Revolutionary Sensor System for Robots

A team of scientists from the Korea Advanced Institute of Science and Technology (KAIST) has created an innovative artificial sensory nervous system for robots that can differentiate between safe and potentially harmful touches, mimicking the behavior of living organisms. This was reported by Interesting Engineering.

This technology is based on a novel neuromorphic semiconductor — a new type of memristor that can respond to external stimuli without the need for complex software or significant computational power.

In animals and humans, constant stimuli such as air conditioner noise or clothing on the body are gradually ignored, while new or dangerous signals, like a sudden touch or pain, elicit an immediate response. This mechanism is regulated through two processes: habituation (the dampening of response to repeated safe stimuli) and sensitization (the enhancement of response to threatening stimuli). The KAIST team has succeeded in replicating these mechanisms electronically.

The innovation lies in the unique design of the new memristor. Unlike previous models that could only change conductivity in one direction, this device features an additional internal layer that allows it to change conductivity in the opposite direction. This enables the memristor to decrease sensitivity to repeated touches while rapidly activating in response to painful signals.

To test their development, researchers integrated the system into a robotic arm. Initially, it reacted to every touch. Over time, if touches were repeated without any threat, the reaction diminished. However, when the same touches were paired with an electric current, the arm became highly sensitive again.

This breakthrough demonstrates that artificial nervous systems can be compact, energy-efficient, and operate without complex software, paving the way for a new era in robotics.