# Deep Learning on Home Drone: Searching for the Optimal Architecture

arXiv: https://arxiv.org/abs/2209.11064 · HTML: https://mlsanity.com/paper/2209.11064/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 21 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition](https://mlsanity.com/paper/1412.6553/) (2014)
- [A Review on Deep Learning Techniques Applied to Semantic Segmentation](https://mlsanity.com/paper/1704.06857/) (2017)
- [Provable Filter Pruning for Efficient Neural Networks](https://mlsanity.com/paper/1911.07412/) (2019)
- [Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition](https://mlsanity.com/paper/2107.11442/) (2021)
- [Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions](https://mlsanity.com/paper/2209.08554/) (2022)
- [A Unified Approach to Coreset Learning](https://mlsanity.com/paper/2111.03044/) (2021)
- [Lightweight Monocular Depth Estimation through Guided Decoding](https://mlsanity.com/paper/2203.04206/) (2022)
- [Optimizing Grouped Convolutions on Edge Devices](https://mlsanity.com/paper/2006.09791/) (2020)
- [Deep Learning Meets Projective Clustering](https://mlsanity.com/paper/2010.04290/) (2020)
- [Retrain or not retrain? -- efficient pruning methods of deep CNN networks](https://mlsanity.com/paper/2002.07051/) (2020)
- [Run Your Visual-Inertial Odometry on NVIDIA Jetson: Benchmark Tests on a Micro Aerial Vehicle](https://mlsanity.com/paper/2103.01655/) (2021)
- [Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems](https://mlsanity.com/paper/2108.10506/) (2021)
- [Newton-PnP: Real-time Visual Navigation for Autonomous Toy-Drones](https://mlsanity.com/paper/2203.02686/) (2022)

## Built on by (most cited first, 5 of 5)

- [Follow Anything: Open-set detection, tracking, and following in real-time](https://mlsanity.com/paper/2308.05737/) (2023)
- [NavRL: Learning Safe Flight in Dynamic Environments](https://mlsanity.com/paper/2409.15634/) (2024)
- [ORBSLAM3-Enhanced Autonomous Toy Drones: Pioneering Indoor Exploration](https://mlsanity.com/paper/2312.13385/) (2023)
- [Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples](https://mlsanity.com/paper/2510.20800/) (2025)
- [Track Anything Rapter(TAR)](https://mlsanity.com/paper/2405.11655/) (2024)

## Abstract (arXiv)

We suggest the first system that runs real-time semantic segmentation via deep learning on a weak micro-computer such as the Raspberry Pi Zero v2 (whose price was 15) attached to a toy-drone. In particular, since the Raspberry Pi weighs less than 16 grams, and its size is half of a credit card, we could easily attach it to the common commercial DJI Tello toy-drone (<100, <90 grams, 98 × 92.5 × 41 mm). The result is an autonomous drone (no laptop nor human in the loop) that can detect and classify objects in real-time from a video stream of an on-board monocular RGB camera (no GPS or LIDAR sensors). The companion videos demonstrate how this Tello drone scans the lab for people (e.g. for the use of firefighters or security forces) and for an empty parking slot outside the lab. Existing deep learning solutions are either much too slow for real-time computation on such IoT devices, or provide results of impractical quality. Our main challenge was to design a system that takes the best of all worlds among numerous combinations of networks, deep learning platforms/frameworks, compression techniques, and compression ratios. To this end, we provide an efficient searching algorithm that aims to find the optimal combination which results in the best tradeoff between the network running time and its accuracy/performance.