Planetary Terrain Datasets and Benchmarks for Rover Path Planning

2025-12-24

AI Summary

To address the lack of real-space data support for path planning research in planetary exploration missions, this paper establishes the first standardized benchmark suite for planetary autonomous navigation, releasing high-resolution terrain datasets—MarsPlanBench and MoonPlanBench—for Mars and the Moon, respectively. We propose a unified evaluation framework integrating classical algorithms (e.g., A*, RRT) and deep reinforcement learning models, accompanied by a multidimensional assessment protocol covering terrain roughness, illumination conditions, and slope angle. Experimental results demonstrate that classical planners achieve 100% global planning success rates in complex terrains such as the lunar polar regions, underscoring their engineering robustness; in contrast, learning-based models exhibit severely limited generalization capability. All code and datasets are publicly released, providing critical infrastructure to advance foundational research in planetary autonomous navigation.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Planetary rover exploration is attracting renewed interest with several upcoming space missions to the Moon and Mars. However, a substantial amount of data from prior missions remain underutilized for path planning and autonomous navigation research. As a result, there is a lack of space mission-based planetary datasets, standardized benchmarks, and evaluation protocols. In this paper, we take a step towards coordinating these three research directions in the context of planetary rover path planning. We propose the first two large planar benchmark datasets, MarsPlanBench and MoonPlanBench, derived from high-resolution digital terrain images of Mars and the Moon. In addition, we set up classical and learned path planning algorithms, in a unified framework, and evaluate them on our proposed datasets and on a popular planning benchmark. Through comprehensive experiments, we report new insights on the performance of representative path planning algorithms on planetary terrains, for the first time to the best of our knowledge. Our results show that classical algorithms can achieve up to 100% global path planning success rates on average across challenging terrains such as Moon's north and south poles. This suggests, for instance, why these algorithms are used in practice by NASA. Conversely, learning-based models, although showing promising results in less complex environments, still struggle to generalize to planetary domains. To serve as a starting point for fundamental path planning research, our code and datasets will be released at: https://github.com/mchancan/PlanetaryPathBench.

Problem

• Develops planetary terrain datasets for rover path planning
• Establishes benchmarks to evaluate path planning algorithms
• Compares classical and learning-based algorithms on planetary terrains

Innovation

• Created MarsPlanBench and MoonPlanBench datasets
• Established unified framework for path planning algorithms
• Evaluated classical and learning-based methods on planetary terrains