Towards Robust Sensor-Fusion Ground SLAM: A Comprehensive Benchmark and A Resilient Framework

TL;DR

This paper introduces a comprehensive benchmark dataset and a resilient multi-sensor fusion framework for ground SLAM, addressing robustness challenges in challenging environments and evaluating existing SLAM systems under diverse degradation scenarios.

Contribution

The paper presents M3DGR, a new benchmark dataset with degradation scenarios, and Ground-Fusion++, a modular framework for robust multi-sensor SLAM, filling gaps in evaluation and adaptive sensor fusion strategies.

Findings

Evaluated 40 SLAM systems under challenging conditions

Identified robustness strengths and weaknesses of existing SLAM methods

Demonstrated improved robustness with the proposed framework

Abstract

Considerable advancements have been achieved in SLAM methods tailored for structured environments, yet their robustness under challenging corner cases remains a critical limitation. Although multi-sensor fusion approaches integrating diverse sensors have shown promising performance improvements, the research community faces two key barriers: On one hand, the lack of standardized and configurable benchmarks that systematically evaluate SLAM algorithms under diverse degradation scenarios hinders comprehensive performance assessment. While on the other hand, existing SLAM frameworks primarily focus on fusing a limited set of sensor types, without effectively addressing adaptive sensor selection strategies for varying environmental conditions. To bridge these gaps, we make three key contributions: First, we introduce M3DGR dataset: a sensor-rich benchmark with systematically induced degradation patterns including visual challenge, LiDAR degeneracy, wheel slippage and GNSS denial. Second, we conduct a comprehensive evaluation of forty SLAM systems on M3DGR, providing critical insights into their robustness and limitations under challenging real-world conditions. Third, we develop a resilient modular multi-sensor fusion framework named Ground-Fusion++, which demonstrates robust performance by coupling GNSS, RGB-D, LiDAR, IMU (Inertial Measurement Unit) and wheel odometry. Codes and datasets are publicly available.