Machine Vision based Sample-Tube Localization for Mars Sample Return

TL;DR

This paper investigates machine vision techniques for autonomous detection and localization of sample tubes on Mars, comparing geometry-driven and data-driven approaches using a new benchmark dataset.

Contribution

It introduces a comprehensive benchmark dataset for Martian sample-tube localization and evaluates two distinct machine vision methods in realistic outdoor conditions.

Findings

CNN-based approach shows robustness under varying environmental conditions

Template matching is efficient but less adaptable to environmental changes

Benchmark dataset enables systematic evaluation of localization methods

Abstract

A potential Mars Sample Return (MSR) architecture is being jointly studied by NASA and ESA. As currently envisioned, the MSR campaign consists of a series of 3 missions: sample cache, fetch and return to Earth. In this paper, we focus on the fetch part of the MSR, and more specifically the problem of autonomously detecting and localizing sample tubes deposited on the Martian surface. Towards this end, we study two machine-vision based approaches: First, a geometry-driven approach based on template matching that uses hard-coded filters and a 3D shape model of the tube; and second, a data-driven approach based on convolutional neural networks (CNNs) and learned features. Furthermore, we present a large benchmark dataset of sample-tube images, collected in representative outdoor environments and annotated with ground truth segmentation masks and locations. The dataset was acquired systematically across different terrain, illumination conditions and dust-coverage; and benchmarking was performed to study the feasibility of each approach, their relative strengths and weaknesses, and robustness in the presence of adverse environmental conditions.