Body Movements for Affective Expression: A Survey of Automatic Recognition and Generation

Karg, Michael; Samadani, Ali-Akbar; Gorbet, Rob; Kühnlenz, Kolja; Hoey, Jesse; Kulić, Dana

doi:10.1109/t-affc.2013.29

Cited by 186 publications

(127 citation statements)

References 150 publications

Supporting

Mentioning

124

Contrasting

Unclassified

Order By: Relevance

“…Some other approaches add an offset motion (in terms of position and its derivatives) on a known gesture: for instance, in [30] the final position and the velocity of a base gesture are modified depending on the emotional information to be conveyed by a humanoid robot, and, similarly, in [34] the intermediate points and the velocity of a given trajectory are transformed to incorporate affective nuances. Interestingly, the field is capturing increasing attention and maturing, and a survey can already be found [24].…”

Section: Related Workmentioning

confidence: 99%

Exploiting the Robot Kinematic Redundancy for Emotion Conveyance to Humans as a Lower Priority Task

Claret

Venture

Basañez

2017

Int J of Soc Robotics

View full text Add to dashboard Cite

Current approaches do not allow robots to execute a task and simultaneously convey emotions to users using their body motions. This paper explores the capabilities of the Jacobian null space of a humanoid robot to convey emotions. A task priority formulation has been implemented in a Pepper robot which allows the specification of a primary task (waving gesture, transportation of an object, etc.) and exploits the kinematic redundancy of the robot to convey emotions to humans as a lower priority task. The emotions, defined by Mehrabian as points in the Pleasure -Arousal -Dominance space, generate intermediate motion features (jerkiness, activity and gaze) that carry the emotional information. A map from this features to the joints of the robot is presented. A user study has been conducted in which emotional motions have been shown to 30 participants. The results show that happiness and sadness are very well conveyed to the user, calm is moderately well conveyed, and fear is not well conveyed. An analysis on the dependencies between the motion features and the emotions perceived by This work has been partially supported by the Spanish MINECO projects DPI2011-22471, DPI2013-40882-P and DPI2014-57757-R, the Spanish predoctoral grant BES-2012-054899, and the Japanese challenging exploratory research grant 15K12124. The authors would like to thank the members of the GVLab for their invaluable support with the translations and attending the local participants during the user study.Josep-Arnau Claret Institute of Industrial and Control Engineering, Technical University of Catalonia (UPC), BarcelonaTECH, Barcelona, Catalonia, Spain E-mail: josep.arnau.claret@upc.edu Gentiane Venture Tokyo University of Agriculture and Technology, Tokyo, Japan E-mail: venture@cc.tuat.ac.jp Luis Basañez Institute of Industrial and Control Engineering, Technical University of Catalonia (UPC), BarcelonaTECH, Barcelona, Catalonia, Spain E-mail: luis.basanez@upc.edu the participants shows that activity correlates positively with arousal, jerkiness is not perceived by the user, and gaze conveys dominance when activity is low. The results indicate a strong influence of the most energetic motions of the emotional task and point out new directions for further research. Overall, the results show that the null space approach can be regarded as a promising mean to convey emotions as a lower priority task.

show abstract

Section: Related Workmentioning

confidence: 99%

Exploiting the Robot Kinematic Redundancy for Emotion Conveyance to Humans as a Lower Priority Task

Claret

Venture

Basañez

2017

Int J of Soc Robotics

View full text Add to dashboard Cite

show abstract

“…LMA has been largely used in computer animation, [17][18][19] motion segmentation, 20 gesture recognition and affect analysis. 21,22 Eshkol-Wachman notation system. Although initially developed for dance, it was also intended to notate and analyze any possible movement in space in a rather mathematical way.…”

Section: Laban Movement Analysis (Lma)mentioning

confidence: 99%

Challenges for the Animation of Expressive Virtual Characters: The Standpoint of Sign Language and Theatrical Gestures

Gibet

Carreno‐Medrano

Marteau

2015

Dance Notations and Robot Motion

View full text Add to dashboard Cite

Designing and controlling virtual characters endowed with expressive gestures requires the modeling of multiple processes, involving high-level abstract representations to lowlevel sensorimotor models. An expressive gesture is here defined as a meaningful bodily motion which intrinsically associates sense, style, and expressiveness. The main challenges rely both on the capability to produce a large spectrum of parametrized actions executed with some variability in various situations, and on the biological plausibility of the motion of the virtual characters. The goals of the paper are twofold. First we review the different formalisms used to describe expressive gestures, from notations to computational languages. Secondly we identify and discuss remaining challenges in the generation of expressive virtual characters. The different models and formalisms are illustrated more particularly for theatrical and sign language gestures.

show abstract

“…However, a few studies focus on dimensional models (such as valence and arousal) [1]. Dimensional approach in automated emotion recognition faces challenges such as unbalanced data, overlapping categories and differences in the inter-observer agreement on the dimensions [1,2]. On the other hand, categorical labels describe emotional states based on their linguistic use in our daily life.…”

Section: Introductionmentioning

confidence: 99%

“…The analysis of body motion data for emotion recognition has become more common only recently. Movement data gives recognition rates comparable to facial expressions or speech in multimodal scenarios, and improves overall accuracy in multimodal systems when combined with other modalities [2]. Emotions collected from real conversations are difficult to classify by means of one channel.…”

Section: Introductionmentioning

confidence: 99%

RAMAS: Russian Multimodal Corpus of Dyadic Interaction for studying emotion recognition

Perepelkina¹,

Kazimirova²,

Konstantinova³

2018

Preprint

View full text Add to dashboard Cite

Abstract-Emotion expression encompasses various types of information, including face and eye movement, voice and body motion. Most of the studies in automated affective recognition use faces as stimuli, less often they include speech and even more rarely gestures. Emotions collected from real conversations are difficult to classify using one channel. That is why multimodal techniques have recently become more popular in automatic emotion recognition. Multimodal databases that include audio, video, 3D motion capture and physiology data are quite rare. We collected The Russian Acted Multimodal Affective Set (RA-MAS) the first multimodal corpus in Russian language. Our database contains approximately 7 hours of high-quality closeup video recordings of subjects faces, speech, motion-capture data and such physiological signals as electro-dermal activity and photoplethysmogram. The subjects were 10 actors who played out interactive dyadic scenarios. Each scenario involved one of the basic emotions: Anger, Sadness, Disgust, Happiness, Fear or Surprise, and some characteristics of social interaction like Domination and Submission. In order to note emotions that subjects really felt during the process we asked them to fill in short questionnaires (self-reports) after each played scenario. The records were marked by 21 annotators (at least five annotators marked each scenario). We present our multimodal data collection, annotation process, inter-rater agreement analysis and the comparison between self-reports and received annotations.RAMAS is an open database that provides research community with multimodal data of faces, speech, gestures and physiology interrelation. Such material is useful for various investigations and automatic affective systems development.

show abstract

Body Movements for Affective Expression: A Survey of Automatic Recognition and Generation

Cited by 186 publications

References 150 publications

Exploiting the Robot Kinematic Redundancy for Emotion Conveyance to Humans as a Lower Priority Task

Exploiting the Robot Kinematic Redundancy for Emotion Conveyance to Humans as a Lower Priority Task

Challenges for the Animation of Expressive Virtual Characters: The Standpoint of Sign Language and Theatrical Gestures

RAMAS: Russian Multimodal Corpus of Dyadic Interaction for studying emotion recognition

Contact Info

Product

Resources

About