MDF: Multi-Modal Data Fusion with CNN-Based Object Detection for Enhanced Indoor Localization Using LiDAR-SLAM

2025-05-13

AI Summary

To address localization challenges in GPS-denied, cluttered, and highly dynamic indoor environments, this paper proposes a lightweight multimodal fusion localization method. The approach employs 2D LiDAR as the primary sensor, tightly fuses IMU measurements, and integrates CNN-based object detection to enhance feature robustness, all embedded within the Cartographer SLAM framework for real-time mapping and localization. Its key innovation lies in a LiDAR-constrained adaptive fusion mechanism tailored for dynamic scenes, significantly improving system stability and accuracy under complex, high-motion conditions. Experimental results demonstrate a 21.03% reduction in absolute trajectory error (ATE), a mean positioning error of −0.884 m (standard deviation: 1.976 m) along the x-axis, and a 26.09% improvement in localization performance within dynamic environments. These outcomes validate the proposed framework’s superior balance of accuracy, robustness, and real-time capability.

Technology Category

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

Application Category

• 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: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Indoor localization faces persistent challenges in achieving high accuracy, particularly in GPS-deprived environments. This study unveils a cutting-edge handheld indoor localization system that integrates 2D LiDAR and IMU sensors, delivering enhanced high-velocity precision mapping, computational efficiency, and real-time adaptability. Unlike 3D LiDAR systems, it excels with rapid processing, low-cost scalability, and robust performance, setting new standards for emergency response, autonomous navigation, and industrial automation. Enhanced with a CNN-driven object detection framework and optimized through Cartographer SLAM (simultaneous localization and mapping ) in ROS, the system significantly reduces Absolute Trajectory Error (ATE) by 21.03%, achieving exceptional precision compared to state-of-the-art approaches like SC-ALOAM, with a mean x-position error of -0.884 meters (1.976 meters). The integration of CNN-based object detection ensures robustness in mapping and localization, even in cluttered or dynamic environments, outperforming existing methods by 26.09%. These advancements establish the system as a reliable, scalable solution for high-precision localization in challenging indoor scenarios

Problem

• Enhancing indoor localization accuracy in GPS-denied environments
• Integrating LiDAR and IMU for real-time, high-velocity precision mapping
• Reducing trajectory errors with CNN-based object detection and SLAM

Innovation

• Integrates 2D LiDAR and IMU sensors
• Uses CNN-based object detection framework
• Optimized through Cartographer SLAM in ROS