World model learning and inference

K Friston, RJ Moran, Y Nagai, T Taniguchi, H Gomi… - Neural Networks, 2021 - Elsevier
Understanding information processing in the brain—and creating general-purpose artificial
intelligence—are long-standing aspirations of scientists and engineers worldwide. The …

What is the role of the next generation of cognitive robotics?

S Shimoda, L Jamone, D Ognibene, T Nagai… - Advanced …, 2022 - Taylor & Francis
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 …

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

T Taniguchi, H Yamakawa, T Nagai, K Doya… - Neural Networks, 2022 - Elsevier
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 …

[HTML][HTML] Hippocampal formation-inspired probabilistic generative model

A Taniguchi, A Fukawa, H Yamakawa - Neural Networks, 2022 - Elsevier
In building artificial intelligence (AI) agents, referring to how brains function in real
environments can accelerate development by reducing the design space. In this study, we …

Symbol emergence as interpersonal cross-situational learning: the emergence of lexical knowledge with combinatoriality

Y Hagiwara, K Furukawa, T Horie, A Taniguchi… - arXiv preprint arXiv …, 2023 - arxiv.org
We present a computational model for a symbol emergence system that enables the
emergence of lexical knowledge with combinatoriality among agents through a Metropolis …

Active exploration based on information gain by particle filter for efficient spatial concept formation

A Taniguchi, Y Tabuchi, T Ishikawa, L El Hafi… - Advanced …, 2023 - Taylor & Francis
Autonomous robots need to learn the categories of various places by exploring their
environments and interacting with users. However, preparing training datasets with linguistic …

Concept formation through multimodal integration using multimodal BERT and VQ-VAE

K Miyazawa, T Nagai - Advanced Robotics, 2023 - Taylor & Francis
Humans form concepts from multimodal information obtained from multiple sensory organs
and understand the environment and language by predicting unobserved information …

Map completion from partial observation using the global structure of multiple environmental maps

Y Katsumata, A Kanechika, A Taniguchi… - Advanced …, 2022 - Taylor & Francis
Using the spatial structure of various indoor environments as prior knowledge, the robot
would construct the map more efficiently. Autonomous mobile robots generally apply …

Unsupervised lexical acquisition of relative spatial concepts using spoken user utterances

R Sagara, R Taguchi, A Taniguchi, T Taniguchi… - Advanced …, 2022 - Taylor & Francis
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 …

Hierarchical Bayesian model for the transfer of knowledge on spatial concepts based on multimodal information

Y Hagiwara, K Taguchi, S Ishibushi… - Advanced …, 2022 - Taylor & Francis
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 …