Personalizing Human-Robot Dialogue Interactions using Face and Name Recognition
Master thesis
Permanent lenke
https://hdl.handle.net/11250/3032541Utgivelsesdato
2022Metadata
Vis full innførselSamlinger
- Studentoppgaver (TN-IDE) [823]
Sammendrag
Task-oriented dialogue systems are computer systems that aim to provide an interactionindistinguishable from ordinary human conversation with the goal of completing user-defined tasks. They are achieving this by analyzing the intents of users and choosingrespective responses. Recent studies show that by personalizing the conversations withthis systems one can positevely affect their perception and long-term acceptance.Personalised social robots have been widely applied in different fields to provide assistance.In this thesis we are working on development of a scientific conference assistant. The goalof this assistant is to provide the conference participants with conference information andinform about the activities for their spare time during conference. Moreover, to increasethe engagement with the robot our team has worked on personalizing the human-robotinteraction by means of face and name recognition.To achieve this personalisation, first the name recognition ability of available physicalrobot was improved, next by the concent of the participants their pictures were takenand used for memorization of returning users. As acquiring the consent for personal datastorage is not an optimal solution, an alternative method for participants recognitionusing QR Codes on their badges was developed and compared to pre-trained model interms of speed. Lastly, the personal details of each participant, as unviversity, country oforigin, was acquired prior to conference or during the conversation and used in dialogues.The developed robot, called DAGFINN was displayed at two conferences happened thisyear in Stavanger, where the first time installment did not involve personalization feature.Hence, we conclude this thesis by discussing the influence of personalisation on dialogueswith the robot and participants satisfaction with developed social robot.