Abstract
This work develops a deep-learning-based cooperative localization technique for high localization accuracy and real-time operation in vehicular networks. In cooperative localization, the noisy observation of the pairwise distance and the angle between vehicles causes nonlinear optimization problems. To handle such a nonlinear optimization task at each vehicle, a deep neural network (DNN) technique is to replace a cumbersome solution of nonlinear optimization along with the saving of the computational loads. Simulation results demonstrate that the proposed technique attains some performance gain in localization accuracy and computational complexity as compared to existing cooperative localization techniques.
Highlights
As vehicular networks, in which the internet of vehicle (IoV) technology is considered, have been developed, a localization technique for accurate positioning is demanded
Most of well-known vehicle localization techniques resort to global navigation satellite systems (GNSS)
In [4], the extended Kalman filter with the information graph is applied to carry out the location estimation in a round robin manner with geolocation information of round trip time (RTT) from the received signal
Summary
In which the internet of vehicle (IoV) technology is considered, have been developed, a localization technique for accurate positioning is demanded. The sum–product algorithm [6,7] over a wireless network (SPAWN) is developed for calculating the marginal posterior distribution of the position of a target node [5] Such a Bayesian-based cooperation attains high localization accuracy, it poses several challenges regarding the computational complexity in calculating and representing the posterior distributions. The connectivity among vehicles enhances the performance of the message-passing-based cooperative localization algorithm [13] When it comes to simultaneous consideration of computational complexity saving and performance improvement, a number of technical challenges still remain. We develop the deep-neural network (DNN) technique to mitigate the computational complexity while sustaining the localization accuracy. We demonstrate that the proposed DNN technique improves localization accuracy and complexity of cooperative localization in the vehicular network
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call