選択的非ガウス精密化による曖昧なSLAM因子グラフの改善
SNGR: Selective Non-Gaussian Refinement for Ambiguous SLAM Factor Graphs
SLAMの不確実性が高い領域を検出し、その部分だけ非ガウス推論で精密化する手法を提案した。誤ったデータ対応を含むレンジオンリーSLAMで精度向上と計算コスト削減を実証した。
著者: Anushka Kulkarni, Sarthak Dubey
分類: cs.RO, cs.NA, math.NA
原文アブストラクト
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.