LXD-SLAM: LiDAR+X Dense SLAM with $\sum_{i=0}^{5}C_5^i$ Configurable Sensor Combinations

2026-06-26

AI Summary

This work addresses the challenges of pose estimation and dense mapping in complex environments caused by geometric degeneracy and sensor drift. The authors propose a modular, 3D LiDAR-centric multi-sensor fusion SLAM framework that supports arbitrary combinations of LiDAR, camera, IMU, wheel encoders, and GNSS—encompassing 32 possible configurations. The system introduces several key innovations: a plug-and-play fusion architecture, Gaussian process submap-based continuous environment representation, an extended scan context descriptor, and a bidirectional PnP optimization scheme, all integrated with iterative error-state Kalman filtering, adaptive hierarchical prediction, and hybrid pose-graph loop closure detection. Experiments demonstrate that the method achieves or surpasses state-of-the-art odometry performance across diverse sensor setups, producing high-fidelity, globally consistent dense maps in real time, with robustness and effectiveness validated on both public benchmarks and real-world scenarios.

Abstract

Simultaneous Localization and Mapping (SLAM) is essential for autonomous systems, yet achieving reliable, globally consistent pose estimation and dense mapping in complex environments remains challenging due to geometric degeneracy and sensor drift. While multi-sensor fusion addresses these issues, existing systems often lack the modularity to adapt to diverse platforms and rely on mathematically inconsistent fusion or suboptimal map representations. To address these limitations, we propose LXD-SLAM (LiDAR+X Dense SLAM), a highly versatile and unified multi-sensor fusion framework. Centered around 3D LiDAR, our system allows for the plug-and-play integration of LiDAR, Camera, IMU, Wheel Encoder, and GNSS, supporting up to 32 distinct sensor combinations. We employ a mathematically unified Iterative Error-Sate Kalman Filter with an adaptive hierarchical prediction strategy and an update step that minimizes point-to-mesh distances and visual reprojection errors. To support this, the environment is modeled using continuous multi-layered Gaussian Process (GP) sub-meshes, which enables efficient ray-to-mesh depth recovery for visual features. For global consistency, we introduce an Extended Scan Context (ESC) descriptor derived from the GP sub-meshes alongside a Bidirectional PnP optimization for robust multi-modal loop closure within a hybrid pose graph. Extensive evaluations on public datasets and real-world experiments demonstrate that LXD-SLAM matches or exceeds state-of-the-art specialized odometry solutions across various configurations while generating high-fidelity, globally consistent dense meshes in real-time. The relevant codes and data will be made available at https://github.com/peterWon/LXD-SLAM upon publication.

Problem

• SLAM
• multi-sensor fusion
• global consistency
• dense mapping
• geometric degeneracy

Innovation

• multi-sensor fusion
• Gaussian Process sub-meshes
• Iterative Error-State Kalman Filter
• Extended Scan Context
• dense SLAM