TY - JOUR
T1 - Reactive virtual agent learning for NUI-based HRI applications
AU - Jin, Daxing
AU - Cho, Seoungjae
AU - Sung, Yunsick
AU - Cho, Kyungeun
AU - Um, Kyhyun
N1 - Publisher Copyright:
© 2014, Springer Science+Business Media New York.
PY - 2016/12/1
Y1 - 2016/12/1
N2 - The natural user interface (NUI) has been investigated in a variety of fields in application software. This paper proposes an approach to generate virtual agents that can support users for NUI-based applications through human–robot interaction (HRI) learning in a virtual environment. Conventional human–robot interaction (HRI) learning is carried out by repeating processes that are time-consuming, complicated and dangerous because of certain features of robots. Therefore, a method is needed to train virtual agents that interact with virtual humans imitating human movements in a virtual environment. Then the result of this virtual agent can be applied to NUI-based interactive applications after the interaction learning is completed. The proposed method was applied to a model of a typical house in virtual environment with virtual human performing daily-life activities such as washing, eating, and watching TV. The results show that the virtual agent can predict a human’s intent, identify actions that are helpful to the human, and can provide services 16 % faster than a virtual agent trained using traditional Q-learning.
AB - The natural user interface (NUI) has been investigated in a variety of fields in application software. This paper proposes an approach to generate virtual agents that can support users for NUI-based applications through human–robot interaction (HRI) learning in a virtual environment. Conventional human–robot interaction (HRI) learning is carried out by repeating processes that are time-consuming, complicated and dangerous because of certain features of robots. Therefore, a method is needed to train virtual agents that interact with virtual humans imitating human movements in a virtual environment. Then the result of this virtual agent can be applied to NUI-based interactive applications after the interaction learning is completed. The proposed method was applied to a model of a typical house in virtual environment with virtual human performing daily-life activities such as washing, eating, and watching TV. The results show that the virtual agent can predict a human’s intent, identify actions that are helpful to the human, and can provide services 16 % faster than a virtual agent trained using traditional Q-learning.
KW - Human–robot interaction
KW - Natural user experience
KW - Natural user interface
KW - Virtual agent learning
UR - http://www.scopus.com/inward/record.url?scp=84901729002&partnerID=8YFLogxK
U2 - 10.1007/s11042-014-2048-5
DO - 10.1007/s11042-014-2048-5
M3 - Article
AN - SCOPUS:84901729002
SN - 1380-7501
VL - 75
SP - 15157
EP - 15170
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
IS - 23
ER -