MarsLGPR: Mars Rover Localization with Ground Penetrating Radar

2025-03-06

AI Summary

Precise localization of rovers on Mars remains challenging due to the absence of GPS and high wheel-slip in unstructured terrain. Method: This work pioneers the integration of ground-penetrating radar (GPR) into rover relative pose estimation, proposing a multi-sensor fusion framework combining GPR, inertial measurement unit (IMU), and wheel odometry. We construct the first publicly available GPR-based localization dataset acquired in Mars-analog environments; design a 1D convolutional deep learning model for end-to-end regression from GPR signals to relative translational displacement; and incorporate a robust filtering algorithm for state estimation. Results: Experiments in high-slip sandy terrain demonstrate that GPR-based displacement estimation outperforms conventional wheel odometry, while multi-modal fusion significantly enhances absolute localization accuracy and resilience to sensor degradation. This study establishes the first GPR-based navigation paradigm for planetary rovers, introducing a novel perception modality and technical pathway for deep-space exploration.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

In this work, we propose the use of Ground Penetrating Radar (GPR) for rover localization on Mars. Precise pose estimation is an important task for mobile robots exploring planetary surfaces, as they operate in GPS-denied environments. Although visual odometry provides accurate localization, it is computationally expensive and can fail in dim or high-contrast lighting. Wheel encoders can also provide odometry estimation, but are prone to slipping on the sandy terrain encountered on Mars. Although traditionally a scientific surveying sensor, GPR has been used on Earth for terrain classification and localization through subsurface feature matching. The Perseverance rover and the upcoming ExoMars rover have GPR sensors already equipped to aid in the search of water and mineral resources. We propose to leverage GPR to aid in Mars rover localization. Specifically, we develop a novel GPR-based deep learning model that predicts 1D relative pose translation. We fuse our GPR pose prediction method with inertial and wheel encoder data in a filtering framework to output rover localization. We perform experiments in a Mars analog environment and demonstrate that our GPR-based displacement predictions both outperform wheel encoders and improve multi-modal filtering estimates in high-slip environments. Lastly, we present the first dataset aimed at GPR-based localization in Mars analog environments, which will be made publicly available upon publication.

Problem

• Mars rover localization in GPS-denied environments
• Improving localization accuracy in high-slip terrains
• Developing a GPR-based deep learning model for pose estimation

Innovation

• GPR-based deep learning for pose prediction
• Fusion of GPR, inertial, and encoder data
• First GPR localization dataset for Mars analogs