I have finished up the Intel Opportunity Scholars research program (this is my third and final year in it). Our poster this year turned out awesome!
I am really excited for the competition and, more importantly, to see everybody else’s work. Bring it on!
Well, I finally made some last-minute changes to our poster… it looks like everybody got an extension on that. After a great year of research, we won SECOND PLACE in the competition! =) It was really exciting!! I am looking forward to another year of fun & exciting research coming up! =)
This is how the final poster turned out. I wrote all of the text, and Brittany was supposed to do all of the pictures. She came up with the outcome matrix, and together, the three of us came up with the rest of the pictures. I have attached a file of the final poster. I will be presenting it on Friday, while Brittany will present it Wednesday (I cannot make the Wednesday workshop because of class). I am *SO* excited and cannot wait for the poster competition!!! =)
We have collected all of the surveys and analyzed the results. For a pilot study, the results were pretty good. There are a few relationship types that must be fixed up and a few questions in the survey that should be either rephrased or discarded.
We have also started working and finalizing everything for our poster presentation. Brittany & I have decided to split the work: She will work on the figures, and I will work on all of the text. I just finished all of the text today, and she should have the figures done by Tuesday. The final poster should be set by Tuesday night. I will soon upload it onto here. I am very much excited and looking forward to the poster competition and seeing everybody else’s research!! =)
We have finally handed out our surveys! We are currently waiting on feedback and data, so we can compile our results and draw our conclusions! We should have a random sample of 40 completed surveys! =)
This week, we discussed the different questions. By next week, we will have a finalized set of questions, and we will receive all of the different questions (with different relationship types on each packet of questions), and we will have one week to collect the data we need. By the time we get back from Spring break, the survey information will be complete and the data will be analyzed. We should be putting our final results together… this is so exciting! =)
For the past two weeks, we have been trying to come up with situations that will be suitable for each type of social relationship type. After two weeks, we have come up with 16 different situations, and there are 10 different relationship types. Last week, we finished coming up with rough drafts of the questions for the survey. This week and next week, we will be reviewing & editing the questions to make sure that they are phrased properly. After that, we will be distributing the surveys to a random population (within our university). After that, we will gather the results and analyze the data. We will draw our conclusions and tie up everything together. That seems to pretty much take us to the end of this academic year of research. Next year, we will try to make our pilot study into a full-blown study with a bigger population sample, along with a more random sample as well. In the meantime, though, here are the different personas that are going to be tested:
- altruist
- ascetic
- competitor
- cooperator
- egoist
- fair
- malevolent
- risk-averse
- risk-seeking
- vengeful
In another week, we should have a final set of surveys ready to hand out to people. So exciting! =)
This past Tuesday, we finally met again! With finals, winter break, and now the new semester starting, we, finally, found some time to all meet and go over a general schedule for this semester. In January, we’ll try to finish designing the experiment and hopefully be able to come up with social-situation questions (i.e. Prisoner’s Dilemma, Investor-Trustee Dilemma, etc.) and word them properly. In February, we can administer these questions (they will probably be in the form of a survey), and then in March, start to analyze the results and wrap up research for this year. This year’s study will probably be more like a pilot study. But, for the fall and next year, we are going to see if we can generalize the research a lot bigger and grow on this research. So, this weekend, we should be looking at some possible questions and discussing them until Tuesday.
This week, we finished discussing the last of the background reading and started talking about our initial experimental design.
The last reading was “a survey of socially interactive robots.” Basically, it was an overview of the history of social robots and the research that has been done in that field so far. It also discussed the different problems or research that could be done in the near future, as well as some long-term research. The reading first starts by talking about “human social characteristics.” These include the following.
If robots can be socially interactive, then they can be used for many different fields, including research platforms, toys, educations tool, therapeutic aids, search-and-rescue, etc. Building social robots also comes one step closer to figuring out how to build empathy and true understanding into robots.
The best approach to making robots socially interactive is to use “functional design.” Functional design works on the theory that a robot can be designed so that it appears to be socially intelligent, but its internal design does not actually have basis in science or nature. Robots using functional design would be very useful if they were short-term interaction robots, have limited embodiment, or limited social expression. Many video games and electronic toys use functional design.
Once the robot is designed, it is also important to study emotion. There are three basic theories of emotion. The first theory tries to repesent emotions in discrete categories (such as happiness). The second theory characterizes emotions based on continuous scales or basis dimensions (such as arousal or valence). The third theory, also know as a componential theory, is a combination of the first two theories. The reading also discuesses artifical emotions and their implications on human-robot interactions.
Another big part of socially interactive robots is dialogue. There are many different types of dialogues that need to be studies: low-leve, non-verbal, natural language, etc. After studying all of these different aspects, they need to all be tied together in order to build a proper socially-interactive robot.
So, in order to study these social relationships further, we decided to use actor script evaluations. We will be doing this using different “games”, or placing people in different situations and seeing what they would do. Some possibilities for these games include The Ultimatum game, The Equitable Division Game, The Minority Game, Insider’s Knowledge Game, The Chicken Game, and last but not least, The Investor-Trustee Game. There will be more on our experimental design and the specifics of each of these games in the weeks to come.
As the title implies, this week, we discussed the interdependence, interaction, and relationships in robotics. This was also the third background-reading paper that we had. We talked about the theory of the mind, which helps a robot reason the state of its partner.
We discussed that behavior is shaped by three different things: propoerties of a person, features of the situation, and social environment. Interaction is also defined in a similar way; it is conceptualized in terms of need, thoughts, and motives in relation to one another, when dealing with two or more people. When trying to represent interactions, it is best to use outcome matrices and transition lists. That way, we can consider all future implications of any current decisions that a robot must make. One type of interaction is called cyclic interaction. There are two primary features of cyclic interaction: time is important and the fact that you are in the current state becuase of something that happened before. All of this interaction and decision making leads to dealing with interdependence space.
Interdependence space consists of three main parts: control, correspondence, and interdependence. All of these are nicely related in a diagram, for any given situation. While trying to figure out different courses of actions, people also create diagnostic situations. A diagnostic situation is one in which the person that is in the situation (un)consciously puts themselves in that situation in order to figure out the other persons’ character. This is one step closer to figuring out how to program trust into robots and helping robots figure out characters of the human beings they will be working with. Diagnostic situations are also used to figure out what situation is best and selection of situations.
On the other hand, relationship-specific motives are often very helpful in guiding robot behaviors. Relationship-specific motiations are inclinations that help robots respond to particular situations in a specific manner with a specific partner.
That was the basic discussion and summary of the paper that we read. We are also reading another paper, “A survey of socially interaction robots”, for two weeks from now. It is a review of “socially interactive robots”, where human-robot interaction is very important. There will be more to discuss about this next time.
 |