I'm trying to build an affective lego robot for my study of human-robot collaboration. Could you suggest me what to read about expressing basic affect in robots (especially with a help of eyebrows and upper body)? And I'd be very grateful if you could answer this short survey so I could get some data about the current emotional expressions of my robot: http://kwiksurveys.com/s.asp?sid=x58ni0wxzxid65t122704 .
I did the survey you have mentioned. It was not easy to identify mood in some cases. But you have opened a very interesting topic for me (and many others). Somehow we now tend to mix face expressions with emoticons. We are corrupted by technology. Happiness now is an emoticon with : and ) combined. It may be useful to incorporate younger kids in this study who are good at judging face expressions and are so much corrupted by technology. KISMET robot at MIT was developed with various face expressions (and a lot of publications are available on it). But I love your idea of using LEGO for similar purposes – very low cost and infinite applications. I’ll be teaching an introduction to robotics course at Johns Hopkins this summer where LEGO kits will also be used. I’d like to explore this idea there, with your permission.
Muhammad Ali Yousuf, thanx for your comment. I like your idea of surveying younger children. And yes, you are welcome to use it in your course. However, I should mention that the design of the specific robot, used in this survey, was inspired by the Phobot robot (H.Cramer et al.).
Kismet is a great robotic face with much more possibilities to display different facial expression with its 15 dof. I'm trying to understand what is possible to do with only one motor (as 2 other are used for wheels, and standard Lego has only 3 in total), and what could be the basic expressions that could be recognized clearly enough using just two characteristics of robot's upper body position and eyebrows.
I agree with Muhammad's suggestion: KISMET. In addition you should check the results from WE-4RII robot (head and torso expression). However the main problems are the technological constraints: only 3 motors! But still the main question is "what is possible to express with only 1 DOF?" I suggest first to read the results of Expression Measurement FACS (FACS=Facial Action Coding System) from Ekman y Friesen (1978). Then, you will decide what to express.
This reference (FACS) seems very useful to me. I'll check it in more detail. Thanks for sharing.
- Badges
- Science topic
- Similar topics
- Correction