MARSHA is part of a research project at Northwest Nazarene University studying the use of Meta-Reinforcement Learning for robotics to account for inaccuracies between simulation and real-world, zero-gravity physics.
View Aaron Borger's Computer Science Thesis
This project is focused on researching a novel method to train an artificial intelligent robot in simulation and then continue learning in the real-wolrd space environment. The payload has been manifested on a Terrier-Improved Malemute Sounding Rocket that will be launched from NASA's Wallops Flight Facility in August 2022. This work seeks to develop the building block for intelligent astro-robotics by learning to catch a ball in space. Subsequent versions may be able to use the same method to learn to grasp uncontrollable, non-uniform objects in space. This effort will be beneficial towards solving multiple challenging problems such as assembling and servicing spacecraft in orbit by learning to manipulate tools and components in zero gravity as well as space debris removal by learning to catch resident space objects.
This repository contains software to control the robotic arms from two different platforms. The Embedded-Platform branch is designed for an Nvidia Jetson Nano while the Auxiliary-Platform branch is designed for interfacing or simulating the robotic arms.
This work is a work in progress so installation procedures have not been written yet. Documentation is currently being written and will be linked as soon as it is presentable. The software will be finalized by May 2022 as the payload is scheduled to launch in August 2022.