用深度强化学习实现航天器长期任务调度，高效可靠。
Deep RL for Fast Long-Horizon Operations Scheduling on NASA's Carruthers Geocorona Observatory Mission
- 引入活动块与动态动作掩码，解决大规模约束调度难题。
- 训练耗时不足6小时，生成方案可行性超99%，优于传统启发式方法。
- 已作为默认调度系统部署于真实航天任务，适合复杂工程场景应用。
航天器任务调度是一个高度受限、长周期的组合优化问题，传统方法依赖启发式算法、约束规划或人工设计。本文为美国宇航局卡鲁瑟斯日地辉光观测任务开发并部署了一种可扩展的深度强化学习框架。该框架采用名为“活动块”的宏观动作抽象，并结合动态动作掩码机制，有效应对难以处理的大规模搜索空间，严格满足电力、热控及仪器等复杂约束。所提架构以极高概率生成全局可行的调度方案，建立操作信任，且可在六小时内完成完整训练周期，无需依赖策略鲁棒性，支持快速按需重训。此外，生成的调度方案在科学数据采集质量上显著优于基准启发式方法。该深度强化学习框架自任务启动起即作为默认操作调度器投入使用，证明深度强化学习可在复杂、动态变化的约束下应用于真实航天器运行。
原文摘要 · Abstract (English)
Spacecraft operations scheduling is a highly constrained, long-horizon combinatorial optimization problem that traditionally relies on heuristics, constraint programming, or manual planning. We present a scalable deep reinforcement learning framework developed and deployed for NASA's Carruthers Geocorona Observatory mission. Our framework introduces a macro-action abstraction known as activity blocks coupled with dynamic action-masking to navigate the intractably large search space and strictly enforce complex power, thermal, and instrument constraints. The resulting architecture generates globally feasible schedules with overwhelming probability, establishes operational trust, and executes a full training cycle in under six hours, circumventing the need for policy robustness by enabling rapid, on-demand retraining. Further, resulting schedules outperform baseline heuristics in scheduled science quality. The deep reinforcement learning framework was deployed as the default operational scheduler for the Carruthers Geocorona Observatory mission from the outset of the mission, demonstrating that deep reinforcement learning can be trusted for real spacecraft operations under complex, evolving constraints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。