Improving Autonomous Nano-Drones Performance via Automated End-to-End Optimization and Deployment of DNNs
- 8 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 11 (4) , 548-562
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-10cm 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 (Palossi et al. , 2019), 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 $2\times $ reduction of memory footprint and a speedup of $1.6\times $ 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 1.65m/s and improving the speed/braking-space ratio of the baseline, ii ) free flight in a familiar environment up to 1.96m/s (0.5m/s for the baseline), and iii ) lane following on a path featuring a 90deg 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.
Keywords
All Related Versions
Funding Information
- Autonomous Robotics Research (ARR) Center of the United Arab Emirates (UAE) Technology Innovation Institute
This publication has 35 references indexed in Scilit:
- Special Issue on High‐Speed Vision‐Based Autonomous Navigation of UAVsJournal of Field Robotics, 2017
- weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart FarmingIEEE Robotics and Automation Letters, 2017
- Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness2017
- Precise, Energy-Efficient Data Acquisition Architecture for Monitoring Radioactivity Using Self-Sustainable Wireless Sensor NodesIEEE Sensors Journal, 2017
- Ultra low-power visual odometry for nano-scale unmanned aerial vehicles2017
- Near-Threshold RISC-V Core With DSP Extensions for Scalable IoT Endpoint DevicesIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017
- RocketLogger2016
- Progress on “Pico” Air Vehicles2016
- Deep Residual Learning for Image Recognition2016
- Enabling the Heterogeneous Accelerator Model on Ultra-Low Power Microcontroller Platforms2016