Ego-Motion Estimation for Autonomous Vehicles Based on Genetic Algorithms and CUDA Parallel Processing

Estimating ego-motion in autonomous vehicles is critical for tasks such as localization, navigation, obstacle avoidance, and so on. While traditional methods often rely on direct pose estimation or AI-based approaches, these can be computationally intensive, especially for small, incremental movements typically observed between consecutive frames. In this work, we propose a brute-force-based ego-motion estimation algorithm that takes advantage of the constraints of autonomous vehicles, which are assumed to have only three degrees of freedom (x, y, and yaw). Our approach is based on a genetic algorithm to efficiently explore potential vehicle movements. By generating an initial seed of random motion candidates and iteratively mutating and selecting the best-performing individuals, we minimize the cost function that measures image similarity between frames. Furthermore, we implement the algorithm using CUDA to exploit parallel processing, significantly improving computational speed. Experimental results demonstrate that our approach achieves accurate ego-motion estimation with high efficiency, making it suitable for real-time autonomous vehicle applications.