Video | Business Headlines | Internet | Science | Scientific Ethics | Technology | Search

 

Artificial Intelligence Resolves Riddle Of Animal Swirling

A group of Skoltech scientists — PhD student Egor Nuzhin, Assistant Professor Maxim Panov, and Professor Nikolay Brilliantov — applied artificial intelligence methods to explain an enigmatic natural phenomenon: animal swirling. While AI has already proved its outstanding performance in a wide range of applied problems and engineering environments, the new study published in Science Reports demonstrates another facet of AI: its ability to solve fundamental problems, in this case, understand the collective behavior of living beings.

Swirling is observed in large groups of animals at different evolution stages, ranging from fish to insects — the creatures move coherently around the common center of a group. The biological function of this bizarre behavior has long since puzzled evolutionary biologists and systems scientists.

Figure 1. Swirling of ants. Credit: Egor Nuzhin et al./Scientific Reports

The conventional approach to explaining swirling assumes artificial forces acting between animals, which move together subject to these forces. In contrast to this, the Skoltech researchers proposed an aim-centered model. It is formulated in terms of reinforcement learning, a powerful tool in the AI toolkit.

Based on simple rules and natural restrictions, the beasts in the simulations learned, by trial and error, to achieve the goal of moving together. Namely, they strived to maintain certain distances between each other and to the center of the pack. Surprisingly, this resulted in spontaneous swirling. Even more strikingly, swirling turned out to be essential for survival: It helped the animals resist hazardous external forces such as wind or underwater flows. A group trained for swirling could resist them hundreds of times more effectively than an untrained one.

Figure 2. Optimal grouping for six, seven, and eight birds. Note the asymmetric patterns for odd numbers. While the depicted arrangements minimize energy expenditure, additional factors may be at play in a natural setting, such as protection from predators. Credit: Egor Nuzhin et al./Scientific Reports

Another interesting application of AI in this context is the grouping of animals. Birds migrate in flocks, fish assemble in schools, wolves hunt in packs, etc. Moving together, with an optimal mutual location, could be very beneficial, as it leads to motion with minimal effort. Applying the same aim-centered approach, together with reinforcement learning, the team demonstrated that the animals were able to find the most efficient patterns of locomotion. Those were the linear arrangement for a group of two, triangles for a group of three, a rhombus for a group of four. These and other, sometimes unexpected patterns for larger groups, were found by another independent method, which additionally validates the RL-based approach.

“Realizing full well that everything is built of elementary ‘building blocks of mathematics,’ I can’t seem to stop being astonished by the power of AI methods,” Professor Brilliantov concluded.

© Scoop Media

 
 
 
Business Headlines | Sci-Tech Headlines

 


MPI: Dry Autumn In Waikato And South Auckland Leads To Drought Classification Drought conditions affecting the primary sector in the Waikato and South Auckland were today classified as a medium-scale adverse event, enabling a package of support for farmers and growers... More>>



Commerce Commission: Invites Feedback On Its Initial Views Of Wellington Airport’s Pricing Decisions

The Commerce Commission is inviting feedback on its initial views, released today, about Wellington Airport’s pricing decisions for specified airport services, such as aircraft parking or airfield and passenger terminal charges, for the period 1 April 2019 to 31 March 2024... More>>



Government: Lower Card Fees On Way For Business, Consumers

A Bill to help lower the fees charged when credit and debit transactions are made, will save New Zealand businesses around $74 million a year... More>>



Barfoot & Thompson: Rents Up By Around 3% In Most Areas

The average weekly rent paid for homes in most areas of Auckland has risen by around 3 percent year-on-year. The figures for end March from more than 16,000 properties... More>>


DoC: Smeagol The ‘Gravel Maggot’ Leaves Its Rare Mark On The Remote West Coast
An extremely rare species of sea slug or ‘gravel maggot’ has been detected for the first time on a remote beach in South Westland... More>>



Immigration: Annual Net Migration Loss Of 7,300

The provisional net loss of 7,300 people in the year ended March 2022 was the lowest net migration for a March year since 2012, Stats NZ said today... More>>