Akira Taniguchi 研究室

主宰者：Akira Taniguchi

立命館大学

AI 要約（直近 5 年の研究成果）

Akira Taniguchi研究室では、ロボットが人間と協働して日常生活を支援するために必要な知識や能力の獲得に関する研究に取り組んでいます。特に、言語理解と環境認識の統合に注力しており、大規模言語モデルを用いて自然言語の指示をロボット行動計画に変換する手法を開発しています。同時に、室内環境の意味的構造をマッピング技術で捉え、物体の所在位置や用途といった文脈情報を活用することで、より正確で柔軟な指示解釈を実現しようとしています。研究室のもう一つの中核テーマは、複数のロボットやエージェント間での共有シンボル（記号）の自律的な出現と発展です。確率的生成モデルとベイズ推論の枠組みを用いて、エージェント同士が互いに相互作用しながら、離散的なシンボルから連続的で微妙な信号まで含むコミュニケーション体系を段階的に構築するプロセスを研究しています。Metropolis-Hastingsサンプリングを組み込んだ命名ゲーム理論など、エージェントが相手の内部状態を直接観測することなく共有知識を形成する仕組みの開発を進めています。さらに、これらの基礎理論を実装ロボットに統合し、家庭環境における動的な学習と知識獲得の実現を目指しています。ユーザーとの相互作用を通じた曖昧性の解消、不確実性に基づく質問生成、そして複数ロボットの分散協調制御など、現実的な支援ロボットに求められる多様な課題に学習理論と推論モデルを適用する研究展開がみられます。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（57 件）

[2026] Toward Spatial Cognition and Semantic Understanding of Place in Robots
DOI: https://doi.org/10.7210/jrsj.44.468
[2026] MH-MuG: Collaborative Music Generation Game Between AI Agents Toward Emergent Musical Creativity
DOI: https://doi.org/10.1109/access.2026.3666234
[2026] Compositional Generalization in Emergent Communication via Metropolis-Hastings Naming Game with Transformer Language Models
DOI: https://doi.org/10.1109/tcds.2026.3699989
[2026] Whose Is This?: Context-Aware Object Ownership Inference with Uncertainty-Guided Questioning
[2026] Variational Bayes naming game: decentralized multi-agent inference for symbol emergence
DOI: https://doi.org/10.1080/01691864.2026.2661967
[2026] Multi-robot task planning for multi-object retrieval tasks with distributed on-site knowledge via large language models
DOI: https://doi.org/10.1007/s10015-026-01123-8
[2026] Reducing Mental Workload through On-Demand Human Assistance for Physical Action Failures in LLM-based Multi-Robot Coordination
[2026] Toward ownership understanding of objects: active question generation with large language model and probabilistic generative model
DOI: https://doi.org/10.1007/s10015-026-01116-7
[2026] Continuous Symbol Emergence via Decentralized Bayesian Inference with Gaussian Processes
DOI: https://doi.org/10.1109/tcds.2026.3661019
[2025] Spatial Concepts-Based Prompts With Large Language Models for Robot Action Planning
DOI: https://doi.org/10.1109/access.2025.3647727

続きを表示（残り 47 件）

[2025] Take That for Me: Multimodal Exophora Resolution with Interactive Questioning for Ambiguous Out-of-View Instructions
DOI: https://doi.org/10.1109/ro-man63969.2025.11217563
[2024] Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game
DOI: https://doi.org/10.3389/frobt.2023.1290604
[2024] Compositionality and Generalization in Emergent Communication Using Metropolis-Hastings Naming Game
DOI: https://doi.org/10.1109/icdl61372.2024.10644635
[2024] Symbol Emergence and Representation Learning by Integrating GPLVM and Neural Network
DOI: https://doi.org/10.7210/jrsj.42.696
[2024] Interactive Learning System for 3D Semantic Segmentation with Autonomous Mobile Robots
DOI: https://doi.org/10.1109/sii58957.2024.10417237
[2024] ECRAP: Exophora Resolution and Classifying User Commands for Robot Action Planning by Large Language Models
DOI: https://doi.org/10.1109/irc63610.2024.00007
[2024] Real-World Instance-Specific Image Goal Navigation: Bridging Domain Gaps via Contrastive Learning
DOI: https://doi.org/10.1109/irc63610.2024.00032
[2024] Object Instance Retrieval in Assistive Robotics: Leveraging Fine-Tuned SimSiam with Multi-View Images Based on 3D Semantic Map
DOI: https://doi.org/10.1109/iros58592.2024.10802697
[2024] Pointing Frame Estimation With Audio-Visual Time Series Data for Daily Life Service Robots
DOI: https://doi.org/10.1109/smc54092.2024.10831649
[2024] Multimodal Continuous Symbol Emergence Using a Probabilistic Generative Model Based on Gaussian Processes
DOI: https://doi.org/10.1109/icdl61372.2024.10644473
[2024] Hierarchical path planning from speech instructions with spatial concept-based topometric semantic mapping
DOI: https://doi.org/10.3389/frobt.2024.1291426
[2024] Hippocampal formation-inspired global self-localization: quick recovery from the kidnapped robot problem from an egocentric perspective
DOI: https://doi.org/10.3389/fncom.2024.1398851
[2024] Emergence of Continuous Signals As Shared Symbols Through Emergent Communication
DOI: https://doi.org/10.1109/icdl61372.2024.10644981
[2023] Exophora Resolution of Linguistic Instructions with a Demonstrative based on Real-World Multimodal Information
DOI: https://doi.org/10.1109/ro-man57019.2023.10309487
[2023] Integrating probabilistic logic and multimodal spatial concepts for efficient robotic object search in home environments
DOI: https://doi.org/10.1080/18824889.2023.2283954
[2023] Multi-agent Reinforcement Learning with Emergent Communication using Discrete and Indifferentiable Message
DOI: https://doi.org/10.1109/iiai-aai-winter61682.2023.00073
[2023] Metropolis-Hastings algorithm in joint-attention naming game: experimental semiotics study
DOI: https://doi.org/10.3389/frai.2023.1235231
[2023] Lexical Acquisition from Audio-Visual Streams Using a Multimodal Recurrent State-Space Model
DOI: https://doi.org/10.1109/icdl55364.2023.10364429
[2023] Cross-Situational Word Learning in Disentangled Latent Space
DOI: https://doi.org/10.1109/icdl55364.2023.10364474
[2023] Lexical Acquisition with Cross-Situational Learning Based on Mutual Segmentation of Sentences and Multi-Attribute Sensory Information
DOI: https://doi.org/10.1109/icdl55364.2023.10364383
[2023] Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
DOI: https://doi.org/10.3389/frai.2023.1229127
[2023] Active Semantic Mapping for Household Robots: Rapid Indoor Adaptation and Reduced User Burden
DOI: https://doi.org/10.1109/smc53992.2023.10394143
[2023] Emergent communication through Metropolis-Hastings naming game with deep generative models
DOI: https://doi.org/10.1080/01691864.2023.2260856
[2023] Unsupervised Multimodal Word Discovery Based on Double Articulation Analysis With Co-Occurrence Cues
DOI: https://doi.org/10.1109/tcds.2023.3307555
[2023] Active exploration based on information gain by particle filter for efficient spatial concept formation
DOI: https://doi.org/10.1080/01691864.2023.2225175
[2023] Maximum isotope accumulation in the retrosplenial cortex during amnesia attack and its temporal change suggest cortical spreading depression as a pathophysiology of patients with transient global amnesia
DOI: https://doi.org/10.1002/ima.22907
[2023] Inferring Place-Object Relationships by Integrating Probabilistic Logic and Multimodal Spatial Concepts
DOI: https://doi.org/10.1109/sii55687.2023.10039318
[2022] Hippocampal formation-inspired probabilistic generative model
DOI: https://doi.org/10.1016/j.neunet.2022.04.001
[2022] A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots
DOI: https://doi.org/10.1016/j.neunet.2022.02.026
[2022] Map completion from partial observation using the global structure of multiple environmental maps
DOI: https://doi.org/10.1080/01691864.2022.2029762
[2022] Multiagent multimodal categorization for symbol emergence: emergent communication via interpersonal cross-modal inference
DOI: https://doi.org/10.1080/01691864.2022.2029721
[2022] Neural Network-based Motion Feasibility Checker to Validate Instructions in Rearrangement Tasks before Execution by Robots
DOI: https://doi.org/10.1109/sii52469.2022.9708602
[2022] Extending HoloGAN by Embedding Image Content into Latent Vectors for Novel View Synthesis
DOI: https://doi.org/10.1109/sii52469.2022.9708823
[2022] Brain-inspired probabilistic generative model for double articulation analysis of spoken language
DOI: https://doi.org/10.1109/icdl53763.2022.9962216
[2022] Symbol Emergence as Inter-personal Categorization with Head-to-head Latent Word
DOI: https://doi.org/10.1109/icdl53763.2022.9962227
[2022] Multimodal Object Categorization with Reduced User Load through Human-Robot Interaction in Mixed Reality
DOI: https://doi.org/10.1109/iros47612.2022.9981374
[2022] Automatic selection of coordinate systems for learning relative and absolute spatial concepts
DOI: https://doi.org/10.3389/frobt.2022.904751
[2021] Autonomous planning based on spatial concepts to tidy up home environments with service robots
[2021] Teaching System for Multimodal Object Categorization by Human-Robot Interaction in Mixed Reality
DOI: https://doi.org/10.1109/ieeeconf49454.2021.9382607
[2021] Teaching System for Multimodal Object Categorization by Human-Robot Interaction in Mixed Reality
[2021] Simultaneous Learning of Relative and Absolute Spatial Concepts without Any Prior Distinction
DOI: https://doi.org/10.1109/gcce53005.2021.9621937
[2021] Unsupervised phoneme and word discovery method utilizing co-occurrence of object and phonological information
[2021] Semiotically adaptive cognition: toward the realization of remotely-operated service robots for the new normal symbiotic society
DOI: https://doi.org/10.1080/01691864.2021.1928552
[2021] Unsupervised lexical acquisition of relative spatial concepts using spoken user utterances
DOI: https://doi.org/10.1080/01691864.2021.2007168
[2021] Hierarchical Bayesian model for the transfer of knowledge on spatial concepts based on multimodal information
DOI: https://doi.org/10.1080/01691864.2021.2004224
[2021] StarGAN-VC+ASR: StarGAN-Based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
DOI: https://doi.org/10.21437/interspeech.2021-492
[2021] Attachment of a cap-like anion with a Lewis base moiety to a coordination cage and enhancement of the guest inclusion

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（57 件）

科研費（0 件）

所属学会・役職（0 件）