End-effector-based robots are widely adopted by physiotherapists and caregivers as support in the delivery of the rehabilitation training to the patient. The validation of these devices presents critical aspects, since the system performance must be assessed analyzing the movement performed by the subject limb, i.e., elements outside the device. This paper presents a multi-sensor approach for the validation of an innovative end-effector-based device, comparing different measurement strategies for evaluating the system effectiveness in imposing an expected training. The study was performed monitoring the movement induced by the device on the upper limb of a young male healthy subject during a set of fictitious rehabilitation sessions. The kinematic structure of the device is characterized by a compact differential mechanism with two degrees of freedom. A sequence of repetitions of a planar reaching pattern was analyzed as illustrative training task. A kinematic model of subject and system was developed, and the kinematics of a set of specific landmark points on the subject limb was evaluated. Data obtained from two measurement systems were compared: (1) an optoelectronic system with two cameras and eight skin passive markers, and (2) two triaxial accelerometers. Results were analyzed in MATLAB and R environment, revealing a high repeatability of the limb movement. Although both the measurement systems allow evaluating the acceleration of subject’s arm and forearm, accelerometers should be preferred for punctual analysis, like components optimizations, whereas optical markers provide a general overview of the system, particularly suitable for the functional design process.

Objective: Robotic devices are commonly used in rehabilitation as support to physiotherapists in their daily rehabilitation activities, since they can monitor and quantify the subject's performance and deliver feedback, as well as supply physical therapy. This work aims at performing a preliminary validation of an innovative device, developed within the SIMeRiON funded project, and identifying the optimal experimental setup for the clinical trials, through the analysis of the characteristics of a planar reaching movement impressed to the upper limb of the subject in a sequence of repetitions. Methods: A male healthy subject (26 years old) has been recruited, and asked to perform an imposed reaching movement with his left arm, during three consecutive sessions. The subject was instrumented with two triaxial accelerometers, placed in two possible configurations, and eight passive optical markers evaluated with a two fixed cameras optoelectronic system. To identify and compare different motion cycles, the collected data have been analyzed in MATLAB and R environment. Results: Data emphasize a high repeatability of the imposed movement, especially at human-machine interface, and suggest that accelerometers data could be integrated with different sensors (e.g. sEMG sensors).

Detecting human motion and predicting human intentions by analyzing body signals are challenging but fundamental steps for the implementation of applications presenting human–robot interaction in different contexts, such as robotic rehabilitation in clinical environments, or collaborative robots in industrial fields. Machine learning techniques (MLT) can face the limit of small data amounts, typical of this kind of applications. This paper studies the illustrative case of the reaching movement in 10 healthy subjects and 21 post-stroke patients, comparing the performance of linear discriminant analysis (LDA) and random forest (RF) in: (i) predicting the subject’s intention of moving towards a specific direction among a set of possible choices, (ii) detecting if the subject is moving according to a healthy or pathological pattern, and in the case of discriminating the damage location (left or right hemisphere). Data were captured with wearable electromagnetic sensors, and a sub-section of the acquired signals was required for the analyses. The possibility of detecting with which arm (left or right hand) the motion was performed, and the sensitivity of the MLT to variations in the length of the signal sub-section were also evaluated. LDA and RF prediction accuracies were compared: Accuracy improves when only healthy subjects or longer signals portions are considered up to 11% and at least 10%, respectively. RF reveals better estimation performance both as intention predictor (on average 59.91% versus the 62.19% of LDA), and health condition detector (over 90% in all the tests).

Soft Tissue Artifact (STA) remains the most significant error for optoelectronic motion analyses based on surface markers. STA knowledge is fundamental for measurement confidence, providing indications about the significance of measured motion conditions of patients. STA is task-related and subject-dependent, but few actual datasets are currently available on STA in hand kinematics, with non-invasive techniques. Besides, STA depends on the measurement protocol, so normalization techniques as the deformation energy evaluation must be applied to make data comparable among different works. Focusing on hand kinematics, this paper presents: i) a new biomechanical model for the description of hand kinematics, and ii) design and results of an experimental campaign leading to a significant dataset of displacements of specific landmark points on fingers during flexion/extension using a non-invasive method. Experimental results show that STA produces an error up to 87% of the phalanges length and it can be suggested as clinical significance of optoelectronic measurements of the hand motion. Copyright © 2020 Praise Worthy Prize - All rights reserved.

Objective: The sit-to-stand transition is an important task for the evaluation of physical independence, especially in fragile subjects like elderly patients, to monitor and reduce the risk of falls or damage. This study aims at assessing the kinematic characteristics of the sit-to-stand transition from a quantitative perspective, using a wireless IMU sensor, and describes a set of parameters suitable for evaluating the movement performance in everyday practice. Methods: An acquisition campaign was designed and carried out on 20 healthy subjects and 13 patients to evaluate acceleration and angular velocity generated during a sit-to-stand task. For each subject, at least four acquisitions were performed, to create a final dataset of 173 acquisitions. The values of the proposed parameters were computed, and results were analyzed with descriptive statistics. Results: According to the proposed parameters definitions and the analyzed dataset, acceleration-and angular velocity-related parameters present statistically significant differences between healthy and pathological data samples, unlike total time TT.