Search

Our study introduces a novel approach that combined probabilistic logic and multimodal spatial concepts to enable a robot to efficiently acquire place–object relationships in a new home environment with few learning iterations. By leveraging probabilistic logic, which employs predicate logic with probability values, we represent common-sense knowledge of the place–object relationships. The integration of logical inference and cross-modal inference to calculate conditional probabilities across different modalities enables the robot to infer object locations even when their likely locations are undefined. To evaluate the effectiveness of our method, we conducted simulation experiments and compared the results with three baselines: multimodal spatial concepts only, common-sense knowledge only, and common-sense knowledge and multimodal spatial concepts combined. By comparing the number of room visits required by the robot to locate 24 objects, we demonstrated the improved performance of our approach. For search tasks including objects whose locations were undefined, the findings demonstrate that our method reduced the learning cost by a factor of 1.6 compared to the baseline methods. Additionally, we conducted a qualitative analysis in a real-world environment to examine the impact of integrating the two inferences and identified the scenarios that influence changes in the task success rate.

Human infants acquire their verbal lexicon with minimal prior knowledge of language based on the statistical properties of phonological distributions and the co-occurrence of other sensory stimuli. This study proposes a novel fully unsupervised learning method for discovering speech units using phonological information as a distributional cue and object information as a co-occurrence cue. The proposed method can acquire words and phonemes from speech signals using unsupervised learning and utilize object information based on multiple modalities—vision, tactile, and auditory—simultaneously. The proposed method is based on the nonparametric Bayesian double articulation analyzer (NPB-DAA) discovering phonemes and words from phonological features, and multimodal latent Dirichlet allocation (MLDA) categorizing multimodal information obtained from objects. In an experiment, the proposed method showed higher word discovery performance than baseline methods. Words that expressed the characteristics of objects (i.e., words corresponding to nouns and adjectives) were segmented accurately. Furthermore, we examined how learning performance is affected by differences in the importance of linguistic information. Increasing the weight of the word modality further improved performance relative to that of the fixed condition.

Word and phone discovery are important tasks in the language development of human infants. Infants acquire words and phones from unsegmented speech signals using segmentation cues, such as distributional, prosodic, and co-occurrence information. Many pre-existing computational models designed to represent this process tend to focus on distributional or prosodic cues. In this study, we propose a nonparametric Bayesian probabilistic generative model called the prosodic hierarchical Dirichlet process-hidden language model (prosodic HDP-HLM) designed to perform simultaneous phone and word discovery from continuous speech signals encoded as time-series data that may exhibit a double articulation structure. Prosodic HDP-HLM, as an extension of HDP-HLM, considers both prosodic and distributional cues within a single integrative generative model. We further propose a prosodic double articulation analyzer (Prosodic DAA) based on an inference procedure derived for prosodic HDP-HLM. We conducted three experiments on different types of data sets, including, Japanese vowel sequence, utterances for teaching object names and features, and utterances following Zipf’s law, and the results demonstrated the validity of the proposed method. The results show that the Prosodic DAA successfully used prosodic cues and was able to discover words directly from continuous human speech using distributional and prosodic information in an unsupervised manner, outperforming a method that solely used distributional cues. In contrast, the phone discovery performance did not improve. We also show that prosodic cues contributed to word discovery performance more when the word frequency was distributed more naturally, i.e., following Zipf’s law.

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, second, 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.

•Given today’s advances in artificial intelligence, expectations are rising for building artificial general intelligence (AGI).•We propose an approach focusing on the process of acquisition of intelligence, called evolutionary and developmental intelligence(EDI).•This review explores how we can integrate advances in neuroscience, machine learning, and robotics to practically construct EDI systems.

In this paper, we propose a novel risk-limiting real-time pricing mechanism for a regional electricity network of prosumers with distributed solar power generation. The target system is a regional electricity network that consists of many prosumers, each equipped with a battery and a renewable energy-based generator. In particular, we assume that each prosumer is in possession of a solar power generator, i.e., photovoltaic cells. In the proposed market mechanism, each prosumer sets an asking price and bids for the amount of electricity that he/she sells or buys, In addition, he/she sets an asking price and bids for a parameter to cope with the uncertainty induced by solar power generation in a day-ahead market, as well. It is a characteristic of regional electricity networks of prosumers that there is a strong correlation in the solar power generation of each house within a network. A market mechanism for a regional electricity network of prosumers with distributed solar power generation should consider such characteristics. The performance of the proposed mechanism is demonstrated numerically through a simulation experiment. It outperformed a conventional real-time pricing method that does not consider uncertainty, and a method that does not involve trading of the parameter for coping with uncertainty.

In this paper, we propose a novel unsupervised learning method for the lexical acquisition of words related to places visited by robots, from human continuous speech signals. We address the problem of learning novel words by a robot that has no prior knowledge of these words except for a primitive acoustic model. Furthermore, we propose a method that allows a robot to effectively use the learned words and their meanings for self-localization tasks. The proposed method is nonparametric Bayesian spatial concept acquisition method (SpCoA) that integrates the generative model for self-localization and the unsupervised word segmentation in uttered sentences via latent variables related to the spatial concept. We implemented the proposed method SpCoA on SIGVerse, which is a simulation environment, and TurtleBot2, which is a mobile robot in a real environment. Further, we conducted experiments for evaluating the performance of SpCoA. The experimental results showed that SpCoA enabled the robot to acquire the names of places from speech sentences. They also revealed that the robot could effectively utilize the acquired spatial concepts and reduce the uncertainty in self-localization.

Human infants can discover words directly from unsegmented speech signals without any explicitly labeled data. Current machine learning methods cannot efficiently estimate language model (LM) and acoustic model (AM) and discover words directly from continuous human speech signals in an unsupervised manner. To solve this problem, we propose an integrative generative model that combines an LM and an AM into a single generative model called the hierarchical Dirichlet process hidden LM (HDP-HLM). The HDP-HLM is obtained by extending the hierarchical Dirichlet process hidden semi-Markov model (HDP-HSMM) proposed by Johnson et al. An inference procedure for the HDP-HLM is derived using the blocked Gibbs sampler originally proposed for the HDP-HSMM. This procedure enables the simultaneous and direct inference of LM and AM from continuous speech signals. Based on the HDP-HLM and its inference procedure, we develop a novel machine learning method called nonparametric Bayesian double articulation analyzer (NPB-DAA) that can directly acquire LM and AM from observed continuous speech signals. By assuming HDP-HLM as a generative model of observed time series data, and by inferring latent variables of the model, the method can analyze latent double articulation structure, i.e., hierarchically organized latent words and phonemes, of the data in an unsupervised manner. We also carried out two evaluation experiments using synthetic data and actual human continuous speech signals representing Japanese vowel sequences. In the word acquisition and phoneme categorization tasks, the NPB-DAA outperformed a conventional double articulation analyzer and baseline automatic speech recognition system whose AM was trained in a supervised manner. The main contributions of this paper are as follows: 1) we develop a probabilistic generative model that integrates LM and AM, i.e., HDP-HLM; 2) we derive an inference method for this, and propose the NPB-DAA; and 3) we show that the NPB-DAA can discover words directly from continuous human speech signals in an unsupervised manner.

In recent years, demand-side management (DSM) has attracted increasing attention in balancing the demand and supply of electricity for future smart grids. Particularly, many researchers consider DSM with dual-decomposition for which the theoretical properties are based on Lagrangian relaxation. It has been proven that the optimal profile of generation and consumption using DSM with dual-decomposition can be obtained. However, the convergence error and the existing range of the optimal price have not been analyzed sufficiently, nevertheless the success of dual decomposition centers on finding an good solution. In this paper, we consider the expanded electricity grid model based on Atzeni and Samadi's model. We introduce a day-ahead pricing algorithm, which is an extension of Samadi's algorithm, and we analyze the error and the range. Finally, we show the main parameters that have an impact on price through this theoretical analysis, that is, the maximum sell and purchase value have an impact and the maximum values of other parameters do not.

Humans can acquire language through physical interaction with their environment and semiotic interaction with other people. It is very important to understand how humans can form a symbol system and obtain semiotic skills through their autonomous mental development from a computational point of view. A machine learning system that enables a robot to obtain and modulate its symbol system is crucially important to develop robotic systems that achieve long-term human-robot communication and collaboration. In this paper, I introduce the basis of our research field and related topics. Specifically, I describe the concept of symbol emergence systems and the recent research topics , e.g., multimodal categorization, spatial concept formation, language acquisition, and double articulation analysis, that will contribute to future human-robot communication and collaboration.

In this paper, we propose a novel learning method that can simultaneously estimate the self-position of a robot and place names. The robot moves in a room environment and performs probabilistic self-localization based on noisy sensory information. Speech recognition results include the uncertainty of phonemes or syllables, because the robot does not have lexical knowledge in advance. The purpose of this study is to reduce the uncertainty of both self-position and speech recognition using knowledge about place names, which is obtained from human speech. The proposed method integrates ambiguous speech recognition results with the self-localization method, i.e., Monte Carlo localization, using a Bayesian approach. Probability distributions over places and the speech recognition error are modeled using the proposed method. We implemented the proposed method in SIGVerse, which is a simulation environment. Experimental results showed that the robot can acquire the names of several places and use this knowledge to reduce the uncertainty of estimation in its position in a self-localization task. In addition, we evaluated the performance of the lexical acquisition task for the names of places and showed its effectiveness. Results showed that the robot could acquire spatial concepts by integrating noisy information from sensors and speech.

There are several problems which discourage an organization from achieving tasks, e.g., partial observation, credit assignment, and concurrent learning in multi-agent reinforcement learning. In many conventional approaches, each agent estimates hidden states, e.g., sensor inputs, positions, and policies of other agents, and reduces the uncertainty in the partially-observable Markov decision process (POMDP), which partially solve the multiagent reinforcement learning problem. In contrast, people reduce uncertainty in human organizations in the real world by autonomously dividing the roles played by individual agents. In a framework of reinforcement learning, roles are mainly represented by goals for individual agents. This paper presents a method for generating internal rewards from manager agents to worker agents. It also explicitly divides the roles, which enables a POMDP task for each agent to be transformed into a simple MDP task under certain conditions. Several situational experiments are also described and the validity of the proposed method is evaluated.