University of Portsmouth. He previously held research appointments at the Departments of Computing Science and Engineering in the Universities of London and Aberdeen and project leader appointments in industrial control and system integration industry. He has published over 100 refereed international journal and conference papers since 2001 including three Best Paper Awards.


In general he is interested in machine intelligence, robot learning, sensor fusion, visual surveillance, pattern recognition and its practical applications with an emphasis on approaches which could make contribution to the intelligent connection of perception to action in a broad context.

His detailed current project topics are:

  • A unified representation with an aim on closing the gap between numeric data and its behavior understanding.
  • Learning the human hand capabilities for controlling multifingered robot hands.
  • Complex human motion analysis based on collaborative visual/capturing cues.
  • Novelty detection and understanding for robots, marine engines and aircrafts.
  • Modelling and control issues in musculoskeletal rehabilitation.
  • Active suspension design and control for electric vehicles.
  • Real-world applications.
 
 

Naoyuki Kubota graduated from Osaka Kyoiku University in 1992, received the M.E. degree from Hokkaido University in 1994, and received the D.E. degree from Nagoya University, Japan in 1997. He joined Osaka Institute of Technology, in 1997. He joined the Department of Human and Artificial Intelligence Systems, Fukui University as an associate professor in 2000. He joined the Department of Mechanical Engineering, Tokyo Metropolitan University in 2004, and has been currently an associate professor of the Department of System Design, Tokyo Metropolitan University since 2005.


He was a Royal Society Visiting Professor at University of Portsmouth in 2007 and 2009, and is an Invited Visiting Professor in Electrical Engineering and Computer Science at Seoul National University in 2009. His current interests are in the fields of computational intelligence, perception-based robotics, robot partners, and informationally structured space. He received the Best Paper Award of IECON'96, the Best Paper Award of CIRA'97, and so on. He is an associate editor of the IEEE Transactions on Fuzzy Systems, and an Editorial Board Member of Journal of Advanced Computational Intelligence and Intelligent Informatics, an Associate Editor of Journal of Control, Measurement and System Integration, and others. He is also the IEEE CIS Intelligent Systems Applications Technical Committee, Robotics Task Force Chair.