Generative deep learning for contingent behaviour production on social robots

01 January 2018 → 31 December 2021
Regional and community funding: Special Research Fund
Research disciplines
  • Natural sciences
    • Artificial intelligence
  • Social sciences
    • Cognitive science and intelligent systems
    • Social psychology
  • Engineering and technology
    • Control systems, robotics and automation
    • Design theories and methods
    • Mechatronics and robotics
    • Computer theory
Social robots Deep Learning machine learning Human-Robot Interaction
Project description

Social robots are robots which interact with people in a natural manner. Autonomously generating contingent verbal and nonverbal behaviour is currently impossible. We use generative Deep Learning to observe video recordings of people and learn which behaviours are appropriate for the robot,
with the aim of having the robot produce matching verbal and non-verbal behaviour.