A New Implementation of NeoSLAM and a Comparative Evaluation with RatSLAM

2026-07-17

AI Summary

This work addresses key limitations of the original NeoSLAM algorithm—namely its inability to operate in real time, low data utilization efficiency, and the absence of systematic comparisons with RatSLAM across diverse environments—by re-engineering it into a modular, ROS 2–compatible real-time system. Leveraging modern SLAM processing techniques, the redesigned architecture enables efficient data streaming and synchronized computation, substantially improving throughput to support real-time operation. A comprehensive evaluation on three public datasets systematically assesses both NeoSLAM and RatSLAM in terms of trajectory reconstruction accuracy and map consistency. Experimental results demonstrate that the proposed system achieves trajectory consistency superior to RatSLAM while maintaining comparable map quality.

Abstract

This paper presents a new implementation of the NeoSLAM algorithm. The proposed version is a complete rewrite of NeoSLAM into a modular architecture using modern frameworks that, together, enable real-time execution with minimal discarding of input data. This work also provides a comparative evaluation between NeoSLAM and RatSLAM across three datasets under varying environmental conditions. The experimental results highlight differences in mapping consistency and trajectory reconstruction, demonstrating the effectiveness and practical applicability of the proposed ROS2-based implementation. The results indicate that the new NeoSLAM outperforms the original in terms of processing throughput for real-time applications and achieves comparable performance to RatSLAM in terms of map reconstruction across the evaluated datasets.

Problem

• NeoSLAM
• RatSLAM
• real-time execution
• mapping consistency
• trajectory reconstruction

Innovation

• NeoSLAM
• modular architecture
• ROS2
• real-time SLAM
• comparative evaluation