Publications

Tremor is a significant movement disorder characterized by involuntary, rhythmic, oscillatory movement of body parts. Traditional methods for tremor detection and analysis rely on visual evaluation and the use of rating scales. However, marker-less pose estimation (MPE) holds great potential for advancing tremor research by enabling the collection of objective and feature-rich data using a simple camera-based setup. This article aims to demonstrate the applicability of MPE for the extraction of relevant tremor features from hand kinematics and the automation of tremor detection and classification. We conducted an experiment involving three healthy subjects performing movements while a weak tremor was induced with functional electrical stimulation (FES). From multi-perspective camera data, we computed the trajectories of 20 key-points of the hand using the marker-less estimator Anipose. After extracting features from these key-point trajectories we trained machine-learning models to assess their validity in differentiating between tremor and non-tremor signals (detection) and between intention and constant tremor (classification). Despite a small intensity of FES-induced tremor, our system could detect tremor with 70.73% accuracy and classify between intention tremor and non-intention tremor with 79.28% accuracy. In conclusion, this research provides a foundation for the development of an MPE-based method for automated tremor assessment at home, using simple camera-based equipment.

Powered lower limb exoskeletons (LLEs) have emerged as wearable robots designed to augment users’ locomotion capabilities, offering mechanical support and additional power for both healthy and impaired subjects. However, current assistive exoskeletons are limited by predefined motion trajectories, hindering adaptability to unstructured environments encountered in daily life. To address this limitation, this paper proposes an environment-adaptive gait planning (EAGP) solution. The approach integrates scene understanding, pose estimation, and adaptive gait planning modules. A novel Collision-Free Foot Trajectory Generator (CFFTG) algorithm facilitates obstacle avoidance by computing collision-free foot trajectories, enhancing safety and adaptability. Through inverse kinematics, the planned trajectories are converted into angular joint trajectories for execution by low-level control. This comprehensive framework aims to enhance the adaptability and safety of LLEs, paving the way for broader real-world applications beyond clinical and research settings.

Semantic segmentation of point clouds is an essential task for understanding the environment in autonomous driving and robotics. Recent range-based works achieve real-time efficiency, while point- and voxel-based methods produce better results but are affected by high computational complexity. Moreover, highly complex deep learning models are often not suited to efficiently learn from small datasets. Their generalization capabilities can easily be driven by the abundance of data rather than the architecture design. In this paper, we harness the information from the three-dimensional representation to proficiently capture local features, while introducing the range image representation to incorporate additional information and facilitate fast computation. A GPU-based KDTree allows for rapid building, querying, and enhancing projection with straightforward operations. Extensive experiments on SemanticKITTI and nuScenes datasets demonstrate the benefits of our modification in a “small data”setup, in which only one sequence of the dataset is used to train the models, but also in the conventional setup, where all sequences except one are used for training. We show that a reduced version of our model not only demonstrates strong competitiveness against full-scale state-of-the-art models but also operates in real-time, making it a viable choice for real-world case applications. The code of our method is available at https://github.com/Bender97/WaffleAndRange.

This paper explores the integration of Artificial Intelligence (AI) into the Italian school curriculum. It proposes an activity to introduce students to the mechanisms behind AI with a special emphasis on Machine Learning (ML) and its integration with a simple robotic DIY artifact, with a maker-oriented approach. The activity aims to encourage the development of problem-solving abilities and cross-cutting skills in an inclusive framework that aligns with European key competencies. The paper also discusses the use of various reference documents, ranging from the White Paper on AI to the Ethical Guidelines for Educators on the use of AI and data. The project uses machine learning and robotics to create an intelligent waste bin to identify and sort waste. This is a way to promote awareness of the European Agenda 2030, which is an essential component of the curriculum, and encourage responsible conduct that emphasizes sustainability and environmental conservation. Future research could focus on the impact of the activity on students’ curriculum-based learning and how it influences their approach to Artificial Intelligence.

In industrial environments like factories and warehouses, transportation of flexible materials that need the collaboration of several subjects is a typical activity. One instance is the handling of enormous fibre sheets in the fabrication of composite parts, which presents several difficulties, including handling flexible materials and needing to place the material with extreme precision. Recently, there has been a lot of interest in employing robots to help human workers carry such things. However, this typically entails the robot adopting a follower attitude just intended for passive support without fully using its accuracy and repeatability. To make the best possible use of the robot’s and the operator’s skills, it is necessary to use an intelligent motion planner that takes into account the ergonomics of the operator but at the same time ensures the precision required by the task. In this paper, we present a preliminary study for a Human-Aware Motion Planner for the cooperative transportation of materials.

The growing volumes of solid waste present a significant challenge for sustainable management. An efficient robotics system for sorting waste materials is essential to improving recycling and contamination removal, but it is often limited by the extreme variation of items to recognize in a cluttered and dirty environment. To bring robots in such scenario, the system must be able to recognize and manipulate different objects, adapting to a high degree of variability. A system based on deep learning can achieve high performance and fulfill these requirements. However, learning models require extensive labeled data, which limits their applicability in this context. Indeed, the complexity of the real-world environment presents a significant challenge to effective data collection, highlighting the importance of data augmentation techniques for creating a suitable dataset for training models for object recognition in this context. To address this challenge, our study investigates the use of Generative Adversarial Networks (GANs) for synthetic data generation in waste-sorting systems. GANs are employed to produce synthetic images of waste streams with corresponding labels that accurately reflect the complexity and diversity of real-world waste. A primary con-cern in synthetic data generation is ensuring alignment between generated images and their labels. To address this, we introduce a novel method for controlling the GAN generation process, which enforces semantic coherence and preserves the intended structure of the labeled data. The experiments demonstrate that semantic segmentation models trained on datasets augmented with these synthetic images perform better in the semantic segmentation of waste.

Robotic technology to assist rehabilitation provides practical advantages compared with traditional rehabilitation treatments, but its efficacy is still disputed. This controversial effectiveness is due to different factors, including a lack of guidelines to adapt devices to users’ individual needs. These needs include the specific clinical conditions of people with disabilities, as well as their psychological and cognitive profiles. This pilot study aims to investigate the relationships between psychological, cognitive, and robot-related factors playing a role in human–robot interaction to promote a human-centric approach in robotic rehabilitation. Ten able-bodied volunteers were assessed for their anxiety, experienced workload, cognitive reserve, and perceived exoskeleton usability before and after a task with a lower-limb exoskeleton (i.e., 10 m path walking for 10 trials). Pre-trial anxiety levels were higher than post-trial ones (p < 0.01). While trait anxiety levels were predictive of the experienced effort (Adjusted-r2 = 0.43, p = 0.02), the state anxiety score was predictive of the perceived overall workload (Adjusted-r2 = 0.45, p = 0.02). High–average cognitive reserve scores were predictive of the perception of exoskeleton usability (Adjusted-r2 = 0.45, p = 0.02). A negative correlation emerged between the workload and the perception of personal identification with the exoskeleton (r = −0.67, p-value = 0.03). This study provides preliminary evidence of the impact of cognitive and psychoaffective factors on the perception of workload and overall device appreciation in exoskeleton training. It also suggests pragmatic measures such as familiarization time to reduce anxiety and end-user selection based on cognitive profiles. These assessments may provide guidance on the personalization of training.

Robotic lower limb exoskeletons are wearable devices designed to augment human motor functions and enhance physical capabilities mostly adopted in healthcare and rehabilitation. The field is strongly dominated by rigid exoskeletons driven by electromagnetic actuators constituted by electrical motors, gearboxes, and cylinders. This review focuses on the design and specifications of the actuation systems of lower limb exoskeletons, with the ultimate goal of providing reporting guidelines to allow for full reproducibility. For each paper, we assessed the quality and completeness of technical characteristics with two ad hoc rating scales for motors and reducers; we extracted the main parameters of the actuation unit and a quantitative analysis of the mechanical characteristics of the individual components was carried out considering the exoskeleton application. Overall, we observed a lack of details in reporting on actuation systems equipped on exoskeletons. To overcome this limitation, herein we conclude by proposing a data form and a checklist to provide researchers with a common approach in reporting the mechanical characteristics of the actuation unit of their lower limb exoskeletons. We believe that the convergence of exoskeletons’ literature toward a clearer standardization of design and reporting will boost the development of this technology and its diffusion outside the laboratory.

Despite the recent advancements in the field of wearable robotics, powered lower limb exoskeletons remain a technology strongly restricted to research or clinical settings. Their uptake as a device to assist mobility in the everyday life is still a challenge due to their high-cost and limited adaptability to unconstrained environments. To overcome these limitations, we propose an open-hardware and open-source platform specifically designed for boosting the research on intelligent exoskeletons (InteLLExo). The proposed prototype adopts design solutions based on low-cost materials, standardized components and simple construction aimed at simplifying the replicability of the device and increase its accessibility. In addition, the control architecture of the exoskeleton is developed within the Robot Operating System (ROS) to facilitate the integration of the device with artificial intelligence and neurorobotic techniques. Overall, InteLLExo aims at combining accessible technologies with robotic intelligence with the purpose of accelerating the research on intelligent exoskeletons and their adoption in everyday life.

Powered lower limb exoskeletons (LLEs) have demonstrated significant potential in augmenting mobility and providing rehabilitative support for individuals with gait impairments. However, most assistive exoskeletons rely on predetermined gait trajectories, limiting their effectiveness in unstructured environments. To address this limitation, Environment Adaptive Gait Planning (EAGP) strategies have emerged, focusing on real-time trajectory adaptation based on environmental perception. This work introduces a novel approach to EAGP using Deep Reinforcement Learning (DRL) for generating adaptive foot trajectories, specifically targeting obstacle avoidance during ground walking. The proposed method optimizes trajectory smoothness, environmental interaction, and compliance with exoskeleton kinematic constraints, as validated by simulations. This study advances the state-of-the-art of adaptive gait planning by leveraging the generalization capabilities of DRL, paving the way for enhanced mobility in real-world applications.