Researchers have developed an autonomous navigation system for small, lightweight drones inspired by insects.
The team from TU Delft was motivated by biological discoveries about how ants use their ability to see their surroundings and calculate their steps to safely navigate back home.
According to engineers, using this method, robots can cover huge distances and return home with minimal computation and memory (0.65 kB per 100 m).
“In the future, small autonomous robots could find a wide range of uses, from monitoring inventory in warehouses to finding gas leaks in industrial sites,” the researchers said in a statement.
Insect-inspired “slide” navigation
Tiny robots weighing from ten to several hundred grams have significant potential for real-world applications. Their lightweight construction ensures safety even in accidental collisions, and their small size allows them to pass through narrow areas. If produced at an affordable cost, they can be deployed in large numbers and effectively cover large areas such as greenhouses for early detection of pests or diseases.
However, autonomous operation is challenging due to limited resources compared to larger drones. Navigation is particularly problematic. While GPS can aid in outdoor navigation, it is ineffective indoors and inaccurate in crowded environments. Indoor wireless beacons are expensive and impractical in scenarios such as search and rescue.
According to the researchers, most artificial intelligence for autonomous navigation is designed for large robots, using heavy, power-hungry sensors such as LiDAR that are unsuitable for small robots. Vision-based approaches, while energy efficient, require the creation of detailed 3D maps, which requires significant computing power and memory beyond the capacity of small robots.
Researchers have turned to nature and inspired insects to navigate small robots with minimal resources. Insects combine odometry (tracking movement) with visually guided behavior (memory display).
In the “snapshot” model, insects such as ants regularly capture images of their surroundings. As they approach the image, they compare the current visuals, minimize the differences to accurately return to the image and correct the odometry deviation.
Effective internal drone navigation
The DU Helft team adapted previously developed techniques to develop a bioinspired approach. This strategy combines visual guidance, which guides orientation in relation to visual cues in the environment, with odometry, which measures the distance traveled in a certain direction.
The researchers tested their method in several indoor conditions using a 56-gram Crazyflie Brushless drone with a panoramic camera, a microcontroller, and 192 KB of memory.
Initially, the robot took off and flew towards its target, periodically stopping to take pictures of its surroundings. The drone used visual guidance to travel the same path back, periodically correcting its course for drift by comparing its current position with photos of waypoints.
This approach was incredibly memory efficient due to high image compression and precise spacing. All visual processing took place on a small computer called a “microcontroller” that can be found in many inexpensive electronic devices.
According to the team, the proposed strategy is less versatile than state-of-the-art methods, lacking mapping capability, but allows a return to the starting point that is adequate for many applications.
Drones can fly out, collect data, and then return to a base station for applications such as greenhouse crop monitoring and warehouse inventory tracking. Images related to a given target can be saved to a small SD card and later processed by the server. However, they would not require them to use simple navigation.
Details of the team’s study were published in the journal Scientific robotics.
ABOUT THE EDITORIAL
Jijo Malayil Jijo is an automotive and business journalist based in India. Armed with a BA in History (Honours) from St. Stephen’s College, Delhi University and a PG Diploma in Journalism from the Indian Institute of Mass Communication, Delhi, has worked for news agencies, national newspapers and automotive magazines. In his spare time, he likes to go out into the field, engage in political discourse, travel and learn languages.