Drone researchers from TU Delft have been inspired by biological research into how ants visually recognize their surroundings and carefully count their steps to get home safely. Armed with this insight created they developed an insect-inspired autonomous navigation strategy for small, lightweight robots. With this strategy, these robots can simply return home after a long journey, and with very little processing power and memory (1.16 kilobytes per 100 m).
In the future, tiny autonomous robots could be used for a wide range of applications, from keeping track of inventory in warehouses to detecting gas leaks in industry. The researchers published their findings in Science Robotics on July 17, 2024.
Small robots, weighing from tens to a few hundred grams, have many interesting practical applications. Their light weight makes them extremely safe, even if they accidentally bump into someone. And thanks to their small size, they are also not afraid of small spaces.
The biggest obstacle is that these types of robots need to be able to navigate themselves to perform their tasks. To solve this problem, the robots can get help from external infrastructure. For example, they can use GPS satellites outside or wireless communication beacons inside. However, it is often not desirable to be dependent on such infrastructure: inside you have no GPS, and in densely built-up areas such as modern cities between tall buildings it is often quite inaccurate. The alternative of installing and maintaining beacons is, on the other hand, quite expensive or simply not possible, for example in rescue operations.
The AI that is typically used for autonomous navigation with sensors and processing power on the robot itself is originally designed for large robots, such as self-driving cars. These approaches rely on heavy, power-hungry sensors such as LiDAR rangefinders, which cannot even be carried by small robots. Another option is to use a very power-efficient vision sensor that provides rich information about the environment as the basis for very detailed 3D maps. However, this requires a lot of processing power and memory, and the associated computing equipment is too large and power-hungry for such small robots.
The proposed insect-inspired navigation strategy allowed a 56-gram CrazyFlie drone equipped with an omnidirectional camera to travel distances of up to 100 meters with only 1.16 KB of memory. All computations were done on a tiny computer, called a microcontroller, which is found in many low-cost electronic devices.
Source: www.emerce.nl
