PAPL-SLAM: Principal Axis-Anchored Monocular Point-Line SLAM
Guanghao Li, Yu Cao, Qi Chen, Xin Gao, Yifan Yang, Jian Pu
AI summary
Problem
Point-line SLAM systems typically separate structural line utilization from line optimization, causing constraint loss and inefficient parameterization. Existing representations either over-parameterize lines or lack the ability to integrate global structural priors during bundle adjustment.
Approach
PAPL-SLAM anchors co-directional lines to a principal axis using an Expectation-Maximization-based probabilistic association model, reducing n lines to n+2 parameters. The system integrates a complete axis management pipeline and Atlanta World structural constraints directly into bundle adjustment for efficient, robust tracking and mapping.
Key results
- Reduces n co-directional line parameters to n+2
- Probabilistic line-axis association via EM algorithm prevents mismatches
- Atlanta World structural constraints improve artificial environment accuracy
- Validated robustness and precision across indoor and outdoor datasets
Why it matters
Enables more accurate and computationally efficient monocular SLAM for complex, structured environments, benefiting robotics and autonomous navigation applications.
Abstract
In point-line Simultaneous Localization and Map- ping (SLAM) systems, the utilization of line structural informa- tion and the optimization of lines are two significant problems. The former is usually addressed through structural regularities, while the latter typically involves using minimal parameter representations of lines in optimization. However, separating these two steps leads to the loss of constraint information to each other. To solve both problems, we anchor lines with similar directions to one principal axis. Precisely, our method models the line-axis probabilistic data association using the Expectation Maximization (EM) algorithm and provides the pipelines for axis creation, updating, and optimization, enhancing the system’s robustness and avoiding mismatch. Our system can optimize n co- directional lines with only n+2 parameters, significantly reducing the number of line parameters to be optimized and enabling rapid mapping and tracking. Additionally, considering that most real- world scenes conform to the Atlanta World (AW) hypothesis, we provide an AW constraint by detecting structural lines based on vertical priors and vanishing points. Experimental results and ablation studies on various indoor and outdoor datasets demonstrate the effectiveness of our system.