Enhancing Space Situational Awareness with AI and Optimization Techniques

Abstract

As space becomes increasingly congested and contested, ensuring the safe operation of satellites has emerged as a critical concern for both public and private sector stakeholders. The growing number of active satellites and space debris significantly increases the risk of collisions, making Space Situational Awareness (SSA) an essential capability for modern space operations. SSA aims to provide timely and accurate assessments of space objects’ trajectories to prevent collisions and maintain the long-term sustainability of space activities.

Currently, SSA processes are heavily reliant on human operators who must analyze large volumes of data from multiple sources, identify high-priority risks, interpret and validate information, and ultimately make decisions regarding collision risks. While computational tools assist in these processes, the dependence on human judgment introduces limitations, including delays in decision-making and potential errors in critical assessments. Given the increasing complexity of the space environment, there is a pressing need for automated and data-driven approaches to enhance SSA capabilities.

A fundamental challenge within SSA is orbit prediction—the ability to accurately forecast the future trajectories of space objects. However, precise trajectory estimation alone is not sufficient, as some scenarios require active collision avoidance maneuvers. In such cases, decision support systems must generate reliable and efficient maneuver plans to ensure satellites can safely adjust their orbits without unnecessary fuel expenditure or operational disruptions.

This thesis addresses both orbit prediction and collision avoidance through a combination of machine learning and optimization techniques. First, a transformer-based deep learning model is trained using publicly available data to predict space object trajectories with high accuracy and computational efficiency. This approach leverages advances in sequence modeling to improve predictive performance in dynamic orbital environments. Next, Reinforcement Learning (RL) techniques are employed to develop an autonomous decision-making framework that generates optimized collision avoidance maneuvers for satellites. By learning from simulated interactions, the RL-based approach aims to provide adaptive and fuel-efficient avoidance strategies. Finally, a Sequential Convex Optimization (SCvx) approach is explored to solve the collision avoidance problem from a purely optimization-driven perspective without relying on data-driven models. This method ensures mathematically rigorous maneuver planning based on physical constraints and operational requirements.

This work contributes to the advancement of SSA by enhancing the accuracy of orbit prediction and the reliability of collision avoidance strategies. Besides that, this work has the potential to improve automation in space traffic management, reducing reliance on human operators and increasing the resilience of satellite operations.