DECENTRALISED DECISION MAKING FOR MULTI-AGENT SYSTEM

The seminar talk will introduce decentralised decision making for multiple agent systems.

At the beginning of the talk, potential benefits of operating a group of unmanned agent systems will be discussed and the main challenges for developing such a system will be addressed.

Then, the talk will focus on identifying key enabling technologies to achieve those potential benefits, followed by introduction on our research developments in achieving the representative key technologies.

The key technology under discussion will be decentralised task allocation based on sequential decision making.

The core idea tested in developing such algorithms is exploitation of emergence of AI technologies, but in combination of domain knowledge already available.

This core idea could be defined as structured learning and the focus of our initial development is identification of the potential benefits and limitations of the structured learning within the decision making of the multiple agent system.

The talk will be concluded with a discussion on the remaining research gaps, lessons learned, future research directions and potential collaborations.

Speaker:

Professor Hyo-Sang Shin is Professor at Korea Advanced Institute of Science and Technology (KAIST) and Adjunct Professor of Guidance, Control and Navigation Systems at Cranfield University.

He gained an MSc on formation flight of unmanned aerial vehicles in Aerospace Engineering from KAIST and a PhD on cooperative missile guidance from Cranfield University in 2006 and 2011, respectively. He has published 3 books, 11 book chapters, and over 250 journal and conference papers.

He has been also invited for many lectures, invited talks and keynotes both in universities and industries on various topics such as UAM/AAM, sensor, data and information fusion, cooperative control, unmanned traffic management (UTM), and future flight.

He has been also involved in many research programs and has been the coordinator of international projects.

Professor Shin is a member of various technical committees (IFAC Technical Committee on Aerospace Control, IEEE Technical Committee on Aerial Robotics and Unmanned Aerial Systems), and program and editorial boards.

Professor Shin is Head of Autonomous and Intelligent Systems Groups and leading relevant research areas in KAIST. His current research interests include UTM, air mobility, data-centric guidance and control, information-driven sensing and fusion, and improvement of multiple vehicle cooperation.

16.12.2024