New tracking technology reveals hidden foraging lives of desert ants

Groundbreaking tracking technology that has revealed new insights into how desert ants navigate their complex world could inspire the next generation of smart, efficient robots.

An international research collaboration involving the University of Sheffield has developed new tracking technology that uses computer vision – a field of computer science that programs computers to interpret and understand images and videos – to track individual desert ants throughout their foraging lives. This tool documents an ant’s journey from the time it leaves its nest until it returns to its colony in search of food.

Their new dataset revealed that ants learn incredibly quickly—remembering their routes home after only one successful trip. But interestingly, their external pathways evolved over time indicating different strategies for exploitation versus exploration. The high-precision data also revealed an underlying oscillatory movement invisible to the human eye, which may explain how ants generate complex search patterns to adapt to current conditions.

The new software works across animal species and uses video captured using standard cameras, is already being adopted by numerous international research groups, and is ideally suited for citizen science projects. The high-precision data collected is crucial to understanding how the brain can guide animals in their complex worlds, which could inspire a new generation of bioinspired robots.

Senior Lecturer in Machine Learning and Robotics in the University’s Department of Computer Science Dr. New technology and dataset produced by Michael Mangan, Lars Halk and Benjamin Risse of the University of Münster, with Antoine Wistrach and Leo Clement of the Center for Integrative. Toulouse and Barbara Webb of the University of Edinburgh show in a new study published in the journal Biology – Science Advances.

The study describes how CATER (Combined Animal Tracking and Environment Reconstruction) uses artificial intelligence and computer vision to track the insect’s position in video captured using off-the-shelf cameras. The system can also detect small objects hard to see by eye, and is robust to background clutter, obstacles and shadows allowing it to function in an animal’s natural habitat where other systems fail.

Dr. is a senior lecturer in machine learning and robotics at the University of Sheffield. Michael Mangan said, “We got this data during a summer field trip, but it took 10 years to build a system capable of extracting the data, so you could say it was a decade in the making.

“I have always been fascinated by how these insects can navigate long distances – up to 1km – in such restricted landscapes where temperatures exceed 50 degrees Celsius.

“Until now, desert ants have been tracked by hand using pen and paper, which involves creating a grid on the ground with string and stakes and monitoring their behavior within the grid. Another method used to get around this is differential global tracking. is using a positioning system (GPS)—but the equipment is expensive and less precise.

“The lack of a low-cost, robust way to capture specific insect paths in the field has created a gap in our knowledge about the behavior of desert ants. In particular, how they learn visual paths, how quickly they do so, and what strategies they adopt. He can make the task easier.”

CATER’s new visual tracking method addresses these challenges by capturing high-resolution footage of ants in their natural environment and using imaging technology to identify individual ants based on motion alone. An innovative image mosaicing technique is used to reconstruct or stitch together the landscape from high resolution imagery. This new approach bridges the gap between field and laboratory studies by providing unique insights into the navigational behavior of ants. Such data will be crucial in explaining how animals with brains smaller than a pinhead navigate their complex environments so efficiently.

Such insights are already being turned into commercial products by Sheffield spin-out company Opteran, who are reverse engineering insect brains to produce extremely robust autonomy using low-cost sensors and computing.

Dr. Mangan said, “Desert ants are the ideal inspiration for the next generation of robots—they navigate long distances in harsh environments and don’t rely on pheromone trails like other ants or GPS and 5G like current robots.

“We hope our tool will allow us to build a more complete picture of how insects learn to pilot through their habitat, bring new scientific knowledge and inform engineers on how they can create similarly capable artificial systems.”