Recognizing human movement intention in less controlled environment is the step needed to go beyond strict laboratory settings in order to improve intuitive and reliable human-robot interaction systems. By taking this into account, the present study evaluates the feasibility of decoding the intention to perform hand-arm gestures in self-paced tasks from electroencephalography (EEG) and electromyography (EMG) collected with wearable dry-electrode devices. An experimental protocol was designed to emulate three gestures in human-robot interaction: Neutral, Ask, and Take. The protocol was implemented in two laboratories using different EEG headsets, Ultracortex Mark IV and Muse 2, and a common EMG device, Mindrove armband. Signals were preprocessed and segmented around the start of movement to be classified with a Bidirectional Long Short-Term Memory network with a fully connected output layer (BiLSTM-FC). Although the typical waveform of intention, movement-related cortical potential (MRCP), could not be reliably identified, the results showed that the combination of EEG and EMG enables the discriminability of intention patterns, achieving a mean of 88.95% in accuracy, and a maximum of 95.98% using the Ultracortex Mark IV and the Mindrove armband. These findings demonstrate the robustness of multimodal data gathered with accessible wearable technology to develop hybrid brain-computer interfaces.
