# A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones

arXiv: https://arxiv.org/abs/1805.01831 · HTML: https://mlsanity.com/paper/1805.01831/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2018.

## Built on by (most cited first, 23 of 23)

- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Event-driven Vision and Control for UAVs on a Neuromorphic Chip](https://mlsanity.com/paper/2108.03694/) (2021)
- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices](https://mlsanity.com/paper/2101.04446/) (2021)
- [NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcopter](https://mlsanity.com/paper/2209.06918/) (2022)
- [Squeezed Edge YOLO: Onboard Object Detection on Edge Devices](https://mlsanity.com/paper/2312.11716/) (2023)
- [Visual Odometry with Neuromorphic Resonator Networks](https://mlsanity.com/paper/2209.02000/) (2022)
- [Parallelizing Optical Flow Estimation on an Ultra-Low Power RISC-V Cluster for Nano-UAV Navigation](https://mlsanity.com/paper/2305.13055/) (2023)
- [Low Latency Visual Inertial Odometry with On-Sensor Accelerated Optical Flow for Resource-Constrained UAVs](https://mlsanity.com/paper/2406.13345/) (2024)
- [Implementation Of Tiny Machine Learning Models On Arduino 33 BLE For Gesture And Speech Recognition](https://mlsanity.com/paper/2207.12866/) (2022)
- [Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones](https://mlsanity.com/paper/2303.10386/) (2023)
- [CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement](https://mlsanity.com/paper/2304.04222/) (2023)
- [AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs](https://mlsanity.com/paper/2102.02988/) (2021)
- [Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization](https://mlsanity.com/paper/2110.14491/) (2021)
- [Adaptive Subsampling for ROI-based Visual Tracking: Algorithms and FPGA Implementation](https://mlsanity.com/paper/2112.09775/) (2021)
- [Continuously Learning to Detect People on the Fly: A Bio-inspired Visual System for Drones](https://mlsanity.com/paper/2202.08023/) (2022)
- [AI and Vision based Autonomous Navigation of Nano-Drones in Partially-Known Environments](https://mlsanity.com/paper/2505.04972/) (2025)
- [Self-Supervised Learning to Fly using Efficient Semantic Segmentation and Metric Depth Estimation for Low-Cost Autonomous UAVs](https://mlsanity.com/paper/2510.16624/) (2025)
- [Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network](https://mlsanity.com/paper/2602.00076/) (2026)
- [S2Act: Simple Spiking Actor](https://mlsanity.com/paper/2603.15725/) (2026)
- [Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System](https://mlsanity.com/paper/2607.09768/) (2026)
- [Micro Neural Policies for Safe Real-Time Robotic Control](https://mlsanity.com/paper/2610.08541/) (2026)
- [RingNav: Task-Shaped Circular Memory for Visual Heading](https://mlsanity.com/paper/2610.19044/) (2026)

## Abstract (arXiv)

Fully-autonomous miniaturized robots (e.g., drones), with artificial intelligence (AI) based visual navigation capabilities are extremely challenging drivers of Internet-of-Things edge intelligence capabilities. Visual navigation based on AI approaches, such as deep neural networks (DNNs) are becoming pervasive for standard-size drones, but are considered out of reach for nanodrones with size of a few cm2. In this work, we present the first (to the best of our knowledge) demonstration of a navigation engine for autonomous nano-drones capable of closed-loop end-to-end DNN-based visual navigation. To achieve this goal we developed a complete methodology for parallel execution of complex DNNs directly on-bard of resource-constrained milliwatt-scale nodes. Our system is based on GAP8, a novel parallel ultra-low-power computing platform, and a 27 g commercial, open-source CrazyFlie 2.0 nano-quadrotor. As part of our general methodology we discuss the software mapping techniques that enable the state-of-the-art deep convolutional neural network presented in [1] to be fully executed on-board within a strict 6 fps real-time constraint with no compromise in terms of flight results, while all processing is done with only 64 mW on average. Our navigation engine is flexible and can be used to span a wide performance range: at its peak performance corner it achieves 18 fps while still consuming on average just 3.5% of the power envelope of the deployed nano-aircraft.