Deformable Cargo Transport in Microgravity with Astrobee

Morton, Daniel, Antonova, Rika, Coltin, Brian, Pavone, Marco, Bohg, Jeannette

arXiv.org Artificial Intelligence 

--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. Looking towards the future of space station logistics and maintenance, any extended uncrewed periods will have to rely on autonomous operations for tasks such as resupply and preparation of the station before/after crew arrival [1]. In particular, to deliver supplies to the Gateway station autonomously, a robot such as Astrobee [2] or Robonaut [3] will need to transport cargo from a docked vehicle to a desired location in the station. However, the deformability of the vinyl cargo transfer bags (CTBs) makes this a difficult problem to solve.