Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents
2026-08-17 • Robotics
RoboticsArtificial Intelligence
AI summaryⓘ
The authors developed Orbit-Planner, a system that helps satellites avoid collisions while orbiting Earth using limited onboard data. Instead of relying on fixed maps, their method predicts future spacecraft positions by imagining different scenarios internally. They also created a way to understand physical changes from these imagined situations. Tests showed Orbit-Planner can successfully avoid obstacles most of the time in a simulated environment.
on-orbit navigationcollision avoidancelatent world modelspacecraft dynamicsfuture-state rolloutPhysics Probeclosed-loop controlIsaac Simsimulationrobotic planning
Authors
Zhijian Li, Chao Ren, Peijin Wang, Xian Sun
Abstract
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.