How Scientists Are Using Locusts to Make Self-Driving Cars Safer Than Ever Before

Engineers have recently discovered how locusts will be able to help make self-driving cars safer. Saptarshi Das, an Assistant Professor of Engineering, Science & Mechanics at Penn State University, and other researchers built their collision detector based on what they learned after examining how locusts avoided bumping into each other.

See, it turns out that locusts aren't just single minded eating machines. They have a single neuron called the lobula giant movement detector (LGMD), according to Monday's issue of the online journal, Nature Electronics. The LGMD is how the short-horned grasshopper prevents itself from getting into a collision with other locusts. Das and his team have built a nanoscale collision detector that works in the same way as the escape response of an LGMD neuron.

Das and his colleagues wrote, "We believe that our in-memory task-specific computing and sensing approach can potentially lead to the development of low-cost, energy- and area-efficient collision avoidance systems for applications in robotics and autonomous vehicle designs."

Collisions detectors aren't something new, but this locust-inspired tech may have them beat. Current detectors within self-driving cars happen to be large and heavy. The molybdenum sulfide-based photodetector is small and uses only a small amount of energy to complete its specific task.

Car
A photo taken on May 28, 2020 shows a Rideflux 'self-driving' car in Jeju. Getty/ED JONES/AFP

So how exactly does it work? Well, when a locust spots an incoming locust, the image of the approaching insect becomes larger. When the excitation signal increases, the locust changes its speed and avoids colliding with the other locust.

"Because the neuron has two branches, the locust computes the changes in these two inputs and realizes that something is going to collide. So the avoiding locust changes direction," said Darsith Jayachandran, Das' team member.

"We are always looking for animals with unusual abilities, ones that do something better than humans. Insect vision is something people use regularly to design automatic systems because they fly and don't collide, but then we found locusts are unique," said Das.

"While locusts can only avoid collisions with other locusts, our device can detect potential collisions of a variety of objects at varying speeds," added Das.

As for the team's next steps, Das told Newsweek, "We are now trying to optimize the design, and explore collision avoidance in 3D space, for objects moving with a wide range of speeds."

When asked about having their work published, Das also said to Newsweek, "It is always a great feeling to share your research success with peers as well as a wide range of audience, motivated and growing science lovers."