Related papers: Improving Autonomous Nano-drones Performance via Automated End-to-End Optimization and Deployment of DNNs

Improving Autonomous Nano-drones Performance via Automated End-to-End Optimization and Deployment of DNNs

URL: http://arxiv.org/abs/2607.12593v1
Date: Tue, 14 Jul 2026 10:12:15 GMT
Title: Improving Autonomous Nano-drones Performance via Automated End-to-End Optimization and Deployment of DNNs
Abstract summary: We focus on the deployment of PULP-Dronet, a state-of-the-art CNN for autonomous navigation of nano-UAVs.<n>Compared to the original hand-crafted CNN, our results show a 2x reduction of memory footprint and a speedup of 1.6x in inference time.<n>To foster new applications and future research, we open-source all the software design in a ready-to-run project compatible with the Crazyflie 2.1.
Score: 16.339855473306475
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: The evolution of energy-efficient ultra-low-power (ULP) parallel processors and the diffusion of convolutional neural networks (CNNs) are fueling the advent of autonomous driving nano-sized unmanned aerial vehicles (UAVs). These sub-10 cm robotic platforms are envisioned as next-generation ubiquitous smart-sensors and unobtrusive robotic-helpers. However, the limited computational/memory resources available aboard nano-UAVs introduce the challenge of minimizing and optimizing vision-based CNNs -- which to date require error-prone, labor-intensive iterative development flows. This work explores methodologies and software tools to streamline and automate all the deployment of vision-based CNN navigation on a ULP multicore system-on-chip acting as a mission computer on a Crazyflie 2.1 nano-UAV. We focus on the deployment of PULP-Dronet, a state-of-the-art CNN for autonomous navigation of nano-UAVs, from the initial training to the final closed-loop evaluation. Compared to the original hand-crafted CNN, our results show a 2x reduction of memory footprint and a speedup of 1.6x in inference time while guaranteeing the same prediction accuracy and significantly improving the behavior in the field, achieving: i) obstacle avoidance with a peak braking-speed of 1.65 m/s and improving the speed/braking-space ratio of the baseline, ii) free flight in a familiar environment up to 1.96 m/s (0.5 m/s for the baseline), and iii) lane following on a path featuring a 90 deg turn -- all while using for computation less than 1.6% of the drone's power budget. To foster new applications and future research, we open-source all the software design in a ready-to-run project compatible with the Crazyflie 2.1

Related papers

Fast Human Attention Prediction for Fixation-guided Active Perception in Autonomous Navigation [10.364779390403337]
We introduce GazeLNN, a lightweight,scanpath prediction model.<n> operating auto-regressively, the architecture predicts sequential fixation heatmaps.<n>It achieves state-of-the-art performance on the MIT Low Resolution dataset.
arXiv Detail & Related papers (2026-06-18T17:08:06Z)
NanoCockpit: Performance-optimized Application Framework for AI-based Autonomous Nanorobotics [50.594459728605734]
Small form factor, i.e., a few 10s grams, severely limits onboard computational resources to sub-SI100milliwatt microcontroller units (MCUs)<n>Our framework achieves ideal end-to-end latency, i.e. zero overhead due to serialized tasks, delivering quantifiable improvements in closed-loop control performance.
arXiv Detail & Related papers (2026-01-12T12:29:38Z)
AI and Vision based Autonomous Navigation of Nano-Drones in Partially-Known Environments [8.595976385391896]
This work focuses on enabling the safe and autonomous flight of a pocket-size, 30-gram platform called Crazyflie 2.1.<n>We propose a novel AI-aided, vision-based reactive planning method for obstacle avoidance under the ambit of Integrated Sensing, Computing and Communication paradigm.<n>We show the ability to command the drone at $sim8$ frames-per-second and a model performance reaching a COCO mean-average-precision of $60.8$.
arXiv Detail & Related papers (2025-05-08T06:16:36Z)
An Efficient Ground-aerial Transportation System for Pest Control Enabled by AI-based Autonomous Nano-UAVs [45.07031440932014]
We design, fine-tune, and optimize a tiny image-based convolutional neural network (CNN) for pest detection.<n>Our CNN runs in real-time at 6.8 frame/s, requiring 33 mW on a GWT GAP9 System-on-Chip aboard a Crazyflie nano-UAV.<n>In this scenario, our efficient transportation system, compared to a traditional single-ground vehicle performing both inspection and treatment, can save up to 20 h working time.
arXiv Detail & Related papers (2025-02-20T11:14:55Z)
Generative Diffusion-based Contract Design for Efficient AI Twins Migration in Vehicular Embodied AI Networks [55.15079732226397]
Embodied AI is a rapidly advancing field that bridges the gap between cyberspace and physical space. In VEANET, embodied AI twins act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving.
arXiv Detail & Related papers (2024-10-02T02:20:42Z)
On-device Self-supervised Learning of Visual Perception Tasks aboard Hardware-limited Nano-quadrotors [53.59319391812798]
Sub-SI50gram nano-drones are gaining momentum in both academia and industry. Their most compelling applications rely on onboard deep learning models for perception. When deployed in unknown environments, these models often underperform due to domain shift. We propose for the first time, on-device learning aboard nano-drones, where the first part of the in-field mission is dedicated to self-supervised fine-tuning.
arXiv Detail & Related papers (2024-03-06T22:04:14Z)
Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones [9.806742394395322]
Miniaturized unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. This work proposes a new automatic optimization pipeline for visual pose estimation tasks using Deep Neural Networks (DNNs) Our results improve the state-of-the-art reducing inference latency by up to 3.22x at iso-error.
arXiv Detail & Related papers (2024-02-23T11:35:57Z)
Ultra-low Power Deep Learning-based Monocular Relative Localization Onboard Nano-quadrotors [64.68349896377629]
This work presents a novel autonomous end-to-end system that addresses the monocular relative localization, through deep neural networks (DNNs), of two peer nano-drones. To cope with the ultra-constrained nano-drone platform, we propose a vertically-integrated framework, including dataset augmentation, quantization, and system optimizations. Experimental results show that our DNN can precisely localize a 10cm-size target nano-drone by employing only low-resolution monochrome images, up to 2m distance.
arXiv Detail & Related papers (2023-03-03T14:14:08Z)
Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs [69.19616451596342]
Miniaturized unmanned aerial vehicles (UAVs) are an emerging and trending topic. We leverage a novel neural architecture search (NAS) technique to automatically identify several convolutional neural networks (CNNs) for a visual pose estimation task. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of 10Hz@10mW and 50Hz@90mW.
arXiv Detail & Related papers (2023-03-03T14:02:09Z)
Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
"smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
arXiv Detail & Related papers (2022-09-27T15:04:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.