Intelligent mission planning for autonomous distributed satellite systems

System autonomy plays a critical role in the success of next generation Distributed Satellite Systems (DSS) mission architectures, enabling the inference of external and internal environment conditions to support system adaptation in unexpected and unfamiliar situations. Artificial Intelligence (AI) based techniques show promise in achieving this desired self-adaptive capability by offering on-board predictive real time analytics, supporting an evolution towards Trusted Autonomous Satellite Operations (TASO). In parallel, TASO requires an evolution of the control and coordination of increasingly autonomous large scale DSS, achieved in the design and operation of intelligent Mission Planning Systems (MPS). In this paper, we focus on intelligent mission planning functionality problem utilising a distributed ant colony optimisation approach to achieve local task allocation and platform coordination. The approach is implemented in the context of a Space-Based Space Surveillance (SBSS) mission architecture that considers self-adaptive capabilities, global coordination and supervisory control aspects. The effectiveness of the approach is shown, demonstrating that the proposed solution based on metaheuristics supports an efficient and pervasive SBSS capability.