Uncertainty Aware Mapping for Vision-Based Underwater Robots

TL;DR

This paper introduces an uncertainty-aware mapping method for underwater robots using vision-based sensing, integrating depth confidence into voxel mapping to improve environmental representation under noisy conditions.

Contribution

It presents a novel approach that incorporates depth estimation confidence into voxel-based mapping, enhancing uncertainty representation in underwater environments.

Findings

Improved mapping accuracy in underwater scenarios.

Effective visualization of environmental uncertainty.

Validated in real-world underwater experiments.

Abstract

Vision-based underwater robots can be useful in inspecting and exploring confined spaces where traditional sensors and preplanned paths cannot be followed. Sensor noise and situational change can cause significant uncertainty in environmental representation. Thus, this paper explores how to represent mapping inconsistency in vision-based sensing and incorporate depth estimation confidence into the mapping framework. The scene depth and the confidence are estimated using the RAFT-Stereo model and are integrated into a voxel-based mapping framework, Voxblox. Improvements in the existing Voxblox weight calculation and update mechanism are also proposed. Finally, a qualitative analysis of the proposed method is performed in a confined pool and in a pier in the Trondheim fjord. Experiments using an underwater robot demonstrated the change in uncertainty in the visualization.