Learning and using context on a humanoid robot using latent dirichlet allocation

Çelikkanat, Hande; Orhan, Guner; Pugeault, Nicolas; Guérin, Frank; Şahi̇n, Erol; Kalkan, Sinan

doi:10.1109/devlrn.2014.6982982

Cited by 10 publications

(12 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We subsequently demonstrate how learning context from high-level concepts, instead of raw features, is easier and achieves higher performance. The current article extends an earlier version of our work [1], where preliminary results on integrating context were presented using the standard LDA with an ad hoc concept web. The current article differs in the following aspects: (i) The LDA is extended in order to make it online and incremental.…”

Section: B This Studymentioning

confidence: 64%

See 1 more Smart Citation

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Çelikkanat

Orhan

Pugeault

et al. 2016

IEEE Trans. Cogn. Dev. Syst.

Self Cite

View full text Add to dashboard Cite

Abstract-In this article, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field, inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make it incremental so that (i) it does not re-learn everything from scratch given new interactions (i.e., it is online) and (ii) it can discover and add a new context into its model when necessary. We demonstrate on the iCub platform that, partly owing to modeling context on top of the concept web, our approach is adaptive, online and robust: It is adaptive and online since it can learn and discover a new context from new interactions. It is robust since it is not affected by irrelevant stimuli and it can discover contexts after a few interactions only. Moreover, we show how to use the context learned in such a model for two important tasks: object recognition and planning.

show abstract

Section: B This Studymentioning

confidence: 64%

“…We define context as the totality of the information characterizing the situation of a cognitive system; e.g., it can include objects, persons, places, and temporally extended information related to ongoing tasks, but also information not directly related to these tasks [1].…”

Section: Introductionmentioning

confidence: 99%

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Çelikkanat

Orhan

Pugeault

et al. 2016

IEEE Trans. Cogn. Dev. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This model enables the identification of which novel words correspond to color, shape, or no attribute at all. Celikkanat et al ( 2014 ) proposed an unsupervised learning method based on latent Dirichlet allocation (LDA) that allows many-to-many relationships between objects and contexts. Their method was able to predict the context from the observation information and plan the action using learned contexts.…”

Section: Related Workmentioning

confidence: 99%

Cross-Situational Learning with Bayesian Generative Models for Multimodal Category and Word Learning in Robots

Taniguchi

Cangelosi

2017

Front. Neurorobot.

View full text Add to dashboard Cite

In this paper, we propose a Bayesian generative model that can form multiple categories based on each sensory-channel and can associate words with any of the four sensory-channels (action, position, object, and color). This paper focuses on cross-situational learning using the co-occurrence between words and information of sensory-channels in complex situations rather than conventional situations of cross-situational learning. We conducted a learning scenario using a simulator and a real humanoid iCub robot. In the scenario, a human tutor provided a sentence that describes an object of visual attention and an accompanying action to the robot. The scenario was set as follows: the number of words per sensory-channel was three or four, and the number of trials for learning was 20 and 40 for the simulator and 25 and 40 for the real robot. The experimental results showed that the proposed method was able to estimate the multiple categorizations and to learn the relationships between multiple sensory-channels and words accurately. In addition, we conducted an action generation task and an action description task based on word meanings learned in the cross-situational learning scenario. The experimental results showed that the robot could successfully use the word meanings learned by using the proposed method.

show abstract

“…The framework presented here is based on latent Dirichlet allocation (LDA), 2 a probabilistic topic model used to discover patterns in an unstructured collection of discrete data. Although LDA was originally developed for semantic analysis of text documents, it has since been applied in the domain of robotics to model context in a humanoid robot, 19 for activity analysis, 8 and autonomous exploration. 20 Following Blei, Griffiths, Jordan, & Tenenbaum, 21 we use a BNP extension to LDA to enable the topic model to automatically adapt its complexity and infer the number of groups, or clusters, present F I G U R E 1 Overview of our proposed technique for fault detection using probabilistic topic models.…”

Section: Data-drivenmentioning

confidence: 99%

“…(7)], subject to principal component analysis (PCA) dimensionality reduction. 19 In Figure 5(a), the pie-chart slices in each circle reflect the relative probability of each control policy P(control policy|z=k), computed using Eq. (6).…”

Section: Training Datasetmentioning

confidence: 99%

Detection of unanticipated faults for autonomous underwater vehicles using online topic models

Raanan

Bellingham

Zhang

et al. 2017

Journal of Field Robotics

View full text Add to dashboard Cite

For robots to succeed in complex missions, they must be reliable in the face of subsystem failures and environmental challenges. In this paper, we focus on autonomous underwater vehicle (AUV) autonomy as it pertains to self-perception and health monitoring, and we argue that automatic classification of state-sensor data represents an important enabling capability. We apply an online Bayesian nonparametric topic modeling technique to AUV sensor data in order to automatically characterize its performance patterns, then demonstrate how in combination with operatorsupplied semantic labels these patterns can be used for fault detection and diagnosis by means of a nearest-neighbor classifier. The method is evaluated using data collected by the Monterey Bay Aquarium Research Institute's Tethys long-range AUV in three separate field deployments. Our results show that the proposed method is able to accurately identify and characterize patterns that correspond to various states of the AUV, and classify faults at a high rate of correct detection with a very low false detection rate.

show abstract

Learning and using context on a humanoid robot using latent dirichlet allocation

Cited by 10 publications

References 32 publications

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Cross-Situational Learning with Bayesian Generative Models for Multimodal Category and Word Learning in Robots

Detection of unanticipated faults for autonomous underwater vehicles using online topic models

Contact Info

Product

Resources

About