PA-LVIO: Real-Time LiDAR-Visual-Inertial Odometry and Mapping with Pose-Only Bundle Adjustment

2026-03-17

AI Summary

This work addresses the challenges of drift suppression and real-time performance in multi-sensor fusion for localization and mapping within intelligent transportation systems. The authors propose a pose-only bundle adjustment (BA) framework that tightly couples LiDAR, visual, and IMU measurements. Key innovations include a frame-to-map LiDAR observation model, a joint BA strategy without marginalization, online spatiotemporal calibration centered on the IMU, and RGB point cloud rendering. Evaluated across 28 cross-platform sequences totaling over 50 kilometers, the system achieves accuracy comparable to or better than state-of-the-art methods while enabling real-time operation on both desktop and ARM embedded platforms.

Technology Category

Intelligent Robots: Multimodal Perception & Sensor FusionPlanning, Routing, and Scheduling: Optimization of Spatio-temporal SystemsComputer Vision: Multi-modal Vision

Application Category

Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applicationsSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAGGraph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Real-time LiDAR-visual-inertial odometry and mapping is crucial for navigation and planning tasks in intelligent transportation systems. This study presents a pose-only bundle adjustment (PA) LiDAR-visual-inertial odometry (LVIO), named PA-LVIO, to meet the urgent need for real-time navigation and mapping. The proposed PA framework for LiDAR and visual measurements is highly accurate and efficient, and it can derive reliable frame-to-frame constraints within multiple frames. A marginalization-free and frame-to-map (F2M) LiDAR measurement model is integrated into the state estimator to eliminate odometry drifts. Meanwhile, an IMU-centric online spatial-temporal calibration is employed to obtain a pixel-wise LiDAR-camera alignment. With accurate estimated odometry and extrinsics, a high-quality and RGB-rendered point-cloud map can be built. Comprehensive experiments are conducted on both public and private datasets collected by wheeled robot, unmanned aerial vehicle (UAV), and handheld devices with 28 sequences and more than 50 km trajectories. Sufficient results demonstrate that the proposed PA-LVIO yields superior or comparable performance to state-of-the-art LVIO methods, in terms of the odometry accuracy and mapping quality. Besides, PA-LVIO can run in real-time on both the desktop PC and the onboard ARM computer.

Problem

• LiDAR-visual-inertial odometry
• real-time mapping
• pose-only bundle adjustment
• odometry drift
• spatial-temporal calibration

Innovation

• pose-only bundle adjustment
• LiDAR-visual-inertial odometry
• frame-to-map registration
• online spatio-temporal calibration
• real-time mapping