Title :
The autonomous sciencecraft experiment
Author :
Sherwood, Rob ; Chien, Steve ; Castano, Rebecca ; Rabideau, Gregg
Author_Institution :
Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA
Abstract :
The Autonomous Sciencecraft Experiment (ASE) will fly onboard the Air Force TechSat 21 constellation of three spacecraft scheduled for launch in 2006. ASE uses onboard continuous planning, robust task and goal-based execution, model-based mode identification and reconfiguration, and onboard machine learning and pattern recognition to radically increase science return by enabling intelligent downlink selection and autonomous retargeting. In this paper we discuss how these AI technologies are synergistically integrated in hybrid multi-layer control architecture to enable to virtual spacecraft science agent. Demonstration of these capabilities in a flight environment will open up tremendous new opportunities in planetary science, space physics, and earth science that would be unreachable without this technology.
Keywords :
aerospace instrumentation; learning (artificial intelligence); pattern recognition; space communication links; space vehicles; virtual instrumentation; AD 2006; AI technologies; ASE; TechSat 21 constellation; autonomous retargeting; autonomous sciencecraft experiment; earth science; flight environment; goal-based execution; intelligent downlink selection; model-based mode identification; multilayer control architecture; onboard continuous planning; onboard machine learning; pattern recognition; planetary science; science return; space physics; virtual spacecraft science agent; Artificial intelligence; Downlink; Geoscience; Learning systems; Machine learning; Pattern recognition; Physics; Robustness; Space technology; Space vehicles;
Conference_Titel :
Aerospace Conference, 2003. Proceedings. 2003 IEEE
Print_ISBN :
0-7803-7651-X
DOI :
10.1109/AERO.2003.1235068
