Broadband passive SONAR systems must detect multiple acoustic sources in environments marked by high noise and limited prior information. Traditional model-based approaches, such as Cell Averaging Constant False Alarm Rate (CA-CFAR), rely on analytical models, which can fail to fully capture complex conditions, creating a need for data-driven methods. We propose a detection framework that integrates a Poisson Random Finite Set (RFS)-based loss function with a Vision Transformer (ViT) architecture. The ViT component processes Bearing Time History (BTH) waterfall data patches, capturing local and global acoustic features, while the Poisson RFS loss naturally accommodates an unknown number of sources. A test-time augmentation (TTA) strategy further boosts performance by exploiting the circular symmetry in bearing data. Experimental results show that our approach improves upon a conventional CFAR detector and CNN-based baselines across Receiver Operating Characteristic (ROC), Precision-Recall, and detection probability metrics. In particular, pairing ViT with the RFS loss yields higher accuracy and robustness to noise, all within a computationally feasible framework for real-time detection tasks.

In this paper, we propose a robust and computationally efficient pipeline for transcribing speech in noisy environments, such as workshops and industrial settings. The pipeline is designed to operate offline, making it suitable for resource-constrained scenarios. It begins with a noise filtering module that preprocesses audio recordings to suppress background noise and enhance speech clarity. The filtered audio is then passed to an Automatic Speech Recognition (ASR) model, which generates initial transcription outputs. Given the potential for transcription errors in challenging acoustic conditions, we incorporate a quantized Small Language Model (SLM) trained on an ontology of defects related to the industrial environment to post-process and correct these errors. The quantization of the SLM significantly reduces its computational footprint while maintaining correction accuracy, enabling the pipeline to function effectively on low-resource devices. Experimental evaluations demonstrate the effectiveness of the proposed approach in improving transcription quality in noisy conditions, highlighting its practicality for offline and resource-limited applications. In fact, preliminary validation on a synthetic dataset of 200 sentences in Italian and English showed a consistent F1 score of 87.04% for SNR as challenging as-5 dBW (Decibels Watt) in Italian sentences and 91.25% in English sentences, with the least computationally expensive version of Whisper (Whisper Tiny) and the SLM correction.

This paper presents an extended target tracking method to track trains using Distributed Acoustic Sensing (DAS) data. The problem is approached using a measurement likelihood based on a Set of Points on a Rigid Body (SPRB) model applied to a clustered version of the Poisson Multi-Bernoulli Mixture filter. The method efficiently handles asymmetric noise within the set of measurements returned by each train, and proposes a solution to merged measurements appearing at crossings. We use experimental data obtained from trains to show that the proposed algorithm has lower localisation and false target error, leading to better performance in terms generalized optimal sub-pattern assignment (GOSPA) metric.

We present theoretical and experimental results regarding the development and the control of a two-link robotic arm with remotized actuation via rolling diaphragm hydrostatic transmissions. We propose a dynamical model capturing the essential dynamics of the developed transmission/robot ensemble and implement a control strategy consisting of two nested loops, the inner one performing high-bandwidth joint torque regulation and the outer one producing various types of compliance responses for effective human–robot interactions. Extensive sets of experiments, testing both the low-level torque controller and the high-level compliance controller, confirm the effectiveness of the proposed hardware-software remotization architecture.

The observation of the anatomy of agile animals and their locomotion capabilities emphasizes the importance of fast and lightweight legs and confirms the intrinsic compliance integrated into muscle-tendon units as a major ingredient for energy efficient and robust locomotion. This quality is especially relevant for distal leg segments which are subject to aggressive dynamics. Legged robots are accordingly designed to improve dynamic performance by lightweight mechanisms combined with series elastic actuation systems. However, so far no designs are available that feature all characteristics of a perfect distal legged locomotion actuator such as a lightweight and low-inertia structure, with high mechanical efficiency, no stick and sliding friction, and low mechanical complexity. With this goal in mind, we propose a novel robotic leg which integrates all above features. Specifically, we develop, implement, and characterize a bioinspired robot leg that features a lightweight Series ELastic Diaphragm distal Actuator (SELDA) for active control of foot motion. We conducted experiments to compare two leg configurations, with and without foot actuation, to demonstrate the effectiveness of the proposed solution in agile forward hopping controlled by a central pattern generator. We studied how tuning SELDA's activation timing can adjust the robot's hopping height by 11% and its forward velocity by 14%, even with comparatively low power injection to the distal joint.

Under the standard multiple target tracking models and a Poisson point process birth model, the Poisson multi-Bernoulli mixture (PMBM) filter provides the closed-form recursion to computing the posterior density over the set of targets. Without approximations, the PMBM computational complexity rapidly rises in time due to the increasing number of data association hypotheses. This paper presents innovative strategies for merging Bernoulli components for the same potential target reducing the number of single-target hypotheses in the PMBM filter, aiming to lower its computational complexity while keeping its performance high. We use several measures to compute the similarity between different Bernoulli components. Simulation results show that the proposed algorithms show performance close to the PMBM filter without Bernoulli merging, as measured by the generalized optimal sub-pattern assignment (GOSPA) metric, with a significantly reduced execution time.

This paper introduces a novel hydrostatic air-liquid torque transmission system for an upper limb exoskeleton. The proposed design is based on remote electrical actuation, with grounded motors, combined with high performance fluid power transmission employed to deliver the power to the joints of the exoskeleton. The fluid transmission is based on rolling membrane cylinders that guarantee leakage-free operation, no backlash, and virtually zero stick-friction. This solution makes it possible to obtain easy controllability, good efficiency, intrinsic backdrivable operation, and reduced mass/inertia of the links of the robot. Additionally, the proposed system can be potentially implemented at relatively low-costs thanks to the employment of standard components and an architecture based on a modular approach. A test bench of the fluid transmission system is developed and a campaign of experiments is conducted to characterize its static/dynamic response for different choice of design parameters. In addition, we present a preliminary complete integrated arrangement of an upper limb exoskeleton equipped with the proposed transmission system. Results confirm the feasibility of the proposed actuation approach for the envisaged application.

Recent researches on image forensics have led to the design of algorithms to study the phylogenetic relationship between near-duplicate (ND) images. The proposed solutions aim at reconstructing the image phylogeny tree (IPT), and they have immediate applications in security, law and copyright enforcement, and news tracking services. Anyway, the effectiveness of such strategies strictly depends on the accuracy in characterizing image similarities. In this paper, we show that it is possible to take into account additional information to better reconstruct the IPT. More specifically, we propose a set of features that blindly model the processing age of an image, i.e., how much an image has been edited in its lifetime. By exploiting these features, it is possible to improve the performance of IPT reconstruction by increasing the accuracy and reducing the computational complexity.

This paper presents a system designed to induce, in healthy subjects, artificial hand-tremor that is observed in persons affected by neurological impairments. The objective is to allow a healthy user to feel in first person the effect of the impairment while performing common manipulative tasks in order for her/him to understand and gain empathy with the impaired person. The developed tool is based on a wrist-attached desktop haptic interface with a workspace that is comparable to that of the arm of the user. Such device is able to exert controlled forces on the user's wrist and induce hand-tremor whose frequency and amplitude is correlated with different pathologies. The control of the device is based on the recording and playback of tremor signals acquired by a motion tracker. In this paper, we present the system with its dynamic characteristics and three different types of controller are experimentally tested and compared.

This paper reports a novel intersection support (IS) system for motorcycles developed through the SAFERIDER project (IS). The IS function described is built on a receding horizon approach that is designed for a set of predefined intersection scenarios. In the receding horizon scheme, a nonlinear optimal control problem is repetitively solved in real time, yielding a reference motion plan. The initial value of the longitudinal jerk (control input) of each plan is used as a measure of the correction that the rider has to apply to conform to an optimal-safe maneuver. This technique has the advantage of yielding a homogenous measure of the threat independent of the scenario, and it is directly linked with the control variable that the rider should use to accordingly change the vehicle's longitudinal dynamics. Additionally, the receding horizon approach naturally accommodates road geometry and constraint attributes, motorcycle dynamics, rider input, and riding styles. Warning feedback is given to the rider by an appropriate combination of human-machine interface elements, such as the haptic throttle, the vibrating glove, and the visual display. This paper explains the IS concept, discusses the implementation aspects of the proposed receding horizon approach, and presents the results of pilot tests conducted on a top-of-the-range riding simulator.

This paper describes the design, the preliminary evaluation and proposes a control strategy of a novel distributed tactile transducer for finger tip stimulation. The presented study has been conducted for the realization of a compact tactile device aiming at integration with a kinesthetic feedback systems. The transducer is a 5×6 array based on custom electromechanical mini-solenoid designed and optimized for reduced encumbrance and lightweight. The realized actuator has a diameter of 2.4mm and is capable of delivering a maximum force of 73mN. In the first section we present the electro-mechanical design, the optimization and the first experimental test of a prototype for the new transducer. In the second section we show the electronic design and a strategy for controlling arrays of transducers with a reduced number of connectors. This principle is based on active matrix addressing of LCD displays.

The PERCRO laboratory of Scuola Superiore Sant'Anna has recently completed the development and functional assessment of the Body Extender (BE) system, an advanced wearable robot expressly conceived for augmenting the human strength for handling of heavy materials in unstructured environment. The system is composed by four robotic limbs with anthropomorphic kinematics and has a total of 22 independently actuated degrees of freedom. The leg locomotion and the force servo-amplification allow operations in environments that are hardly accessible by the conventional handling systems preserving the force sensibility during the manipulative tasks. Possible applications are handling of military materials in narrow spaces, rescuing of victims in natural and human provoked disasters and handling of heavy parts in the manufacturing of large products. The paper reports the system specifications taken as a reference for the design, the criteria and verification methods, the architectural solutions used for the implementation of mechanics, electronic and control components and the results of the preliminary experimental assessment.

Advanced robotics needs a new breed of actuators, capable to exhibit a large number of desirable features, ranging from high power/torque density, high efficiency, zero backlash and low noise, to low reflected mechanical impedance, high bandwidth and accuracy. Even if it is quite evident that to fully match these requirements new basic actuation principles have to be investigated and developed in the long term, there is still scope now for innovating the field by combining mature components into new actuation schemes. This paper reports the development and the experimental evaluation of a new actuator, aiming at improving the torque density and the mechanical efficiency. The device has shown impressive performances being able to exert up to 500Nm continuous torque and 800Nm peak torque with 85% mechanical efficiency and zero backlash, up to 60°/s maximum output speed for a total weight of just 6Kg, comprising the structural case covering the internal mechanics. The actuator has been expressly conceived as an actuation module to be integrated in a fully powered whole body exoskeleton intended for material handling in tight and unstructured environments (see Fig.1).

This paper deals with the mechanical and control design of an exoskeletric power extender for the whole human body. A critical issue in the design of such kid of devices is granting a sufficient level of transparency. The authors propose two design conditions based on tracking force threshold and equilibrium considerations that should be complied. This methodology has been applied to the specific design of a body extender for material handling that is currently being developed at the PERCRO (PERceptual RObotics) Lab of Scuola Superiore S. Anna of Pisa, Italy.

This paper deals with the mechanical design of a novel haptic hand exoskeleton (HE) that allows exerting controlled forces on the fingertip of the index and thumb of the operator. The proposed device includes several design solutions for optimizing the accuracy and mechanical performances. Remote centers of motion mechanisms have been adopted for delocalizing the encumbrance of linkages of the structure away from the operator's fingers. An improved stiffness of the transmission and reduced requirements for the actuators have been achieved thanks to a novel patent pending principle for integrating speed reduction ratio with the transmission system.

This paper describes the design, the development and the tests of an innovative 6 degrees of freedom (DoFs) mechanical tracker. The new device has a modular structure that exploits three mechanical units each composed of two rotational joints and allows to scale the usable workspace by substituting the connecting links. The sensing principle for the joint angles measurement is based on an innovative hall-effect angle sensor with high resolution, developed and conceived for low cost applications. The system that has been realized and tested is conceived for the tracking of portable haptic devices. Furthermore, the system includes a weight balancing system that allows to exploit the mechanical structure of the tracker for balancing a given weight located at the end-effector of the device.

The EU funded RTD project "HAPTEX" addresses the challenge of developing a Virtual Reality (VR) system for the realistic and accurate rendering of the physical interactions of humans with textiles, through the real-time generation of artificial visual and haptic stimuli. This challenge concerns the development of both the SW and the HW components of the VR system, as well as it implies a substantial advancement in the understanding of the mechanisms underlying the human haptic perception of fine physical properties like those of textiles. This paper reports some important details relating to the technical implementation of the developed HW and SW components with special emphasis on the issues related to their integration into a single VR system. Furthermore some preliminary results relating to the functional tests carried out on the integrated system are also reported.

This paper presents the synthesis and the analysis of the kinematics of a new robotic parallel wrist for laparoscopic surgery applications. The main properties of this new wrist are the wide singularity free orientation workspace and the capability of making large rotations of the end-effector with small rotation of the actuators. First, it is shown how these features suit the application of minimally invasive surgery. Secondly, the kinematics is described showing its working principle that allows the achievement of rotation multiplication. The forward kinematics problem is solved geometrically. Afterwards, a methodology based on screw theory for the solution of the differential kinematics is proposed. Finally a workspace representation is presented making a comparison with another known parallel wrist