International Journal of Robotics and Autonomous Systems ISSN: 3107-7382 (Online)

Authors: Dr. Ravi Bansal, Ananya Ghosh

Abstract : Sensor fusion has become a cornerstone in the advancement of mobile robotic systems, particularly in achieving real-time localization and mapping. Simultaneous Localization and Mapping (SLAM) has emerged as a critical task in autonomous robotics, relying on the integration of various sensors such as LiDAR, GPS, IMU, and vision systems. This paper explores modern techniques in sensor fusion that enable robust SLAM in dynamic and unstructured environments. The work delves into Kalman Filters, Particle Filters, and deep learning-based fusion approaches. A comparative analysis of these techniques is presented, highlighting their effectiveness in indoor and outdoor navigation. Emphasis is laid on accuracy, computational efficiency, and adaptability. Real-world applications in autonomous vehicles, drones, and service robots are discussed to showcase practical relevance. The study concludes with insights into the challenges, limitations, and future research directions of sensor fusion for SLAM.

Keywords: Sensor Fusion, SLAM, Mobile Robots, Localization, Mapping, Kalman Filter, Deep Learning.