出版者・発行元：SICE Journal of Control Measurement and System Integration  

Soil compaction is a critical element in construction, as it directly influences the quality and durability of structures. Vibratory rollers are widely employed to enhance ground stiffness, with traditional methods emphasizing the number of compaction cycles. However, these methods require preliminary testing to establish the relationship between compaction cycles and ground stiffness, failing to account for actual ground conditions that vary by location. Continuous compaction control (CCC), utilizing accelerometers mounted on vibratory rollers, has been introduced as a more effective quantitative evaluation method tailored to real-world ground conditions. This approach measures the distortion rate of the acceleration waveform generated by the vibratory roller. Nevertheless, since the accelerometer is affixed directly to the drum, the measurement is inevitably affected by noise from the vibration source. To address this limitation, this study proposed an innovative ground stiffness evaluation method employing multiple accelerometers installed on the ground surface. This proposed technique is significantly less influenced by noise directly caused by the vibratory roller. Experimental results demonstrated that the proposed method offers superior suitability for quantitatively assessing ground stiffness. By adopting this method, a more precise evaluation of ground stiffness can streamline quality control processes and minimize the need for rework.

DOI： 10.1080/18824889.2026.2643014

Web of Science

Scopus

記述言語：英語   出版者・発行元：富士技術出版株式会社  

<p>This paper investigates state estimation for continuum robotic fingers in feature-sparse and dynamic in-hand manipulation environments. Continuum fingers, inspired by continuum robots, offer enhanced flexibility and wider reachable workspace compared with conventional rigid-link fingers to enable grasping and manipulation tasks. However, they lack encoder-based joint angle measurements, making it difficult to determine fingertip positions, particularly under external forces during contact. This limitation hinders precision grasping and prevents the full exploitation of their high dexterity. To address this challenge, we developed a simultaneous localization and mapping framework for continuum fingers using proximity sensors. Unlike conventional simultaneous localization and mapping that assumes feature-rich environments, grasping scenarios present feature-sparse conditions with limited environmental information. We propose an estimator that fuses proximity sensing with a constant-curvature kinematic prior by replacing encoder angles with virtual joint angles. The key idea is to leverage the designed in-hand elements, namely opposing fingers and the palm, as stable reference geometry. Simulations demonstrate that the proposed estimator outperforms a kinematics-only baseline by suppressing bias and reducing position error. Three-dimensional contoured palms enhance observability, with a composite wavy palm yielding the smallest errors without temporal drift. These findings indicate that the designed in-hand geometry combined with temporal map management enables effective state estimation for continuum fingers in feature-sparse and dynamic grasping scenarios.</p>

DOI： 10.20965/jrm.2026.p0772

Web of Science

CiNii Research

記述言語：英語   出版者・発行元：富士技術出版株式会社  

High-speed sensors, such as high-speed cameras and optical proximity sensors, enable the detailed temporal measurements of physical phenomena that exceed the dynamic capabilities of conventional industrial robots. However, effectively leveraging this sensor information for robot motion planning remains challenging be-cause of the temporal-scale gap between sensors and robots. This paper proposes a motion planning method that extracts the task-relevant meta-information of tar-get phenomena from high-speed sensor data and generates feasible trajectories by considering robot constraints. The information extraction process identifies task-relevant characteristics from high-speed sensor data. To integrate heterogeneous sensor information and enable trajectory adaptation, we employed multiple virtual-dynamics-based control (MVDC), which can asynchronously integrate heterogeneous sensors with different measurement principles. To validate the proposed method, we conducted a case study in which a conventional industrial manipulator grasped a pendulum at its equilibrium point, the most challenging position. The system integrated global measurements from a 1 kHz high-speed camera with local measurements from proximity sensors using MVDC to predict the pendulum period and optimal grasping timing. Experimental results demonstrated that the proposed method enables successful grasping by bridging the temporal-scale gap between high-speed sensors and conventional robots through information integration.

DOI： 10.20965/jrm.2026.p0785

Web of Science

Scopus

CiNii Research

掲載種別：研究論文（学術雑誌）  

DOI： 10.48550/arXiv.2603.12663

researchmap

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2026 IEEE SICE International Symposium on System Integration Sii 2026  

Mobile robot navigation in dynamic environments that contain pedestrians is one of the key challenges in the development of autonomous mobile service robots. This field, known as social navigation, has seen significant research progress using reinforcement learning approaches. In recent years, numerous diffusion-based reinforcement learning methods capable of generating diverse actions have been proposed. However, compared to conventional reinforcement learning approaches, the diffusion model's slow generation process presents a significant barrier to real-time processing. To address this, we propose a method for knowledge distillation of conditional diffusion models by combining Gaussian Prior with Flow Matching to enable faster action generation in dynamic environments. Experiments using a crowd navigation benchmark in simulation environments demonstrate that a significant reduction of the time required for action generation is possible while maintaining nearly the same performance as teacher models.

DOI： 10.1109/SII64115.2026.11404587

Scopus

researchmap

その他リンク： https://dblp.org/db/conf/sii/sii2026.html#TomitaMHNK26

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2026 IEEE SICE International Symposium on System Integration Sii 2026  

High temporal resolution sensors have become increasingly widespread in recent years, enabling detailed and accurate observation of fast physical phenomena and contributing to the understanding of their essential properties. However, a fundamental challenge remains in bridging the temporal resolution gap between such sensors and conventional industrial robots. Typical high-speed visual feedback control require all system components to operate at high speed, inherently restricting their applicability to phenomena within the robot's dynamic capabilities. As a result, valuable high-speed sensing data often cannot be fully utilized, especially when target phenomena evolve faster than the robot can respond. This study proposes a novel motion planning method that extracts essential, task-relevant information from high-speed sensor data to bridge the timescale gap between sensors and robots. Based on the extracted information, feedforward control is executed with consideration of the robot's motion characteristics. To explore practical solutions, we developed an integrated system combining a high-speed camera and a proximity sensor module―both with existing applications in robotics―with a general-purpose industrial robot and gripper. A case study involving the grasping of a pendulum-swinging object by a low-speed robot demonstrates the effectiveness of the proposed approach in utilizing high-frequency measurements for tasks beyond the limits of conventional feedback control.

DOI： 10.1109/SII64115.2026.11404605

Scopus

researchmap

その他リンク： https://dblp.org/db/conf/sii/sii2026.html#KorekiCANT26

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2026 IEEE SICE International Symposium on System Integration Sii 2026  

Grasping soft and individualized food and agricultural products without causing damage is a significant challenge in robotics. This task requires balancing two conflicting demands: applying sufficient force to lift the object and avoiding excessive force that could cause damage. Conventional approaches include learning-based manipulation and sequential control based on slip detection. However, the former requires prior training, while the latter takes time to adjust the grasping force. Therefore, these methods are not suitable for environments where object properties change frequently or for high-throughput operations. To address these issues, we propose a parameter adaptation method for deformation suppression that does not require learning and enables high-speed processing. The proposed method reduces the grasping force according to object deformation, which is detected by optical proximity sensors. A key benefit of optical proximity sensors is high-speed data acquisition, which enables real-time adjustment of grasping force without stopping the motion, leading to faster task completion. Furthermore, the deformation information obtained from the proximity sensor is converted into a virtual force, and the grasping force is adjusted based on the virtual dynamics framework. This enables seamless integration with pre-grasp control strategies that gently approach the object.

DOI： 10.1109/SII64115.2026.11404480

Scopus

researchmap

その他リンク： https://dblp.org/db/conf/sii/sii2026.html#TokiwaASNT26

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2026 IEEE SICE International Symposium on System Integration Sii 2026  

Contact task execution in unknown environments is fundamental to robotic applications, requiring three essential functions: accurate position tracking, safe contact establishment, and achievement of desired contact force. In our previous work, the Multiple Virtual Dynamics-based Force Control (MVDFC) was proposed. This method seamlessly integrates these three functions; however, several challenges remain when considering practical force control. The first challenge is that time delays in the force sensor can destabilize the control system. The second challenge is that loss of contact with the environment during a force control task can result in acceleration of robot and collisions with the environment. These two challenges are commonly encountered in various force control methods. Here, a key feature of MVDFC is its flexibility, allowing the motion of virtual objects in each virtual dynamics to be independently designed. Therefore, by leveraging this flexibility, it is possible to overcome the two challenges without compromising the three functions. This study proposes a direction for parameter design to address the above issues, and its effectiveness is demonstrated through both simulations and experiments.

DOI： 10.1109/SII64115.2026.11404551

Scopus

researchmap

その他リンク： https://dblp.org/db/conf/sii/sii2026.html#KanekiyoANT26

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2026 IEEE SICE International Symposium on System Integration Sii 2026  

Soft grippers have attracted attention as a safe and adaptable means of grasping fragile or irregularly shaped objects. However, challenges remain in performing advanced tasks such as in-hand manipulation. This study proposes a soft-rigid hybrid two-finger hand that integrates position-controlled motors and flexible links, based on a design concept that combines the mechanical properties of rigid and flexible components. The proposed hand directly drives the flexible links using position-controlled motors, enabling active control of the interaction between the flexible structure and the environment. Leveraging this feature, a position-based force control strategy is introduced, in which fingertip positions are adjusted to shift the equilibrium of the flexible links, indirectly modulating the contact force through their passive deformation. The effectiveness of the proposed method is validated through simulations of object grasping tasks, demonstrating stable and dexterous in-hand manipulation.

DOI： 10.1109/SII64115.2026.11404728

Scopus

researchmap

その他リンク： https://dblp.org/db/conf/sii/sii2026.html#KatamineANT26

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2026 IEEE SICE International Symposium on System Integration Sii 2026  

This paper studies state estimation for continuum robotic fingers during in-hand manipulation, where accurate pose estimation relative to the environment is required in feature-sparse scenes. To address this requirement, we adopt a SLAM-based formulation that estimates the robot pose and a local map from exteroceptive sensing. Continuum fingers lack encoder-based joint angle measurements, while conventional SLAM assumes feature-rich environments that are rarely available inside the hand. We propose a SLAM-based estimator that fuses exteroceptive proximity sensing with a constant-curvature kinematic prior by replacing encoder angles with virtual joint angles from the model. The key idea is to leverage designed in-hand self-body elements, namely the opposing fingers and the palm, as stable reference geometry to maintain observability in feature-spares environments. We evaluate our method through free motion and grasping simulations, and analyze the effect of presence and shape of the palm on estimation accuracy. The proposed estimator outperforms a kinematics-only baseline by suppressing bias, reducing a position error of an end effector, and improving map quality. We demonstrate that three-dimensional contoured palms enhance observability, and a composite wavy palm yields the smallest errors without temporal drift. These results indicate that designed in-hand geometry enables effective state estimation for continuum fingers in feature-sparse grasping scenarios, supporting reliable in-hand manipulation.

DOI： 10.1109/SII64115.2026.11404608

Scopus

researchmap

その他リンク： https://dblp.org/db/conf/sii/sii2026.html#MoritaANT26

掲載種別：研究論文（学術雑誌）  

DOI： 10.48550/arXiv.2510.11817

researchmap

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings IEEE International Conference on Robotics and Automation  

Building LiDAR generative models holds promise as powerful data priors for restoration, scene manipulation, and scalable simulation in autonomous mobile robots. In recent years, approaches using diffusion models have emerged, significantly improving training stability and generation quality. Despite their success, diffusion models require numerous iterations of running neural networks to generate high-quality samples, making the increasing computational cost a potential barrier for robotics applications. To address this challenge, this paper presents R2Flow, a fast and high-fidelity generative model for LiDAR data. Our method is based on rectified flows that learn straight trajectories, simulating data generation with significantly fewer sampling steps compared to diffusion models. We also propose an efficient Transformer-based model architecture for processing the image representation of LiDAR range and reflectance measurements. Our experiments on unconditional LiDAR data generation using the KITTI-360 dataset demonstrate the effectiveness of our approach in terms of both efficiency and quality.

DOI： 10.1109/ICRA55743.2025.11127894

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/icra/icra2025.html#NakashimaLMIK25

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>In this study, we develop Pile-type Sensor Pods for monitoring conditions at civil engineering sites. The Pile-type Sensor Pod consists of a pile, two multi-core microcomputers, two 220° cameras, a GNSS receiver, and a vibration sensor. In this report, we have redesigned the housing for waterproofing. In addition, the accuracy of the data acquired by the vibration sensor was verified.</p>

DOI： 10.1299/jsmermd.2025.1a1-b05

CiNii Research

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Conference on Automation Science and Engineering  

Contact task execution in unknown environments is fundamental to robotic applications, requiring three essential capabilities: accurate position tracking, safe contact establishment, and achievement of desired contact force. While our previous study has demonstrated that combining admittance and impedance control in series enables accurate position tracking and safe contact, achieving desired contact force remains challenging due to environmental and robot dynamic uncertainties. This paper presents a novel force control methodology that integrates all three capabilities by introducing an additional admittance layer to the series admittance-impedance control framework. The key idea lies in the conversion of sensor information into continuous virtual object motion through virtual dynamics, enabling seamless transition from position to force tracking control without controller switching. This approach eliminates the need for direct feedback of raw sensor measurements to controllers while ensuring precise contact force achievement regardless of environmental or dynamic uncertainties. The effectiveness of the proposed method is validated through both numerical simulations using a 2-DOF manipulator model and experimental verification on a physical manipulator system.

DOI： 10.1109/CASE58245.2025.11164077

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/case/case2025.html#KanekiyoANT25

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Conference Proceedings IEEE International Conference on Systems Man and Cybernetics  

As global efforts to explore the Moon intensify, the need for high-quality 3D lunar maps becomes increasingly critical - particularly for long-distance missions such as NASA's Endurance mission concept, in which a rover aims to traverse 2,000 km across the South Pole-Aitken basin. Kaguya TC (Terrain Camera) images, though globally available at 10 m/pixel, suffer from altitude inaccuracies caused by stereo matching errors and JPEG-based compression artifacts. This paper presents a method to improve the quality of 3D maps generated from Kaguya TC images, focusing on mitigating the effects of compression-induced noise in disparity maps. We analyze the compression behavior of Kaguya TC imagery, and identify systematic disparity noise patterns, especially in darker regions. In this paper, we propose an approach to enhance 3D map quality by reducing residual noise in disparity images derived from compressed images. Our experimental results show that the proposed approach effectively reduces elevation noise, enhancing the safety and reliability of terrain data for future lunar missions.

DOI： 10.1109/SMC58881.2025.11343204

Web of Science

Scopus

researchmap

その他リンク： https://dblp.org/db/conf/smc/smc2025.html#IwashitaMCAGSNKT25

掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEE Access  

Gait recognition enables the non-contact identification of individuals from a distance based on their walking patterns and body shapes. For vision-based gait recognition, covariates (e.g., clothing, baggage and background) can negatively impact identification. As a result, many existing studies extract gait features from silhouettes or skeletal information obtained through preprocessing, rather than directly from RGB image sequences. In contrast to preprocessing which relies on the fitting accuracy of models trained on different tasks, disentangled representation learning (DRL) is drawing attention as a method for directly extracting gait features from RGB image sequences. However, DRL learns to extract features of the target attribute from the differences among multiple inputs with various attributes, which means its separation performance depends on the variation and amount of the training data. In this study, aiming to enhance the variation and quantity of each subject's videos, we propose a novel data augmentation pipeline by feature swapping for RGB-based gait recognition. To expand the variety of training data, features of posture and covariates separated through DRL are paired with features extracted from different individuals, which enables the generation of images of subjects with new attributes. Dynamic gait features are extracted through temporal modeling from pose features of each frame, not only from real images but also from generated ones. The experiments demonstrate that the proposed pipeline increases both the quality of generated images and the identification accuracy. The proposed method also outperforms the RGB-based state-of-the-art method in most settings.

DOI： 10.1109/ACCESS.2024.3445415

Web of Science

Scopus

researchmap

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2024 IEEE/SICE International Symposium on System Integration, SII 2024  

Most existing retrofit remote-control systems for backhoes are large, hard-to-install, and expensive. Therefore, we propose an easy-to-install and inexpensive teleoperation system. The proposed system comprised remote-control and sensing systems. The remote-control system retrofits robot arm-based devices to 'Cat Command', a compact embedded teleoperation system with a limited communication range, and controls these devices via a 5G commercial network to realize control from a remote office. Because this system does not require any additional modifications to the embedded control unit in the cockpit, the operator can continue working in the cockpit even if the backhoe is remotely controlled. The system enables the remote control of various devices from an extremely long distance by changing the joint parts between the robot arm and the embedded remote-control device. The sensing system estimates the posture and position of the backhoe by attaching original sensing devices to the backhoe. In addition, a 360 camera was installed in the cockpit to transmit work images from the construction site to a remote office in real time. The sensing device was smaller and lighter than conventional devices. We confirmed that the proposed system can be used to operate a construction site backhoe from a remote office, and that the system can be used to excavate soil using an actual backhoe.

DOI： 10.1109/SII58957.2024.10417625

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2024.html#ShibataNTMNK24

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings - IEEE International Conference on Robotics and Automation  

Generative modeling of 3D LiDAR data is an emerging task with promising applications for autonomous mobile robots, such as scalable simulation, scene manipulation, and sparse-to-dense completion of LiDAR point clouds. While existing approaches have demonstrated the feasibility of image-based LiDAR data generation using deep generative models, they still struggle with fidelity and training stability. In this work, we present R2DM, a novel generative model for LiDAR data that can generate diverse and high-fidelity 3D scene point clouds based on the image representation of range and reflectance intensity. Our method is built upon denoising diffusion probabilistic models (DDPMs), which have shown impressive results among generative model frameworks in recent years. To effectively train DDPMs in the LiDAR domain, we first conduct an in-depth analysis of data representation, loss functions, and spatial inductive biases. Leveraging our R2DM model, we also introduce a flexible LiDAR completion pipeline based on the powerful capabilities of DDPMs. We demonstrate that our method surpasses existing methods in generating tasks on the KITTI-360 and KITTI-Raw datasets, as well as in the completion task on the KITTI-360 dataset. Our project page can be found at https://kazuto1011.github.io/r2dm.

DOI： 10.1109/ICRA57147.2024.10611480

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/icra/icra2024.html#NakashimaK24

掲載種別：研究論文（学術雑誌）  

Building LiDAR generative models holds promise as powerful data priors for
restoration, scene manipulation, and scalable simulation in autonomous mobile
robots. In recent years, approaches using diffusion models have emerged,
significantly improving training stability and generation quality. Despite
their success, diffusion models require numerous iterations of running neural
networks to generate high-quality samples, making the increasing computational
cost a potential barrier for robotics applications. To address this challenge,
this paper presents R2Flow, a fast and high-fidelity generative model for LiDAR
data. Our method is based on rectified flows that learn straight trajectories,
simulating data generation with significantly fewer sampling steps compared to
diffusion models. We also propose an efficient Transformer-based model
architecture for processing the image representation of LiDAR range and
reflectance measurements. Our experiments on unconditional LiDAR data
generation using the KITTI-360 dataset demonstrate the effectiveness of our
approach in terms of both efficiency and quality.

DOI： 10.48550/arXiv.2412.02241

arXiv

researchmap

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Symposium on Safety Security and Rescue Robotics 2024 Ssrr 2024  

In this study, we propose distributed sensor ter-minals named 'Sensor Pods' and 'Petit-Sensor Pods', and a Cyber-Physical System (CPS) platform named 'ROS2-TMS for Construction' that aims to improve both the efficiency and safety of earthwork operations. The proposed system collects on-site environmental information, stores it in a database, and visualizes it using virtual reality (VR). To evaluate the system's performance in environments simulating real-world earthwork operations, two types of experiments were conducted. In the first experiment, the integrated system of the Sensor Pods and ROS2-TMS for Construction successfully demonstrated the collection of environmental information, its storage, and visualization through VR. The results indicate that the proposed system has significant potential to provide a comprehensive understanding of on-site conditions. In the second experiment, the performance of the Petit-Sensor Pods was verified, confirming its proper functionality and suggesting expanded possibilities for the future use of ROS2- TMS for Construction. This paper presents the developed system and the experiments conducted to assess its performance. A demonstration video is available at: https: / /youtu. be/u4Jo-dU4ewo/.

DOI： 10.1109/SSRR62954.2024.10770031

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/ssrr/ssrr2024.html#MaedaKMKINTK24

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2023 IEEE/SICE International Symposium on System Integration, SII 2023  

People depend on medical equipment to support their movements when their motor function declines. Our previous study developed a method to estimate motor function from the force applied to a vertical handrail while standing. However, the effect of the handrail direction on movement remains unclear. Additionally, the force applied to the handrail and floor reaction forces on the buttocks and feet may also change with a decline in motor function. Here, this study constructed a system with force plates and handles in both the horizontal and vertical directions to measure the forces applied to the handrails, buttocks, and feet. Furthermore, the change in accuracy of the estimation of motor function, depending on the direction of the handrails and input information, was investigated. In the experiment, healthy participants stood up using a handrail with unrestricted movement and while wearing elderly experience kits that artificially impaired their motor function. The results showed that people exert more downward force on horizontal handrails than on vertical handrails. However, people rely on the vertical handrail for a longer period of time to stabilize anterior-posterior movement. These results indicate that different directions of handrails cause different strategies of the standing-up motion. Additionally, the accuracy of the estimation of motor function improved when the horizontal handrail was used rather than the vertical handrail. This suggests that the classification accuracy could be improved by using different handrail directions, depending on the subject's condition and standing-up motion.

DOI： 10.1109/SII55687.2023.10039452

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2023.html#KiharaATINK23

出版者・発行元：Proceedings of the International Symposium on Automation and Robotics in Construction  

Soil compaction is one of the most important basic elements in construction work because it directly affects the quality of structures. Compaction work using vibratory rollers is generally applied to strengthen ground stiffness, and the method that focuses on the number of compaction cycles is widely used to manage the ground stiffness by vibratory rollers. In contrast to this method, the continuous compaction control (CCC) using accelerometers installed on the vibratory rollers has been proposed as a quantitative evaluation method more suited to actual ground conditions. This method quantifies the distortion rate of the acceleration waveform of the vibratory roller. However, this method based on acceleration response has problems in measurement discrimination accuracy and sensor durability because the accelerometer is installed on the vibration roller, which is the source of vibration. In this paper, we propose a new ground stiffness evaluation method using multiple accelerometers installed on the ground surface. The proposed method measures the acceleration response during compaction work by vibratory rollers using multiple accelerometers on the ground surface. Experiments show the proposed method has a higher discrimination than the conventional methods.

DOI： 10.22260/ISARC2023/0037

Scopus

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023  

3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular resolution and missing properties. Existing studies have tackled the issue by learning inter-domain mapping, while the transferability is constrained by the training configuration and the training is susceptible to peculiar lossy noises called ray-drop. To address the issue, this paper proposes a generative model of LiDAR range images applicable to the data-level domain transfer. Motivated by the fact that LiDAR measurement is based on point-by-point range imaging, we train an implicit image representation-based generative adversarial networks along with a differentiable ray-drop effect. We demonstrate the fidelity and diversity of our model in comparison with the point-based and image-based state-of-the-art generative models. We also showcase upsampling and restoration applications. Furthermore, we introduce a Sim2Real application for LiDAR semantic segmentation. We demonstrate that our method is effective as a realistic ray-drop simulator and outperforms state-of-the-art methods.

DOI： 10.1109/WACV56688.2023.00131

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/wacv/wacv2023.html#NakashimaIK23

掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEE Access  

Gait recognition is a biometric identification method based on individual walking patterns. This modality is applied in a wide range of applications, such as criminal investigations and identification systems, since it can be performed at a long distance and requires no cooperation of interests. In general, cameras are used for gait recognition systems, and previous studies have utilized depth information captured by RGB-D cameras, such as Microsoft Kinect. In recent years, multi-layer LiDAR sensors, which can obtain range images of a target at a range of over 100 m in real time, have attracted significant attention in the field of autonomous mobile robots and self-driving vehicles. Compared with general cameras, LiDAR sensors have rarely been used for biometrics due to the low point cloud densities captured at long distances. In this study, we focus on improving the robustness of gait recognition using LiDAR sensors under confounding conditions, specifically addressing the challenges posed by viewing angles and measurement distances. First, our recognition model employs a two-scale spatial resolution to enhance immunity to varying point cloud densities. In addition, this method learns the gait features from two invariant viewpoints (i.e., left-side and back views) generated by estimating the walking direction. Furthermore, we propose a novel attention block that adaptively recalibrates channel-wise weights to fuse the features from the aforementioned resolutions and viewpoints. Comprehensive experiments conducted on our dataset demonstrate that our model outperforms existing methods, particularly in cross-view, cross-distance challenges, and practical scenarios.

DOI： 10.1109/ACCESS.2023.3333037

Web of Science

Scopus

researchmap

記述言語：英語   出版者・発行元：Institute of Electrical and Electronics Engineers (IEEE)  

3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular resolution and missing properties. Existing studies have tackled the issue by learning inter-domain mapping, while the transferability is constrained by the training configuration and the training is susceptible to peculiar lossy noises called ray-drop. To address the issue, this paper proposes a generative model of LiDAR range images applicable to the data-level domain transfer. Motivated by the fact that LiDAR measurement is based on point-by-point range imaging, we train an implicit image representation-based generative adversarial networks along with a differentiable ray-drop effect. We demonstrate the fidelity and diversity of our model in comparison with the point-based and image-based state-of-the-art generative models. We also showcase upsampling and restoration applications. Furthermore, we introduce a Sim2Real application for LiDAR semantic segmentation. We demonstrate that our method is effective as a realistic ray-drop simulator and outperforms state-of-the-art methods.

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>In this study, we develop a sensor terminal with multiple and various sensors named sensor pod, which collects various environmental information at a construction site. The sensor pod is equipped with a 3D-LiDAR and a vibration sensor, which can be used to predict the surrounding hazards and evaluate the ground stiffness. In this paper, we introduce a method of evaluating ground stiffness using the waveform distortion of multi-point synchronized vibration data obtained by the distributed sensor pods.</p>

DOI： 10.1299/jsmermd.2022.1a1-e04

CiNii Research

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2022 IEEE/SICE International Symposium on System Integration, SII 2022  

Gait recognition, which is a biometric identifier for individual walking patterns, is utilized in many applications, such as criminal investigation and identification systems, because it can be applied at a long distance and requires no explicit cooperation of the subjects. In general, cameras are used for gait recognition, and several methods in previous studies have used depth information captured by RGB-D cameras. However, RGB-D cameras are limited in terms of their measurement distance and are difficult to access outdoors. In recent years, real-time multi-layer 3D LiDAR, which can obtain 3D range images of a target at ranges of over 100 m, has attracted significant attention for use in autonomous mobile robots, serving as eyes for obstacles detection and navigation. Compared with cameras, such 3D LiDAR has rarely been used for biometrics owing to its low spatial resolution. However, considering the unique characteristics of 3D LiDAR, such as the robustness of the illumination conditions, long measurement distances, and wide-angle scanning, the approach has the potential to be applied outdoors as a biometric identifier. The present paper describes a gait recognition system, called 2V-Gait, which is robust to variations in the walking direction of a subject and the distance measured from the 3D LiDAR. To improve the performance of gait recognition, we leverage the unique characteristics of 3D LiDAR, which are not included in regular cameras. Extensive experiments on our dataset show the effectiveness of the proposed approach.

DOI： 10.1109/SII52469.2022.9708899

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2022.html#AhnNYIK22

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2022 IEEE/SICE International Symposium on System Integration, SII 2022  

Gait recognition is a non-contact person identification method that utilizes cameras installed at a distance. However, gait images contain person-agnostic elements (covariates) such as clothing, and the removal of covariates is important for identification with high performance. Disentanglement representation learning, which separates gait-dependent information such as posture from covariates by unsupervised learning, has been attracting attention as a method to remove covariates. However, because the amount of gait data is negligible compared to other computer vision tasks, such as image recognition, the separation performance of existing methods is insufficient. In this study, we propose a gait recognition method to improve the separation performance, which augments the training data by adversarial generation based on identity features, separated by disentanglement representation learning. The proposed method first separates gait-dependent features (pose features) and appearance-related covariate features (style features) from gait videos based on disentanglement representation learning. Then, synthesized gait images are generated by exchanging pose features between gait images of the person under different walking conditions, followed by adding them to the training data. The experiments indicate that our method can improve the separation performance, and generate high-quality gait images that are effective for data augmentation.

DOI： 10.1109/SII52469.2022.9708776

Web of Science

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2022.html#YoshinoNAIK22

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics  

Assisting patients with dementia is a significant social issue. Currently, to assist patients with dementia, a multimodal care technique called Humanitude is gaining popularity. In Humanitude, the patients are assisted through various techniques to stand up independently by utilizing their motor functions as much as possible. Humanitude care techniques encourage caregivers to increase the area of contact with patients during the sit-to-stand motion. However, Humanitude care techniques are not accurately performed by novice caregivers. Therefore, in this study, a smock-type wearable sensor was developed to measure the proximity between caregivers and care recipients during sit-to-stand motion assistance. A measurement experiment was conducted to evaluate the proximity differences between Humanitude care and simulated novice care. In addition, the effects of different care techniques on the center of mass (CoM) trajectory and muscle activity of the care recipients were investigated. The results showed that the caregivers tend to bring their top and middle trunk closer in Humanitude care compared with novice simulated care. Furthermore, it was observed that the CoM trajectory and muscle activity under Humanitude care were similar to those observed when the care recipient stands up independently. These results validate the effectiveness of Humanitude care and provide useful information for teaching techniques in Humanitude.

DOI： 10.1109/SMC53654.2022.9945156

Scopus

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/smc/smc2022.html#AnTNSSK22

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>This paper presents a retrofit backhoe remote control system that is inexpensive, compact, and easy to install. The system consists of a remote control system using a teleoperation system embedded by a construction machinery manufacturer and a small robot arm, and a remote sensing system using a multi-core microcomputer.</p>

DOI： 10.1299/jsmermd.2022.1p1-c07

CiNii Research

記述言語：英語   会議種別：口頭発表（一般）  

国名：日本国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：シンガポール共和国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：カナダ  

記述言語：英語   会議種別：口頭発表（一般）  

国名：台湾  

記述言語：英語   会議種別：口頭発表（一般）  

国名：アメリカ合衆国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：日本国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：アメリカ合衆国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：アメリカ合衆国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：ノルウェー王国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：ノルウェー王国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：チェコ共和国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：アメリカ合衆国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：インド  

記述言語：英語   会議種別：口頭発表（招待・特別）  

国名：日本国  

記述言語：英語   会議種別：口頭発表（一般）  

国名：ベトナム社会主義共和国  

researchmap

researchmap

Recently, 3D LiDAR has emerged as a promising technique in the field of
gait-based person identification, serving as an alternative to traditional RGB
cameras, due to its robustness under varying lighting conditions and its
ability to capture 3D geometric information. However, long capture distances or
the use of low-cost LiDAR sensors often result in sparse human point clouds,
leading to a decline in identification performance. To address these
challenges, we propose a sparse-to-dense upsampling model for pedestrian point
clouds in LiDAR-based gait recognition, named LidarGSU, which is designed to
improve the generalization capability of existing identification models. Our
method utilizes diffusion probabilistic models (DPMs), which have shown high
fidelity in generative tasks such as image completion. In this work, we
leverage DPMs on sparse sequential pedestrian point clouds as conditional masks
in a video-to-video translation approach, applied in an inpainting manner. We
conducted extensive experiments on the SUSTeck1K dataset to evaluate the
generative quality and recognition performance of the proposed method.
Furthermore, we demonstrate the applicability of our upsampling model using a
real-world dataset, captured with a low-resolution sensor across varying
measurement distances.

DOI： 10.48550/arXiv.2410.08680

arXiv

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

Generative modeling of 3D LiDAR data is an emerging task with promising
applications for autonomous mobile robots, such as scalable simulation, scene
manipulation, and sparse-to-dense completion of LiDAR point clouds. Existing
approaches have shown the feasibility of image-based LiDAR data generation
using deep generative models while still struggling with the fidelity of
generated data and training instability. In this work, we present R2DM, a novel
generative model for LiDAR data that can generate diverse and high-fidelity 3D
scene point clouds based on the image representation of range and reflectance
intensity. Our method is based on the denoising diffusion probabilistic models
(DDPMs), which have demonstrated impressive results among generative model
frameworks and have been significantly progressing in recent years. To
effectively train DDPMs on the LiDAR domain, we first conduct an in-depth
analysis regarding data representation, training objective, and spatial
inductive bias. Based on our designed model R2DM, we also introduce a flexible
LiDAR completion pipeline using the powerful properties of DDPMs. We
demonstrate that our method outperforms the baselines on the generation task of
KITTI-360 and KITTI-Raw datasets and the upsampling task of KITTI-360 datasets.
Our code and pre-trained weights will be available at
https://github.com/kazuto1011/r2dm.

DOI： 10.48550/arXiv.2309.09256

arXiv

researchmap

その他リンク： http://arxiv.org/pdf/2309.09256v1

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

3D LiDAR sensors are indispensable for the robust vision of autonomous mobile
robots. However, deploying LiDAR-based perception algorithms often fails due to
a domain gap from the training environment, such as inconsistent angular
resolution and missing properties. Existing studies have tackled the issue by
learning inter-domain mapping, while the transferability is constrained by the
training configuration and the training is susceptible to peculiar lossy noises
called ray-drop. To address the issue, this paper proposes a generative model
of LiDAR range images applicable to the data-level domain transfer. Motivated
by the fact that LiDAR measurement is based on point-by-point range imaging, we
train an implicit image representation-based generative adversarial networks
along with a differentiable ray-drop effect. We demonstrate the fidelity and
diversity of our model in comparison with the point-based and image-based
state-of-the-art generative models. We also showcase upsampling and restoration
applications. Furthermore, we introduce a Sim2Real application for LiDAR
semantic segmentation. We demonstrate that our method is effective as a
realistic ray-drop simulator and outperforms state-of-the-art methods.

DOI： 10.48550/arXiv.2210.11750

arXiv

researchmap

その他リンク： http://arxiv.org/pdf/2210.11750v1

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

種別：査読等 

国際会議録　査読論文数：1