Volume 2, Issue 4

Although surface electromyography (sEMG) has a high correlation to muscle force, an accurate model that can estimate joint torque from sEMG is still elusive. Artificial neural networks (NN), renowned as universal approximators, have been employed to capture this complex nonlinear relation. This work focuses on investigating possible improvements to the NN methodology and algorithm that would consistently produce reliable sEMG-to-knee-joint torque mapping for any individual. This includes improvements in number of inputs, data normalization techniques, NN architecture and training algorithms. Data (sEMG) from five knee extensor and flexor muscle from one subject were recorded on 10 random days over a period of 3 weeks whilst subject performed both isometric and isokinetic movements. The results indicate that incorporating more muscles into the NN and normalizing the data at each isometric angle prior to NN training improves torque estimation. The mean lowest estimation error achieved for isometric motion was 10.461% (1.792), whereas the lowest estimation errors for isokinetic motion were larger than 20%.

Stroke is one of the major causes of permanent adult disability. Stroke frequently affects motor control of the arm, leading to diffculties in doing activities of daily living. This research focuses on developing an upper limb rehabilitation robotic prototype through user-centered design to aid stroke survivors in rehabilitating their arm. To gather requirements from end users, stroke therapy sessions were observed and a survey of stroke therapists was conducted. End user requirements were evaluated to determine technical targets for the mechanical design of the prototype. Evaluation of the prototype was done with stroke therapists in a focus group and a preliminary biomechanical study. As user-centered design would require more iterations of design, testing and evaluation, this project reports a first step in developing an affordable, portable device, which could increase access to stroke rehabilitation for the arm.

Hemiparesis is a frequent and disabling consequence of stroke and can lead to asymmetric and ineffcient walking patterns. Training on a split-belt treadmill, which has two separate treads driving each leg at a different speed, can correct such asymmetries post-stroke. However, the effects of split-belt treadmill training only partially transfer to everyday walking over ground and extended training sessions are required to achieve long-lasting effects. Our aim is to develop an alternative device, the Gait Enhancing Mobile Shoe (GEMS), that mimics the actions of the split-belt treadmill, but can be used during over-ground walking and in one’s own home, thus enabling long-term training. The GEMS does not require any external power and is completely passive; all necessary forces are redirected from the natural forces present during walking. Three healthy subjects walked on the shoes for twenty minutes during which one GEMS generated a backward motion and the other GEMS generated a forward motion. Our preliminary experiments suggest that wearing the GEMS did cause subjects to modify coordination between the legs and these changes persisted when subjects returned to normal over-ground walking. The largest effects were observed in measures of temporal coordination (e.g., duration of double-support). These results suggest that the GEMS is capable of altering overground walking coordination in healthy controls and could potentially be used to correct gait asymmetries post-stroke.

This project deals with technical assistance for people of reduced mobility. The goal of this work is to have a mobile platform with an embedded prehensive arm (MANUS ® ) track a wheelchair. The use of this mobile unit in relation to the patient’s wheelchair is carried out on a master-slave basis. This study, therefore, has a plural-disciplinary nature: Science for the Engineer, Human, Social and Clinical Sciences. To ensure the tracking of the wheelchair by the mobile platform, we applied a stereo bearings-only tracking (BOT) paradigm to a single moving target. The observer, the mobile platform (robot), is equipped with two omnidirectional vision sensors, that each provides output with which we compute two bearing angles. Having two bearing angles makes it possible to track a manoeuvring target. In this paper we will show how we take advantage of the multi-sensor data fusion to improve the BOT process and hence obtain a more reliable wheelchair tracking.

The objective of the work presented is to improve functional electrical stimulation (FES) assisted sit-to-stand motion in complete paraplegic individuals by restoring coordination between the upper part of the subject’s body, under voluntary control, and the lower part of the body, under FES control. The proposed approach is based on the observation of trunk movement during rising motion and a detection algorithm, which triggers a pre-programmed stimulation pattern. We present a pilot study carried out on one T6 paraplegic subject. We validated the ability of the subject to produce repeatable trunk acceleration during sit-to-stand transfers under FES and, the ability of the system to trigger the stimulator at the desired instant in time. We also analyzed the influence of the timing of leg stimulation, relative to the trunk acceleration profile, on upper limb efforts applied during sit-to-stand motion.

Due to their quantitative nature, robotic systems are useful tools for systematically augmenting human behavior and performance in dynamic environments, such as therapeutic rehabilitation settings. The efficacy of human-robot interaction (HRI) in these settings will depend on the robot’s coaching style. Our goal was to investigate the influence of robot coaching styles designed to enhance motivation and encouragement on post-stroke individuals during motor task practice. We hypothesized that coaching styles incorporating user performance and preference would be preferred in a therapeutic HRI setting. We designed an evaluation study with seven individuals post stroke. A socially assistive robotics (SAR) system using three different coaching styles guided participants during performance of an upper extremity practice task. User preference was not significantly affected by the different robot coaching styles in our participant sample (H(2) = 2.638, p = 0.267). However, trends indicated differences in preference for the coaching styles. Our results provide insights into the design and use of SAR systems in therapeutic interactions aiming to influence user behavior.