Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs

• URL: http://arxiv.org/abs/2303.01931v1
• Date: Fri, 3 Mar 2023 14:02:09 GMT
• Title: Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs
• Authors: Elia Cereda, Luca Crupi, Matteo Risso, Alessio Burrello, Luca Benini, Alessandro Giusti, Daniele Jahier Pagliari, Daniele Palossi
• Abstract summary: 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.
• Score: 69.19616451596342
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Miniaturized autonomous unmanned aerial vehicles (UAVs) are an emerging and trending topic. With their form factor as big as the palm of one hand, they can reach spots otherwise inaccessible to bigger robots and safely operate in human surroundings. The simple electronics aboard such robots (sub-100mW) make them particularly cheap and attractive but pose significant challenges in enabling onboard sophisticated intelligence. In this work, we leverage a novel neural architecture search (NAS) technique to automatically identify several Pareto-optimal convolutional neural networks (CNNs) for a visual pose estimation task. Our work demonstrates how real-life and field-tested robotics applications can concretely leverage NAS technologies to automatically and efficiently optimize CNNs for the specific hardware constraints of small UAVs. We deploy several NAS-optimized CNNs and run them in closed-loop aboard a 27-g Crazyflie nano-UAV equipped with a parallel ultra-low power System-on-Chip. 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.

Related papers

• Training on the Fly: On-device Self-supervised Learning aboard Nano-drones within 20 mW [52.280742520586756]
  Miniaturized cyber-physical systems (CPSes) powered by tiny machine learning (TinyML), such as nano-drones, are becoming an increasingly attractive technology. Simple electronics make these CPSes inexpensive, but strongly limit the computational, memory, and sensing resources available on board. We present a novel on-device fine-tuning approach that relies only on the limited ultra-low power resources available aboard nano-drones.
  arXiv  Detail & Related papers  (2024-08-06T13:11:36Z)
• Tiny-PULP-Dronets: Squeezing Neural Networks for Faster and Lighter Inference on Multi-Tasking Autonomous Nano-Drones [12.96119439129453]
  This work moves from PULP-Dronet, a State-of-the-Art convolutional neural network for autonomous navigation on nano-drones, to Tiny-PULP-Dronet, a novel methodology to squeeze by more than one order of magnitude model size. This massive reduction paves the way towards affordable multi-tasking on nano-drones, a fundamental requirement for achieving high-level intelligence.
  arXiv  Detail & Related papers  (2024-07-02T16:24:57Z)
• 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)
• DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions [121.05720140641189]
  We develop a family of models with the distilling neural architecture (DNA) techniques. Our proposed DNA models can rate all architecture candidates, as opposed to previous works that can only access a sub- search space using algorithms. Our models achieve state-of-the-art top-1 accuracy of 78.9% and 83.6% on ImageNet for a mobile convolutional network and a small vision transformer, respectively.
  arXiv  Detail & Related papers  (2024-03-02T22:16:47Z)
• 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)
• High-throughput Visual Nano-drone to Nano-drone Relative Localization using Onboard Fully Convolutional Networks [51.23613834703353]
  Relative drone-to-drone localization is a fundamental building block for any swarm operations. We present a vertically integrated system based on a novel vision-based fully convolutional neural network (FCNN) Our model results in an R-squared improvement from 32 to 47% on the horizontal image coordinate and from 18 to 55% on the vertical image coordinate, on a real-world dataset of 30k images.
  arXiv  Detail & Related papers  (2024-02-21T12:34:31Z)
• Adaptive Deep Learning for Efficient Visual Pose Estimation aboard Ultra-low-power Nano-drones [5.382126081742012]
  We present a novel adaptive deep learning-based mechanism for the efficient execution of a vision-based human pose estimation task. On a real-world dataset and the actual nano-drone hardware, our best-performing system shows 28% latency reduction while keeping the same mean absolute error (MAE), 3% MAE reduction while being iso-latency, and the absolute peak performance, i.e., 6% better than SoA model.
  arXiv  Detail & Related papers  (2024-01-26T23:04:26Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.