低光照环境下的SLAM：项目报告

摘要

同步定位与地图构建是机器人领域的基础性问题之一，它使得机器人在真实场景中的自主操作成为可能。在低光照条件下，对比度降低、传感器噪声和运动模糊会削弱特征提取与匹配的效果，而采用激光雷达、深度传感器或热成像传感器进行补偿则会增加成本、功耗及系统集成复杂度。现有基准测试主要基于光照充足的室内或日光场景，尚不清楚标准RGB相机在黑暗环境中能实现何种程度的同步定位与地图构建性能。我们针对五种不同难度与光照条件的LaMARia序列，对涵盖基于特征、直接法、滤波法及学习型范式的六种系统——ORB-SLAM3、DSO、Kimera-VIO、OpenVINS、DPVO和DPV-SLAM——进行了基准测试，报告了绝对位姿误差、相对位姿误差及控制点召回率。Kimera-VIO是唯一能完整跟踪所有五个序列的系统，其相对位姿误差最低，但由于缺少回环检测，绝对误差持续增长；DPVO和DPV-SLAM从未丢失跟踪，但在低光照下绝对误差约为100米；经典单目管线（ORB-SLAM3、DSO）以及基于滤波的OpenVINS在大部分高难度和低光照序列中完全失效或发散。结果表明，仅依赖RGB相机的同步定位与地图构建只有在惯性融合与全局优化同时存在时，才能在低光照下维持稳定跟踪。要弥合剩余的性能差距，可能需要专用低光照学习型前端或回归互补传感方案。

English

Simultaneous localization and mapping (SLAM) is one of the fundamental problems in robotics, as it enables autonomous operations in real-world scenarios. Under low illumination, reduced contrast, sensor noise, and motion blur degrade both feature extraction and feature matching, while compensating with LiDAR, depth, or thermal sensors raises cost, power draw, and integration complexity. Existing benchmarks remain dominated by well-lit indoor or daylight sequences, leaving open how far SLAM with standard RGB cameras can be pushed in the dark. We benchmark six systems spanning the feature-based, direct, filter-based, and learning-based paradigms - ORB-SLAM3, DSO, Kimera-VIO, OpenVINS, DPVO, and DPV-SLAM - on five LaMARia sequences of varying difficulty and illumination, reporting absolute and relative pose error alongside control-point recall. Kimera-VIO is the only system to track all five sequences to completion, combining the lowest relative pose error with steadily growing absolute error due to the absence of loop closure; DPVO and DPV-SLAM never lose tracking but incur absolute errors of roughly 100 m under low light; and the classical monocular pipelines (ORB-SLAM3, DSO) together with the filter-based OpenVINS fail outright or diverge on most of the harder and low-light sequences. The results suggest that RGB-only SLAM maintains stable low-light tracking only when both inertial fusion and global optimization are present. Closing the remaining gap will likely require low-light-specific learned front-ends or a return to complementary sensing.