While the implementation of an artificial nervous system may seem counterintuitive to the usefulness of an automaton — don’t we want them to work tirelessly and painlessly? — scientists say this distinctly human ability will help robots react quickly to dangerous situations, potentially warning their flesh and blood counterparts of impending risks.
The robot’s nervous system is based upon “insights from human pain research,” scientists from Leibniz University in Hannover, Germany, said. “Pain is a system that protects us,” researcher Johannes Kuehn told Spectrum IEEE. “When we evade from the source of pain, it helps us not get hurt.”
In initial tests, the research team equipped a robotic arm with a fingertip sensor capable of determining pressure and temperature. This sensor, if successful, will act like a human neuron, passing along information to the robot’s “brain” about whether its discomfort is light, moderate, or severe. Ultimately, the goal is to create a system that helps robots “detect and classify unforeseen physical states and disturbances, rate the potential damage they may cause to it, and initiate appropriate countermeasures, i.e. reflexes.”
“Getting robots to learn is one of the most challenging things but is fundamental because it will make them more intelligent,” Cambridge University Professor Fumiya Iida told the BBC. “Learning is all about trial and error. When a child learns that falling over causes pain, it then learns to do it with more skill.”
Research remains in its nascent stages for now, but as robots become more autonomous and work alongside — rather than under — humans more frequently, this pain research may become a crucial component of a robot’s future. It looks like growing pains are real.
