sislaboratory
owm-iss-numerical-v1-noncoop-goal-dt50ms-500k
Spacecraft docking dataset featuring a 12-tonne Dragon-class chaser maneuvering to the International Space Station from 100-225 meters away under realistic orbital mechanics with sensor noise from non-cooperative navigation.
Downloads0
Episodes121
Hours7.73
Why This Matters for Physical AI
This dataset demonstrates world-model training for spacecraft autonomous rendezvous and docking under realistic orbital dynamics and sensor constraints, providing a benchmark for learning-based control in high-stakes aerospace applications.
Technical Profile
- Modalities
- proprioceptionrgbstate_vector
- Robot Embodiments
- spacecraft
- Action Space
- end_effector_delta
- Environment
- simulation
- Task Types
- dockingnavigation
- Episodes
- 121
- Total Hours
- 7.73
- Data Format
- LeRobot
- Annotation Types
- reward_labelsaction_labels
Access
Need custom proprioception data?
Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.
Request a Sample Pack