ABSTRACT. Designing effective hand rehabilitation devices requires integrating clinical needs with engineering solutions. This study shows how to apply the PICO framework (Population/Problem, Intervention, Comparison, Outcome) to guide the development of two robotic hand exoskeletons: a rigid device and a tendon-driven soft glove. The rigid exoskeleton provides precise, repeatable finger actuation, suitable for patients requiring controlled movements, while the soft glove offers compliant, adaptable assistance for users with low hand strength or spasticity. Comparative analysis highlights differences in actuation, adaptability, and user interaction. Preliminary tests demonstrate improved range of motion and exercise repeatability for both devices. The PICO approach proves a practical tool to systematically translate clinical requirements into user-centered rehabilitation device design.

ABSTRACT. Autonomous systems, such as vehicles and robots, are rapidly advancing, and their ability to navigate complex and dynamic environments is crucial for practical deployment. This need is particularly evident in assistive mobility devices, such as wheelchairs, where safety, autonomy, and adaptability are paramount. We introduce a hierarchical planning framework that integrates both a macro planner and a micro planner for navigating robots in crowded environments. The macro planner provides high-level guidance by identifying preferred regions of the environment based on macroscopic features, while the micro planner operates at a finer scale, accounting for dynamic constraints and safety considerations to compute feasible short-term trajectories. This design enables the robot to act proactively by anticipating possible deviations in the predicted trajectories of surrounding obstacles. As a result, the robot avoids collisions through smoother, less abrupt motion adjustments. As a concrete application, we propose the design of an autonomous wheelchair capable of safely and efficiently navigating both structured and dynamic environments. The system is divided into two main layers: low-level motor control and high-level motion planning. This architecture allows for fine-grained control of movement while also enabling intelligent decision-making in the presence of obstacles. By embedding safety-driven algorithms into the control system, the wheelchair is not only responsive to real-time changes in its environment but also adaptive to unexpected scenarios, thereby ensuring that users can maintain independence without compromising safety.

ABSTRACT. Lower-limb exoskeletons (LLEs) have demonstrated considerable potential for rehabilitation, assistive, and augmentative purposes. Besides, existing devices typically lack user-friendliness and real-time adaptation to unstructured environments. We propose a modular framework for adaptive locomotion, consisting of a robotic vision module for perception of the environment and a step generation module for executing foot trajectories in real time. This research highlights the ongoing development of a multi-step planning module to generate coordinated sequences of steps that will enable the exoskeleton to run actions in advance, respecting environmental and task constraints.

ABSTRACT. This paper presents examples of green-aware assistive robotic solutions developed at University of Calabria addressing critical challenges in healthy aging and rehabilitation while minimizing environmental impact. Our systematic design methodology incorporates sustainability principles, producing innovative mechatronic devices including energy-efficient upper-limb rehabilitation systems, sustainable cable-driven exoskeletons, and low-power wheelchair-mounted feeding assistants. These solutions feature intuitive interfaces, energy-optimized telemonitoring, and adaptive green-aware control systems for clinical and home environments. Experimental validation demonstrates significant improvements in user engagement, motor function recovery, and quality of life while achieving up to 30% energy reduction compared to traditional systems. The approach combines advanced robotics with user-centered and environmentally conscious design principles, making assistive technologies more sustainable and accessible for elderly populations and individuals with disabilities.

ABSTRACT. AuReha is an intelligent wearable system for upper-limb rehabilitation, integrating inertial sensors, serious games, and a web platform for remote monitoring. Its clinical validation, designed under Medical Device Regulation (MDR) 2017/745, includes accuracy, usability, and proprioception studies with healthy volunteers, patients, and clinicians. This rigorous approach aims to generate robust clinical evidence supporting safe and effective adoption in healthcare.

ABSTRACT. This work presents an egocentric vision module for adaptive gait planning in lower-limb exoskeletons. By combining exoskeleton-mounted and head-mounted cameras, the system builds a unified 3D map of the environment, enabling early obstacle detection and robust terrain classification. An Environment-Adaptive Gait Planning (EAGP) system computes safe footpaths, while augmented reality feedback provides intuitive visualization for the user. A dedicated dataset with step and corridor walking scenarios was collected to support development and evaluation.

ABSTRACT. The study tested an immersive teleoperation system for quadruped robots in harbor container parks, comparing a Head-Mounted Display (HMD) with 5G control to a standard gamepad and 2D display. Nine harbor workers performed hazard detection tasks while researchers measured success rate, time, workload, usability, and simulator sickness. Both setups showed low workload and good usability, with the immersive system offering slight improvements in performance. However, simulator sickness with the HMD was a drawback. Workers found the system relevant for real inspections. Overall, immersive teleoperation may improve safety by limiting human exposure to hazards, but larger studies and solutions for simulator sickness are needed before real-world deployment.

ABSTRACT. We present a field study investigating whether social robots can nudge cruise passengers to complete a digital satisfaction survey. Conducted across 15 non-consecutive days at the Stazione Marittima (Ponte dei Mille, Genoa, Italy), the study involved approximately 11,000 passengers under three conditions: (1) static QR-code posters, (2) robots autonomously promoting the code, and (3) robots with human staff support. Robots increased scans and survey submissions by more than ten times compared to posters, while staff support added only marginal gains. The study suggests that social robots can serve as effective nudging agents even in crowded, non-cooperative environments.

ABSTRACT. Quadruped robots are increasingly used for exploration, inspection, and monitoring in environments where wheeled or tracked vehicles are inadequate. While locomotion has been extensively studied, the use of legs not only to achieve locomotion but also to manipulate the environment is largely unexplored. Inspired by biological counterparts, pedipulation can extend autonomy by enabling non-prehensile interactions such as pushing obstacles or opening doors, as well as simple social gestures that may enhance acceptance in human-centered environments. This paper presents a modular task-priority control framework for pedipulation on the Unitree Go1 quadruped. The architecture combines inverse dynamics, balance maintenance, and mission-level sequencing, allowing the robot to execute pedipulation tasks while preserving stability. The framework was validated in simulation and real-world experiments across representative scenarios, including object pushing, door opening, object removal, and human interaction.

ABSTRACT. The development of autonomous underwater vehicles (AUVs) has recently seen rapid advances in both mechanical design and control systems. Traditional PID controllers are being increasingly replaced by model-based control laws that more accurately capture system dynamics. This paper presents a method for estimating AUV dynamic parameters using Physics-Informed Neural Networks (PINNs). Unlike conventional neural networks, PINNs embed the physical model directly into training, enabling the extraction of more information from limited data. Tests focused on estimating the added mass and damping terms along the surge motion of the vehicle. To evaluate the estimation, a feedforward action was implemented on the vehicle. By comparing the control action provided by the feedforward and the actual control action of the PID, we obtain an error at steady state of less than 5N, demonstrating an elevate accuracy in the parameters estimation.

ABSTRACT. This work proposes the integration of a multi-floor autonomous exploration system, based on a novel approach to frontier evaluation, with a semantic mapping system able to detect and localize relevant features using a depth camera. The system has been tested to evaluate and discuss the effect of exploration on feature detection.

ABSTRACT. Hospital isolation rooms expose healthcare workers to infection risks during routine tasks like IV bag replacement and material delivery. This paper presents a teleoperated TIAGo robot system controlled via Bluetooth joystick through a modular ROS 2 architecture including five specialized Python nodes to manage robot subsystems. Two Gazebo simulation scenarios validate the approach: IV replacement and meal delivery in modeled hospital rooms, demonstrating feasibility for reducing exposure.

ABSTRACT. Palpation is a fundamental diagnostic tool for identifying stiffness variations in soft tissues, but its effectiveness is limited by subjectivity and practitioner variability. This work presents an autonomous palpation framework that continuously reconstructs viscoelastic tissue properties using only a standard force/torque sensor. The framework integrates force-based viscoelastic estimation, Gaussian Process Regression to generate probabilistic stiffness maps, and ergodic trajectory planning to adaptively balance exploration and refinement. Both simulations and phantom experiments confirm the robustness of the approach, demonstrating accurate stiffness reconstruction and reliable inclusion localisation. These results highlight the potential of ergodic palpation as an objective and practical diagnostic tool in medical robotics.

ABSTRACT. This paper integrates physics-informed neural networks with gated recurrent units to leverage both physical modeling and data-driven learning to achieve accurate and generalizable solutions in sparse-data regimes. The approach targets robot-assisted superficial oncological hyperthermia treatment, retrieving temperature distributions along a monodimensional domain from boundary measurements with uncertain domain properties and sparse internal measurements. Validation encompasses both heat equation simulations and experimental scenarios.

ABSTRACT. Accurate modeling of organ deformation during surgery is crucial for intraoperative guidance, augmented reality overlays, and robotic assistance. We present a vision-based framework for estimating non-rigid deformation of kidney and tumor structures directly from stereo surgical video. Our method integrates depth reconstruction, tool-organ interaction analysis, and dense 3D motion estimation to deform preoperative meshes of the organs. Both local tool deformation and global organ motion are computed, while a restorative process models elastic recovery of tissues. We demonstrate the ability to continuously update a planned surgical cutting path to reflect intraoperative deforma- tions, supporting adaptive and safe guide and/or execution.

ABSTRACT. Radical prostatectomy is the gold standard treatment for localized prostate cancer, where surgical success depends on preserving vascular and nervous structures while ensuring oncological radicality. Quantifying the interactions between surgical instruments and vessels could provide surgeons with objective indicators of intraoperative safety. We present a vision-based framework for vessel–instrument distance estimation in robot-assisted radical prostatectomy, combining stereo 3D reconstruction, vessel and instrument segmentation, and Euclidean distance computation. Evaluation reported a Mean Absolute Error (MAE) of 2.83 ± 2.22 mm for 3D reconstruction, a mean Dice of 0.83 ± 0.07 for vessel segmentation, and 0.70 ± 0.18 for instrument segmentation. The framework achieved an average processing rate of 4 FPS. These results demonstrate the feasibility of quantifying vessel–instrument proximity during robotic surgery, providing a proof-of-concept toward quantitative safety metrics. Current limitations include sub–real-time performance and the lack of quantitative ground truth for distance validation, which will be addressed in future work.

ABSTRACT. Autonomous mobile robots in hospitals must navigate cluttered, dynamic environments safely and efficiently. We present an extension of Informed RRT* tailored for such settings: our static evaluation shows that enhancements — elliptical sampling, tree pruning, adaptive neighborhood radius, and goal bias — yield lower computation times without sacrificing path quality. We further introduce a dynamic replanning scheme: when a moving obstacle blocks the current trajectory, the robot halts, prunes its planning tree around a reshaped ellipse (between current pose and goal), and replans until a new feasible path is found. Experiments using realistic personnel‐movement models onboard the TIAGo platform demonstrate that our method adapts rapidly to changes and is suitable for real‐time deployment in hospital environments.

ABSTRACT. Robot-aided percutaneous surgery faces significant challenges due to organ deformation between preoperative and intraoperative phases. This work presents an integrated framework featuring: deformable registration algorithm for aligning pre/intraoperative 3D models; real-time motion planner for needle path replanning; advanced teleoperated control strategy for needle insertion. The registration algorithm achieved an RMSE of 1.7±0.5 mm with real-time suitability on clinical datasets. Validation of the planning and control modules on a phantom model with non-expert users showed improved needle orientation and positioning accuracy (maximum deviation: 0.006±0.003 rad, target error: 0.8±0.9 mm). Clinical experts confirmed system feasibility with moderate cognitive workload.

ABSTRACT. This extended abstract investigates how terrain slope influences human preferences in physical interaction with a robotic guide dog for visually impaired individuals. A quadruped robot equipped with a rigid handle guides users through haptic feedback while varying admittance control parameters according to slope. We introduce a design combining slope-aware admittance, an energy tank for passivity, path following, and interaction force estimation. A human subjects study with blindfolded participants confirms that stiffness modulation is crucial for safety and comfort, while damping plays a minor role. These results offer design guidelines for future assistive robots.

ABSTRACT. Wearable soft exosuits are emerging as lightweight and compliant solutions for upper-limb assistance in daily life and rehabilitation. This work presents the experimental characterization of a cable-driven hybrid elbow exosuit that combines rigid and soft components to deliver assistance while preserving comfort and mobility. Characterization addressed three domains: pressure distribution under interfaces, human-in-the-loop bandwidth, and range of motion. Results show that the dual-cable architecture and compliant cuff design maintain interface pressures below reported discomfort thresholds, while the system achieves a bandwidth of 1.37 Hz, sufficient to track natural elbow dynamics in daily activities. Range of motion testing confirmed preservation of functional joint mobility. These findings demonstrate that the exosuit can provide effective assistance without compromising usability, establishing a foundation for future rehabilitation and augmentation applications.

ABSTRACT. Functional Electrical Stimulation (FES) can assist patients walking since it induces muscle contractions through the non-invasive delivery of electrical pulses. Literature studies have shown that environmental factors affect patients’ myoelectric activity during gait. However, no closed-loop FES system has yet integrated such information to modulate stimulation. The aim of this study is to develop a novel closed-loop multichannel FES system for lower limb assistance, which adapt stimulation on the basis of both exteroceptive and proprioceptive information. The system performance was evaluated on seven leg muscles of five healthy participants during walking in five different scenarios: Up Ramp (UR), Up Stair (US), Level Ground (LG), Down Ramp (DR) and Down Stair (DS). The system can classify terrains with 98% accuracy and successfully activate muscles achieving success rates of 100% except for US (90%) and DS (93%).

ABSTRACT. Sentry is a modular tracking platform based on IMUs that unifies acquisition, real-time supervision, and offline kinematic reconstruction for human movement analysis. A Nordic-based controller orchestrates up to four BNO085 sensors with on-device preprocessing (quaternions, angular velocities, and linear accelerations), streaming via BLE or logging to microSD. A companion app enables immediate quality control; C/C++/Python tools reconstruct joint angles.

ABSTRACT. Traditional assessments often overlook the interaction between cognitive and motor impairments. Robotic systems allow measurement of both domains, supporting more comprehensive rehabilitation. This study presents an upper-limb robotic cognitive-sensorimotor assessment protocol and assesses its feasibility in 7 unimpaired participants with a robotic wrist device. Kinematic and cognitive outcomes were recorded, demonstrating the potential of integrated assessments for more detailed user profiling

ABSTRACT. This study presents a novel approach based on the Hand Blink Reflex (HBR) to quantitatively estimate the perceived sense of control during human-robot interaction. In twenty participants, we measured HBR while a robotic arm entered their defensive peripersonal space under three control modes: autonomous, discrete, and continuous control. As expected, HBR amplitude increased as the robot neared the user, but crucially, increased human control confidence corresponded to reduced HBR amplitude. This method offers a quantitative index of human confidence in robot control, paving the way for safer, more effective collaborative interfaces and algorithms.

ABSTRACT. In human augmentation, researchers have successfully demonstrated the control of supernumerary limbs but none have investigated the human potential to control the maximum number of degrees of freedom (DoFs) from both kinematic and cognitive perspectives. Existing works impose both the body part to be used and the specific movement to perform, limiting user adaptability. Here, in order to characterize the human potential, we implemented a strategy enabling the control of multiple DoFs through user-defined movements. Subjects can efficiently manage up to two DoFs with little practice, good performance, and acceptable perceived workload. Consistent performance when controlling more than two DoFs requires additional training.

ABSTRACT. Equipping robots with emotional capabilities enhances human–robot interaction by increasing trust, social presence, and predictability. Existing approaches largely rely on Cognitive Appraisal Theory. We propose EmoACT, a platform-independent framework for synthetic emotion generation based on Affect Control Theory (ACT). ACT models emotions as emerging from social interaction in a three-dimensional Evaluation– Potency–Activity (EPA) space. EmoACT integrates three modules: an Impression Estimator that infers real-time user impressions, an Identity Generator that combines personality, role, and comfortability, and an Emotion Generator that produces affective states in EPA space and maps them to basic emotions. Results show EmoACT generates personality-sensitive emotions with low computational cost, enabling real-time use in social robots.

ABSTRACT. This abstract addresses the incorporation of human motion prediction into proactive and dynamic human-aware motion planning, with the goal of enabling safe collaboration between humans and robots. A deep learning, graph-based model is used to forecast human motion and is integrated into a planning framework. This framework employs a static roadmap along with a time-variant A* algorithm to modify the trajectory of a UR5e manipulator. This method greatly improves human-robot interaction and enables proactive collision avoidance by combining precise motion forecasts with adaptive trajectory planning.

ABSTRACT. Conversational robots often struggle to produce natural backchanneling cues. We propose here a system that enables a robot to provide timely, empathetic feedback. Its integrated processing architecture combines voice activity detection, speech-to-text transcription, large language model (LLM)-based emotion recognition, and context-appropriate responses. The robot responds with synchronized facial expressions, lip movements, and gestures tailored to the user’s emotional state. By leveraging LLMs, the system can infer nuanced emotional cues and produce emotionally congruent backchannels, thus enhancing the naturalness and empathy of HRI.

ABSTRACT. We investigate a non-invasive Body–Machine Interface (BoMI) for robotic teleoperation that translates fingers motion into 2D cursor position. We propose a low-cost, webcambased approach for continuous teleoperation of the TIAGo mobile base. A two-dimensional autoencoder mapped 42 hand landmarks extracted from video to a 2D cursor position, and the cursor position is what users control. A 3×3 graphical user interface then converts the cursor’s on-screen location into linear and angular velocity commands for a TIAGo mobile base. In a training–test protocol with four participants, post-training performance improved: completion times decreased for all and movement counts decreased for most, indicating more stable, efficient control on the slalom evaluation.

ABSTRACT. Contact-rich tasks are widely used in various medical applications, e.g., Cardiopulmonary resuscitation (CPR), Ultrasound imaging, and palpation. To improve the usability, efficiency, and intuitiveness during robot-assisted medical contact-rich tasks, a novel augmented reality (AR)-based framework has been developed. Specifically, this framework integrates robotic systems to perform the contact-rich tasks, an optical see-through head-mounted display (OST-HMD) for robot teleoperation control, and an external RGB-D camera to acquire the point cloud of the phantom of the patient. Preliminary results indicate the framework’s effectiveness, including remote robotic control, point-cloud acquisition, and force control for medical contact-rich task execution.

ABSTRACT. We present smpl_ros, a ROS 2 package integrating the SMPL parametric human body model for robotic applications. It enables real-time volumetric human tracking, combining semantic and biomechanical realism, outperforming classical skeleton trackers in pose accuracy. Our toolbox, available at https://github.com/idra-lab/smpl_ros, facilitates efficient fitting, visualisation, and use of SMPL models, all within the ROS 2 middleware, bridging human modelling within applications in robotic perception and physical interaction.

ABSTRACT. Error-Related Potentials (ErRPs) in brain activity can provide insight into user intent prediction errors during robot teleoperation. This paper proposes a protocol for systematically acquiring EEG recordings from participants performing simplified virtual teleoperation and telemanipulation tasks with increasing cognitive load, including artificially induced error trials. With synchronized task triggers and commands, the protocol enables analysis of how cognitive load affects the occurrence, amplitude, and timing of ErRPs, supporting research in adaptive human-robot interaction. A preliminary dataset from five subjects following the proposed protocol is made available to the community.

ABSTRACT. We present an update on HORUS Holistic Operational Reality for Unified Systems), a mixed-reality (MR) interface for managing heterogeneous robot teams from a Meta Quest~3 headset. HORUS anchors robot state, plans, sensor data, and controls in a shared mini-map (``Ground Station'') with per-robot {Robot Manager} panels and a semi-immersive view for precise teleoperation. Relative to the prior wheeled-robot study, we (i) move to ROS~2 for local/remote operation, (ii) replace post-hoc map merging with multi-robot SLAM maintaining a single shared occupancy map, (iii) add a usable legged integration (Boston Dynamics Spot) with a body/stance panel while preserving the wheeled workflow, (iv) implement an aerial pathway flight-tested indoors, and (v) define an ongoing} LLM planner copilot that communicates plan intent via concise text and lightweight 3D highlights. We restate key numbers from the wheeled phase and include the evaluated architecture.

ABSTRACT. Humans are capable of discovering knowledge through dynamic interaction with the environment, especially guided by the semantics associated with their actions. This study introduces the design of a cognitive framework intended to replicate these human-like capabilities within a robotic system, alternating exploration and exploitation processes.

ABSTRACT. The complexity of natural disaster incidents demands innovative technological solutions to support first responders in their efforts. The increasing autonomy of UGVs and UAVs, along with the improvement in perception capabilities in terms of both the quantity and accuracy of data, necessitate the design of advanced technologies that can contextually frame and abstract data to aid first responders in making informed decisions. In this context, we investigate the design of a cognitive framework to support mission-level decisions and coordinate the autonomy of the UGV by integrating knowledge representation with task planning. On the one hand, semantic technologies aggregate perception data collected from available sources and support situation awareness by inferring relevant situations and suitable mission-level tasks that could be performed. On the other hand, task planning contextually coordinates the behaviors of UGVs to accomplish mission-level goals and support first responders.

ABSTRACT. This work addresses the integration of Human Factors (HF) into Human-Robot Collaboration (HRC) within the transition from Industry 4.0 to Industry 5.0. While collaborative robots and AI enable flexible, adaptive, and safe production environments, industrial deployment remains challenging due to the need for accurate and semantically rich knowledge representations. We propose an ontological model that formalizes the production environment, robot capabilities, human skills, and psycho-physiological states of operators. This approach aims to enhance task planning and execution by supporting both efficiency and human well-being in collaborative industrial settings.

ABSTRACT. This work investigates the use of the Sentinel Transformer architecture for anomaly detection in UAVs. Through a statistical analysis on the ALFA dataset, we show that attention maps can reveal distinctive patterns between normal and failure conditions. Results on standard benchmarks confirm state-of-the-art anomaly detection performances.

ABSTRACT. We propose a unified framework for robotic manipulation that integrates incremental learning from demonstrations, reinforcement learning, and symbolic task planning. The system supports the training of manipulation skills from Virtual Reality (VR) demonstrations, exploiting the ease of integration provided by Unity for recording demonstrations and training policies. A key feature is incremental learning, where policies acquired in early stages (e.g., proximity grasps with multi-fingered hands) are frozen and reused to accelerate the learning of more complex tasks (e.g., grasp-and-lift). Learned and predefined behaviors are stored in a structured repository, which can be flexibly queried during execution. Task composition is achieved through Hierarchical Task Network (HTN) planning, enabling the generation of long-horizon activities. Validation is performed in CoppeliaSim, transferring trained policies to different manipulators and end-effectors and testing with novel objects not seen during training. Preliminary results from the integrated works underscore the potential of the proposed approach, suggesting its scalability toward increasingly complex robotic manipulation tasks.

ABSTRACT. Nature inspires the Whale Optimization Algorithm (WOA), a well-liked metaheuristic for complex global optimization problems. WOA imitates the humpback whales' bubble-net hunting strategy using a population-based approach with random initialization. However, a major disadvantage of WOA is its tendency to get stuck in local optima when used on complex problems. This work presents an improved version called the Improved Whale Optimization Algorithm (I-WOA), which is practically used in the intelliwriter.io (IW) tool by robx.ai research lab. This improved version improves the standard WOA by making it more capable of exploitation. In addition, we initialize using a quasi-random Torus sequence, which helps us get around convergence and diversity problems. For WOA, proper population initialization is crucial because it has a big impact on the convergence and diversity of the swarm. It has been demonstrated that quasi-random sequences work better than random distributions. We employed our suggested approach on a collection of common benchmark functions that are frequently utilized in studies. The experimental data unequivocally demonstrate the superior performance of our method. The simulations verify that the Improved Whale Optimization Algorithm performs better than the conventional WOA for function optimization.

ABSTRACT. This article presents an egocentric mapless navigation approach for cognitive robotics that avoids pre-built maps and explicit localization. Using LiDAR embeddings and vector search, the system learns navigation commands through human-guided training and adapts in real time via cosine similarity comparing real-time measurements with the vector memory. A FlowProtocol-based architecture with Moliris and SkRobot enables distributed control, supporting robust, efficient, and adaptive autonomous navigation in dynamic environments.

ABSTRACT. Inspecting photovoltaic (PV) plants is essential to ensure optimal performance. Drones can be employed to acquire both optical and thermal data for anomaly detection. However, while visual servoing can accurately guide a drone along individual PV panel rows, the inter-panel transitions between subsequent rows rely on the Global Navigation Satellite System (GNSS) and are therefore subject to larger errors in positioning accuracy. To address this problem, this paper presents a path-planning solution that minimizes the portion of the route dependent on GNSS navigation by formulating three variants of the Traveling Salesman Problem (TSP) and analyzing their impact on path length and inter-panel transitions in simulated models of actual PV plants.

ABSTRACT. Defect detection in car-body manufacturing is a demanding task that traditionally relies on expert operators combining visual and tactile assessment. To advance the automation of tactile inspection, we developed a dedicated device integrating force and acceleration sensors to record the interaction dynamics arising during surface exploration. A preliminary dataset was collected with human participants and analyzed through supervised learning with standard classifiers. The results indicate that the device can reliably discriminate defective from non-defective regions. Furthermore, the collected tactile data provide a basis for training robotic systems to autonomously perform defect detection using the same sensing principles.

ABSTRACT. This paper presents a hierarchical planning architecture for multi-vehicle autonomous systems in dynamic industrial environments, built on a novel hybrid roadmap that integrates static and dynamic areas. The approach addresses a multi-objective optimization problem, balancing high-level criteria and generating feasible low-level paths. Experimental results demonstrate improved mission efficiency and reduced travel time variability.

ABSTRACT. This paper presents two approaches for minimizing jerk in redundant manipulators, leveraging the redundancy with respect to the desired task. As optimization variables, we consider the position of a selected redundant joint of the robot and the angles that define the end-effector orientation for each considered way point. These strategies are tested on a seven-degree-of-freedom robotic system executing a pick-and-place task. The results of numerical simulations highlight the performance of the proposed strategies in reducing the jerk of the robot end-effector.

ABSTRACT. The proposed decentralized strategy for cooperative object transportation consists of two steps. First, each robot estimates the wrenches applied to the object by all the other robots. Second, an admittance control scheme is used to limit internal wrenches. Experiments have been carried out with ABB Dual-arm YuMi and a UR5e robot, confirming the effectively reduction of internal wrenches.

ABSTRACT. A frequent task for industrial robots is to visit a set of target points in a closed path. If the sequence of operations is not constrained by the task, one may wish to minimize the path length. This means solving a Traveling Salesman Problem (TSP), a classic topic in Operations Research. The TSP has already been applied to mobile robots and to serial manipulators. We formulate the TSP for parallel robots, whose end-effector is connected to the base by two or more kinematic chains. We define the goal function as the maximum absolute change in joint coordinates (for all motors), which we take as proportional to the task time. We show that this is not equivalent to minimizing the geometric distance. Finally, we benchmark representative TSP solvers on an example planar robot, comparing heuristic methods and an exact solver based on mixed integer programming, which provides a reference optimal solution. We then report the solution time and quality. Our results show that TSP-based path planning with appropriate definitions can improve the efficiency of parallel robots.

ABSTRACT. In this study, the application of one-dimensional convolutional autoencoders is investigated under supervised, one-class unsupervised, and full unsupervised learning paradigms and across three case studies, respectively. The results demonstrate the adaptability of convolutional autoencoders to diverse sensing modalities and problem settings, with each paradigm offering complementary strengths depending on data availability. Promising outcomes across all three scenarios suggest that the proposed frameworks can address heterogeneous challenges in non-destructive testing and beyond.

ABSTRACT. Teleoperation systems extend human capabilities in complex or unsafe environments. This paper presents a unilateral telemanipulation framework that combines direct and rate control modes for intuitive human–robot interaction. Direct control provides accurate mapping of haptic device motion to robot motion, while rate control enables efficient large-scale movements. Haptic feedback signals the current control mode and the velocity magnitude, improving transparency and usability. A dedicated Graphical User–Machine Interface (GUMI) offers real-time visualization of control states, stylus position, and synchronized video streams. The framework was implemented both in simulation (MuJoCo) and on a Franka Emika Panda manipulator, and validated on a wiring task with deformable linear objects. Results confirm that users can switch seamlessly between modes, leveraging precision in direct control and efficiency in rate control. The system demonstrates robustness, flexibility, and potential for industrial applications, especially in training and programming by demonstration.

ABSTRACT. Trajectory optimization for robotic manipulators requires balancing smoothness, feasibility, and reliable collision avoidance in cluttered environments. Classical approaches such as Covariant Hamiltonian Optimization for Motion Planning (CHOMP) and Stochastic Trajectory Optimization for Motion Planning (STOMP) have shown strong performance, but they generally depend on Signed Distance Fields (SDFs) to represent obstacle proximity. This reliance introduces geometric approximations, discontinuities, and additional computational overhead. In this work, we present a geometry-aware extension of the STOMP framework in which the robot and obstacles are modeled with differentiable primitives—cylindrical links and spherical obstacles. This formulation allows direct and accurate evaluation of collision costs, removing the need for precomputed SDFs or explicit gradient-based updates. By preserving STOMP’s stochastic optimization structure, our method overcomes the limitations of gradient-descent strategies such as CHOMP while preserving robustness and scalability. The resulting planner generates smooth, collision-free trajectories at reduced computational cost, making it well suited for high-dimensional manipulators operating in complex environments.

ABSTRACT. Ensuring the robustness and usability of web applications requires testing methodologies that go beyond traditional functional and performance evaluations. This paper presents Test4You, an LLM-based testing framework that integrates automated stress testing, accessibility evaluation, and hybrid testing workflows with real and synthetic agents. Test4You enables comprehensive analysis of web applications by combining advanced visualization tools, moderated and unmoderated execution modes, and an intelligent logging system. The proposed framework provides interactive diagnostics through tree-based and page-wise visualizations, pushes the limits of automated checks on accessibility tests, and leverages synthetic agents guided by LLMs for autonomous execution. This innovative design offers both scalability and human-centered adaptability, addressing key challenges in next-generation web testing.

ABSTRACT. This work proposes an active sensing strategy for efficient surface defects detection in industrial settings, using robotic manipulators. The approach leverages prior knowledge of the underlying manufacturing process to focus inspection on the most relevant surface regions. The sensing trajectories are planned through ergodic control, balancing exploration and exploitation toward areas with higher defects likelihood.

ABSTRACT. The birth of Foundation Models brought unprecedented results in a wide range of tasks, from language to vision, to robotic control. These models are able to process huge quantities of data, and can extract and develop rich representations, which can be employed across different domains and modalities. However, they still have issues in adapting to dynamic, real-world scenarios without retraining the entire model from scratch. In this work, we propose the application of Continual Learning and Compositionality principles to foster the development of more flexible, efficient and smart AI solutions.

ABSTRACT. This work investigates whether Large Language Models (LLMs) can support predicate grounding in Child–Robot Interaction (CRI). We introduce a synthetic dataset of 1,800 dialogues covering explicit and implicit mental states, derived from the Applied Behavior Analysis (ABA) framework. The dataset was validated by domain experts and used to evaluate GPT-4o’s ability to classify children’s mental states from dialogue contexts. Results highlight systematic differences between explicit and implicit classifications and reveal the impact of interaction length on accuracy. These findings establish a foundation for applying LLM-based inference to real child–educator dialogues, advancing the development of socially aware robotic systems.

ABSTRACT. This work presents a prompt-engineered Large Language Model-based (LLM) control of empathic linguistic styles for conversational companions in Active Assisted Living (AAL) settings. Four compact, empathy-oriented styles, i.e., Mimical, Motivational, Distractional, and Alleviational, are induced via short “style cards” while preserving semantic intent. The proposed approach was tested on 50 AAL utterances. The responses generated by the system were evaluated by means of sentiment metrics and word count, and the distance among them was assessed with cosine-similarity analysis. Results show different separable profiles among the implemented styles, and the similarity analysis reveals two different clusters. These findings indicate that prompt-only style modulation is a lightweight, reproducible mechanism for empathic response generation.

ABSTRACT. This preliminary work introduces a method to inspect intersections between two 3D clothoid splines for detecting collisions between non-holonomic autonomous robotic systems trajectories. The proposed algorithm operates by decomposing each spline into a set of small tangent tetrahedra, which are then arranged within a hierarchical tree structure to enable efficient intersection detection. An Axis-Aligned Bounding Box (AABB) tree is adopted, as it provides a balanced trade- off between construction complexity and evaluation efficiency. Collision checks at the curve level are performed exclusively for those pairs of tetrahedra identified as intersecting. This approach significantly reduces computational effort. Thereby, we aim at employing the algorithm in real-time applications.

ABSTRACT. The challenge of controlling soft robots, despite their potential, has limited their widespread use. Traditional methods are either too complex for real-time applications or lack the necessary interpretability and reliability. We introduce a novel approach using symbolic regression to learn simple, yet accurate, forward kinematic models from data. Our models, validated on a soft robotic arm, can be integrated into a controller to achieve precise trajectory tracking. This research marks a step toward turning data-driven modelling into an efficient and interpretable tool for controlling nonlinear systems.

ABSTRACT. Data labeling poses significant challenges in data quality, domain discrepancies, overfitting, and the intensive effort required for accurate annotation. This is significantly pronounced in industrial contexts, where existing datasets often fail to represent real-world complexities. To address these challenges, we introduce an innovative image data labeling solution. HAWK4Label exploits a weak-supervised approach for the auto-labeling process mixed with the human’s feedback to improve the label quality. Experiments demonstrate that the instance segmentation model trained on datasets generated with HAWK4Label performs better than a manually labeled dataset with an IoU of 97\% (w.r.t. 90\%).

ABSTRACT. In recent years, robots have been increasingly expected to exhibit cultural competence—that is, the ability to adapt to different cultural contexts—not only for social and ethical reasons but also to improve system robustness. This need is particularly evident given that robots’ perception relies heavily on Machine Learning (ML) models. Because datasets cannot be assumed to be culturally balanced, the risk of underrepresentation bias in ML can directly undermine the robustness of autonomous systems such as social robots.

We compare oversampling (OS), random transformations (RT), and diffusion model (DM)-generated images as strategies for mitigating cultural underrepresentation in two social robotics classification tasks. Our results show that while OS and RT provide moderate improvements, DM-generated images consistently yield the greatest reduction in Cultural InCompetence (CIC), a metric that quantifies disparities in model performance across cultures.

ABSTRACT. Effectively managing unintended contacts between humans and collaborative robots is critical for ensuring safety in industrial and service environments. Sensorless methods, relying solely on proprioceptive measurements, such as joint torque sensors and encoders, and mathematical models provide a practical and cost-effective alternative to external sensing. This paper explores a hybrid strategy that integrates the classical momentum-based residual method using pseudoinversion with a contact particle filter (CPF) to enhance estimation of an external contact force and its localization across all links of a 7-DOF manipulator. For contacts on a distal robot link (i ≥ 6), the residual method yields accurate estimates of both a pure external force and its contact point, with CPF further refining the solution. Conversely, when contact occurs on a proximal link (i < 6), the associated link Jacobian loses rank and the pseudoinverse method alone fails. Instead, the proposed combination enables reliable estimation of contact force and location. Experimental validation on a KUKA LWR4+ robot highlights robustness and practical applicability of this approach.

ABSTRACT. Robust and precise object manipulation remains a central challenge in robotics, requiring the tight integration of perception and control. In this work, a robotic system capable of recognizing and reorienting a dice to a desired face by combining computer vision and tactile sensing to aid robotic manipulation is presented.

ABSTRACT. Automation in manufacturing has rapidly expanded through the widespread integration of industrial and mobile robots. Yet many asynchronous tasks, such as machine tending, remain manual due to the technological and economic challenges of automating flexible operations with traditional robots. These limitations, combined with labor shortages, motivate the need for flexible, easy-to-program robotic solutions to automate common manual activities in manufacturing plants. This work presents a mobile manipulator platform for flexible operation integrated with a Learning-from-Demonstration (LfD) framework based on 3D perception, enabling intuitive teaching and adaptive task execution. Lab-based experiments and preliminary field tests demonstrate the feasibility of this approach for automating relevant operator-dependent tasks in various industrial settings.

ABSTRACT. Programming by Demonstration (PbD) offers an intuitive way to program robots, but turning hand-guided demonstrations into precise and adaptable skills remains challenging, especially for complex interactions. In this work, we present a novel PbD framework that improves skill programming and adaptive execution for robots operating with physical interfaces, such as the one available on aircraft cockpits.

ABSTRACT. We propose a push-to-grasp framework that coordinates pushing and grasping actions through three Deep Q-Networks orchestrated by a perception-based oracle module, to achieve occluded object retrieval from a cluttered environment. The networks are trained through Deep Reinforcement Learning (DRL) in simulation, and then deployed on a robot, successfully executing retrieval tasks in the real world.

ABSTRACT. In this work, we perform non-prehensile object pushing with a compliant robotic manipulation system to ensure safe operations in human-populated environments. We extend a state-of-the-art model-based controller to realize a desired pushing force while varying the contact point using an impedance-controlled robot. We then integrate an energy tank passivity-based control framework to modulate the velocity set-point in a way that preserves passivity of the system. The proposed method has been rigorously tested in simulation and validated through real-world experiments.

ABSTRACT. This work presents a neural network-based motion planning approach designed to allow redundant robotic manipulators to emulate the arm movements of a human subject, by selecting the optimal kinematic configuration. The proposed approach is developed with the aim of improving human-robot collaboration in terms of acceptability and trustability. Experimental results on a robot with 7 degrees of freedom demonstrate the feasibility and the effectiveness of the proposed approach, in correctly replicating the motion of a human arm.

ABSTRACT. Human–robot collaboration demands controllers that are both intuitive and safe. While admittance control ensures compliant interaction, it does not guarantee compliance with ISO/TS~15066 safety limits. We propose a framework that unifies stability and safety in variable admittance control. Passivity is maintained through an energy tank, and safety is enforced via a damping injection strategy that reduces kinetic energy when Power and Force Limiting (PFL) thresholds are exceeded. Experiments with a UR10e robot show that unsafe energy levels are rapidly dissipated while interaction remains natural, enabling safer and more effective collaborative robotics.

ABSTRACT. In human-robot collaboration (HRC), robots must operate safely and adapt fluidly within dynamic, shared environments. We introduce THOR (Trajectory receding HOrizon interpolatoR), a model predictive control algorithm designed to explicitly minimize jerk and produce smooth, predictable robot motions. It continuously adapts trajectories in response to dynamic events, like path changes or safety slowdowns, while always respecting joint position, velocity, and acceleration limits. Validated in simulations and real life experiments, THOR significantly reduces jerk and improves motion continuity compared to standard approaches, making it suitable for human-robot interaction scenarios.

ABSTRACT. Predicting human motion enhances safety and efficiency in human–robot collaboration. We evaluate a predictor based on an Interacting Multiple Model (IMM) estimator combined with a human dynamics and control model. This approach is compared against a baseline Unscented Kalman Filter (UKF) using a constant acceleration model (CA). Additionally, we introduce a human kinematic model to predict joint angles instead of keypoints, enforcing kinematic constraints.

ABSTRACT. We present an optimization framework for mobile manipulators in human-robot collaborative tasks integrating layout planning, base pose selection, task sequencing, and human-aware adaptation. A Particle Swarm Optimization scheme balances efficiency and safety by considering cycle time, manipulability, and operator proximity. Demonstrated in a box-packing scenario, the framework reduces cycle time and adapts to human presence.

ABSTRACT. Dynamic grasping of objects in motion is a key challenge in robotics manipulation for enabling efficient robotic manipulation in both daily-living and industrial-like scenarios. However, to go toward a better human-robot interaction, the behaviour of the manipulator also has to be taken into account, ensuring, for example, the human-likeness in the motion produced for an increased perceived safety. To this aim, in this work, we present a method which exploits a human-like motion planning algorithm to grasp moving objects. We tested the framework by grasping objects from a conveyor belt, showing promising results both in terms of success rate and human-likeness.

ABSTRACT. We introduce a control strategy for jointly shaping human attention and opinion in interaction with a robot. Attention is captured by a modulation variable governed by spatial factors, such as distance and relative heading, while opinion evolves through nonlinear social dynamics. The proposed sequential strategy unfolds in three phases. First, the robot uses geometry to adjust human attention, thereby increasing her/his receptivity. Next, it steers the coupled opinions into the basin of attraction of the desired equilibrium by temporarily modifying its own dynamics. Finally, once aligned, the system naturally converges under unforced dynamics. This framework bridges the gap between motion planning and opinion dynamics, showing how spatial behaviour can be exploited to regulate both attention and consensus in human–robot interaction.

ABSTRACT. This work outlines a framework that combines knowledge representation systems with planning capabilities for robotics applications. It is based on four main pillars: - Automated knowledge extraction from natural language descriptions using large language models. - Generation of temporal plans for multi-robot systems using inference rules. - Automatic translation of plans into executable formalisms. - Runtime monitoring of the plan execution, learning from exceptions, and updating the knowledge-base dynamically.

ABSTRACT. Orienteering problem (OP) has wide real-world applications and also great potential in human-robot collaboration. However, existing approaches struggle to simultaneously ensure safe and feasible trajectories while achieving high-quality task execution in shared workspaces. To this end, this work studies the OP with time windows and variable profits (OPTWVP). A two-stage DEcoupled discrete-Continuous Optimization with Service-time-guided Trajectory (DeCoST) approach is proposed to effectively solve OPTWVP in shared spaces. Meanwhile, the safety-aware time windows of nodes and the discretized workspace are introduced to ensure collision-free trajectories between the end effector and the human. Preliminary results validate the effectiveness of DeCoST in generating collision-free trajectory plans while preserving the quality of orienteering tasks.