ESR15 : Endowing robots with high-level conversational skills

PhD fellowship

Objectives:

For social robots and conversational agents to take part in real-life interactions with users, these robots need to possess certain social and conversational skills that will enable them to interact naturally with a human partner, using language, gesture, and other cognitive and social skills that reflect aspects of the user’s behaviour. These include models of engagement, joint attention, personality style and collaborative state. ESR15 will contribute to developing computational models of high-level conversational skills in a multiparty human-robot interaction set-up (two humans, one robot). Using an interaction set-up based on language-learning problem solving with one robot, a touch table, and two humans, ESR15 will exploit a number of social signals derived from sensors of human behavior (cameras, microphones, gaze tracker, etc.) to develop data-driven models of conversational skills that will deepen our understanding of human-robot interactions.


Expected results:

A scientific platform for exploring models of conversational skill and for the assessment of multiparty human-robot interaction behavior. This platform will be used to perform user tests and build universal computational models of engagement, joint attention, involvement and other signals that allow the robot to adapt its behavior to maximize the efficiency of the interaction.

Based in Stockholm, Sweden

Full-time three-year contract, starting September 2020

PhD enrolment at: Max Planck Institute for Psycholinguistics / Radboud University, Nijmegen, the Netherlands

Main supervisors’ institutions: Furhat Robotics, Stockholm, Sweden, and Max Planck Institute for Psycholinguistics, Nijmegen, the Netherlands

Main supervisors: Prof Gabriel Skantze and Prof Peter Hagoort

Secondments:

  • HU-ZAS, Berlin: training in recording and analysis of head motion in multi-party conversations (5 months);
  • MPG, Nijmegen: experimental training on testing the efficiency of the interaction set-up (5,5 months).

Co-supervisor’s institution:

  • HU-ZAS, Berlin, Germany


Scroll to top