Search

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Constructive studies on symbol emergence systems seek to investigate computational models that can better explain human language evolution, the creation of symbol systems, and the construction of internal representations. Specifically, emergent communication aims to formulate a computational model that enables agents to build efficient sign systems and internal representations. This study provides a new model for emergent communication, which is based on a probabilistic generative model (PGM) instead of a discriminative model based on deep reinforcement learning. We define the Metropolis-Hastings (MH) naming game by generalizing previously proposed models. It is not a referential game with explicit feedback, as assumed by many emergent communication studies. Instead, it is a game based on joint attention without explicit feedback. Mathematically, the MH naming game is proved to be a type of MH algorithm for an integrative PGM that combines two agents that play the naming game. From this viewpoint, symbol emergence is regarded as decentralized Bayesian inference, and semiotic communication is regarded as inter-personal cross-modal inference. This notion leads to the collective predictive coding hypothesis regarding language evolution and, in general, the emergence of symbols. We also propose the inter-Gaussian mixture model (GMM)+ variational autoencoder (VAE), a deep generative model for emergent communication based on the MH naming game. In this model, two agents create internal representations and categories and share signs (i.e. names of objects) from raw visual images observed from different viewpoints. The model has been validated on MNIST and Fruits 360 datasets. Experimental findings demonstrate that categories are formed from real images observed by agents, and signs are correctly shared across agents by successfully utilizing both of the observations of agents via the MH naming game. Furthermore, scholars verified that visual images were recalled from signs uttered by agents. Notably, emergent communication without supervision and reward feedback improved the performance of the unsupervised representation learning of agents. [ABSTRACT FROM AUTHOR]

Although tendon-driven anthropomorphic robot hands have the potential to achieve human-level dexterity, controlling them is a great challenge owing to their mechanical complexities. Therefore, investigating human-hand control strategies is of the utmost importance. An important skill that enables the versatile manipulation ability of humans is visual posturing, i.e. the skill to make arbitrary hand postures based solely on visual observation. Visual posturing facilitates manipulation learning by enabling visual imitation learning and reusing visually similar past experiences. Therefore, this study investigates a method to replicate visual posturing in anthropomorphic robotic hands. Visual posturing in tendon-driven hands is challenging because of the hysteresis in tendon systems, the partial observability of the problem, and the presence of many actuators owing to the antagonistic tendon arrangement. To address these challenges, we propose a method that combines a model predictive path integral, a world model, and bio-inspired muscle synergies. The evaluation in a physical tendon-driven anthropomorphic robot hand showed that the proposed method achieved better visual posturing performance than a naive regression model. We anticipate that our visual posturing method will lay the foundation for versatile manipulation controllers that can adaptively learn manipulation tasks, similar to humans. [ABSTRACT FROM AUTHOR]

In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most current reinforcement learning method assumes a single-view observation space, and this imposes limitations on the observed data, such as lack of spatial information and occlusions. This makes obtaining ideal observational information from the environment difficult and is a bottleneck for real-world robotics applications. In this paper, we use contrastive learning to train a shared latent space between different viewpoints and show how the Products of Experts approach can be used to integrate and control the probability distributions of latent states for multiple viewpoints. We also propose Multi-View DreamingV2, a variant of Multi-View Dreaming that uses a categorical distribution to model the latent state instead of the Gaussian distribution. Experiments show that the proposed method outperforms simple extensions of existing methods in a realistic robot control task. [ABSTRACT FROM AUTHOR]

Creating autonomous robots that can actively explore the environment, acquire knowledge and learn skills continuously is the ultimate achievement envisioned in cognitive and developmental robotics. Importantly, if the aim is to create robots that can continuously develop through interactions with their environment, their learning processes should be based on interactions with their physical and social world in the manner of human learning and cognitive development. Based on this context, in this paper, we focus on the two concepts of world models and predictive coding. Recently, world models have attracted renewed attention as a topic of considerable interest in artificial intelligence. Cognitive systems learn world models to better predict future sensory observations and optimize their policies, i.e. controllers. Alternatively, in neuroscience, predictive coding proposes that the brain continuously predicts its inputs and adapts to model its own dynamics and control behavior in its environment. Both ideas may be considered as underpinning the cognitive development of robots and humans capable of continual or lifelong learning. Although many studies have been conducted on predictive coding in cognitive robotics and neurorobotics, the relationship between world model-based approaches in AI and predictive coding in robotics has rarely been discussed. Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics. Furthermore, we outline the frontiers and challenges involved in world models and predictive coding toward the further integration of AI and robotics, as well as the creation of robots with real cognitive and developmental capabilities in the future. [ABSTRACT FROM AUTHOR]

Autonomous robots need to learn the categories of various places by exploring their environments and interacting with users. However, preparing training datasets with linguistic instructions from users is time-consuming and labor-intensive. Moreover, effective exploration is essential for appropriate concept formation and rapid environmental coverage. To address this issue, we propose an active inference method, referred to as spatial concept formation with information gain-based active exploration (SpCoAE) that combines sequential Bayesian inference using particle filters and information gain-based destination determination in a probabilistic generative model. This study interprets the robot's action as a selection of destinations to ask the user, 'What kind of place is this?' in the context of active inference. This study provides insights into the technical aspects of the proposed method, including active perception and exploration by the robot, and how the method can enable mobile robots to learn spatial concepts through active exploration. Our experiment demonstrated the effectiveness of the SpCoAE in efficiently determining a destination for learning appropriate spatial concepts in home environments. [ABSTRACT FROM AUTHOR]

The workforce shortage in the service industry, recently highlighted by the pandemic, has increased the need for automation. We propose an autonomous robot to fulfill this purpose. Our mobile manipulator includes an extendable and compliant end effector design, as well as a custom-made automated shelf, and it is capable of manipulating food products such as lunch boxes, while traversing narrow spaces and reacting to human interventions. We benchmarked the solution in the international robotics competition Future Convenience Store Challenge (FCSC) where we obtained the first place in the 2020 edition, as well as in a laboratory setting, both situated in a convenience store scenario. We reported the results evaluated in terms of the score of the FCSC 2020 and further discussed the real-world applicability of the current system and open challenges. [ABSTRACT FROM AUTHOR]

In recent years, the labor shortage has become a significant problem in Japan and other countries due to aging societies. However, service robots can play a decisive role in relieving human workers by performing various household and assistive tasks. Restroom cleaning is one of such challenging tasks that involve performing motion planning in a constrained restroom setting. In this study, we propose a mobile manipulator to perform various tasks related to restroom cleaning. Our key contributions include system integration of multiple tools on an arm with high DoF mounted on a mobile, omni-directional platform capable of versatile service cleaning and with extended reachability. We evaluate the performance of our system with the competition setting used for the restroom cleaning task of the Future Convenience Store Challenge at the World Robot Summit 2020, where we obtained the 1st Place. The proposed system successfully completed all the competition tasks within the time limit and could remove the liquid with a removal rate of 96%. The proposed system could also dispose of most garbage and got an average garbage disposal rate of 90%. Further experiments confirmed the scores obtained in the competition with an even higher liquid removal rate of 98%. [ABSTRACT FROM AUTHOR]

Using the spatial structure of various indoor environments as prior knowledge, the robot would construct the map more efficiently. Autonomous mobile robots generally apply simultaneous localization and mapping (SLAM) methods to understand the reachable area in newly visited environments. However, conventional mapping approaches are limited by only considering sensor observation and control signals to estimate the current environment map. This paper proposes a novel SLAM method, map completion network-based SLAM (MCN-SLAM), based on a probabilistic generative model incorporating deep neural networks for map completion. These map completion networks are primarily trained in the framework of generative adversarial networks (GANs) to extract the global structure of large amounts of existing map data. We show in experiments that the proposed method can estimate the environment map 1.3 times better than the previous SLAM methods in the situation of partial observation. [ABSTRACT FROM AUTHOR]

This paper describes a computational model of multiagent multimodal categorization that realizes emergent communication. We clarify whether the computational model can reproduce the following functions in a symbol emergence system, comprising two agents with different sensory modalities playing a naming game. (1) Function for forming a shared lexical system that comprises perceptual categories and corresponding signs, formed by agents through individual learning and semiotic communication. (2) Function to improve the categorization accuracy in an agent via semiotic communication with another agent, even when some sensory modalities of each agent are missing. (3) Function that an agent infers unobserved sensory information based on a sign sampled from another agent in the same manner as cross-modal inference. We propose an interpersonal multimodal Dirichlet mixture (Inter-MDM), which is derived by dividing an integrative probabilistic generative model, which is obtained by integrating two Dirichlet mixtures (DMs). The Markov chain Monte Carlo algorithm realizes emergent communication. The experimental results demonstrated that Inter-MDM enables agents to form multimodal categories and appropriately share signs between agents. It is shown that emergent communication improves categorization accuracy, even when some sensory modalities are missing. Inter-MDM enables an agent to predict unobserved information based on a shared sign. [ABSTRACT FROM AUTHOR]

Domestic robots are often required to understand spoken commands in noisy environments, including service appliances' operating sounds. Most conventional domestic robots use electret condenser microphones (ECMs) to record the sound. However, the ECMs are known to be sensitive to the noise in the direction of sound arrival. The laser Doppler vibrometer (LDV), which has been widely used in the research field of measurement, has the potential to work as a new speech-input device to solve this problem. The aim of this paper is to investigate the effectiveness of using the LDV as an optical laser microphone for human-robot interaction in extremely noisy service environments. Our robot irradiates an object near a speaker with a laser and measures the vibration of the object to record the sound. We conducted three experiments to assess the performance of speech recognition using the optical laser microphone in various settings and showed stable performance in extremely noisy conditions compared with a conventional ECM. [ABSTRACT FROM AUTHOR]

Social demand for robots to be our partners in daily life has been rapidly increasing. Cognitive robotics should play a major role in making robots our partners. To discuss the role of cognitive robotics, we organized the round table in December 2020. This review paper aimed at clarifying the role of cognitive robotics summarizing the discussion in the round table. The round table noted that the existence of uncertainty in the continuous control loop is a source of the need for cognitive robots and is the key factor that distinguishes cognitive robotics from the cognitive system in other fields. This paper summarized the discussion focusing on the creation of several cognitive functions without stopping even if the robots face novel uncertainty in daily life. We discussed information generalization, active sensing, prediction, and language communication as the necessary functions for future cognitive robots. One of the conclusions of the discussion is the importance of setting primitive but concrete targets for cognitive robotics research as cognitive robotics problems. We should continue to discuss the setting of these targets as a grand challenge for cognitive robotics. [ABSTRACT FROM AUTHOR]

This paper proposes a hierarchical Bayesian model based on spatial concepts that enables a robot to transfer the knowledge of places from experienced environments to a new environment. The transfer of knowledge based on spatial concepts is modeled as the calculation process of the posterior distribution based on the observations obtained in each environment with the parameters of spatial concepts generalized to environments as prior knowledge. We conducted experiments to evaluate the generalization performance of spatial knowledge for general places such as kitchens and the adaptive performance of spatial knowledge for unique places such as 'Emma's room' in a new environment. In the experiments, the accuracies of the proposed method and conventional methods were compared in the prediction task of location names from an image and a position, and the prediction task of positions from a location name. The experimental results demonstrated that the proposed method has a higher prediction accuracy of location names and positions than the conventional method owing to the transfer of knowledge. [ABSTRACT FROM AUTHOR]

This paper proposes methods for unsupervised lexical acquisition for relative spatial concepts using spoken user utterances. A robot with a flexible spoken dialog system must be able to acquire linguistic representation and its meaning specific to an environment through interactions with humans as children do. Specifically, relative spatial concepts (e.g. front and right) are widely used in our daily lives, however, it is not obvious which object is a reference object when a robot learns relative spatial concepts. Therefore, we propose methods by which a robot without prior knowledge of words can learn relative spatial concepts. The methods are formulated using a probabilistic model to estimate the proper reference objects and distributions representing concepts simultaneously. The experimental results show that relative spatial concepts and a phoneme sequence representing each concept can be learned under the condition that the robot does not know which located object is the reference object. Additionally, we show that two processes in the proposed method improve the estimation accuracy of the concepts: generating candidate word sequences by class n-gram and selecting word sequences using location information. Furthermore, we show that clues to reference objects improve accuracy even though the number of candidate reference objects increases. [ABSTRACT FROM AUTHOR]

The installation of remotely-operated service robots in the environments of our daily life (including offices, homes, and hospitals) can improve work-from-home policies and enhance the quality of the so-called new normal. However, it is evident that remotely-operated robots must have partial autonomy and the capability to learn and use local semiotic knowledge. In this paper, we argue that the development of semiotically adaptive cognitive systems is key to the installation of service robotics technologies in our service environments. To achieve this goal, we describe three challenges: the learning of local knowledge, the acceleration of onsite and online learning, and the augmentation of human–robot interactions. [ABSTRACT FROM AUTHOR]

Tidy-up tasks by service robots in home environments are challenging in robotics applications because they involve various interactions with the environment. In particular, robots are required not only to grasp, move, and release various home objects but also to plan the order and positions for placing the objects. In this paper, we propose a novel planning method that can efficiently estimate the order and positions of the objects to be tidied up by learning the parameters of a probabilistic generative model. The model allows a robot to learn the distributions of the co-occurrence probability of the objects and places to tidy up using the multimodal sensor information collected in a tidied environment. Additionally, we develop an autonomous robotic system to perform the tidy-up operation. We evaluate the effectiveness of the proposed method by an experimental simulation that reproduces the conditions of the Tidy Up Here task of the World Robot Summit 2018 international robotics competition. The simulation results show that the proposed method enables the robot to successively tidy up several objects and achieves the best task score among the considered baseline tidy-up methods. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Robots are required to not only learn spatial concepts autonomously but also utilize such knowledge for various tasks in a domestic environment. Spatial concept represents a multimodal place category acquired from the robot's spatial experience including vision, speech-language, and self-position. The aim of this study is to enable a mobile robot to perform navigational tasks with human speech instructions, such as 'Go to the kitchen', via probabilistic inference on a Bayesian generative model using spatial concepts. Specifically, path planning was formalized as the maximization of probabilistic distribution on the path-trajectory under speech instruction, based on a control-as-inference framework. Furthermore, we described the relationship between probabilistic inference based on the Bayesian generative model and control problem including reinforcement learning. We demonstrated path planning based on human instruction using acquired spatial concepts to verify the usefulness of the proposed approach in the simulator and in real environments. Experimentally, places instructed by the user's speech commands showed high probability values, and the trajectory toward the target place was correctly estimated. Our approach, based on probabilistic inference concerning decision-making, can lead to further improvement in robot autonomy. [ABSTRACT FROM AUTHOR]

The integration of reinforcement learning (RL) and imitation learning (IL) is an important problem that has long been studied in the field of intelligent robotics. RL optimizes policies to maximize the cumulative reward, whereas IL attempts to extract general knowledge about the trajectories demonstrated by experts, i.e, demonstrators. Because each has its own drawbacks, many methods combining them and compensating for each set of drawbacks have been explored thus far. However, many of these methods are heuristic and do not have a solid theoretical basis. This paper presents a new theory for integrating RL and IL by extending the probabilistic graphical model (PGM) framework for RL, control as inference. We develop a new PGM for RL with multiple types of rewards, called probabilistic graphical model for Markov decision processes with multiple optimality emissions (pMDP-MO). Furthermore, we demonstrate that the integrated learning method of RL and IL can be formulated as a probabilistic inference of policies on pMDP-MO by considering the discriminator in generative adversarial imitation learning (GAIL) as an additional optimality emission. We adapt the GAIL and task-achievement reward to our proposed framework, achieving significantly better performance than policies trained with baseline methods. [ABSTRACT FROM AUTHOR]

We are pleased to announce the special issue on World Models and Predictive Coding in Robotics. This library will accelerate robotics research using such models, including world models. [Extracted from the article]

Keywords: machine leading; cognitive robotics; language acquisition; neural networks; cognitive architecture; probabilistic models; robot learning Following the successfully organized session "the Workshop on Machine Learning Methods for High-Level Cognitive Capabilities in Robotics 2016" held in IEEE-IROS 2016[1], we organized this Research Topic. Nakajo et al. proposed a machine learning method for viewpoint transformation and action mapping using a neural network having encoder-decoder architecture, i.e., sequence to sequence. Machine leading, cognitive robotics, language acquisition, neural networks, cognitive architecture, probabilistic models, robot learning. [Extracted from the article]

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. [ABSTRACT FROM AUTHOR]

In this paper, we propose a hierarchical spatial concept formation method based on the Bayesian generative model with multimodal information e.g., vision, position and word information. Since humans have the ability to select an appropriate level of abstraction according to the situation and describe their position linguistically, e.g., "I aminmy home" and "I am in front of the table," a hierarchical structure of spatial concepts is necessary in order for human support robots to communicate smoothly with users. The proposed method enables a robot to form hierarchical spatial concepts by categorizing multimodal information using hierarchical multimodal latent Dirichlet allocation (hMLDA). Object recognition results using convolutional neural network (CNN), hierarchical k-means clustering result of self-position estimated by Monte Carlo localization (MCL), and a set of location names are used, respectively, as features in vision, position, and word information. Experiments in forming hierarchical spatial concepts and evaluating how the proposed method can predict unobserved location names and position categories are performed using a robot in the real world. Results verify that, relative to comparable baseline methods, the proposed method enables a robot to predict location names and position categories closer to predictions made by humans. As an application example of the proposed method in a home environment, a demonstration in which a human support robot moves to an instructed place based on human speech instructions is achieved based on the formed hierarchical spatial concept. [ABSTRACT FROM AUTHOR]

Data representing driving behavior, as measured by various sensors installed in a vehicle, are collected as multi-dimensional sensor time-series data. These data often include redundant information, e.g., both the speed of wheels and the engine speed represent the velocity of the vehicle. Redundant information can be expected to complicate the data analysis, e.g., more factors need to be analyzed; even varying the levels of redundancy can influence the results of the analysis. We assume that the measured multi-dimensional sensor time-series data of driving behavior are generated from low-dimensional data shared by the many types of one-dimensional data of which multi-dimensional time-series data are composed. Meanwhile, sensor time-series data may be defective because of sensor failure. Therefore, another important function is to reduce the negative effect of defective data when extracting low-dimensional time-series data. This study proposes a defect-repairable feature extraction method based on a deep sparse autoencoder (DSAE) to extract low-dimensional time-series data. In the experiments, we show that DSAE provides high-performance latent feature extraction for driving behavior, even for defective sensor time-series data. In addition, we show that the negative effect of defects on the driving behavior segmentation task could be reduced using the latent features extracted by DSAE. [ABSTRACT FROM AUTHOR]

This paper describes how to achieve highly accurate unsupervised spatial lexical acquisition from speech-recognition results including phoneme recognition errors. In most research into lexical acquisition, the robot has no pre-existing lexical knowledge. The robot acquires sequences of some phonemes as words from continuous speech signals. In a previous study, we proposed a nonparametric Bayesian spatial concept acquisition method (SpCoA) that integrates the robot’s position and words obtained by unsupervised word segmentation from uncertain syllable recognition results. However, SpCoA has a very critical problem to be solved in lexical acquisition; the boundaries of word segmentation are incorrect in many cases because of many phoneme recognition errors. Therefore, we propose an unsupervised machine learning method (SpCoA++) for the robust lexical acquisition of novel words relating to places visited by the robot. The proposed SpCoA++ method performs an iterative estimation of learning spatial concepts and updating a language model using place information. SpCoA++ can select a candidate including many words that better represent places from multiple word-segmentation results by maximizing the mutual information between segmented words and spatial concepts. The experimental results demonstrate a significant improvement of the phoneme accuracy rate of learned words relating to place in the proposed method by word-segmentation results based on place information, in comparison to the conventional methods. We indicate that the proposed method enables the robot to acquire words from speech signals more accurately, and improves the estimation accuracy of the spatial concepts. [ABSTRACT FROM AUTHOR]