Microbots Swimmers Increase Speed with Artificial Intelligence

Recent studies show that machine learning could assist tiny microbots swim through fluid and reach their goal without getting knocked off course by random movement of particles on their journey.

Microbotic ‘swimmers’ are usually designed to copy the manner bacteria propels themselves through a fluid, but bacteria has one edge over the robots.

‘A real bacterium can sense where to go and decide that it goes in that direction because it wants food’, says Frank Cichos at the University of Leipzig, Germany.

It is tasking for the microbots to stay on course because their miniscule size means that they are buffeted by particles in the fluid. And unlike actual bacteria, they are unable to correct their direction of travel, so they follow a random path described by Brownian motion.

Cichos and his team gave their microbot swimmers a ‘brain’— a machine learning algorithm which rewards ‘good’ movements in the direction of a desired target.

‘We decided it would be good to combine [the swimming microbots] with machine learning, which is a bit like what we do in life’, says Cichos. ‘We experience our environment and depending on the success of what we do, we keep that in memory or not.’

The microbot is a blob of melamine resin, with gold nanoparticles covering 30% of its surface. Directing a narrow laser beam on one point on the microbot’s surface heats the gold nanoparticles there, and the temperature difference drives the microbots through the fluid.

The machine learning algorithm operates on a nearby computer. It tracks the robot’s movement and gives instructions for the laser to fire at a specific point on its surface to get closer to its goal.

If the instruction moves the microbot closer to its goal, the algorithm is rewarded. If it moves it further, the algorithm gets a penalty. As time passes, the algorithm learns from its rewards and penalties which instructions are most effective in getting the microbot to its target swiftly and most efficiently.

After 7 hours of training, the system was able to reduce the amount of instruction needed for the microbot to reach its goal from 600 to 100.

‘The study of the movement of microscopic living organisms is important across a variety of the biological and biomedical sciences’, says Jonathan Aitken at the University of Sheffield, UK. ‘The movement of these microscopic organisms is difficult to mimic, yet this mimicry is important to understand more about their properties, and their effect within the environment.’

Although the controlling system for the swimmers is situated outside the microbots for now, Cichos has plans for introducing chemically powered signaling so the microbots can ‘think’ for themselves.

By Marvellous Iwendi.

Source: New Scientist