Hippocampal formation-inspired global self-localization: quick recovery from the kidnapped robot problem from an egocentric perspective.

It remains difficult for mobile robots to continue accurate self-localization when they are suddenly teleported to a location that is different from their beliefs during navigation. Incorporating insights from neuroscience into developing a spatial cognition model for mobile robots may make it possible to acquire the ability to respond appropriately to changing situations, similar to living organisms. Recent neuroscience research has shown that during teleportation in rat navigation, neural populations of place cells in the cornu ammonis-3 region of the hippocampus, which are sparse representations of each other, switch discretely. In this study, we construct a spatial cognition model using brain reference architecture-driven development, a method for developing brain-inspired software that is functionally and structurally consistent with the brain. The spatial cognition model was realized by integrating the recurrent state-space model, a world model, with Monte Carlo localization to infer allocentric self-positions within the framework of neuro-symbol emergence in the robotics toolkit. The spatial cognition model, which models the cornu ammonis-1 and -3 regions with each latent variable, demonstrated improved self-localization performance of mobile robots during teleportation in a simulation environment. Moreover, it was confirmed that sparse neural activity could be obtained for the latent variables corresponding to cornu ammonis-3. These results suggest that spatial cognition models incorporating neuroscience insights can contribute to improving the self-localization technology for mobile robots. The project website is https://nakashimatakeshi.github.io/HF-IGL/.

Hierarchical path planning from speech instructions with spatial concept-based topometric semantic mapping.

Assisting individuals in their daily activities through autonomous mobile robots is a significant concern, especially for users without specialized knowledge. Specifically, the capability of a robot to navigate to destinations based on human speech instructions is crucial. Although robots can take different paths toward the same objective, the shortest path is not always the most suitable. A preferred approach would be to accommodate waypoint specifications flexibly for planning an improved alternative path even with detours. Furthermore, robots require real-time inference capabilities. In this sense, spatial representations include semantic, topological, and metric-level representations, each capturing different aspects of the environment. This study aimed to realize a hierarchical spatial representation using a topometric semantic map and path planning with speech instructions by including waypoints. Thus, we present a hierarchical path planning method called spatial concept-based topometric semantic mapping for hierarchical path planning (SpCoTMHP), which integrates place connectivity. This approach provides a novel integrated probabilistic generative model and fast approximate inferences with interactions among the hierarchy levels. A formulation based on "control as probabilistic inference" theoretically supports the proposed path planning algorithm. We conducted experiments in a home environment using the Toyota human support robot on the SIGVerse simulator and in a lab-office environment with the real robot Albert. Here, the user issues speech commands that specify the waypoint and goal, such as "Go to the bedroom via the corridor." Navigation experiments were performed using speech instructions with a waypoint to demonstrate the performance improvement of the SpCoTMHP over the baseline hierarchical path planning method with heuristic path costs (HPP-I) in terms of the weighted success rate at which the robot reaches the closest target (0.590) and passes the correct waypoints. The computation time was significantly improved by 7.14 s with the SpCoTMHP than the baseline HPP-I in advanced tasks. Thus, hierarchical spatial representations provide mutually understandable instruction forms for both humans and robots, thus enabling language-based navigation.

Collective predictive coding hypothesis: symbol emergence as decentralized Bayesian inference.

Understanding the emergence of symbol systems, especially language, requires the construction of a computational model that reproduces both the developmental learning process in everyday life and the evolutionary dynamics of symbol emergence throughout history. This study introduces the collective predictive coding (CPC) hypothesis, which emphasizes and models the interdependence between forming internal representations through physical interactions with the environment and sharing and utilizing meanings through social semiotic interactions within a symbol emergence system. The total system dynamics is theorized from the perspective of predictive coding. The hypothesis draws inspiration from computational studies grounded in probabilistic generative models and language games, including the Metropolis-Hastings naming game. Thus, playing such games among agents in a distributed manner can be interpreted as a decentralized Bayesian inference of representations shared by a multi-agent system. Moreover, this study explores the potential link between the CPC hypothesis and the free-energy principle, positing that symbol emergence adheres to the society-wide free-energy principle. Furthermore, this paper provides a new explanation for why large language models appear to possess knowledge about the world based on experience, even though they have neither sensory organs nor bodies. This paper reviews past approaches to symbol emergence systems, offers a comprehensive survey of related prior studies, and presents a discussion on CPC-based generalizations. Future challenges and potential cross-disciplinary research avenues are highlighted.

Metropolis-Hastings algorithm in joint-attention naming game: experimental semiotics study.

We explore the emergence of symbols during interactions between individuals through an experimental semiotic study. Previous studies have investigated how humans organize symbol systems through communication using artificially designed subjective experiments. In this study, we focused on a joint-attention-naming game (JA-NG) in which participants independently categorized objects and assigned names while assuming their joint attention. In the Metropolis-Hastings naming game (MHNG) theory, listeners accept provided names according to the acceptance probability computed using the Metropolis-Hastings (MH) algorithm. The MHNG theory suggests that symbols emerge as an approximate decentralized Bayesian inference of signs, which is represented as a shared prior variable if the conditions of the MHNG are satisfied. This study examines whether human participants exhibit behavior consistent with the MHNG theory when playing the JA-NG. By comparing human acceptance decisions of a partner's naming with acceptance probabilities computed in the MHNG, we tested whether human behavior is consistent with the MHNG theory. The main contributions of this study are twofold. First, we reject the null hypothesis that humans make acceptance judgments with a constant probability, regardless of the acceptance probability calculated by the MH algorithm. The results of this study show that the model with acceptance probability computed by the MH algorithm predicts human behavior significantly better than the model with a constant probability of acceptance. Second, the MH-based model predicted human acceptance/rejection behavior more accurately than four other models (i.e., Constant, Numerator, Subtraction, Binary). Among the models compared, the model using the MH algorithm, which is the only model with the mathematical support of decentralized Bayesian inference, predicted human behavior most accurately, suggesting that symbol emergence in the JA-NG can be explained by the MHNG.

Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models.

In the studies on symbol emergence and emergent communication in a population of agents, a computational model was employed in which agents participate in various language games. Among these, the Metropolis-Hastings naming game (MHNG) possesses a notable mathematical property: symbol emergence through MHNG is proven to be a decentralized Bayesian inference of representations shared by the agents. However, the previously proposed MHNG is limited to a two-agent scenario. This paper extends MHNG to an N-agent scenario. The main contributions of this paper are twofold: (1) we propose the recursive Metropolis-Hastings naming game (RMHNG) as an N-agent version of MHNG and demonstrate that RMHNG is an approximate Bayesian inference method for the posterior distribution over a latent variable shared by agents, similar to MHNG; and (2) we empirically evaluate the performance of RMHNG on synthetic and real image data, i.e., YCB object dataset, enabling multiple agents to develop and share a symbol system. Furthermore, we introduce two types of approximations-one-sample and limited-length-to reduce computational complexity while maintaining the ability to explain communication in a population of agents. The experimental findings showcased the efficacy of RMHNG as a decentralized Bayesian inference for approximating the posterior distribution concerning latent variables, which are jointly shared among agents, akin to MHNG, although the improvement in ARI and κ coefficient is smaller in the real image dataset condition. Moreover, the utilization of RMHNG elucidated the agents' capacity to exchange symbols. Furthermore, the study discovered that even the computationally simplified version of RMHNG could enable symbols to emerge among the agents.

Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game.

Deep generative models (DGM) are increasingly employed in emergent communication systems. However, their application in multimodal data contexts is limited. This study proposes a novel model that combines multimodal DGM with the Metropolis-Hastings (MH) naming game, enabling two agents to focus jointly on a shared subject and develop common vocabularies. The model proves that it can handle multimodal data, even in cases of missing modalities. Integrating the MH naming game with multimodal variational autoencoders (VAE) allows agents to form perceptual categories and exchange signs within multimodal contexts. Moreover, fine-tuning the weight ratio to favor a modality that the model could learn and categorize more readily improved communication. Our evaluation of three multimodal approaches - mixture-of-experts (MoE), product-of-experts (PoE), and mixture-of-product-of-experts (MoPoE)-suggests an impact on the creation of latent spaces, the internal representations of agents. Our results from experiments with the MNIST + SVHN and Multimodal165 datasets indicate that combining the Gaussian mixture model (GMM), PoE multimodal VAE, and MH naming game substantially improved information sharing, knowledge formation, and data reconstruction.

Automatic selection of coordinate systems for learning relative and absolute spatial concepts.

Robots employed in homes and offices need to adaptively learn spatial concepts using user utterances. To learn and represent spatial concepts, the robot must estimate the coordinate system used by humans. For example, to represent spatial concept "left," which is one of the relative spatial concepts (defined as a spatial concept depending on the object's location), humans use a coordinate system based on the direction of a reference object. As another example, to represent spatial concept "living room," which is one of the absolute spatial concepts (defined as a spatial concept that does not depend on the object's location), humans use a coordinate system where a point on a map constitutes the origin. Because humans use these concepts in daily life, it is important for the robot to understand the spatial concepts in different coordinate systems. However, it is difficult for robots to learn these spatial concepts because humans do not clarify the coordinate system. Therefore, we propose a method (RASCAM) that enables a robot to simultaneously estimate the coordinate system and spatial concept. The proposed method is based on ReSCAM+O, which is a learning method for relative spatial concepts based on a probabilistic model. The proposed method introduces a latent variable that represents a coordinate system for simultaneous learning. This method can simultaneously estimate three types of unspecified information: coordinate systems, reference objects, and the relationship between concepts and words. No other method can estimate all these three types. Experiments using three different coordinate systems demonstrate that the proposed method can learn both relative and absolute spatial concepts while accurately selecting the coordinate system. The proposed approach can be beneficial for service robots to flexibly understand a new environment through the interactions with humans.

A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots.

Building a human-like integrative artificial cognitive system, that is, an artificial general intelligence (AGI), is the holy grail of the artificial intelligence (AI) field. Furthermore, a computational model that enables an artificial system to achieve cognitive development will be an excellent reference for brain and cognitive science. This paper describes an approach to develop a cognitive architecture by integrating elemental cognitive modules to enable the training of the modules as a whole. This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model (PGM)-based cognitive architecture to develop a cognitive system for developmental robots by integrating PGMs. The proposed development framework is called a whole brain PGM (WB-PGM), which differs fundamentally from existing cognitive architectures in that it can learn continuously through a system based on sensory-motor information. In this paper, we describe the rationale for WB-PGM, the current status of PGM-based elemental cognitive modules, their relationship with the human brain, the approach to the integration of the cognitive modules, and future challenges. Our findings can serve as a reference for brain studies. As PGMs describe explicit informational relationships between variables, WB-PGM provides interpretable guidance from computational sciences to brain science. By providing such information, researchers in neuroscience can provide feedback to researchers in AI and robotics on what the current models lack with reference to the brain. Further, it can facilitate collaboration among researchers in neuro-cognitive sciences as well as AI and robotics.

World model learning and inference.

Understanding information processing in the brain-and creating general-purpose artificial intelligence-are long-standing aspirations of scientists and engineers worldwide. The distinctive features of human intelligence are high-level cognition and control in various interactions with the world including the self, which are not defined in advance and are vary over time. The challenge of building human-like intelligent machines, as well as progress in brain science and behavioural analyses, robotics, and their associated theoretical formalisations, speaks to the importance of the world-model learning and inference. In this article, after briefly surveying the history and challenges of internal model learning and probabilistic learning, we introduce the free energy principle, which provides a useful framework within which to consider neuronal computation and probabilistic world models. Next, we showcase examples of human behaviour and cognition explained under that principle. We then describe symbol emergence in the context of probabilistic modelling, as a topic at the frontiers of cognitive robotics. Lastly, we review recent progress in creating human-like intelligence by using novel probabilistic programming languages. The striking consensus that emerges from these studies is that probabilistic descriptions of learning and inference are powerful and effective ways to create human-like artificial intelligent machines and to understand intelligence in the context of how humans interact with their world.

Explainable Artificial Intelligence Model for Diagnosis of Atrial Fibrillation Using Holter Electrocardiogram Waveforms.

Atrial fibrillation is a clinically important arrhythmia. There are some reports on machine learning models for AF diagnosis using electrocardiogram data. However, few reports have proposed an eXplainable Artificial Intelligence (XAI) model to enable physicians to easily understand the machine learning model's diagnosis results.We developed and validated an XAI-enabled atrial fibrillation diagnosis model based on a convolutional neural network (CNN) algorithm. We used Holter electrocardiogram monitoring data and the gradient-weighted class activation mapping (Grad-CAM) method.Electrocardiogram data recorded from patients between January 4, 2016, and October 31, 2019, totaling 57,273 electrocardiogram waveform slots of 30 seconds each with diagnostic information annotated by cardiologists, were used for training our proposed model. Performance metrics of our AI model for AF diagnosis are as follows: sensitivity, 97.1% (95% CI: 0.969-0.972); specificity, 94.5% (95% CI: 0.943-0.946); accuracy, 95.3% (95% CI: 0.952-0.955); positive predictive value, 89.3% (95% CI: 0.892-0.897); and F-value, 93.1% (95% CI: 0.929-0.933). The area under the receiver operating characteristic curve for AF detection using our model was 0.988 (95% CI: 0.987-0.988). Furthermore, using the XAI method, 94.5 ± 3.5% of the areas identified as regions of interest using our machine learning model were identified as characteristic sites for AF diagnosis by cardiologists.AF was accurately diagnosed and favorably explained with Holter ECG waveforms using our proposed CNN-based XAI model. Our study presents another step toward realizing a viable XAI-based detection model for AF diagnoses for use by physicians.

Panacea: Visual exploration system for analyzing trends in annual recruitment using time-varying graphs.

Annual recruitment data of new graduates are manually analyzed by human resources (HR) specialists in industries, which signifies the need to evaluate the recruitment strategy of HR specialists. Different job seekers send applications to companies every year. The relationships between applicants' attributes (e.g., English skill or academic credentials) can be used to analyze the changes in recruitment trends across multiple years. However, most attributes are unnormalized and thus require thorough preprocessing. Such unnormalized data hinder effective comparison of the relationship between applicants in the early stage of data analysis. Thus, a visual exploration system is highly needed to gain insight from the overview of the relationship among applicant qualifications across multiple years. In this study, we propose the Polarizing Attributes for Network Analysis of Correlation on Entities Association (Panacea) visualization system. The proposed system integrates a time-varying graph model and dynamic graph visualization for heterogeneous tabular data. Using this system, HR specialists can interactively inspect the relationships between two attributes of prospective employees across multiple years. Further, we demonstrate the usability of Panacea with representative examples for finding hidden trends in real-world datasets, and we discuss feedback from HR specialists obtained throughout Panacea's development. The proposed Panacea system enables HR specialists to visually explore the annual recruitment of new graduates.

Exploring Behaviors of Caterpillar-Like Soft Robots with a Central Pattern Generator-Based Controller and Reinforcement Learning.

Due to their flexibility, soft-bodied robots can potentially achieve rich and various behaviors within a single body. However, to date, no methodology has effectively harnessed these robots to achieve such diverse desired functionalities. Controllers that accomplish only a limited range of behaviors in such robots have been handcrafted. Moreover, the behaviors of these robots should be determined through body-environment interactions because an appropriate behavior may not always be manifested even if the body dynamics are given. Therefore, we have proposed SenseCPG-PGPE, a method for automatically designing behaviors for caterpillar-like soft-bodied robots. This method optimizes mechanosensory feedback to a central pattern generator (CPG)-based controller, which controls actuators in a robot, using policy gradients with parameter-based exploration (PGPE). In this article, we deeply investigated this method. We found that PGPE can optimize a CPG-based controller for soft-bodied robots that exhibit viscoelasticity and large deformation, whereas other popular policy gradient methods, such as trust region policy optimization and proximal policy optimization, cannot. Scalability of the method was confirmed using simulation as well. Although SenseCPG-PGPE uses a CPG-based controller, it can achieve nonsteady motion such as climbing a step in a simulated robot. The approach also resulted in distinctive behaviors depending on different body-environment conditions. These results demonstrate that the proposed method enables soft robots to explore a variety of behaviors automatically.

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

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.

Unsupervised Phoneme and Word Discovery From Multiple Speakers Using Double Articulation Analyzer and Neural Network With Parametric Bias.

This paper describes a new unsupervised machine-learning method for simultaneous phoneme and word discovery from multiple speakers. Phoneme and word discovery from multiple speakers is a more challenging problem than that from one speaker, because the speech signals from different speakers exhibit different acoustic features. The existing method, a nonparametric Bayesian double articulation analyzer (NPB-DAA) with deep sparse autoencoder (DSAE) only performed phoneme and word discovery from a single speaker. Extending NPB-DAA with DSAE to a multi-speaker scenario is, therefore, the research problem of this paper.This paper proposes the employment of a DSAE with parametric bias in the hidden layer (DSAE-PBHL) as a feature extractor for unsupervised phoneme and word discovery. DSAE-PBHL is designed to subtract speaker-dependent acoustic features and speaker-independent features by introducing parametric bias input to the DSAE hidden layer. An experiment demonstrated that DSAE-PBHL could subtract distributed representations of acoustic signals, enabling extraction based on the types of phonemes rather than the speakers. Another experiment demonstrated that a combination of NPB-DAA and DSAE-PBHL outperformed other available methods accomplishing phoneme and word discovery tasks involving speech signals with Japanese vowel sequences from multiple speakers.

Symbol Emergence as an Interpersonal Multimodal Categorization.

This study focuses on category formation for individual agents and the dynamics of symbol emergence in a multi-agent system through semiotic communication. In this study, the semiotic communication refers to exchanging signs composed of the signifier (i.e., words) and the signified (i.e., categories). We define the generation and interpretation of signs associated with the categories formed through the agent's own sensory experience or by exchanging signs with other agents as basic functions of the semiotic communication. From the viewpoint of language evolution and symbol emergence, organization of a symbol system in a multi-agent system (i.e., agent society) is considered as a bottom-up and dynamic process, where individual agents share the meaning of signs and categorize sensory experience. A constructive computational model can explain the mutual dependency of the two processes and has mathematical support that guarantees a symbol system's emergence and sharing within the multi-agent system. In this paper, we describe a new computational model that represents symbol emergence in a two-agent system based on a probabilistic generative model for multimodal categorization. It models semiotic communication via a probabilistic rejection based on the receiver's own belief. We have found that the dynamics by which cognitively independent agents create a symbol system through their semiotic communication can be regarded as the inference process of a hidden variable in an interpersonal multimodal categorizer, i.e., the complete system can be regarded as a single agent performing multimodal categorization using the sensors of all agents, if we define the rejection probability based on the Metropolis-Hastings algorithm. The validity of the proposed model and algorithm for symbol emergence, i.e., forming and sharing signs and categories, is also verified in an experiment with two agents observing daily objects in the real-world environment. In the experiment, we compared three communication algorithms: no communication, no rejection, and the proposed algorithm. The experimental results demonstrate that our model reproduces the phenomena of symbol emergence, which does not require a teacher who would know a pre-existing symbol system. Instead, the multi-agent system can form and use a symbol system without having pre-existing categories.

Robust Understanding of Robot-Directed Speech Commands Using Sequence to Sequence With Noise Injection.

This paper describes a new method that enables a service robot to understand spoken commands in a robust manner using off-the-shelf automatic speech recognition (ASR) systems and an encoder-decoder neural network with noise injection. In numerous instances, the understanding of spoken commands in the area of service robotics is modeled as a mapping of speech signals to a sequence of commands that can be understood and performed by a robot. In a conventional approach, speech signals are recognized, and semantic parsing is applied to infer the command sequence from the utterance. However, if errors occur during the process of speech recognition, a conventional semantic parsing method cannot be appropriately applied because most natural language processing methods do not recognize such errors. We propose the use of encoder-decoder neural networks, e.g., sequence to sequence, with noise injection. The noise is injected into phoneme sequences during the training phase of encoder-decoder neural network-based semantic parsing systems. We demonstrate that the use of neural networks with a noise injection can mitigate the negative effects of speech recognition errors in understanding robot-directed speech commands i.e., increase the performance of semantic parsing. We implemented the method and evaluated it using the commands given during a general purpose service robot (GPSR) task, such as a task applied in RoboCup@Home, which is a standard service robot competition for the testing of service robots. The results of the experiment show that the proposed method, namely, sequence to sequence with noise injection (Seq2Seq-NI), outperforms the baseline methods. In addition, Seq2Seq-NI enables a robot to understand a spoken command even when the speech recognition by an off-the-shelf ASR system contains recognition errors. Moreover, in this paper we describe an experiment conducted to evaluate the influence of the injected noise and provide a discussion of the results.

SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model.

To realize human-like robot intelligence, a large-scale cognitive architecture is required for robots to understand their environment through a variety of sensors with which they are equipped. In this paper, we propose a novel framework named Serket that enables the construction of a large-scale generative model and its inferences easily by connecting sub-modules to allow the robots to acquire various capabilities through interaction with their environment and others. We consider that large-scale cognitive models can be constructed by connecting smaller fundamental models hierarchically while maintaining their programmatic independence. Moreover, the connected modules are dependent on each other and their parameters must be optimized as a whole. Conventionally, the equations for parameter estimation have to be derived and implemented depending on the models. However, it has become harder to derive and implement equations of large-scale models. Thus, in this paper, we propose a parameter estimation method that communicates the minimum parameters between various modules while maintaining their programmatic independence. Therefore, Serket makes it easy to construct large-scale models and estimate their parameters via the connection of modules. Experimental results demonstrated that the model can be constructed by connecting modules, the parameters can be optimized as a whole, and they are comparable with the original models that we have proposed.

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot.

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.