Thursday, Oct 19 2017 | Updated at 03:26 AM EDT

Stay Connected With Us F T R

Apr 29, 2017 11:47 AM EDT

Cornell University's Humanoid Robot Makes North American Debut [VIDEO]

Close
George Clooney, Meryl Streep to Jennifer Lawrence: Hollywood stars speak out against Harvey Weinstein

Rodolphe Gelin, chief scientific officer of SoftBank Robotics presented a speech at the Entrepreneurship event at Cornell celebration. More than 100 Cornell alumni were present during the conference that featured the North American debut for "Pepper," the name of the three humanoid robots developed by SoftBank Robotics since 2014.

The three versions of Pepper were introduced as the first humanoid robots capable of recognizing human emotions and adapt behaviors accordingly. Soumitra Dutta, dean of the SC Johnson College of Buisness said it was the first time that Pepper is here in Cornell, which happens to be a great fit for the university is known for engineering and business.

Gelin has had 20 years of research experience in robotics and is passionate about using robots to assist people and help with rehabilitation. He also directed the development of Romeo, which is a research prototype designed to assist the elderly. He said all his service robots were designed to interact with humans.

The Cornell Sun reported, Gelin said 20,000 Pepper robot units were sold in more than 70 countries, which makes SoftBank a world leader in the market of humanoid robotics. Gelin introduced the smaller humanoid robot, Nao, through a series of videos. It has applications that include autism clinical treatment, disability aid, educational assistance, physical coaching, environment exploration, communication and cognitive games.

Gelin said emotional detection in the voice and emotional interaction with humans are unique to humanoid robots. It could create important connections with the use of empathy. By learning, the robot understands why one says and how they say it.

Despite the progress in robotics there are still barriers that need to be overcome, he said. One of the challenges he pointed out was between having a slow-speaking robot and a potential privacy violation. Signal processing in real-time is prevented by a limited CPU (central processing unit). By sending the signal to a remote server however, requires personal information to be shared with the rest of the world, creating a balancing act.

© 2017 University Herald, All rights reserved. Do not reproduce without permission.

Join the Conversation

Get Our FREE Newsletters

Stay Connected With Us F T R

Real Time Analytics