A Comprehensive Review of Path-Planning Algorithms for Planetary Rover Exploration

Abstract

Path-planning algorithms for planetary rovers are critical for autonomous robotic exploration, enabling the efficient and safe traversal of complex and dynamic extraterrestrial terrains. Unlike terrestrial mobile robots, planetary rovers must navigate highly unpredictable environments influenced by diverse factors such as terrain variability, obstacles, illumination conditions, and temperature fluctuations, necessitating advanced path-planning strategies to ensure mission success. This review comprehensively synthesizes recent advancements in planetary rover path-planning algorithms. First, we categorize these algorithms from a constraint-oriented perspective, distinguishing between internal rover state constraints and external environmental constraints. Next, we examine rule-based path-planning approaches, including graph search-based methods, potential field methods, sampling-based techniques, and dynamic window approaches, analyzing representative algorithms in each category. Subsequently, we explore bio-inspired path-planning methods, such as evolutionary algorithms, fuzzy computing, and machine learning-based approaches, with a particular emphasis on the latest developments and prospects of machine learning techniques in planetary rover navigation. Finally, we synthesize key insights from existing algorithms and discuss future research directions, highlighting their potential applications in planetary exploration missions.