arXiv subjects

Marco Esposito

Publications and source records attributed to Marco Esposito.

At least 19 recordsLinked to original sources

arXiv2026

Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics

Autonomous medical robots hold promise to improve patient outcomes, reduce provider workload, democratize access to care, and enable superhuman precision. However, autonomous medical robotics has been limited by a fundamental data problem: existing medical robotic datasets are small, single-embodiment, and rarely shared openly, restricting the development of foundation models that the field needs to advance. We introduce Open-H-Embodiment, the largest open dataset of medical robotic video with synchronized kinematics to date, spanning more than 50 institutions and multiple robotic platforms including the CMR Versius, Intuitive Surgical's da Vinci, da Vinci Research Kit (dVRK), Rob Surgical BiTrack, Virtual Incision's MIRA, Moon Surgical Maestro, and a variety of custom systems, spanning surgical manipulation, robotic ultrasound, and endoscopy procedures. We demonstrate the research enabled by this dataset through two foundation models. GR00T-H is the first open foundation vision-language-action model for medical robotics, which is the only evaluated model to achieve full end-to-end task completion on a structured suturing benchmark (25% of trials vs. 0% for all others) and achieves 64% average success across a 29-step ex vivo suturing sequence. We also train Cosmos-H-Surgical-Simulator, the first action-conditioned world model to enable multi-embodiment surgical simulation from a single checkpoint, spanning nine robotic platforms and supporting in silico policy evaluation and synthetic data generation for the medical domain. These results suggest that open, large-scale medical robot data collection can serve as critical infrastructure for the research community, enabling advances in robot learning, world modeling, and beyond.

cs.RO↗

arXiv2026

Self-Sovereign Identity and eIDAS 2.0: An Analysis of Control, Privacy, and Legal Implications

European digital identity initiatives are grounded in regulatory frameworks designed to ensure interoperability and robust, harmonized security standards. The evolution of these frameworks culminates in eIDAS 2.0, whose origins trace back to the Electronic Signatures Directive 1999/93/EC, the first EU-wide legal foundation for the use of electronic signatures in cross-border electronic transactions. As technological capabilities advanced, the initial eIDAS 1.0 framework was increasingly criticized for its limitations and lack of comprehensiveness. Emerging decentralized approaches further exposed these shortcomings and introduced the possibility of integrating innovative identity paradigms, such as Self-Sovereign Identity (SSI) models. In this article, we contribute to the ongoing legal and policy debate on the European Digital Identity Framework by analyzing key provisions of eIDAS 2.0 and its accompanying recitals, drawing on a systematic literature review guided by defined Research Questions (RQ). This work employs a structured methodological approach that combines descriptive and comparative analysis, systematic gap analysis supported by a defined scoring matrix, and normative analysis to evaluate the compatibility of SSI properties with eIDAS 2.0 regulation, as operationalized via its Architecture and Reference Framework (ARF). Furthermore, we assess the ARF's guidelines and examine the extent to which it aligns with SSI. The analysis adopts a complementary perspective demonstrating how the regulation can be further developed to better support SSI in the future by identifying existing limitations and potential adoption opportunities within the current legal foundations of the framework.

cs.CR↗

arXiv2025

Time-Series at the Edge: Tiny Separable CNNs for Wearable Gait Detection and Optimal Sensor Placement

We study on-device time-series analysis for gait detection in Parkinson's disease (PD) from short windows of triaxial acceleration, targeting resource-constrained wearables and edge nodes. We compare magnitude thresholding to three 1D CNNs for time-series analysis: a literature baseline (separable convolutions) and two ultra-light models - one purely separable and one with residual connections. Using the BioStampRC21 dataset, 2 s windows at 30 Hz, and subject-independent leave-one-subject-out (LOSO) validation on 16 PwPD with chest-worn IMUs, our residual separable model (Model 2, 533 params) attains PR-AUC = 94.5%, F1 = 91.2%, MCC = 89.4%, matching or surpassing the baseline (5,552 params; PR-AUC = 93.7%, F1 = 90.5%, MCC = 88.5%) with approximately 10x fewer parameters. The smallest model (Model 1, 305 params) reaches PR-AUC = 94.0%, F1 = 91.0%, MCC = 89.1%. Thresholding obtains high recall (89.0%) but low precision (76.5%), yielding many false positives and high inter-subject variance. Sensor-position analysis (train-on-all) shows chest and thighs are most reliable; forearms degrade precision/recall due to non-gait arm motion; naive fusion of all sites does not outperform the best single site. Both compact CNNs execute within tight memory/latency budgets on STM32-class MCUs (sub-10 ms on low-power boards), enabling on-sensor gating of transmission/storage. Overall, ultra-light separable CNNs provide a superior accuracy-efficiency-generalization trade-off to fixed thresholds for wearable PD gait detection and underscore the value of tailored time-series models for edge deployment.

cs.LG↗

arXiv2025

HyperScout-H: the hyperspectral imager for the ESA Hera mission

The HyperScout-H (HS-H) instrument is one of the payloads aboard ESA's Hera spacecraft. Hera is a planetary defence mission that aims to provide a detailed characterization of the near-Earth binary asteroid (65803) Didymos-Dimorphos after the NASA/DART mission impact. HS-H is a versatile dual-use payload, functioning as a hyperspectral imager that captures both images and spectral data within the 0.65--0.95 $μ$m wavelength range. The observations from this instrument will offer key insights regarding the composition of the two bodies Didymos and Dimorphos, space weathering effects, and the potential presence of exogenous material on these asteroids. Thanks to its wide field of view ($\approx 15.5^\circ \times 8.3^\circ$ in paraxial approximation), HS-H will be able to monitor the system's orbital dynamic and dust environment. At the same time, both components of this binary asteroid remain in the field of view for most of the asteroid phase of the mission. These results also complement the data obtained from other instruments in characterizing the geomorphological units. The data that will be obtained by HS-H will enable the creation of maps highlighting key spectral features, such as taxonomic classification, spectral slope, and band parameters. This article presents the pre-flight calibration of the instrument, outlines the science objectives, and discusses the expected investigations. The instrument's capabilities are demonstrated through laboratory observations of two meteorite samples and a dedicated software toolbox was developed specifically for processing the instrument's data.

astro-ph.EP↗

arXiv2025

A Private Smart Wallet with Probabilistic Compliance

We propose a privacy-preserving smart wallet with a novel invitation-based private onboarding mechanism. The solution integrates two levels of compliance in concert with an authority party: a proof of innocence mechanism and an ancestral commitment tracking system using bloom filters for probabilistic UTXO chain states. Performance analysis demonstrates practical efficiency: private transfers with compliance checks complete within seconds on a consumer-grade laptop, and overall with proof generation remaining low. On-chain costs stay minimal, ensuring affordability for all operations on Base layer 2 network. The wallet facilitates private contact list management through encrypted data blobs while maintaining transaction unlinkability. Our evaluation validates the approach's viability for privacy-preserving, compliance-aware digital payments with minimized computational and financial overhead.

cs.CR↗

arXiv2025

Visual-Haptic Model Mediated Teleoperation for Remote Ultrasound

Tele-ultrasound has the potential greatly to improve health equity for countless remote communities. However, practical scenarios involve potentially large time delays which cause current implementations of telerobotic ultrasound (US) to fail. Using a local model of the remote environment to provide haptics to the expert operator can decrease teleoperation instability, but the delayed visual feedback remains problematic. This paper introduces a robotic tele-US system in which the local model is not only haptic, but also visual, by re-slicing and rendering a pre-acquired US sweep in real time to provide the operator a preview of what the delayed image will resemble. A prototype system is presented and tested with 15 volunteer operators. It is found that visual-haptic model-mediated teleoperation (MMT) compensates completely for time delays up to 1000 ms round trip in terms of operator effort and completion time while conventional MMT does not. Visual-haptic MMT also significantly outperforms MMT for longer time delays in terms of motion accuracy and force control. This proof-of-concept study suggests that visual-haptic MMT may facilitate remote robotic tele-US.

cs.RO↗

arXiv2024

Prototyping liquid-crystal coronagraphs for exo-Earth imaging

This paper presents initial results from the ESA-funded ``SUPPPPRESS'' project, which aims to develop high-performance liquid-crystal coronagraphs for direct imaging of Earth-like exoplanets in reflected light. The project focuses on addressing the significant challenge of polarization leakage in vector vortex coronagraphs (VVCs). We utilize newly manufactured multi-grating, liquid-crystal VVCs, consisting of a two- or three-element stack of vortex and grating patterns, to reduce this leakage to the $10^{-10}$ contrast level. We detail the experimental setups, including calibration techniques with polarization microscopes and Mueller matrix ellipsometers to enhance the direct-write accuracy of the liquid-crystal patterns. The performance testing of these coronagraph masks will be conducted on the THD2 high-contrast imaging testbed in Paris.

astro-ph.IM↗

arXiv2024

AI techniques for near real-time monitoring of contaminants in coastal waters on board future Phisat-2 mission

Differently from conventional procedures, the proposed solution advocates for a groundbreaking paradigm in water quality monitoring through the integration of satellite Remote Sensing (RS) data, Artificial Intelligence (AI) techniques, and onboard processing. The objective is to offer nearly real-time detection of contaminants in coastal waters addressing a significant gap in the existing literature. Moreover, the expected outcomes include substantial advancements in environmental monitoring, public health protection, and resource conservation. The specific focus of our study is on the estimation of Turbidity and pH parameters, for their implications on human and aquatic health. Nevertheless, the designed framework can be extended to include other parameters of interest in the water environment and beyond. Originating from our participation in the European Space Agency (ESA) OrbitalAI Challenge, this article describes the distinctive opportunities and issues for the contaminants monitoring on the Phisat-2 mission. The specific characteristics of this mission, with the tools made available, will be presented, with the methodology proposed by the authors for the onboard monitoring of water contaminants in near real-time. Preliminary promising results are discussed and in progress and future work introduced.

cs.CV↗

arXiv2024

Hybrid plasmonic Bound State in the Continuum entering the zeptomolar biodetection range

Optical Bound States in the Continuum are peculiar localized states within the continuous spectrum that are unaffected by any far-field radiation and intrinsic absorption, therefore possessing infinite mode lifetime and Q-factor. To date they have been widely studied in dielectric structures whereas their exploitation in lossy media, i.e. plasmonic nanostructures, still remains a challenge. Here, we show the emergence of a hybrid BIC state in a 2D system of silver-filled dimers, quasi-embedded in a high-index dielectric waveguide. The hybrid BIC onset is found to be highly dependent on the bare modes' spectral and spatial overlap, but particularly on the plasmonic field's intensity. By tailoring the hybridizing plasmonic/photonic fractions we select an ideal coupling regime for which the mode exhibits both, high Q-factor values and strong near-field enhancement tightly confined in the nanogap and a consequently extremely small modal volume. We demonstrate that this optical layout can be exploited in a proof-of-concept experiment for the detection of TAR DNA-binding protein 43, which outperforms the sensitivity of current label-free biosensing platforms, reaching the zeptomolar range of concentration.

physics.optics↗

arXiv2024

Implicit Neural Representations for Breathing-compensated Volume Reconstruction in Robotic Ultrasound

Ultrasound (US) imaging is widely used in diagnosing and staging abdominal diseases due to its lack of non-ionizing radiation and prevalent availability. However, significant inter-operator variability and inconsistent image acquisition hinder the widespread adoption of extensive screening programs. Robotic ultrasound systems have emerged as a promising solution, offering standardized acquisition protocols and the possibility of automated acquisition. Additionally, these systems enable access to 3D data via robotic tracking, enhancing volumetric reconstruction for improved ultrasound interpretation and precise disease diagnosis. However, the interpretability of 3D US reconstruction of abdominal images can be affected by the patient's breathing motion. This study introduces a method to compensate for breathing motion in 3D US compounding by leveraging implicit neural representations. Our approach employs a robotic ultrasound system for automated screenings. To demonstrate the method's effectiveness, we evaluate our proposed method for the diagnosis and monitoring of abdominal aorta aneurysms as a representative use case. Our experiments demonstrate that our proposed pipeline facilitates robust automated robotic acquisition, mitigating artifacts from breathing motion, and yields smoother 3D reconstructions for enhanced screening and medical diagnosis.

cs.RO↗

arXiv2024

Monitoring water contaminants in coastal areas through ML algorithms leveraging atmospherically corrected Sentinel-2 data

Monitoring water contaminants is of paramount importance, ensuring public health and environmental well-being. Turbidity, a key parameter, poses a significant problem, affecting water quality. Its accurate assessment is crucial for safeguarding ecosystems and human consumption, demanding meticulous attention and action. For this, our study pioneers a novel approach to monitor the Turbidity contaminant, integrating CatBoost Machine Learning (ML) with high-resolution data from Sentinel-2 Level-2A. Traditional methods are labor-intensive while CatBoost offers an efficient solution, excelling in predictive accuracy. Leveraging atmospherically corrected Sentinel-2 data through the Google Earth Engine (GEE), our study contributes to scalable and precise Turbidity monitoring. A specific tabular dataset derived from Hong Kong contaminants monitoring stations enriches our study, providing region-specific insights. Results showcase the viability of this integrated approach, laying the foundation for adopting advanced techniques in global water quality management.

cs.CV↗

arXiv2023

DXP: Billing Data Preparation for Big Data Analytics

In this paper, we present the data preparation activities that we performed for the Digital Experience Platform (DXP) project, commissioned and supervised by Doxee S.p.A.. DXP manages the billing data of the users of different companies operating in various sectors (electricity and gas, telephony, pay TV, etc.). This data has to be processed to provide services to the users (e.g., interactive billing), but mainly to provide analytics to the companies (e.g., churn prediction or user segmentation). We focus on the design of the data preparation pipeline, describing the challenges that we had to overcome in order to get the billing data ready to perform analysis on it. We illustrate the lessons learned by highlighting the key points that could be transferred to similar projects. Moreover, we report some interesting results and considerations derived from the preliminary analysis of the prepared data, also pointing out some possible future directions for the ongoing project, spacing from big data integration to privacy-preserving temporal record linkage.

cs.DB↗

arXiv2023

Optimizing Fault-Tolerant Quality-Guaranteed Sensor Deployments for UAV Localization in Critical Areas via Computational Geometry

The increasing spreading of small commercial Unmanned Aerial Vehicles (UAVs, aka drones) presents serious threats for critical areas such as airports, power plants, governmental and military facilities. In fact, such UAVs can easily disturb or jam radio communications, collide with other flying objects, perform espionage activity, and carry offensive payloads, e.g., weapons or explosives. A central problem when designing surveillance solutions for the localization of unauthorized UAVs in critical areas is to decide how many triangulating sensors to use, and where to deploy them to optimise both coverage and cost effectiveness. In this article, we compute deployments of triangulating sensors for UAV localization, optimizing a given blend of metrics, namely: coverage under multiple sensing quality levels, cost-effectiveness, fault-tolerance. We focus on large, complex 3D regions, which exhibit obstacles (e.g., buildings), varying terrain elevation, different coverage priorities, constraints on possible sensors placement. Our novel approach relies on computational geometry and statistical model checking, and enables the effective use of off-the-shelf AI-based black-box optimizers. Moreover, our method allows us to compute a closed-form, analytical representation of the region uncovered by a sensor deployment, which provides the means for rigorous, formal certification of the quality of the latter. We show the practical feasibility of our approach by computing optimal sensor deployments for UAV localization in two large, complex 3D critical regions, the Rome Leonardo Da Vinci International Airport (FCO) and the Vienna International Center (VIC), using NOMAD as our state-of-the-art underlying optimization engine. Results show that we can compute optimal sensor deployments within a few hours on a standard workstation and within minutes on a small parallel infrastructure.

cs.RO↗

arXiv2022

Surface Lattice Resonances in 3D Chiral Metacrystals for Plasmonic Sensing

Chiral lattice modes are hybrid states arising from chiral plasmonic particles assembled in ordered arrays with opportune periodicity. These resonances exhibit dependence on excitation handedness, and their observation in plasmonic lattices is strictly related to the chiroptical features of the fundamental plasmonic unit. Here, we show the emergence of chiral surface lattice resonances in properly engineered arrays of nanohelices, fully 3D chiral nano-objects fabricated by focused ion beam processing. By tuning the relative weight of plasmonic and photonic components in the hybrid mode, we analyze the physical mechanism of strong diffractive coupling leading to the emergence of the lattice modes, opening the way to the engineering of chiral plasmonic systems for sensing applications. In particular, we identify a coupling regime where the combination of a large intrinsic circular dichroism of the plasmonic resonance with a well-defined balance between the photonic quality factor and the plasmonic field enhancement maximizes the capability of the system to discriminate refractive index changes in the surrounding medium. Our results lay the foundation for exploiting circular dichroism in plasmonic lattices for high performance biosensing.

physics.optics↗

arXiv2021

Three-Dimensional Chiral MetaCrystals

Fine control of the chiral light-matter interaction at the nanoscale, by exploiting designed metamaterial architecture, represents a cutting-edge craft in the field of biosensing, quantum and classic nanophotonics. Recently, artificially engineered 3D nanohelices have demonstrated programmable wide chiroptical properties by tuning materials and architecture, but fundamental diffractive aspects that are to the origin of chiral resonances still remain elusive. Here, we proposed a novel concept of three-dimensional chiral MetaCrystal, where the chiroptical properties are finely tuned by in-plane and out-of-plane diffractive coupling. Different chiral dipolar modes can be excited along the helix arms, generating far field optical resonances and radiation pattern with in-plane side lobes and suggesting that a combination of efficient dipole excitation and diffractive coupling matching controls the collective oscillations among the neighbor helices in the chiral MetaCrystal. This concept enables the tailorability of chiral properties in a broad spectral range for a plethora of forefront applications, since the proposed compact chiral MetaCrystal can be suitable for integration with quantum emitters and can open perspectives in novel schemes of enantiomeric detection.

physics.optics↗

arXiv2021

Autonomous Robotic Screening of Tubular Structures based only on Real-Time Ultrasound Imaging Feedback

Ultrasound (US) imaging is widely employed for diagnosis and staging of peripheral vascular diseases (PVD), mainly due to its high availability and the fact it does not emit radiation. However, high inter-operator variability and a lack of repeatability of US image acquisition hinder the implementation of extensive screening programs. To address this challenge, we propose an end-to-end workflow for automatic robotic US screening of tubular structures using only the real-time US imaging feedback. We first train a U-Net for real-time segmentation of the vascular structure from cross-sectional US images. Then, we represent the detected vascular structure as a 3D point cloud and use it to estimate the longitudinal axis of the target tubular structure and its mean radius by solving a constrained non-linear optimization problem. Iterating the previous processes, the US probe is automatically aligned to the orientation normal to the target tubular tissue and adjusted online to center the tracked tissue based on the spatial calibration. The real-time segmentation result is evaluated both on a phantom and in-vivo on brachial arteries of volunteers. In addition, the whole process is validated both in simulation and physical phantoms. The mean absolute radius error and orientation error ($\pm$ SD) in the simulation are $1.16\pm0.1~mm$ and $2.7\pm3.3^{\circ}$, respectively. On a gel phantom, these errors are $1.95\pm2.02~mm$ and $3.3\pm2.4^{\circ}$. This shows that the method is able to automatically screen tubular tissues with an optimal probe orientation (i.e. normal to the vessel) and at the same to accurately estimate the mean radius, both in real-time.

cs.RO↗

arXiv2021

Femtomolar Biodetection by a Compact Core-Shell 3D Chiral Metamaterial

Highly sensitive and selective label free devices for real-time identification of specific biomarkers are expected to significantly impact the biosensing field. The ability of plasmonic systems to confine the light in nanometer volume and to manipulate it by tuning the size, shape and material features of the nanostructures, makes these systems promising candidates for biomedical devices. In this work we demonstrate the engineered sensing capabilities of a compact array of 3D metal dielectric core-shell chiral metamaterial. The intrinsic chirality of the nano-helices makes the system circular polarization dependent and unaffected by the background interferences, allowing to work even in complex environment. The core-shell architecture enhances the sensing properties of the chiral metamaterial on both in the far and near field, offering also a large surface to molecular immobilization. With our system we recorded sensitivity of about 800nm/RIU and FOM= 1276 RIU-1. The sensing abilities of the system is demonstrated with the detection of the of the TAR DNA-binding protein 43 (TDP-43) , a critical biomarker for the screening of neurodegenerative diseases. In particular, the sensor was tested in different environments, such as human serum, with concentrations ranging from 1pM down to 10fM, opening new perspectives for novel diagnostic tools.

physics.optics↗

arXiv2021

How many phases nucleate in the bidimensional Potts model?

We study the kinetics of the two-dimensional q > 4-state Potts model after a shallow quench slightly below the critical temperature and above the pseudo spinodal. We use numerical methods and we focus on intermediate values of q, 4 < q < 100. We show that, initially, the system evolves as if it were quenched to the critical temperature. The further decay from the metastable state occurs by nucleation of k out of the q possible phases. For a given quench temperature, k is a logarithmically increasing function of the system size. This unusual finite size dependence is a consequence of a scaling symmetry underlying the nucleation phenomenon for these parameters.

cond-mat.stat-mech↗