Integrating computer vision into powered prosthetic devices is garnering attention as a potential avenue for enhancing functionality. These methodologies have been introduced to address challenges such as prosthetic abandonment, which can be attributed to the unreliability and lack of intuitiveness of myoelectric control. This paper provides insights into the current state, challenges, and future directions of integrating computer vision into prosthetic limb control systems. To this aim, a literature review was conducted, identifying 50 relevant studies (33 on upper-limb and 17 on lower-limb prostheses), sourced from Scopus, PubMed, and IEEE Xplore, with the search updated to May 2025. The hardware implementation aspects, including camera sensor positioning and computational units, were synthesized, as well as the computer vision approaches implemented with a specific emphasis on their implications for limb functional performance. The review identified strengths and suggested areas for improvement, emphasizing the need for studies on optimal camera placement and the feasibility of embedded computational units for real-world testing. Even if the reported results are promising, the performed analysis outlined the need to conduct usability studies and introduce vision-based approaches into lower-limb prosthesis control, which should be tested in real-world scenarios. Validation in real settings is crucial for these technologies to move beyond laboratory settings. • Literature review of vision-based control strategies for prosthetic limbs. • Identify gaps in real-world testing and multimodal integration for prosthetic control. • Guide future research on vision-based strategies for prosthetic control.

Hospital logistics can significantly benefit from autonomous robotic technologies capable of alleviating personnel workload, reducing operational costs, and streamlining internal workflows. This paper introduces HOSBOT (HOSpital roBOT), a modular and cost-effective robotic system designed to enhance hospital logistics and workflow management through autonomous missions and real-time monitoring of transported items. HOSBOT combines a commercially available autonomous mobile robot with a customisable non-motorised cart, the SmartRack, which accommodates standalone, sensorised SmartBoxes equipped with Radio Frequency IDentification technology. This paper describes the overall design of HOSBOT, including its mechanical, electrical, and software interfaces. The system has been validated in three pilot experiments in real hospital environments across Europe, demonstrating good levels of acceptability, usability and efficacy. This innovative robotic solution highlights the potential for scalable integration of autonomous mobile robots in healthcare and other indoor logistics settings.

Work-related musculoskeletal disorders represent one main contributor to production workers absenteeism. In industry 5.0, exoskeletons have been proposed to mitigate risks of injury by supporting workers during repetitive tasks, with surface Electromyography (sEMG) showcasing their effects. Although existing studies have primarily evaluated exoskeletons by comparing muscle activity with and without the device, a systematic investigation of which sEMG features most effectively reflect muscle fatigue during prolonged arm elevation is still missing. This study aims to evaluate the effectiveness of different sEMG features in estimating perceived physical effort during an overhead bolting-unbolting task, performed by 10 participants both with and without a passive shoulder exoskeleton. It further assesses how the use of the exoskeleton influences the fatigue-related metrics identified. sEMG signals were collected from seven bilateral muscle groups, and 15 time-, frequency-, and spatial-domain features were extracted and correlated with two subjective effort perception models. Our results highlight strong correlations between time-domain features and perceived physical effort. Moreover, comparisons between conditions demonstrate that the exoskeleton provides a measurable fatigue-reducing effect. In contrast, spatial-domain features showed weak associations with perceived effort, suggesting limited suitability for low-intensity, long-duration tasks. These findings contribute to identifying the most informative sEMG features for fatigue estimation and provide evidence of the benefits of passive exoskeletons in industrial scenarios.

Rehabilitative therapies play a crucial role in upper limb motor recovery, as upper limbs are the most active parts in executing the activities of daily living. Because of a huge number of people with motor disorders and a shortage of therapists, the integration of data-driven AI methodologies and robots for rehabilitation could be helpful in creating personalized and challenging therapies, leading to a myriad of benefits for both patients and therapists. AI methods can be implemented in different functional modules of the robotic platform, such as user intention recognition, robot motion planning, robot interaction control, and system adaptation through different learning paradigms. This article presents a systematic literature review on the use of data-driven learning methods applied in upper limb robot-aided rehabilitation. The analysis is structured around the learning paradigms adopted, namely, supervised, unsupervised, and reinforcement learning, as well as the corresponding task types (e.g., classification, regression, and control tasks) and model types, distinguishing between machine learning and deep learning approaches. The review reveals that most studies employ supervised learning to address classification tasks, and that deep learning models are the most frequently adopted.

Rehabilitation robotics enables consistent and personalized therapy but still relies on complex, expert-driven tuning of control parameters. To address this, a reinforcement learning strategy based on Q-learning is proposed to autonomously adapt key parameters during upper-limb rehabilitation, without requiring prior task-specific knowledge. A systematic evaluation is conducted across combinations of control parameters (radial stiffness and execution time), performance-based reward functions (pointing accuracy and movement smoothness), and exploration strategies ( ɛ ɛ - greedy and Upper Confidence Bound). The Q-learning agent selects discrete actions (increase, decrease, or maintain the current value) for each control parameter, enabling real-time adaptation based on observed performance. The method is validated using a Kuka robotic arm in experiments involving 16 right-handed healthy subjects (13 males, 3 females) and 8 right-handed individuals simulating impaired motor behavior (5 males, 3 females). Motion signals are acquired through internal robot sensors, while a wearable physiological monitoring system define the Q-learning agent state. Reward improvement and exploration ratio are analyzed as key performance indicators and statistically compared across all tested conditions using the Mann–Whitney test. The results demonstrate that the proposed algorithm effectively adjusts control parameters online, with performance influenced by the reward function, exploration strategy, and selected control actions. Reward improvements of 0 . 11 ± 0 . 09 ( ɛ ɛ - greedy , reward based on pointing ability) and 0 . 13 ± 0 . 11 (reward based on smoothness, Upper Confidence Bound strategy) were observed in healthy subjects, indicating enhancements in pointing accuracy and movement smoothness. In simulated pathological cases, improvements of 0 . 08 ± 0 . 13 and 0 . 06 ± 0 . 16 were observed, respectively.

Robot-aided rehabilitation is pushing forward novel robotic architectures to provide physical therapy. This paper presents a patient-tailored control architecture for upper-limb robot-aided orthopaedic rehabilitation capable of i) adapting the robot workspace on the basis of patient Range of Motion (RoM); ii) generating a tunnel, around the desired path to be followed by the patient, which guarantees spatial autonomy; iii) introducing a back-wall inside the tunnel sliding with variable speed on the basis of patient performance to ensure temporal autonomy; iv) rehabilitating to working gestures, thanks to a DMP-based trajectory planner, with the aim of favoring an effective translation of the patient's motor recovery results to the occupational sphere; v) ensuring a patient-tailored assistance also thanks to the evaluation of performance indicators. The designed system was validated demonstrating the adaptability of the system to orthopaedic patient motor imnrovements.

Restoring tactile sensations in upper limb neuro-prosthetic users is an important challenge to improve amputee quality of life. Neural prostheses are based on neural interfaces that allow delivering direct stimuli to the nerve fibers. Different kinds of neural electrodes, characterized by different properties as regards geometry or current stimulation parameters, were proposed in the literature. Studying the interaction between electrode stimulation and nerve fibers is fundamental for evaluating its ability to activate axon fibers and the electric potential distribution in the nerve. In this paper, the ds-FILE electrode is considered in the FEM simulation to study its interaction with the nerve fibers. The results can be very useful for the advancement of more realistic tactile sensations in amputee subjects from two point of view: the efficacy of the stimulation, that is related to the activation of axons subjected to the electrical stimulation, and the safety of the stimulation, related from a first consideration to the current intensity and waveform used. So in this paper are considered the results of three type of waveform that are the more safety as reported in literature [1] and they are compared. The research aims to study, by means of a FEM-Neuron computational model, the axon fibers activation by means of the intraneural stimulation using different types of stimulus waveforms. The obtained results show that, using a biphasic charge unbalanced stimulus, the threshold to activate all the fibers considered in a location near an active site of the electrode is lower than the threshold found using biphasic charge balanced stimuli. This is an important result because the stimulation is equally efficient using low current amplitude.

The lack of sensory feedback in lower-limb amputees is the major cause of (i) amputees difficulty to keep balance, (ii) suboptimal performance in gait functions and (iii) increased energy consumption. This also hugely affects their participation in the activities of daily living. Improving postural control functions in people with lower-limb amputation has the aim to enhance their quality of life and is achieved through the restoration of their lost sensory feedback. The objective of this paper is to propose a stimulation system for restoring plantar pressure perception and knee-joint proprioception in lower-limb amputees. The proposed approach is based on the combined use of two FSRs, two accelerometers and two or three vibrotactile actuators. For validating the system, two experimental sessions were carried out on sixteen healthy subjects and one lower-limb amputee. They were aimed to (i) assess if vibrotactile feedback can improve balance control in lower-limb amputees and (ii) investigate the potentiality of the vibrotactile perception as a means to restore amputees' knee-joint proprioception. Quantitative indices capable of describing users' performance were extracted from the processed data and a statistical analysis was performed to compare different types of sensory feedback: i.e. (i) augmented visuo-proprioceptive feedback, no feedback, forearm vibrotactile feedback and low-back vibrotactile feedback in the 1stexperimental session and (ii) forearm continuous vibrotactile feedback, low-back continuous vibrotactile feedback, forearm discrete vibrotactile feedback, and low-back discrete vibrotactile feedback in the 2ndexperimental session. The achieved results on the vibrotactile stimulation were encouraging for both applications, i.e. restoring amputees' plantar pressure perception and knee-joint proprioception.

In this paper we propose and validate a teleoperated control approach for an anthropomorphic redundant robotic manipulator, using magneto-inertial sensors (IMUs). The proposed method allows mapping the motion of the human arm (used as the master) on the robot end-effector (the slave). We record arm movements using IMU sensors, and calculate human forward kinematics to be mapped on robot movements. In order to solve robot kinematic redundancy, we implemented different algorithms for inverse kinematics that allows imposing anthropomorphism criteria on robot movements. The main objective is to let the user to control the robotic platform in an easy and intuitive manner by providing the control input freely moving his/her own arm and exploiting redundancy and anthropomorphism criteria in order to achieve human-like behaviour on the robot arm. Therefore, three inverse kinematics algorithms are implemented: Damped Least Squares (DLS), Elastic Potential (EP) and Augmented Jacobian (AJ). In order to evaluate the performance of the algorithms, four healthy subjects have been asked to control the motion of an anthropomorphic robot arm (i.e. the Kuka Light Weight Robot 4+) through four magneto-inertial sensors (i.e. Xsens Wireless Motion Tracking sensors - MTw) positioned on their arm. Anthropomorphism indices and position and orientation errors between the human hand pose and the robot end-effector pose were evaluated to assess the performance of our approach.

One of the main problems in the prosthetic hand design is to provide the hand with a reliable system for force and slippage control. The real-time detection of an object slippage during grasping plays a fundamental role in performing a stable grasp. Aim of this paper is to propose and test (i) a system for object slippage detection during grasping, (ii) a control strategy for grasping force regulation and slippage prevention and (iii) a finger coordination method for replicating on the prosthesis system a human-like behaviour. The approach has been validated on a real prosthetic hand, i.e. the IH2 Azzurra (developed by Prensilia), on which tips force sensing resistors have been placed. The preliminary experimental results have demonstrated the feasibility of the methods for slipping detection and for force/slippage control and have shown that the prosthetic hand is able to perform a stable pinch grasp of different objects guaranteeing finger coordination.

This paper presents a robotic system for 3D upperlimb robot-aided rehabilitation, grounded on a patient-tailored approach: it real-time adapts therapy characteristics to patient needs, by including the patient in the control loop. The system is composed of a 7-DoF robot arm, an adaptive interaction control system and a module for the evaluation of patient performance; it records patient biomechanical data through an unobtrusive sensory system, evaluates patient biomechanical state and updates robot control parameters for modifying the level of assistance and task complexity in the 3D space. The adaptive interaction control and the module for assessing patient biomechanical state are described in detail in the paper. The experimental validation is carried out on healthy subjects and results in 2D and 3D space are provided.

The wrist plays a fundamental role in reaching and grasping actions, i.e. it guides the hand to the grasp position and adjusts its orientation on the basis of the grasping type and task. This paper proposes a novel, low-cost method for wrist pose estimation by using the Asus Xtion Pro Live motion sensing device and a robust marker-based tracking approach based on Unscented Kalman Filter (UKF). The hand palm kinematic model is also considered. The applicability of the approach to evaluate some interesting kinematics parameters, such as position, orientation, Range Of Motion, angular and linear velocity and trajectory has been proved. In particular, since the nature of the paper is to present a novel approach for wrist pose estimation, only initial validation for wrist kinematic measurement will be reported.

One of the main limitations of systems for Minimally Invasive Robotic Surgery is the lack of haptic feedback. In this paper, a teleoperated system for robotic surgery is introduced, able to guide the surgeon towards a target anatomy by providing her with force feedback based on Virtual Fixtures (VF). The teleoperated system has a redundant slave robot. A closed-form inverse kinematics is proposed to solve redundancy that is based on an optimization approach in one variable. Four different cost objective functions are proposed in the paper and one is implemented and validated, i.e. the cost function aimed at minimizing the amount of space of the robot in the operative theater during the surgical procedure. The proposed teleoperated architecture has been tested on a teleoperated system composed of a 3-DoFs haptic joystick and a 7-DoFs anthropomorphic manipulator. Experimental tests on 12 volunteer subjects have been carried out. Results demonstrate that a force feedback based on VF provides a statistically significant enhancement of procedure accuracy.

Humans have the ability to learn novel motor tasks while manipulating the environment. Several models of motor learning have been proposed in the literature, but few of them address the problem of retention and interference of motor memory. The modular selection and identification for control (MOSAIC) model, originally proposed by Wolpert and Kawato, is one of the most relevant contributions; it suggests a possible strategy on how the human motor control system learns and adapts to novel environments. MOSAIC employs the concept of forward and inverse models. The same group later proposed the hidden Markov model (HMM) MOSAIC, which affords learning multiple tasks. The significant drawback of this second approach is that the HMM must be trained with a complete data set that includes all contexts. Since the number of contexts or modules is fixed from the onset, this approach does not afford incremental learning of new tasks. In this letter, we present an alternative architecture to overcome this problem, based on a nonparametric regression algorithm, named locally weighted projection regression (LWPR). This network structure develops according to the contexts allowing incremental training. Of notice, interaction force is used to disambiguate among different contexts. We demonstrate the capability of this alternative architecture with a simulated 2 degree-of-freedom representation of the human arm that learns to interact with three distinct objects, reproducing the same test paradigm of the HMM MOSAIC. After learning the dynamics of the three objects, the LWPR network successfully learns to compensate for a novel velocity-dependent force field. Equally important, it retains previously acquired knowledge on the interaction with the three objects. Thus, this architecture allows both incremental learning of new tasks and retention of previously acquired knowledge, a feature of human motor learning and memory.

This paper presents the design criteria of a robot manipulator for the rehabilitation of the upper limb. The machine is conceived to optimize the dynamic behavior in the interaction with the patient, basically in terms of low impedance when back-driven and low and isotropic inertial properties. Robot kinematics and dynamics are mathematically modeled and its dynamic properties are measured in the workspace in terms of inertia and acceleration capabilities. A method is used that is borrowed from the literature and is based on inertia and acceleration graphical representation through ellipsoids.

In recent years, advances and improvements in engineering and robotics have been strengthening interactions between biological science and robotics in the goal of mimicking the complexity of biological systems. In this paper, motor control paradigms inspired by human mechanisms of sensory-motor coordination are applied to a biologically-inspired, purpose-designed robotic platform. The goal was to define and implement a multi-network architecture and to demonstrate that progressive learning of object grasping and manipulation can greatly increase performance of a robotic system in terms of adaptability, flexibility, growing competences and generalization, while preserving the robustness of traditional control. The paper presents the neural approach to sensory-motor coordination and shows preliminary results of the integration with the robotic system by means of simulation tests and experimental trials.

In this paper a PD control with on-line gravity compensation is proposed for robot manipulators with elastic joints. The work extends the existing PD control with constant gravity compensation, where only the gravity torque needed at the desired configuration is used throughout motion. The control law requires measuring only position and velocity on the motor side of the elastic joints, and the on-line compensation scheme estimates the actual gravity torque using a biased measure of the motor position. It is proved via a Lyapunov argument that the control law globally stabilizes the desired robot configuration. Experimental results on an 8-d.o.f. robot manipulator with elastic joints show that this control scheme improves the transient behavior with respect to a PD controller with constant gravity compensation. In addition, it can be usefully applied in combination with a point-to-point interpolating trajectory leading to a reduction of final steady-state errors due to static friction and/or uncertainty in the gravity compensation.

Studies of human motor control suggest that humans develop internal models of the arm during the execution of voluntary movements. In particular, the internal model consists of the inverse dynamic model of the musculoskeletal system and intervenes in the feedforward loop of the motor control system to improve reactivity and stability in rapid movements. In this paper, an interaction control scheme inspired by biological motor control is resumed, i.e. the coactivation-based compliance control in the joint space (Zollo, L, et al., 2003), and a feedforward module capable of online learning the manipulator inverse dynamics is presented. A novel recurrent learning paradigm is proposed which derives from an interesting functional equivalence between locally weighted regression networks and Takagi-Sugeno-Kang fuzzy systems. The proposed learning paradigm has been named recurrent locally weighted regression networks and strengthens the computational power of feedforward locally weighted regression networks. Simulation results are reported to validate the control scheme.

Neurophysiological studies show that humans possess the capability of generating appropriate motor behaviors to different uncertain environmental conditions by combining a forward action, produced by the internal forward dynamic model, and a feedback control, realising the transformation from sensory information to motor commands. To this regard, a control system based on the combination of a feedforward and a feedback control loop has been developed in order to provide a robot arm with human-like adaptation capabilities. The work analyses the role of biological coactivation in the mechanism of adjustable visco-elastic arm properties and proposes a function for the evaluation of the robot arm coactivation based on the measure of the position error and the interaction force. The coactivation function is used to update the proportional and derivative parameters of the feedback controller and, consequently, the arm visco-elasticity in unpredictable environmental conditions. Finally, experimental results on the evolution of the coactivation in the adaptation and de-adaptation phases are provided in the last section of the paper.

The development of humanoid robots and their application as personal robots introduce problems related to the interaction of robots with humans and with environments specifically designed for human beings. In tasks where human-robot cooperation is required, compliance of the robot arm can provide a helpful solution, not only to ensure safety, but especially to increase the robot functionality and usability. The concept of functional compliance is illustrated and an experimental validation is reported, where the functionality of an anthropomorphic robot arm is comparatively assessed with and without compliant control. The paper describes the implementation of a compliant control scheme on an anthropomorphic robotic manipulator, illustrates in detail the methodology adopted for the experimental comparative validation and reports the results obtained in the execution of a sample task by a set of potential users, showing the increased performance in the case of compliant control. Indications are also provided on the improvement of acceptability, which is also affected by the enhanced performance.

This paper presents a research work on compliant control of an anthropomorphic robot arm used as a personal robot. In personal applications of robotics, human-robot interaction represents a critical factor for a robot design and introduces strict requirements on its behavior and control, which has to ensure safety and effectiveness. In this work, the problem of controlling the Dexter anthropomorphic robot arm with variable compliance has been investigated, not only to ensure safety in the interaction with humans, but especially to increase the robot functionality in tasks of physical interaction, performed in co-operation with humans. Two different control schemes have been formulated and implemented, to compare their performance experimentally. Both schemes aim at realising a self-controlled compliant behavior without using information from force/torque sensors. The experimental comparison outlines how the performance of the two control systems are inverted with respect to the theoretical considerations, based on the classical control theory, on their accuracy and effectiveness.

The aim of the work is the integration of an anthropomorphic robotic platform, starting from a neurophysiological model of grasping, in order to provide tools for an experimental validation of the model and also to provide new anthropomorphic solutions for robot grasping. The resulting robotic system is composed of an anthropomorphic arm/hand system and visual and tactile sensors. Grasp planning, control and learning have been achieved by a neural approach, inspired by a model of the inter-connections among the brain areas involved in grasping, as formulated by neurophysiologists. After a description of objectives and specifications for the robotic platform, the system is illustrated and experimental results are reported. Finally, the results are discussed as a starting point for current activities, involving the development of novel human-like robotic components and the implementation of more sophisticated learning schemes.

A research work on the interaction control of a cable-actuated robot arm, the Dexter arm, is presented in this paper. Firstly, general considerations on the cable-actuated structures and their application potential are provided and then the Dexter structure peculiarities are accurately analyzed in order to develop proper control solutions. Starting from the analysis of the limitations of the compliance control schemes in Cartesian space and in joint space, previously implemented and experimentally validated on the Dexter arm, a novel control strategy, named impedance-compliance controller, is developed. The proposed control strategy tries to combine the benefits of a compliance control scheme in Cartesian space with the benefits of an impedance control scheme in the operational space by compensating the dynamics of the sole proximal joints. The impedance-compliance controller is capable to achieve accurate smooth motions while guaranteeing functional control of the whole structure, even though a greater computational complexity is required The last section of the paper, dedicated to the experimental results, points out the differences with the previously experimented control solutions anti provides some proofs of the increased Dexter functionality.

The research in the field of advanced robotics is turning its attention more and more to man and his assistance, by developing systems such as service robots, personal robots, and even humanoid robots. Interaction control of such robot manipulators is of paramount importance for an effective execution of manipulation and tracking and, over all, for a safe and effective interaction with the humans. The paper concerns the problem of the control of an 8 degree of freedom anthropomorphic arm named DEXTER, mounted on the mobile platform of the MOVAID System, a robotic system for household personal assistance. The goal is to realize a compliant control for this manipulator in tasks of assistance to disabled and elderly people. On the basis of the control theory applied to industrial robotics, a specific compliant control solution has been developed for the DEXTER peculiar mechanical structure and actuation system, which cause a coupled joint configuration. The solution provides the capability of regulating the robot compliance according to the level of stiffness of the interaction environment. The paper describes the theoretical model of the control system, the implementation on the MOVAID platform and the experimental results in the execution of a set of demonstration tasks.