Various emotional expressions with emotion expression humanoid robot WE-4RII

Itoh, Kazuko; Miwa, Hiroyoshi; Matsumoto, Mitsuharu; Zecca, Massimiliano; Takanobu, Hideaki; Roccella, S.; Carrozza, M.C.; Dario, P.; Takanishi, Atsuo

doi:10.1109/texcra.2004.1424983

Cited by 37 publications

(31 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gestures implemented in robots are however, until now, subject to two important limitations. Firstly, the gestures implemented in a robot are always limited to a set of gestures necessary for the current research, and often limited to one type of gestures, see [94] for an example. The reason for this can be found in the second limitation: gestures are mostly preprogrammed off-line for the current robot configuration.…”

Section: Platform Independent Flavourmentioning

confidence: 99%

How to Build a Supervised Autonomous System for Robot-Enhanced Therapy for Children with Autism Spectrum Disorder

Esteban

Baxter

Belpaeme

et al. 2017

Paladyn, Journal of Behavioral Robotics

117

View full text Add to dashboard Cite

Robot-Assisted Therapy (RAT) has successfully been used to improve social skills in children with autism spectrum disorders (ASD) through remote control of the robot in so-called Wizard of Oz (WoZ) paradigms. However, there is a need to increase the autonomy of the robot both to lighten the burden on human therapists (who have to remain in control and, importantly, supervise the robot) and to provide a consistent therapeutic experience. This paper seeks to provide insight into increasing the autonomy level of social robots in therapy to move beyond WoZ. With the final aim of improved human-human social interaction for the children, this multidisciplinary research seeks to facilitate the use of social robots as tools in clinical situations by addressing the challenge of increasing robot autonomy. We introduce the clinical framework in which the developments are tested, alongside initial data obtained from patients in a first phase of the project using a WoZ set-up mimicking the targeted supervised-autonomy behaviour. We further describe the implemented system architecture capable of providing the robot with supervised autonomy.

show abstract

Section: Platform Independent Flavourmentioning

confidence: 99%

How to Build a Supervised Autonomous System for Robot-Enhanced Therapy for Children with Autism Spectrum Disorder

Esteban

Baxter

Belpaeme

et al. 2017

Paladyn, Journal of Behavioral Robotics

117

View full text Add to dashboard Cite

show abstract

“…These emotions were commonly dealt with in the existing studies on emotion expression by robots [5,8,9,11,16]. In Wong et al [17], six emotions of anger, disgust, fear, happiness, surprise, sadness, and neutral were used, and age effects were confirmed for anger, disgust, fear, and sadness.…”

Section: Affective Body Motions Of the Robotmentioning

confidence: 99%

“…Itoh et al [5] developed a humanoid robot that could express several emotions including anger, sadness, and happiness, based on body motions. Marui and Matsumaru [9] explored motion expressions of three basic emotions, pleasure, sadness, and anger, by using a teddy bear robot.…”

Section: Introductionmentioning

confidence: 99%

Comparison on Identification of Affective Body Motions by Robots Between Elder People and University Students: A Case Study in Japan

Nomura

Nakao

2010

Int J of Soc Robotics

View full text Add to dashboard Cite

Expressive behaviors based on body motions are one of the useful methods that social robots present their emotional states toward users. On the other hand, some psychological research found age dependence on emotion identification in human facial expressions. In order to investigate this dependence in affective body expressions of robots, a psychological experiment was conducted in Japan, by using a small-sized humanoid robot on which three types of affective motion expression (anger, sadness, and pleasure) were implemented. The results of the experiment, which consisted of seventeen university student subjects and fifteen elder subjects, showed differences between younger and elder subjects on emotion identification, body parts paid attention to, and impressions of motion speed and magnitude for these affective body motions of the robot. Moreover, the results suggested correlations between the accuracy of emotion identification and cognitive bias to the robot's specific body motion parts. Based on these results, the paper discusses about some implications in human-robot interaction research.T. Nomura ( )

show abstract

“…Examples of relatively fast two DOF necks are ASIMO by Honda [1], the GuRoo by University of Queensland [2], the humanoid head developed by UC San Diego [3], and Maveric [4], the fast three DOF neck created at the University of Southern California. Examples of necks with a long range of motion are WE-4RII from the University of Waseda [5], QRIO by Sony [6], Cog by MIT [7], the humanoid head by the University of Karlsruhe [8], iSHA by Waseda University [9], and iCub by the Technical University of Madrid [10].…”

Section: Introductionmentioning

confidence: 99%

Mechatronic design of the Twente humanoid head

Reilink

Visser

Brouwer

et al. 2010

Intel Serv Robotics

View full text Add to dashboard Cite

This paper describes the mechatronic design of the Twente humanoid head, which has been realized in the purpose of having a research platform for human-machine interaction. The design features a fast, four degree of freedom neck, with long range of motion, and a vision system with three degrees of freedom, mimicking the eyes. To achieve fast target tracking, two degrees of freedom in the neck are combined in a differential drive, resulting in a low moving mass and the possibility to use powerful actuators. The performance of the neck has been optimized by minimizing backlash in the mechanisms, and using gravity compensation. The vision system is based on a saliency algorithm that uses the camera images to determine where the humanoid head should look at, i.e. the focus of attention computed according to biological studies. The motion control algorithm receives, as input, the output of the vision algorithm and controls the humanoid head to focus on and follow the target point. The control architecture exploits the redundancy of the system to show human-like motions while looking at a target. The head has a translucent plastic cover, onto which an internal LED system projects the mouth and the eyebrows, realizing human-like facial expressions.Keywords Humanoid head · Mechatronic design · Saliency-based vision system · Vision-based motion control · Human-like behavior

show abstract

Various emotional expressions with emotion expression humanoid robot WE-4RII

Cited by 37 publications

References 3 publications

How to Build a Supervised Autonomous System for Robot-Enhanced Therapy for Children with Autism Spectrum Disorder

How to Build a Supervised Autonomous System for Robot-Enhanced Therapy for Children with Autism Spectrum Disorder

Comparison on Identification of Affective Body Motions by Robots Between Elder People and University Students: A Case Study in Japan

Mechatronic design of the Twente humanoid head

Contact Info

Product

Resources

About