Skip to main content

Human-Robot Negotiation

TÜBİTAK 3501 Project: Design, Development and Experimental

Evaluation of Autonomous Agents for Human-Robot Negotiation

 

nao

 

This work has been supported by a grant from The Scientific and Research Council of Turkey (TÜBİTAK) with the grant number 118E197. The contents of this article reflect the ideas and positions of the authors and do no necessarily reflect the ideas or positions of TÜBİTAK.  

 

Principal investigator:  Dr. Reyhan Aydoğan

Scholar (Graduate Students): Umut Çakan, Mehmet Onur Keskin, Anıl Doğru

STAR Scholar (Undergraduate Student): Atahan Çaldır

Counselor: Prof. Erhan Öztop

 

Contact: Dr. Reyhan Aydoğan, reyhan.aydogan@ozyegin.edu.tr

 

Project Summary

The ultimate goal of this project is to develop autonomous negotiating agents taking human factors into account for a social robot that needs to negotiate with people, provide integration of the software agent with the robot, and demonstrate the effectiveness of the developed agents through human-robot negotiation experiments. In order to achieve this aim, it is aimed at

  1. Designing a negotiation protocol that determines rules of the encounter between a human negotiator and robot in negotiation,
  2. Developing negotiating agents that are sensitive to the feelings of their opponent, and also developing negotiating agents that do not consider their opponent's emotion during the negotiation,
  3. Evaluating their performance in human-robot negotiation experiments.

In addition, it is planned to investigate the effect of physical embodiment in the human-agent negotiations and the use of gestures by the robot on negotiation outcome. 

As the Science and Technology High Council emphasized in the TÜBİTAK Vision 2023 Strategy document prepared to determine new science and technology policies, it is expected that robots will be more autonomous and work in cooperation with people with the emergence of Industry 4.0. In addition, social robots interacting with people have rapidly appeared in our daily life. In the near future, social robots that will work with people will need to negotiate with people to reach their own goals or the goals of the people they represent. Therefore, it is essential to make robots be able to negotiate with people autonomously. Not enough work has been done in this area yet. To the best of our knowledge, an autonomous negotiating agent, which is sensitive to the feelings of its opponent, has not been developed. In this respect, the proposed project is original. 

The proposed project conducted by Reyhan Aydoğan, assistant professor at Özyeğin University, has been realized in 37 months with the participation of two graduate students, Onur Keskin and Umut Çakan. In addition to them, one graduate student (Anıl Doğru) and one undergraduate student (Atahan Çaldır) took part in the project for a short time. The project consists of several tasks:

  1. Design and development of a human-robot negotiation system
  2. Design and development of an intelligent agent that is responsive to their opponent's feelings
  3. Evaluation and comparison of negotiating robot agents
  4. Study the effect of usage of gestures by the robot on the negotiation outcome
  5. Study the effect of physical embodiment on human negotiations