Maharmeh, Elias (INRIA - Paris Research Centre), Nashashibi, Fawzi (INRIA), ALSAYED, Zayed (Valeo - VMTC)

PL-RAS++: Real-Time Integrity Assurance for Robust Localization Via Risk-Adaptive Protection Level

Scheduled for presentation during the Regular Session "S28b-Multi-Sensor Fusion and Perception for Robust Autonomous Driving" (TH-EA-T28), Thursday, November 20, 2025, 14:10−14:30, Stradbroke

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Accurate uncertainty estimation is critical for perception-based tasks such as localization in intelligent vehicles. However, conventional methods often misestimate uncertainty, failing to reflect true errors.

This work addresses this issue within the integrity framework, combining qualitative and quantitative aspects. Qualitative integrity ensures robustness against faults and outliers, while quantitative integrity provides real-time protection level (PL) that bound the true pose error. We propose PL-RAS++, an enhanced version of our previous PL-RAS approach for solving nonlinear least squares problems in factor-graph-based localization. PL-RAS++ introduces a smoothed residual weighting scheme and a novel PL computation based on Value at Risk (VaR) and Conditional Value at Risk (CVaR) to capture extreme residual variations.

We validate PL-RAS++ on real datasets collected at Valeo VMTC site and compare it against a state-of-the-art method. Results demonstrate the clear superiority of PL-RAS++ in achieving zero integrity risk across all tested scenarios while maintaining robustness in challenging environments and under potential faults.