对比五种视觉SLAM在无GPS、低光照等恶劣环境下的表现，指导无人机嵌入式部署。
Robust Visual SLAM for UAV Navigation in GPS-Denied and Degraded Environments: A Multi-Paradigm Evaluation and Deployment Study
- 横跨经典、深度学习、Transformer等多种方法，系统评估其鲁棒性。
- 学习型方法如MASt3R在严重退化下仍保持0.027米的低定位误差。
- DPVO兼顾效率与鲁棒性，适合资源受限的无人机平台。
在无GPS、视觉退化的环境下实现可靠定位对自主无人机运行至关重要。本文系统比较了五种V-SLAM系统：ORB-SLAM3、DPVO、DROID-SLAM、DUSt3R和MASt3R，涵盖经典、深度学习、递归及视觉变压器（ViT）范式。实验基于四个公开基准（TUM RGB-D、EuRoC MAV、UMA-VI、SubT-MRS）和自建单目室内数据集，在五种受控退化条件下（正常、低光、尘雾、运动模糊、综合）进行，采用亚毫米级Vicon真值。结果表明，ORB-SLAM3在严重退化下表现崩溃（总体追踪成功率62.4%；浓雾下为0%），而基于学习的方法保持鲁棒：MASt3R达到最低退化状态下的绝对轨迹误差（ATE）0.027 m，DUSt3R拥有最高追踪成功率96.5%。DPVO在效率与鲁棒性间取得最佳平衡（18.6 FPS，3.1 GB GPU内存，86.1% TSR），是资源受限嵌入式平台的优选方案。跨NVIDIA Jetson平台的嵌入式部署分析为SWaP约束下的无人机SLAM选型提供可操作指南。
原文摘要 · Abstract (English)
Reliable localization in GPS-denied, visually degraded environments is critical for autonomous UAV opera- tions. This paper presents a systematic comparative evaluation of five V-SLAM systems ORB-SLAM3, DPVO, DROID-SLAM, DUSt3R, and MASt3R spanning classical, deep learning, recurrent, and Vision Transformer (ViT) paradigms. Experiments are conducted on curated sequences from four public benchmarks (TUM RGB-D, EuRoC MAV, UMA-VI, SubT-MRS) and a custom monocular indoor dataset under five controlled degradation conditions (normal, low light, dust haze, motion blur, and combined), with sub-millimeter Vicon ground truth. Results show that ORB-SLAM3 fails critically under severe degradation (62.4% overall TSR; 0% under dense haze), while learning-based methods remain robust: MASt3R achieves the lowest degraded ATE (0.027 m) and DUSt3R the highest tracking success (96.5%). DPVO offers the best efficiency robustness trade-off (18.6 FPS, 3.1 GB GPU memory, 86.1% TSR), making it the preferred choice for memory-constrained embedded platforms. Embedded deployment analysis across NVIDIA Jetson platforms provides actionable guidelines for SLAM selection under SWaP-constrained UAV scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。