Role determination in human-human interaction

Physical human-robot interaction can be significantly improved when being aware about the role each partner takes in a joint manipulation task. This holds especially in computer assisted teleoperation, where depending on the identified role of the human, different roles can be assigned to the assistance function. This work proposes a method for the determination of two non exclusive roles, an executor and conductor. Hereby the executor refers to the person who mainly contributes to the execution of the task and the conductor to the person who takes the decision and controls the motion. The method is based on the analysis of haptic data, whereby the signs of force and motion signals are evaluated. Two different cases are considered in the analysis: direct interaction of the two partners as well as interaction via an object. The effort each operator makes to either carry out the task or initiate a change in the task is also estimated. The proposed method can be used to actively influence the role assignment, to extract features or for task segmentation.

[1]  Gerald Friedland,et al.  Estimating the dominant person in multi-party conversations using speaker diarization strategies , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Kyle B. Reed,et al.  Haptic cooperation between people, and between people and machines , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Eva-Lotta Sallnäs,et al.  The effect of modality on social presence, presence and performance in collaborative virtual environments , 2004 .

[4]  Kenneth C. Smith The Prospects for Multivalued Logic: A Technology and Applications View , 1981, IEEE Transactions on Computers.

[5]  Waqar Mahmood,et al.  A Matrix Based Approach For Modeling Robotic Swarm Behavior , 2006, IC-AI.

[6]  Sumit Basu,et al.  Learning Human Interactions w ith the Influence Model , 2001, NIPS 2001.

[7]  L. Benedicenti,et al.  Mathematical analysis of agent swarm behavior in an agent-based electronic health record system , 2005, Canadian Conference on Electrical and Computer Engineering, 2005..

[8]  Kazuhiro Kosuge,et al.  Dynamic control for robot-human collaboration , 1993, Proceedings of 1993 2nd IEEE International Workshop on Robot and Human Communication.

[9]  Oussama Khatib,et al.  Mobile manipulation: The robotic assistant , 1999, Robotics Auton. Syst..