Towards Explaining Uncertainty Estimates in Point Cloud Registration

Ziyuan Qin, Jongseok Lee, Rudolph Triebel
12/29/2024
cs.ROcs.AI

No confident code implementation found for this paper.

Abstract

Iterative Closest Point (ICP) is a commonly used algorithm to estimate transformation between two point clouds. The key idea of this work is to leverage recent advances in explainable AI for probabilistic ICP methods that provide uncertainty estimates. Concretely, we propose a method that can explain why a probabilistic ICP method produced a particular output. Our method is based on kernel SHAP (SHapley Additive exPlanations). With this, we assign an importance value to common sources of uncertainty in ICP such as sensor noise, occlusion, and ambiguous environments. The results of the experiment show that this explanation method can reasonably explain the uncertainty sources, providing a step towards robots that know when and why they failed in a human interpretable manner

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Human-Interpretable Uncertainty Explanations for Point Cloud Registration

82% match2025

Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators

82% match1 repo12025

Sanity Checks for Explanation Uncertainty

80% match2024

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations

80% match2025

Explainability through uncertainty: Trustworthy decision-making with neural networks

79% match2024

Uncertainty Estimation for 3D Object Detection via Evidential Learning

79% match2024

Cite this paper

@article{qin2024towards,
  title  = {Towards Explaining Uncertainty Estimates in Point Cloud Registration},
  author = {Ziyuan Qin and Jongseok Lee and Rudolph Triebel},
  year   = {2024},
  eprint = {2412.20612},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.20612v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.20612.svg)](https://codeofpaper.com/paper/2412.20612)

Discussion