Robot head puts on your friend’s face

New Scientist

 

The spooky robotic head was watching me. As I passed by, it followed me with its eyes and slowly craned in my direction. Then it spoke, its animated lips moving realistically as it promoted an imminent crowdfunding campaign. When I stood still, it looked me over: its sensors examined my face and counted up my wrinkles. Then, rather annoyingly, it correctly guessed my age.

I was interacting with SociBot-Mini, a 60-centimetre-high robot built by Will Jackson and his colleagues at Engineered Arts in Penryn, UK. The model is one of their first generation of robots, already on sale. The company bills it as a futuristic information terminal that people could interact with in a mall, airport or bank, say. And if the Kickstarter campaign is successful, a cheaper, slimmed-down version will follow for home use, as a kind of personal assistant.

“Today’s computer interfaces have moved on very little from the typewriter,” says Jackson. “We have social software and a social internet, but we don’t have social hardware.”

SociBot-Mini uses a depth-sensing camera – similar to Microsoft’s Kinect system – to capture and recognise gestures. It can also capture facial expressions using a webcam. Computer vision software lets it perform tricks like recognising people, working out someone’s mood from their grimaces and smiles, as well as guessing their age. It also has some understanding of speech and comes with chatbot software based on Rosette, which in 2011 won the Loebner prize, awarded for a computer’s ability to hold simple conversations. The idea is to build a system that people enjoy working closely with. “It’ll become a butler who knows you inside out,” says Jackson.

Its transparent plastic face has contours for a nose, mouth and eyes, and is backlit with a digital projector. It can display a generic face like the one that sized me up, or create one based on a headshot of a friend or colleague to add telepresence to voice calls.

“It’s as spooky as all hell,” says Jackson. “We’ve tried it with a couple of our telecommuting colleagues in meetings and when it suddenly turns and joins in the conversation as our colleague Dan, and with his face, it is quite amazing. But you get used to it quickly.”

I ran into SociBot-Mini at the Human-Robot Interaction conference in Bielefield, Germany, earlier this month. It isn’t the only one of its kind. At the Royal Institute of Technology in Stockholm, Sweden, Samer Al Moubayed is developing an animated head called Furhat to which 3D-printed faces can be attached. The idea is to take infrared scans of someone’s friends and print their faces, so that the appropriate one can be used just before the person calls them.

It sounds like a palaver, but Al Moubayed says being able to animate the 3D-printed face of a real person lends extra authenticity to the telepresence experience. Skype is interested in the project, and will team up with the group developing Furhat to bring animated delegates to the Interspeech conference in Singapore in September.

Tony Belpaeme, who has researched facial projection in robots at Plymouth University in the UK, believes the technology will make a big difference to video chat in particular. “Two dimensional video conferences are quite impoverished experiences. There is still something missing and so we prefer to meet real people. So the more you can bring that 2D experience into the 3D physical space the better the interaction will flow.”

“Having a robot in which your face is projected, carrying all the right expressive signals, will provide an immensely strong presence, even though it will seem uncanny at first,” Belpaeme says.

Source: Newscientist

Ubiquitous Network Robot (UNR-PF)

Ubiquitous Network Robots (UNR)

Aiming at coordination/cooperation of robot services for elderly and handicapped people in multiple area

Background and goals

The previous research project in 2004-2009 focuses on single area, and developed several network robot systems allowing cooperation/coordination of robots with ambient sensor networks, mobile phones, etc.

Current research project extends the system to multiple area such as home, hospitals and shopping malls and has developed a common infrastructure for robotic services to support our daily life: the Ubiquitous Network Robot Platform (UNR-PF). It allows cooperation and coordination of robotic services,

Features

  • We aim at realizing robot services with spatial expansion, by linking multiple locations such as home, hospitals and commercial facilities, though cooperative network robots.

  • We aim at establishing technologies for allowing the provision of robot services related with patrol, life support, and social activity supports, assuming that users can be elderly and handicapped people.

Future plans

Along with the development of base technologies, we plan to develop a cooperative service system which links two locations, and realize robot service trial experiments such as shopping support services and remote dialogue support services.

Shopping Support Service

(This research/development is supported by the Ministry of Internal Affairs and Communication.)

Contact the IRC

irc-contact@atr.jp

ATR Intelligent Robotics and Communication Laboratories

〒619-0288
2-2-2 Hikaridai
Keihanna Science City
Kyoto 619-0288 Japan
ATR Intelligent Robotics and Communication Laboratories
TEL: +81-774-95-1405
FAX: +81-774-95-1408

Source: IRC

Relationships: Robots and Humans. ROILA

ROILA, Robot Interaction Language, is a spoken language for robots. It is constructed to make it easy for humans to learn, but also easy for the robots to understand. ROILA is optimized for the robots’ automatic speech recognition and understanding.

The number of robots in our society is increasing rapidly. The number of service robots that interact with everyday people already outnumbers industrial robots. The easiest way to communicate with these service robots, such asRoomba or Nao, would be natural speech. But current speech recognition technology has not reached a level yet at which it would be easy to use. Often robots misunderstand words or are not able to make sense of them. Some researchers argue that speech recognition will never reach the level of humans.

Palm Inc. faced a similar problem with hand writing recognition for their handheld computers. They invented Graffiti, an artificial alphabet, that was easy to learn and easy for the computer to recognize.  ROILA takes a similar approach by offering an artificial language that is easy to learn for humans and easy to understand for robots. An artificial language as defined by the Oxford Encyclopedia is a language deliberately invented or constructed, especially as a means of communication in computing or information technology.

We reviewed the most successful artificial and natural languages across the dimensions of morphology and phonology (see overview in the form of a large table) and composed a language that is extremely easy to learn. The simple grammar has no irregularities and the words are composed of phonemes that are shared amongst the majority of natural languages. The set of major phonemes was generated from the overview of natural languages. Moreover, we composed a genetic algorithm that generated ROILA’s words in a way that they are easy to pronounce. The same algorithm makes sure that the words in the dictionary sound as different from each other as possible.  This helps the speech recognizer to accurately understand the human speaker.

Most previously developed artificial languages have not been able to attract many human speakers, with the exception of Esperanto. However, with the rise of robots a new community on our planet is formed and there is no reason why robots should not have their own language. Soon there will be millions or robots to which you can talk to in the ROILA language. In summary, we aim to design a “Robotic Interaction Language” that addresses the problems associated with speech interaction using natural languages. Our language is constructed on the basis of two important goals, firstly it should be learnable by the user and secondly, the language should be optimized for efficient recognition by a robot.

ROILA is free to use for everybody and we offer all the technical tools and manuals to make your robot understand and speak ROILA. At the same time we offer courses for humans to learn the ROILA language.

Automated Installer and Java Library March 17, 2013. Development versions of the Automated Installer and Java Library are currently available on GitHub. Please report any issues to Josh at 17019428@student.uws.edu.au. The automated installer and java library are designed to help make it easier to work with ROILA. They are still a work in progress, so there are some features that won’t work fully (especially in the library.) GitHub will be updated with improved copies in the coming months. It will be changed shortly to update a bug with the downloading of the pre-compiled library. There are more planned features for this to come, so keep an eye out on GitHub.

We are currently developing courses in ROILA. They are available in our ROILA Academy. We are also giving a ROILA introductory course to Dutch High School students at the Huygens College Eindhoven. The short course will consist of three lessons followed by a ROILA final exam. The ROILA course will be part of their Science curriculum. The homework curriculum for this course is uploaded in theROILA academy and also on an external website. The vocabulary for this course is uploaded here. You can also find a similar dictionary in the ROILA academy. We will post videos and power point PDFs of each lesson given at the school. We have removed parts of the video that were only relevant to the students (such as administration of the course, etc).

Lesson 1

Lesson 1 Powerpoint PDF

Homework Lessons requirement: Topic 1, 2, 3, 4

Lesson 1 – November 15, 2010

Lesson 1 – November 19, 2010

Lesson 2

Lesson 2 Powerpoint PDF

Homework Lessons requirement: Topic 5, 6, 7

Lesson 2 – November 22, 2010

http://youtu.be/RkCUcWtyk_g

Publications

We have published several articles about ROILA: