Double Deep Q Networks for Sensor Management in Space Situational Awareness

TL;DR

This paper applies a Double Deep Q Network reinforcement learning approach to optimize sensor management for space situational awareness, effectively improving satellite tracking with limited sensors.

Contribution

It introduces a novel DDQN-based method for sensor management in SSA, demonstrating its effectiveness through simulation and state covariance reduction.

Findings

DDQN policy reduces state covariance compared to random policy

Reinforcement learning improves satellite tracking efficiency

Simulation results support further development of RL in SSA

Abstract

We present a novel Double Deep Q Network (DDQN) application to a sensor management problem in space situational awareness (SSA). Frequent launches of satellites into Earth orbit pose a significant sensor management challenge, whereby a limited number of sensors are required to detect and track an increasing number of objects. In this paper, we demonstrate the use of reinforcement learning to develop a sensor management policy for SSA. We simulate a controllable Earth-based telescope, which is trained to maximise the number of satellites tracked using an extended Kalman filter. The estimated state covariance matrices for satellites observed under the DDQN policy are greatly reduced compared to those generated by an alternate (random) policy. This work provides the basis for further advancements and motivates the use of reinforcement learning for SSA.