Hardware-accelerated Mars Sample Localization via deep transfer learning from photorealistic simulations

TL;DR

This paper presents a hardware-accelerated system for autonomous detection and localization of Martian soil sample tubes using deep transfer learning from photorealistic simulations, validated on a Mars-like testbed.

Contribution

It introduces a novel system architecture combining deep neural networks and computer vision for sample localization, leveraging synthetic data for transfer learning.

Findings

Effective detection and pose estimation of sample tubes in Mars-like conditions

Validation of the approach on different hardware architectures

Promising results in sample localization accuracy

Abstract

The goal of the Mars Sample Return campaign is to collect soil samples from the surface of Mars and return them to Earth for further study. The samples will be acquired and stored in metal tubes by the Perseverance rover and deposited on the Martian surface. As part of this campaign, it is expected that the Sample Fetch Rover will be in charge of localizing and gathering up to 35 sample tubes over 150 Martian sols. Autonomous capabilities are critical for the success of the overall campaign and for the Sample Fetch Rover in particular. This work proposes a novel system architecture for the autonomous detection and pose estimation of the sample tubes. For the detection stage, a Deep Neural Network and transfer learning from a synthetic dataset are proposed. The dataset is created from photorealistic 3D simulations of Martian scenarios. Additionally, the sample tubes poses are estimated using Computer Vision techniques such as contour detection and line fitting on the detected area. Finally, laboratory tests of the Sample Localization procedure are performed using the ExoMars Testing Rover on a Mars-like testbed. These tests validate the proposed approach in different hardware architectures, providing promising results related to the sample detection and pose estimation.