Search

Seabed inspection is one of the most sought-after applications for Autonomous Underwater Vehicles (AUVs). In particular, acoustic sensors, as Side Scan Sonars (SSSs) and Forward-Looking Sonars (FLSs), are commonly favored over optical cameras to carry out such a task being not influenced by the illumination conditions and providing high-range data. However, acoustic images are often hard to interpret with conventional automatic techniques, forcing human operators to analyze thousands of collected images to identify the so-called Objects of Potential Interest (OPIs). In this perspective, this paper reports the development of an Automatic Target Recognition (ATR) methodology to identify and localize OPIs in FLS imagery; such detections have been then exploited to realize a world model with the Probabilistic Multiple Hypothesis Anchoring (PMHA) data association algorithm. Both the ATR and world modeling systems were on-field tested at the Naval Support and Experimentation Centre (Centro di Supporto e Sperimentazione Navale - CSSN) basin, in La Spezia, Italy, in a multi-vehicle architecture by employing an acoustic channel between FeelHippo AUV and an autonomous moving buoy.

In the early 2000s, data from the latest World Health Organization estimates paint a picture where one-seventh of the world population needs at least one assistive device. Fortunately, these years are also characterized by a marked technological drive which takes the name of the Fourth Industrial Revolution. In this terrain, robotics is making its way through more and more aspects of everyday life, and robotics-based assistance/rehabilitation is considered one of the most encouraging applications. Providing high-intensity rehabilitation sessions or home assistance through low-cost robotic devices can be indeed an effective solution to democratize services otherwise not accessible to everyone. However, the identification of an intuitive and reliable real-time control system does arise as one of the critical issues to unravel for this technology in order to land in homes or clinics. Intention recognition techniques from surface ElectroMyoGraphic (sEMG) signals are referred to as one of the main ways-to-go in literature. Nevertheless, even if widely studied, the implementation of such procedures to real-case scenarios is still rarely addressed. In a previous work, the development and implementation of a novel sEMG-based classification strategy to control a fully-wearable Hand Exoskeleton System (HES) have been qualitatively assessed by the authors. This paper aims to furtherly demonstrate the validity of such a classification strategy by giving quantitative evidence about the favourable comparison to some of the standard machine-learning-based methods. Real-time action, computational lightness, and suitability to embedded electronics will emerge as the major characteristics of all the investigated techniques.

Spinal Muscular Atrophy (SMA) is a neuromuscular disease characterized by the degeneration of the \(\alpha \)-motor neurons in the spinal cord, resulting in progressive proximal muscle weakness and paralysis. It is the second most common fatal autosomal recessive disorder after cystic fibrosis in the world. In the context of assistive robotics for SMA, in this work the authors have preliminarily assessed the feasibility of using low-cost electromyography pattern recognition and simultaneous/proportional myocontrol to enforce smooth, intuitive control of an assistive hand exoskeleton system. A target achievement control test has involved ten healthy subjects. Synthetic noise has been added to their surface ElectroMyoGraphic (sEMG) signals in order to reach a signal-to-noise ratio similar to that of sEMG signals gathered from a SMA patient. The results indicate that, even neglecting any learning effect, an SMA patient could reach an average success rate of up to 82% through the proposed approach.

Every day more and more robotic aids, of different shapes, sizes, and functions, enter the clinics to take part in the rehabilitative and assistive paths for patients with reduced mobility. Accompanying discharged patients with robotics-based remote rehabilitation and home assistance seems to be one of the most promising avenues to follow to increase the success rate of these practices and lighten the overall burden on national health systems. However, to get out of clinics effectively, robotics must become wearable and, therefore, based on the use of embedded low-power electronics, both for practicality and safety reasons. The point is further complicated when it comes to assisting or rehabilitating lost hand functionalities due to the small size and complex mobility of such a limb; moreover, ensuring the real-time execution of gesture classification algorithms for controlling these devices hence becomes a vital engineering challenge. A hand gesture classification solution, specifically designed for the implementation of embedded electronics, based on surface electromyography, and ensuring real-time action, will be presented in this paper.

Personalized medicine is an effective tool to improve the quality of rehabilitation and treatment for patients with disabilities. This study deals with the development of a low-cost hand scanner for the acquisition of anthropometric measures. The data acquired by the scanner is used, thanks to the developed procedure, to tailor the dimensions of a hand exoskeleton. The exoskeleton is used for assistive and rehabilitation purposes.

In the widespread field of underwater robotics applications, the demand for increasingly intelligent vehicles is leading to the development of Autonomous Underwater Vehicles (AUVs) with the capability of understanding and engaging the surrounding environment. Consequently, the automatic recognition of targets is becoming one of the most investigated topics and Deep Learning-based strategies have shown astonishing results. In the context of this work, two different neural network architectures, based on the Single Shot Multibox Detector (SSD) and on the Faster Region-based Convolutional Neural Network (Faster R-CNN), have been trained and validated, respectively, on optical and acoustic datasets. The models have been trained with the images acquired by FeelHippo AUV during the European Robotics League (ERL) competition, which took place in La Spezia, Italy, in July 2018. The proposed ATR strategy has then been validated with FeelHippo AUV in an on-board postprocessing stage by exploiting the images provided by both a 2D Forward Looking Sonar (FLS) as well as an IP camera mounted on-board on the vehicle., https://youtu.be/6e_Ks924daQ

Robotic-based human assistance is increasingly spreading both in clinical practice and in the industrial sector. The use of wearable robots, such as exoskeletons, is considered one of the most promising applications since it allows for merging human flexibility and creativity with machine endurance. Such devices shall be comfortable and lightweight to be as transparent as possible to the user’s perception. At the same time, they shall also be stiff enough to drive body parts while bearing the exchanged forces efficiently. The gold standard methodology to achieve such results is the topology optimization, which, even if used mainly in structural optimization, is still relatively new to wearable robots. In this paper, the authors propose a topology-optimization-based design strategy suitable to be applied, if adapted case by case, to a generic design of a wearable system. The presented test case, used as a benchmark to assess the optimization-based design process, focuses on a hand exoskeleton made of aluminum alloy, resorting to an additive manufacturing process.

Every day more and more robotic aids enter the clinics to take part in the rehabilitative and assistive paths for patients with reduced mobility. Accompanying discharged patients with robotics-based remote rehabilitation and home assistance seems to be one of the most promising avenues to follow to increase the success rate of these practices and lighten the overall burden on national health systems. However, to get out of clinics effectively, robotics must become wearable and, therefore, based on the use of embedded low-power electronics, both for practicality and safety reasons. The point is further complicated when it comes to assisting or rehabilitating lost hand functionalities due to the small size and complex mobility of such a limb; moreover, ensuring the real-time execution of gesture classification algorithms for controlling these devices hence becomes a vital engineering challenge. A hand gesture classification solution, specifically designed for the implementation of embedded electronics, based on surface electromyography, and ensuring real-time action, will be presented in this paper., https://youtu.be/sToEpJwHywc https://www.youtube.com/watch?v=IqmHkrFhGh8

Robotics for Medicine and Healthcare is undoubtedly an important emerging sector of the newborn third millennium. There are many aspects in which this branch of robotics already operates; in this article, the focus will be on the so-called “Robotic assistive technology”. In particular, a novel electromechanical design for an assistive Hand Exoskeleton System is presented here. Since freedom of movement plays a crucial role in making actually usable an assistive device, the main point of innovation of the proposed solution lies in the complete wearability of the resulting system: including mechanics, control electronics, and power supply. From the combination of the authors’ previous experience with the improvements presented in this article comes a fully standalone tailor-made assistive device, https://youtu.be/MiF5Hn1Q3fA https://www.youtube.com/watch?v=KfjOP6QuUnk

Acoustic sensors play a fundamental role in underwater applications. They are used to perform a wide variety of tasks: from the perception of the surrounding environment to the support of inertial sensors in navigation strategies. The quality of the acquired images deeply affects the obtained results and, consequently, image enhancement approaches need to be developed and tested. Super-Resolution (SR) techniques are employed to reconstruct one high-resolution image by composing a sequence of low-resolution ones. By applying these strategies, the information content of an image can be considerably increased, but the required computational time is incompatible for real-time employment. Due to this limitation, an SR Generative Adversarial Network (SRGAN) approach has been developed in the presented work, where the SR images are used during the training phase of the GAN framework. The proposed approach, which has been developed for images provided by a Forward-Looking Sonar (FLS), can guarantee a solid trade-off between the quality of the generated high-resolution image and the run-time execution.

In recent years, seabed inspection has become one of the most sought-after tasks for Autonomous Underwater Vehicles (AUVs) in various applications. Forward-Looking Sonars (FLS) are commonly favored over optical cameras, which are not-negligibly affected by environmental conditions, to carry out inspection and exploration tasks. Indeed, sonars are not influenced by illumination conditions and can provide high-range data at the cost of lower-resolution images compared to optical sensors. However, due to the lack of features, sonar images are often hard to interpret by using conventional image processing techniques, leading to the necessity of human operators analyzing thousands of images acquired during the AUV mission to identify the potential targets of interest. This paper reports the development of an Automatic Target Recognition (ATR) methodology to identify and localize potential targets in FLS imagery, which could help human operators in this challenging, demanding task. The Mask R-CNN (Region-based Convolutional Neural Network), which constitutes the core of the proposed solution, has been trained with a dataset acquired in May 2019 at the Naval Support and Experimentation Centre (Centro di Supporto e Sperimentazione Navale - CSSN) basin, in La Spezia (Italy). The ATR strategy was then successfully validated online in the same site in October 2019, where the targets were replaced and relocated on the seabed.

Robotics for Medicine and Healthcare is undoubtedly an important emerging sector of the newborn third millennium. There are many aspects in which this branch of robotics already operates; in this article, the focus will be on the so-called “Robotic assistive technology”. In particular, a novel electromechanical design for an assistive Hand Exoskeleton System is presented here. Since freedom of movement plays a crucial role in making actually usable an assistive device, the main point of innovation of the proposed solution lies in the complete wearability of the resulting system: including mechanics, control electronics, and power supply. From the combination of the authors’ previous experience with the improvements presented in this article comes a fully standalone tailor-made assistive device.

The interaction with a highly complex anatomical morphology, the high performance in conjunction with the limits of the bearable wearability, and the frequent change of user make the development of rehabilitative devices for the hand a real engineering challenge. Considering the described scenario, the Department of Industrial Engineering of the University of Florence, in collaboration with MOV’IT S.r.l., has developed a modular remote actuated system with noteworthy characteristics. An overview of the mechanical design is reported.

Despite the current industrial trend towards automation, many workers are still daily exposed to heavy loads during their duties. Regarding the construction industry, the shotcrete projection results in a particularly arduous whole-body effort for the so-called “concrete reinforcement workers”. In this paper, the design of a passive robotic human assistance tool to assist workers in dealing with the specific task of shotcrete projection will be described. If the design of an effective aid plays a crucial role in improving the job’s quality, following the guidelines given by the French company Eiffage Infrastructures; besides, the acceptance of the proposed solution shall have special consideration. Therefore, starting from an in-site assessment of the scenario, the presented solution has been profoundly adjusted to address the issues coming from this particular task. The exoskeleton adaptability to different lower-limb activities has been preserved without lowering its comfort during daily life in the working area. The developed solution’s operation range has been specifically optimized to assist the worker during specific efforts without hindering the other movements.

Modern robotics is a field that is constantly involving more and more aspects of daily life, from industry to the healthcare sector. Nowadays, robotic assistance to hand-impaired people still represents a hurdle and a challenging task to achieve. The research work of recent years carried out by the Department of Industrial Engineering of the University of Florence has focused on the development of a tailor-made hand exoskeleton to assist people with hand disabilities. In this chapter the synthesis of the development process, sequentially ordered, is given in order to provide an exhaustive description of the design procedure yielding a fully portable and wearable robotics system. The final version of the designed robotic system presents two levels of personalization on the patient. A single-degree-of-freedom finger mechanism allows precise replication of the natural grasping gesture keeping a lightweight structure and an electromyography-based actuation strategy ensures a straightforward use of the device. These two characteristics lead to a fully patient-based solution for hand assistance.

Nowadays, many are the ways in which robotics can help but unfortunately, as of today, the design of hand exoskeletons can still be considered one of the hardest task in robotics and, surely, an open point. Towards this delicate aim, the researchers of the Department of Industrial Engineering of the University of Florence have conceived and are developing a novel hand exoskeleton design strategy that puts the patient at the core of the process, yielding completely customized devices (both in ergonomic and control terms). These devices act on the four long fingers by means of four planar mechanisms and have a total of four actuated (flexion/extension) and four passive (abduction/adduction) degrees of freedom, two per finger.

Recently, robotics has increasingly become a companion for the human being and assisting physically impaired people with robotic devices is showing encouraging signs regarding the application of this largely investigated technology to the clinical field. As of today, however, exoskeleton design can still be considered a hurdle task and, even in modern robotics, aiding those patients who have lost or injured their limbs is surely one of the most challenging goal. In this framework, the research activity carried out by the Department of Industrial Engineering of the University of Florence concentrated on the development of portable, wearable and highly customizable hand exoskeletons to aid patients suffering from hand disabilities, and on the definition of patient-centered design strategies to tailor-made devices specifically developed on the different users&rsquo, needs. Three hand exoskeletons versions will be presented in this paper proving the major taken steps in mechanical designing and controlling a compact and lightweight solution. The performance of the resulting systems has been tested in a real-use scenario. The obtained results have been satisfying, indicating that the derived solutions may constitute a valid alternative to existing hand exoskeletons so far studied in the rehabilitation and assistance fields.

The number of scientific researches focusing on designing assistive or rehabilitative robotics devices has remarkably increased with respect to just a few decades ago. However, when it comes to developing such devices for children, literature becomes poor. This paper presents the work carried out by the researchers of the Department of Industrial Engineering of the University of Florence in order to design and develop an assistive hand exoskeleton for a child. The results of a preliminary ergonomics test are also given at the end of the paper.

Robotic assistance to hand-impaired people represents an as difficult as important challenge. In this context, the research work of the Department of Industrial Engineering of the University of Florence (UNIFI) led to a tailor-made wearable device for rehabilitative and assistive purposes. In this paper, the synthesis of the development process, sequentially ordered, is given.

Among the most challenging aspects of the current bio-robotics trends, a place of honor is certainly reserved to the assistance to physically impaired people during the Activities of Daily Living (ADLs). The aim of this work is to assess the interaction between an assistive hand exoskeleton, controlled through surface ElectroMyoGraphy (sEMG) signals, and its user. A new control strategy, which focuses mainly on the wearability and the usability of the system, is presented. Promising results of two preliminary tests, conducted in collaboration with the “Don Carlo Gnocchi” Foundation, are also reported.

Developing wearable robotic systems for children’s hand rehabilitation highlights several issues during the design phase due to the difficult interactions with the patients and the high adaptability these devices require to fit fingers always growing. In this research work, the authors propose a model-based approach which exploits only a photograph of the hand to automatically generate a tailor-made device capable of replicating hand trajectories. A real device has been developed and tested on a patient after three growing steps in order to assess its kinematic compliance with fingers.