发表机构
Seoul National University; ETH Zürich; Robotics and AI Institute（首尔国立大学; 苏黎世联邦理工学院; 机器人与人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TRaIL-Odom提出紧耦合雷达-IMU-激光雷达里程计的自适应多普勒加权模块，在13个序列上达SOTA，退化场景优势显著， ablation实验降RMSE ATE和RTE达86.0%、78.5%。
AI 中文摘要
现有雷达-激光雷达融合方法依赖固定残差权重，然而雷达多普勒与激光雷达几何的信息性随扫描和方向变化，均匀的雷达权重会导致多普勒信息在平移方向上分配不当。为解决这一局限，我们在紧耦合雷达-惯性测量单元-激光雷达里程计框架内提出两个感知退化的多普勒重加权模块：逐点雷达重加权和扫描级雷达增益调度。由于几何退化具有方向性，我们首先从激光雷达几何中识别弱平移方向，并根据各雷达多普勒约束与弱子空间的对齐情况对其进行重加权。我们还利用激光雷达几何各向异性调整雷达的整体贡献，即在激光雷达可观测性差时增强雷达作用，在激光雷达约束已可靠时抑制雷达作用。在评估的13个序列中，TRaIL-Odom实现了最先进的整体性能，在几何退化场景中具有明显优势。在3个退化序列的 ablation实验中，与固定权重基线相比，结合两个自适应加权模块使RMSE ATE和RTE分别降低86.0%和78.5%。我们将代码和配套数据集公开于此https URL。
英文摘要
Existing radar-LiDAR fusion methods rely on fixed residual weights, even though the informativeness of radar Doppler and LiDAR geometry is scan- and direction-dependent, leading to uniform radar weighting that misallocates Doppler information across translational directions. To address this limitation, we propose two degeneracy-aware Doppler reweighting modules within a tightly coupled Radar-IMU-LiDAR odometry framework: per-point radar reweighting and scan-wise radar gain scheduling. Since geometric degeneracy is directional, we first identify weak translational directions from the LiDAR geometry and reweight individual radar Doppler constraints based on their alignment with the weak subspace. We further adjust the overall radar contribution using LiDAR geometric anisotropy such that radar is emphasized when LiDAR observability is poor and suppressed when LiDAR constraints are already reliable. Across 13 evaluated sequences, TRaIL-Odom achieves state-of-the-art overall performance, with clear advantages in geometrically degenerate scenes. In ablation experiments on three degenerate sequences, combining the two adaptive weighting modules reduces RMSE ATE and RTE by 86.0% and 78.5% relative to the fixed-weight baseline. We make our code and an accompanying dataset publicly available at https://github.com/ChiyunNoh/TRaIL-Odom.
CommentsAccepted for publication at the IEEE Robotics and Automation Letters on 23 August, 2026
