Range-based 6-DoF Monte Carlo SLAM with Gradient-guided Particle Filter on GPU

2025-04-25

AI Summary

This paper addresses the low sampling efficiency, high memory overhead, and poor real-time performance of nonparametric particle filtering in high-dimensional 6-DOF SLAM—caused by the “curse of dimensionality.” We propose a gradient-guided, GPU-accelerated Monte Carlo SLAM system. Methodologically, we introduce a novel observation-gradient-based particle redistribution strategy, integrated with a sparse keyframe map representation and lightweight loop-closure-driven pose-graph optimization. The entire pipeline is implemented end-to-end on GPU, enabling real-time processing of up to 10⁵ particles. Our contributions include significantly improved localization robustness and trajectory consistency under severe state ambiguity and kidnapping scenarios (e.g., elevator floor transitions), an order-of-magnitude gain in sampling efficiency, over 40% reduction in memory footprint, and—crucially—the first real-time, robust execution of high-dimensional nonparametric SLAM.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

This paper presents range-based 6-DoF Monte Carlo SLAM with a gradient-guided particle update strategy. While non-parametric state estimation methods, such as particle filters, are robust in situations with high ambiguity, they are known to be unsuitable for high-dimensional problems due to the curse of dimensionality. To address this issue, we propose a particle update strategy that improves the sampling efficiency by using the gradient information of the likelihood function to guide particles toward its mode. Additionally, we introduce a keyframe-based map representation that represents the global map as a set of past frames (i.e., keyframes) to mitigate memory consumption. The keyframe poses for each particle are corrected using a simple loop closure method to maintain trajectory consistency. The combination of gradient information and keyframe-based map representation significantly enhances sampling efficiency and reduces memory usage compared to traditional RBPF approaches. To process a large number of particles (e.g., 100,000 particles) in real-time, the proposed framework is designed to fully exploit GPU parallel processing. Experimental results demonstrate that the proposed method exhibits extreme robustness to state ambiguity and can even deal with kidnapping situations, such as when the sensor moves to different floors via an elevator, with minimal heuristics.

Problem

• Improving sampling efficiency in high-dimensional SLAM using gradient-guided particles
• Reducing memory usage with keyframe-based map representation
• Enabling real-time processing of large particle sets via GPU parallelism

Innovation

• Gradient-guided particle filter improves sampling efficiency
• Keyframe-based map reduces memory usage
• GPU parallel processing enables real-time performance