发表机构
Clemson University（克莱姆森大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有雷达SLAM系统不足，提出DiffRadar，将雷达观测建模为可微高斯场，通过可微雷达前向模型联合优化位姿与场景结构，经实验验证该方法能显著提升轨迹精度、地图一致性并保持实时性能。
AI 中文摘要
雷达传感在移动系统中应用日益广泛，因其在光照差、天气恶劣和隐私敏感环境下能可靠运行，而相机和激光雷达常失效。但现有多数雷达SLAM系统通过离散雷达热图扫描匹配估计运动，破坏了几何连续性。本文提出DiffRadar，将雷达观测建模为可微、物理感知的高斯场，以各向异性高斯基元表示场景，通过可微雷达前向模型在距离-方位和多普勒-方位空间渲染雷达测量，实现直接从雷达测量联合优化机器人位姿和场景结构。在商品FMCW雷达硬件上实现DiffRadar，并在公共Radarize基准测试和针对常见雷达SLAM故障模式的受控压力测试套件上进行评估。结果表明，在信号域直接对雷达观测建模可实现更强大、一致的移动平台纯雷达SLAM。
英文摘要
Radar sensing is increasingly used in mobile systems because it operates reliably under poor lighting, adverse weather, and privacy-sensitive settings where cameras and LiDAR often fail. However, most existing radar SLAM systems estimate motion through scan matching on discretized radar heatmaps, which breaks geometric continuity and fails to capture key radar sensing properties, often leading to unstable pose estimation and degraded mapping in regenerate or dynamically changing environments. We present DiffRadar, a real-time radar SLAM system that models radar observations as a differentiable, physics-aware Gaussian field rather than discrete scans. DiffRadar represents the scene as anisotropic Gaussian primitives and renders radar measurements in range-azimuth and Doppler-azimuth spaces through a differentiable radar forward model, enabling joint optimization of robot pose and scene structure directly from radar measurements. We implement DiffRadar on commodity FMCW radar hardware and evaluate it on both the public Radarize benchmark and a controlled stress-test suite that targets common radar SLAM failure modes, including corridor degeneracy, motion regime transitions, dynamic clutter, and long-horizon loop closures. DiffRadar achieves substantial reductions in trajectory error on the benchmark, with especially large gains under feature-poor corridor motion, while more than doubling map consistency and maintaining real-time performance at 70 FPS. These results show that modeling radar observations directly in the signal domain enables substantially more robust and consistent radar-only SLAM for mobile platforms.
