Search

Artificial agents, particularly humanoid robots, interact with their environment, objects, and people using cameras, actuators, and physical presence. Their communication methods are often pre-programmed, limiting their actions and interactions. Our research explores acquiring non-verbal communication skills through learning from demonstrations, with potential applications in sign language comprehension and expression. In particular, we focus on imitation learning for artificial agents, exemplified by teaching a simulated humanoid American Sign Language. We use computer vision and deep learning to extract information from videos, and reinforcement learning to enable the agent to replicate observed actions. Compared to other methods, our approach eliminates the need for additional hardware to acquire information. We demonstrate how the combination of these different techniques offers a viable way to learn sign language. Our methodology successfully teaches 5 different signs involving the upper body (i.e., arms and hands). This research paves the way for advanced communication skills in artificial agents.

A core part of the rehabilitation scheduling process consists of planning rehabilitation physiotherapy sessions for patients, by assigning proper operators to them in a certain time slot of a given day, taking into account several legal, medical and ethical requirements and optimizations, e.g., patient's preferences and operator's work balancing. Being able to efficiently solve such problem is of upmost importance, in particular after the COVID-19 pandemic that significantly increased rehabilitation's needs. In this paper, we present a two-phase solution to rehabilitation scheduling based on Answer Set Programming, which proved to be an effective tool for solving practical scheduling problems. We first present a general encoding, and then add domain specific optimizations. Results of experiments performed on both synthetic and real benchmarks, the latter provided by ICS Maugeri, show the effectiveness of our solution as well as the impact of our domain specific optimizations. Under consideration in Theory and Practice of Logic Programming (TPLP)., Comment: Under consideration in Theory and Practice of Logic Programming (TPLP)

Dissolution testing is part of the target product quality that is essential in approving new products in the pharmaceutical industry. The prediction of the dissolution profile based on spectroscopic data is an alternative to the current destructive and time-consuming method. Raman and near-infrared (NIR) spectroscopies are two fast and complementary methods that provide information on the tablets' physical and chemical properties and can help predict their dissolution profiles. This work aims to compare the information collected by these spectroscopy methods to support the decision of which measurements should be used so that the accuracy requirement of the industry is met. Artificial neural network models were created, in which the spectroscopy data and the measured compression curves were used as an input individually and in different combinations in order to estimate the dissolution profiles. Results showed that using only the NIR transmission method along with the compression force data or the Raman and NIR reflection methods, the dissolution profile was estimated within the acceptance limits of the f2 similarity factor. Adding further spectroscopy measurements increased the prediction accuracy., Comment: 11 pagee, 5 figures, 3rd International Conference on Data Science and Machine Learning (DSML 2022)

Learning fine-grained movements is a challenging topic in robotics, particularly in the context of robotic hands. One specific instance of this challenge is the acquisition of fingerspelling sign language in robots. In this paper, we propose an approach for learning dexterous motor imitation from video examples without additional information. To achieve this, we first build a URDF model of a robotic hand with a single actuator for each joint. We then leverage pre-trained deep vision models to extract the 3D pose of the hand from RGB videos. Next, using state-of-the-art reinforcement learning algorithms for motion imitation (namely, proximal policy optimization and soft actor-critic), we train a policy to reproduce the movement extracted from the demonstrations. We identify the optimal set of hyperparameters for imitation based on a reference motion. Finally, we demonstrate the generalizability of our approach by testing it on six different tasks, corresponding to fingerspelled letters. Our results show that our approach is able to successfully imitate these fine-grained movements without additional information, highlighting its potential for real-world applications in robotics.

Signed Language Processing (SLP) concerns the automated processing of signed languages, the main means of communication of Deaf and hearing impaired individuals. SLP features many different tasks, ranging from sign recognition to translation and production of signed speech, but has been overlooked by the NLP community thus far. In this paper, we bring to attention the task of modelling the phonology of sign languages. We leverage existing resources to construct a large-scale dataset of American Sign Language signs annotated with six different phonological properties. We then conduct an extensive empirical study to investigate whether data-driven end-to-end and feature-based approaches can be optimised to automatically recognise these properties. We find that, despite the inherent challenges of the task, graph-based neural networks that operate over skeleton features extracted from raw videos are able to succeed at the task to a varying degree. Most importantly, we show that this performance pertains even on signs unobserved during training., Comment: Accepted at ACL 2022 main conference

Inspired by recent developments in natural language processing, we propose a novel approach to sign language processing based on phonological properties validated by American Sign Language users. By taking advantage of datasets composed of phonological data and people speaking sign language, we use a pretrained deep model based on mesh reconstruction to extract the 3D coordinates of the signers keypoints. Then, we train standard statistical and deep machine learning models in order to assign phonological classes to each temporal sequence of coordinates. Our paper introduces the idea of exploiting the phonological properties manually assigned by sign language users to classify videos of people performing signs by regressing a 3D mesh. We establish a new baseline for this problem based on the statistical distribution of 725 different signs. Our best-performing models achieve a micro-averaged F1-score of 58% for the major location class and 70% for the sign type using statistical and deep learning algorithms, compared to their corresponding baselines of 35% and 39%., Comment: 5 pages

The problem of scheduling chemotherapy treatments in oncology clinics is a complex problem, given that the solution has to satisfy (as much as possible) several requirements such as the cyclic nature of chemotherapy treatment plans, maintaining a constant number of patients, and the availability of resources, e.g., treatment time, nurses, and drugs. At the same time, realizing a satisfying schedule is of upmost importance for obtaining the best health outcomes. In this paper we first consider a specific instance of the problem which is employed in the San Martino Hospital in Genova, Italy, and present a solution to the problem based on Answer Set Programming (ASP). Then, we enrich the problem and the related ASP encoding considering further features often employed in other hospitals, desirable also in S. Martino, and/or considered in related papers. Results of an experimental analysis, conducted on the real data provided by the San Martino Hospital, show that ASP is an effective solving methodology also for this important scheduling problem. Under consideration for acceptance in TPLP., Comment: Paper presented at the 37th International Conference on Logic Programming (ICLP 2021), 16 pages

A numerical tool for analysing spatially anisotropic electron populations in electron cyclotron resonance (ECR) plasmas has been developed, using a trial-and-error electron energy distribution function (EEDF) fitting method. The method has been tested on space-resolved warm electrons in the energy range $2-20\,\mathrm{keV}$, obtained from self-consistent simulations modelling only electron dynamics in ECR devices, but lacked real-world validation. For experimentally benchmarking the method, we attempted to numerically reproduce the experimental X-ray emission spectrum measured from an argon plasma. Results of this analysis have provided crucial information about density and temperature of warm electrons, and competing distributions of warm and hot electron components. This information can be fed back to simulation models to generate more realistic data. Subsequent application of the numerical tool as described to the improved simulation data can result in continuous EEDFs that reflect the nature of charge distributions in anisotropic ECR plasmas. These functions can be also applied to electron dependent reactions, in order to reproduce experimental results, like those concerning space-dependent K$\alpha$ emissions.

The incumbent technology for bringing light to the nanoscale, the near-field scanning optical microscope, has notoriously small throughput efficiencies - of the order of 10^(-4) - 10^(-5), or less. We report on a broadband, topological, unidirectionally-guiding structure, not requiring adiabatic tapering and in principle enabling near-perfect (ideally, ~100%) optical transmission through an unstructured single (POTUS) arbitrarily-subdiffraction slit at its end. Specifically, for a slit width of just lambda_eff / 72 (lambda_0 / 138) the attained normalized transmission coefficient reaches a value of 1.52, while for a unidirectional-only (non-topological) device the normalized transmission through a lambda_eff / 21 (~lambda_0 / 107) slit reaches 1.14 - both, limited only by inherent material losses, and with zero reflection from the slit. The associated, under ideal conditions, near-perfect optical extraordinary transmission (POET) has implications, among diverse areas in wave physics and engineering, for high-efficiency, maximum-throughput nanoscopes and heat-assisted magnetic recording devices., Comment: 10 pages, 4 figures

The Operating Room Scheduling (ORS) problem is the task of assigning patients to operating rooms, taking into account different specialties, lengths and priority scores of each planned surgery, operating room session durations, and the availability of beds for the entire length of stay both in the Intensive Care Unit and in the wards. A proper solution to the ORS problem is of primary importance for the healthcare service quality and the satisfaction of patients in hospital environments. In this paper we first present a solution to the problem based on Answer Set Programming (ASP). The solution is tested on benchmarks with realistic sizes and parameters, on three scenarios for the target length on 5-day scheduling, common in small-medium sized hospitals, and results show that ASP is a suitable solving methodology for the ORS problem in such setting. Then, we also performed a scalability analysis on the schedule length up to 15 days, which still shows the suitability of our solution also on longer plan horizons. Moreover, we also present an ASP solution for the rescheduling problem, i.e. when the off-line schedule cannot be completed for some reason. Finally, we introduce a web framework for managing ORS problems via ASP that allows a user to insert the main parameters of the problem, solve a specific instance, and show results graphically in real-time. Under consideration in Theory and Practice of Logic Programming (TPLP)., Comment: Under consideration in Theory and Practice of Logic Programming (TPLP)

In the context of the INFN project PANDORA_Gr3 (Plasma for Astrophysics, Nuclear Decays Observation and Radiation for Archaeometry) and of multi-messenger astronomy, we propose a feasibility study for in-laboratory plasma's opacity investigation, in an environment resembling thermodynamic conditions typical of the ejecta of compact binary mergers containing at least a neutron star. We aim to advance knowledge on the physics of kilonovae, the electromagnetic transients following a merger, which are relevant for the study of the origin of heavy nuclei in the Universe produced via r-process nucleosynthesis. In this paper, we present preliminary results of numerical simulations for some physics cases considered in the light of a possible experimental setup for future in-laboratory opacity spectroscopic measurements., Comment: 5 pages, 2 figures. Invited by S.I.F. to appear in Nuovo Cimento C

This paper discusses the capture of an ion beam in a magnetized plasma of an Electron Cyclotron Resonance Ion Source based Charge Breeder, as modelled by numerical simulations. As a relevant step forward with respect to previous works, here the capture is modeled by considering a plasma structure determined in a self-consisent way. The plasmoid-halo structure of the ECR plasma - that is consisting of a dense core (the plasmoid) surrounded by a rarefied halo - is further confirmed by the self-consistent calculations, having also some fine structures affected by the electromagnetic field distribution and by the magnetostatic field profile. The capture of Rb1+ ions has been investigated in details, vs. various plasma parameters, and then compared to experimental results., Comment: New results about a self-consistent modeling of magnetized plasmas

We introduce a new architecture called ChoiceNet where each layer of the network is highly connected with skip connections and channelwise concatenations. This enables the network to alleviate the problem of vanishing gradients, reduces the number of parameters without sacrificing performance, and encourages feature reuse. We evaluate our proposed architecture on three benchmark datasets for object recognition tasks (ImageNet, CIFAR- 10, CIFAR-100, SVHN) and on a semantic segmentation dataset (CamVid).

Nuclear astrophysics, the union of nuclear physics and astronomy, went through an impressive expansion during the last twenty years. This could be achieved thanks to milestone improvements in astronomical observations, cross section measurements, powerful computer simulations and much refined stellar models. Italian groups are giving quite important contributions to every domain of nuclear astrophysics, sometimes being the leaders of worldwide unique experiments. In this paper we will discuss the astrophysical scenarios where nuclear astrophysics plays a key role and we will provide detailed descriptions of the present and future of the experiments on nuclear astrophysics which belong to the scientific programme of INFN (the National Institute for Nuclear Physics in Italy)., Comment: Added paragraphs 5.6 and 7.2. Paragraph 7.3 (former 7.2) revised. Accepted for publication in La Rivista del Nuovo Cimento