🤖 AI Summary
This work addresses the challenge of manipulating deformable cargo transfer bags (CTBs) with the Astrobee robot in microgravity. We propose a sampling-based model predictive control (MPC) framework driven by a reduced-order model (ROM). To this end, we develop pyastrobee—an open-source Python simulation environment—that enables, for the first time, real-time closed-loop ROM control of a high-fidelity deformable finite-element CTB model. The controller achieves stable grasping, deformation suppression, and precise pose regulation of the CTB at 10 Hz. Our approach overcomes the longstanding technical bottleneck of real-time closed-loop manipulation of soft goods in microgravity, significantly improving controller computational efficiency and robustness. The implementation is fully open-source, thoroughly documented, and compatible with NASA’s Astrobee hardware interface. It establishes a verifiable simulation baseline and a novel control paradigm for autonomous on-orbit cargo handling.
📝 Abstract
We present pyastrobee: a simulation environment and control stack for Astrobee in Python, with an emphasis on cargo manipulation and transport tasks. We also demonstrate preliminary success from a sampling-based MPC controller, using reduced-order models of NASA's cargo transfer bag (CTB) to control a high-order deformable finite element model. Our code is open-source, fully documented, and available at https://danielpmorton.github.io/pyastrobee