针对模糊的SLAM图优化，选择性地非高斯精修，提升精度且更高效。
SNGR: Selective Non-Gaussian Refinement for Ambiguous SLAM Factor Graphs
- 通过条件数检测高斯近似失效区域，只对局部窗口做非高斯精修。
- 在仅测距的错误关联场景中，故障检测准确率高，局部似然提升显著。
- 适合需要高精度与计算效率平衡的机器人定位任务。
我们提出选择性非高斯精修（SNGR），在iSAM2基础上，对可能偏离高斯假设的因子图窗口进行针对性嵌套采样。通过联合边际协方差的条件数识别此类区域，并利用完整的非线性因子图似然进行选择性精修，同时采用门控机制防止多模态情况下的性能退化。在存在错误数据关联的仅测距SLAM实验中，SNGR实现了高精度的故障检测与一致的局部似然改进，同时相比全量非高斯推断显著降低计算开销。结果表明，选择性精修在近似SLAM后验中兼具潜力与局限性。
原文摘要 · Abstract (English)
We present Selective Non-Gaussian Refinement (SNGR), a SLAM framework that augments iSAM2 with targeted nested sampling on windows where Gaussian approximations are likely to fail. We detect such regions using the condition number of joint marginal covariances and selectively refine them using the full nonlinear factor graph likelihood, with a gating mechanism to avoid degradation in multimodal cases. Experiments on range-only SLAM with wrong data association show that SNGR achieves high-precision failure detection and consistent local likelihood improvements while reducing computational cost relative to exhaustive non-Gaussian inference. These results highlight both the promise and the limitations of selective refinement for approximate SLAM posteriors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。