Active learning of confidence measure function in robot language acquisition framework

Sugiura, Komei; Iwahashi, Naoto; Kashioka, Hideki; Nakamura, Satoshi

doi:10.1109/iros.2010.5649754

Cited by 18 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two popular approaches to motion modeling: dynamical systems [1]- [4] and stochastic This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0/ systems [5]- [9]. Dynamical systems represent motions as differential equations in the state space, while stochastic systems represent motion transitions and distributions.…”

Section: Related Workmentioning

confidence: 99%

Annotation Generation From IMU-Based Human Whole-Body Motions in Daily Life Behavior

Takano¹

2020

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

This article describes a stochastic framework for integrating human whole-body motions with natural language. Human whole-body motions in daily life are measured by inertial measurement units (IMU) and subsequently encoded into motion primitives. Sentences are manually attached to the human motion primitives for their descriptions. Two aspects of semantics and syntactics are represented by stochastic modules. One stochastic module trains the linking of motion primitives to words, and the other module represents word order in the sentence structure. These two modules are helpful toward converting human whole-body motions into descriptions, where multiple words are generated from the human motions by the first module, and the second module searches for syntactically consistent sentences consisting of the generated words. The proposed framework is tested on a large dataset of human whole-body motions and their descriptive sentences. The linking of human motions to natural language enables robots to understand observations of human behavior as sentences.

show abstract

Section: Related Workmentioning

confidence: 99%

Annotation Generation From IMU-Based Human Whole-Body Motions in Daily Life Behavior

Takano¹

2020

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

show abstract

“…Green and Eklundh, 2003;Matsui et al, 1999). Sugiura et al have begun investigating when and how to confirm a robot's pending action(s) (Sugiura et al, 2010(Sugiura et al, , 2011. Vanderheiden and Vanderheiden's product accessibility guideline which suggests to "use selection techniques where the person need only make a single, simple, non-time-dependent movement to select" is applicable to the users from our target population commanding telepresence robots (Vanderheiden and Vanderheiden, 1992).…”

Section: Designing Telepresence Robot Navigationmentioning

confidence: 99%

Towards designing telepresence robot navigation for people with disabilities

Tsui

McCann

McHugh

et al. 2014

International Journal of Intelligent Computing and Cybernetics

View full text Add to dashboard Cite

Purpose – The authors believe that people with cognitive and motor impairments may benefit from using of telepresence robots to engage in social activities. To date, these systems have not been designed for use by people with disabilities as the robot operators. The paper aims to discuss these issues. Design/methodology/approach – The authors conducted two formative evaluations using a participatory action design process. First, the authors conducted a focus group (n=5) to investigate how members of the target audience would want to direct a telepresence robot in a remote environment using speech. The authors then conducted a follow-on experiment in which participants (n=12) used a telepresence robot or directed a human in a scavenger hunt task. Findings – The authors collected a corpus of 312 utterances (first hand as opposed to speculative) relating to spatial navigation. Overall, the analysis of the corpus supported several speculations put forth during the focus group. Further, it showed few statistically significant differences between speech used in the human and robot agent conditions; thus, the authors believe that, for the task of directing a telepresence robot's movements in a remote environment, people will speak to the robot in a manner similar to speaking to another person. Practical implications – Based upon the two formative evaluations, the authors present four guidelines for designing speech-based interfaces for telepresence robots. Originality/value – Robot systems designed for general use do not typically consider people with disabilities. The work is a first step towards having our target population take the active role of the telepresence robot operator.

show abstract

“…RELATED WORK There have been many attempts to construct communicative robots for manipulation tasks [3]. Recently, in some studies [6], [7], [11]- [13], linguistic inputs were processed along with visual information to handle the many-to-many mapping between language and the environment.…”

Section: Introductionmentioning

confidence: 99%

Alleviating the Burden of Labeling: Sentence Generation by Attention Branch Encoder-Decoder Network

Ogura

Magassouba

Sugiura³

et al. 2020

Preprint

View full text Add to dashboard Cite

Domestic service robots (DSRs) are a promising solution to the shortage of home care workers. However, one of the main limitations of DSRs is their inability to interact naturally through language. Recently, data-driven approaches have been shown to be effective for tackling this limitation; however, they often require large-scale datasets, which is costly. Based on this background, we aim to perform automatic sentence generation of fetching instructions: for example, "Bring me a green tea bottle on the table." This is particularly challenging because appropriate expressions depend on the target object, as well as its surroundings. In this paper, we propose the attention branch encoder-decoder network (ABEN), to generate sentences from visual inputs. Unlike other approaches, the ABEN has multimodal attention branches that use subword-level attention and generate sentences based on subword embeddings. In experiments, we compared the ABEN with a baseline method using four standard metrics in image captioning. Results show that the ABEN outperformed the baseline in terms of these metrics.

show abstract

Active learning of confidence measure function in robot language acquisition framework

Cited by 18 publications

References 16 publications

Annotation Generation From IMU-Based Human Whole-Body Motions in Daily Life Behavior

Annotation Generation From IMU-Based Human Whole-Body Motions in Daily Life Behavior

Towards designing telepresence robot navigation for people with disabilities

Alleviating the Burden of Labeling: Sentence Generation by Attention Branch Encoder-Decoder Network

Contact Info

Product

Resources

About