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

2025-07-11

AI Summary

To address the insufficient robustness of SLAM in complex environments, this paper introduces Ground-Fusion++, the first multi-sensor fusion SLAM benchmark and resilient framework tailored for ground vehicles. First, we construct M3DGR—a systematic degradation dataset covering four representative challenging scenarios: visual/LiDAR degradation, wheel slip, and GNSS denial. Second, we propose a modular, tightly coupled fusion architecture that supports dynamic sensor selection among GNSS, RGB-D, LiDAR, IMU, and wheel encoders, enhanced by a degradation-aware mechanism and an adaptive weighting algorithm. Comprehensive evaluation across 40 state-of-the-art SLAM systems demonstrates that Ground-Fusion++ achieves significant performance gains under extreme degradation conditions. Both the codebase and M3DGR dataset are publicly released, establishing a standardized evaluation platform and an extensible framework for advancing robust SLAM research.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• 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

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.

Problem

• Lack of standardized benchmarks for SLAM in diverse degradation scenarios
• Limited sensor fusion adaptability in varying environmental conditions
• Need for robust performance evaluation under challenging real-world conditions

Innovation

• Introduces M3DGR dataset for SLAM benchmarking
• Evaluates forty SLAM systems comprehensively
• Develops Ground-Fusion++ multi-sensor fusion framework