Efficient Path Estimation via Sensor Fusion of IMU, GPS, and Wheel Encoder and Control Parameter Optimization

In autonomous vehicles, precise estimation of control parameters is essential for ensuring safety, adaptability, and energy efficiency. However, standalone estimators often fall short due to their inability to detect sharp turns, wheel skidding, and slippage, along with their high computational demands. This study presents a fusion model that integrates GPS, IMU, and wheel encoder data to accurately estimate control parameters while maintaining safety and adaptability under varying environmental conditions. The model also determines the optimal tack of the vehicle using these estimated parameters. Extensive testing demonstrated the model's superior ability to detect subtle changes, identify wheel skidding and slippage, and outperform state-of-the-art stand alone and fusion models in computational efficiency. This research marks a significant advancement in au-tonomous vehicle technology, offering a robust and sophisticated tool for precise control parameter estimation and optimal path prediction.