Artificial nervous system senses light and learns to catch like humans

A straightforward artificial nervous system can mimic just how humans respond to light and learn to perform basic tasks. The principle could be used to create more useful robots and prostheses.

Humans, when confronted by external stimuli such as for example light or heat, can react rapidly and automatically – think about how precisely your hand withdraws from a hot surface, or how your leg flicks up when tapped on the knee. These are unconscious responses. But conscious responses, such as catching a ball, should be honed by repeated stimulation.

Researchers at three universities in South Korea are suffering from an artificial system with the capacity of simulating a conscious response to external stimuli. It contains a photodiode – which converts light into an electrical signal, a transistor acting as a mechanical synapse, an artificial neuron circuit, which acts as the system’s brain, and a robotic hand.

When the photodiode detects light, it sends an electrical signal through the transistor that the light is on. That signal is carried to the artificial neuron circuit. There, the message is received, and that circuit then learns how to react to the signal, sending a command to a robotic hand it controls.

As well as the light is turned on, starting the complete process off at the photodiode, a ball is dropped from above the hand. The theory is for the contraption to figure out how to cup the hand quickly enough to catch the ball.

The process is similar to just how our eye transmits electrical signals via synapses to your brain, which in turn translates those signals, decides on a course of action and sends a command to muscles to go – all within a fraction of another.

In the first stages of the experiment, the mind of the machine was slow to translate the light signal right into a decision to cup the hand. Before “learning” how exactly to react, the system took 2.56 seconds to get this done. After it turned out exposed repeatedly to the light signal and allowed time to process how to proceed, this decreased to 0.23 seconds. The researchers say the artificial neural system is imitating something like a conscious biological response.

The machine isn’t the first ever to make an effort to mimic the biological response humans need to external stimuli. A paper in 2018 detailed attempts to recreate sensory neurons within skin, while a 2019 paper focused on the development of artificial synapses. Among the authors of this paper even used an artificial nervous system to control cockroach limb movement.

Among the goals of this sort of research is to help people with neurological conditions regain control of organs and limbs that they can’t control as quickly as before.

“The operation of the device shows great promise, especially in human assistance tasks, or in training robotic systems predicated on human movement,” says Jonathan Aitken at the University of Sheffield, UK.

Aitken believes the machine could be coupled with wearables tracking how persons move to create robots trained to behave in an identical fashion. It could, for example, allow robots to accomplish manual tasks that require responding to external circumstances.

Journal reference: Science Advances , DOI: 10.1126/sciadv.abe3996

More on these topics:

  • robots

Leave a Reply

Your email address will not be published.