Naoya Takeishi
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
Naoya Takeishi has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Takehisa Yairi
The University of Tokyo
6 shared publications - Koichi Hori
Department of Aeronautics and Astronautics, The University of Tokyo
2 shared publications - Akira Tanimoto
NEC Corporation
1 shared publication - Chun Fui Liew
The University of Tokyo
1 shared publication - Fuyuto Terui
Graduate School of Engineering, Kanagawa Institute of Technology, Atsugi 243-0292, Japan
1 shared publication - Gengyu Li
Research Center for Advanced Science and Technology (RCAST) The University of Tokyo
1 shared publication
Latest Publications
- Open Access
- 12 September 2026
- Published by Elsevier in Mechanism and Machine Theory
- Vol. 230
Dynamics-based forward kinematics estimation for Stewart platform using unscented Kalman filter with extended actuator observations
- 12 September 2026
- Published by Elsevier in Mechanism and Machine Theory
- Vol. 230
Open AccessDynamics-based forward kinematics estimation for Stewart platform using unscented Kalman filter with extended actuator observations
- Open Access
- 13 January 2026
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 5 (1)
Data-driven Anomaly Detection for Quadcopter UAV Indoor Flight Platform
Ensuring the safe operation of unmanned aerial vehicles (UAVs) requires timely and accurate detection of anomalies that may indicate system faults or external disturbances. In this study, we propose a data-driven approach for unsupervised anomaly detection in UAVs, leveraging a newly developed multimodal dataset that includes synchronized telemetry, sensor measurements, motion capture data, and pilot inputs. Our method learns representations of normal UAV behavior from healthy flight records and is applied to fault-injection scenarios to identify potential anomalies. Preliminary results on experimental data suggest that the approach can capture subtle deviations from expected behavior across multiple data modalities, including flight dynamics and environmental feedback. This work lays the foundation for data-driven UAV health monitoring through unsupervised learning. It complements our publicly released dataset and analysis tools and aims to facilitate broader research on autonomous anomaly detection, early fault diagnostics, and the development of resilient UAV systems in safety-critical applications.
- 13 January 2026
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 5 (1)
Open AccessData-driven Anomaly Detection for Quadcopter UAV Indoor Flight Platform
Ensuring the safe operation of unmanned aerial vehicles (UAVs) requires timely and accurate detection of anomalies that may indicate system faults or external disturbances. In this study, we propose a data-driven approach for unsupervised anomaly detection in UAVs, leveraging a newly developed multimodal dataset that includes synchronized telemetry, sensor measurements, motion capture data, and pilot inputs. Our method learns representations of normal UAV behavior from healthy flight records and is applied to fault-injection scenarios to identify potential anomalies. Preliminary results on experimental data suggest that the approach can capture subtle deviations from expected behavior across multiple data modalities, including flight dynamics and environmental feedback. This work lays the foundation for data-driven UAV health monitoring through unsupervised learning. It complements our publicly released dataset and analysis tools and aims to facilitate broader research on autonomous anomaly detection, early fault diagnostics, and the development of resilient UAV systems in safety-critical applications.
- Open Access
- 1 January 2026
- Published by Japan Society for Aeronautical and Space Sciences in TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES
- Vol. 69 (1) , 9-18
High-fidelity Aircraft Trajectory Generation Using a Flow-based Generative Model
Aircraft trajectory generation is one of the key technologies for realizing and researching a highly efficient air traffic system. Fast-time simulations are used for the initial evaluation of newly proposed operational concepts, and the employed scenarios must be faithful to actual aircraft operations and include a wide range of possible future events. In addition, since aircraft trajectories are influenced by numerous complex factors, incorporating these factors into the generation process is essential to improve the fidelity of the generated trajectories. This study employed a deep generative model to capture these factors, with surrounding traffic conditions selected as a representative example. In particular, a flow-based generative model was employed to obtain the generation probability of the trajectory to allow evaluation based on the probability of events occurring in the simulation. The generated trajectories were confirmed to be consistent with the operational flight envelope and surrounding traffic using publicly available track data.
- 1 January 2026
- Published by Japan Society for Aeronautical and Space Sciences in TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES
- Vol. 69 (1) , 9-18
Open AccessHigh-fidelity Aircraft Trajectory Generation Using a Flow-based Generative Model
Aircraft trajectory generation is one of the key technologies for realizing and researching a highly efficient air traffic system. Fast-time simulations are used for the initial evaluation of newly proposed operational concepts, and the employed scenarios must be faithful to actual aircraft operations and include a wide range of possible future events. In addition, since aircraft trajectories are influenced by numerous complex factors, incorporating these factors into the generation process is essential to improve the fidelity of the generated trajectories. This study employed a deep generative model to capture these factors, with surrounding traffic conditions selected as a representative example. In particular, a flow-based generative model was employed to obtain the generation probability of the trajectory to allow evaluation based on the probability of events occurring in the simulation. The generated trajectories were confirmed to be consistent with the operational flight envelope and surrounding traffic using publicly available track data.
- 1 December 2023
- Published by Elsevier in Neural Networks
- Vol. 171, 40-52
Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
- 1 December 2023
- Published by Elsevier in Neural Networks
- Vol. 171, 40-52
Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
- 2 May 2022
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Applied Dynamical Systems
- Vol. 21 (2) , 1030-1058
Discriminant Dynamic Mode Decomposition for Labeled Spatiotemporal Data Collections
Extracting coherent patterns is one of the standard approaches toward understanding spatiotemporal data. Dynamic mode decomposition (DMD) is a powerful tool for extracting coherent patterns, but the original DMD and most of its variants do not consider label information, which is often available as side information of spatiotemporal data. In this work, we propose a new method for extracting distinctive coherent patterns from labeled spatiotemporal data collections such that they contribute to major differences in a labeled set of dynamics. We achieve such pattern extraction by incorporating discriminant analysis into DMD. To this end, we define a kernel function on subspaces spanned by sets of dynamic modes and develop an objective to take both reconstruction goodness as DMD and class-separation goodness as discriminant analysis into account. We illustrate our method using a synthetic dataset and several real-world datasets. The proposed method can be a useful tool for exploratory data analysis for understanding spatiotemporal data.
- 2 May 2022
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Applied Dynamical Systems
- Vol. 21 (2) , 1030-1058
Discriminant Dynamic Mode Decomposition for Labeled Spatiotemporal Data Collections
Extracting coherent patterns is one of the standard approaches toward understanding spatiotemporal data. Dynamic mode decomposition (DMD) is a powerful tool for extracting coherent patterns, but the original DMD and most of its variants do not consider label information, which is often available as side information of spatiotemporal data. In this work, we propose a new method for extracting distinctive coherent patterns from labeled spatiotemporal data collections such that they contribute to major differences in a labeled set of dynamics. We achieve such pattern extraction by incorporating discriminant analysis into DMD. To this end, we define a kernel function on subspaces spanned by sets of dynamic modes and develop an objective to take both reconstruction goodness as DMD and class-separation goodness as discriminant analysis into account. We illustrate our method using a synthetic dataset and several real-world datasets. The proposed method can be a useful tool for exploratory data analysis for understanding spatiotemporal data.
- Open Access
- 1 January 2019
- Published by Japan Society for Aeronautical and Space Sciences in TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES, AEROSPACE TECHNOLOGY JAPAN
- Vol. 17 (2) , 244-252
Visualization Methods for Spacecraft Telemetry Data Using Change-Point Detection and Clustering
For secure operation of spacecraft, automatic or assistive health monitoring systems utilizing telemetry data are important. However, it is difficult to utilize them comprehensively because they consist of myriad heterogeneous variables. Although various monitoring systems focusing on only a few variables or homogeneous variables have been suggested, a definitive method to deal with the relationship among multiple heterogeneous variables has not yet. This paper proposes a new visualization framework that aims to show the correlation rules underlying multiple variables of spacecraft telemetry data. The proposed framework consists of a change-point detection algorithm based on subspace identification, clustering methods using dimensionality reduction, and a visualization method using heatmaps. In experiments conducted with real telemetry data obtained from JAXA spacecraft SDS-4, the proposed framework demonstrated effective visualizations that reflected the correlations among variables expected from mechanical characteristics of the satellite. Despite differences in scales and/or units, this framework succeeded in visualizing dynamic correlations not only among continuous variables but also among continuous and discrete variables. This framework can be utilized as an initial stage of anomaly detection focusing on the relationship among multiple variables, as well as a method to perceive the overall state of the spacecraft at a glance.
- 1 January 2019
- Published by Japan Society for Aeronautical and Space Sciences in TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES, AEROSPACE TECHNOLOGY JAPAN
- Vol. 17 (2) , 244-252
Open AccessVisualization Methods for Spacecraft Telemetry Data Using Change-Point Detection and Clustering
For secure operation of spacecraft, automatic or assistive health monitoring systems utilizing telemetry data are important. However, it is difficult to utilize them comprehensively because they consist of myriad heterogeneous variables. Although various monitoring systems focusing on only a few variables or homogeneous variables have been suggested, a definitive method to deal with the relationship among multiple heterogeneous variables has not yet. This paper proposes a new visualization framework that aims to show the correlation rules underlying multiple variables of spacecraft telemetry data. The proposed framework consists of a change-point detection algorithm based on subspace identification, clustering methods using dimensionality reduction, and a visualization method using heatmaps. In experiments conducted with real telemetry data obtained from JAXA spacecraft SDS-4, the proposed framework demonstrated effective visualizations that reflected the correlations among variables expected from mechanical characteristics of the satellite. Despite differences in scales and/or units, this framework succeeded in visualizing dynamic correlations not only among continuous variables but also among continuous and discrete variables. This framework can be utilized as an initial stage of anomaly detection focusing on the relationship among multiple variables, as well as a method to perceive the overall state of the spacecraft at a glance.
- Open Access
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
- p. 516-520
Dynamic and Static Topic Model for Analyzing Time-Series Document Collections
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
- p. 516-520
Open AccessDynamic and Static Topic Model for Analyzing Time-Series Document Collections
- Open Access
- 1 January 2015
- Published by Japan Society for Aeronautical and Space Sciences in TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES
- Vol. 58 (1) , 45-53
Evaluation of Interest-region Detectors and Descriptors for Automatic Landmark Tracking on Asteroids
- 1 January 2015
- Published by Japan Society for Aeronautical and Space Sciences in TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES
- Vol. 58 (1) , 45-53
Open AccessEvaluation of Interest-region Detectors and Descriptors for Automatic Landmark Tracking on Asteroids