Human-agent interaction
1
2
3
Human cognition is the result of interaction between several complex cognitive processes with limited capabilities. Intention recognition of user is key to effective human-agentinteraction. In augmented cognition, recognition of user's intention helps in active and relevant support. I focused on three following applications of intention and attention recognition.
Memory and decision making support tool based on the recognition of information seeking intention
We developed a glass type augmented cognition system. It attempted to actively assist human memory functions by providing relevant, necessary and intended information by constantly assessing intention of the user.
-
To provide memory support selective attention and intention processes were measured.
-
The performance of the system was tested in a person identity scenario.
-
To detect the intended face, the system analysed the gaze points and change in pupil size to determine the intention of the user.
-
An assessment of the gaze points and change in pupil size together indicates that the user intends to know the identity and information about the person in question.
-
The system retrieved several clues through speech recognition system and retrieved relevant information about the face.
Figure 1. Overall architecture of the memory and decision making support tool
Human-robot interaction by inferring user intention from gestures and affordance model
Recognition of human intention is an important issue in human-robot interaction research and allows a robot to respond adequately according to human’s wish. We proposed a model to show how robots can infer human intention by learning affordance concept.
-
Affordance concept represents the relation between an agent and its environment.
-
Learning of the robot, to understand human and its interaction with environment, was achieved within the framework of action- perception cycle.
-
The action-perception cycle explains how an intelligent agent learns and enhances its ability continuously by interacting with its surrounding.
-
The proposed intention recognition and recommendation system included several key functions such as joint attention, object recognition, affordance model, motion understanding module and so on.
Attention and concentration monitoring system using low cost EEG for online learning
Concentration is an important part of our life especially during learning or thinking. Visually or auditory evoked concentration influences information processing in human brain. To understand the concentration process of humans, the underlying neural mechanism needs to be explored.
-
We proposed an accurate concentration monitoring method using a low cost EEG device.
-
Our low cost EEG device had two channel electrodes (FP1, FP2).
-
We investigated effective filters for removing noises from raw data and suitable features for monitoring the concentration status in real time.
-
The data came from participants for rest state with open eyes and concentration task state.
-
For concentration task, Sudoku game was used.
-
Using support vector machine, we successfully distinguished between rest state and concentration state over 88% accuracy in real time.
Figure 2. Overall architecture of concentration monitoring system
Related Publications
