Bridging Reinforcement Learning and Online Learning for Spacecraft Attitude Control
- 1 January 2022
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 19 (1), 62-69
- https://doi.org/10.2514/1.i010958
Abstract
Artificial intelligence is expected to revolutionize all areas of space operations in the coming years. The most advanced space systems will possess the ability to adapt and improve performance over time, or online learning. This work presents a novel framework that uses the highly researched artificial intelligence paradigm, reinforcement learning, to perform online learning. The spacecraft attitude control problem is used as a benchmark, with experimental results for using reinforcement learning to train neural spacecraft attitude controllers. Additionally, experimental results in a simulation environment are also shown to compare and contrast two state-of-the-art single-agent continuous control reinforcement learning algorithms to motivate their use in the online learning scenario.Keywords
This publication has 17 references indexed in Scilit:
- Robot Online Learning Through Digital Twin Experiments: A Weightlifting ProjectLecture Notes in Networks and Systems, 2017
- In-Datacenter Performance Analysis of a Tensor Processing UnitACM SIGARCH Computer Architecture News, 2017
- In-Datacenter Performance Analysis of a Tensor Processing UnitPublished by Association for Computing Machinery (ACM) ,2017
- Human-level control through deep reinforcement learningNature, 2015
- Geometric Integration of QuaternionsJournal of Guidance, Control, and Dynamics, 2013
- The Digital Twin Paradigm for Future NASA and U.S. Air Force VehiclesPublished by American Institute of Aeronautics and Astronautics (AIAA) ,2012
- High‐Water Marks and Hedge Fund Management ContractsThe Journal of Finance, 2003
- Attitude Error Representations for Kalman FilteringJournal of Guidance, Control, and Dynamics, 2003
- Accurate and Efficient Simulation of Rigid-Body RotationsJournal of Computational Physics, 2000
- Self-improving reactive agents based on reinforcement learning, planning and teachingMachine Learning, 1992