Deep Reinforcement Learning-based policy for autonomous imaging planning of small celestial bodies mapping

Gaskell, 2008, Characterizing and navigating small bodies with imaging data, Meteorit. Planet. Sci., 43, 1049, 10.1111/j.1945-5100.2008.tb00692.x Giese, 1996, The topography of asteroid Ida: a comparison between photogrammetric and two-dimensional photoclinometric image analysis, Int. Arch. Photogramm. Remote Sens., 31, B3 Capannolo, 2019, Families of bounded orbits near binary asteroid 65803 Didymos, J. Guid. Control Dyn., 42, 189, 10.2514/1.G003437 Broschart, 2014, Quasi-terminator orbits near primitive bodies, Celest. Mech. Dyn. Astron., 120, 195, 10.1007/s10569-014-9574-3 Scheeres, 2012, Orbit mechanics about asteroids and comets, J. Guid. Control Dyn., 35, 987, 10.2514/1.57247 Scheeres, 2013, Design, dynamics and stability of the osiris-rex sun-terminator orbits, Adv. Astronaut. Sci., 148, 3263 Circi, 2019, Global mapping of asteroids by frozen orbits: the case of 216 Kleopatra, Acta Astronaut., 161, 101, 10.1016/j.actaastro.2019.05.026 Zhang, 2019, Spacecraft hovering flight in a binary asteroid system by using fuzzy logic control, IEEE Trans. Aerosp. Electron. Syst., 55, 3246, 10.1109/TAES.2019.2906435 Zeng, 2016, Solar sail body-fixed hovering over elongated asteroids, J. Guid. Control Dyn., 39, 1223, 10.2514/1.G001061 Pavlak, 2015 Broschart, 2005, Control of hovering spacecraft near small bodies: application to asteroid 25143 Itokawa, J. Guid. Control Dyn., 28, 343, 10.2514/1.3890 Wen, 2020, Hop reachable domain on irregularly shaped asteroids, J. Guid. Control Dyn., 43, 1269, 10.2514/1.G004682 de Santayana, 2015, Optical measurements for Rosetta navigation near the comet Feder, 1999, Adaptive mobile robot navigation and mapping, Int. J. Robot. Res., 18, 650, 10.1177/02783649922066484 Carrillo, 2012, On the comparison of uncertainty criteria for active slam, 2080 Kollar, 2008, Trajectory optimization using reinforcement learning for map exploration, Int. J. Robot. Res., 27, 175, 10.1177/0278364907087426 Agha-mohammadi, 2003, FIRM: sampling-based feedback motion planning under motion uncertainty and imperfect measurements, Int. J. Robot. Res., 33, 268, 10.1177/0278364913501564 Izzo, 2019, A survey on artificial intelligence trends in spacecraft guidance dynamics and control, Astrodynamics, 3, 287, 10.1007/s42064-018-0053-6 Gaudet, 2020, Reinforcement learning for angle-only intercept guidance of maneuvering targets, Aerosp. Sci. Technol., 99, 10.1016/j.ast.2020.105746 Zhou, 2020, Incremental model based online heuristic dynamic programming for nonlinear adaptive tracking control with partial observability, Aerosp. Sci. Technol., 105, 10.1016/j.ast.2020.106013 Riedmiller, 2005, Neural fitted q iteration – first experiences with a data efficient neural reinforcement learning method, 317 Mnih, 2015, Human-level control through deep reinforcement learning, Nature, 518, 529, 10.1038/nature14236 Li, 2006, Autonomous navigation and guidance for landing on asteroids, Aerosp. Sci. Technol., 10, 239, 10.1016/j.ast.2005.12.003 Shang, 2018, Parameter estimation for optimal asteroid transfer trajectories using supervised machine learning, Aerosp. Sci. Technol., 79, 570, 10.1016/j.ast.2018.06.002 Pesce, 2018, Autonomous navigation & mapping of small bodies, 1 Chan, 2019, Autonomous imaging and mapping of small bodies using deep reinforcement learning Piccinin, 2020, Deep reinforcement learning approach for small bodies shape reconstruction enhancement, 1909 Sutton, 2018 Durrant-Whyte, 2006, Simultaneous localization and mapping: part I, IEEE Robot. Autom. Mag., 13, 99, 10.1109/MRA.2006.1638022 Bailey, 2006, Simultaneous localization and mapping (slam): part II, IEEE Robot. Autom. Mag., 13, 108, 10.1109/MRA.2006.1678144 Cadena, 2016, Past, present, and future of simultaneous localization and mapping: toward the robust-perception age, IEEE Trans. Robot., 32, 1309, 10.1109/TRO.2016.2624754 Mihaylova, 2002, A comparison of decision making criteria and optimization methods for active robotic sensing, 316 Jiang, 2020, Path planning for asteroid hopping rovers with pre-trained deep reinforcement learning architectures, Acta Astronaut., 171, 265, 10.1016/j.actaastro.2020.03.007 Géron, 2017 Riedmiller, 1993, A direct adaptive method for faster backpropagation learning: the rprop algorithm, 586