# FLYNN: Robust Neural Network for Robot Navigation using Fly Brain Topology

arXiv: https://arxiv.org/abs/2607.00025 · HTML: https://mlsanity.com/paper/2607.00025/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 36 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Exploring Randomly Wired Neural Networks for Image Recognition](https://mlsanity.com/paper/1904.01569/) (2019)
- [Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs](https://mlsanity.com/paper/2409.18794/) (2024)
- [Small-World Brain Networks Revisited](https://mlsanity.com/paper/1608.05665/) (2016)
- [Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art](https://mlsanity.com/paper/2503.08695/) (2025)
- [RGB cameras failures and their effects in autonomous driving applications](https://mlsanity.com/paper/2008.05938/) (2020)
- [Generating Out-Of-Distribution Scenarios Using Language Models](https://mlsanity.com/paper/2411.16554/) (2024)
- [Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?](https://mlsanity.com/paper/2409.10775/) (2024)
- [MisConv: Convolutional Neural Networks for Missing Data](https://mlsanity.com/paper/2110.14010/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks](https://mlsanity.com/paper/2610.10014/) (2026)

## Abstract (arXiv)

While deep learning models achieve state-of-the-art performance in complex tasks, they remain brittle when faced with new environments or sensory deprivation. In contrast, biological systems exhibit remarkable tolerance to these challenges. We address this vulnerability by developing a recurrent neural network (RNN) whose architecture is directly derived from the synaptic-resolution brain connectome of the fruit fly Drosophila melanogaster. We demonstrate the feasibility of training the fly connectome neural network (FLYNN) to perform vision-based navigation in MuJoCo, achieving performance comparable to modern hand-crafted networks of similar parameter counts. Crucially, FLYNN exhibits superior resistance to out-of-distribution (OOD) data and tolerance to sensory loss without further training. It remained functional even under total vision loss while hand-crafted networks largely failed, even when specifically trained with camera dropout. Principal Component Analysis (PCA) of the internal state of FLYNN suggests that it exhibits a particularly high degree of representational modularity, which might be related to its robustness. Our work provides a new direction for designing resilient artificial agents following the topology of biological brains.