A maze is a common tool used by psychologists to measure the learning ability of mice or rats. Their robot makes judgments based on the same system that people use to think and act: the brain. The research lays the path for fascinating new uses of neuromorphic devices in medicine and beyond. Researchers from Eindhoven University of Technology (TU/e) in the Netherlands and the Max Planck Institute for Polymer Research in Mainz, Germany, have now demonstrated that they can. Their robot makes judgments based on the same system that people use to think and act: the brain. The research, which was published in the journal Science Advances, lays the door for fascinating new uses of neuromorphic devices in health and beyond. 

Attempting to imitate the human brain

One of the reasons that researchers have been attempting to design computers that are considerably more energy efficient is because of this power issue. To discover a solution, many people are looking to the human brain, a thinking machine that is unrivalled in its low power consumption owing to the way it mixes memory and computation.

Neurons in our brain interact with others via connections, which increase with each data flows across them. This adaptability is what allows us to remember and learn. 'In our study, we used this concept to create a robot that can learn to travel around a labyrinth,' explains Imke Krauhausen, PhD student at TU/Mechanical e's Engineering department and the paper's lead author.

'A synapse in a mouse brain is reinforced each time it takes the proper turn in a psychologist's labyrinth, and our gadget is 'tuned' by providing a specific quantity of electricity. You may modify the voltage that controls the motors by adjusting the resistance in the device. They, in turn, determine whether the robot turns left or right.' 

How does it function?

Krauhausen and her colleagues conducted their investigation with a Mindstorms EV3, a Lego robotics kit. It was placed into a 2 m2 huge maze made up of black-lined hexagons in a honeycomb-like layout, equipped with two wheels, typical guiding software to ensure it can follow a line, and a variety of reflectance and touch sensors.

By default, the robot is configured to turn right. When it comes to a dead end or deviates from the intended path to the exit (as indicated by visual signals), it is instructed to either return or turn left. This corrected stimulus is subsequently stored in the neuromorphic device for future use. 'In the end, it took our robot 16 passes to correctly identify the exit,' Krauhausen explains. 'Furthermore, once it has trained to traverse this specific route (target path 1), it can navigate any other road that is presented to it in a single pass (target path 2). As a result, the information it has gained is generalizable.'

According to Krauhausen, who collaborated closely with the Max Planck Institute for Polymer Project in Mainz on this research, the unique combination of sensors and motors contributes to the robot's capacity to learn and leave the maze. 'This sensorimotor integration, in which sensation and movement reinforce one another, is also very much how nature functions, so we attempted to recreate it in our robot.'