2 citations · 5 across the 3 of their papers we have counts for
6 papers
Multiagent Multimodal Categorization for Symbol Emergence: Emergent Communication via Interpersonal Cross-modal Inference
Yoshinobu Hagiwara, Kazuma Furukawa, Akira Taniguchi +1
This paper describes a computational model of multiagent multimodal categorization that realizes emergent communication. We clarify whether the computational model can reproduce th…
Hierarchical Bayesian Model for the Transfer of Knowledge on Spatial Concepts based on Multimodal Information
Yoshinobu Hagiwara, Keishiro Taguchi, Satoshi Ishibushi +2
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 environm…
Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model
Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi +1
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 multim…
Autonomous Planning Based on Spatial Concepts to Tidy Up Home Environments with Service Robots
Akira Taniguchi, Shota Isobe, Lotfi El Hafi +2
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…
Symbol Emergence as an Interpersonal Multimodal Categorization
Yoshinobu Hagiwara, Hiroyoshi Kobayashi, Akira Taniguchi +1
This study focuses on category formation for individual agents and the dynamics of symbol emergence in a multi-agent system through semiotic communication. Semiotic communication i…
Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping
Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi +1
We propose a novel online learning algorithm, called SpCoSLAM 2.0, for spatial concepts and lexical acquisition with high accuracy and scalability. Previously, we proposed SpCoSLAM…