Abstract: The advancement of Autonomous Vehicle technology hinges on the system’s ability to perceive its surroundings accurately and make timely, intelligent decisions. One of the major challenges in autonomous navigation is achieving reliable perception in dynamic and complex environments. This paper investigates the integration and fusion of heterogeneous sensors to improve situational awareness and decision-making for autonomous vehicles. The data from multiple sensors are combined by the system which includes LiDAR, RADAR, Ultrasonic Sensors, and RGB cameras, it is observed that the data from each of the sensor is found to be complementary about the environment. LiDAR offers precise depth and 3D mapping, cameras feed the visual data in the view of object detection, radar is effective when the visibility is poor, and ultrasonic sensors support close-range obstacle detection. Through the technique of sensor fusion, the strengths of each sensor are leveraged while minimizing their individual weaknesses.

Simulation environments are developed using MATLAB, where realistic driving scenarios are created with various actors (vehicles, pedestrians, static objects) and environmental conditions. The data from the various sensors are processed through perception algorithms to perform object detection, classification, and tracking. Based on the interpreted environment, decision-making algorithms enable actions such as lane- maintenance, obstacle avoidance, and speed control.

The results demonstrate that a multi-sensor fusion approach significantly enhances the reliability, accuracy, and robustness of autonomous vehicle perception and decision-making, particularly in challenging scenarios. This work contributes to the design of safer, more intelligent self-driving systems and lays a foundation for future improvements in real-world autonomous navigation.

Keywords: Autonomous Vehicle, Muti sensor, Data fusion, perception, Decision making.

Downloads: | DOI: 10.17148/IARJSET.2026.13120