用100次示范实现航天器精准控制，比传统方法更高效平滑。
Action Chunking with Transformers for Image-Based Spacecraft Guidance and Control
- 将动作分块与Transformer结合，从少量专家示范中学习视觉-状态到推进指令的映射
- 仅用6300次环境交互即达成优于元强化学习（4000万次）的轨迹平滑性与精度
- 适用于数据稀缺场景下的航天器自主导航，尤其适合太空对接任务
我们提出一种用于航天器制导、导航与控制（GNC）的模仿学习方法，仅需100个专家示范（相当于6300次环境交互），即可实现高性能控制。该方法采用动作分块与Transformer结合的架构（ACT），将视觉与状态观测映射为推力与扭矩指令。在国际空间站（ISS）在轨对接任务上评估显示，ACT生成的轨迹更平滑、控制更一致，且显著提升样本效率。相比基于元强化学习（meta-RL）的基线方法（训练达4000万次交互），本方法在相同性能下大幅降低数据需求。
原文摘要 · Abstract (English)
We present an imitation learning approach for spacecraft guidance, navigation, and control(GNC) that achieves high performance from limited data. Using only 100 expert demonstrations, equivalent to 6,300 environment interactions, our method, which implements Action Chunking with Transformers (ACT), learns a control policy that maps visual and state observations to thrust and torque commands. ACT generates smoother, more consistent trajectories than a meta-reinforcement learning (meta-RL) baseline trained with 40 million interactions. We evaluate ACT on a rendezvous task: in-orbit docking with the International Space Station (ISS). We show that our approach achieves greater accuracy, smoother control, and greater sample efficiency.
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。