Towards Explaining Uncertainty Estimates in Point Cloud Registration

TL;DR

This paper introduces a method using kernel SHAP to explain the sources of uncertainty in probabilistic ICP point cloud registration, enhancing interpretability of robot failure modes.

Contribution

It applies explainable AI techniques to probabilistic ICP, enabling interpretation of uncertainty sources like noise and occlusion.

Findings

The explanation method reasonably identifies uncertainty sources.

It enhances interpretability of ICP failure modes.

Provides a step towards human-understandable robot diagnostics.

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