Concept formation by robots using an infinite mixture of models

Nagaoka, Tomoaki; Yoshiki, Atsushi; Nagai, Takayuki; Kaneko, Masahide

doi:10.1109/iros.2015.7354031

Cited by 15 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, object categories have a hierarchical structure, an object is categorized into several classes, and they have different modality-dependency based on the types of categories. Unsupervised machine learning methods for such complex categorization problem have proposed by several researchers based on hierarchical Bayesian models (Griffiths and Ghahramani, 2006 ; Ando et al, 2013 ; Nakamura et al, 2015 ). Theoretically, the main assumption we used was that the MHDP is a hierarchical Bayesian model and action selection is corresponding to obtaining an observation which is a probabilistic variable on the leaf node of its graphical model.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot

2018

View full text Add to dashboard Cite

In this paper, we propose an active perception method for recognizing object categories based on the multimodal hierarchical Dirichlet process (MHDP). The MHDP enables a robot to form object categories using multimodal information, e.g., visual, auditory, and haptic information, which can be observed by performing actions on an object. However, performing many actions on a target object requires a long time. In a real-time scenario, i.e., when the time is limited, the robot has to determine the set of actions that is most effective for recognizing a target object. We propose an active perception for MHDP method that uses the information gain (IG) maximization criterion and lazy greedy algorithm. We show that the IG maximization criterion is optimal in the sense that the criterion is equivalent to a minimization of the expected Kullback–Leibler divergence between a final recognition state and the recognition state after the next set of actions. However, a straightforward calculation of IG is practically impossible. Therefore, we derive a Monte Carlo approximation method for IG by making use of a property of the MHDP. We also show that the IG has submodular and non-decreasing properties as a set function because of the structure of the graphical model of the MHDP. Therefore, the IG maximization problem is reduced to a submodular maximization problem. This means that greedy and lazy greedy algorithms are effective and have a theoretical justification for their performance. We conducted an experiment using an upper-torso humanoid robot and a second one using synthetic data. The experimental results show that the method enables the robot to select a set of actions that allow it to recognize target objects quickly and accurately. The numerical experiment using the synthetic data shows that the proposed method can work appropriately even when the number of actions is large and a set of target objects involves objects categorized into multiple classes. The results support our theoretical outcomes.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot

2018

View full text Add to dashboard Cite

show abstract

“…Categories can be formed and inferred by an agent from sensorimotor information, i.e., features, alone without any labeled data. For example, the MLDAbased approach can categorize objects into object categories probabilistically [112]- [118]. A multimodal autoencoder can also perform a similar task.…”

Section: Redefinition Of the Terminologymentioning

confidence: 99%

Symbol Emergence in Cognitive Developmental Systems: A Survey

Taniguchi

Piater

Wörgötter

et al. 2019

IEEE Trans. Cogn. Dev. Syst.

Self Cite

View full text Add to dashboard Cite

Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and adaptation to our real-world environment. The symbol systems we use in our human society adaptively and dynamically change over time. In the context of artificial intelligence (AI) and cognitive systems, the symbol grounding problem has been regarded as one of the central problems related to symbols. However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered. In this paper, we focus on the symbol emergence problem, addressing not only cognitive dynamics but also the dynamics of symbol systems in society, rather than the symbol grounding problem. We first introduce the notion of a symbol in semiotics from the humanities, to leave the very narrow idea of symbols in symbolic AI. Furthermore, over the years, it became more and more clear that symbol emergence has to be regarded as a multifaceted problem. Therefore, secondly, we review the history of the symbol emergence problem in different fields, including both biological and artificial systems, showing their mutual relations. We summarize the discussion and provide an integrative viewpoint and comprehensive overview of symbol emergence in cognitive systems. Additionally, we describe the challenges facing the creation of cognitive systems that can be part of symbol emergence systems. Fig. 1. Robot in a home environment that has to deal with complex manipulation, planning, and interaction via semiotic communication with human users.

show abstract

“…In this result, SpCoMapping with DP prior is better than SpCoMapping with Dirichlet prior which the number of categories is given. As same as (Nakamura et al, 2015 ) when Gibbs sampling algorithm samples using fixed quantities of categories, it is sometimes harder than using changing quantities of categories. Figure 5 shows an example of the change in the ARI by iteration for Room2ldk4.…”

Section: Experiments 1: Simulation Environmentmentioning

confidence: 99%

Semantic Mapping Based on Spatial Concepts for Grounding Words Related to Places in Daily Environments

et al. 2019

View full text Add to dashboard Cite

An autonomous robot performing tasks in a human environment needs to recognize semantic information about places. Semantic mapping is a task in which suitable semantic information is assigned to an environmental map so that a robot can communicate with people and appropriately perform tasks requested by its users. We propose a novel statistical semantic mapping method called SpCoMapping, which integrates probabilistic spatial concept acquisition based on multimodal sensor information and a Markov random field applied for learning the arbitrary shape of a place on a map.SpCoMapping can connect multiple words to a place in a semantic mapping process using user utterances without pre-setting the list of place names. We also develop a nonparametric Bayesian extension of SpCoMapping that can automatically estimate an adequate number of categories. In the experiment in the simulation environments, we showed that the proposed method generated better semantic maps than previous semantic mapping methods; our semantic maps have categories and shapes similar to the ground truth provided by the user. In addition, we showed that SpCoMapping could generate appropriate semantic maps in a real-world environment.

show abstract

Concept formation by robots using an infinite mixture of models

Cited by 15 publications

References 23 publications

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot

Symbol Emergence in Cognitive Developmental Systems: A Survey

Semantic Mapping Based on Spatial Concepts for Grounding Words Related to Places in Daily Environments

Contact Info

Product

Resources

About