UCA-SLAM: Tightly Coupled Visual-LiDAR SLAM with DoF-wise Uncertainty-driven Constraint Analysis
Shizhuo Yu, Wenbin Zhu, Jing Yuan, Yuanxi Gao
AI summary
Problem
Current tightly coupled visual-LiDAR SLAM systems omit explicit feature uncertainty modeling and fail to quantify per-degree-of-freedom constraint strength, preventing optimal cross-sensor fusion.
Approach
UCA-SLAM propagates closed-form uncertainties for visual points and LiDAR planes, analyzes their continuous constraint strength per DoF, and uses these metrics to dynamically weight sensor residuals during tracking and bundle adjustment.
Key results
- Proposes a DoF-wise, uncertainty-driven adaptive fusion mechanism for visual-LiDAR residuals
- Implements a tightly coupled SLAM framework with uncertainty-aware landmark creation and keyframe selection
- Derives closed-form uncertainty propagation from features to the 6-DoF pose
- Demonstrates superior accuracy and robustness over state-of-the-art methods on public and real-world datasets
Why it matters
Enables more reliable robot navigation and mapping in degenerate or texture-poor environments by principled, uncertainty-aware sensor fusion.
Abstract
Single sensor (visual or LiDAR) simultaneous localization and mapping (SLAM) is fragile in the complex environment, which makes visual-LiDAR fusion a mainstream in SLAM research. However, most existing fusion methods omit explicit modeling of feature uncertainties and do not quantify each feature’s constraint strength on each degree of freedom (DoF) of the 6-DoF pose, thereby hindering the full exploitation of the complementary information across different sensors. In this paper, a tightly coupled visual-LiDAR SLAM method termed UCA-SLAM is proposed, which integrates the closed- form uncertainty propagation and the DoF-wise constraint analysis. Specifically, UCA-SLAM maintains uncertainties for visual map points and LiDAR voxel planes, and computes DoF-wise constraint strength for each feature. In the front-end tracking, the DoF-wise constraints of features are comprehen- sively analyzed, which provides an adaptive fusion mechanism for pose estimation, and an explicit uncertainty propagation from feature measurements to the 6-DoF pose is derived. The resultant feature and pose uncertainties are then used to weight the cost function in local bundle adjustment (BA) optimization of UCA-SLAM to improve the accuracy of the system. Extensive experiments conducted on public datasets and in real-world environments demonstrate that UCA-SLAM outperforms state- of-the-art visual-LiDAR fusion SLAM methods. UCA-SLAM is open-sourced to benefit the community.