MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy

Raúl Castilla-Arquillo; Miguel Olivares-Mendez

cs.ROOct 20, 2026

MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy

Authors: Raúl Castilla-Arquillo, Miguel Olivares-Mendez

Organizations: Space Robotics (SpaceR) Research Group, SnT, University of Luxembourg, Luxembourg

Abstract

Lunar surface exploration increasingly relies on autonomous rovers that must perceive and traverse unstructured terrain under extreme illumination conditions. Near the lunar poles, low sun elevations produce long, high-contrast shadows that challenge stereo vision, terrain segmentation, and localization. Developing perception and navigation algorithms for these conditions requires large amounts of sensor data with accurate ground truth, which field campaigns and analog facilities can only provide at high cost and with limited variety. This paper presents MARE (Modular Autonomy and Rendering Environment), an open-source simulation suite for lunar rover perception and autonomy built on Unreal Engine 5 and ROS 2. MARE consists of three integrated components. Terrain Studio generates cratered and rocky lunar Digital Elevation Maps (DEMs) to build simulation scenes. A dedicated Unreal Engine project hosts two physics-based rovers with plugins for stereo, lidar, event, and Single-Photon Avalanche Diode (SPAD) cameras, streaming time-stamped sensor data and pixel-accurate ground truth. Lastly, a Guidance, Navigation, and Control (GNC) stack provides web-based mission control. Validation shows a mean Intersection over Union (IoU) of 0.79 between predicted and rendered shadows at low sun elevations, and stereo depth analysis verifies decreased pixel coverage in shadowed regions relative to sunlit terrain.

Figures & tables

Fig. 1: Overview of MARE: (1) terrain generation, (2) simulation, (3) ground truth, and (4) autonomous navigation.

Fig. 2: Architecture of the MARE simulation suite.

Fig. 3: Terrain Studio: (a) terrain generation, (b) predicted cast shadows, and (c) rendered terrain.

Fig. 4: Simulated rovers: (a) Raph Rover and (b) Yutu.

Fig. 6: Ground-truth masks: (a) along a crater rim and (b) approaching a boulder.

Fig. 7: Autonomous navigation: (a) global route around a crater and (b) lidar-based re-planning.

Fig. 8: Web-based mission control during an autonomous drive. The global map shows the whole terrain, with relief shading that makes its craters visible, and a planned route of about $500\text{\,}\mathrm{m}$ between the large craters.

Fig. 9: Terrains of the shadow evaluation, with the predicted shadows (blue) for a sun at 10 ° elevation.

Terrain	Area	Craters (radius)	Relief	Mean slope	IoU
Mare	$0.09\text{\,}\mathrm{k}\mathrm{m}^{2}$	26 ( $249\text{\,}\mathrm{m}$ )	$26\text{\,}\mathrm{m}$	10.4 °	0.78
Cratered	$1\text{\,}\mathrm{k}\mathrm{m}^{2}$	400 ( $5103\text{\,}\mathrm{m}$ )	$66\text{\,}\mathrm{m}$	9.1 °	0.79
Procedural	$1\text{\,}\mathrm{k}\mathrm{m}^{2}$	400 ( $5186\text{\,}\mathrm{m}$ )	$111\text{\,}\mathrm{m}$	10.8 °	0.78

TABLE I: Terrains of the shadow evaluation.

Fig. 10: IoU between predicted and rendered shadows as a function of sun elevation.

Fig. 11: Rendered against predicted shadowed area.

Fig. 12: Image, shadow label, and stereo depth of the front navigation camera at three sun elevations. Red: pixels within the stereo range without a valid depth.

			Coverage (%)		Error $>$ $10\text{\,}\mathrm{\%}$ (%)
Sun elev.	Frames	Shadowed (%)	Sunlit	Shadowed	Sunlit	Shadowed
5 °	189	86.7	93.4	84.7	1.2	0.7
10 °	136	65.7	91.2	85.0	2.0	0.9
15 °	110	46.7	91.5	84.2	1.8	0.7
20 °	122	31.0	90.1	79.5	1.7	1.8
30 °	114	9.9	86.1	57.4	2.7	9.8

TABLE II: Stereo depth on sunlit and shadowed ground as a function of sun elevation.

Fig. 13: The eight dataset maps ( $500\text{\,}\mathrm{m}$ $\times$ $500\text{\,}\mathrm{m}$ , hillshaded) with the driven routes in orange. Relief is the elevation range of each map.

Fig. 14: Frames from the front navigation camera on the test map, shown alongside their ground-truth object and shadow labels and the corresponding U-Net predictions.

Fig. 15: Networks trained exclusively on MARE data applied to real images from the SPICE-HL3 dataset [ 2 ] , captured in the LunaLab analog facility. The figure displays object segmentation from U-Net and shadow segmentation from SegFormer-B2, representing the models that transferred best for each respective task.

Fig. 16: Rear camera: the wheel tracks behind the rover and the U-Net prediction.

Object segmentation
	Front camera			Rear	SPAD
Class	U-Net	DeepLabV3+	SegFormer	U-Net	U-Net
Sky	0.99	0.99	0.99	0.99	0.99
Landscape	0.90	0.90	0.90	0.88	0.88
Small rock	0.63	0.60	0.61	0.64	0.43
Boulder	0.43	0.39	0.49	0.54	0.33

TABLE III: Per-class IoU of the segmentation baselines on the test map (585 frames, sun elevations of 8 ° , 16 ° , and 20 ° ), with the mean IoU over all frames and per sun elevation. Best front-camera model in bold.

Robotics Simulation

Robotics simulation builds virtual robots and environments to model, train, and evaluate autonomous systems before real-world deployment.

See all 320 papers

MarsLab: A Martian Rover Simulator for Planetary Rover Autonomous Navigation
Sep 28, 2026Hoyun Kim, Beomsu Kim, Giseop KimSimultaneous Localization and Mapping Off-Road Robot Navigation
Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea
MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data
Apr 1, 2026Clémentine Grethen, Yuang Shi, Simone Gasparini +1Remote Sensing Benchmarks 3D Reconstruction
IRIT - Université de Toulouse, France · National University of Singapore, Singapore · IPAL, IRL2955, Singapore
Visual SLAM with DEM Anchoring for Lunar Surface Navigation
Mar 18, 2026Adam Dai, Guillem Casadesus Vila, Grace GaoSimultaneous Localization and Mapping Visual SLAM
Stanford University William F. Durand Building 496 Lomita Mall Stanford, CA 94305

Sep 28, 2026J/K move · Enter open · S save

MarsLab: A Martian Rover Simulator for Planetary Rover Autonomous Navigation

Hoyun Kim, Beomsu Kim, Giseop Kim

Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea

Simultaneous Localization and Mapping Off-Road Robot Navigation Space Robotics Robot Navigation Planetary Rover Robotics

Open paper AskPDF arXiv

Future Mars missions will require rover autonomy that can operate across unstructured terrain, changing illumination, atmospheric dust, and limited communication. Simulation is a practical way to study these conditions before deployment, but existing Mars-relevant resources differ in scope, including mission-oriented simulators, fixed analog datasets, task-specific environments, and open robotics interfaces. In this context, we present MarsLab, an open-source, ROS2-native Mars rover simulator for autonomy and navigation algorithm development. MarsLab combines HiRISE-derived and procedural terrain with customizable rock, crater, solar-illumination, and atmospheric-dust settings, and runs a Perseverance-class rover model in NVIDIA Isaac Sim. The runtime publishes RGB, depth, RGB-D point clouds, LiDAR, IMU, wheel odometry, and Ground Truth (GT) pose data through standard ROS2 topics. We demonstrate MarsLab with Simultaneous Localization and Mapping (SLAM) benchmarks across sensing modalities, dust levels, scene geometry, and route length, and with Visual Place Recognition (VPR) benchmarks over repeated Mars Base traversals under illumination and dust changes. The results illustrate how controlled scene variation and shared GT trajectories can be used to compare trajectory-level estimation and image-level place recognition within the same simulator. Our Project Page: https://kimhoyun-robotair.github.io/MarsLab/.

Abstract

Robotics Simulation

Explore similar work

MarsLab: A Martian Rover Simulator for Planetary Rover Autonomous Navigation

MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data

Visual SLAM with DEM Anchoring for Lunar Surface Navigation