We Choose to Go to Space:
Agent-driven Human and Multi-Robot Collaboration in Microgravity

Miao Xin1* , Zhongrui You2 ✝ , Zihan Zhang3✝, Taoran Jiang4✝, Tingjia Xu5✝, Haotian Liang4✝, Guojing Ge1, Yuchen Ji6✝, Shentong Mo7, Jian Cheng1
1Institute of Automation, Chinese Academy of Sciences, 2Beijing University of Posts and Telecommunications, 3TongJi University, 4Beihang University, 5Beijing Normal University, 6Nanjing University of Aeronautics and Astronautics,
7Carnegie Mellon University,
Paper arXiv Video

SpaceAgents-1 IJCAI 2024 Demo

Abstract

We present SpaceAgents-1, a system for learning human and multi-robot collaboration (HMRC) strategies under microgravity conditions. Future space exploration requires humans to work together with robots. However, acquiring proficient robot skills and adept collaboration under microgravity conditions poses significant challenges within ground laboratories. To address this issue, we develop a microgravity simulation environment and present three typical configurations of intra-cabin robots. We propose a hierarchical heterogeneous multi-agent collaboration architecture: guided by foundation models, a Decision-Making Agent serves as a task planner for human-robot collaboration, while individual Skill-Expert Agents manage the embodied control of robots. This mechanism empowers the SpaceAgents-1 system to execute a range of intricate long-horizon HMRC tasks.

BibTeX

@article{xin2024we,
  title={We Choose to Go to Space: Agent-driven Human and Multi-Robot Collaboration in Microgravity},
  author={Xin, Miao and You, Zhongrui and Zhang, Zihan and Jiang, Taoran and Xu, Tingjia and Liang, Haotian and Ge, Guojing and Ji, Yuchen and Mo, Shentong and Cheng, Jian},
  journal={arXiv preprint arXiv:2402.14299},
  year={2024}
}