Written by Antero Mäkinen
Could there be a
social robot, which fits for all humans? All-in-one robot? I don’t think so, or
at least it should have some transformer’s skills to adapt to every situation.
Human’s gender, age and senses matter very much when concerning how social
robot fits for every individual human. Some people don’t see, some people are
deaf, some are young, and some are old and so on. I watched a couple of videos
from YouTube to think about how user group matters when designing robots. A
video called “The next frontier in
robotics: social, collaborative robots | Andrea Thomaz | TEDxPeachtree” (https://www.youtube.com/watch?v=O1ZhWv84eWE)
explained it quite well with great examples.
In this video,
Roboticist Andrea Thomaz had her robot buddy with her and she showed couple of
examples with the robot. Even though the video is almost three years old, I
think it’s still valid. I was really surprised when her robot started to talk,
and it sounded like a little kid even though in my mind it didn’t look a kid,
more like a monkey, so maybe it should have sounded a bit monkey-ish.
So, the first thing I
would consider when thinking about designing a robot is that how it should
visually look and what kind of voice should it have to match the visuals. For
example, maybe for kids or elder people it wouldn’t be so weird if the robot
talked like a little kid, but for middle-aged people it probably wouldn’t be so
good choice if they wanted to take the robot seriously. Of course, there are
always exceptions and good thing is that robots can have multiple voices in the
same package.
Second thing that
needs to be considered when designing to different age groups are gestures.
Gestures are quite common in human-human interaction and in the video example,
the robot acted very inhuman when she did actions without showing her eye
and/or hand and body movement. This would definitely scare youngest and oldest
users who would interact with the robot, because it would act so differently
compared to humans and thus it wouldn’t be so easily approachable. In
industrial robots, which actually doesn’t even try to look like humans, these
things aren’t so important, but with social robots they truly are.
Last thing I would
like to point out is the need of human-kind of interaction. It includes
everything: visuals, gestures, sounds and even behavior. I think social robots
should show empathy for all target users, but especially for kids and elders or
those with special needs. First level of being empathic would be just to say
correct things at correct times, but I think we’re still quite far from
empathically skilled robots. Besides words, robots could also show emotions via
gestures, for example by showing their support to grief they could give hugs or
simply touch user’s shoulder, like we humans do.
To summarize, there
are quite many things that need to be considered when designing social robots.
Creating fits for all social robot that would have perfect visual, audio and
behavior experience to every user will be hard, but I’m looking forward what
the future brings on this area. Will social robots adapt perfectly to every
user and how would they adapt in a group situation with multiple humans and robots?
Nice blog! It was interesting to read it since we did our group assignment about social robots and as our concept we suggested a robot to help children with disabilities and that could adapt to whatever situation it is in. Of course, this kind of technology doesn't exist yet. On mental/social level, it can can be easier to make adaptions. But the physical appearance of a robot is much harder to change (like you said, it should be some kind of a transformer...) Not saying it impossible in the future, but much more investigation is needed from both psychological and techonogical viewpoints.
ReplyDeleteOn the adaptation angle, robots could take advantage of metamaterials, contruction and lights to physically transform to better match the target group. A simple change could be eyebrows of sorts that can retract and extend, allowing them to exaggerate them and if they angle can be changed to help with the expression the robot hold in general.
ReplyDeleteThough personally i feel that the best "face" for a robot is a black screen, thus avoiding the uncanny valley and allowing the robot to emote using emoticons and shapes. Thus instead of trying to recreate facial animations in plastic or something you instead allows for teardrops, suns and all kinds of different expressions.
Just my two cents.
Miikael
Good thoughts! There are some very big questions presented here and I think you've done well to consider so many aspects of a complex topic in one brief blog post. I enjoyed reading your personal opinions about the robot on the video. Thanks for sharing the fascinating TED talk along with your post. The speaker on the video, Andrea Thomaz, makes an important remark how we often think that robots are being designed by mad scientists in their labs, and how this is nothing but a myth. Designing and developing robots requires experts from various fields, including psychology, sociology and many others, to create robots that can make a true social impact.
ReplyDeleteNice question !
ReplyDeleteWell , designing a social robot is challenging as the designer needs to consider several aspects such as quality experience , emotion, speech recognition in noise environment, gesture , interactive robot with eye contact and still more. Through several research, scientists have succeeded in creating a social robot with the help of AI that has been achieving the experience goals that fulfills the requirements of the users.
The current social robots are able to make eye contact and respond to questions from the person who interacts .The proactive social robot Qtrobot has been designed specially for autism children interacts with the children and makes them active and ease learning. This has also showed effective in treatment. Here's a video of Qtrobot that would provide answer for our questions.
https://www.youtube.com/watch?time_continue=28&v=q-A2hKe_oJ4
With AI and trending technologies , We would be able to forsee the social robots being designed for multiple user groups in the near future with qualitative experience goals.
Thanks for your blog post.
The blog post was interesting to read with good thoughts. I agree with the statement that gesture is one of the major aspect for effective communication through emotions.
ReplyDeleteWith the help of AI, many companies have come up with social robots with gesture, emotion, interaction and several other psychological aspects which would benefit the user groups. From recent invention, QTrobot a prosocial robot, which can be programmed based on user needs and an interactive robot, specially designed for autism children which helps the children to be active and learn with attention has influenced fast recovery in the treatment process. Here is the video for reference: https://www.youtube.com/watch?time_continue=28&v=q-A2hKe_oJ4
This makes a footage in designing a future social robot possible for different user groups with prior qualitative analysis of user requirements along with psychological and social aspects.
Nice considerations! I also feel making a robot that could adapt to every situation might be a challenge, as thinking from human's perspective, are we, as humans always adapting to every situation either? Sometimes there may be situations where one person feels very comfortable in (e.g. giving a presentation to a crowd, or networking at an event), and another one might feel that those kinds of situations are nerve-wrecking. On the other hand, with the possibilities of AI advancing, perhaps robots could also sense emotions of the humans better and be able to adapt even better. Also the use of facial expressions might help humans to interpret the robot's behaviour better, but the uncanny valley (as mentioned in one comment above) needs to be considered. This is a very interesting topic, and I am enthusiastically waiting where the science leads us in this field!
ReplyDeleteI agree with you that in many parts the uncanny valley is a big problem with human-like robots, wheter it’s in the design of the face and expressions, the robot’s voice that is almost right, but not quite, or its actions missing the proper body language. Like you mentioned, with industrial robots it’s not a problem, since we don’t link their appearance to humans. Therefore I think that simplified designs work the best with robots at the moment, where it’s easy to not see them as weird versions of humans, but clearly as robots.
ReplyDeleteThere’s so much to human socialization like you said, the facial expressions, tone and intonation of the voice, body language, the actual words and if they should use some local slang or identify the relationship with the participant (frinedly, respectful, advisory …) or the tone of the conversation (casual, proper, excited …). There’s so many things a truly adaptive social robot would have to consider, I agree with that I’m not sure when it will be possible.
Very interesting writing! A lot of questions arose. But I like the questions most, “How well it will adopt when taking part in a group conversation with different people from each other”. Well I think with the use of big data automation most of the problems can be solved by creating different persona for the robot while communicating with different people. But! Do we really need different personality for communication with different personalities? When I think about myself communicating with others, I don’t behave that differently for different audiences. As extraversion is more popular among most of the people, can we define a common personality that is acceptable for everyone? Or is it a really bad idea?
ReplyDeleteThanks for an insightful blog post.
ReplyDeleteRobots and AI have always fascinated me. When I think of the blog subject, I often land in a philosophic state reasoning where the core of robots and their artificial intelligence could exist or what could it made of. The endgame of my contemplation concludes in self-awareness been the answer to my question. I think social robots can be created to function in certain situations and perhaps, with more advanced algorithms, be able to contain, analyze and adapt to the contextual situation presented. As a result, this could be a good condition of function for robots in their interaction with humans, and why not even among robots.
We humans are complex beings with probably thousands or even millions behavioral entities ready to be activated at every situation, whether complex or not. In this aspect, I believe our behavior can be encapsulated, retained and processed and even transferred to a robot to match human behavior and establish a profound interaction with humans.
I believe we still have a long way to go. Nevertheless, the development in AI and robotics is reaching new horizons and pushing the boundaries of self-learning mechanisms in robots, systems or applications. Elon, one of the greatest technology pioneers of our time has warned us about artificial intelligence. In addition to this warning, I think Elon is onto something. Nonetheless, I really liked the design process of construction, the how to and what to think, as a theoretical attempt to build one.
Very interesting topic! Non-verbal communication is truly an important aspect in human-human as well as in human-robot interaction. Someone who doesn't make any facial expressions or gestures is kind of odd to communicate with. Increasing the feeling of empathetic robot could lead to better user experience.
ReplyDeleteIf it's not possible to make one robot meet every user's needs, I think the next best option is to make very specific robots. One to take care of the elderly, one to guide a shopper in a mall. If there are many user groups present, a common design principle has to be found.
Anyhow, making robots too humane is not a good direction either, as they might fall into the uncanny valley. The important part is to match the robot's appearance and behaviour.
I started wondering, if we try to design a robot that would feel like a real person, then maybe we shouldn't even try to create just one robot that can fit to all users, but instead we would create different personalities for robots. Humans are all different, so why should robots try to cater for everyone?
ReplyDeleteIf there would be commercial robot friends available in the future, I could see them having different kinds of personalities available in the software. I think having a distinct and coherent personality even when talking to different people would make it feel more like any human who also has their own personality.
Companies could then gain an edge for their business by creating different kinds of personality software for robots, instead of trying to create a robot that pleases everyone. So people could choose the preferred personality for their robot.
This is only considering the personality preferences of people, and it is true that people with special needs might also need different kinds of functionalities, so just one kind of physical robot body wouldn't be enough to satisfy all user groups. But I would argue that also a special robot for blind people for example, could have different kinds of personalities available.
-Jaana Tikkanen
Designing a social robot that could adapt to every sitution is an interesting topic, but i think the answer is quite simple.
ReplyDeleteIf we can design an social robot that fits into one situation, we can also design it to fit to another. After that it is only a matter of combaning these designs. For example if the robot is designed for assiting autistic children and another is set for helping elderly, it is only a matter of parameters the robot is eating. So, in the end we probably will have social robots that can fit everyone. On the physical aspect matter, I dont really think it causes a serious problem that would block the robot from working somewhere. Probably the robot would have some means to change its physical appearance.