With the increase of car's number, the problem of insufficient parking space in cities is becoming more and more prominent. The high-density parking lots using parking robots can greatly improve space utilization. However, there is a great collision risk in the parking lot's tight space navigation. So, precise LIDAR localization and trajectory tracking control are the key technologies of autonomous driving along a predetermined path. Due to the laser points' sparse character, the LIDAR points' extracted features have distribution errors. In order to further optimize the LIDAR's localization, this study establishes the feature's error ellipsoid model, and the model's information and error entropies are calculated separately. The error entropy is utilized to optimize the feature-matching weight and improve the localization accuracy. Based on the higher localization result, a state-of-the-art lateral tracking model is proposed to address the challenges faced by the long parking robot. Then, the adaptive fuzzy control is designed to achieve precise control of wheel motion. Finally, an experimental platform is built to compare the effectiveness of different positioning and tracking algorithms. The comparison results show that the integration of laser evaluation localization and lateral tracking optimization algorithm can provides a collision-free improvement of 50 % in the parking lot's tight spaces.