Space exploration and establishing human presence on other planets demand advanced technology and effective collaboration between robots and astronauts. Efficient space resource utilization is also vital for extraterrestrial settlements. The Collaborative In-Situ Resources Utilisation (CISRU) project has developed a software suite comprising five key modules. The first module manages multi-agent autonomy, facilitating communication between agents and mission control. The second focuses on environment perception, employing AI algorithms for tasks like environment segmentation and object pose estimation. The third module ensures safe navigation, covering obstacle avoidance, social navigation with astronauts, and cooperation among robots. The fourth module addresses manipulation functions, including multi-tool capabilities and tool-changer design for diverse tasks in In-Situ Resources Utilization (ISRU) scenarios. Finally, the fifth module controls cooperative behaviour, incorporating astronaut commands, Mixed Reality interfaces, map fusion, task supervision, and error control. The suite was tested using an astronaut-rover interaction dataset in a planetary environment and GMV SPoT analogue environments. Results demonstrate the advantages of E4 autonomy and AI in space systems, benefiting astronaut-robot collaboration. This paper details CISRU's development, field test preparation, and analysis, highlighting its potential to revolutionize planetary exploration through AI-powered technology.

翻译：太空探索以及在其它行星上建立人类存在需要先进技术和机器人与宇航员之间的有效协作。高效的太空资源利用对于地外定居点也至关重要。协作式原位资源利用（CISRU）项目开发了一套包含五个关键模块的软件套件。第一模块管理多智能体自主性，促进智能体与任务控制中心之间的通信。第二模块专注于环境感知，采用AI算法执行环境分割和物体姿态估计等任务。第三模块确保安全导航，涵盖避障、与宇航员的社交导航以及机器人间的协作。第四模块处理操作功能，包括多工具能力和适用于原位资源利用（ISRU）场景中多样化任务的工具更换器设计。最后，第五模块控制协作行为，整合宇航员指令、混合现实界面、地图融合、任务监督和错误控制。该套件在行星环境下的宇航员-漫游车交互数据集以及GMV SPoT模拟环境中进行了测试。结果表明E4自主性和AI在太空系统中的应用具有优势，有利于宇航员-机器人协作。本文详细介绍了CISRU的开发、现场测试准备和分析，凸显了其通过人工智能技术革新行星探索的潜力。