CNNNav: Enhancing Navigation Systems with Convolutional Neural Networks

Kodeti Haritha Rani, Midhun Chakkaravarthy

Abstract: With the ubiquitous use of navigation systems in our daily lives, there is an increasing demand for accurate and reliable positioning solutions. However, traditional navigation systems often face challenges such as signal degradation in urban environments, multipath interference, and inaccurate positioning in complex terrains. In this paper, we introduce CNNNav, a novel approach that leverages Convolutional Neural Networks (CNNs) to enhance navigation systems' accuracy and robustness. CNNNav processes raw sensor data, including GPS, IMU, and visual inputs, to predict precise user positions in real - time. The proposed CNN architecture is designed to capture spatial and temporal dependencies in the sensor data, allowing for accurate localization even in challenging environments. We evaluate CNNNav using real - world navigation datasets and demonstrate significant improvements in positioning accuracy compared to traditional methods. Furthermore, CNNNav exhibits robust performance across various scenarios, including urban areas, dense foliage, and indoor environments. Our findings suggest that CNN - based approaches hold promise for advancing navigation systems, enabling more reliable and seamless navigation experiences for users worldwide.

Keywords: navigation systems, CNNNav, Convolutional Neural Networks (CNNs), robust performance

How to Cite?: Kodeti Haritha Rani, Midhun Chakkaravarthy, "CNNNav: Enhancing Navigation Systems with Convolutional Neural Networks", Volume 13 Issue 8, August 2024, International Journal of Science and Research (IJSR), Pages: 1114-1117, https://www.ijsr.net/getabstract.php?paperid=SR24515224431, DOI: https://dx.doi.org/10.21275/SR24515224431