{"id":2217,"date":"2021-01-11T18:57:51","date_gmt":"2021-01-11T18:57:51","guid":{"rendered":"https:\/\/thenextweb.com\/?p=1333660"},"modified":"2021-01-11T18:57:51","modified_gmt":"2021-01-11T18:57:51","slug":"ai-devs-claim-theyve-created-a-robot-that-demonstrates-a-primitive-form-of-empathy","status":"publish","type":"post","link":"https:\/\/www.londonchiropracter.com\/?p=2217","title":{"rendered":"AI devs claim they\u2019ve created a robot that demonstrates a \u2018primitive form of empathy\u2019"},"content":{"rendered":"\n

Columbia University researchers have developed a robot that displays a \u201cglimmer of empathy\u201d by visually predicting how another machine will behave.<\/p>\n

The robot learns to forecast its partner\u2019s future actions and goals by observing a few video frames of its actions<\/p>\n

The researchers first programmed the partner robot to move towards green circles in a playpen of around 3\u00d72 feet in size. It would sometimes move directly towards a green circle spotted by its cameras, but if the circles were hidden by an obstacle, it would either roll towards a different circle or not move at all.<\/p>\n

Credit: Creative Machines Lab\/Columbia Engineering<\/figcaption>
<\/i><\/a>The machine uses visual observations to predict how its partner robot will try to reach the green dots.<\/figcaption><\/figure>\n

After the observer robot watched the actor\u2019s behavior for roughly two hours, it started guessing its partner\u2019s future movements. It eventually managed to predict the subject\u2019s goal and path 98 out of 100 times.<\/p>\n

[Read: Meet the 4 scale-ups using data to save the planet<\/a>]<\/em><\/p>\n

Boyuan Chen, the lead author of the study, said<\/a> the initial results were \u201cvery exciting:\u201d<\/p>\n

\n

Our findings begin to demonstrate how robots can see the world from another robot\u2019s perspective. The ability of the observer to put itself in its partner\u2019s shoes, so to speak, and understand, without being guided, whether its partner could or could not see the green circle from its vantage point, is perhaps a primitive form of empathy.<\/span><\/p>\n<\/blockquote>\n

The team believes their approach could help pave a towards a robotic \u201cTheory of Mind,\u201d which humans use to understand other people\u2019s thoughts and feelings.<\/p>\n

\u201cWe hypothesize that such visual behavior modeling is an essential cognitive ability that will allow machines to understand and coordinate with surrounding agents, while sidestepping the notorious symbol grounding problem<\/a>,\u201d the researchers said in their study paper<\/a>.<\/span><\/p>\n