Maki Sugimoto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maki Sugimoto has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
- Masahiko Inami
University of Tokyo, Tokyo, Japan and Research Center for Advanced Science and Technology, Tokyo, Japan
7 shared publications - Katsutoshi Masai
Kyushu University, Japan
6 shared publications - Ryota Kondo
The University of Tokyo, Tokyo, Japan
6 shared publications - Fumihiko Nakamura
Ritsumeikan University, Osaka, Japan
3 shared publications - Gun A. Lee
IVE, Adelaide University, Adelaide, SA, Australia
3 shared publications - Mark Billinghurst
Empathic Computing Laboratory, Adelaide University, Mawson Lakes, South Australia, Australia
3 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
The Future of AI & XR: How Will AI Reshape the Spatial Computing Pipeline?
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessThe Future of AI & XR: How Will AI Reshape the Spatial Computing Pipeline?
- Open Access
- 16 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
The Effect of Avatar Appearance on the Sense of Body Ownership and Agency During the Parallel Control of Multiple Bodies
- 16 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessThe Effect of Avatar Appearance on the Sense of Body Ownership and Agency During the Parallel Control of Multiple Bodies
- Open Access
- 12 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 16 (4) , 1-35
LLiBTree: An Assessment of Usability and Trust of LLM-integrated Behavior Tree Nodes for Robot Programming
As robot programming becomes increasingly important in enabling non-expert users to customize autonomous systems across domains such as manufacturing, healthcare, and service industries, there is a growing demand for methods that are both intuitive and support users’ perceived trust. While natural language programming (NLP) lowers the barrier to entry by allowing users to describe robot behavior in everyday language, it often lacks structural transparency—particularly when paired with opaque deep learning models. To address this challenge, we present LLiBTree, a novel robot programming framework that integrates Large Language Models (LLMs) directly into Behavior Trees (BTs) as executable nodes. This approach allows users to iteratively define and refine robot behavior via natural language while preserving the modularity and clarity of visual programming. By embedding the LLM within the BT, users can generate and replace sub-trees in response to natural language instructions, enabling a seamless blend of language-based flexibility and structured visual logic. We evaluate LLiBTree through a controlled user study, comparing it with both natural language-only and conventional visual programming methods. The results show that the PreGeneratedLLiBTree condition yields significantly higher perceived trust, while LLiBTree conditions achieve usability that is non-inferior to natural language-only programming and improve users’ sense of agency, suggesting that LLiBTree offers a practical approach for end-user robot programming.
- 12 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 16 (4) , 1-35
Open AccessLLiBTree: An Assessment of Usability and Trust of LLM-integrated Behavior Tree Nodes for Robot Programming
As robot programming becomes increasingly important in enabling non-expert users to customize autonomous systems across domains such as manufacturing, healthcare, and service industries, there is a growing demand for methods that are both intuitive and support users’ perceived trust. While natural language programming (NLP) lowers the barrier to entry by allowing users to describe robot behavior in everyday language, it often lacks structural transparency—particularly when paired with opaque deep learning models. To address this challenge, we present LLiBTree, a novel robot programming framework that integrates Large Language Models (LLMs) directly into Behavior Trees (BTs) as executable nodes. This approach allows users to iteratively define and refine robot behavior via natural language while preserving the modularity and clarity of visual programming. By embedding the LLM within the BT, users can generate and replace sub-trees in response to natural language instructions, enabling a seamless blend of language-based flexibility and structured visual logic. We evaluate LLiBTree through a controlled user study, comparing it with both natural language-only and conventional visual programming methods. The results show that the PreGeneratedLLiBTree condition yields significantly higher perceived trust, while LLiBTree conditions achieve usability that is non-inferior to natural language-only programming and improve users’ sense of agency, suggesting that LLiBTree offers a practical approach for end-user robot programming.
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Proxemics of Physical AI: Opportunities and Challenges of Augmenting Intimate, Personal, Social, and Public Spaces
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessProxemics of Physical AI: Opportunities and Challenges of Augmenting Intimate, Personal, Social, and Public Spaces
- Open Access
- 3 September 2026
- Published by Elsevier in Computers & Graphics
- Vol. 140
Photo-reflective sensing for parametric 3D facial expression reconstruction in head-mounted display
- 3 September 2026
- Published by Elsevier in Computers & Graphics
- Vol. 140
Open AccessPhoto-reflective sensing for parametric 3D facial expression reconstruction in head-mounted display
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 748-750
User-Centric Spatial Referring for Tabletop RobotManipulation with MR Grounding and LLMs
Interpreting perspective-dependent spatial referring expressions is a key challenge for intuitive human–robot interaction, as users naturally communicate in egocentric terms. We present an interactive spatial grounding system that integrates mixed reality (MR) sensing with LLM-based reasoning to translate free-form spatial language into actionable robot targets. Using a unified table-centric representation, the backend computes viewpoint- and robot-relative spatial features and ranks candidate targets under underspecified constraints. We further apply confirmation-gated execution, which visualizes the current target hypothesis in MR and triggers robot motion only after explicit user confirmation. Overall, this demo focuses on enabling robots to understand user-centric, perspective-dependent spatial references by grounding them in MR for tabletop manipulation.
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 748-750
Open AccessUser-Centric Spatial Referring for Tabletop RobotManipulation with MR Grounding and LLMs
Interpreting perspective-dependent spatial referring expressions is a key challenge for intuitive human–robot interaction, as users naturally communicate in egocentric terms. We present an interactive spatial grounding system that integrates mixed reality (MR) sensing with LLM-based reasoning to translate free-form spatial language into actionable robot targets. Using a unified table-centric representation, the backend computes viewpoint- and robot-relative spatial features and ranks candidate targets under underspecified constraints. We further apply confirmation-gated execution, which visualizes the current target hypothesis in MR and triggers robot motion only after explicit user confirmation. Overall, this demo focuses on enabling robots to understand user-centric, perspective-dependent spatial references by grounding them in MR for tabletop manipulation.
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 578-588
SyncArms: Gaze-Driven Implicit Assistive Control for Parallel Robot Arms in Distributed Environments
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 578-588
Open AccessSyncArms: Gaze-Driven Implicit Assistive Control for Parallel Robot Arms in Distributed Environments
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
3D Human Pose Estimation Using Ultra-low Resolution Thermal Images
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open Access3D Human Pose Estimation Using Ultra-low Resolution Thermal Images
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 432-438
Facial Gesture Classification with Few-shot Learning Using Limited Calibration Data from Photo-reflective Sensors on Smart Eyewear
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 432-438
Open AccessFacial Gesture Classification with Few-shot Learning Using Limited Calibration Data from Photo-reflective Sensors on Smart Eyewear
- Open Access
- 23 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Necomimi illusion: Generating Ownership of Cat Ears through Haptic Feedback via Hair
- 23 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessNecomimi illusion: Generating Ownership of Cat Ears through Haptic Feedback via Hair