Development of a brain-controlled feeding robot

Abstract

Feeding difficulty and malnutrition are common phenomena in disabled people. Feeding is often time consuming, unpleasant, and may result in asphyxiation. In many cases, robotic aids are applied to assist disabled people in eating. In particular, for people with severe disabilities including sensory losses and difficulty in basic physical mobility, assistive robots that require any movement from users cannot be applicable. A robotic system which can be controlled merely by thoughts and brain signals would be quite a remarkable aid for them. Brain Machine Interface (BMI) is a direct communication pathway between brain and an external electronic device. BMIs aim to translate brain activities into control commands. To design a system that translates brain waves to desired commands, motor imagery tasks classification is the core part of this work. Classification accuracy not only depends on how capable the classifier is but also on the input data. Feature extraction highlights the properties of signal that make it distinct from the signals of the other mental tasks. Performance of BMIs directly depends on the effectiveness of the feature extraction and classification algorithms. If a feature provides large interclass difference for different classes, the applied classifier exhibits a better performance. In this work, the application of time domain features for time-series Electroencephalogram (EEG) signal is discussed. Time domain features have low computational complexity; thus, they can be considered as a suitable option for real-time BMI systems. This study includes a comprehensive assessment of time domain features in which their effectiveness has been evaluated with two classifiers, namely Support Vector Machine (SVM) and Fuzzy C-means (FCM). Experimental verifications of the selected combination of feature and classifier have been done. Based on the requirements for real-time performance, a prototype of an EEG-based feeding robot has been developed. Experimental results show that the developed BMI was able to perform the required tasks in real-time, with tolerable errors of around 17% in average, which can be further supervised to be reduced or eliminated. For further research, combining some of the effective features and applying fusion classifiers are suggested to improve the performance of the BMI system.