This work presents the application of an upper-limb rehabilitation protocol in chronique stroke using a Brain-Computer Interface (BCI) based on Motor Imagery (MI), Non-Invasive Brain Stimulation (NIBS) like transcranial Alternating Current Stimulation (tACS), and Functional Electrical Stimulation (FES). This protocol uses the concept of Alternating Treatment Design (ATD), in which a chronic post-stroke subject is submitted to these techniques for recovery of his upper-limb movements affected by the stroke. The rehabilitation progress was verified through metrics, such as Fugl Meyer Assessment Scale (FMS), Functional Independence Measure (FIM), Modified Ashworth Scale (MAS), surface Electromyography (sEMG) and Electroencephalography (EEG). Results from these metrics include a 2.4% increase in FMS and an 11% increase in the muscle contraction of his finger extensors, evaluated by sEMG. For the EEG analysis, there was an energy increase in mu and beta rhythms at the end of protocol.

This study proposes a Brain-Computer Interface (BCI) based on Motor Imagery (MI) for ankle-foot dorsiflexion training, providing Functional Electrical Stimulation (FES) as a way of NeuroFeedback (NF), in the tibialis anterior muscle. Riemannian geometry is utilized as a feature extraction technique for a more reliable MI-based electroencephalography discrimination, also considering Passive Movement (PM) data. A complete Spinal Cord Injury (SCI) individual tested the BCI during five sessions, each one on a different day, achieving an accuracy around 0.33, greater than the chance level of 0.25, considering that this is a four-class classification system. The mean BCI latency was lower than 240 ms. Significant Relative power changes (R) were observed in the mu (8-12 Hz) band for MI of dorsiflexion of the feet as well as negative R values centered around Cz, suggesting a better MI performance after observing PM as a visual real guide. As a highlight, our BCI calibrated with more reliable MI data, greatly enhanced the mu (8-12 Hz) rhythm modulation in the operation stage more than the high-beta (18-24 Hz) band modulation. These findings are relevant for advancing NF and BCI approaches to restore lower-limb motor functions, as well as enhance neuroplasticity.

Prevention is key to avoid pressure ulcer generation in people with mobility restrictions. In recent years, preventive medicine has focused on posture control by considering people who frequently have the same position for too long, such as wheelchair users. Optical fiber sensors have gained recognition for their applications in biomedical engineering; however, approaches to assistive devices, such as wheelchairs, have been relatively unexplored. This study proposes a polymeric-optical-fiber (POF) sensing system based on machine learning (ML) for human posture recognition in an electrical wheelchair-based human machine interface (HMI). The ML-based model was used to classify time- and frequency-domain features obtained from a matrix of POF-based pressure sensors and 24 photodetectors during the execution of eight body postures. In an offline stage, multiclassification was conducted using k-nearest neighbors (KNN), decision tree, extra tree classifier (ETC), and random forest, where the best performance, in terms of accuracy (ACC), was obtained through the use of ETC (94%). Hence, this classifier was implemented in real-time, where the wheelchair-based HMI achieved a CPU time of approximately 117 ms, and an ACC higher than 96%, outperforming the metrics previously reported in the literature. We believe that this study contributes to the development of smart assistive systems that integrate ML and soft sensors to recognize body postures in an HMI, which is a promising approach for preventing the generation of pressure ulcers in wheelchair users.

The evaluation of systems under non-ideal conditions is a research problem, particularly in robotic applications for the rehabilitation of people with disabilities. Accordingly, the evaluation of algorithmic strategies for robustness validation under different non-ideal conditions is a current challenge for the scientific community. Therefore, in this study, a computational methodology based on Extreme Learning Machine (ELM) was evaluated for the recognition of seven hand gestures using sEMG under five non-ideal conditions. The shift of eight sEMG electrodes, three upper-limb postures, increased muscle fatigue, and inter-subject and inter-day variabilities were evaluated. The results indicate that the proposed methodology performs well under specific conditions in comparison with previous strategies reported in the literature using Machine Learning classifiers. Therefore, the findings of this study are potentially important for the field of robotics; however, more efforts are still needed to develop more robust computational methods to obtain higher accuracy under non-ideal conditions, with the aim of implementing more controllable, usable, and reliable systems.

The knee flexion-extension angle is an important variable to be monitored in various clinical scenarios, for example, during physical rehabilitation assessment. The purpose of this work is to develop and validate a sensor fusion system based on a knee sleeve for monitoring of physical therapy. The system consists of merging data from two inertial measurement units (IMUs) and an intensityvariation based Polymer Optical Fiber (POF) curvature sensor using a quaternion-based Multiplicative Extended Kalman Filter (MEKF). The proposed data fusion method is magnetometer-free and deals with sensors' uncertainties through reliability intervals defined during gait. Walking trials were performed by twelve healthy participants using our knee sleeve system and results were validated against a gold standard motion capture system. Additionally, a comparison with other three knee angle estimation methods, which are exclusively based on IMUs, was carried out. The proposed system presented better performance (mean RMSE1= 0.99 ± 0.04, α0= 0.70 ± 2.29, R2= 0.98 ± 0.01 and ρC > 0.99) when compared to the other evaluated methods. Experimental results demonstrate the usability and feasibility of our system to estimate knee motion with high accuracy, repeatability, and reproducibility. This wearable system may be suitable for motion assessment in rehabilitation labs in future studies.

Stroke is a neurological syndrome that may affect upper and lower limbs functions of post-stroke survivors. Brain-Computer Interfaces (BCIs) are becoming as a promising alter-native to help post-stroke patients rehabilitation, although there are very few associated studies and systems being applied in clinical environment. As a novelty, developing a motor imagery (MI) BCI based on pedal end-effector for motor rehabilitation, we propose to combine pedaling MI and passive pedaling into a Calibration phase. As a result, users would activate continuously their central and peripheral mechanisms linked to lower-limbs throughout BCI intervention. We hypothesize that this strategy enables to obtain a better classification model for our BCI by selecting those feature vectors corresponding to pedaling MI closer to real movements. Therefore, it is expected to have a more effective BCI intervention. Preliminary results show that the proposed method may increase the BCI performance. For almost all participants was noted, during MI tasks, a power decreasing over the foot area (Cz location), corresponding mainly to beta frequency bands, specifically for both low (13 to 22 Hz) and high (23 to 30 Hz) beta bands.

This work presents a brain-computer interface (BCI) based on unsupervised methods for conveying control commands to a robotic exoskeleton, in order to provide support to patients with severe motor disability during walking. For this purpose, an adaptive spatial filter based on similarity indices is proposed to preserve the useful information on electroencephalography (EEG) signals. Additionally, a method for feature selection based on the Maximal Information Compression Index (MICI), and the representation entropy (RE) is used, increasing its robustness for uncertain patterns, such as gait planning. Good values of accuracy (ACC > 75%) and false positive rate (FPR<; 10%) were obtained for four subjects. Thus, this BCI based on unsupervised method may be suitable to recognize uncertainty pattern, such as gait planning.

Upper limb disorders may impair the use of control interfaces for Electric Powered Wheelchairs (EPW), such as joysticks, for many individuals with disabilities. The aims of this study were to develop and test a virtual wheelchair driving environment that can provide quantifiable measures of driving ability, offer driver training, and measure the performance of alternative controls. This work introduces UFES's SimCadRoM, a virtual reality (VR) system for EPW driving training purposes and testing of control interfaces. It uses a real EPW and a VR headset, making the system very immersive. Some tests were conducted to compare the VR experience and driving performance, with a real EPW driving experience and performance, and the results showed that there is no significant difference between the mean elapsed times along real paths and the virtual ones in the performed pilot test. The Igroup presence questionnaire (IPQ) revealed high values of G1 and SP factors, which are a clear manifestation of presence as the "sense of being there". The INV and REAL factors also presented good indicators of the presence experience's attention component and reality comparison between driving the virtual EPW and the real one.

New research reports shows that important progresses for controlling electric-powered wheelchair have been made recently aiming people with severe disabilities. In fact, a significant amount of people affected by those physical disabilities still cannot take advantage of autonomous mobility, even electronic or automated ones. For those people, the use of proper biological signals to control the assisted environment may be the only existing solution. In such scenario, the act of commanding an electric-powered wheelchair without proper training may be a serious safety risk. To avoid this kind of dangerous situation and to permit users to make use of such technology, one viable solution would be to be trained by using virtual driving simulators. Nevertheless, when using biomedical signals as commands it is not possible to ensure a continuous and reliable control of the wheelchair, it is necessary to associate the control possibilities with autonomous features such as semiautomatic obstacle detection or contour. Thus, it is interesting to offer to new wheelchair users the possibility of using simulators to allow them to learn to drive at distance, making use of telematics techniques combined with mobile and wearable devices, and publishing their progress and worries in social networks, which is the objective of this work. This project joints complementary skills from researchers from the Federal University of Amazonas, Federal University of Espirito Santo, and Federal University of Uberlandia, with the collaboration of researches from the University of Lorraine in Metz-France.

This paper proposes an exponential interpolation to merge a part-of-speech-based language model and a word-based$n$-gram language model to accomplish word prediction tasks. In order to find a set of mathematical equations to properly describe the language modeling, a model based on partial differential equations is proposed. With the appropriate initial conditions, it was found an interpolation model similar to the traditional maximum entropy language model. Improvements in keystroke saved and perplexity over the word-based$n$-gram language model and two other traditional interpolation models is obtained, considering three different languages. The proposed interpolation model also provides additional improvement in hit rate parameter.

This paper presents a comparison among three methods for Steady-State Visually Evoked Potentials (SSVEP) detection. These techniques are based on Power Spectral Density Analysis (PSDA) and Canonical Correlation Analysis (CCA). The first method estimates the signal-to-noise ratio of the power spectrum in each stimulus frequency using PSDA, which is called Traditional-PSDA. The second analysis estimates the relation between the difference of the stimulus frequency and its neighbor frequencies, using the power spectrum in these neighbor frequencies, and seeks the neighbor frequency which presents the lowest relation value. This technique is referred to Ratio-PSDA. The third and final techniques called Hybrid-PSDA-CCA. The performances of the methods were evaluated using a database of electroencephalogram (EEG) signals. The EEG signals were recorded from 19 volunteers, from which six people present disabilities. They were stimulated with visual stimuli flickering at 5.6, 6.4, 6.9 and 8.0 Hz. The system performance was evaluated considering the accuracy, the Information Transfer Rate (ITR) and the computational cost for several windows length of each stimulus frequency. The results showed that the Hybrid-PSDA-CCA method achieved the best result with an average accuracy of 91.14%.

This paper proposes a new reactive method to avoid obstacles during trajectory tracking, considering unicycle mobile robots navigating in semi-structured environments, which can be used in association with any trajectory tracking controller. A meaningful improvement in the obstacle avoidance process is achieved analyzing the layout of the obstacles in relation to the planned trajectory. Experimental results show that the evasion algorithm is fairly efficient, reducing the time spent to avoid obstacles and shortening the path traveled by the robot during such procedure as well.

This paper presents a new fuzzy controller for trajectory tracking for unicycle-like mobile robots, represented by a Takagi-Sugeno fuzzy model. Such controller allows setting different gains for the controller, according to the values of the velocity of the trajectory and the values of the tracking error. The noise inherent to the robot odometry is treated by the fuzzy controller itself, not requiring the use of filters. The stability of the developed controller is proven based on the theory of Lyapunov. Experimental results are also presented, and show that the proposed controller is effectively able to guide the robot during a trajectory tracking task.

This paper presents the classification of three mental tasks, using the electroencephalographic signal and simulating a real-time process, that is, the pseudo-online technique. Linear Discriminant Analysis is used to recognize the mental tasks, and the feature extraction uses the Power Spectral Density. The choice of EEG channel and frequency uses the Kullback-Leibler symmetric divergence and a reclassification model is proposed to stabilize the classifier. Finally, it is expected that the proposed method can be implemented in a Brain-Computer Interface associated with a robotic wheelchair.

This paper proposes a solution to a door crossing problem in unknown environments for an autonomous wheelchair. The problem is solved by a dynamic path planning algorithm implementation based on successive frontier points determination. An adaptive trajectory tracking control based on the dynamic model is implemented on the vehicle to direct the wheelchair motion along the path in a smooth movement. An EKF feature-based SLAM is also implemented on the vehicle which gives an estimate of the wheelchair pose inside the environment. The SLAM allows the map reconstruction of the environment for future safe navigation purposes. The entire system is evaluated in a real time simulator of a robotic wheelchair.

In this work a robot cooperation strategy based on omnidirectional vision is presented. Such strategy will be applied to a mobile robot team formed by small and simple robots and a bigger leader robot with more computational power. The leader must control team formation. It has an omnidirectional camera and sees the other robots. Color segmentation and Kalman filtering is used to obtain the pose of the followers. This information is then used by a nonlinear stable controller to manage team formation. Simulations and some preliminary experiments were run. The current results are interesting and encourage towards the next steps.

This work presents a strategy to control a mobile robot navigating along a corridor. The proposed control system is based on the fusion of the control signals generated by two redundant controllers. Redundancy here means that both controllers have the same objective, which is to keep the mobile robot in the middle of the corridor. The two control signals being fused are generated by a controller based on the optical flow technique and by a controller based on distance measures provided by ultrasonic sensors.

This work presents a new approach to calculate the optical flow, which uses the decentralized information filter to accomplish a data fusion step. The proposal consists in taking some least mean square estimates of the optical flow vector associated to a certain region of the image considered and to fuse them in order to get a more accurate final estimate of such a vector. Besides this, the way the initial least mean square estimates are obtained is also modified, by reducing the number of observations used to get each one of them, in order to make the overall algorithm faster. The idea is that such initial estimates can be rougher, once the fusion engine improves the accuracy of the final estimate, in the sense that the decentralized information filter generates a final estimate whose variance is lower than the smallest variance associated to the initial estimates.

This paper proposes an alternative approach to address the problem of coordinating behaviors in mobile robot navigation: fusion of control signals. Such approach is based on a set of two decentralized information filters, which accomplish the data fusion involved. Besides these two fusion engines, control architectures designed according to this approach also embed a set of different controllers that generate reference signals for the robot linear and angular speeds. Such signals are delivered to the two decentralized information filters, which estimate suitable overall reference signals for the robot linear and angular speeds, respectively. Thus, the background for designing such control architectures is provided by the nonlinear systems theory, which makes this approach different from any other yet proposed. This background also allows checking control architectures designed according to the proposed approach for stability. Such analysis is carried out in the paper, and shows that the robot always reaches its final destination, in spite of either obstacles along its path or the environment layout. As an example, a control architecture is designed to guide a mobile robot in an experiment, whose results allows checking the good performance of the control architecture and validating the design approach proposed as well.