arXiv subjects

Koichi Hashimoto

Publications and source records attributed to Koichi Hashimoto.

13 recordsLinked to original sources

arXiv2026

ViHaTeleop: A Low-Cost, Lightweight Visual-Haptic Teleoperation System for Dexterous Manipulation Learning

Learning from demonstration is a promising approach for dexterous manipulation, but collecting high-quality contact-critical demonstrations remains difficult with low-cost teleoperation hardware. We present ViHaTeleop, a lightweight (0.7 kg), low-cost (\$550) visual-haptic teleoperation system with SLAM-based wrist tracking, camera-based hand tracking, and finger-wise vibrotactile feedback through Linear Resonant Actuators (LRA). The system includes several design choices (LED illumination, fisheye hand camera, and tactile-aware retargeting constraints) and is deployed on Franka + LEAP Hand + 9DTact in both real and simulated environments. Under matched with/without-haptic conditions with nine participants across six contact-critical tasks, haptics improved success rates across all tasks (+2.2 to +15.6 percentage points), while completion-time effects were task-dependent. Subjective ratings showed significant gains in contact clarity and grasp confidence in both simulation and real-world settings (Wilcoxon signed-rank, $p<0.05$). We also integrate a lightweight depth-camera-based tactile proxy in Isaac Sim, enabling a full pipeline from multi-modal demonstration collection to visual-tactile policy training. Preliminary downstream validation by training visual-tactile policies from collected demonstrations shows tactile cues benefit contact-critical subtasks (peg-in-hole: +17 percentage points over vision-only).

cs.RO↗

arXiv2026

Boundary-by-Mask: Few-Shot Instance Segmentation with Mask-Conditioned Boundary Learning for Texture-Poor Industrial Parts

Recent advances in large pre-trained models have led to remarkable progress in instance segmentation on general images. However, industrial scenarios remain challenging. Instance definitions are often application-specific and inconsistent, and the domain gap from general imagery is substantial due to weak textures and limited contextual cues. Consequently, a direct application of existing models is unreliable. We propose Boundary-by-Mask, a few-shot instance segmentation framework that supervises boundaries instead of interior appearance. Given a few RGB images and corresponding instance masks, the method extracts rich visual features using a foundation-model encoder and trains a lightweight Signed Distance Function (SDF) head to predict boundary-aware distance maps. Segmentation masks are obtained through an SDF-to-mask reconstruction process. By explicitly estimating contours, the framework achieves reliable instance separation even on low-texture and color-uniform surfaces. The instance definition is conditioned by the instance mask. Replacing the mask specifies the segmentation target, such as the whole object or a sub-part. A pixel-wise shallow MLP head enables rapid training. Experiments on industrial parts and food items with ambiguous boundaries show strong few-shot generalization, robustness in feature-poor conditions, and precise control over mask-level targets.

cs.CV↗

arXiv2025

Hierarchical Image-Guided 3D Point Cloud Segmentation in Industrial Scenes via Multi-View Bayesian Fusion

Reliable 3D segmentation is critical for understanding complex scenes with dense layouts and multi-scale objects, as commonly seen in industrial environments. In such scenarios, heavy occlusion weakens geometric boundaries between objects, and large differences in object scale will cause end-to-end models fail to capture both coarse and fine details accurately. Existing 3D point-based methods require costly annotations, while image-guided methods often suffer from semantic inconsistencies across views. To address these challenges, we propose a hierarchical image-guided 3D segmentation framework that progressively refines segmentation from instance-level to part-level. Instance segmentation involves rendering a top-view image and projecting SAM-generated masks prompted by YOLO-World back onto the 3D point cloud. Part-level segmentation is subsequently performed by rendering multi-view images of each instance obtained from the previous stage and applying the same 2D segmentation and back-projection process at each view, followed by Bayesian updating fusion to ensure semantic consistency across views. Experiments on real-world factory data demonstrate that our method effectively handles occlusion and structural complexity, achieving consistently high per-class mIoU scores. Additional evaluations on public dataset confirm the generalization ability of our framework, highlighting its robustness, annotation efficiency, and adaptability to diverse 3D environments.

cs.CV↗

arXiv2023

Crowd simulation incorporating a route choice model and similarity evaluation using real large-scale data

Modeling and simulation approaches that express crowd movement with mathematical models are widely and actively studied to understand crowd movement and resolve crowd accidents. Existing literature on crowd modeling focuses on only the decision-making of walking behavior. However, the decision-making of route choice, which is a higher-level decision, should also be modeled for constructing more practical simulations. Furthermore, the reproducibility evaluation of the crowd simulation incorporating the route choice model using real data is insufficient. Therefore, we generalize and propose a crowd simulation framework that includes actual crowd movement measurements, route choice model estimation, and crowd simulator construction. We use the Discrete choice model as the route choice model and the Social force model as the walking model. In experiments, we measure crowd movements during an evacuation drill in a theater and a firework event where tens of thousands of people moved and prove that the crowd simulation incorporating the route choice model can reproduce the real large-scale crowd movement more accurately.

cs.MA↗

arXiv2019

Animated Stickies: Fast Video Projection Mapping onto a Markerless Plane through a Direct Closed-Loop Alignment

This paper presents a fast projection mapping method for moving image content projected onto a markerless planar surface using a low-latency Digital Micromirror Device (DMD) projector. By adopting a closed-loop alignment approach, in which not only the surface texture but also the projected image is tracked by a camera, the proposed method is free from a calibration or position adjustment between the camera and projector. We designed fiducial patterns to be inserted into a fast flapping sequence of binary frames of the DMD projector, which allows the simultaneous tracking of the surface texture and a fiducial geometry separate from a single image captured by the camera. The proposed method implemented on a CPU runs at 400 fps and enables arbitrary video contents to be "stuck" onto a variety of textured surfaces.

cs.GR↗

arXiv2018

Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data

In this paper, we demonstrate an end-to-end spatiotemporal gesture learning approach for 3D point cloud data using a new gestures dataset of point clouds acquired from a 3D sensor. Nine classes of gestures were learned from gestures sample data. We mapped point cloud data into dense occupancy grids, then time steps of the occupancy grids are used as inputs into a 3D convolutional neural network which learns the spatiotemporal features in the data without explicit modeling of gesture dynamics. We also introduced a 3D region of interest jittering approach for point cloud data augmentation. This resulted in an increased classification accuracy of up to 10% when the augmented data is added to the original training data. The developed model is able to classify gestures from the dataset with 84.44% accuracy. We propose that point cloud data will be a more viable data type for scene understanding and motion recognition, as 3D sensors become ubiquitous in years to come.

cs.CV↗

arXiv2012

Development of Lattice QCD Tool Kit on Cell Broadband Engine Processor

We report an implementation of a code for SU(3) matrix multiplication on Cell/B.E., which is a part of our project, Lattice Tool Kit on Cell/B.E.. On QS20, the speed of the matrix multiplication on SPE in single precision is 227GFLOPS and it becomes 20GFLOPS {this vaule was remeasured and corrcted.} together with data transfer from main memory by DNA transfer, which is 4.6% of the hardware peak speed (460GFLOPS), and is 7.4% of the theoretical peak speed of this calculation (268.77GFLOPS). We briefly describe our tuning procedure.

hep-lat↗

arXiv2008

eta' meson From Two Flavor Dynamical Domain Wall Fermions

We explore flavor singlet pseudoscalar meson, eta', spectrum in two-flavor (Nf=2) lattice QCD. The continuum-like relation between the topology of the QCD vacuum and the U(1)_A anomaly, that prevents eta' meson from being a would-be Nambu-Goldstone boson, are expected to hold in the domain wall fermions (DWF) used as a lattice quark field in this work. Although our simulation is limited to relatively heavy quark masses and statistical error is not magnificently small despite of improvements in measurements and fit procedures for meson propagators, we obtained m_eta'=819(127) MeV for Nf=2 QCD, where the error is statistical only. Potentially serious systematic error in the number are discussed. Results for other meson are also reported.

hep-lat↗

arXiv2008

Dynamical QCD simulation with theta terms

The theta term that breaks the Strong CP symmetry is introduced in the two flavors of dynamical QCD simulation. theta is analytically continued to a pure imaginary number to make the probability of Monte Carlo positive. The Neutron's Electric Dipole Moment (NEDM) is measured on the ensemble under a uniform and week electric field. Other applications of theta terms are also discussed.

hep-lat↗

arXiv2005

The static quark potential in 2+1 flavour Domain Wall QCD from QCDOC

We report our present status of on-going project on the measurement of the static quark potential in 2+1 flavour domain wall QCD with various improved gauge actions and couplings. Lattice spacing determined from Sommer scale on these ensembles are from 1.6 GeV to 2.0 GeV for $16^3 \times 32$ lattice with fifth dimension size 8. We also examine size of discretization error from scaling of a pair of dimensionless quantities, $(r_0 m_\pi)^2$ and $r_0 m_\rho$, and found small scaling violation.

hep-lat↗

arXiv2004

Static $\bar{Q}$-$Q$ Potential from $N_f=2$ Dynamical Domain-Wall QCD

We calculate the static quark and anti-quark potential both in quenched and two-flavor dynamical quark lattice QCD using DBW2 gauge and domain-wall quark actions. Lattice spacings from Sommer scale are determined. We find (i) mixing of excited states is different in between quenched and dynamical, (ii) lattice spacing $a_{r_0}\sim a_{m_{\rho}}$ in dynamical and (iii) coefficient of Coulomb term being $\alpha_{N_f=0}<\alpha_{N_f=2}$ at $a^{-1}\sim$ 2 GeV.

hep-lat↗

arXiv2003

Matter degrees of freedom and string breaking in Abelian projected quenched SU(2) QCD

In the Abelian projection the Yang--Mills theory contains Abelian gauge fields (diagonal degrees of freedom) and the Abelian matter fields (off-diagonal degrees) described by a complicated action. The matter fields are essential for the breaking of the adjoint string. We obtain numerically the effective action of the Abelian gauge and the Abelian matter fields in quenched SU(2) QCD and show that the Abelian matter fields provide an essential contribution to the total action even in the infrared region. We also observe the breaking of an Abelian analog of the adjoint string using Abelian operators. We show that the adjoint string tension is dominated by the Abelian and the monopole contributions similarly to the case of the fundamental particles. We conclude that the adjoint string breaking can successfully be described in the Abelian projection formalism.

hep-lat↗

arXiv2003

An Abelian effective action reproducing screening and confinement in quenched SU(2) QCD

In an Abelian projection SU(2) gluodynamics contains Abelian gauge fields (diagonal degrees of freedom) and Abelian matter fields (off-diagonal degrees). The matter fields are essential for the breaking of the adjoint string. We obtain numerically the effective action of the Abelian fields in quenched SU(2) QCD and show that the Abelian matter fields provide an essential contribution to the total action even in the infrared region.

hep-lat↗