Papers by Kevin A. Hernandez-Ossa
XXVI Brazilian Congress on Biomedical Engineering, 2019
Previous works in literature have indicated that pedaling movements are safe, effective and acces... more Previous works in literature have indicated that pedaling movements are safe, effective and accessible to patients with a wide range of motor impairments. Recent research in the field of rehabilitation has shown that patients with stroke and cerebral palsy may improve their motor and balance abilities after an early short duration of pedaling training. In this work, a novel low-cost Motor Exercise Static Bike (MESB) has been enhanced by incorporating a Raspberry Pi 3B. The enhanced MESB includes custom-made hardware and software for allowing a user to command it, in addition, to monitor its operation through a Graphical User Interface (GUI). The GUI was programmed in Python 3.5 and was tested on Ubuntu 16.04 and Raspbian (rel. 2017-09-08) operating system. An Inertial Movement Unit (IMU) was selected in order to acquire both bike’s angular velocity and position data. The angular velocity was measured in degrees per second (DPS) directly from the IMU’s gyroscope z-axis, and the angular position was calculated by integrating the angular velocity over time.
XXVI Brazilian Congress on Biomedical Engineering, 2019
For some people with severe physical impairments, the main assistive device to improve their inde... more For some people with severe physical impairments, the main assistive device to improve their independence in activities of daily living and to enhance overall well-being is an electric powered wheelchair (EPW). However, a large number of wheelchair users find nearly impossible to drive with conventional EPW interfaces, so there is a necessity to offer users EPW training. In this work the SimCadRoM is presented. It is a virtual reality simulator for EPW safe driving learning purposes, testing of driving skills and performance, and testing of input interfaces. At this research stage, some tests were conducted to validate this version of the SimCadRoM as a reliable simulator capable of providing a training experience close to reality. The SimCadRoM was, in general, well accepted by the volunteers and proved to be a system that simulates, very realistically, the usability, kinematics, and dynamics of an EPW in a virtual environment (VE) using a standard EPW’s joystick as input interface. The level of sense of presence in the VE generated by the simulator revealed a great potential for training and transferring skills to a real environment (RE).
This work presents an intuitive and customizable assistive technology based on eye gaze, which is... more This work presents an intuitive and customizable assistive technology based on eye gaze, which is an integration of a previous multimodal assistive domotics system developed for the UFES robotic wheelchair. Users with motor disabilities are able to control home devices, communicate with family or caregiver through short phrases, and navigate a wheelchair by means of eye gaze. The interface is easy to use, in which there is a computer and a screen monitor on board the wheelchair, displaying some options for the user to select. This selection is made using an eye tracker. Experimental results with volunteers showed good performance in terms of the system usability. The main goal of this system is to improve life quality for users, providing augmented and alternative communication, mobility assistance and enhancement on activities of daily living.
2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2017
Upper limb disorders may impair the use of control interfaces for Electric Powered Wheelchairs (E... more 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.
Sensors
For some people with severe physical disabilities, the main assistive device to improve their ind... more For some people with severe physical disabilities, the main assistive device to improve their independence and to enhance overall well-being is an electric-powered wheelchair (EPW). However, there is a necessity to offer users EPW training. In this work, the Simcadrom is introduced, which is a virtual reality simulator for EPW driving learning purposes, testing of driving skills and performance, and testing of input interfaces. This simulator uses a joystick as the main input interface, and a virtual reality head-mounted display. However, it can also be used with an eye-tracker device as an alternative input interface and a projector to display the virtual environment (VE). Sense of presence, and user experience questionnaires were implemented to evaluate this version of the Simcadrom in addition to some statistical tests for performance parameters like: total elapsed time, path following error, and total number of commands. A test protocol was proposed and, considering the overall ...
Procedia Computer Science, 2019
Intelligent service robots are needed in office-like
environments to perform common tasks of pick... more Intelligent service robots are needed in office-like
environments to perform common tasks of picking up, and
delivering things such as mail, goods, trash recycled paper, etc.
These tasks are challenging since robots must avoid static and
dynamic obstacles, and mainly robots have to perform path
planning considering multiple goals as saving energy. This work
proposes an autonomous multi-goal path planning system for
picking up or delivering tasks in mobile robotics. The multi-goal
path planning method is based on the Lin-Kernighan Heuristics
(LKH) algorithm [1], which was modified in order to implement
an autonomous system for picking up/delivering tasks using non-
Euclidean distances, Hamiltonian paths, and a Pioneer 3DX
mobile robot. This work proposes a client – robot system ARMM
[2] where many clients request pickup / delivery services, then
the robot continuously plan a Hamiltonian path to visit each one
of the requested pickup / delivery goals, and return to its base
station. To validate the results of this work two well-known
metrics were performed [3]: distance traveled and time elapsed.
A comparison between the nearest goal, random selection, the
LKH with Euclidean distances, and the LKH with non-Euclidean
distances algorithms were performed.
Conference Presentations by Kevin A. Hernandez-Ossa
XIII Simpósio Brasileiro de Automação Inteligente (SBAI 2017) , 2017
XIII Simpósio Brasileiro de Automação Inteligente (SBAI 2017) , 2017
The present work evaluates a PD-like and impedance controller proposed for application on a teleo... more The present work evaluates a PD-like and impedance controller proposed for application on a teleoperated wheelchair with visual feedback from a camera. This evaluation contemplates the influence of data and image transmission delay on the system. The force feedback imposed by the controller was applied to a robot, emulating the wheelchair, and to a joystick, which is related to the difference between master and slave, and the presence of possible obstacles in the path. There were analyzed the time to complete the proposed task, robot synchronization error, and spatial error referring to the trajectory on the specified pathway. In addition, EEG signals were collected in order to measure a level of user's attention during the task execution, which was correlated with the NASA-TLX questionnaire score answered after the protocol was completed. There were noted a satisfactory behavior of the controller and correct execution of the task by the user, and that the attention level increases with the presence of time delay. Resumo O presente trabalho avalia o controlador PD-Like e de impedância propostos para a aplicação em uma cadeira de rodas teleoperada com realimentação visual proveniente de uma câmera. Esta avaliação aborda a influência do atraso de tempo de trans-missão de dados e imagem no sistema. A realimentação de força imposta pelo controlador foi aplicada a um robô, emulando uma cadeira de rodas, e ao joystick, relacionado à diferença entre mestre e escravo, e à presença de possíveis obstáculos no caminho. Foram analisados o tempo para completar as tarefas propostas, o erro de sincronismo do robô e o erro espacial referente à trajetória percorrida e o caminho especificado. Além disso, foram coletados sinais de EEG a fim de mensurar o nível de atenção do usuário durante a execução da tarefa, o qual foi correlacionado com o questionário NASA-TLX preenchido logo após conclusão do proto-colo. Foi observado um satisfatório comportamento do controlador e execução da tarefa pelo usuário, e que o nível de atenção aumenta com a presença de retardo de tempo.
Upper limb disorders may impair the use of control interfaces for Electric Powered Wheelchairs (E... more 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.
V Congresso Brasileiro de Eletromiografia e Cinesiologia e o X Simpósio de Engenharia Biomédica (COBEC-SEB 2017), 2017
This work presents an intuitive and customizable assistive technology based on eye gaze, which is... more This work presents an intuitive and customizable assistive technology based on eye gaze, which is an integration of a previous multimodal assistive domotics system developed to the UFES robotic wheelchair. Users with motor disabilities are able to control home devices, communicate with family or caregiver through short phrases, and navigate a wheelchair by means of eye gaze. The interface is easy to use, in which there is a computer and a screen monitor on board the wheelchair, displaying some options for the user to select. This selection is made using an eye tracker. Experimental results with volunteers showed good performance in terms of the system usability. The main goal of this system is to improve life quality for users, providing augmented and alternative communication, mobility assistance and enhancement on activities of daily living.
Uploads
Papers by Kevin A. Hernandez-Ossa
environments to perform common tasks of picking up, and
delivering things such as mail, goods, trash recycled paper, etc.
These tasks are challenging since robots must avoid static and
dynamic obstacles, and mainly robots have to perform path
planning considering multiple goals as saving energy. This work
proposes an autonomous multi-goal path planning system for
picking up or delivering tasks in mobile robotics. The multi-goal
path planning method is based on the Lin-Kernighan Heuristics
(LKH) algorithm [1], which was modified in order to implement
an autonomous system for picking up/delivering tasks using non-
Euclidean distances, Hamiltonian paths, and a Pioneer 3DX
mobile robot. This work proposes a client – robot system ARMM
[2] where many clients request pickup / delivery services, then
the robot continuously plan a Hamiltonian path to visit each one
of the requested pickup / delivery goals, and return to its base
station. To validate the results of this work two well-known
metrics were performed [3]: distance traveled and time elapsed.
A comparison between the nearest goal, random selection, the
LKH with Euclidean distances, and the LKH with non-Euclidean
distances algorithms were performed.
Conference Presentations by Kevin A. Hernandez-Ossa
environments to perform common tasks of picking up, and
delivering things such as mail, goods, trash recycled paper, etc.
These tasks are challenging since robots must avoid static and
dynamic obstacles, and mainly robots have to perform path
planning considering multiple goals as saving energy. This work
proposes an autonomous multi-goal path planning system for
picking up or delivering tasks in mobile robotics. The multi-goal
path planning method is based on the Lin-Kernighan Heuristics
(LKH) algorithm [1], which was modified in order to implement
an autonomous system for picking up/delivering tasks using non-
Euclidean distances, Hamiltonian paths, and a Pioneer 3DX
mobile robot. This work proposes a client – robot system ARMM
[2] where many clients request pickup / delivery services, then
the robot continuously plan a Hamiltonian path to visit each one
of the requested pickup / delivery goals, and return to its base
station. To validate the results of this work two well-known
metrics were performed [3]: distance traveled and time elapsed.
A comparison between the nearest goal, random selection, the
LKH with Euclidean distances, and the LKH with non-Euclidean
distances algorithms were performed.