arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.05985cs.RO
收藏

AI赋能的下一代火星车表面操作能力

AI-Enabled Capabilities to Facilitate Next-Generation Rover Surface Operations

GMV Aerospace and Defence SAU(GMV航空航天与防御西班牙分公司);GMV NSL

Cristina Luna, Robert Field, Steven Kay

AI总结:

本研究提出集成AI系统,通过障碍物检测、多机器人协调和地形分类,显著提升火星车行驶速度与安全性,并在模拟环境中验证至技术就绪水平4级。

摘要:

当前行星探测车以约10厘米/秒的行驶速度运行,从根本上限制了探测效率。本研究提出了集成AI系统,通过三个组件显著提升自主性:(i)FASTNAV远距离障碍物检测器(FOD),基于计算机视觉的障碍物检测,能够支持持续1.0米/秒的行驶速度;(ii)CISRU,一种多机器人协调框架,实现人机协作以进行原位资源利用;(iii)基于深度学习的ViBEKO和AIAXR地形分类研究。在火星模拟环境中的现场验证表明,这些系统达到技术就绪水平4级,为下一代行星任务在行驶速度、分类精度和操作安全性方面提供了可衡量的改进。

英文摘要:

Current planetary rovers operate at traverse speeds of approximately 10 cm/s, fundamentally limiting exploration efficiency. This work presents integrated AI systems which significantly improve autonomy through three components: (i) the FASTNAV Far Obstacle Detector (FOD), capable of facilitating sustained 1.0 m/s speeds via computer vision-based obstacle detection; (ii) CISRU, a multi-robot coordination framework enabling human-robot collaboration for in-situ resource utilisation; and (iii) the ViBEKO and AIAXR deep learning-based terrain classification studies. Field validation in Mars analogue environments demonstrated these systems at Technology Readiness Level 4, providing measurable improvements in traverse speed, classification accuracy, and operational safety for next-generation planetary missions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑