Non-Cooperative Target Relative Motion Prediction Dataset

#Relative state prediction #Trajectory prediction #State transition modeling #Reinforcement learning evaluation #On-orbit servicing #Autonomous approach #Non-cooperative target rendezvous #Spacecraft relative navigation

5960
0.4GB
JSON
CATL
MOBIUSI INC

Updated:2026-11-03

AI Analysis & Value Prop

Designed for relative motion modeling in on-orbit servicing, this dataset describes the initial relative pose and motion state, target spin, external force and torque disturbances, robot control actions, and simulation configuration. Dynamics simulations produce future relative motion trajectories and next-state prediction targets, accompanied by trajectory statistics for training and evaluating single-step or sequence prediction models. The data supports verifiable-reward reinforcement learning (RLVR), state transition modeling, and research on on-orbit approach and rendezvous scenarios.

Dataset Insights

Sample Examples

{}

Technical Specifications

Field	Type	Description
file_name	string	File name
control_action	object	Translational and rotational control commands applied by the servicing robot during the current prediction window.
simulation_config	object	Dynamics simulation time step, prediction horizon, and target dynamics parameters used to generate the relative motion trajectory.
target_spin_state	object	Spin axis, rotation rate, and initial rotation phase of the non-cooperative target.
trajectory_statistics	object	Statistics computed from the complete future trajectory, including measures of approach, velocity, and attitude change.
disturbance_conditions	object	External force, torque, and noise disturbances applied to the relative motion system during simulation.
initial_relative_state	object	Relative pose and motion state of the servicing robot and non-cooperative target at the start of the prediction window.
future_relative_trajectory	array	Sequence of future relative poses and velocities computed by dynamics simulation, usable as a supervised target for sequence prediction.
next_state_prediction_target	object	First subsequent state extracted from the future trajectory, used to validate single-step relative motion predictions.

Compliance Statement

Authorization Type	Proprietary - Commercial AI Training License (No Redistribution)
Commercial Use	Requires exclusive subscription or authorization contract (monthly or per-invocation charging)
Privacy and Anonymization	No PII, no real company names, simulated scenarios follow industry standards
Compliance System	Compliant with China's Data Security Law / EU GDPR / supports enterprise data access logs

Frequently Asked Questions

What does the dataset contain?: Samples can include the initial relative state, target spin state, disturbance conditions, control actions, and simulation configuration. They also provide future relative motion trajectories, next-state prediction targets, and trajectory statistics.

Is this real flight data or simulation data?: This is simulation data. Future trajectories and next-state targets are computed using dynamics simulation, making the data suitable for training and evaluating prediction models under known generation conditions. For real missions, assess the gap between the simulation and the operational environment.

Which training and evaluation tasks does it support?: It can support single-step relative state prediction, future trajectory prediction, state transition modeling, and validation of prediction outcomes for RLVR. Configure each task according to the dataset fields and the model's input and output definitions.

How can I obtain the data, and what are the licensing terms?: Check the dataset product page for available access methods, file specifications, and licensing terms. The information provided here does not specify a license, so confirm the applicable terms with the listing or data provider before use.

Can't find the data you need?

Post a request and let data providers reach out to you.

Get this Dataset

Verified for Enterprise Use

Cite this Work

@dataset{Mobiusi2026,
  title={Non-Cooperative Target Relative Motion Prediction Dataset},
  author={MOBIUSI INC},
  year={2026},
  url={https://www.mobiusi.com/datasets/0793cd23ddb70e4960613a4358a2cac7},
  urldate={2026-10-28},
  keywords={non-cooperative target dataset,relative motion prediction,on-orbit servicing robot,spacecraft rendezvous,state prediction,dynamics simulation,RLVR dataset,trajectory prediction},
  version={1.0}
}

Using this in research? Please cite us.

placeholder

Scene

Domain

Modality

Task