NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU)processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We apply supervised learning using real data to estimate the soil mass collected without the need for mass flow rate monitors or other explicate sensing techniques. We also create a reduced-order simulation environment to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. Our initial results suggest that excavated regolith mass can be inferred within 2.9% RMS error of full scale, and reinforcement learning for autonomous operations has learned viable trenching strategies and helped identify desirable sensing capabilities, arrangements, and considerations. Future work includes regolith mass estimation during dynamic operation, expanding our simulation to more complex environments, and transfer learning from simulation to hardware.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen


    Exportieren, teilen und zitieren



    Titel :

    ICE-RASSOR: Intelligent Capabilities Enhanced Regolith Advanced Surface Systems Operations Robot


    Beteiligte:
    Michael Dupuis (Autor:in) / Joe Cloud (Autor:in) / Evan Bell (Autor:in) / Andrew Nick (Autor:in) / Bradley C Buckles (Autor:in) / Thomas John Muller (Autor:in) / Kurt W Leucht (Autor:in) / Drew Smith (Autor:in) / Jennifer G Wilson (Autor:in)

    Kongress:

    Lunar Surface Innovation Consortium Virtual Fall Meeting ; 2020 ; Virtual Meeting, US


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Keine Angabe


    Sprache :

    Englisch




    Regolith Advanced Surface Systems Operations Robot (RASSOR)

    Mueller, Robert P. / Cox, Rachel E. / Ebert, Tom et al. | IEEE | 2013


    Design of an Excavation Robot: Regolith Advanced Surface Systems Operations Robot (RASSOR) 2.0

    R. P. Mueller / J. D. Smith / J. M. Schuler et al. | NTIS | 2016


    Design of an Excavation Robot: Regolith Advanced Surface Systems Operations Robot (RASSOR) 2.0

    Robert P Mueller / Jonathan D Smith / Jason M Schuler et al. | NTRS | 2016


    ICE-RASSOR (Intelligent Capabilities Enhanced-Regolith Advanced Surface Systems Operations Robot)

    Michael Dupuis / Bradley Buckles / Joseph Cloud et al. | NTRS | 2021