We present an insect-inspired visual teach-and-repeat framework demonstrated on Antflie, a 33-gram MAV equipped with an ultra-low-resolution camera (24× 24 px) and a narrow 87% field of view (FoV). During a one-shot teach flight along an outbound route, the MAV performs periodic physical scans and uses a local compass based on inertial and optic flow cues to categorize views as left or right relative to the path, storing compact, lateralized visual memories in a Mushroom Body (MB) neural network with a footprint under 4 kB. In the repeat phase, the MAV flies the inbound route by retracing the outbound path, and autonomously lands at its home location using only visual familiarity through direct sensorimotor coupling, rather than map-based reasoning. Offline simulations show that the Route Lateralized (R-Lat) algorithm in Antflie matches the accuracy of a state-of-the-art insect visual compass (V-Comp) while running up to 20× faster and supporting narrow FoVs. Real-world indoor experiments further demonstrate 24 autonomous inbound repeats totaling 110 meters of flight, with a 13-cm median lateral error and a mean landing error of 34 cm. These results highlight the feasibility of frugal, bio-inspired, vision-only navigation for MAVs operating under strict size, weight, power, and cost constraints, inspired by the navigation of Cataglyphis and Melophorus ants.
Gattaux et al. (Thu,) studied this question.