Paper Info
Title
Gesture-based attention direction for a telepresence robot: Design and experimental study
Abstract
The application of robotics to telepresence can enhance user interaction experience by providing embodiment, engaging behaviors, automatic control, and human perception. This paper presents a new telepresence robot with gesture-based attention direction to orient the robot towards attention targets according to human deictic gestures. Gesture-based attention direction is realized by combining Localist Attractor Network (LAN) and Short-Term Memory (STM).We also propose audio-visual fusion based on context-dependent prioritization among the 3 types of audio-visual cues (gesture, speech source location, head location). Experiment results are very promising and show that i) the average gesture recognition rate is 92%, i) gesture-based attention direction rate is 90%, and that ii) only by considering the 3 types of audio-visual cues together can the robot perform on par with a human in directing attention to the correct person in a meeting scenario.
Year
DOI
Venue
2014
10.1109/IROS.2014.6943138
IROS
Keywords
Field
DocType
gesture-based attention direction,attention targets,lan,short-term memory,human-robot interaction,telepresence robot,localist attractor network,context-dependent prioritization,human deictic gestures,audio-visual fusion,stm,gesture recognition,telerobotics,audio-visual cues
Computer vision,Social robot,Computer science,Gesture,Gesture recognition,Artificial intelligence,Robot,Telerobotics,Robotics,Acoustic source localization,Facial motion capture
Conference
ISSN
Citations 
PageRank 
2153-0858
1
0.36
References 
Authors
8
5
Name
Order
Citations
PageRank
Keng-Peng Tee1106259.75
Rui Yan216916.91
Yuanwei Chua3506.76
Zhiyong Huang410611.79
Somchaya Liemhetcharat51059.75