Implicit LiDAR SLAM with Confidence-Guided SDF and Normal-Driven Sampling
Hong Liu, Feixuan Huang, Wang Gao, Jinle Xu, Shuguo Pan, Keck-Voon Ling
AI summary
Problem
Implicit LiDAR SLAM lacks uncertainty quantification for sparse or noisy data, while its Signed Distance Field accuracy is degraded by systematic errors from oblique LiDAR incident angles.
Approach
We propose a neural network that predicts SDF uncertainty to guide localization and mapping, alongside an adaptive sampling strategy that weights LiDAR rays based on surface normal information to correct angular bias.
Key results
- Neural network learns and predicts SDF uncertainty
- Adaptive sampling weights LiDAR rays via surface normals
- Uncertainty-guided optimization improves localization precision
- Higher mapping completeness and accuracy on public datasets
Why it matters
Enables reliable, high-fidelity implicit LiDAR SLAM for real-world robotics and autonomous navigation in geometrically complex or sensor-degraded conditions.
Abstract
Implicit representations for LiDAR-based Simul- taneous Localization and Mapping (SLAM) offer significant advantages in storage efficiency and expressive power over traditional explicit maps. However, a critical limitation for implicit SLAM is their deterministic nature, which prevents the quantification of prediction uncertainty in sparse or noisy conditions. Furthermore, the accuracy of the underlying Signed Distance Field (SDF) is often compromised by systematic errors arising from the angular dependency of LiDAR measurements, where oblique incident angles lead to biased distance estimations and degrade map quality. To address these challenges, this paper introduces a framework that enhances the robustness and accuracy of implicit LiDAR SLAM by integrating uncertainty estimation and an adaptive sampling strategy. We propose a neural network-based approach to learn and predict SDF uncertainty, which is then effectively incorporated into both localization and mapping processes. Concurrently, to mitigate incident angle-induced errors, we develop an adaptive sampling scheme that weights LiDAR rays based on surface normal information. Validation on public datasets and a custom exper- imental platform demonstrates that our approach outperforms baseline methods in terms of localization, mapping accuracy, and robustness.