In the never-ending quest to make smarter robots, researchers at two United Kingdom universities have commenced on a project to harness some of the very clever attributes of the humble honeybee. Scientists at Sheffield and Sussex Universities intend to construct computer models of how a honeybee’s brain works in an attempt to increase our understanding and implementation of artificial intelligence.
What’s so clever about honeybees? Well, they are smart enough to fly distances of up to seven miles from the hive, do some work, and then find their way back—pretty amazing stuff for such a small insect. But, what is its importance, and correlation, to robotics?
Bees have compound eyes and the lenses are polarized. Therefore, in a view of the sky, a bee will experience varying patches of light and dark caused by the polarisation of the sunlight. Bees know the angle of their flight in relation to this polarisation pattern.
They also have an integral clock, which makes them aware of how long they have been in flight. They can even compensate for varying wind directions and strengths. The bee is then able to cleverly reverse all of this data on its homeward journey to ensure it finds its hive.
The research teams plan to build models of the systems that control vision and sense of smell in a bee’s brain. Subsequently, with these models, they will attempt to create the first flying robot able to sense and act as autonomously as a bee, rather than just carry out a pre-programmed set of instructions.
If successful, this project will meet one of the major challenges of modern science: Building a robot brain that can perform complex tasks equally as well as the brain of an animal. The robot will be expected to perform tasks such as finding the source of particular odours or gases in the same way that a bee can identify flowers.
Researchers think that such an artificial brain could eventually be used in applications like search and rescue missions, or possibly the mechanical pollination of crops.
Dr. James Marshall leads the £1 million Engineering and Physical Sciences Research Council funded project in Sheffield. “The development of an artificial brain is one of the greatest challenges in artificial intelligence,” says Marshall. “So far, researchers have typically studied brains such as those of rats, monkeys, and humans, but actually ‘simpler’ organisms such as social insects have surprisingly advanced cognitive abilities.”
The “Green Brain” project is partially supported with hardware donated by NVIDIA Corp. It invites comparison with the IBM-sponsored Blue Brain initiative, which is involved in developing brain modeling technologies using supercomputers with the goal of producing an accurate model of a human brain.
NVIDIA’s hardware is based on high-performance processors called “GPU accelerators,” which generate the 3D graphics on home PCs and game consoles and power some of the world’s highest-performance supercomputers. These accelerators efficiently perform the massive calculations needed to simulate a brain using a standard desktop PC, rather than on a large, expensive supercomputing cluster.
Green Brain’s researchers anticipate that developing a model of a honeybee’s brain will create a more accessible method of understanding the inner workings of a brain’s cognitive systems. Ultimately, it would lead to advances in understanding animal and human cognition.
“Because the honeybee brain is smaller and more accessible than any vertebrate brain,” says Dr. Marshall, “we hope to eventually be able to produce an accurate and complete model that we can test within a flying robot.”
It’s anticipated that this research will pioneer future advances in autonomous flying robots. Furthermore, the computer modeling involved in this process is expected to be used extensively in other brain modeling and computational neuroscience projects.