This thesis explores sensor fusion techniques and hardware solutions to advance self-driving cars. It provides a historical overview, conducts a literature review, and analyzes various sensors (cameras, LiDAR, radar, IMUs) in terms of cost and performance. The research introduces advanced sensor fusion algorithms and cost-effective hardware solutions to seamlessly integrate data from different sensors, addressing challenges in existing systems. Real-world testing and simulations validate the proposed system's effectiveness under diverse driving conditions, contributing valuable insights to the autonomous vehicle industry and paving the way for further advancements in self-driving technology.