The field of autonomous navigation is rapidly advancing, with a focus on developing innovative solutions for robust and accurate localization in challenging environments. Researchers are exploring alternative methods to traditional GPS-based navigation, such as landmark-based localization, LiDAR-inertial SLAM, and thermal-LiDAR fusion. These approaches aim to improve navigation accuracy and reliability in environments with limited or disrupted GPS signals, such as tunnels, urban disaster zones, and battlefield scenarios. Noteworthy papers in this area include:

• A navigation approach using landmark-based localization combined with a battlefield-specific motion model and Extended Kalman Filter, which demonstrates superior performance in Average Displacement Error and Final Displacement Error.
• A comprehensively integrated MRNC framework for skid-steer wheeled mobile robots, which incorporates LiDAR-inertial SLAM and AI-driven control systems to ensure rigorous safety standards.
• A novel sensor fusion framework that integrates thermal cameras with LiDAR for robust localization in tunnels and low-visibility conditions.
• A data-dependent Hidden Markov Model with off-road state determination and real-time Viterbi algorithm for lane determination in autonomous vehicles, which achieves an average accuracy of 95.9%.
• An online map matching method using lane markings and scenario recognition, which improves map matching accuracy in complex road networks, especially in multilevel road areas.