The recent advancements in robotics and satellite trajectory management have shown significant progress in enhancing precision and adaptability. In the realm of robotics, there is a notable shift towards developing systems capable of high-precision local navigation and manipulation tasks. This trend is driven by the need for robots to perform complex tasks with centimeter-level accuracy, such as docking and inspection, which require precise relative positioning. Additionally, the integration of multi-modal perception and simulation-based training is enabling robots to achieve robust performance in real-world scenarios without extensive fine-tuning. In satellite trajectory management, the focus has been on improving the accuracy of predicting and mitigating the effects of solar radiation pressure on Low Earth Orbit (LEO) satellites. This involves the development of semi-analytical models combined with machine learning techniques to enhance the precision of trajectory predictions. These models leverage historical data and real-time inputs to refine predictions, offering a deeper understanding of the underlying physics and enabling more accurate adjustments. Overall, the field is moving towards more integrated and adaptive systems that combine traditional analytical methods with modern machine learning approaches to achieve higher levels of precision and robustness in both robotics and satellite trajectory management.