2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005199
R. Cantrell, P. Schermerhorn, Matthias Scheutz
{"title":"Learning actions from human-robot dialogues","authors":"R. Cantrell, P. Schermerhorn, Matthias Scheutz","doi":"10.1109/ROMAN.2011.6005199","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005199","url":null,"abstract":"Natural language interactions between humans and robots are currently limited by many factors, most notably by the robot's concept representations and action repertoires. We propose a novel algorithm for learning meanings of action verbs through dialogue-based natural language descriptions. This functionality is deeply integrated in the robot's natural language subsystem and allows it to perform the actions associated with the learned verb meanings right away without any additional help or learning trials. We demonstrate the effectiveness of the algorithm in a scenario where a human explains to a robot the meaning of an action verb unknown to the robot and the robot is subsequently able to carry out the instructions involving this verb.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115407395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005291
M. Nakanishi, Y. Mitsukura, Akira Hara
{"title":"EEG analysis for acoustic quality evaluation using PCA and FDA","authors":"M. Nakanishi, Y. Mitsukura, Akira Hara","doi":"10.1109/ROMAN.2011.6005291","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005291","url":null,"abstract":"In this study, we propose the quantitative evaluation method of acoustic quality by using electroencephalogram (EEG). We analyze the EEG observed when subjects are listening to music by 3 kinds of stereo speaker system with different acoustic property. In this paper, as the first step of quantification, we analyze whether the difference of acoustic quality appear EEG by principal component analysis, analysis of variance and Fisher discriminant analysis. As a result, we confirmed that 1st principal component of EEG contains the imformation of acoustic quality evaluation which we can not obtain from questionnaires, and the possibility that we can use EEG for quantitative evaluation of acoustic quality.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115657973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005273
R. T. Peralta, Tasneem Kaochar, Ian R. Fasel, C. Morrison, Thomas J. Walsh, P. Cohen
{"title":"Challenges to decoding the intention behind natural instruction","authors":"R. T. Peralta, Tasneem Kaochar, Ian R. Fasel, C. Morrison, Thomas J. Walsh, P. Cohen","doi":"10.1109/ROMAN.2011.6005273","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005273","url":null,"abstract":"Currently, most systems for human-robot teaching allow only one mode of teacher-student interaction (e.g., teaching by demonstration or feedback), and teaching episodes have to be carefully set-up by an expert. To understand how we might integrate multiple, interleaved forms of human instruction into a robot learner, we performed a behavioral study in which 44 untrained humans were allowed to freely mix interaction modes to teach a simulated robot (secretly controlled by a human) a complex task. Analysis of transcripts showed that human teachers often give instructions that are nontrivial to interpret and not easily translated into a form useable by machine learning algorithms. In particular, humans often use implicit instructions, fail to clearly indicate the boundaries of procedures, and tightly interleave testing, feedback, and new instruction. In this paper, we detail these teaching patterns and discuss the challenges they pose to automatic teaching interpretation as well as the machine-learning algorithms that must ultimately process these instructions. We highlight the challenges by demonstrating the difficulties of an initial automatic teacher interpretation system.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115550083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005253
T. Lorenz, A. Mortl, Björn N. S. Vlaskamp, A. Schubö, S. Hirche
{"title":"Synchronization in a goal-directed task: Human movement coordination with each other and robotic partners","authors":"T. Lorenz, A. Mortl, Björn N. S. Vlaskamp, A. Schubö, S. Hirche","doi":"10.1109/ROMAN.2011.6005253","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005253","url":null,"abstract":"Synchronization occurs frequently in human behaviour: Everybody has experienced that in a group of people walking pace tends to equalize. The phenomenon of synchrony has been established in the literature in tasks which have little in common with daily life such as pendulum swinging and chair rocking. We extend the knowledge about human movement synchronization by showing that it also occurs during goal-directed actions. In a first experiment, we investigate how synchrony emerges develops over time. In a second experiment, we show that humans also synchronize their actions with a robot. Results are interpreted in the light of joint action theory. Possible implications and improvements for human-robot interaction are discussed.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122955061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005249
Séverin Lemaignan, Raquel Ros, R. Alami, M. Beetz
{"title":"What are you talking about? Grounding dialogue in a perspective-aware robotic architecture","authors":"Séverin Lemaignan, Raquel Ros, R. Alami, M. Beetz","doi":"10.1109/ROMAN.2011.6005249","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005249","url":null,"abstract":"While key for human-robot interaction, natural language interpretation is a notoriously difficult task, especially because the interaction context is at the same time essential for dialogue understanding, difficult to build for machines, and depends on each speaker point of view. However, robots as embodied artifacts, can perceive their environment and interactors, and hence compute symbolic models from various perspectives. This allows in turn to build symbolic contexts for dialogues. In this paper, we introduce DIALOGS, a component for natural language interpretation that relies on these structured symbolic models of the world to ground verbal interaction.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114057132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005256
Victor Emeli, H. Christensen
{"title":"Enhancing the robot service experience through social media","authors":"Victor Emeli, H. Christensen","doi":"10.1109/ROMAN.2011.6005256","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005256","url":null,"abstract":"The development of effective robot servers has been an intensely studied research area for many years. Their operation in a dynamic environment presents multiple challenges in navigation, recognition, human-robot interaction, and manipulation. This paper addresses the challenges presented by recognition and human-robot interaction by utilizing Twitter and Facebook to potentially mitigate some of the long known issues in these areas. Specifically, we will address the problems of reliable human-robot communications and efficiency of service delivery. An online scenario study is administered to participants to evaluate the performance of a social media enabled robot as compared to a traditional speech synthesis and recognition enabled robot. The potential for the robot to learn and build long-term relationships through access to these social mediums is also discussed as a future work.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124043419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005231
Yanchao Dong, Zhencheng Hu
{"title":"A fast human face modeler and tracker for Driver Inattention Monitoring","authors":"Yanchao Dong, Zhencheng Hu","doi":"10.1109/ROMAN.2011.6005231","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005231","url":null,"abstract":"For the application of Driver Inattention Monitoring System this paper propose a zero-order binocular EKF face tracker. By combining the facial feature extraction algorithm our proposed tracker could estimate the face pose, the eyeball yaw & pitch, the eyelids animation and the mouth & jaw animation as well as shape parameters. The facial feature extraction algorithms are also presented. Experiments shows the proposed full detection and tracking loop could give more reliable result than monocular tracker with real time performance on a general purpose personal computer. It is also shown the tracker has tolerance against feature point detection error.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"110 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124160636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005276
A. Samadani, Brandon J. DeHart, Kirsten Robinson, D. Kulić, E. Kubica, R. Gorbet
{"title":"A study of human performance in recognizing expressive hand movements","authors":"A. Samadani, Brandon J. DeHart, Kirsten Robinson, D. Kulić, E. Kubica, R. Gorbet","doi":"10.1109/ROMAN.2011.6005276","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005276","url":null,"abstract":"This paper presents a study on human performance in recognizing affective expressions conveyed through movements of hand-like structures. One movement sequence, closing and opening the hand, was performed by a demonstrator in 3 sets of 5 repeated trials, each set intending to convey a different affective expression. Three different expressions, sadness, happiness and anger, were considered. Expressive movement animations were replicated with a human-like hand model, a stick hand model and with a model resembling a palm frond structure. The structures tested have identical kinematics but different physical appearance. The ability of a human to correctly identify the intended expressive movements performed on these different structures was tested with 66 users viewing videos of the animated structures and reporting via an online questionnaire. Results show that anger is reliably perceived by observers from animated movements on different structures, while the other emotions are easily misperceived. The physical appearance of the structure has some impact on perception performance, but was not found to be statistically significant in this study. Furthermore, analyzing the participants' responses in the context of the valence-arousal model of emotion shows that the subjects were able to recognize the arousal component of the affective hand movements across all structures.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128126299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005229
M. Wongphati, Hirotaka Osawa, M. Imai
{"title":"3D low-profile evaluation system (LES) an unobtrusive measurement tool for HRI","authors":"M. Wongphati, Hirotaka Osawa, M. Imai","doi":"10.1109/ROMAN.2011.6005229","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005229","url":null,"abstract":"An unobtrusive measurement tool is important for Human-Robot Interaction (HRI) research that does not want to attach markers or devices on the experiment subjects. This property allows a natural observation of interaction between human and robot during the experiment. In HRI, an experiment that involves with psychological evaluation usually requires physical measurement for evaluating the interaction, for instance, distance, direction, and approaching speed between human and robot. Low-profile Evaluation System (LES) is an ongoing work in creating an unobtrusive measurement tool for HRI research that provides 3D video recording, playback and measurement inside 3D scene in real-time. LES is designed to operate on a single computer to make setup and experiment outside laboratory environment easier. The demonstration in the real-word setup shows that LES provides acceptable 3D measurement accuracy for HRI research.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131474425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2011 RO-MANPub Date : 2011-08-30DOI: 10.1109/ROMAN.2011.6005252
M. Lohse
{"title":"Bridging the gap between users' expectations and system evaluations","authors":"M. Lohse","doi":"10.1109/ROMAN.2011.6005252","DOIUrl":"https://doi.org/10.1109/ROMAN.2011.6005252","url":null,"abstract":"What users expect of a robot strongly influences their ratings of the interaction. If the robot satisfies the expectations, the users are usually pleased. If not, their experience of the interaction is negative. We as robot designers strive to design for positive interaction experiences. Therefore, users' expectations need to be taken into account. However, in this paper we argue that not all expectations are equally important. Based on a semantic differential questionnaire, we show a correlation between the perceived importance of users' expectations and the difficulty to satisfy them in interaction. The paper argues that this correlation allows to identify the most important improvements that should be made to robot systems but also to find attributes which the robot is quite good at already.","PeriodicalId":408015,"journal":{"name":"2011 RO-MAN","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115330932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}