Alle Publikationen
- <<
- <
- 1
2017
-
(2017): Real‐time gesture–based communication using possibility theory–based hidden Markov model. In: Computational Intelligence 33 (4), S. 843-862. DOI: 10.1111/coin.12116
DOI: https://doi.org/10.1111/coin.12116 Abstract: Exploring correct patterns from low‐frequency time‐series data is challenging. For resolving this problem, the concept of possibility theory–based hidden Markov model (PTBHMM) has been proposed. In this article, all three fundamental problems (evaluation, decoding, and learning) of conventional HMM have been addressed using possibility theory. For handling uncertainty, we have used an axiomatic approach of possibility theory proposed by Zadeh. The time complexity of existing solutions of HMM (forward, backward, Viterbi, and Baum Welch) and proposed possibility‐based solutions has been calculated and compared. From the comparison result, it has been found that PTBHMM has lesser time complexity and hence will be more suitable for real‐time gesture–based communication. (PsycINFO Database Record (c) 2018 APA, all rights reserved)
2016
-
(2016): Iconic gestures for robot avatars, recognition and integration with speech. In: Frontiers in psychology 7
Abstract: Co-verbal gestures are an important part of human communication, improving its efficiency and efficacy for information conveyance. One possible means by which such multi-modal communication might be realized remotely is through the use of a tele-operated humanoid robot avatar. Such avatars have been previously shown to enhance social presence and operator salience. We present a motion tracking based tele-operation system for the NAO robot platform that allows direct transmission of speech and gestures produced by the operator. To assess the capabilities of this system for transmitting multi-modal communication, we have conducted a user study that investigated if robot-produced iconic gestures are comprehensible, and are integrated with speech. Robot performed gesture outcomes were compared directly to those for gestures produced by a human actor, using a within participant experimental design. We show that iconic gestures produced by a tele-operated robot are understood by participants when presented alone, almost as well as when produced by a human. More importantly, we show that gestures are integrated with speech when presented as part of a multi-modal communication equally well for human and robot performances. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
-
(2016): Recollection reduces unitised familiarity effect. In: Memory (Hove, England) 24 (4), S. 535-547. DOI: 10.1080/09658211.2015.1021258
DOI: http://www.ncbi.nlm.nih.gov/pubmed/25793354 Abstract: Two types of encoding tasks have been employed in previous research to investigate the beneficial effect of unitisation on familiarity-based associative recognition (unitised familiarity effect), namely the compound task and the interactive imagery task. Here we show how these two tasks could differentially engage subsequent recollection-based associative recognition and consequently lead to the turn-on or turn-off of the unitised familiarity effect. In the compound task, participants studied unrelated word pairs as newly learned compounds. In the interactive imagery task, participants studied the same word pairs as interactive images. An associative recognition task was used in combination with the Remember/Know procedure to measure recollection-based and familiarity-based associative recognition. The results showed that the unitised familiarity effect was present in the compound task but was absent in the interactive imagery task. A comparison of the compound and the interactive imagery task revealed a dramatic increase in recollection-based associative recognition for the interactive imagery task. These results suggest that unitisation could benefit familiarity-based associative recognition; however, this effect will be eliminated when the memory trace formed is easily accessed by strong recollection without the need for a familiarity assessment. zitiert von 5
2015
-
(2015) : Multimodal affect recognition for naruralistic human-computer and human-robot interactions In: Calvo, Rafael A.; D’Mello, Sidney K.; Gratch, Jonathan; Kappas, Arvid (Hg.): The Oxford handbook of affective computing. Unter Mitarbeit von Rafael A. Calvo, Sidney K. D’Mello, Jonathan Gratch und Arvid Kappas: New York, NY: Oxford University Press (Oxford library of psychology), S. 246-257
Abstract: This chapter provides a synthesis of research on multimodal affect recognition and discusses methodological considerations and challenges arising from the design of a multimodal affect recognition system for naturalistic human-computer and human-robot interactions. Identified challenges include the collection and annotation of spontaneous affective expressions, the choice of appropriate methods for feature representation and selection in a multimodal context, and the need for context sensitivity and for classification schemes that take into account the dynamic nature of affect and the relationship between different modalities. Finally, two examples of multimodal affect recognition systems used in (soft) real-time naturalistic human-computer and human-robot interaction frameworks are presented. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
2013
-
(2013): Ontology-based state representations for intention recognition in human–robot collaborative environments. In: Robotics and Autonomous Systems 61 (11), S. 1224-1234. DOI: 10.1016/j.robot.2013.04.004
DOI: https://doi.org/10.1016/j.robot.2013.04.004 Abstract: In this paper, we describe a novel approach for representing state information for the purpose of intention recognition in cooperative human–robot environments. States are represented by a combination of spatial relationships in a Cartesian frame along with cardinal direction information. This approach is applied to a manufacturing kitting operation, where humans and robots are working together to develop kits. Based upon a set of predefined high-level state relationships that must be true for future actions to occur, a robot can use the detailed state information described in this paper to infer the probability of subsequent actions occurring. This would allow the robot to better help the human with the task or, at a minimum, better stay out of his or her way. (PsycINFO Database Record (c) 2016 APA, all rights reserved)
Keywords: Bedienung & Handhabung, Environmental Effects, Human Machine Systems, human robot environments, Intention, intention recognition, Intentional Learning, Knowledge representation, Ontology (Philosophy), ontology based state representations, Recognition (Learning), Robotics, Spatial Learning, spatial relationships
- <<
- <
- 1