arXiv subjects

Yoshihiro Sato

Publications and source records attributed to Yoshihiro Sato.

8 recordsLinked to original sources

arXiv2026

Conceptual Design of an Ecosystem for Real Farm Data Collection toward Agricultural AI Foundation Models

Data scarcity is a fundamental challenge in developing AI and foundation models for agricultural robots. Existing open-source data platforms do not provide sufficient incentives for data providers so long-term data collection remains difficult. Furthermore, advances in generative AI have introduced a new challenge of verifying that collected data genuinely originates from real farm environments. We propose an ecosystem for the sustainable collection and distribution of real farm data, integrating automatic pricing driven by demand and rarity, revenue sharing that distributes earnings to farmers as an incentive to keep providing data, and data authenticity guarantees through authenticated device uploads. To demonstrate the economic sustainability for all three parties among farmers, AI companies, and the platform, we estimate the economic value that agricultural robots stand to generate.

cs.RO↗

arXiv2026

ScanDP: Generalizable 3D Scanning with Diffusion Policy

Learning-based 3D Scanning plays a crucial role in enabling efficient and accurate scanning of target objects. However, recent reinforcement learning-based methods often require large-scale training data and still struggle to generalize to unseen object categories.In this work, we propose a data-efficient 3D scanning framework that uses Diffusion Policy to imitate human-like scanning strategies. To enhance robustness and generalization, we adopt the Occupancy Grid Mapping instead of direct point cloud processing, offering improved noise resilience and handling of diverse object geometries. We also introduce a hybrid approach combining a sphere-based space representation with a path optimization procedure that ensures path safety and scanning efficiency. This approach addresses limitations in conventional imitation learning, such as redundant or unpredictable behavior. We evaluate our method on diverse unseen objects in both shape and scale. Ours achieves higher coverage and shorter paths than baselines, while remaining robust to sensor noise. We further confirm practical feasibility and stable operation in real-world execution.

cs.RO↗

arXiv2024

CAPT: Category-level Articulation Estimation from a Single Point Cloud Using Transformer

The ability to estimate joint parameters is essential for various applications in robotics and computer vision. In this paper, we propose CAPT: category-level articulation estimation from a point cloud using Transformer. CAPT uses an end-to-end transformer-based architecture for joint parameter and state estimation of articulated objects from a single point cloud. The proposed CAPT methods accurately estimate joint parameters and states for various articulated objects with high precision and robustness. The paper also introduces a motion loss approach, which improves articulation estimation performance by emphasizing the dynamic features of articulated objects. Additionally, the paper presents a double voting strategy to provide the framework with coarse-to-fine parameter estimation. Experimental results on several category datasets demonstrate that our methods outperform existing alternatives for articulation estimation. Our research provides a promising solution for applying Transformer-based architectures in articulated object analysis.

cs.CV↗

arXiv2021

Learning 6DoF Grasping Using Reward-Consistent Demonstration

As the number of the robot's degrees of freedom increases, the implementation of robot motion becomes more complex and difficult. In this study, we focus on learning 6DOF-grasping motion and consider dividing the grasping motion into multiple tasks. We propose to combine imitation and reinforcement learning in order to facilitate a more efficient learning of the desired motion. In order to collect demonstration data as teacher data for the imitation learning, we created a virtual reality (VR) interface that allows humans to operate the robot intuitively. Moreover, by dividing the motion into simpler tasks, we simplify the design of reward functions for reinforcement learning and show in our experiments a reduction in the steps required to learn the grasping motion.

cs.RO↗

arXiv2016

Describing upper body motions based on the Labanotation for learning-from-observation robots

We have been developing a paradigm, which we refer to as Learning-from-observation, for a robot to automatically acquire what-to-do through observation of human performance. Since a simple mimicking method to repeat exact joint angles does not work due to the kinematic and dynamic difference between a human and a robot, the method introduces an intermediate symbolic representation, task models, to conceptually represent what-to-do through observation. Then, these task models are mapped appropriate robot motions depending on each robot hardware. This paper presents task models, designed based on the Labanotation, for upper body movements of humanoid robots. Given a human motion sequence, we first analyze the motions of the upper body, and extract certain fixed poses at certain key frames. These key poses are translated into states represented by Labanotation symbols. Then, task models, identified from the state transitions, are mapped to robot movements on a particular robot hardware. Since the task models based on Labanotation are independent from different robot hardware, we can share the same observation module; we only need task mapping modules depending on different robot hardware. The system was implemented and demonstrated that three different robots can automatically mimic human upper body motions with satisfactory level of resemblance.

cs.RO↗

arXiv2012

Balloon-borne gamma-ray telescope with nuclear emulsion : overview and status

Detecting the first electron pairs with nuclear emulsion allows a precise measurement of the direction of incident gamma-rays as well as their polarization. With recent innovations in emulsion scanning, emulsion analyzing capability is becoming increasingly powerful. Presently, we are developing a balloon-borne gamma-ray telescope using nuclear emulsion. An overview and a status of our telescope is given.

astro-ph.IM↗

arXiv2010

Causality in quantum physics, the ensemble of beginnings of time, and the dispersion relations of wave function

In quantum physics, disturbance due to a measurement is not negligible. This requires the time parameter $t$ in the Schrödinger or Heisenberg equation to be considered differently from a time continuum of experimenter's clock $T$ on which physical events are recorded. It will be shown that $t$ represents an ensemble of time intervals on $T$ during which a microsystem travels undisturbed. In particular $t=0$ represents the ensemble of preparation events that we refer to as the ensemble of beginnings of time. This restricts $t$ to be $0\leq t<\infty$. But such a time evolution of quantum states cannot be achieved in the Hilbert space $L^2$ functions because due to the Stone-von Neumann theorem this time evolution is given by the unitary group with $t$ extending $-\infty<t<\infty$. Hence one needs solutions of the Schrödinger (and Heisenberg) equation under time asymmetric boundary condition in which only the semigroup time evolution is allowed. This boundary condition is fulfilled by the energy wave functions for quantum states (and as well as for observables) which are smooth Hardy function satisfying the Hilbert transform, called the dispersion relation in physics.

quant-ph↗

arXiv2005

Relativistic resonances: Their masses, widths, lifetimes, superposition, and causal evolution

Whether one starts form the analytic S-matrix definition or the requirement of gauge parameter independence in renormalization theory, a relativistic resonance is given by a pole at a complex value s of energy squared. The complex number s does not define the mass and width separately and this definition does not lead to interfering Breit-Wigner if two or more resonances are involved. To accomplish both we invoke the decaying particle aspect of a resonance and associate to each pole a space of relativistic Gamow kets which transform irreducibly under causal Poincare transformations. A Gamow state has an exponential time evolution and one can choose of the many possible width parameters, that parameter as the width of the relativistic resonance which equals the inverse lifetime. This uniquely defines the mass and width parameters for a relativistic resonance. Two or more poles in the same partial wave are given by the sum of Breit-Wigners in the scattering amplitude and by a superposition of Gamow vectors with each Gamow vector corresponding to one Breit-Wigner. In addition to the sum of Breit-Wigners the scattering amplitude contains a background amplitude representing direct production of the final state (contact terms).This contact amplitude is associated to a background vector which is a continuous superposition of Lippmann-Schwinger states. Omitting this continuum gives the Weisskopf-Wigner approximation.

hep-ph↗