Roboticists already have developed a robot that runs like a cheetah and one that moves like an earthworm. Now engineers in the UK are trying to create artificial intelligence that will power a flying robot that can think like a honey bee.
The Green Brain project, out of the Universities of Sheffield and Sussex, is working on the production of the first computer models of the brain of a honey bee, particularly the systems that control vision and sense of smell, according to researchers.
Using this artificial intelligence, scientists plan to develop a flying robot that can act autonomously as a bee would, rather than be programmed to carry out movements and actions. The robot will be used in further research to help solve the tricky problem of creating a true artificial brain that can actually think for itself, rather than perform tasks via programmed software, according to scientists.
While researchers have tried to do this by studying brains of more complex organisms, such as rats and monkeys, Project Green Brain's scientists think focusing on simpler yet social creatures like honey bees could garner more success, according to the project’s leader, Dr. James Marshall of the University of Sheffield. "The development of an artificial brain is one of the greatest challenges in artificial intelligence,” Marshall said in a press release. “Because the honey bee brain is smaller and more accessible than any vertebrate brain, we hope to eventually be able to produce an accurate and complete model that we can test within a flying robot.”
Once this artificial intelligence is developed, scientists expect to accelerate the development of new advancements in autonomous flying robots, said Dr. Thomas Nowotny, the leader of the University of Sussex team, in the press release. The project also could have future applications in brain modeling and computational neuroscience. Additionally, researchers will learn more about honey bees and perhaps glean information about their decline in population in recent years.
The UK Engineering and Physical Sciences Research Council (EPSRC) funded the project, which also is using high-performance processors donated by NVIDIA. The processors -- used to generate 3D graphics on PCs and game consoles, as well as power supercomputers -- will allow scientists to forgo using expensive supercomputers to run their calculation-heavy models and use a less expensive and cumbersome standard PC instead, researchers said.
It really is amazing to me what we can learn from "lower life forms." I was also skeptical but according to one web page (benefits-of-honey.com): The bee's brain is oval in shape and only about the size of a sesame seed, yet it has remarkable capacity to learn and remember things and is able to make complex calculations on distance travelled and foraging efficiency.
And remember - these little guys aren't supposed to be able to fly if you calculate their wingspan to body mass ratio - so they obviously know something we don't!
I always assumed the next great phase of industrialization is genetically engineering machines (based on existing plants/animals) that you would grow with seeds like a crop (and power with biomatter) rather than manufacture in a factory and power on carbon derived energy.
Insects are a perfect starting point, since they are simple enough for us to start understanding their operation and they are already autonomous. This is the perfect first step in this path. Only need to know enough about their operation to replace their original "programming" with ours. Insects are hardly "smart", but they are more than capable of carrying out simple tasks.
Of course, this is also how every sci-fi horror movie starts out.
Never thought about a honey bee's brain as a model for AI. This sounds like the PA university group that demo bees flying in sync with each other around different obstacles.
Honey bees are GREAT models for AI for autonomous flight. Bees explore independently, looking for the best food source. When they come back to the hive, they "dance" to precisely communicate the best path to the abundance. It's fascinating and very complex.
If drones could work together, communicating like bees, they could be more effective and used in benign applications.
Hard to think that the tiny brain of a honey bee could hold so much promise in terms of directing autonomous flight. I would think studying the characteristics of migrating birds would have more impact on AI advances in this area.
Gigabit and PoE are two networking technologies moving ahead in tandem as industrial users power remote Ethernet devices such as IP security cameras at 1,000 Mbps over existing CAT5 cable.
New disc magnet motors fit into the design trend of stepping up to closed loop performance while maintaining the cost advantage of stepper motor technology.
At the Design News webinar on June 27, learn all about aluminum extrusion: designing the right shape so it costs the least, is simplest to manufacture, and best fits the application's structural requirements.
A new battery design, which replaces lithium with abundant and low-cost elemental sulfur, is still in its nascent stages but shows real promise for giving batteries more energy potential.
From Dell / Intel® New Paradigms in Design Work Scott Hamilton, vertical market strategist for Dell Precision workstations, 5/2/2013 5
Early in my career, I worked as a draftsman and remember the days of drawing on vellum with numbered pencils and Mylar with plastic lead. This was a fun experience in the sense that I ...
I've been using workstations for more than 10 years and love finding ways to get more performance from my system. With demanding professional applications that require more power each ...
A lasting memory from my first job as an engineer in an auto assembly plant is standing on hard concrete at six in the morning, vending-machine coffee clutched in hand, listening to ...
For industrial control applications, or even a simple assembly line, that machine can go almost 24/7 without a break. But what happens when the task is a little more complex? That’s where the “smart” machine would come in. The smart machine is one that has some simple (or complex in some cases) processing capability to be able to adapt to changing conditions. Such machines are suited for a host of applications, including automotive, aerospace, defense, medical, computers and electronics, telecommunications, consumer goods, and so on. This radio show will show what’s possible with smart machines, and what tradeoffs need to be made to implement such a solution.
To save this item to your list of favorite Design News content so you can find it later in your Profile page, click the "Save It" button next to the item.
If you found this interesting or useful, please use the links to the services below to share it with other readers. You will need a free account with each service to share an item via that service.
Tweet This
2 
