Research group

Human-AI Interaction Group

AlI systems are increasingly becoming an everyday presence for the average person, but how the systems do and should interact with humans, and how they can more optimally support human users in their tasks is often an open question.

The group’s overall research goal is to create methods and algorithms for more effective human-AI interaction. To achieve this goal, we employ human behavioural data , which becomes available due to the increased network connectivity of many everyday devices. This data is used to train and improve AI systems, and to generate predictive models of human behaviour that enables an AI to better adapt to their users. In addition, we study the use of reinforcement learning to train intelligent assistants that support the work of human users.In addition to tackling fundamental research questions about human-AI interaction, we are targeting a wide range of application areas in our work, including:
  • Software Development, e.g. intelligent programmer assistance.
  • MOOCs, e.g. learner performance prediction and personalized exercise generation.
  • Robotics, e.g. socially aware robots.

Publications

  • T. Bryskin, A. Shpilman, D. Kudenko
    Automated refactoring of object-oriented code using clustering ensembles
    AAAI Workshop on Natural Language Processing for Software Engineering,
  • A. Malysheva, A. Shpilman, and D. Kudenko
    Learning to Run with Reward Shaping from Video Data
    Workshop on Adaptive and Learning Agents (ALA) at ICML-AAMAS,
  • M. Li, T. Brys, D. Kudenko
    Introspective Reinforcement Learning and Learning from Demonstration
    17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS),
  • D. Zendle, D. Kudenko, P. Cairns
    Entertainment Computing,