A study on the mental models of consumers in humanoid robot design preferences using EEG and eye tracker

• Main Author: Tang, Lin Hei
• Other Authors: Chen Chun-Hsien
• Format: Final Year Project
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Mechanical engineering
• Online Access: http://hdl.handle.net/10356/78268
• Institution: Nanyang Technological University

Currently, many modern humanoid robots have little appeal due to their simple designs and bland appearances. To provide recommendations for designers and improve the designs of humanoid robots, a study of random humanoid robot designs on people’s perceptions towards them is conducted using Electroencephalography (EEG) data, visual tracking information and questionnaires. This can give us some insights on how people react to the aesthetic designs of different humanoid robot models. As a result, designers can deduct from the findings about the consumers’ taste and preferences and measure the appeal of certain traits in a humanoid robot design, such as the perceived smartness and friendliness of the robots. Another point of interest is the most prominent feature of the robot, which is determined to be the head and its facial features followed by the chest. Moreover, decisiveness of the participants is also investigated based on their cognitive levels against the time taken to make their selections, with findings of little evidence to establish a connection between the two variables. However, it is also discovered that more attention is paid to the robots that appear to be more appealing and vice versa. Lastly, it is affirmed that first impressions of the robots generally do not change over time based on how the participants think they feel from the metric ratings and how they actually feel from the EEG data, provided that there is no new and additional information obtained by them about the robots. Therefore, a good humanoid robot design will impress the consumers at first sight.