As space systems become more complex and capable, the control logic required for optimal operations similarly increases in complexity. Generally, decision space dimensionality increases exponentially with input and linearly with output. Technology miniaturization and increasing access to launch capacity enable large networks of these complex systems. Proliferation of these complex systems of systems means automation is necessary for cost e_ective management of per-spacecraft and network-wide operations.
This paper presents a Hierarchical Ensembles of Autonomous Decision Systems, or HEADS, system with a recursive ensemble weighting update. The hierarchical structure enables multi-layered logic for granular control and decisions incorporating inferred information. The control output from each ensemble is a mixture from independently trained fuzzy systems processed through a gating network, with weights updated recursively. Each expert uses a subset of the input space, minimizing per-expert complexity while supporting ensemble robustness under uncertain or evolving state realizations and operating environments. Finally, autonomy based on fuzzy systems o_ers the potential for increased human comprehension of an agent's status and decision logic. The proposed ight control system is demonstrated through simulation of a notional remote sensing spacecraft. Performance results under competing mission criteria are shown.
AUTONOMOUS FLIGHT CONTROL USING HIERARCHICAL ENSEMBLES OF AUTONOMOUS DECISION SYSTEMS
Proceedings of the 44th Annual American Astronautical Society Guidance, Navigation, and Control Conference, 2022 ; Chapter : 75 ; 1369-1390
2024-01-01
22 pages
Article/Chapter (Book)
Electronic Resource
English
European Patent Office | 2023
|Real-Time Decision Making for Autonomous Flight Control
SAE Technical Papers | 1989
|Hierarchical control systems for autonomous space robots
AIAA | 1988
|