The robot was able to take care of you in old age, he will have to learn from scratch - as a child

It is likely that very soon robots will live in homes with people helping older people to live independently. But to do this they will have to learn how to do all the little jobs that people could perform without thinking. Many modern systems of artificial intelligence are trained to perform certain tasks, analyzing thousands of images signed by a particular action. Although these methods help to solve more complex problems, they still apply only to very specific problems and require a lot of time and computing power to study.

The robot was able to take care of you in old age, he will have to learn from scratch - as a child

If the robot will take care of the elderly, problems of this work will be very different when compared with the typical situations in the learning process. During the day, the robots have to do a lot of things, from tea to change the bed linen during the conversation. These are complex tasks that are more complex in combination. There are no two identical houses, which means the robots have to quickly learn and adapt to the environment. And as it often happens, if you live with someone else, things have to migrate the property. The robot will have to learn to find their own.

One approach is to develop a robot capable of learning throughout life, which would keep the knowledge based on experience, and to develop ways to adapt and apply to new tasks. Once you learn how to make a cup of tea, these skills can be applied to coffee. the human brain learns throughout his life, constantly adapting to the complex and changing environments and solving a wide range of everyday problems. Simulation of how people learn, could help in the development of robots with which we can interact in a natural way, as if the other person.

Simulation of child development for robot training

The first question to ask when you start to model people: where to start? Alan Turing, the famous mathematician and pioneer of artificial intelligence, once said:

"Instead of trying to create a program to simulate the adult mind, why not try to make a program for the simulation of the child? If it were so, then after an appropriate course of education one would obtain the adult brain. "

He compared the brain child of a blank notebook that you can fill in the educational process and to develop an intelligent adult "system." But what should be the age of the child for modeling? What knowledge and skills necessary to lay the first?

Newborn babies are very limited in what they can do and how to perceive the world around them. Of muscle strength in the child's neck is not enough to support the head, and he has not learned to control their arms and legs.

Start from zero months - such a move could severely limit the robot. But the child's physical limitations actually help him focus on solving small subclass of problems, for example, he learns to relate his eyes so that he hears and sees. These steps are in the initial stages of construction of model child build his body before he begins to understand the complexity of the world around them. Engineers have used these restrictions to the robot, initially blocking movement of various joints to simulate the lack of muscle control. They also adjusted the image with a robot camera that he "saw" through the eyes of a newborn - with the blurring and weak periphery. Instead of talking to the robot, how to move, he was allowed to find it yourself. Plus there was the fact that as the calibration changes or as limb damage, the robot will be able to adapt to these changes and continue to work.

Learning to play the

Studies have shown that the application of restrictions in the learning process, not only increases the speed with which to acquire new knowledge and skills, but also increases the accuracy of what is being studied.

Giving the robot control deregulation - giving him control over the joint and improving its vision - we can ensure that the robot itself will control their speed of learning. Scientists have simulated a "child" and the first 10 months of its growth. As soon as the robot is trained to correlate traffic and the resulting sensory information, it acquired stereotyped behavior observed in infants - like that when children spend long periods of time staring at his hands while driving.

When the robot learns to coordinate his own body, the next important milestone, which he passed - he begins to understand the world around him. Game - it is an important part of a child's learning. It helps him to explore the environment, to test various possibilities and study the results. At first, it may be something simple, like a knock spoon on the table or put in the mouth of any subject. But then it turns into building towers out of blocks or placing objects in the appropriate holes. All of these actions create an experience that in the future provide a basis for skills such as finding the right key to open the lock and fine motor skills, to insert the key into the lock, and then turn it off.

In the future, the use of these methods will give robots the means for learning and adaptation to difficult conditions and tasks that people take for granted in everyday life. Once robots can help the elderly, but will be able to teach them even the children in the kindergarten.

Do not forget that you can discuss robots in our chat in the telegram.