跳到正文
Science Robotics· Daniel M. Gaines, Gregg R. Rabideau, Stephen R. Kuhn, Steve A. Chien, Elyse Moffi, Edward Benowitz, Vincent Wong·· 21 天前AI 评分38

《火星2020 OnBoard Planner:提升“毅力号”火星车自主任务效率》

The Mars 2020 OnBoard Planner: Increasing autonomy mission productivity of the Perseverance rover

AI 导读

《Science Robotics》第11卷第119期(2026年10月)刊载的OnBoard Planner系统研究显示,该系统可提升“毅力号”火星车的自主任务效率。研究聚焦火星2020任务在轨规划能力,具体样本量、效应量与数据开放情况原文未提供。

原文摘要

出版方登记 · Crossref

Operators of planetary rovers, under strict energy and thermal constraints, face substantial challenges in maintaining high levels of rover productivity because of conservative ground-based planning and long communication latencies. In October 2023, to overcome these limits and increase science return, the Mars 2020 mission deployed OnBoard Planner into Perseverance rover operations. OnBoard Planner uses artificial intelligence constraint–based search to dynamically construct and modify activity schedules on board, adapting to real-time changes in rover state and martian environmental conditions. By replacing conservative ground predictions with real-time resource tracking, the system dynamically adjusts heating durations, reclaims unused schedule margin, and inserts opportunistic activities when extra resources become available. Here, we report on OnBoard Planner’s performance on Mars across more than 2 years of surface operations. The results demonstrate that OnBoard Planner increased discretionary rover activity by 10.5% overall while also improving the thermal and temporal conditions for certain types of scientific observations. Furthermore, the system achieved these productivity gains without increasing ground operations timelines. These findings are part of why OnBoard Planner has successfully become a standard part of Mars 2020 operations and demonstrate how dynamic onboard autonomy can enable resource-efficient operations for complex robotic systems in deep-space environments.

页面未能读取全文,以上为出版方登记的摘要;方法与图表见原文

来源:Science Robotics · science.org