Online control of a humanoid robot through hand movement imagination using CSP and ECoG based features.

Intention recognition through decoding brain activity could lead to a powerful and independent Brain-Computer-Interface (BCI) allowing for intuitive control of devices like robots. A common strategy for realizing such a system is the motor imagery (MI) BCI using electroencephalography (EEG). Changing to invasive recordings like electrocorticography (ECoG) allows extracting very robust features and easy introduction of an idle state, which might simplify the mental task and allow the subject to focus on the environment. Especially for multi-channel recordings like ECoG, common spatial patterns (CSP) provide a powerful tool for feature optimization and dimensionality reduction. This work focuses on an invasive and independent MI BCI that allows triggering from an idle state, and therefore facilitates tele-operation of a humanoid robot. The task was to lift a can with the robot's hand. One subject participated and reached 95.4 % mean online accuracy after six runs of 40 trials. To our knowledge, this is the first online experiment with a MI BCI using CSPs from ECoG signals.

Single trial detection of hand poses in human ECoG using CSP based feature extraction.

Decoding brain activity of corresponding highlevel tasks may lead to an independent and intuitively controlled Brain-Computer Interface (BCI). Most of today's BCI research focuses on analyzing the electroencephalogram (EEG) which provides only limited spatial and temporal resolution. Derived electrocorticographic (ECoG) signals allow the investigation of spatially highly focused task-related activation within the high-gamma frequency band, making the discrimination of individual finger movements or complex grasping tasks possible. Common spatial patterns (CSP) are commonly used for BCI systems and provide a powerful tool for feature optimization and dimensionality reduction. This work focused on the discrimination of (i) three complex hand movements, as well as (ii) hand movement and idle state. Two subjects S1 and S2 performed single `open', `peace' and `fist' hand poses in multiple trials. Signals in the high-gamma frequency range between 100 and 500 Hz were spatially filtered based on a CSP algorithm for (i) and (ii). Additionally, a manual feature selection approach was tested for (i). A multi-class linear discriminant analysis (LDA) showed for (i) an error rate of 13.89 % / 7.22 % and 18.42 % / 1.17 % for S1 and S2 using manually / CSP selected features, where for (ii) a two class LDA lead to a classification error of 13.39 % and 2.33 % for S1 and S2, respectively.

A BCI using VEP for continuous control of a mobile robot.

A brain-computer interface (BCI) translates brain activity into commands to control devices or software. Common approaches are based on visual evoked potentials (VEP), extracted from the electroencephalogram (EEG) during visual stimulation. High information transfer rates (ITR) can be achieved using (i) steady-state VEP (SSVEP) or (ii) code-modulated VEP (c-VEP). This study investigates how applicable such systems are for continuous control of robotic devices and which method performs best. Eleven healthy subjects steered a robot along a track using four BCI controls on a computer screen in combination with feedback video of the movement. The average time to complete the tasks was (i) 573.43 s and (ii) 222.57 s. In a second non-continuous trial-based validation run the maximum achievable online classification accuracy over all subjects was (i) 91.36 % and (ii) 98.18 %. This results show that the c-VEP fits the needs of a continuous system better than the SSVEP implementation.

Performance of a tactile P300 speller for healthy people and severely disabled patients.

P300 based Brain-Computer Interfaces (BCIs) for communication are well known since many years. Most of them use visual stimuli to elicit evoked potentials because it is easy to integrate a high number of different classes into the paradigm. Nevertheless, a BCI that depends on visual stimuli is sometimes not feasible due to the presence of visual impairment in patients with severe brain injuries. In this case, it could be possible to use auditory or somatosensory stimulation. In this publication a vibrotactile P300 based BCI is introduced. Two different approaches were tested: a first approach using two stimulators and a second one that utilizes three stimulators for emitting the stimuli. The two paradigms were tested on 16 users: A group of ten healthy users and a second group comprising of 6 patients suffering Locked-In Syndrome. The control accuracy was calculated for both groups and both approaches, proving the feasibility of the device, not only for healthy people but also in severely disabled patients. In a second step we evaluated the influence of the number of stimuli on the accuracy. It was shown that in many cases the maximum accuracy was already reached with a small number of stimuli, this could be used in future tests to speed up the Information transfer rate.