LiDAR bundle adjustment (BA) is an effective approach to reduce the drifts in pose estimation from the front-end. Existing works on LiDAR BA usually rely on predefined geometric features for landmark representation. This reliance restricts generalizability, as the system will inevitably deteriorate in environments where these specific features are absent. To address this issue, we propose SGBA, a LiDAR BA scheme that models the environment as a semantic Gaussian mixture model (GMM) without predefined feature types. This approach encodes both geometric and semantic information, offering a comprehensive and general representation adaptable to various environments. Additionally, to limit computational complexity while ensuring generalizability, we propose an adaptive semantic selection framework that selects the most informative semantic clusters for optimization by evaluating the condition number of the cost function. Lastly, we introduce a probabilistic feature association scheme that considers the entire probability density of assignments, which can manage uncertainties in measurement and initial pose estimation. We have conducted various experiments and the results demonstrate that SGBA can achieve accurate and robust pose refinement even in challenging scenarios with low-quality initial pose estimation and limited geometric features. We plan to open-source the work for the benefit of the community https://github.com/Ji1Xinyu/SGBA.

翻译：激光雷达束调整（BA）是一种有效减少前端位姿估计漂移的方法。现有的激光雷达BA研究通常依赖于预定义的几何特征进行地标表示。这种依赖性限制了方法的泛化能力，因为系统在缺乏这些特定特征的环境中性能必然会下降。为解决此问题，我们提出了SGBA，一种将环境建模为语义高斯混合模型（GMM）的激光雷达BA方案，无需预定义特征类型。该方法同时编码几何与语义信息，提供了一种全面且通用的表示，可适应各种环境。此外，为在保证泛化能力的同时限制计算复杂度，我们提出了一种自适应语义选择框架，通过评估代价函数的条件数来选择信息量最大的语义簇进行优化。最后，我们引入了一种概率特征关联方案，该方案考虑了整个分配的概率密度，能够处理测量和初始位姿估计中的不确定性。我们进行了多项实验，结果表明即使在初始位姿估计质量较低且几何特征有限的挑战性场景中，SGBA仍能实现准确且鲁棒的位姿优化。我们计划将此项工作开源，以惠及研究社区 https://github.com/Ji1Xinyu/SGBA。