Skip to main content
To KTH's start page

COIN – Co-adaptive human-robot interactive systems

The main goal is to develop a systematic, bi-directional short- and long-term adaptive framework that yields safe, effective, efficient, and socially acceptable robot behaviors and human-robot interactions.

The research topics involved in the development of the targeted methodology include:

  1. long-term adaptive reinforcement learning approaches for affect-based co-adaptation in social HRI; 
  2. methods for adapting the robot’s linguistic behaviour to the user and for entraining the users’ linguistic behaviour 
  3. methods for correct-by-design task planning, re-planning and robot control under uncertainty and model adaptation based on formal verification; and
  4. techniques for learning of predictive state representation

This is a collaboration between:

  • Department of Speech Music and Hearing, KTH
  • Computer Vision and Active Perception Lab, KTH
  • Automatic Control, School of Electrical Engineering, KTH
  • Department of Information Technology, Uppsala University

Total funding: 33 MSEK

Staff:

Gabriel Skantze
Gabriel Skantze professor
Dimos Dimarogonas
Dimos Dimarogonas professor, head of division
Danica Kragic Jensfelt
Danica Kragic Jensfelt professor, professor, head of division

Ginevra Castellano 

Funding: SSF (Stiftelsen för Strategisk Forskning)

Duration: 2016-05-01 - 2020-12-31