To assist people with disabilities, exoskeletons must be provided with human-robot interfaces and smart algorithms capable to identify the user’s movement intentions. Surface electromyographic (sEMG) signals could be suitable for this purpose, but their applicability in shared control schemes for real-time operation of assistive devices in daily-life activities is limited due to high inter-subject variability, which requires custom calibrations and training. Here, we developed a machine-learning-based algorithm for detecting the user’s motion intention based on electromyographic signals, and discussed its applicability for controlling an upper-limb exoskeleton for people with severe arm disabilities. Ten healthy participants, sitting in front of a screen while wearing the exoskeleton, were asked to perform several reaching movements toward three LEDs, presented in a random order. EMG signals from seven upper-limb muscles were recorded. Data were analyzed offline and used to develop an algorithm that identifies the onset of the movement across two different events: moving from a resting position toward the LED (Go-forward), and going back to resting position (Go-backward). A set of subject-independent time-domain EMG features was selected according to information theory and their probability distributions corresponding to rest and movement phases were modeled by means of a two-component Gaussian Mixture Model (GMM). The detection of movement onset by two types of detectors was tested: the first type based on features extracted from single muscles, whereas the second from multiple muscles. Their performances in terms of sensitivity, specificity and latency were assessed for the two events with a leave one-subject out test method. The onset of movement was detected with a maximum sensitivity of 89.3% for Go-forward and 60.9% for Go-backward events. Best performances in terms of specificity were 96.2 and 94.3% respectively. For both events the algorithm was able to detect the onset before the actual movement, while computational load was compatible with real-time applications. The detection performances and the low computational load make the proposed algorithm promising for the control of upper-limb exoskeletons in real-time applications. Fast initial calibration makes it also suitable for helping people with severe arm disabilities in performing assisted functional tasks.

This paper presents the H-PULSE, a novel semi-passive upper-limb exoskeleton for worker assistance, with motorized tuning of the assistive level. The H-PULSE presents novel design features compared to other passive industrial exoskeletons for the upper limbs, namely joint angle sensors for measuring shoulder flexion/extension and a novel active mechanism for regulating the assistance level. These features could enhance the effectiveness of the system. Along with the presentation of the exoskeleton design, this paper reports on the system experimental evaluation with human subjects. The H-PULSE was assessed in prolonged static overhead tasks under different conditions of assistive support. The set of metrics to evaluate the effects of the device included shoulder muscular activity, heart rate, and subjective user feedback. Results show that the exoskeleton can reduce the users’ muscular activity and the heart rate. Subjective questionnaires allowed the assessment of perceived exoskeleton effectiveness. In this study, the H-PULSE exoskeleton was found to be potentially effective in reducing the muscular strain while reducing the global fatigue level during prolonged continuous overhead activities.

This paper presents the design and experimental characterization of a 4-degree-of-freedom shoulder-elbow exoskeleton (NESM) for upper-limb neurorehabilitation and treatment of spasticity. The NESM employs a self-aligning mechanism based on passive rotational joints to smoothly self-align the robot's rotational axes to the user's ones. Compliant yet high-torque series-elastic actuators allow the NESM to safely interact with the user, particularly in response to sudden unpredicted movements, such as those caused by spastic contractions. The NESM control system provides a variety of rehabilitation exercises, enabling the customization of therapy to patients exhibiting a range of movement capabilities. Available exercises include passive mobilization, active-assisted, active-resisted, and active-disturbed training modes. The experimental characterization of two NESM actuation units demonstrated position and torque control performance suitable for use in neurorehabilitation applications, including up to 7 Hz of bandwidth in torque control. An algorithm for online detection of spastic contractions or sudden object collisions has been implemented and tested as well, with results suggesting that the current system can ensure safe interaction with patients.

Arm and finger paralysis, e.g. due to brain stem stroke, often results in the inability to perform activities of daily living (ADLs) such as eating and drinking. Recently, it was shown that a hybrid electroencephalography/electrooculography (EEG/EOG) brain/neural hand exoskeleton can restore hand function to quadriplegics, but it was unknown whether such control paradigm can be also used for fluent, reliable and safe operation of a semi-autonomous whole-arm exoskeleton restoring ADLs. To test this, seven abled-bodied participants (seven right-handed males, mean age 30 ± 8 years) were instructed to use an EEG/EOG-controlled whole-arm exoskeleton attached to their right arm to perform a drinking task comprising multiple sub-tasks (reaching, grasping, drinking, moving back and releasing a cup). Fluent and reliable control was defined as average ‘time to initialize’ (TTI) execution of each sub-task below 3 s with successful initializations of at least 75% of sub-tasks within 5 s. During use of the system, no undesired side effects were reported. All participants were able to fluently and reliably control the vision-guided autonomous whole-arm exoskeleton (average TTI 2.12 ± 0.78 s across modalities with 75% successful initializations reached at 1.9 s for EOG and 4.1 s for EEG control) paving the way for restoring ADLs in severe arm and hand paralysis.

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.

Stroke survivors with chronic paralysis often have difficulties to perform various activities of daily living (ADLs), such as preparing a meal or eating and drinking independently. Recently, it was shown that a brain/neural hand exoskeleton can restore hand and finger function, but many stroke survivors suffer from motor deficits affecting their whole upper limb. Therefore, novel hybrid electroencephalography/electrooculography (EEG/EOG)-based brain/neural control paradigms were developed for guiding a whole-arm exoskeleton. It was unclear, however, whether hemiplegic stroke survivors are able to reliably use such brain/neural-controlled device. Here, we tested feasibility, safety, and user-friendliness of EEG/EOG-based brain/neural robotic control across five hemiplegic stroke survivors engaging in a drinking task that consisted of several subtasks (e.g., reaching, grasping, manipulating, and drinking). Reliability was assumed when at least 75% of subtasks were initialized within 3 s. Fluent control was assumed if average “time to initialize” each subtask ranged below 3 s. System's safety and user-friendliness were rated using Likert-scales. All chronic stroke patients were able to operate the system reliably and fluently. No undesired side effects were reported. Four participants rated the system as very user-friendly. These results show that chronic stroke survivors are capable of using an EEG/EOG-controlled semiautonomous whole-arm exoskeleton restoring ADLs.