A Classification Method for Workers' Physical Risk.

In Industry 4.0 scenarios, wearable sensing allows the development of monitoring solutions for workers' risk prevention. Current approaches aim to identify the presence of a risky event, such as falls, when it has already occurred. However, there is a need to develop methods capable of identifying the presence of a risk condition in order to prevent the occurrence of the damage itself. The measurement of vital and non-vital physiological parameters enables the worker's complex state estimation to identify risk conditions preventing falls, slips and fainting, as a result of physical overexertion and heat stress exposure. This paper aims at investigating classification approaches to identify risk conditions with respect to normal physical activity by exploiting physiological measurements in different conditions of physical exertion and heat stress. Moreover, the role played in the risk identification by specific sensors and features was investigated. The obtained results evidenced that k-Nearest Neighbors is the best performing algorithm in all the experimental conditions exploiting only information coming from cardiorespiratory monitoring (mean accuracy 88.7±7.3% for the model trained with max(HR), std(RR) and std(HR)).

A parallel classification strategy to simultaneous control elbow, wrist, and hand movements.

BACKGROUND: In the field of myoelectric control systems, pattern recognition (PR) algorithms have become always more interesting for predicting complex electromyography patterns involving movements with more than 2 Degrees of Freedom (DoFs). The majority of classification strategies, used for the prosthetic control, are based on single, hierarchical and parallel linear discriminant analysis (LDA) classifiers able to discriminate up to 19 wrist/hand gestures (in the 3-DoFs case), considering both combined and discrete motions. However, these strategies were introduced to simultaneously classify only 2 DoFs and their use is limited by the lack of online performance measures. This study introduces a novel classification strategy based on the Logistic Regression (LR) algorithm with regularization parameter to provide simultaneous classification of 3 DoFs motion classes. METHODS: The parallel PR-based strategy was tested on 15 healthy subjects, by using only six surface EMG sensors. Twenty-seven discrete and complex elbow, hand and wrist motions were classified by keeping the number of electromyographic (EMG) electrodes to a bare minimum and the classification error rate under 10 %. To this purpose, the parallel classification strategy was implemented by using three classifiers one for each DoF: the "Elbow classifier", the "Wrist classifier", and the "Hand classifier" provided the simultaneous control of the elbow, hand, and wrist joints, respectively. RESULTS: Both the offline and real-time performance metrics were evaluated and compared with the LDA parallel classification results. The real-time recognition results were statistically better with the LR classifier with respect to the LDA classifier, for all motion classes (elbow, hand and wrist). CONCLUSIONS: In this paper, a novel parallel PR-based strategy was proposed for classifying up to 3 DoFs: three joint classifiers were employed simultaneously for classifying 27 motion classes related to the elbow, wrist, and hand and promising results were obtained.

Microneurography as a tool to develop decoding algorithms for peripheral neuro-controlled hand prostheses.

BACKGROUND: The usability of dexterous hand prostheses is still hampered by the lack of natural and effective control strategies. A decoding strategy based on the processing of descending efferent neural signals recorded using peripheral neural interfaces could be a solution to such limitation. Unfortunately, this choice is still restrained by the reduced knowledge of the dynamics of human efferent signals recorded from the nerves and associated to hand movements. FINDINGS: To address this issue, in this work we acquired neural efferent activities from healthy subjects performing hand-related tasks using ultrasound-guided microneurography, a minimally invasive technique, which employs needles, inserted percutaneously, to record from nerve fibers. These signals allowed us to identify neural features correlated with force and velocity of finger movements that were used to decode motor intentions. We developed computational models, which confirmed the potential translatability of these results showing how these neural features hold in absence of feedback and when implantable intrafascicular recording, rather than microneurography, is performed. CONCLUSIONS: Our results are a proof of principle that microneurography could be used as a useful tool to assist the development of more effective hand prostheses.

A Motion Analysis Protocol for Kinematic Assessment of Poly-Articulated Prosthetic Hands With Cosmetic Gloves.

To provide upper-limb amputees with devices that best fit their needs and to test innovative solutions, it is necessary to quantitatively appraise a device performance with rigorous measurement methods. The aim of this work was to define an optimal motion analysis protocol, suitable for optoelectronic systems, to measure the kinematics of poly-articulated hands even when covered by a cosmetic glove. This is a fundamental aspect, because gloves can decrease device speed and range of motion and, ultimately, patients' acceptance of the artificial limb. In this work, different mathematical models of the joints and marker-sets for motion analysis were conceived. A regression model to choose a reduced marker-set for studying the hand performance with different cosmetic glove models was developed. The proposed approaches for finger motion analysis were experimentally tested on the index finger of the i-Limb, a commercial myoelectric poly-articulated prosthetic hand, but the results can be easily extended to the whole hand and to other poly-articulated prosthetic hands. The methods proposed for the performance analysis of prosthetic hands points out that the cosmetic gloves imply a reduction of the finger flexion/extension (F/E) angles and of the motion velocity. This draws attention to the need for performing independent cyclic tests on commercial products with various cosmetic solutions to better guide component selection.

Transcutaneous Vagus Nerve Stimulation Combined with Robotic Rehabilitation Improves Upper Limb Function after Stroke.

The efficacy of standard rehabilitative therapy for improving upper limb functions after stroke is limited; thus, alternative strategies are needed. Vagus nerve stimulation (VNS) paired with rehabilitation is a promising approach, but the invasiveness of this technique limits its clinical application. Recently, a noninvasive method to stimulate vagus nerve has been developed. The aim of the present study was to explore whether noninvasive VNS combined with robotic rehabilitation can enhance upper limb functionality in chronic stroke. Safety and efficacy of this combination have been assessed within a proof-of-principle, double-blind, semirandomized, sham-controlled trial. Fourteen patients with either ischemic or haemorrhagic chronic stroke were randomized to robot-assisted therapy associated with real or sham VNS, delivered for 10 working days. Efficacy was evaluated by change in upper extremity Fugl-Meyer score. After intervention, there were no adverse events and Fugl-Meyer scores were significantly better in the real group compared to the sham group. Our pilot study confirms that VNS is feasible in stroke patients and can produce a slight clinical improvement in association to robotic rehabilitation. Compared to traditional stimulation, noninvasive VNS seems to be safer and more tolerable. Further studies are needed to confirm the efficacy of this innovative approach.

NLR, MLP, SVM, and LDA: a comparative analysis on EMG data from people with trans-radial amputation.

BACKGROUND: Currently, the typically adopted hand prosthesis surface electromyography (sEMG) control strategies do not provide the users with a natural control feeling and do not exploit all the potential of commercially available multi-fingered hand prostheses. Pattern recognition and machine learning techniques applied to sEMG can be effective for a natural control based on the residual muscles contraction of amputated people corresponding to phantom limb movements. As the researches has reached an advanced grade accuracy, these algorithms have been proved and the embedding is necessary for the realization of prosthetic devices. The aim of this work is to provide engineering tools and indications on how to choose the most suitable classifier, and its specific internal settings for an embedded control of multigrip hand prostheses. METHODS: By means of an innovative statistical analysis, we compare 4 different classifiers: Nonlinear Logistic Regression, Multi-Layer Perceptron, Support Vector Machine and Linear Discriminant Analysis, which was considered as ground truth. Experimental tests have been performed on sEMG data collected from 30 people with trans-radial amputation, in which the algorithms were evaluated for both performance and computational burden, then the statistical analysis has been based on the Wilcoxon Signed-Rank test and statistical significance was considered at p < 0.05. RESULTS: The comparative analysis among NLR, MLP and SVM shows that, for either classification performance and for the number of classification parameters, SVM attains the highest values followed by MLP, and then by NLR. However, using as unique constraint to evaluate the maximum acceptable complexity of each classifier one of the typically available memory of a high performance microcontroller, the comparison pointed out that for people with trans-radial amputation the algorithm that produces the best compromise is NLR closely followed by MLP. This result was also confirmed by the comparison with LDA with time domain features, which provided not significant differences of performance and computational burden between NLR and LDA. CONCLUSIONS: The proposed analysis would provide innovative engineering tools and indications on how to choose the most suitable classifier based on the application and the desired results for prostheses control.

Slippage Detection with Piezoresistive Tactile Sensors.

One of the crucial actions to be performed during a grasping task is to avoid slippage. The human hand can rapidly correct applied forces and prevent a grasped object from falling, thanks to its advanced tactile sensing. The same capability is hard to reproduce in artificial systems, such as robotic or prosthetic hands, where sensory motor coordination for force and slippage control is very limited. In this paper, a novel algorithm for slippage detection is presented. Based on fast, easy-to-perform processing, the proposed algorithm generates an ON/OFF signal relating to the presence/absence of slippage. The method can be applied either on the raw output of a force sensor or to its calibrated force signal, and yields comparable results if applied to both normal or tangential components. A biomimetic fingertip that integrates piezoresistive MEMS sensors was employed for evaluating the method performance. Each sensor had four units, thus providing 16 mono-axial signals for the analysis. A mechatronic platform was used to produce relative movement between the finger and the test surfaces (tactile stimuli). Three surfaces with submillimetric periods were adopted for the method evaluation, and 10 experimental trials were performed per each surface. Results are illustrated in terms of slippage events detection and of latency between the slippage itself and its onset.

Exploration and learning in capuchin monkeys (Sapajus spp.): the role of action-outcome contingencies.

Animals have a strong propensity to explore the environment. Spontaneous exploration has a great biological significance since it allows animals to discover and learn the relation between specific behaviours and their consequences. The role of the contingency between action and outcome for learning has been mainly investigated in instrumental learning settings and much less in free exploration contexts. We tested 16 capuchin monkeys (Sapajus spp.) with a mechatronic platform that allowed complex modules to be manipulated and to produce different outcomes. Experimental subjects could manipulate the modules and discover the contingencies between their own specific actions and the outcomes produced (i.e., the opening and lighting of a box). By contrast, Control subjects could operate on the modules, but the outcomes experienced were those performed by their paired Experimental subjects ("yoked-control" paradigm). In the exploration phase, in which no food reward was present, Experimental subjects spent more time on the board and manipulated the modules more than Yoked subjects. Experimental subjects outperformed Yoked subjects in the following test phase, where success required recalling the effective action so to open the box, now baited with food. These findings demonstrate that the opportunity to experience action-outcome contingencies in the absence of extrinsic rewards promotes capuchins' exploration and facilitates learning processes. Thus, this intrinsically motivated learning represents a powerful mechanism allowing the acquisition of skills and cognitive competence that the individual can later exploit for adaptive purposes.

Invasive neural interfaces: the perspective of the surgeon.

BACKGROUND: By implanting electrodes inside peripheral nerves, amputee's intentions are picked up and exploited to control novel dexterous sensorized hand prostheses. Under the pretext of presenting surgical technique and clinical outcomes of the implant of invasive peripheral neural interfaces in a human amputee, this article critically comments, from the point of view of the surgeon, strengths and weaknesses of the procedure. MATERIALS AND METHODS: Four multielectrodes were implanted in the medial and ulnar nerves of a young volunteer, which, following a car-crash, had a left transradial amputation. Both nerves were approached with a single incision in the medial aspect of the upper arm. Four weeks later, the electrodes were removed. RESULTS: Even if the trauma and the postamputation plastic processes altered the anatomy, electrodes were proficiently implanted with an overall success of 66%. Looking at the procedure from the surgeon's viewpoint unveils few still open issues. Electrodes weaknesses were related to the absence of stabilizing structures, the cable transit through the skin, the implant angle, and the unproven magnetic resonance imaging compatibility. Future investigations are needed to definitely address the better anesthesia, number and sites of incisions, the nerves to implant, and the convenience of performing epineural microdissection. CONCLUSIONS: Invasive neural interfaces developmental process almost completely relies on the efforts of bioengineers and neurophysiologists; however, the surgeon is responsible for intra and perioperative factors. Therefore, he deserves to play a major role also at the stage of specifying the requirements, to satisfy the requisites of a safe, stable, and long-lasting implant.

Development of goal-directed action selection guided by intrinsic motivations: an experiment with children.

Action selection is extremely important, particularly when the accomplishment of competitive tasks may require access to limited motor resources. The spontaneous exploration of the world plays a fundamental role in the development of this capacity, providing subjects with an increasingly diverse set of opportunities to acquire, practice and refine the understanding of action-outcome connection. The computational modeling literature proposed a number of specific mechanisms for autonomous agents to discover and target interesting outcomes: intrinsic motivations hold a central importance among those mechanisms. Unfortunately, the study of the acquisition of action-outcome relation was mostly carried out with experiments involving extrinsic tasks, either based on rewards or on predefined task goals. This work presents a new experimental paradigm to study the effect of intrinsic motivation on action-outcome relation learning and action selection during free exploration of the world. Three- and four-year-old children were observed during the free exploration of a new toy: half of them were allowed to develop the knowledge concerning its functioning; the other half were not allowed to learn anything. The knowledge acquired during the free exploration of the toy was subsequently assessed and compared.

Shoulder motor performance assessment in the sagittal plane in children with hemiplegia during single joint pointing tasks.

BACKGROUND: Pointing is a motor task extensively used during daily life activities and it requires complex visuo-motor transformation to select the appropriate movement strategy. The study of invariant characteristics of human movements has led to several theories on how the brain solves the redundancy problem, but the application of these theories on children affected by hemiplegia is limited. This study aims at giving a quantitative assessment of the shoulder motor behaviour in children with hemiplegia during pointing tasks. METHODS: Eight children with hemiplegia were involved in the study and were asked to perform movements on the sagittal plane with both arms, at low and high speed. Subject movements were recorded using an optoelectronic system; a 4-DOF model of children arm has been developed to calculate kinematic and dynamic variables. A set of evaluation indexes has been extracted in order to quantitatively assess whether and how children modify their motor control strategies when perform movements with the more affected or less affected arm. RESULTS: In low speed movements, no differences can be seen in terms of movement duration and peak velocity between the More Affected arm (MA) and the Less Affected arm (LA), as well as in the main characteristics of movement kinematics and dynamics. As regards fast movements, remarkable differences in terms of strategies of motor control can be observed: while movements with LA did not show any significant difference in Dimensionless Jerk Index (JI) and Dimensionless Torque-change Cost index (TC) between the elevation and lowering phases, suggesting that motor control optimization is similar for movements performed with or against gravity, movements with MA showed a statistically significant increase of both JI and TC during lowering phase. CONCLUSIONS: Results suggest the presence of a different control strategy for fast movements in particular during lowering phase. Results suggest that motor control is not able to optimize Jerk and Torque-change cost functions in the same way when controls the two arms, suggesting that children with hemiplegia do not actively control MA lowering fast movements, in order to take advantage of the passive inertial body properties, rather than to attempt its optimal control.

Technological solutions and main indices for the assessment of newborns' nutritive sucking: a review.

Nutritive Sucking (NS) is a highly organized process that is essential for infants' feeding during the first six months of their life. It requires the complex coordination of sucking, swallowing and breathing. The infant's inability to perform a safe and successful oral feeding can be an early detector of immaturity of the Central Nervous System (CNS). Even though the importance of early sucking measures has been confirmed over the years, the need for standardized instrumental assessment tools still exists. Clinicians would benefit from specifically designed devices to assess oral feeding ability in their routine clinical monitoring and decision-making process. This work is a review of the main instrumental solutions developed to assess an infant's NS behavior, with a detailed survey of the main quantities and indices measured and/or estimated to characterize sucking behavior skills and their development. The adopted sensing measuring systems will be described, and their main advantages and weaknesses will be discussed, taking into account their application to clinical practice, or to at-home monitoring as post-discharge assessment tools. Finally, the study will highlight the most suitable sensing solutions and give some prompts for further research.

A new calibration methodology for thorax and upper limbs motion capture in children using magneto and inertial sensors.

Recent advances in wearable sensor technologies for motion capture have produced devices, mainly based on magneto and inertial measurement units (M-IMU), that are now suitable for out-of-the-lab use with children. In fact, the reduced size, weight and the wireless connectivity meet the requirement of minimum obtrusivity and give scientists the possibility to analyze children's motion in daily life contexts. Typical use of magneto and inertial measurement units (M-IMU) motion capture systems is based on attaching a sensing unit to each body segment of interest. The correct use of this setup requires a specific calibration methodology that allows mapping measurements from the sensors' frames of reference into useful kinematic information in the human limbs' frames of reference. The present work addresses this specific issue, presenting a calibration protocol to capture the kinematics of the upper limbs and thorax in typically developing (TD) children. The proposed method allows the construction, on each body segment, of a meaningful system of coordinates that are representative of real physiological motions and that are referred to as functional frames (FFs). We will also present a novel cost function for the Levenberg-Marquardt algorithm, to retrieve the rotation matrices between each sensor frame (SF) and the corresponding FF. Reported results on a group of 40 children suggest that the method is repeatable and reliable, opening the way to the extensive use of this technology for out-of-the-lab motion capture in children.

A marker-based approach to determine the centers of rotation of finger joints.

BACKGROUND AND OBJECTIVE: The methods proposed in literature to estimate the position of hand joints Centers of Rotation (CoRs) typically require computationally non-trivial optimization routines and exploit a high number of markers to calculate CoRs positions from surface marker trajectories. Moreover, most of the existing works evaluated the accuracy only in simulation. This work proposes a new procedure, based on the Pratt circle fit, to estimate joints CoRs position in 2D through marker-based acquisitions. METHODS: The advantage of the Pratt circle fit lies in its simplicity and computational speed, and in the possibility of exploiting a reduced markerset for calculating CoRs. By applying simplifying assumptions regarding the movement of the fingers (i.e., planar and decoupled flexion-extension movements of each joint occurring in the same flexion plane for all the joints of the finger), it is possible to determine the position of the CoR of each joint in 2D. For this reason, the estimation of the Carpo-MetaCarpal joint of the thumb was not included in this work, as it exhibits a more complex movement associated to the combination of a flexion-extension and adduction-abduction degree of freedom. The errors in estimating CoRs were evaluated by conducting experimental acquisitions on an anthropomorphic robotic hand and comparing the position of the estimated CoR with the real position of the CoR. The repeatability of the method and its capability to estimate anatomically plausible CoRs were evaluated through experimental acquisitions conducted on five healthy volunteers. RESULTS: Errors in estimating finger joints CoRs were in the order of 0.70 mm and 0.18 mm respectively along the finger longitudinal direction (i.e., x coordinate) and thickness (i.e., y coordinate). Standard Deviations of CoRs positions were comparable to the ones obtained in literature (i.e., below 2 mm and 1 mm respectively for the x and y coordinates), thus demonstrating the repeatability of the method. The Anatomical Plausibility Rate of the proposed approach was between 80% and 100%. CONCLUSIONS: The performance of the Pratt-based CoRs estimation procedure proposed in this work was comparable to other existing methods, with the advantage of exploiting a simple fitting algorithm and a reduced markerset with respect to the state-of-the-art techniques.

Development and Validation of a System for the Assessment and Recovery of Grip Force Control.

The ability to finely control hand grip forces can be compromised by neuromuscular or musculoskeletal disorders. Therefore, it is recommended to include the training and assessment of grip force control in rehabilitation therapy. The benefits of robot-mediated therapy have been widely reported in the literature, and its combination with virtual reality and biofeedback can improve rehabilitation outcomes. However, the existing systems for hand rehabilitation do not allow both monitoring/training forces exerted by single fingers and providing biofeedback. This paper describes the development of a system for the assessment and recovery of grip force control. An exoskeleton for hand rehabilitation was instrumented to sense grip forces at the fingertips, and two operation modalities are proposed: (i) an active-assisted training to assist the user in reaching target force values and (ii) virtual reality games, in the form of tracking tasks, to train and assess the user's grip force control. For the active-assisted modality, the control of the exoskeleton motors allowed generating additional grip force at the fingertips, confirming the feasibility of this modality. The developed virtual reality games were positively accepted by the volunteers and allowed evaluating the performance of healthy and pathological users.

A Multiaxial Rehabilitation Programme for Workers with COVID-19 Sequelae Using a Conventional and Technological-Robotic Approach: The Proposal of INAIL and Fondazione Don Carlo Gnocchi.

The COVID-19 sequelae have been shown to affect respiratory and cardiological functions as well as neuro-psychological functions, and, in some cases, metabolic/nutritional aspects. The Italian National Institute for Insurance against Accidents at Work (Istituto Nazionale Assicurazione Infortuni sul Lavoro, INAIL) recorded that, until December 2022, 315,055 workers were affected by COVID-19; therefore, there is a need to identify an effective approach to treat such patients. Robotic and technological devices could be integrated into the rehabilitation programme of people with long COVID conditions. A review of the literature showed that telerehabilitation may improve functional capacity, dyspnoea, performance, and quality of life in these patients, but no studies were found evaluating the effects of robot-mediated therapy or virtual reality systems. Considering the above, Fondazione Don Carlo Gnocchi and INAIL propose a multi-axial rehabilitation for workers with COVID-19 sequelae. To accomplish this goal, the two institutions merged the epidemiological information gathered by INAIL, the expertise in robotic and technological rehabilitation of Fondazione Don Carlo Gnocchi, and the literature review. Our proposal aims to facilitate a multi-axial rehabilitation approach customized to meet the unique needs of each individual, with a particular emphasis on utilizing advanced technologies to address the current and future challenges of patient care.

The passive stiffness of the wrist and forearm.

Because wrist rotation dynamics are dominated by stiffness (Charles SK, Hogan N. J Biomech 44: 614-621, 2011), understanding how humans plan and execute coordinated wrist rotations requires knowledge of the stiffness characteristics of the wrist joint. In the past, the passive stiffness of the wrist joint has been measured in 1 degree of freedom (DOF). Although these 1-DOF measurements inform us of the dynamics the neuromuscular system must overcome to rotate the wrist in pure flexion-extension (FE) or pure radial-ulnar deviation (RUD), the wrist rarely rotates in pure FE or RUD. Instead, understanding natural wrist rotations requires knowledge of wrist stiffness in combinations of FE and RUD. The purpose of this report is to present measurements of passive wrist stiffness throughout the space spanned by FE and RUD. Using a rehabilitation robot designed for the wrist and forearm, we measured the passive stiffness of the wrist joint in 10 subjects in FE, RUD, and combinations. For comparison, we measured the passive stiffness of the forearm (in pronation-supination), as well. Our measurements in pure FE and RUD agreed well with previous 1-DOF measurements. We have linearized the 2-DOF stiffness measurements and present them in the form of stiffness ellipses and as stiffness matrices useful for modeling wrist rotation dynamics. We found that passive wrist stiffness was anisotropic, with greater stiffness in RUD than in FE. We also found that passive wrist stiffness did not align with the anatomical axes of the wrist; the major and minor axes of the stiffness ellipse were rotated with respect to the FE and RUD axes by ∼20°. The direction of least stiffness was between ulnar flexion and radial extension, a direction used in many natural movements (known as the "dart-thrower's motion"), suggesting that the nervous system may take advantage of the direction of least stiffness for common wrist rotations.

Embedding inertial-magnetic sensors in everyday objects: assessing spatial cognition in children.

This paper describes an interdisciplinary approach to the assessment of children development of spatial cognition, with a focus on the technology. An instrumented toy (block-box) is presented which embeds magneto-inertial sensors for orientation tracking, specifically developed to assess the ability to insert objects into holes. The functional specifications are derived from experimental protocols devised by neuroscientists to assess spatial cognition skills in children. Technological choices are emphasized with respect to ecological requirements. Ad-hoc calibration procedures are presented which are suitable to unstructured environments. Preliminary results based on experimental trials carried out at a day-care on typically developing children (12-36 months old) show how the instrumented objects can be used effectively in a semi-automatic fashion (i.e., rater-independent) to derive accurate measurements such as orientation errors and insertion time which are relevant to the object insertion task. This study indicates that a technological approach to ecological assessment of spatial cognition in children is indeed feasible and maybe useful for identification and early assessment of developmental delay.

A mechatronic platform for behavioral analysis on nonhuman primates.

In this work we present a new mechatronic platform for measuring behavior of nonhuman primates, allowing high reprogrammability and providing several possibilities of interactions. The platform is the result of a multidisciplinary design process, which has involved bio-engineers, developmental neuroscientists, primatologists, and roboticians to identify its main requirements and specifications. Although such a platform has been designed for the behavioral analysis of capuchin monkeys (Cebus apella), it can be used for behavioral studies on other nonhuman primates and children. First, a state-of-the-art principal approach used in nonhuman primate behavioral studies is reported. Second, the main advantages of the mechatronic approach are presented. In this section, the platform is described in all its parts and the possibility to use it for studies on learning mechanism based on intrinsic motivation discussed. Third, a pilot study on capuchin monkeys is provided and preliminary data are presented and discussed.

Experimental characterization of a flexible thermal slip sensor.

Tactile sensors are needed for effectively controlling the interaction between a robotic hand and the environment, e.g., during manipulation of objects, or for the tactile exploration of unstructured environments, especially when other sensing modalities, such as vision or audition, become ineffective. In the case of hand prostheses, mainly intended for dexterous manipulation of daily living objects, the possibility of quickly detecting slip occurrence, thus avoiding inadvertent falling of the objects, is prodromal to any manipulation task. In this paper we report on a slip sensor with no-moving parts, based on thermo-electrical phenomena, fabricated on a flexible substrate and suitable for integration on curved surfaces, such as robotic finger pads. Experiments performed using a custom made test bench, which is capable of generating controlled slip velocities, show that the sensor detects slip events in less than 50 ms. This response time is short enough for enabling future applications in the field of hand prosthetics.