Simultaneous localization and mapping (SLAM) technology is essential for autonomous navigation and motion control in robotics and computer vision, with applications in autonomous driving, mobile robotics, and augmented reality. Despite its importance, existing studies often focus on specific SLAM aspects, lacking comprehensive reviews of vision-based SLAM applications. This article aims to fill that gap with two major objectives: to use VOSviewer software to analyze SLAM-related keywords, identify current research hotspots, and predict future research trends. The research results indicate the significant potential of SLAM technology in automatic parking and driving trajectory memory, emphasizing the need for continued research to enhance system accuracy and efficiency. Key application areas include parking lot mapping, localization and navigation, object detection, and mission planning. VOSviewer analysis reveals that SLAM is closely linked with artificial intelligence, deep learning, and machine learning. The integration of these technologies has advanced SLAM development, especially in augmented reality and object recognition. Future SLAM trends may involve more sophisticated algorithms to address existing challenges and broaden practical applications.