TY - GEN
T1 - Role determination in human-human interaction
AU - Stefanov, Nikolay
AU - Peer, Angelika
AU - Buss, Martin
PY - 2009
Y1 - 2009
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=67649660545&partnerID=8YFLogxK
U2 - 10.1109/WHC.2009.4810846
DO - 10.1109/WHC.2009.4810846
M3 - Conference contribution
AN - SCOPUS:67649660545
SN - 9781424438587
T3 - Proceedings - 3rd Joint EuroHaptics Conference and Symposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems, World Haptics 2009
SP - 51
EP - 56
BT - Proceedings - 3rd Joint EuroHaptics Conference and Symposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems, World Haptics 2009
T2 - 3rd Joint EuroHaptics Conference and Symposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems, World Haptics 2009
Y2 - 18 March 2009 through 20 March 2009
ER -