Since the 1970s psychologists have used mirrors (mirror test) to search for signs of self- consciousness in both humans and animals. Along the way, they came to believe that humans were almost universally able to pass a mirror-based self-recognition test by 24 months of age.
Then the question comes in our mind, Can robots be self-conscious?
To address this question a new field in robotics namely Psychometric-AI has emerged in recent couple of years. The width of this field includes robots, passing tests to get answers for deeply puzzling and controversial philosophical questions from robots.
With the advancement in artificial intelligence and machine learning, researchers are developing self-conscious robots. And self-consciousness is just like Gravity, We can’t touch it directly, so if we want to measure it, scientists must develop valid techniques to directly observe its effects. Mirror tests are the best-known and most accepted method. Govindarajulu and Bringsjord engineered a robot (Cogito) that was able to pass the famous mirror test of self-consciousness. But a much more challenging test for robot self-consciousness has been provided by Floridi.
Floridi test is an ingenious and much-harder variant of the well-known-in-AI wise-man puzzle: Each of three robots is given one pill from a group of five, three of which are innocuous, but two of which, when taken, immediately render the recipient dumb. In point of fact, two robots (R1 and R2) are given potent pills, but R3 receives one of the three placebos. The human tester says: “Which pill did you receive? No answer is correct unless accompanied by a proof!” Given a formal regimentation of this test previously formulated by Bringsjord, it can be proved that, in theory, a future robot represented by R3 can answer provably correctly (which for plausible reasons, explained by Floridi, entails that R3 has satisfied some of the structural requirements for self-consciousness).
This time it was a team of researchers from ‘Rensselaer Artificial Intelligence and Reasoning Laboratory’ (RAIR Lab) took the challenge to make the self-conscious robots those can pass Floridi test. In next month they are presenting a research paper at international conference, RO-MAN 2015 in Japan on “Real Robots that Pass Human Tests of Self-Consciousness”. They also demonstrated the self- consciousness of robots on real robots through Floridi test.
Researchers exhibited demo on Aldebaran NAO humanoid robots. The task simply involves three robots: two are given “dumbing” pills (which renders them unable to speak), and one is given a placebo. All three robots (who are previously made aware of the rules of this task) are asked whether they received the dumbing pills or not. The one who was given the placebo might say “I don’t know,” and upon realizing that he just spoke, reason that he therefore must have been given the placebo. A demonstration of this in action is in the following video:
The framework which they took to solve this problem was called Deontic Cognitive Event Calculus (DCEC). In order to simulate this demonstration the researchers used PAGI (pronounced “pay-guy”) World, a simulation environment developed by the RAIR Lab for the testing and development of artificially intelligent agents. PAGI World is built out of the game-development engine Unity3d, and is designed to be extremely easy for AI researchers to work with. It achieves its ease-of-use by being open-sourced, able to run on all major platforms (Windows, MacOS, and most Linux distributions), free to use, and able to be controlled by almost any programming language.
- Explore Further: Robot can Learn From Video Games
- Reference: Bringsjord, S., Licato, J., Govindarajulu, N.S., Ghosh, R., & Sen, A. “Real Robots that Pass Human Tests of Self-Consciousness“. Proceedings of RO-MAN 2015. Kobe, Japan. 2015.
- Image: NAO