Human-robot manipulation of soft materials, such as fabrics, composites, and sheets of paper/cardboard, is a challenging operation that presents several relevant industrial applications. Estimating the deformation state of the manipulated material is one of the main challenges. Viable methods provide the indirect measure by calculating the human-robot relative distance. In this paper, we develop a data-driven model to estimate the deformation state of the material from a depth image through a Convolutional Neural Network (CNN). First, we define the deformation state of the material as the relative roto-translation from the current robot pose and a human grasping position. The model estimates the current deformation state through a Convolutional Neural Network, specifically, DenseNet-121 pretrained on ImageNet. The delta between the current and the desired deformation state is fed to the robot controller that outputs twist commands. The paper describes the developed approach to acquire, preprocess the dataset and train the model. The model is compared with the current state-of-the-art method based on a camera skeletal tracker. Results show that the approach achieves better performances and avoids the drawbacks of a skeletal tracker. The model was also validated over three different materials showing its generalization ability. Finally, we also studied the model performance according to different architectures and dataset dimensions to minimize the time required for dataset acquisition.

The programming complexity of industrial robots significantly limits their expansion in complex industrial applications. Consequently, research has focused extensively on the development of intuitive programming methods.This article proposes a framework for task-oriented programming introducing an intuitive and modular task structure. The framework provides an algorithm able to optimize the execution parameter of the tasks. A physical simulation environment allows accurate parameter optimization in a virtual environment providing feasible and safe results. Efficiency tests demonstrated the method's effectiveness, and a comparison with genetic and Bayesian -based ones have been conducted.

The automotive industry is involved in a massive transformation from standard endothermic engines to electric propulsion. The core element of the Electic Vehicle (EV) is the battery pack. Battery pack production misses regulations concerning manufacturing standards and safety-related issues. In such a fragmented scenario, the increasing number of EVs in circulation is growing exponentially, opening new challenges for managing the End-of-Life (EoL) of their battery packs. This paper analyses the use of robotics for EVs' battery pack disassembly to enable the extraction of the battery modules preserving their integrity for further reuse or recycling. The analysis highlights that a complete automatic disassembly remains difficult, while human-robot collaborative disassembly guarantees high flexibility and productivity. The paper introduces guidelines for designing a robotic cell to disassemble a battery pack with the support of an operator. The design of the workcell evaluates the technological requirements for disassembly, the analysis of potentially explosive atmospheres (ATEX) of the area around the battery pack, and the design and optimisation of robotics tools in the ATEX zone. The work proposes solutions according to the current international standards.

This article highlights the importance of continuous flights and sustainable maintenance techniques to maintain competitiveness in the aviation industry. Structural components represent a significant portion of overall maintenance costs, and advanced nondestructive inspection techniques can help reduce maintenance time and associated costs. With the increasing use of composite structures in aircraft, it is essential to understand the possible types of defects that can occur and to use techniques the appropriate nondestructive techniques (NDT) for their identification and characterization. Comprehensive knowledge of possible defects and proper application of NDT techniques can help simplify maintenance operations and ensure sustainable and safe aircraft operations. The use of NDT techniques makes it possible to verify the quality of the composite material and identify any defects. This allows timely action to correct any problems and ensure maximum reliability and durability of the material. In this context, this paper provides a comparison of several techniques as nondestructive methods on a sample of interest to the aerospace industry and evaluates the parameters of their use: shearography, thermography and ultrasound.

Obiettivi del seminario: Comprendere il fenomeno del chatter rigenerativo e da accoppiamento modale. Diagrammi di stabilità. Scelta dei parametri di lavorazione ottimali per ridurre il chatter. Legame tra cedevolezza dinamica della macchina e struttura del diagramma di stabilità: come valutare una FRF ottenuta dal FEM. Come distinguere il chatter rigenerativo dalle vibrazioni forzate nelle misure di accelerazione durante lavorazioni di fresatura. Soluzioni tecnologiche per mitigare le vibrazioni: utensili a passo variabile, a profilo "serrated-cutter", Spindle Speed Variation, tuning del sistema di controllo. Uso modulo SW MillingStab.

System for supporting an operator for navigation, which allows to at least partially solve the drawbacks highlighted above with reference to the background art, in particular, which allows supporting, in the most effective and reliable manner possible, an operator in assessing in a timely manner which decisions to make about the navigation maneuvers to be implemented on a ship to avoid a possible collision between the ship and an obstacle, be it a movable obstacle, such as another ship or a person at sea, or a fixed obstacle, such as mainland or a quay or another ship at berth in a harbor, taking into account other boundary conditions, such as the need to maneuver in narrow channels or close to shore or ni such bathymetric conditions as to require an appropriate assessment by the operator before performing any maneuver.

This document reports the activities carried out in collaboration of CNR and POLIBA in the context of WP8 in the CNR-STEMS's pilot site located in Torino, Italy. The main objective of this pilot is to test the robotic technologies developed in WP4 and the related sensing technologies developed in WP4 and WP5, through an extensive experimentation aimed at assessing the capability of the agrirobot to traverse different types of soil and to perform autonomously or with limited human supervision in-field crop monitoring tasks. In the following, first the pilot test site is described; then, all the pursued activities and related results are reported.

Computer Vision Systems (CVSs) have proved to be a powerful tool to evaluate the quality of agricultural products in a non-destructive, contactless, sustainable and objective way. Machine learning techniques have proved to simplify the development of CVS and to provide better performance and greater flexibility in matching the requirements of different products and environmental characteristics, but they are often computationally complex and difficult to be understood by humans. It is desirable to develop methods that exploit the benefits of learning and generate simple and fast solutions that are also interpretable by humans. The approach described in this paper analyses a previously developed and effective machine learning model to extract the information useful to develop computationally light and easily understandable algorithms that evaluate the characteristics of interest on rocket leaves. A Random Forest model previously developed to classify visual quality and to estimate chlorophyll and ammonia contents in rocket leaves has been studied to identify a small set of visual characteristics (colours) that correlate with relevant properties of the product. These visual characteristics have been used as input for several simple, fast and easily understandable algorithms that classify visual quality (QL) and estimate chlorophyll and ammonia contents with lower computational complexities with respect to the original Random Forest model. Results obtained by these methods are shown and compared with the ones provided by the original Random Forest model. All the algorithms provided a good separation between marketable and non-marketable samples. They required from 1ms to 22ms to classify a new sample instead of the 25ms of the original Random Forest model. Additionally, two methods provided good prediction of chlorophyll (R2v = 0.70) and ammonia (R2v = 0.72) contents requiring only 3ms and 1ms respectively.

Report per definire gli esperimenti di foratura da eseguire su provini in Titanio per il progetto LAMPO.

Titan project aims to improve immunotherapy, targeting the efficiency of methods to obtain genetically engineered T cells. Immunotherapy has achieved great success in clinical trials, but it is currently very expensive in terms of time required for analysis, reagents and samples. TITAN aims to the continuous sampling of critical quality attributes, in order to quickly recognize deviations from the desired range and take appropriated corrective actions of process parameters, for an optimal outcome. To achieve its aims, TITAN is currently developing microfluidic and sensing tools for the accurate and efficient real-time monitoring of the T-cells amplification process.

This paper investigates the potential of a consumer-grade infrared stereo camera, i.e. the Intel RealSense D435, to automatically extract crop status information, such as Normalized Difference Vegetation Index (NDVI), in arable and permanent crops. The sensing device includes two infrared (IR) sensors for depth calculation and one colour sensor, which provide, for each point of the scene, both IR and visible light information thus making it possible pixel per pixel NDVI estimations. Measurements were performed on various arable crops including corn (Zea mays) and barley (Ordeum vulgare) and on two vine varieties, Freisa and Malvasia, and were compared to measurements taken by a Trimble GreenSeeker handheld crop sensor. Results show that the RealSense camera tends to underestimate NDVI values compared to the GreenSeeker, with squared correlation coefficient r2 = 0.68. The fitted regression equation is successively applied to correct new camera observations, resulting in good agreement with the GreenSeeker output. The use of the RGB-D camera to simultaneously provide canopy height measurements by a farmer robot is also demonstrated in a Malvasia field, showing that the proposed system can be effectively adopted for fully automated plant-scale monitoring of vineyards.

The use of natural dyes in textile manufacturers is growing to implement eco-friendly processes. Natural dyes, however, require additives to be absorbed by the textile substrate. Metals-based mordants are typically used in spite of environmental pollution. In this work, waste wool hydrolysates were employed to test the possibility of dyeing cotton and wool fabrics. The process conditions to treat the fabrics with the wool hydrolysates were studied to set up the mordanting phase and prepare the fabrics for the dyeing process. Preliminary results show that the wool hydrolysates improve the dyeing of wool and enable that of cotton.

Software tool to compute the stability lobes Diagram in milling considering a 3D process model. Enhanced algorithm for lobes trimming.

The textile industry is a pillar of the manufacturing sector worldwide, but it still represents a significantly polluting production sector since it is energy-, water- and natural resources-intensive. Herein, we recovered waste wool that does not meet the technical requirements to be used for yarns and fabrics to prepare materials for wastewater remediation. The wool underwent an alkaline treatment, eventually saturated with FeCl3 and then left at RT or heated at 180 °C to induce crosslinking/stabilization. The materials were characterized by SEM, TGA, DSC, FT-IR and water uptake tests. The main findings concern the impact of alkaline treatment on morphology and crystalline structure; additionally, the samples with iron displayed a behavior attributable to a crosslinking effect operated by Fe3+. Preliminary batch adsorption experiments were performed with five samples: bare wool (S1), S_Wool_NaOH (S2), S_Wool_NaOH_180 (S3), S_Wool_Fe_NaOH (S4) and S_Wool_Fe_NaOH_180 (S5). Samples 1, 2 and 3 showed to be inefficient in phosphate removal, so further batch experiments were carried out only for S4 and S5. Investigated samples showed similar adsorbed amounts of 16.653 and 16.902 mg/g, respectively, at the initial phosphate concentration of 20 mg/L. A high removal percentage was obtained in a wide pH spectrum - from 3 to 10. Results suggest that the proposed Fe-added adsorbents have the potential for phosphate removal from wastewater.

STIIMA-CNR was asked to prepare a full LCA study of MAGIC technology, analyzing its environmental impact according to the ISO 14040/44 standard. This report presents the results obtained during the modelling of the MAGIC process. The study will evaluate the environmental impact of the production of Spongel and Airgel developed by MAGIC. The LCA includes raw materials collection, transportation, and energy consumption as well as other flows involved in the MAGIC production process. The system boundaries and declared unit will be defined in accordance with ISO 14040/44 standards.

Development of a methodological report aimed at a possible certification reporting the carbon footprints of Vibram SpA's Albizzate production hub

Development of LCA study on textiles in accord with INDUSTRIE CHIMICHE FORESTALI S.p.A. with the aim of EPD certification of Extruded non-woven fabrics and Impregnated cotton fabrics.

Preventing and reducing physical and cognitive decay in older adults is among the challenges of Healthcare 5.0. The research project ActivE3 aims at promoting older adults' health and social inclusion through regular physical activity, leveraging an ICT-enabled network composed of elderlies, young people, and clinical personnel. Using a virtual reality-based application (SocialBike), older adults can adopt a healthier lifestyle while socializing with youngers through collaborative exercise. The exercise involves both physical and cognitive training, as users must cycle on a stationary bike while recognizing target animals or objects appearing along the way. Using wearable sensors and relying on clinical expertise, ActivE3 exploits semantic reasoning capabilities to tailor exercise's workload and goals according to the specific users' health conditions and abilities. The system stores the results from each exercise session and dispatches them to clinical personnel, to support the non-invasive monitoring of frail older adults' health conditions.

The work is focused on the study of antibacterial fabrics, which can be applied in many different sectors. Cotton and polyamide 6,6 fabrics were treated with chitosan, a non-toxic antibacterial biopolymer that allows the dyeing of the textile substrate, and tested against Gram-positive and Gram-negative bacteria. The objective is to evaluate the efficiency over time of the chitosan antibacterial action by performing the standard antibacterial tests at different contact times. Since the fabrics must keep antibacterial property preserved also after dyeing and washing, the experiments were executed on dyed and washed chitosan-treated fabrics.

Cotton and polyamide 6,6 fabrics coated with chitosan, a natural biopolymer, have been tested against two different bacteria strains: Staphylococcus aureus as Gram-positive bacterium and Escherichia coli as Gram-negative bacterium. Using the ASTM standard method (Standard Test Method for Determining the Antimicrobial Activity of Antimicrobial Agents Under Dynamic Contact Conditions) for antibacterial testing, the treated fabrics is contacted for 1 h with the bacterial inoculum, the present study aims to investigate the possibility to reach interesting results considering shorter contact times. Moreover, the antibacterial activity of chitosan-treated fibers dyed with a natural dye, Carmine Red, was evaluated since chitosan has an interesting property that favors the attachment of the dye to the fiber (cross-linking ability). Finally, fabric samples were tested after washing cycles to verify the resistance of the dye and if the antibacterial property was maintained.