用隐空间建模让卫星自主避障，91.7%成功率。
Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents
- 两阶段隐空间模型预测轨道动态，支持长时程推演。
- 在模拟环境中实现91.7%的避障成功率达行业领先。
- 适合航天智能导航、自主决策研究者参考。
面向在轨导航任务的卫星代理需基于有限星上观测预测碰撞风险。然而，传统规划器常依赖预设地图与固定环境假设，难以适应动态在轨场景。本文提出Orbit-Planner，一种用于在轨障碍物避让的两阶段隐世界模型。该模型学习动作条件下的航天器动力学，在隐空间中执行未来状态推演，并引入物理探针，从想象的隐轨迹中解码物理状态变化。实验表明，Orbit-Planner可实现长时程隐空间推演，并从想象轨迹中恢复物理状态。在Isaac Sim中的闭环避障导航测试中，成功率高达91.7%。代码已开源：https://github.com/ZhijianLi2003/Orbit_Planner。
原文摘要 · Abstract (English)
Satellite agents for on-orbit navigation tasks need to predict collision risks using limited onboard observations. However, conventional planners often rely on predefined maps and fixed environmental assumptions, limiting their adaptability in dynamic on-orbit scenarios. In this paper, we propose Orbit-Planner, a two-stage latent world model for on-orbit obstacle avoidance. Orbit-Planner learns action-conditioned spacecraft dynamics to perform future-state rollouts in latent space, and introduces a Physics Probe to decode physical state changes from imagined latent trajectories. Experiments demonstrate that Orbit-Planner can perform long-horizon latent rollouts and recover physical states from imagined trajectories. In closed-loop obstacle-avoidance navigation in Isaac Sim, it attains a success rate of 91.7%. Code is available at https://github.com/ZhijianLi2003/Orbit_Planner.
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。