The first question a child always asks is always: “Why?” it is not enough “having to do”, rather, he wants to understand the reason; the principle of robotic philosophy is the same. We need to review robots and their learning, because if they understood the reason for their actions, they would be able to operate safely and better support humans.
This is what emerges from a study in collaboration between the School of Advanced Studies Sant’Anna in Pisa and the University of Birmingham. According to the researchers, the development of a robotic philosophy is not only an improvement, but will become a concrete necessity in various sectors, including automation, 4.0 industry and domotics.
As the human-robot relationship intensifies, machines need to learn not only how to make a movement; above all, they need to think about the action in order to be cooperative. For example, a generic command in a workshop, such as “pass me the screwdriver”. Up to now, the robot would only hold it and deliver it to the operator, risking to wound it with the tip, as it would grab it from the handle side.
What to do to implement robotic philosophy?
What is required, therefore, is to rethink the way the robot performs the action. We need powerful technologies that integrate digital vision, AI and sensors so that the robot understands the action it has to take. It is no longer enough for the robot to grab an object to believe that it has been successful in its action. The manipulation technology applied in the last 20 years, therefore, is no longer able to sustain the cooperation between man and robot.
Therefore, according to robotic philosophy, the machine -just like a child- needs to know its final goal, so that it can work in harmony with men. In order to do this, science must take a completely different approach to machines.