Realization of natural interaction dialogs in public environments using the humanoid robot ROMAN

Schmitz, Norbert M.; Hirth, Jochen; Berns, Karsten

doi:10.1109/ichr.2008.4756008

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tielman et al [8] proposed a robot that adaptively expresses various emotions by using its voice and gestures. Schmitz et al [9] developed a humanoid robot called ROMAN that is able to track and communicate with a human partner using verbal and nonverbal features. Nakano et al [10] proposed a two-layer model of behavior and dialogue planning for conversational service robots engaging in multi-domain guidance.…”

Section: Red Greenmentioning

confidence: 99%

Development of a robot quizmaster with auditory functions for speech-based multiparty interaction

Nishimuta

Yoshii

Itoyama

et al. 2014

2014 IEEE/SICE International Symposium on System Integration

View full text Add to dashboard Cite

Abstract-This paper presents a robot quizmaster that has auditory functions (i.e., ears) for moderating a multiplayer quiz game. The most basic form of oral interaction in a quiz game is that a quizmaster reads aloud a question, and each player is allowed to answer it whenever the answer comes to his or her mind. A critical problem in such oral interaction is that if multiple players speak almost simultaneously for answering, it is difficult for a "human" quizmaster to recognize overlapping answers and judge the correctness of each answer. To avoid this problem, players have conventionally been required to push a button, raise a hand, or say "Yes" to just get a right to answer a question before doing it. This requirement, however, inhibits natural oral interaction. In this paper we propose a "robot" quizmaster that can identify a player who correctly answers a question first, even when multiple players utter answers almost at the same time. Since our robot uses its own microphones (ears) embedded in the head, individual players are not required to wear small pin microphones close to their mouths. To localize, separate, and recognize overlapping utterances captured by the ears, we use a robot audition software called HARK and an automatic speech recognizer called Julius. Experimental results showed the effectiveness of our approach.

show abstract

Section: Red Greenmentioning

confidence: 99%

Development of a robot quizmaster with auditory functions for speech-based multiparty interaction

Nishimuta

Yoshii

Itoyama

et al. 2014

2014 IEEE/SICE International Symposium on System Integration

View full text Add to dashboard Cite

show abstract

“…Neck with 2 DOFs -movements about the yaw and pitch axes, have ASIMO [10], HUBO [11], HRP-4 [12], EveR1 [13], NAO [14], AILA [15], TORO [16], Justin [17], Pepper [18] etc.Neck with3 DOFs -movements about the yaw, roll and pitch axes, haveWABIAN-2 [19], Albert HUBO [20], HRP-4C [21], Affetto [22], iCub [23], Probo [24], EveR-2 [25], Geminoid F [26], Actroid-F [27] etc.Neck with4 DOFs -yaw, roll, upper and lower pitch movements, haveWE-4RII [28], ARMAR-III [29], ROMAN [30], KOBIAN [31], SAYA [32], BARTHOC [33], Romeo [34], Flutist Robot WF-4 [35], Twente Humanoid Head [36] etc.Neck structures with 2, 3 or 4 DOFs usually consist of rigid and low backlash mechanisms that are interconnected -harmonic drive, cable-driven mechanisms, spindle drive, low backlash gears, etc. In addition to high reliability and carrying capacity, the advantage of these mechanisms is low backlash that provide high positioning accuracy and repeatability of movements.…”

Section: State Of the Artmentioning

confidence: 99%

Assistive humanoid robot MARKO: development of the neck mechanism

et al. 2017

View full text Add to dashboard Cite

Abstract.The paper presents the development of neck mechanism for humanoid robots. The research was conducted within the project which is developing a humanoid robot Marko that represents assistive apparatus in the physical therapy for children with cerebral palsy.There are two basic ways for the neck realization of the robots. The first is based on low backlash mechanisms that have high stiffness and the second one based on the viscoelastic elements having variable flexibility. We suggest low backlash differential gear mechanism that requires small actuators. Based on the kinematic-dynamic requirements a dynamic model of the robots upper body is formed. Dynamic simulation for several positions of the robot was performed and the driving torques of neck mechanism are determined.Realized neck has 2 DOFs and enables movements in the direction of flexion-extension 100°, rotation ±90° and the combination of these two movements. It consists of a differential mechanism with three spiral bevel gears of which the two are driving and are identical, and the third one which is driven gear to which the robot head is attached. Power transmission and motion from the actuators to the input links of the differential mechanism is realized with two parallel placed gear mechanisms that are identical.Neck mechanism has high carrying capacity and reliability, high efficiency, low backlash that provide high positioning accuracy and repeatability of movements, compact design and small mass and dimensions.

show abstract

Multi-party Interactions by Quizmaster Robot in Speech-Based Jeopardy! Like Games

Gan

Chadwick

Gresty³

et al. 2017

2017 International Conference on Computational Science and Computational Intelligence (CSCI)

View full text Add to dashboard Cite

In the field of Natural Language Processing (NLP), we revisit the well-known word embedding algorithm word2vec. Word embeddings identify words by vectors such that the words' distributional similarity is captured. Unexpectedly, besides semantic similarity even relational similarity has been shown to be captured in word embeddings generated by word2vec, whence two questions arise. Firstly, which kind of relations are representable in continuous space and secondly, how are relations built. In order to tackle these questions we propose a bottom-up point of view. We call generating input text for which word2vec outputs target relations solving the Corpus Replication Task. Deeming generalizations of this approach to any set of relations possible, we expect solving of the Corpus Replication Task to provide partial answers to the questions.

show abstract

Realization of natural interaction dialogs in public environments using the humanoid robot ROMAN

Cited by 4 publications

References 12 publications

Development of a robot quizmaster with auditory functions for speech-based multiparty interaction

Development of a robot quizmaster with auditory functions for speech-based multiparty interaction

Assistive humanoid robot MARKO: development of the neck mechanism

Multi-party Interactions by Quizmaster Robot in Speech-Based Jeopardy! Like Games

Contact Info

Product

Resources

About