Machine Learning-Aided Cooperative Localization under Dense Urban Environment

TL;DR

This work tackles robust vehicular localization in dense urban environments where centralized processing is impractical due to scale and reliability concerns. It proposes a decentralized, ML-driven cooperative localization framework (MLCL) that fuses measurement-, communication-, and time-domain information through four DNN units (MTNN, MRNN, SUNN, LENN) trained end-to-end with time-sequence supervision. The approach is validated on a realistic urban virtual testbed, showing competitive localization accuracy against centralized baselines and resilience to varying neighbor counts, with end-to-end inference around 8 ms. This framework offers a scalable pathway for real-time, cooperative localization in V2X networks, addressing domain heterogeneity and time-varying connectivity in dense urban settings.

Abstract

Future wireless network technology provides automobiles with the connectivity feature to consolidate the concept of vehicular networks that collaborate on conducting cooperative driving tasks. The full potential of connected vehicles, which promises road safety and quality driving experience, can be leveraged if machine learning models guarantee the robustness in performing core functions including localization and controls. Location awareness, in particular, lends itself to the deployment of location-specific services and the improvement of the operation performance. The localization entails direct communication to the network infrastructure, and the resulting centralized positioning solutions readily become intractable as the network scales up. As an alternative to the centralized solutions, this article addresses decentralized principle of vehicular localization reinforced by machine learning techniques in dense urban environments with frequent inaccessibility to reliable measurement. As such, the collaboration of multiple vehicles enhances the positioning performance of machine learning approaches. A virtual testbed is developed to validate this machine learning model for real-map vehicular networks. Numerical results demonstrate universal feasibility of cooperative localization, in particular, for dense urban area configurations.

Figures (5)

• Figure 1: Cooperative localization over vehicle group.
• Figure 2: Vehicle interactions over three domains of the MLCL framework.
• Figure 3: Decentralized structure of MLCL models.
• Figure 4: Virtual testbed and realistic vehicular simulation in urban environment.
• Figure 5: Performance comparison of various localization schemes.