Core Viewpoint - The article discusses the development and advantages of wheel-legged rovers, highlighting their mobility and adaptability in various terrains, while also addressing the complexities in path planning algorithms required for their operation in dense environments [1][2]. Group 1: Research and Methodology - The research team from Shanghai Jiao Tong University proposed a novel path planning method based on extended Markov decision processes, integrating GF set theory and configuration topology to quantify energy consumption and risks associated with different actions [2][3]. - The team developed an offline motion planning library to analyze energy consumption and risks, introducing "foot-end motion-related nodes" to describe the interaction between the robot and its environment [2][10]. - The proposed value iteration algorithm, guided by information, significantly reduces computational complexity by focusing on directions strongly correlated with the target point [2][14]. Group 2: Experimental Results - Experimental results demonstrated that the proposed method efficiently solves optimal paths in non-uniform maps, validating its robustness on the TAWL wheel-legged rover [3][19]. - The research team conducted various experiments to compare different algorithms based on node access frequency, computation time, energy consumption, and success rates, finding that the Informed VI algorithm and multilayer map methods showed higher efficiency [21][22]. - The experiments revealed that the proposed algorithms maintain safety while exhibiting high efficiency and adaptability, particularly in non-uniform map environments [22][23]. Group 3: Future Directions - The research team aims to further explore motion planning and control theories for wheel-legged and crawling robots, focusing on overcoming key technological bottlenecks in embodied perception, intelligent decision-making, and adaptive control [23].