Robots to undergo social emotions test

New evidence from the brain sciences, including cognitive psychology and neurophysiology, shows that emotions play an important role in the mental processes of humans. And that means if we want to create human-like artificial intelligence, we must make it emotionally responsive. But how do we know whether we have succeeded and the intelligence we have created is indeed able to experience real human-like emotions? That's where the metrics and tests developed by Alexei Samsonovich, a professor in the Cybernetics Department at the Moscow Engineering Physics Institute (MEPhI) National Research Nuclear University, could help us.

Samsonovich has come up with an artificial intelligence test based on a relatively simple computer game. The program and a human both manipulate virtual people on a computer display, thus interacting with each other. The game involves actions with emotional content: a player may strike or push aside his co-player, or say "hello" and step aside to make way for him, or help him move off a stone or get out of a trap. As a result, the players engage in different types of social relationships, for instance, mutual trust, subordination and leadership.

Normally, the Turing test is considered passed if a person is unable to guess whether his co-player is a machine or a human. In Samsonovich's case the idea is that the machine should have an emotional advantage over the average human player, which will manifest itself in players' wish to rescue the machine first. Such is the immediate task set forth by the researcher. Moreover, multiple behavioral parameters of the player and the machine will be calculated during the game, characterizing the inner worlds of both. For the machine, those parameters should, in the future, become statistically identical to human behavior.

Samsonovich's artificial intelligence test is just a small part of a far bigger scientific challenge: to build an artificial brain that reproduces the principles and mechanisms of emotional awareness in humans, a brain that would pass the aforementioned test and be accepted by humans as capable of experiencing emotions, commiserating and providing moral support in difficult situations.

A tentative solution could come in a year and a half from now, by which time, as scheduled, the researcher from the Institute of Cyber Intelligence Systems in MEPhI hopes to create a virtual being capable of drawing up plans, setting goals and establishing lasting social relationships with humans. Named Virtual Actor, it will hopefully possess both emotional and narrative intelligence and understand the context of events and what turns they could take.

Alexei Samsonovich presented his current research in his talk at the BICA 2016 conference, held in New York on July 16-19. The conference focuses on biologically inspired cognitive architectures as one of the approaches to creating artificial intelligence. Its main focus is on reproducing the principles and mechanisms of human thought in a computer.