Researchers are training a robotic dog to fight invasive fire ants

A multidisciplinary research team based in China and Brazil has used a dog-like robot and AI to create a new way to find fire ant nests. Published in the magazine Pest Management Sciencethe study highlights how a “CyberDog” robot integrated with an AI model can automate the identification and control of Red Imported Fire Ants (RIFA), a globally destructive pest.

Field tests conducted by the researchers show that the robotic system can significantly outperform human inspectors, identifying three times more RIFA nests with greater precision. Eduardo Fox, postdoctoral researcher at the State University of Goiás in Brazil, and corresponding author of the study explained the motivation behind this approach to pest management.

“Fire ant nests are difficult for untrained personnel to identify and confirm in the field, and searching large areas can be time-consuming and exhausting under the hot sun. A robot could automatically locate the nests without requiring specially trained individuals and operate on different times of day regardless of temperature conditions,” Fox said

Control an invasive species

RIFA is one of the most destructive pests worldwide. Accidentally introduced to the United States in the 1930s, they have since spread as an invasive organism across numerous areas including China, Japan and Europe, causing extensive environmental damage and economic losses.

Discussing the importance of detecting RIFA nests, Fox noted, “RIFA proliferate rapidly in established areas, displacing local fauna and flora by out-competing and eliminating susceptible species. Small vertebrates, such as birds and reptiles, are particularly vulnerable. In addition, RIFA associates with important agricultural pests such as mealybugs and can damage some plants, exposing them to pathogens.”

Conventional approaches to controlling RIFA populations involve the use of pesticides, with the risk of damaging local ecosystems. To implement effective and targeted RIFA control strategies that minimize damage to native species, comprehensive monitoring of populations is essential.

Training the dog

The team used Xiaomi’s CyberDog robot, and integrated it with a machine learning model trained on an extensive dataset of more than 1,100 RIFA nest images. This approach resulted in a nest detection precision rate of over 90%.

They conducted rigorous field tests to measure the effectiveness of the system. The CyberDog was programmed to push the nest with its front leg: if a fire ant nest mound is disturbed, the workers rush out of cracks and openings with aggressive behavior. This, the researchers said, is key to diagnosing active mounds from abandoned nests, and to avoiding false positives with mounds inhabited by other species.

Hualong Qiu, a researcher at the Guangdong Academy of Forestry in China, and corresponding author of the study explained: “A group of students received official standard training for quarantine inspectors and were tasked with locating fire ant nests in an open field. Subsequently, the AI ​​-trained robot was challenged with the same field, and the performance of the students and the robot were compared.”

Despite the promising results, the researchers acknowledge several challenges in scaling up the technology.

“The primary limitations to scaling up the use of robots are their battery autonomy, which lasts about 30 minutes, and the high cost of acquiring more agile and efficient models,” said Zheng Yan, a researcher at Lanzhou University in China and corresponding author of the study.

“At the moment it is still more expensive using the robotic system than through the traditional approach, but we believe that production costs can optimize this over time,” he said.

The findings of the study could have a significant impact on pest control policies and public awareness.

“In addition to being versatile machines for navigating urban environments, robot dogs attract a lot of public attention. Fire ants pose a serious threat in China, but most people remain unaware of the dangers of invasive fire ant nests in public areas. Therefore, sightings of robots that follow fire ant nests are likely to captivate the public and raise awareness about the presence of fire ants,” Yan said.

Provided by Society of Chemical Industry