Modeling and Evaluating Narrative Gestures for Humanlike Robots

Huang, Chien-Ming; Mutlu, Bilge

doi:10.15607/rss.2013.ix.026

Cited by 100 publications

(77 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Every time its gesture state changed, the robot determined its new gaze target based on these distributions. The behaviors generated using this approach predicted significant improvements in learning and perceptions of the robot [10].…”

Section: Study Design Task and Proceduresmentioning

confidence: 99%

See 1 more Smart Citation

Learning-based modeling of multimodal behaviors for humanlike robots

Huang

Mutlu

2014

Proceedings of the 2014 ACM/IEEE International Conference on Human-Robot Interaction

Self Cite

View full text Add to dashboard Cite

In order to communicate with their users in a natural and effective manner, humanlike robots must seamlessly integrate behaviors across multiple modalities, including speech, gaze, and gestures. While researchers and designers have successfully drawn on studies of human interactions to build models of humanlike behavior and to achieve such integration in robot behavior, the development of such models involves a laborious process of inspecting data to identify patterns within each modality or across modalities of behavior and to represent these patterns as "rules" or heuristics that can be used to control the behaviors of a robot, but provides little support for validation, extensibility, and learning. In this paper, we explore how a learning-based approach to modeling multimodal behaviors might address these limitations. We demonstrate the use of a dynamic Bayesian network (DBN) for modeling how humans coordinate speech, gaze, and gesture behaviors in narration and for achieving such coordination with robots. The evaluation of this approach in a human-robot interaction study shows that this learning-based approach is comparable to conventional modeling approaches in enabling effective robot behaviors while reducing the effort involved in identifying behavioral patterns and providing a probabilistic representation of the dynamics of human behavior. We discuss the implications of this approach for designing natural, effective multimodal robot behaviors.

show abstract

Section: Study Design Task and Proceduresmentioning

confidence: 99%

“…In our prior work, we explored how robots might display coherent multimodal behaviors involving speech, gaze, and gestures [10]. We explicitly specified the semantic link between speech and gestures and empirically obtained parameters to quantify the temporal speech-gesture and gaze-gesture alignments.…”

Section: Multimodal Behaviors In Robotsmentioning

confidence: 99%

Learning-based modeling of multimodal behaviors for humanlike robots

Huang

Mutlu

2014

Proceedings of the 2014 ACM/IEEE International Conference on Human-Robot Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to gazing, a robot's gesture can influence its persuasiveness (see e.g., [38]), and also various variables that are related to persuasion (see e.g., [39]). For example, a robot's pointing gestures can improve a human observer's comprehension of spatial information and have been found to be useful for an observer to identify objects [40,41].…”

Section: Introductionmentioning

confidence: 99%

Combining Robotic Persuasive Strategies: The Persuasive Power of a Storytelling Robot that Uses Gazing and Gestures

Ham

Cuijpers

Cabibihan

2015

Int J of Soc Robotics

102

View full text Add to dashboard Cite

Earlier theorizing suggested that an (artificial) agent that combines persuasive strategies will be more persuasive. Therefore, the current research investigated whether a robot that uses two persuasive strategies is more persuasive than a robot that uses only one. Two crucial persuasive strategies that humans use in face-to-face persuasion are gazing and gestures, and therefore we studied the combined and individual contribution of these two persuasive strategies (gestures and gazing) on the persuasiveness of a storytelling robot. A robot told a classical persuasive story about the consequences of lying to forty-eight participants, and was programmed to use (persuasive) gestures (or not) and gazing (or not). Next, we asked participants to evaluate the character in the story thereby assessing the robot's persuasiveness. Results presented evidence a robot's persuasiveness is increased when gazing is used. When the robot used gestures, its persuasiveness only increased when it also used gazing. When the robot did not use gazing, using gestures diminished the robot's persuasiveness. We discuss the implications for theory and design of robots that are more persuasive.

show abstract

“…We then discovered significant themes of findings by combining an examination of these models and observations of the video data. This approach has been utilized in past HCI research to better understand how a range of behaviors shape task outcomes [2,24].…”

Section: Discussionmentioning

confidence: 99%

How social cues shape task coordination and communication

Sauppé

Mutlu

2014

Proceedings of the 17th ACM Conference on Computer Supported Cooperative Work &Amp; Social Computing

Self Cite

View full text Add to dashboard Cite

To design computer-supported collaborative work (CSCW) systems that effectively support remote collaboration, designers need a better understanding of how people collaborate face-to-face and the mechanisms that they use to coordinate their actions. While research in CSCW has studied how specific social cues might facilitate collaboration in specific tasks, such as the role of gestures in video instruction, less is known about how a range of communicative cues might facilitate activities across many collaborative settings. In this paper, we model the predictive relationships between facial, gestural, and vocal cues and collaborative outcomes in three different tasks, drawing conclusions on how each cue might contribute to these outcomes in a given task and how such relationships generalize across tasks. The resulting models provide a quantitative understanding of the relative importance of each type of social cue in predicting collaborative outcomes, as well as a more thorough understanding of how the role of each social cue changes across tasks. Additionally, our results provide confirmation and illumination of prior findings in face-to-face and computer-mediated communication research.

show abstract

Modeling and Evaluating Narrative Gestures for Humanlike Robots

Cited by 100 publications

References 36 publications

Learning-based modeling of multimodal behaviors for humanlike robots

Learning-based modeling of multimodal behaviors for humanlike robots

Combining Robotic Persuasive Strategies: The Persuasive Power of a Storytelling Robot that Uses Gazing and Gestures

How social cues shape task coordination and communication

Contact Info

Product

Resources

About