Agentic AI Research Team
Team Outline
Our team aims to develop AI technologies that integrate data-driven and knowledge-driven AI to understand the Semantics of human activities.
Human activities in daily living spaces are highly individualized and composed of various elements, including people, objects, and their interactions. Interpreting these highly individualized situations still depends heavily on the human who knows about the environment, tasks, and human activities. Providing this knowledge to an AI system to support daily life is still difficult.
For example, general-purpose robots or embodied-AI systems for home use require: 1) Knowledge of the physical characteristics of the individual living in the house and the indoor environment. 2) Knowledge of actions in performing the tasks (such as older adults support or young child care). 3) General knowledge of the human body, accident risk reports, and safety guidelines. 4) Service procedures. 5) Common knowledge of objects and events, etc.
The system must incorporate this multi-layered heterogeneous daily life knowledge into the inference and recognition process by linking it with information in different modalities, such as images and natural language cascading in multiple time and space occurrences.
To capture and integrate the multi-modality and heterogeneity nature of these data and knowledge, we conduct research on Knowledge Graphs, Machine Learning, Natural Language Processing, Embodied-AI, and Human-Agent-Interaction research.
DKIRT Youtube channel
Event Information
■ Daily Activity data generation in Cyberspace for Semantic AI technology and HRI simulation
We are hosting the Knowledge Graph Reasoning Challenge for Social Issues (KGRC4SI), where the task is to identify the risks in daily living activities to support the safety of older adults in their homes.The Challenge will provide two types of data sets generated by VirtualHome2KG, (1) the Video data recorded by a virtual space simulator reproducing daily life, and (2) Knowledge graphs representing human actions, object states, and relationships between scenes in the video
■ the event:https://challenge.knowledge-graph.jp/2022/ (In Japanese)
■ dataset: https://github.com/KnowledgeGraphJapan/KGRC-RDF/tree/kgrc4si(dataset labels are in English)
■ The 1st International Knowledge Graph Reasoning Challenge 2023
"In the challenge, the task is to estimate the culprits with a reasonable explanation using a dataset of knowledge graphs representing eight Sherlock Holmes mystery stories. "(cite: https://ikgrc.org/2023/)
■ the workshop: https://ikgrc.org/2023/
■ dataset:https://github.com/KnowledgeGraphJapan/KGRC-RDF/tree/ikgrc2023

Ken Fukuda,
Team Leader
Information
Dr. Wiradee Imrattanatrai, Dr. Masaki Asada, Dr. Ken Fukuda, Research Team Leader, along with Carnegie Mellon University will present the joint research paper "A Video-grounded Dialogue Dataset and Metric for Event-driven Activities" as an oral presentation at AAAI2025 (The 39th Annual AAAI Conference on Artificial Intelligence), one of the largest AI conferences in the world. (The paper acceptance rate is 23.4%, with 19.8% accepted for oral presentation)
DKIRT is featured in the IROS TV 'Thought Leadership' at IROS2024, one of the largest and most influential international conference in robotics.
https://www.youtube.com/watch?v=655DcfEtlzE
Our presentation "S Egami, S Nishimura and K Fukuda, VirtualHome2KG: Constructing and Augmenting Knowledge Graphs of Daily Activities Using Virtual Space" won the Best Poster award at ISWC2021, which is one of the top conferences in the Knowledge Graph domain.
https://twitter.com/iswc_conf/status/1453752712454094851?s=20
List of Publications
Mitsuji, Fumiya, Sudesna Chakraborty, Takeshi Morita, Shusaku Egami, Takanori Ugai, and Ken Fukuda. "Entity Linking for Wikidata Using Large Language Models and Wikipedia Links." 2024 Twelfth International Symposium on Computing and Networking Workshops (CANDARW),pp144-49,(2024)
Egami, Shusaku, Takanori Ugai, and Ken Fukuda. :Compressing Multi-Modal Temporal Knowledge Graphs of Videos.: Edited by Lorena Etcheverry, Vanessa Lopez Garcia, Francesco Osborne, and Romana Pernisch. Proceedings of the ISWC 2024 Posters, Demos and Industry Tracks: From Novel Ideas to Industrial Practice, CEUR Workshop Proceedings,pp3828,(2024)
Anaguchi, Fumikatsu, Sudesna Chakraborty, Takeshi Morita, Shusaku Egami, Takanori Ugai, and Ken Fukuda. :Reasoning and Justification System for Domestic Hazardous Behaviors Based on Knowledge Graph of Daily Activities and Retrieval-Augmented Generation.: 2024 Twelfth International Symposium on Computing and Networking (CANDAR),pp11-20,(2024)
Researcher Profile
Photo | Name and role | Field of Expertise | E-mail address HP |
---|---|---|---|
![]() |
Team Leader Masahiro Hamasaki |
Social Media Analysis, Web Mining, Online Community, Knowledge Sharing | |
![]() |
Senior Researcher Sohrab Golam Mohammad |
Natural Language Processing, Information Extraction, Data Mining, Knowledge Graph | |
![]() |
Senior Researcher The University of Electro-Communications, Collaborative Associate Professor Shusaku Egami |
Semantic Web, Ontology, Knowledge Graph Embedding | |
![]() |
Researcher Wiradee Imrattanatrai |
Information Retrieval, Web Search, Data Mining, Knowledge Graphs, and Natural Language Processing | |
![]() |
Researcher Masaki Asada |
Natural Language Processing, Knowledge Graphs | |
![]() |
Researcher Lucie Kunitomo-Jacquin |
Machine learning, Trustworthy AI, Dempster–Shafer theory, Causality | |
![]() |
Researcher Aoi Ohta |
Knowledge Graph Embedding | |
![]() |
Invited Senior Researcher Makoto Miwa |
Natural Language Processing, Information Extraction, Knowledge Graph | |
![]() |
Invited Senior Researcher Professor Takeshi Morita |
Semantic Web, Ontology Engineering, Knowledge Engineering | |
![]() |
Research Assistant Fumikatsu Anaguchi |
Natural Language Processing, Knowledge Engineering | |
![]() |
Research Assistant Soushi Gotou |
Natural Language Processing, Knowledge Engineering | |
![]() |
Research Assistant Fumiya Mitsuji |
Natural Language Processing, Knowledge Engineering | |
Research Assistant Akikazu Kimura |
Natural Language Processing,LLM agent |