First of all, the mirror test is not exactly intended as a general test for consciousness, but a specific test for self-consciousness, and more exactly self-recognition. It is generally applied to some higher mammals and infants. The test consists on determining whether or not the subject can recognize its own reflection in a mirror. So far, only subjects belonging to the following species have passed the mirror test:

Mirror Test

humans (over 2 years old),
great apes (bonobos, chimps, orangutans, and gorillas),
rhesus monkeys,
elephants,
bottlenose dolphins,
rats,
and octopuses.

I think it is important to note that only a determined number of individuals of these species have passed the tests, while others generally fail to pass it. Obviously the test has to be adapted to each specie, although it typically consists on an odorless paint mark made in the forehead while the animal is anesthetized.

The mirror test has been considered by some researchers as one of the best available ways to test self-consciousness in organisms (see for instance how it is applied to Elephants in [1], and see [2] for an open discussion about the mirror test validity). Mirror test is famous thanks to its application to primates, as introduced by Gordon Gallup in the 70’s [3]. However, little work has been done in the application of the mirror test to robots.

Can we build a robot able to successfully pass the mirror test? And if so, does it really mean that the robot is self-aware?

Robot Mirror Test

Takeno et al. [4] at Meiji University in Japan claim that they have succeeded in achieving mirror image cognition for a robot. They define four steps for their experiments, where four robots are used: the self robot Rs, the other robot Ro, the controlled robot Rc, and the automatic robot Ra. The first two robots are endowed with the mirror image cognition system. The third robot is controlled by the self robot, while the last one moves automatically.

The four experiments are as follows:

1) The self robot Rs imitates the action of its own image reflected in a mirror.
2) The self robot Rs imitates an action taken intentionally by the other robot Ro as imitative behavior.
3) The controlled robot Rc is controlled completely from the self-robot to imitate his behavior.
4) The self robot Rs imitates the random actions of the automatic robot Ra.

The robot is able to recognize its own image reflected in a mirror without confusing it with the image of another robot with the same physical aspect. The mirror image cognition system is based on an artificial neural network. The aim of this system is to recognize and differentiate robot’s own behavior from other robot’s behavior. Takeno also suggests that imitation is a proof of consciousness as it requires the recognition of other subject’s behavior and then the application of that behavior to oneself.

The results described in the paper indicate that in some way the robots are passing the mirror test with an accuracy of 70%, but I am reluctant to claim that they are self-conscious. I would rather say that the present a-consciousness of their recognized image.

[1] http://www.conscious-robots.com/en/neuroscience/mammals-brain/elephants-recognize-themselves-in-the-m-3.html
[2] http://www.conscious-robots.com/en/forums-./test-for-consciousness/mirror-test/view.html
[3] Gallup, G.G., Jr. (1977). Self-recognition in primates: A comparative approach to the bidirectional properties of consciousness. American Psychologist, 32, 329-337.
[4] Junichi Takeno, Keita Inaba, Tohru Suzuki. Experiments and examination of mirror image cognition using a small robot. Proceedings. 2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation, 2005. CIRA 2005. Full paper available at: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1554325

Comments (1) | Add as favourites (112) | Quote this article on your site | Views: 1804 | E-mail

Do robots dream of God? This is a controversial question raised many times in Hollywood movies. However, in recent years scientists and theologians are looking at the possible implications of Strong Artificial Intelligence.

The possibility of a future in which humans and robots live together in a new technological society is bringing together science and religion. Anne Foerst, a theologian and research scientist seeks to bridge the gap between religion and AI research. In her book God in the Machine [1], she argues that robots have much to teach us about ourselves and our relationship with God. Back in 1993 Foerst was working with Rodney Brook’s team at the MIT AI Lab. They identified a set of questions that are intrinsically related with the two fields of robotics and religion: Can a robot be human? What does it mean to be human? Are we made in the image of God?

MIT’s Cog robot was designed to learn from physical and social interaction. It was programmed to show social and emotional responses. According to Foerst, personhood is just playing a role in a mutual process of telling stories. Even though robots like Cog can’t tell their own story, they can at least play a role in our lives so we can include him in our narrative process [2]. 

Be first to comment this article | Add as favourites (60) | Quote this article on your site | Views: 1789 | E-mail

  It seems that some governments are taking very seriously the possibility of the everyday use of robots in society. Japan and South Korea are worried about human safety in a world where many critical tasks can be performed by machines. They share the Issac Asimov’s vision of a future world where human beings and robots coexist. However, they don’t seem to trust mechanical creatures controlled by only three simple laws.

 As reported by The Times a few weeks ago, Japanese robotics experts assure that the famous Three Laws are not enough to keep us safe when the next generation robots become a reality. A 60 page draft document titled ‘Guidelines to Secure the Safe Performance of Next Generation Robots’ is being discussed by the industry, researchers, and lawyers with the aim to elaborate a law that protect us effectively.

This draft document proposes the creation of a central database where all incidents of human harmed by robots will be recorded and accessible by robot manufacturers. Therefore, robots must be equipped with the corresponding mechanisms to log and communicate any injures they cause to people during their task accomplishment. Japan is envisioning a near future where robots play a key role in society and they have detected the need for a well-built regulation. It is foreseen that the domestic robot market grow in Japan up to more than 3.3 trillion yen in the next 15 years. Assistant robots able to help and chat with pensioners are already a reality. Nursing robots, security patrol robots, home assistant robots are going to be common in the coming years.

Comments (9) | Add as favourites (81) | Quote this article on your site | Views: 2129 | E-mail

Self-modelling

What do robots dream of? This is the title of a perspective paper published this week in Science written by Christoph Adami. The author argues that robots that create and update internal models of their own structure may be able to better adapt to the world. Indeed, the robot developed by J. C. Bongard, H. Lipson, and V. Zykov is able to self-detect his own damages and generate a new gaits adapted to its new (damaged) situation. This capability can improve the use of robots in dangerous enrironments. Usually, animals adapt their gaits to any injure they may have. However, this is not common in machines. Bongard et al. have developed a four legged robot able to sense its own movements and structure and calculate new adapted Gait models after it has suffered a damaged.

•  Watch Robot video.

Be first to comment this article | Add as favourites (56) | Quote this article on your site | Views: 1841 | E-mail