RaUF: Learning the Spatial Uncertainty Field of Radar

2026-03-01

AI Summary

This work addresses the challenges of millimeter-wave radar in adverse weather conditions, where low spatial fidelity, angular ambiguity, and clutter interference degrade the clarity of feature-to-label mapping and compromise the geometric reliability of downstream perception tasks. To this end, the authors propose RaUF, a novel framework that introduces an anisotropic probabilistic model to characterize the spatial uncertainty field of radar measurements for the first time. RaUF further incorporates a bidirectional domain attention mechanism that jointly leverages spatial structure and Doppler consistency to effectively suppress multipath effects and spurious reflections. Evaluated on public benchmarks and real-world road datasets, the method achieves highly reliable detection and well-calibrated uncertainty estimates, significantly enhancing the robustness and scalability of perception systems in complex driving scenarios.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Millimeter-wave radar offers unique advantages in adverse weather but suffers from low spatial fidelity, severe azimuth ambiguity, and clutter-induced spurious returns. Existing methods mainly focus on improving spatial perception effectiveness via coarse-to-fine cross-modal supervision, yet often overlook the ambiguous feature-to-label mapping, which may lead to ill-posed geometric inference and pose fundamental challenges to downstream perception tasks. In this work, we propose RaUF, a spatial uncertainty field learning framework that models radar measurements through their physically grounded anisotropic properties. To resolve conflicting feature-to-label mapping, we design an anisotropic probabilistic model that learns fine-grained uncertainty. To further enhance reliability, we propose a Bidirectional Domain Attention mechanism that exploits the mutual complementarity between spatial structure and Doppler consistency, effectively suppressing spurious or multipath-induced reflections. Extensive experiments on public benchmarks and real-world datasets demonstrate that RaUF delivers highly reliable spatial detections with well-calibrated uncertainty. Moreover, downstream case studies further validate the enhanced reliability and scalability of RaUF under challenging real-world driving scenarios.

Problem

• radar
• spatial uncertainty
• azimuth ambiguity
• spurious returns
• feature-to-label mapping

Innovation

• spatial uncertainty field
• anisotropic probabilistic model
• Bidirectional Domain Attention
• radar perception
• feature-to-label ambiguity