Expressive face helps robot bridge ‘uncanny valley’

A good-looking robot is seriously hard to find. Robots can be pretty, some even handsome, but as soon as they get too realistic they start to creep us out. A new system for helping robots to generate more realistic expressions might go some way to help.

Many years ago, robotcists realized that as you morph an abstract robot into a human you generate a peak of unease – the “uncanny valley principle” – that makes people feel uncomfortable when a robot looks realistic but not realistic enough. Some say it’s because they remind us of a corpse. However, researchhas shown that if you manipulate the robotic images so that they are more attractive, you can bypass this feeling of unease.

To create a robot we are more likely to accept, life-like expressions are vital. That’s why Nicole Lazzeri at the University of Pisa, Italy, and her colleagues have designed a “Hybrid Engine for Facial Expressions Synthesis” (HEFES) – a facial animation engine that gives realistic expressions to a humanoid robot called FACE.

FACE’s appearance is modelled on one of the team’s wives. “It’s really realistic,” says Lazzeri, who presented the work at BioRob in Rome last month. See for yourself in the video above.

To mimic the myriad expressions that facial muscles are capable of achieving, the team placed 32 motors around FACE’s skull and upper torso that manipulate its polymer skin in the same way that real muscles do.

To create expressions they used a combination of motor movements based on the Facial Action Coding System(FACS) – a system created over 30 years ago which codes facial expressions in terms of anatomic muscle movements.

HEFES is used to control FACE’s expressions. It is essentially a mathematical programme that creates an “emotional space” which a person can use to choose an expression for FACE that exists anywhere between one or more basic emotions, including anger, disgust, fear, happiness, sadness, and surprise. The algorithm then works out which motors need to be moved to create that expression or transition between two or more.

The team evaluated the accuracy of their expressions by asking five autistic and 15 non-autistic children to identify a set of expressions performed first by FACE and then by a psychologist. Both groups were able to identify happiness, anger and sadness but less able identify fear, disgust and surprise.

So is it more attractive? I’m not convinced. But FACE’s ability to smoothly transition between one emotion and another is pretty remarkable. And not too creepy.


Blowfish12@2012 blowfish12.tk Author: Sudharsun. P. R.

Robotic surgery performed for normalising urinary bladder

07THROBOT_1136435f

A seven-year-old girl from Dar es Salaam has a robot to thank for a life reboot.

The Tanzanian girl, who was admitted to Apollo Children’s Hospital after her urethra was crushed in a road accident in her home town, had been subjected to a complex robotic surgery to restore the urinary bladder to normal function.

Ashura Ibrahim had come to Apollo almost a year ago after unsuccessful attempts by doctors in Tanzania to normalize the urinary bladder that left her with a tube hanging from her bladder to pass urine causing physical and mental trauma.

Pediatric urologists found that the child’s bladder was constantly draining to the outside and holding capacity had shrunk. In an open surgery procedure, a flap of the bladder muscle was fashioned into a tube and tunneled to a normal position to serve as the urethra. A few weeks ago, the girl was back for a review and doctors found that in the process of healing, her left ureter had displaced towards the bladder neck and urine was refluxing into the kidney making her prone to frequent urinary infections and renal damage.

After evaluating the options before them, a team led by V. Sripathi, consultant pediatric urologist at Apollo, scheduled the patient for a robotic surgery to stop the urine reflux on June 25. “We ruled out open surgery to cease urine reflux, as it would leave the girl again with a tube to pass urine while a laparoscopy would have been unusually complicated because the ureteral opening was very low,” Dr. Sripathi said.

With the help of the Da Vinci Si robotic system with features such as 3-D field-view and “snake-wrist” arms that can be maneuvered 360 degrees, doctors could create a new bed and suture the ureter into it without reopening the bladder.

Little Ashura is now ready to return home along with her parents. Khery Goloka, Medical Attache, Tanzanian High Commission, Delhi, facilitated the treatment. According to doctors, the procedure was perhaps the first robotic surgery of its kind in pediatrics and the first complex redo on the bladder base.

Robotic surgery enabled us to achieve a perfect result in a very difficult situation with very minimal morbidity, with no pain and helped achieve discharge within a day,” he said. And, he believed that this more than made up for extra Rs.1 lakh in expenses when compared to conventional intervention tagged at around Rs.80,000.

According to Srinidhi Chidambaram, coordinator for international patient services, Africa accounted for a significant proportion of the 16,000 foreign patient visits last year. Patients from Africa, along with West Asia and the SAARC countries, account for nearly 80 per cent of foreign patient arrivals.


Blowfish12@2012 blowfish12.tk Author; Sudharsun. P. R.

Artificial brain with billion connections

Google has done the unthinkable — the creation of an ‘artificial brain’ from 16,000 computer processors, with more than a billion connections.

The team led by Google’s Jeff Dean then fed it random images culled from 10 million YouTube videos — and let it ‘learn’ by itself.

Surprisingly, the machine focused in on cats. “We never told it during the training ‘this is a cat’,” said Dean. “It basically invented the concept of a cat.”

The revelation

“Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not,” says the team.

“We also find that the same network is sensitive to other high-level concepts such as cat faces and human bodies.”

“Starting with these learned features, we trained our network to obtain 15.8 per cent accuracy in recognizing 20,000 object categories from Image Net, a leap of 70 per cent relative improvement over the previous state-of-the-art,” it said,Daily Mail reports.

The ‘brain’ was a creation of the company’s ‘blue sky ideas’ lab, Google X, reportedly located in Google’s Mountain View, California, headquarters — known as ‘the Googolplex.’

Engineers are free to work on projects such as connected fridges that order groceries when they run low — or even tableware that can connect to social networks.

Other Google engineers have reportedly researched ideas as far-out as elevators to space.


Blowfish12@2012 blowfish12.tk Author: Sudharsun. P. R.