Beyond Point Estimates: Likelihood-Based Full-Posterior Wireless Localization

2025-09-29

AI Summary

This work addresses the critical need in wireless localization to output a posterior position distribution with explicit uncertainty quantification. We propose Monte Carlo Candidate Likelihood Estimation (MC-CLE), which formulates localization as a Bayesian posterior inference problem—inferring the transmitter’s location from multi-antenna channel measurements. MC-CLE employs a neural network to score candidate positions via likelihood estimation and trains this scorer using Monte Carlo sampling, explicitly incorporating physical characteristics such as antenna radiation patterns and angular ambiguities. Unlike baseline methods relying on simplistic Gaussian or uniform priors, MC-CLE end-to-end produces high-fidelity posterior distributions. In line-of-sight online simulations, it significantly reduces cross-entropy loss and more accurately captures complex spatial likelihood structures. The resulting calibrated uncertainty estimates provide robust support for intelligent planning, control, and resource management in wireless systems.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Modern wireless systems require not only position estimates, but also quantified uncertainty to support planning, control, and radio resource management. We formulate localization as posterior inference of an unknown transmitter location from receiver measurements. We propose Monte Carlo Candidate-Likelihood Estimation (MC-CLE), which trains a neural scoring network using Monte Carlo sampling to compare true and candidate transmitter locations. We show that in line-of-sight simulations with a multi-antenna receiver, MC-CLE learns critical properties including angular ambiguity and front-to-back antenna patterns. MC-CLE also achieves lower cross-entropy loss relative to a uniform baseline and Gaussian posteriors. alternatives under a uniform-loss metric.

Problem

• Estimating transmitter location uncertainty in wireless systems
• Inferring posterior distributions from receiver measurements
• Addressing angular ambiguity in multi-antenna localization scenarios

Innovation

• Monte Carlo sampling trains neural scoring network
• Posterior inference for transmitter location estimation
• Learns angular ambiguity and antenna patterns