Scholarlink

<p>The global surge in demand for unmanned aerial vehicles (UAVs), projected to reach $91 billion by 2033, spans diverse applications in urban environments. However, achieving accurate horizontal geo-localization in urban settings remains challenging due to poor GPS performance, creating a significant barrier to effective drone operations, even in static or slow-moving deployments. Recreational-grade GPS systems, commonly used in low Size, Weight and Power (SWaP) UAVs, suffer from residual errors exceeding 100&#xa0;m in urban environments, severely limiting real-time navigation accuracy and drone autonomy. Although capable of good accuracy in conventional aerospace deployments, existing traditional aerospace-ready GPS receivers are expensive, power-intensive, and heavy, making them unsuitable for low SWaP drone deployment. Existing performance-enhancing post-processing techniques for recreational GPS are limited by the real-time requirements and the noise, power, and computational constraints inherent to drone operations. This underscores the critical need for accurate, robust, lightweight, and power-efficient urban localization solutions for UAVs. In this work, we present a hybrid Integrated Recurrent Neural Network–Deep Neural Network (IRNN–DNN) architecture, capable of running on embedded microcontrollers with recreational-grade L1C GPS receivers. Leveraging Long Short-Term Memory (LSTM) networks, the IRNN–DNN model captures temporal dependencies and spatial error patterns across multiple concurrent GPS receivers, allowing real-time error correction. Field tests with MTK3339 GPS receiver on UAVs in static test conditions showed, with a 2D residual error of 1.71&#xa0;m at 10&#xa0;Hz, a 30% improvement over existing models—validate the IRNN–DNN approach as a promising embedded solution for enhancing urban localization performance in constrained UAV applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design and deployment of a hybrid neural network for real-time GPS correction in slow moving, low SWaP, UAV flight systems

  • 期刊论文

  • 发表日期：

    2025年6月29日

查看全文
  • Gokul Nathan,
  • Alperen Cucioglu,
  • Sep Makhsous

摘要

The global surge in demand for unmanned aerial vehicles (UAVs), projected to reach $91 billion by 2033, spans diverse applications in urban environments. However, achieving accurate horizontal geo-localization in urban settings remains challenging due to poor GPS performance, creating a significant barrier to effective drone operations, even in static or slow-moving deployments. Recreational-grade GPS systems, commonly used in low Size, Weight and Power (SWaP) UAVs, suffer from residual errors exceeding 100 m in urban environments, severely limiting real-time navigation accuracy and drone autonomy. Although capable of good accuracy in conventional aerospace deployments, existing traditional aerospace-ready GPS receivers are expensive, power-intensive, and heavy, making them unsuitable for low SWaP drone deployment. Existing performance-enhancing post-processing techniques for recreational GPS are limited by the real-time requirements and the noise, power, and computational constraints inherent to drone operations. This underscores the critical need for accurate, robust, lightweight, and power-efficient urban localization solutions for UAVs. In this work, we present a hybrid Integrated Recurrent Neural Network–Deep Neural Network (IRNN–DNN) architecture, capable of running on embedded microcontrollers with recreational-grade L1C GPS receivers. Leveraging Long Short-Term Memory (LSTM) networks, the IRNN–DNN model captures temporal dependencies and spatial error patterns across multiple concurrent GPS receivers, allowing real-time error correction. Field tests with MTK3339 GPS receiver on UAVs in static test conditions showed, with a 2D residual error of 1.71 m at 10 Hz, a 30% improvement over existing models—validate the IRNN–DNN approach as a promising embedded solution for enhancing urban localization performance in constrained UAV applications.