Search Results for author:
Found 46 papers, 11 papers with code
Real-world Instance-specific Image Goal Navigation for Service Robots: Bridging the Domain Gap with Contrastive Learning
To address this, we propose a novel method called Few-shot Cross-quality Instance-aware Adaptation (CrossIA), which employs contrastive learning with an instance classifier to align features between massive low- and few high-quality images.
Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
As a sub-discipline of evolutionary and computational linguistics, emergent communication (EC) studies communication protocols, called emergent languages, arising in simulations where agents communicate.
Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learning
Moreover, experiments on image retrieval using MNIST and PascalVOC showed that the representations of our method can be operated by OR and AND operations.
Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning
Therefore, the agents change their actions according to the estimated messages to achieve cooperative tasks.
Symbol emergence as interpersonal cross-situational learning: the emergence of lexical knowledge with combinatoriality
We present a computational model for a symbol emergence system that enables the emergence of lexical knowledge with combinatoriality among agents through a Metropolis-Hastings naming game and cross-situational learning.
Metropolis-Hastings algorithm in joint-attention naming game: Experimental semiotics study
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.
Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Models
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, enabling multiple agents to develop and share a symbol system.
World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges
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.
Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation
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.
Brain-inspired probabilistic generative model for double articulation analysis of spoken language
This study proposes a PGM for a DAA hypothesis that can be realized in the brain based on the outcomes of several neuroscientific surveys.
Speak Like a Dog: Human to Non-human creature Voice Conversion
This paper proposes a new voice conversion (VC) task from human speech to dog-like speech while preserving linguistic information as an example of human to non-human creature voice conversion (H2NH-VC) tasks.
Symbol Emergence as Inter-personal Categorization with Head-to-head Latent Word
On the basis of the H2H-type Inter-MDM, we propose a naming game in the same way as the conventional Inter-MDM.
Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models
Instead, it is a game based on joint attention without explicit feedback.
Representation Uncertainty in Self-Supervised Learning as Variational Inference
In this study, a novel self-supervised learning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties.
Hierarchical Path-planning from Speech Instructions with Spatial Concept-based Topometric Semantic Mapping
Navigation experiments using speech instruction with a waypoint demonstrated the performance improvement of path planning, WN-SPL by 0. 589, and reduced computation time by 7. 14 sec compared to conventional methods.
Multi-View Dreaming: Multi-View World Model with Contrastive Learning
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.
Tactile-Sensitive NewtonianVAE for High-Accuracy Industrial Connector Insertion
An industrial connector insertion task requires submillimeter positioning and grasp pose compensation for a plug.
DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction
The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming.
Unsupervised Multimodal Word Discovery based on Double Articulation Analysis with Co-occurrence cues
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.
Multiagent Multimodal Categorization for Symbol Emergence: Emergent Communication via Interpersonal Cross-modal Inference
(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.
StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
Although this method is powerful, it can fail to preserve the linguistic content of input speech when the number of available training samples is extremely small.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Unsupervised Lexical Acquisition of Relative Spatial Concepts Using Spoken User Utterances
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.
StarGAN-based Emotional Voice Conversion for Japanese Phrases
Through subjective evaluation experiments, we evaluated the performance of our StarGAN-EVC system in terms of its ability to achieve EVC for Japanese phrases.
Map completion from partial observation using the global structure of multiple environmental maps
Using the spatial structure of various indoor environments as prior knowledge, the robot would construct the map more efficiently.
Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery
The main contributions of this study are as follows: 1) We develop a probabilistic generative model for time series data including prosody that potentially has a double articulation structure; 2) We propose the Prosodic DAA by deriving the inference procedure for Prosodic HDP-HLM and show that Prosodic DAA can discover words directly from continuous human speech signals using statistical information and prosodic information in an unsupervised manner; 3) We show that prosodic cues contribute to word segmentation more in naturally distributed case words, i. e., they follow Zipf's law.
A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots
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 system to develop a cognitive system for developmental robots by integrating PGMs.
Hierarchical Bayesian Model for the Transfer of Knowledge on Spatial Concepts based on Multimodal Information
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.
Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction
In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels.
PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference
In this paper, we extend VI-MPC and PaETS, which have been originally introduced in previous literature, to address partially observable cases.
Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model
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.
Autonomous Planning Based on Spatial Concepts to Tidy Up Home Environments with Service Robots
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.
Domain-Adversarial and Conditional State Space Model for Imitation Learning
We experimentally evaluated the model predictive control performance via imitation learning for continuous control of sparse reward tasks in simulators and compared it with the performance of the existing SRL method.
Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor
An important component of SMC, i. e., a proposal distribution, is designed as a probabilistic neural pose predictor, which can propose diverse and plausible hypotheses by incorporating epistemic uncertainty and heteroscedastic aleatoric uncertainty.
Variational Inference MPC for Bayesian Model-based Reinforcement Learning
Probabilistic ensembles with trajectory sampling (PETS) is a leading type of MBRL, which employs Bayesian inference to dynamics modeling and model predictive control (MPC) with stochastic optimization via the cross entropy method (CEM).
Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model
In this paper, we present a new theory for integrating reinforcement and imitation learning by extending the probabilistic generative model framework for reinforcement learning, {\it plan by inference}.
Symbol Emergence as an Interpersonal Multimodal Categorization
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.
Towards Understanding Language through Perception in Situated Human-Robot Interaction: From Word Grounding to Grammar Induction
Robots are widely collaborating with human users in diferent tasks that require high-level cognitive functions to make them able to discover the surrounding environment.
Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping
We propose a novel online learning algorithm, called SpCoSLAM 2. 0, for spatial concepts and lexical acquisition with high accuracy and scalability.
Symbol Emergence in Cognitive Developmental Systems: a Survey
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.
SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
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.
Online Spatial Concept and Lexical Acquisition with Simultaneous Localization and Mapping
We have proposed a nonparametric Bayesian spatial concept acquisition model (SpCoA).
Spatial Concept Acquisition for a Mobile Robot that Integrates Self-Localization and Unsupervised Word Discovery from Spoken Sentences
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.
Multimodal Hierarchical Dirichlet Process-based Active Perception
We propose an MHDP-based active perception method that uses the information gain (IG) maximization criterion and lazy greedy algorithm.
Symbol Emergence in Robotics: A Survey
Humans can learn the use of language through physical interaction with their environment and semiotic communication with other people.
Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signals
In this paper, we develop a novel machine learning method called nonparametric Bayesian double articulation analyzer (NPB-DAA) that can directly acquire language and acoustic models from observed continuous speech signals.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
