Sunday, April 09, 2006

Conversational Humanoid

Humanoids are one of the fast developing areas in the robotics. Many research institutes and companies are doing researches in areas such as human-robot interactions, biomimetics and so on. Companies such as Honda, Sony together with leading institutions in Japan and US developed many interesting humanoid technologies. One such example is the conversational humanoid from MIT Media Lab. They are developing autonomous agents that are capable of having a real-time face-to-face conversation with a human. These agents are human in form and communicate using both verbal and non-verbal modalities. We believe that such agents provide a new form of human-computer interface which users can interact with naturally, without training, since they already know how to engage in face-to-face conversation with other people. In addition to providing a platform for evaluating theories of human communicative behavior, these agents can be used in applications from virtual salespeople and support personnel to virtual playmates for children. Their first generation humanoid system was Animated Conversation, where two autonomous humanoid animated characters carried on a conversation. While there was no human participant in these dialogues, Animated Conversation was the first system to automatically generate verbal and non-verbal communicative behaviors such as hand gestures, facial displays, intonation and speech. The second generation humanoid was Gandalf, an animated cartoon face on a screen that could answer spoken questions about the solar system. Gandalf could sense the user's motion by having the user wear an electro-magnetic tracking system, and thus could respond to non-verbal behavior as well as verbal behavior. Although Gandalf operated in real-time, his outputs were simply selected from a library of stock responses. The next generation has a fully articulated body and senses the user passively through cameras. The agent, named Rea (for Real Estate Agent), plays the role of a real estate salesperson who interacts with users to determine their needs, shows them around virtual properties, and attempts to sell them a house. We selected real estate sales as our application area, since there are opportunities for both task-oriented and socially-oriented conversation. As opposed to Gandalf, Rea actually synthesizes her responses--including speech and accompanying hand gestures--based on a grammar and lexicon and communicative context. Their challenges comprise creating a synthetic human is a large undertaking that introduces a wide range of hard research issues. Current research directions we are pursuing include the recognition of classes of user conversational hand gestures, the synthesis of Rea's hand gestures based on a more detailed understanding of pragmatic information, and the planning of mixed-initiative dialog including non-task-oriented 'small talk' and conversational storytelling. The research version of Rea runs on a collection of five SGIs and PCs. A German version of Rea has also been developed and we are currently working on a PC-based application of the technology in which the agent plays the role of a child's virtual playmate. Their team involves Justine Cassell, Tim Bickmore, Lee Campbell, Hannes Vilhjálmsson,and Hao Yan from MIT Media Lab. Reference:


Exploration said...

u0206584- Vidhya Ganesan

While it is indeed cool that man has invented robots that can talk to him, I am beginning to get worried on whether we are taking this whole robot craze too far! In our efforts to automate and ease day to day life, are we slowly losing out on the little pleasures of life? For example, a robot acting as a virtual conversationist with kids who are alone at home only gives more incentive for the parents of the kids to leave them alone for longer, thereby gradually reducing the human interaction. Also, in areas that are risky or tiresome, replacing humans with robots maybe a boon but in areas like sales etc., if robots are going to replace humans, won't it render too many people jobless?

Security said...

u0204635 Tan Pei-En

Indeed. If robots were to take over the world, how insufferably boring it would be.

But I think that this kind of research has 2-fold benefits. Firstly, it helps us to develop technologies to automate many functions that a human may find bothersome to perform. For example, answering similar queries on the phone, or greeting people at the door.

Secondly, it offers invaluable insight on how human language is structured and how our brains process verbal and non-verbal inputs before coming up with an appropriate meaningful response. What exactly is the connection between 'signs' (e.g. patterns on a paper, waves in the air, certain bodily positions) and meanings (e.g. words on a paper, spoken language, and body language)? In trying to develop a conversational robot, we learn a lot about all these.

Edutainment said...

U025313R Chua Kin Chye

I agree with Vidhya. While the creation and implementation of this conversational humanoid may be an engineering acccomplishment, it may be difficult to find applications for this robot. Who wants to shop at a mart where you are served by humanoids, espeically at this time when the quality of service is an important component of the consumer experience. Then again,this robot could be put to good use as a teaching aid where children can be encouraged to learn more about a subject through interaction with the robot.
However, we must never lose sight of the human touch for without that, the humanoid will not be the only robot around.

Home said...

U0205077 Mu Jun

I believe that pure “conversational” humanoids do not have many practical applications. Replacing humans with robots in daily life, such as sales person, is not going to happen soon. However, the research will definitely benefit the manufacturing of other humanoids, such as those for entertainment purposes. It will be interesting for children to have a toy humanoid with the ability to “chatting” and it will also be soothing if you can talk to your robot when alone.

I am very interested in the speech synthesizing ability of Rea, but I think this technology has not matured yet.

Exploration said...

I dont think machine could simulate human's speech perfectly, as it contains too much emotional factors and personal style. Human could easily distinguish real human speech from machine speech. I beleive machine could speak only when it becomes human.

Exploration said...

u0204999 Sim Xin'An Eddie
I think its quite cool that robots can be able to carry out conversations with humans but I am afraid it misses the point of human interaction sometimes. I believe its difficult for the robot to replace human interaction and it shouldn't in fact. I don't think I did like to spend the rest of a day talking to a robot when all I can get from it are just information that is translated into speech. Also there is no emotion and feelings involved. This is perhaps the one thing robots cannot replace. However on the bright side, I think the futuristic shows that we see in the movies are a testament to this technology. I believe Singapore has a bad service culture so imagine next time, if you buy movie tickets or ask an information counter for directions, what you get is a robot face that is pleasant and gets you what you want on time. Amazing and I believe a brilliant prospect for the service industry.