Machine learning and neural networks have become an exciting field recently. Considering their success in medical diagnosis, e-commerce, and other areas, it became more popular.
The software-based approach to machine intelligence has a significant drawback; it consumes much power to train algorithms.
This power issue is one of the prime reasons researchers work on energy-efficient computing.
When It comes to energy-efficient solutions, everyone takes inspiration from the human brain. It works so efficiently with low power for both memory and processing.
A maze is a popular device that psychologists use to assess the learning capacity of mice or rats.
Researchers at the Eindhoven University of Technology (TU/e) and the Max Planck Institute for Polymer Research in Mainz, Germany, have proved that robots can successfully navigate the twist and turns of a maze.
The study, published in Science Advances, paves the way to exciting new applications of neuromorphic devices in health and beyond.
Neurons in our brain communicate through synapses, which are strengthened each time information flows through them. It is this plasticity that ensures that humans remember and learn.
“In our research, we have taken this model to develop a robot that is able to learn to move through a labyrinth”, explains Imke Krauhausen, Ph.D. student at the Department of Mechanical Engineering at TU/e and principal author of the paper.
“Just as a synapse in a mouse brain is strengthened each time it takes the correct turn in a psychologist’s maze, our device is ‘tuned’ by applying a certain amount of electricity. By tuning the resistance in the device, you change the voltage that control the motors. They in turn determine whether the robot turns right or left.”
Krauhausen and her colleagues used the robot to research-Mindstorms EV3, a robotics kit made by Lego. Equipped with two wheels, traditional guiding software to make sure it can follow a line, and a number of reflectance and touch sensors, it was sent into a 2 m*m large maze made up of black-lined hexagons in a honeycomb-like pattern.
The robot is programmed to turn right by default. Each time it reaches a dead-end or diverges from the designated path to the exit (indicated by visual cues), it will return or turn left as taught. It will then remember the corrective stimulus in the neuromorphic device for the next effort.
“In the end, it took our robot 16 runs to find the exit successfully,” says Krauhausen. “And, what’s more, once it has learned to navigate this specific route, it can navigate any other path that it is given in one go (target path 2). So, the knowledge it has acquired is generalizable.”
Part of the success of the robot’s ability to learn and exit the maze lies in the unique integration of sensors and motors, according to Krauhausen, who cooperated closely with the Max Planck Institute for Polymer Research in Mainz for this research. “This sensorimotor integration, in which sense and movement reinforce one another, is also very much how nature operates, so this is what we tried to emulate in our robot.”
Another intelligent thing about the research is the organic material used for the neuromorphic robot. This polymer (known as p(g2T-TT)) is not only stable, but it also can ‘retain’ a large part of the specific states in which it has been tuned during the various runs through the labyrinth. It ensures that the learned behavior ‘sticks’, just like neurons and synapses in a human brain, remember events or actions.
Paschalis Gkoupidenis of the Max Planck Institute for Polymer Research in Mainz and Yoeri van de Burgt TU/e pioneered using polymer instead of silicon in neuromorphic computing. Both are co-authors of the paper.
Their research (dating from 2015 and 2017) proved that the material could be tuned in a much larger range of conduction than inorganic materials.
It can ‘remember’ or store learned states for extended periods. Since then, organic devices have become a hot topic in hardware-based artificial neural networks.
Polymeric materials also have the advantage of being used in numerous biomedical applications. “Because of their organic nature, these smart devices can in principle be integrated with actual nerve cells. Say you lost your arm during an injury. Then you could potentially use these devices to link your body to a bionic hand,” says Krauhausen.
Another promising application of organic neuromorphic computing lies in small edge computing devices where data from sensors is processed locally outside of the cloud. Van de Burgt: “This is where I see our devices going in the future, our materials will be very useful because they are easy to tune, use much less power, and are cheap to make.”
So will neuromorphic robots one day be able to play a soccer game, just like TU/e’s successful soccer robots?
Krauhausen: “In principle, that is certainly possible. But there’s a long way to go. Our robots still rely partly on traditional software to move around. And for the neuromorphic robots to execute really complex tasks, we need to build neuromorphic networks in which many devices work together in a grid. That’s something that I will be working on in the next phase of my PhD research.”
Journal Reference
- Imke Krauhausen, Dimitrios A. Koutsouras, Armantas Melianas, Scott T. Keene, Katharina Lieberth, Hadrien Ledanseur, Rajendar Sheelamanthula, Alexander Giovannitti, Fabrizio Torricelli, Iain Mcculloch, Paul W. M. Blom, Alberto Salleo, Yoeri van de Burgt, Paschalis Gkoupidenis. Organic neuromorphic electronics for sensorimotor integration and learning in robotics. Science Advances, 10 Dec 2021; Vol 7, Issue 50 DOI: 10.1126/sciadv.abl5068
Credit: Source link