Hybrid brain/neural interface and autonomous vision-guided whole-arm exoskeleton control to perform activities of daily living (ADLs).

BACKGROUND: The aging of the population and the progressive increase of life expectancy in developed countries is leading to a high incidence of age-related cerebrovascular diseases, which affect people's motor and cognitive capabilities and might result in the loss of arm and hand functions. Such conditions have a detrimental impact on people's quality of life. Assistive robots have been developed to help people with motor or cognitive disabilities to perform activities of daily living (ADLs) independently. Most of the robotic systems for assisting on ADLs proposed in the state of the art are mainly external manipulators and exoskeletal devices. The main objective of this study is to compare the performance of an hybrid EEG/EOG interface to perform ADLs when the user is controlling an exoskeleton rather than using an external manipulator. METHODS: Ten impaired participants (5 males and 5 females, mean age 52 ± 16 years) were instructed to use both systems to perform a drinking task and a pouring task comprising multiple subtasks. For each device, two modes of operation were studied: synchronous mode (the user received a visual cue indicating the sub-tasks to be performed at each time) and asynchronous mode (the user started and finished each of the sub-tasks independently). Fluent control was assumed when the time for successful initializations ranged below 3 s and a reliable control in case it remained below 5 s. NASA-TLX questionnaire was used to evaluate the task workload. For the trials involving the use of the exoskeleton, a custom Likert-Scale questionnaire was used to evaluate the user's experience in terms of perceived comfort, safety, and reliability. RESULTS: All participants were able to control both systems fluently and reliably. However, results suggest better performances of the exoskeleton over the external manipulator (75% successful initializations remain below 3 s in case of the exoskeleton and bellow 5s in case of the external manipulator). CONCLUSIONS: Although the results of our study in terms of fluency and reliability of EEG control suggest better performances of the exoskeleton over the external manipulator, such results cannot be considered conclusive, due to the heterogeneity of the population under test and the relatively limited number of participants.

The WGD-A Dataset of Assembly Line Working Gestures for Ergonomic Analysis and Work-Related Injuries Prevention.

This paper wants to stress the importance of human movement monitoring to prevent musculoskeletal disorders by proposing the WGD-Working Gesture Dataset, a publicly available dataset of assembly line working gestures that aims to be used for worker's kinematic analysis. It contains kinematic data acquired from healthy subjects performing assembly line working activities using an optoelectronic motion capture system. The acquired data were used to extract quantitative indicators to assess how the working tasks were performed and to detect useful information to estimate the exposure to the factors that may contribute to the onset of musculoskeletal disorders. The obtained results demonstrate that the proposed indicators can be exploited to early detect incorrect gestures and postures and, consequently to prevent work-related disorders. The approach is general and independent on the adopted motion analysis system. It wants to provide indications for safely performing working activities. For example, the proposed WGD can also be used to evaluate the kinematics of workers in real working environments thanks to the adoption of unobtrusive measuring systems, such as wearable sensors through the extracted indicators and thresholds.

A semi-autonomous robot control based on bone layer transition detection for a safe pedicle tapping.

PURPOSE: Automatic robotic platforms for robot-aided spinal surgery are mostly employed for drilling the pedicle screw path and do not adapt the tool rotational speed depending on the variation of the bone density. This feature is highly desirable in control strategies for robot-aided pedicle tapping, which may result in a poor quality thread if the surgical tool speed is not adequately tuned depending on the bone density to be threaded. Therefore, the objective of this paper is to propose a novel semi-autonomous control for robot-aided pedicle tapping that is able to (i) identify the bone layer transition, (ii) adapt the tool velocity depending on the detected bone layer density and (iii) stop the tool tip before propulsion of the bone boundaries. METHODS: The proposed semi-autonomous control for pedicle tapping consists of: (i) a hybrid position/force control loop that allows the surgeon to move the surgical tool along a pre-planned axis and (ii) a velocity control loop that allows him/her to finely tune the tool rotational speed by modulating the tool-bone interaction force along the same axis. The velocity control loop integrates also a bone layer transition detection algorithm that dynamically limits the tool velocity depending on the bone layer density. The approach was tested on the Kuka LWR4+ provided with an actuated surgical tapper which was used to tap a wood specimen simulating the bone layer density characteristics and bovine bones. RESULTS: A normalized maximum time delay in the bone layer transition detection of 0.25 was achieved by the experiments. A success rate of [Formula: see text] was achieved for all the tested tool velocities. The proposed control achieved a maximum steady-state error of 0.4 rpm. CONCLUSION: The study demonstrated high capability of the proposed approach to i) promptly detect transition among the specimen layers and ii) adapt the tool velocities depending on the detected layers.

Affective state estimation based on Russell's model and physiological measurements.

Affective states are psycho-physiological constructs connecting mental and physiological processes. They can be represented in terms of arousal and valence according to the Russel's model and can be extracted from physiological changes in human body. However, a well-established optimal feature set and a classification method effective in terms of accuracy and estimation time are not present in the literature. This paper aims at defining a reliable and efficient approach for real-time affective state estimation. To obtain this, the optimal physiological feature set and the most effective machine learning algorithm, to cope with binary as well as multi-class classification problems, were identified. ReliefF feature selection algorithm was implemented to define a reduced optimal feature set. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), cubic and gaussian Support Vector Machine, and Linear Discriminant Analysis, were implemented to compare their effectiveness in affective state estimation. The developed approach was tested on physiological signals acquired on 20 healthy volunteers during the administration of images, belonging to the International Affective Picture System, conceived for inducing different affective states. ReliefF algorithm reduced the number of physiological features from 23 to 13. The performances of machine learning algorithms were compared and the experimental results showed that both accuracy and estimation time benefited from the optimal feature set use. Furthermore, the KNN algorithm resulted to be the most suitable for affective state estimation. The results of the assessment of arousal and valence states on 20 participants indicate that KNN classifier, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation.

Tailoring Upper-Limb Robot-Aided Orthopedic Rehabilitation on Patients' Psychophysiological State.

Physical therapy keeps exploiting more and more the capabilities of the robot of adapting the treatments to patients' needs. This paper aims at presenting a psychophysiological-aware control strategy for upper limb robot-aided orthopedic rehabilitation. The main features are the capability of i) generating point-to-point trajectories inside an adaptable workspace, ii) providing assistance in guiding the patients' limbs in accomplishing the assigned task allowing them to freely move with a certain degree of spatial and temporal autonomy and iii) tuning the control parameters according to the patients' kinematics performance and psychophysiological state. The implemented control strategy is validated in a real clinical setting on eight orthopedic patients undergoing twenty daily robot-aided rehabilitation sessions. The psychophysiological-aware control strategy evidenced a positive impact on the enrolled participants since they are effectively conducted in a calmer condition with respect to the patients who did not receive the psychophysiological adaptation. Moreover, clinical performance indicators suggest that the proposed tailored control strategy improves motor functions.

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.

Visual vs vibrotactile feedback for posture assessment during upper-limb robot-aided rehabilitation.

Repetitive and intensive exercises during robot-aided rehabilitation may expose patients to inappropriate and unsafe postures. The introduction of a sensory feedback can help the subject to perform the rehabilitation task with an ergonomic posture. In this work, the introduction of visual and vibrotactile feedback in a robotic platform for upper limb rehabilitation has been proposed to ensure ergonomic posture during rehabilitation. The two feedback modalities have been used to provide information about incorrect neck and trunk posture. Ten healthy subjects have been involved in this study. Each of them performed 3D reaching movements with the aid of the robotic platform in three different conditions, i.e. without feedback, with visual feedback and with vibrotactile feedback, and a comparative analysis has been carried out to evaluate feedback effectiveness, acceptance and performance. Experimental results show that in case of no feedback the subjects reach and maintain configurations that can lead to incorrect neck and trunk configurations and therefore, if repeated, to musculoskeletal disorders. Conversely, with visual or vibrotactile feedback, the subjects tend to correct inappropriate posture with both trunk and head during task performing.

Learning by Demonstration for Motion Planning of Upper-Limb Exoskeletons.

The reference joint position of upper-limb exoskeletons is typically obtained by means of Cartesian motion planners and inverse kinematics algorithms with the inverse Jacobian; this approach allows exploiting the available Degrees of Freedom (i.e. DoFs) of the robot kinematic chain to achieve the desired end-effector pose; however, if used to operate non-redundant exoskeletons, it does not ensure that anthropomorphic criteria are satisfied in the whole human-robot workspace. This paper proposes a motion planning system, based on Learning by Demonstration, for upper-limb exoskeletons that allow successfully assisting patients during Activities of Daily Living (ADLs) in unstructured environment, while ensuring that anthropomorphic criteria are satisfied in the whole human-robot workspace. The motion planning system combines Learning by Demonstration with the computation of Dynamic Motion Primitives and machine learning techniques to construct task- and patient-specific joint trajectories based on the learnt trajectories. System validation was carried out in simulation and in a real setting with a 4-DoF upper-limb exoskeleton, a 5-DoF wrist-hand exoskeleton and four patients with Limb Girdle Muscular Dystrophy. Validation was addressed to (i) compare the performance of the proposed motion planning with traditional methods; (ii) assess the generalization capabilities of the proposed method with respect to the environment variability. Three ADLs were chosen to validate the system: drinking, pouring and lifting a light sphere. The achieved results showed a 100% success rate in the task fulfillment, with a high level of generalization with respect to the environment variability. Moreover, an anthropomorphic configuration of the exoskeleton is always ensured.