Dragonfly insect technology used in artificial vision system tests for driverless cars
RESEARCHERS AT the University of Adelaide, Australia, and Lund University in Sweden are studying how a dragonfly tracks its prey in order to improve artificial vision systems for driverless cars.
The way a driverless car sees is a critical part of how it operates. Poor vision makes for a bad driver – that’s a given. Dragonflies have a certain something, a neuron in their brain, and great tracking capabilities, that cars could really learn from.
The researchers favour a ‘hybrid approach’ to visual systems and algorithms, and are keen to take as much from nature as they can. The dragonfly’s ability to chase prey and not bump into things is to be commended, and would make for a perfect driverless car on the UK’s confusing and busy streets.
“It is one thing for artificial systems to be able to see moving targets, but tracing movement so it can move out of the way of those things is a really important aspect to self-steering vehicles,” said research supervisor and lecturer at the University of Adelaide’s Medical School, Steven Wiederman.
“What we found was the neuron in dragonflies not only predicted where a target would reappear, it also traced movement from one eye to the other – even across the brain hemispheres.
“This is also evident in cluttered environments where an object might be difficult to distinguish from the background,” he added.