Nvidia GPUs to Help Simulate a Bee's Brain for Flying Robots

The idea is to guide the robot by the senses of vision and smell and eventually aid in search and rescue missions or, as bees do, "mechanical pollination of crops".

Covering the massive computational power of an organic brain is now small feat. For example, IBM recently estimated that the human brain is capable of more than 35 Pflops (the world's fastest supercomputer currently peaks at 20.1 Pflops). So it is not surprising that we should be starting with a brain much smaller. But even a robot with a "Green Brain" that resembles the brain power of a bee will need GPU accelerators - donated to the research project by Nvidia - to perform "the massive calculations needed to simulate a brain using a standard desktop PC – rather than on a large, expensive supercomputing cluster," the scientists leading the project at the University of Sheffield said.

The researchers hope that the project will expand our understanding of brain modeling, computational neuroscience projects, as well as the honey bee itself.

"Green Brain's modeling could help scientists to understand why honey bee numbers are dwindling and also contribute to the development of artificial pollinators, such as those being researched by the National Science Foundation-funded Robobees project, led by Harvard University," the scientists said.