The Regolith Advanced Surface Systems Operations Robot (RASSOR) Excavator is a mobile robotic bucket-drum excavator platform with a unique space regolith excavation capability. The Intelligent Capabilities Enhanced RASSOR research project developed functionality for estimating the quantity of regolith mass ingested during RASSOR operation, enhancing RASSOR’s ability to successfully complete In-Situ Resource Utilization (ISRU) missions. To teleoperate or run autonomously, it is crucial for the amount of regolith mass ingested to be available as a system state for efficient operation. For example, during autonomous operation, RASSOR should navigate and move to a processing plant to offload the collected regolith when the drums are full; without knowledge of the total mass in the drums, this type of high-level planning is not possible. Three distinct modeling approaches were employed in developing a mass inferencing approach that could work on RASSOR, none of which require modification to the hardware. All take in system states, such as arm/drum motor positions, velocities, currents, voltages, and robot pose, and output a mass prediction for each set of the robot’s bucket drums. The developed models run in real-time, outputting predictions for the front drum mass, rear drum mass, timestamp of the last prediction, and total drum mass (sum of front and rear) in RASSOR’s drums. Models deployed to the hardware have low error (<7.5% mean error over the mass range, and <2.6% mean error when drums are more than half full) when making predictions in real-time. Our modeling approach can be adapted to use lunar excavation data to create models that are reflective of RASSOR’s dynamics when operating on the lunar surface. The results of this work are promising and show that models can be developed to accurately estimate excavated regolith mass.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Mass Inferencing Model Creation and Deployment to the RASSOR Lunar Excavation Robot


    Contributors:

    Conference:

    ASCEND Conference ; 2021 ; Online / Las Vegas, US


    Type of media :

    Miscellaneous


    Type of material :

    No indication


    Language :

    English





    MASS INFERENCING MODEL CREATION AND DEPLOYMENT TO THE RASSOR LUNAR EXCAVATION ROBOT

    Janmohamed, Nashir A. / Cloud, Joe M. / Leucht, Kurt W. et al. | TIBKAT | 2021


    Mass Inferencing Model Creation and Deployment to the RASSOR Lunar Excavation Robot

    N. A. Janmohamed / J. M. Cloud / K. W. Leucht et al. | NTIS | 2021



    Mass Inferencing Model Creation and Deployment to the RASSOR Lunar Excavation Robot

    Nashir A Janmohamed / Joseph M Cloud / Kurt W Leucht et al. | NTRS