mmE-Loc: Facilitating Accurate Drone Landing with Ultra-High-Frequency Localization

2025-07-12

AI Summary

Addressing the challenge of achieving real-time, high-precision localization of ground platforms for autonomous drone landing, this paper proposes a low-latency multimodal localization system integrating millimeter-wave radar and event cameras. To ensure temporal alignment across modalities, we introduce hardware-level sampling synchronization and a consistency-guided collaborative tracking module. Furthermore, we design a graph-aware adaptive joint optimization module that exploits the drone’s periodic micro-movements and motion priors to achieve spatially complementary fusion. Our approach synergistically combines physics-informed modeling, graph neural networks, and adaptive sensor fusion algorithms. Evaluated in realistic logistics landing scenarios, the system achieves centimeter-level positioning accuracy and millisecond-scale latency—significantly outperforming existing state-of-the-art methods in both precision and responsiveness.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

For precise, efficient, and safe drone landings, ground platforms should real-time, accurately locate descending drones and guide them to designated spots. While mmWave sensing combined with cameras improves localization accuracy, lower sampling frequency of traditional frame cameras compared to mmWave radar creates bottlenecks in system throughput. In this work, we upgrade traditional frame camera with event camera, a novel sensor that harmonizes in sampling frequency with mmWave radar within ground platform setup, and introduce mmE-Loc, a high-precision, low-latency ground localization system designed for precise drone landings. To fully exploit the extit{temporal consistency} and extit{spatial complementarity} between these two modalities, we propose two innovative modules: extit{(i)} the Consistency-instructed Collaborative Tracking module, which further leverages the drone's physical knowledge of periodic micro-motions and structure for accurate measurements extraction, and extit{(ii)} the Graph-informed Adaptive Joint Optimization module, which integrates drone motion information for efficient sensor fusion and drone localization. Real-world experiments conducted in landing scenarios with a drone delivery company demonstrate that mmE-Loc significantly outperforms state-of-the-art methods in both accuracy and latency.

Problem

• Achieving precise drone landing with high-frequency localization
• Overcoming throughput bottlenecks in mmWave and camera systems
• Integrating event cameras with mmWave radar for accurate measurements

Innovation

• Event camera replaces frame camera for higher frequency
• Consistency-instructed Collaborative Tracking module for precise measurements
• Graph-informed Adaptive Joint Optimization for efficient fusion