Andrés Úbeda

Wireless and Portable EOG-Based Interface for Assisting Disabled People

This paper describes a new portable and wireless interface based on electrooculography (EOG) aimed at people with severe motor disorders. This interface allows us detecting the movement of the eyes measuring the potential between the cornea and the retina. The interface uses five electrodes placed around the eyes of the user in order to register this potential. A processing algorithm of the EOG signals has been developed in order to detect the movement of the eyes. This interface has many advantages in comparison to commercial devices. It is a cheap and small sized device with USB compatibility. It does not need power supply from the network as it works with batteries and USB supply. Several experiments have been done to test the electronics of the interface. A first set of experiments has been performed to obtain the movement of the eyes of the user processing the signals provided by the interface. In addition, the interface has been used to control a real robot arm. The accuracy and time taken have been measured showing that the user is capable of controlling the robot using only his/her eyes with satisfactory results.

SVM-based Brain–Machine Interface for controlling a robot arm through four mental tasks

Abstract Human–Machine Interfaces can be very useful to improve the quality of life of physically impaired users. In this work, a non-invasive spontaneous Brain–Machine Interface (BMI) has been designed to control a robot arm through the mental activity of the users. This BMI uses the classification of four mental tasks in order to manage the movements of the robot. The high accuracy in the classification of these tasks (around 70%) allows a quick accomplishment of the experiment designed, even with the low signal-to-noise ratio of this kind of signals. The experiment consists of reaching four points in the workspace of an industrial robot in the established order. After a brief training, the volunteers are able to control the robot in a real time activity. The real time test shows that the system can be applied to do more complex activity such as pick and place tasks if a supplementary system is added. These interfaces are very adequate in the control of rehabilitation or assistance systems for people suffering from motor impairment.

Evaluating Classifiers to Detect Arm Movement Intention from EEG Signals

This paper presents a methodology to detect the intention to make a reaching movement with the arm in healthy subjects before the movement actually starts. This is done by measuring brain activity through electroencephalographic (EEG) signals that are registered by electrodes placed over the scalp. The preparation and performance of an arm movement generate a phenomenon called event-related desynchronization (ERD) in the mu and beta frequency bands. A novel methodology to characterize this cognitive process based on three sums of power spectral frequencies involved in ERD is presented. The main objective of this paper is to set the benchmark for classifiers and to choose the most convenient. The best results are obtained using an SVM classifier with around 72% accuracy. This classifier will be used in further research to generate the control commands to move a robotic exoskeleton that helps people suffering from motor disabilities to perform the movement. The final aim is that this brain-controlled robotic exoskeleton improves the current rehabilitation processes of disabled people.

Multimodal human-machine interface based on a brain-computer interface and an electrooculography interface

This paper describes a multimodal interface that combines a Brain-Computer Interface (BCI) with an electrooculography (EOG) interface. The non-invasive spontaneous BCI registers the electrical brain activity through surface electrodes. The EOG interface detects the eye movements through electrodes placed on the face around the eyes. Both kind of signals are registered together and processed to obtain the mental task that the user is thinking and the eye movement performed by the user. Both commands (mental task and eye movement) are combined in order to move a dot in a graphic user interface (GUI). Several experimental tests have been made where the users perform a trajectory to get closer to some targets. To perform the trajectory the user moves the dot in a plane with the EOG interface and using the BCI the dot changes its height.

Shared control architecture based on RFID to control a robot arm using a spontaneous brain–machine interface

Abstract This paper describes a shared control architecture combining a Brain–Machine Interface (BMI) with Radio-frequency Identification (RFID) technology to control a robot arm in pick and place operations. A non-invasive spontaneous BMI capable of distinguishing between three different mental tasks has been designed. Using the BMI, the user can control the robot in order to perform complex actions (e.g. pick and place operations). RFID tags have been placed in the experimental setup to give information about the position of the objects in the scene. With this information, the user is able to pick and place the objects with a robot arm by performing simple commands: move left, move right, pick or place, with the only help of the BMI. Four volunteers have successfully controlled the robot arm, and time and accuracy have been measured.

P300-Based Brain-Computer Interface for Internet Browsing

This paper describes the implementation of a Brain-Computer Interface (BCI) for controlling Internet browsing. The system uses electroencephalographic (EEG) signals to control the computer by evoked potentials through the P300 paradigm. This way, using visual stimulus, the user is able to control the Internet navigation via a virtual mouse and keyboard. The system has been developed under the BCI2000 platform. This paper also shows the experimental results obtained by different users.

Combining a Brain-Machine Interface and an Electrooculography Interface to perform pick and place tasks with a robotic arm

This paper presents a multimodal Human-Machine Interface system that combines an Electrooculography Interface and a Brain-Machine Interface. This multimodal interface has been used to control a robotic arm to perform pick and place tasks in a three dimensional environment. Five volunteers were asked to pick two boxes and place them in different positions. The results prove the feasibility of the system in the performance of pick and place tasks. By using the multimodal interface, all the volunteers (even naive users) were able to successfully move two objects within a satisfactory period of time with the help of the robotic arm. A multimodal HMI to perform pick and place tasks with a robotic arm is presented.The EOG interface is applied to control planar movements and to operate the gripper.The BMI is used to control the height of the gripper through two mental tasks.The system had been tested by five healthy subjects.The results prove the feasibility of the system in the performance of these tasks.

Classification method for BCIs based on the correlation of EEG maps

Abstract This paper describes a new method of classification for a Brain–Computer Interface (BCI) based on a normalized cross-correlation of EEG maps which represent the mental activity of the brain. An optimization protocol has been designed to choose the main parameters of the classifier in order to increase the accuracy on the classification. This protocol has been tested with the registers provided by IDIAP Research Institute for BCI Competition 2003. Three different mental tasks based on motor imagery are performed in these sessions. The data have been processed and tested with the classifier to obtain the optimal success rate and reliability. To that end, the optimization protocol has been applied to select the suitable parameters for the classification. The results are very satisfactory and prove that this kind of classification can be successfully introduced in a real time BCI.

Interface based on electrooculography for velocity control of a robot arm

This paper describes a technique based on electrooculography to control a robot arm. This technique detects the movement of the eyes, measuring the difference of potential between the cornea and the retina by placing electrodes around the ocular area. The processing algorithm developed to obtain the position of the eye at the blink of the user is explained. The output of the processing algorithm offers, apart from the direction, four different values zero to three to control the velocity of the robot arm according to how much the user is looking in one direction. This allows controlling two degrees of freedom of a robot arm with the eyes movement. The blink has been used to mark some targets in tests. In this paper, the experimental results obtained with a real robot arm are shown.

Online classification of two mental tasks using a SVM-based BCI system

A Brain-Computer Interface (BCI) can be very useful to help people with several movement disabilities to improve their independence or to assist them in rehabilitation tasks. In this paper, the results of the online classification of two mental tasks from electroencephalographic signals (EEG) are shown. The objective of this paper is to determine whether the accuracy in the online differentiation of two mental tasks could be enough to command a robot arm using two mental tasks. The results demonstrate that the features obtained using periodogram (a Power Spectral Density estimation) and the classification of these using a SVM-based (Support Vector Machine) system can be used in a reliable control of a robot arm. For all the users, the accuracy is around 87±2%. This accuracy is enough to be used to this end in real time.