Reproduce “Towards bio-inspired visual navigation: a neuromorphic navigation paradigm for MAVs” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Junjie Jiang, Ankang Zhou, Zheng Fang

The authors present an end-to-end event-driven navigation pipeline for aerial robots, using an event camera and spiking networks to estimate scene geometry, select waypoints, and generate trajectories. In simulation, spiking and artificial neural network versions show comparable performance. Physical trials reach targets in 7 of 10 indoor and 9 of 10 outdoor attempts, but deployment remains partly conventional.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.