μDialBot: MUlti-party perceptually-active situated DIALog for human-roBOT interaction

ANR 2020 – CES 33 – PRCE

a.k.a muDB

Motivations

Companion robots able to assist people in their everyday life and to communicate with them:

social assistive robots

How to improve acceptance?

Several technological barriers to overcome:

  • better ability to move, see and hear in order to naturally communicate with people in various configurations (face-to-face, multi-party, close, distant etc)
  • pro-active use of perceptions
  • audio-visual strategies to handle interactions

Ambitions

New level in the exploitation of the rich information available with audio and visual data flowing from humans when interacting with robots:

  • fusing highly informative verbal and non-verbal perceptive features to enhance the robot’s decision-making ability such that it can
  • switch between multi-party/group interactions and face-to-face dialogues where required, and
  • take speech turns more naturally

Tested and validated with several use cases in a day-care hospital unit. Large-scale data collection,  complement in-situ tests, to fuel further researches.

The project is mainly funded by ANR and has also been labeled by the Pole SCS (Solution Communicantes Spécialisées) : https://www.pole-scs.org/projets/mudialbot/

Get more information about muDialBot, and its consortium.