Anti-Degeneracy Scheme for Lidar SLAM based on Particle Filter in Geometry Feature-Less Environments

2025-02-17

AI Summary

To address particle degeneracy and poor pose estimation robustness in particle-filter-based SLAM under geometrically feature-poor environments, this paper proposes a deep learning–driven anti-degeneracy LiDAR SLAM system. Methodologically: (1) we introduce the first degeneration detection model integrating ResNet and Transformer architectures; (2) we design a scale-invariant coordinate mapping scheme coupled with Gaussian augmentation for robust data discretization; and (3) we develop a hierarchical coarse-to-fine registration framework enabling adaptive pose optimization. Experiments demonstrate that the system significantly mitigates particle degeneracy and improves both localization accuracy and map consistency in both simulated and real-world feature-scarce scenarios. Ablation studies confirm the effectiveness of each component, and GPU acceleration reduces computational latency by 42%.

Technology Category

• Search and Optimization: Learning to Search
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Simultaneous localization and mapping (SLAM) based on particle filtering has been extensively employed in indoor scenarios due to its high efficiency. However, in geometry feature-less scenes, the accuracy is severely reduced due to lack of constraints. In this article, we propose an anti-degeneracy system based on deep learning. Firstly, we design a scale-invariant linear mapping to convert coordinates in continuous space into discrete indexes, in which a data augmentation method based on Gaussian model is proposed to ensure the model performance by effectively mitigating the impact of changes in the number of particles on the feature distribution. Secondly, we develop a degeneracy detection model using residual neural networks (ResNet) and transformer which is able to identify degeneracy by scrutinizing the distribution of the particle population. Thirdly, an adaptive anti-degeneracy strategy is designed, which first performs fusion and perturbation on the resample process to provide rich and accurate initial values for the pose optimization, and use a hierarchical pose optimization combining coarse and fine matching, which is able to adaptively adjust the optimization frequency and the sensor trustworthiness according to the degree of degeneracy, in order to enhance the ability of searching the global optimal pose. Finally, we demonstrate the optimality of the model, as well as the improvement of the image matrix method and GPU on the computation time through ablation experiments, and verify the performance of the anti-degeneracy system in different scenarios through simulation experiments and real experiments. This work has been submitted to IEEE for publication. Copyright may be transferred without notice, after which this version may no longer be available.

Problem

• Enhances SLAM accuracy in feature-less environments
• Proposes anti-degeneracy system using deep learning
• Improves particle filter robustness with adaptive strategies

Innovation

• Deep learning-based anti-degeneracy system
• ResNet and transformer degeneracy detection
• Adaptive hierarchical pose optimization strategy