Salvato in:
Dettagli Bibliografici
Autori principali: Xin, Miao, You, Zhongrui, Zhang, Zihan, Jiang, Taoran, Xu, Tingjia, Liang, Haotian, Ge, Guojing, Ji, Yuchen, Mo, Shentong, Cheng, Jian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2402.14299
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917595622408192
author Xin, Miao
You, Zhongrui
Zhang, Zihan
Jiang, Taoran
Xu, Tingjia
Liang, Haotian
Ge, Guojing
Ji, Yuchen
Mo, Shentong
Cheng, Jian
author_facet Xin, Miao
You, Zhongrui
Zhang, Zihan
Jiang, Taoran
Xu, Tingjia
Liang, Haotian
Ge, Guojing
Ji, Yuchen
Mo, Shentong
Cheng, Jian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_14299
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle We Choose to Go to Space: Agent-driven Human and Multi-Robot Collaboration in Microgravity
Xin, Miao
You, Zhongrui
Zhang, Zihan
Jiang, Taoran
Xu, Tingjia
Liang, Haotian
Ge, Guojing
Ji, Yuchen
Mo, Shentong
Cheng, Jian
Robotics
Artificial Intelligence
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.
title We Choose to Go to Space: Agent-driven Human and Multi-Robot Collaboration in Microgravity
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2402.14299