Creating an insect-inspired autonomous robot navigation strategy

Advantages of tiny robots

Tiny robots, weighing from tens to a few hundred grams, offer several practical applications. Their lightweight ensures safety even in the event of accidental collisions. Their small size allows them to manoeuvre through narrow spaces. If they can be produced cost-effectively, they could be deployed in large numbers to quickly cover extensive areas, such as greenhouses for early pest or disease detection. However, enabling these small robots to operate autonomously presents a significant challenge due to their limited resources compared to larger robots.

A key hurdle is autonomous navigation. While these robots can use external infrastructure like GPS outdoors or wireless beacons indoors, relying on such infrastructure is often impractical. GPS is unreliable indoors and in cluttered environments like urban areas. Installing and maintaining indoor beacons is expensive and sometimes infeasible, especially in scenarios like search-and-rescue missions.

Existing AI for autonomous navigation has been designed for larger robots, such as self-driving cars, which use heavy, power-intensive sensors like LiDAR. These sensors are unsuitable for small robots. Vision-based approaches, while power-efficient and rich in information, typically require creating detailed 3D maps. This demands substantial processing power and memory, which small robots lack.

Nature-inspired solutions

To address these challenges, some researchers have turned to nature. Insects, which navigate effectively using limited sensing and computing resources, offer valuable insights. Biologists have learned that insects combine motion tracking ("odometry") with visually guided behaviours based on a low-resolution, wide-field visual system ("view memory"). While odometry is well understood, the mechanisms of view memory are still being studied. One theory, the "snapshot" model, suggests that insects like ants take occasional snapshots of their environment. Later, they compare their current view to the snapshot and adjust their path to minimise differences, helping them return to the snapshot location and correct any drift from odometry.

Tom van Dijk, the study's first author, explained: “Snapshot-based navigation can be compared to how Hansel tried not to get lost in the fairy tale of Hansel and Gretel. When Hans threw stones on the ground, he could get back home. However, when he threw breadcrumbs that were eaten by the birds, Hans and Gretel got lost. In our case, the stones are the snapshots. As with a stone, for a snapshot to work, the robot has to be close enough to the snapshot location. If the visual surroundings get too different from that at the snapshot location, the robot may move in the wrong direction and never get back anymore. Hence, one has to use enough snapshots – or in the case of Hansel, drop a sufficient number of stones. On the other hand, dropping stones too close to each other would deplete Hans’ stones too quickly. In the case of a robot, using too many snapshots leads to large memory consumption. Previous works in this field typically had the snapshots very close together, so that the robot could first visually home to one snapshot and then to the next.”

Guido de Croon, Full Professor in bio-inspired drones and co-author of the article, added: “The main insight underlying our strategy is that you can space snapshots much further apart if the robot travels between snapshots based on odometry. Homing will work as long as the robot ends up close enough to the snapshot location, i.e., as long as the robot’s odometry drift falls within the snapshot’s catchment area. This also allows the robot to travel much further, as the robot flies much slower when homing to a snapshot than when flying from one snapshot to the next based on odometry.”

This insect-inspired navigation strategy enabled a 56-gram “CrazyFlie” drone, equipped with an omnidirectional camera, to cover distances of up to 100 metres using only 1.16kB of memory. All visual processing occurred on a tiny micro-controller, commonly found in inexpensive electronic devices.

Real-world applications

Guido de Croon commented: “The proposed insect-inspired navigation strategy is an important step towards applying tiny autonomous robots in the real world. The functionality of the proposed strategy is more limited than state-of-the-art navigation methods. It does not generate a map and only allows the robot to return to the starting point. Still, for many applications, this may be sufficient. For instance, for stock tracking in warehouses or crop monitoring in greenhouses, drones could fly out, gather data, and then return to the base station. They could store mission-relevant images on a small SD card for post-processing by a server, but they would not need them for navigation itself.”