Using Brain–computer Interfaces to Detect Human Satisfaction in Human–robot Interaction

Abstract

This article discusses the use of a brain-computer interface (BCI) to obtain emotional feedback from a human in response to the motion of humanoid robots in collaborative environments. The purpose of this study is to detect the human satisfaction level and use it as a feedback for correcting and improving the behavior of the robot to maximize human satisfaction. This article describes experiments and algorithms that use human brains activity collected through BCI in order to estimate the level of satisfaction. Users wear an electroencephalogram (EEG) headset and control the movement of the robot by mental imagination. The robots responds to the mental imagination may not be the same as human mental command and this will affect the emotional satisfaction level. The headset records brain activity from 14 locations on the scalp. Power spectral density of each EEG frequency band and four largest Lyapunov exponents of each EEG signal form the feature vector. The Mann-Whitney-Wilcoxon test is then used to rank all the features. The highest rank features are then selected to train a linear discriminant classifier (LDC) to determine the satisfaction level. Our experimental results show an accuracy of 79.2% in detecting the human satisfaction level.

Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review

“…A Brain Computer Interface (BCI) is a system that takes a biosignal, measured from a person, and predicts (in real-time) certain aspects of the person's cognitive state [1,2]. At the outset, BCIs started as assistive technological solutions for individuals with significant speech anomalies.…”

Affective, Natural Interaction Using EEG: Sensors, Application and Future Directions

“…Emotiv provides as direct output frustration and excitement in [11], long-term excitement, instantaneous excitement and engagement in [4,13] and excitement, engagement, boredom, meditation and frustration in [5] through its simple interface. In some cases information from the Emotiv sensor about the raw EEG and wave variations are combined with the information provided by other biological or non biological sensors, resulting in different types of emotion representation: anger, disgust, fear, happiness, sadness, joy, despisal, stress, concentration and excitement in [8], positive, negative and neutral state of mind in [3,20]. In cases where the cognitive load of the subject is being studied during a task [7], changes in power of lower frequency (alpha, theta) brain waves detected by Emotiv are analysed in order to determine whether the cognitive load is low, medium or high.…”

“…Sometimes annotation is provided by the experiment itself. An example of that is [3] where positive, negative and neutral state of mind are measured. During this experiment the participants are asked to control a robot in a maze by thinking about the direction it must take (in reality they can't).…”

“…Visual stimuli can include displaying pleasant, neutral and unpleasant pictures from the International Affective Picture System [20], visuals in game-playing [13] or a robot's movement [3]. If the P300 signal is to be detected, examples of stimuli can be found in [21] where the subject is looking at a monitor where a ship appears intermittently or in [1] where the photo of each person in a mobile phone's addressbook flashes and when the photo of the person we want to call flashes the signal is detected.…”

“…The main fields in which the wireless EEG sensors find application are games (subsection 5.1), learning (subsection 5.2) and health (subsection 5.3). They are also used in mobile phones [1,20], Human-Robot Interaction (HRI) [3] and interactive information seeking [7].…”