Robust Visual SLAM for UAV Navigation in GPS-Denied and Degraded Environments: A Multi-Paradigm Evaluation and Deployment Study
Prasoon Kumar, Akshay Deepak, Sandeep Kumar
TLDR
This paper evaluates five V-SLAM systems for UAV navigation in GPS-denied, degraded environments, finding learning-based methods more robust.
Key contributions
- Systematically evaluated 5 V-SLAM systems (classical, deep learning, ViT) for UAVs in degraded environments.
- Tested on public and custom datasets under low light, dust haze, motion blur, and combined degradations.
- Learning-based methods (MASt3R, DUSt3R) proved robust, while ORB-SLAM3 failed critically.
- DPVO offers the best efficiency-robustness trade-off for embedded platforms, with deployment guidelines.
Why it matters
This paper is crucial for developing autonomous UAVs operating in challenging, GPS-denied environments. It provides a systematic comparison and actionable guidelines for selecting robust V-SLAM systems, especially for resource-constrained embedded platforms. This helps engineers choose optimal solutions for real-world deployment.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.