点群位置合わせにおける人間が解釈可能な不確かさの説明
Human-Interpretable Uncertainty Explanations for Point Cloud Registration
点群位置合わせの不確かさを定量化し、その原因を既知の誤差要因に帰属させて説明するガウス過程概念帰属(GP-CA)を提案し、能動学習で新たな不確かさ要因も発見する。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Johannes A. Gaus, Loris Schneider, Yitian Shi, Jongseok Lee, Rania Rayyes, Rudolph Triebel
分類: cs.RO, cs.CV
原文アブストラクト
In this paper, we address the point cloud registration problem, where well-known methods like ICP fail under uncertainty arising from sensor noise, pose-estimation errors, and partial overlap due to occlusion. We develop a novel approach, Gaussian Process Concept Attribution (GP-CA), which not only quantifies registration uncertainty but also explains it by attributing uncertainty to well-known sources of errors in registration problems. Our approach leverages active learning to discover new uncertainty sources in the wild by querying informative instances. We validate GP-CA on three publicly available datasets and in our real-world robot experiment. Extensive ablations substantiate our design choices. Our approach outperforms other state-of-the-art methods in terms of runtime, high sample-efficiency with active learning, and high accuracy. Our real-world experiment clearly demonstrates its applicability. Our video also demonstrates that GP-CA enables effective failure-recovery behaviors, yielding more robust robotic perception.
