Ufil: A Unified Framework for Infrastructure-based Localization

2026-04-23

AI Summary

This work addresses the fragmentation and limited reusability in existing infrastructure-based positioning systems, which stem from tightly coupled perception, tracking, and middleware components and the absence of a standardized architecture. To overcome these limitations, we propose Ufil—the first modular, open-source framework tailored for infrastructure-centric localization. Ufil decouples core functionalities—including prediction, detection, association, state update, and trajectory management—through a standardized object model and reusable multi-object tracking components. Built on C++ and ROS 2, the framework supports plug-and-play integration of heterogeneous data sources such as ITS-G5 messages, roadside LiDAR, and in-pavement sensors, and enables seamless transition from simulation to real-world deployment. Experimental results demonstrate lane-level localization accuracy in both CARLA simulations and a connected autonomous vehicle testbed, achieving lateral RMSE of 0.31 m and 0.29 m, respectively, with an average heading error of approximately 2.2° and end-to-end latency under 100 ms.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Computer Vision: Motion & Tracking

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Infrastructure-based localization enhances road safety and traffic management by providing state estimates of road users. Development is hindered by fragmented, application-specific stacks that tightly couple perception, tracking, and middleware. We introduce Ufil, a Unified Framework for Infrastructure-Based Localization with a standardized object model and reusable multi-object tracking components. Ufil offers interfaces and reference implementations for prediction, detection, association, state update, and track management, allowing researchers to improve components without reimplementing the pipeline. Ufil is open-source C++/ROS 2 software with documentation and executable examples. We demonstrate Ufil by integrating three heterogeneous data sources into a single localization pipeline combining (i) vehicle onboard units broadcasting ETSI ITS-G5 Cooperative Awareness Messages, (ii) a lidar-based roadside sensor node, and (iii) an in-road sensitive surface layer. The pipeline runs unchanged in the CARLA simulator and a small-scale CAV testbed, demonstrating Ufil's scale-independent execution model. In a three-lane highway scenario with 423 and 355 vehicles in simulation and testbed, respectively, the fused system achieves lane-level lateral accuracy with mean lateral position RMSEs of 0.31 m in CARLA and 0.29 m in the CPM Lab, and mean absolute orientation errors around 2.2°. Median end-to-end latencies from sensing to fused output remain below 100 ms across all modalities in both environments.

Problem

• infrastructure-based localization
• fragmented software stacks
• perception-tracking coupling
• reusability
• multi-object tracking

Innovation

• Unified Framework
• Infrastructure-based Localization
• Multi-object Tracking
• Heterogeneous Sensor Fusion
• Modular Architecture