Abstract: Autonomous path planning represents a cornerstone technology for enabling planetary rovers to carry out exploration missions on extraterrestrial planets. This technology facilitates planetary rovers in navigating safely and efficiently toward their mission goal. However, the special conditions of extraterrestrial planetary environments pose significant challenges for autonomous path planning compared with those faced by ground-based mobile robots. These challenges include communication delays and bandwidth limitations between the planetary rover and the ground control station, limited light, unknown and unpredictable terrain, distinct environmental features, and the difficulty of accurately modeling interactions between the rover wheels and the ground. Therefore, addressing how to generate a safe, efficient, and reasonable traversable path for a planetary rover under conditions of incomplete environmental data and uncertain positioning is a focal point of current research. This paper reviews advancements in perception map construction and autonomous path planning for planetary rovers, examining both research progress and engineering applications. First, this paper summarizes advances in perception map construction methods that rely on binocular vision. This method uses stereo vision to generate parallax maps, which in turn help construct a digital elevation model of the planet’s surface. Stereo matching algorithms are typically used to acquire parallax maps. The discussion includes an analysis of two main types of methods: region-based matching algorithms and feature-based matching algorithms. Second, the paper classifies existing autonomous path-planning methods for planetary rovers into two categories: those based on cost evaluation and those leveraging machine learning. As a typical representative of cost-evaluation–based path planning methods, the optional arc-based autonomous path planning method is spotlighted for its algorithmic principles and iterative applications in ongoing planetary rover missions. Furthermore, the potential of A* heuristic search algorithm, rapidly-exploring random tree star (RRT*) algorithm, and fast marching method(FMM) algorithms for enhancing planetary rover path planning is explored in a categorical manner. The application of machine learning in autonomous path planning for planetary rovers is also reviewed. Such methods are classified into two groups: end-to-end path planning methods and auxiliary approaches leveraging machine learning. Ultimately, based on the above analysis of the key technologies of planetary rover autonomous path planning, the paper identifies and discusses future research directions for improving autonomous path planning methods for planetary rovers. These include enhancing perception capabilities, improving optional arc paths, reducing slippage, integrating multiple path planning methods, and strengthening the use of machine learning.