Thruster Fault and Actuation Delay State Transition Dataset

#State prediction #State transition modeling #Reinforcement learning #Fault impact assessment #On-orbit servicing robots #Thruster fault simulation #Spacecraft control validation #Fault resilience evaluation

5900
0.2GB
JSON
CATL
MOBIUSI INC

Updated:2026-11-03

AI Analysis & Value Prop

This simulation dataset captures state transitions for on-orbit servicing robots, including the robot state before control execution, commanded actions, thruster faults, execution delays, effective actions, and resulting next states. It covers anomalous conditions such as thrust deviations, thruster failures, saturation, and control delays, with state differences and transition metrics provided for analysis. Use it to train reinforcement learning dynamics models, predict robot states, and evaluate control strategies under fault conditions.

Dataset Insights

Sample Examples

{}

Technical Specifications

Field	Type	Description
file_name	string	File name
next_state	object	The robot state at the next time step after the effective action is applied and fault-conditioned dynamics evolve.
state_delta	object	The difference between the current and next states, provided for dynamics transition modeling.
current_state	object	The robot's kinematic and energy state before it executes a control action.
execution_delay	object	Delay parameters and observed outcomes for the interval between control command generation and thruster execution.
fault_condition	object	The fault type and parameters applied to a thruster or actuator in the current sample.
commanded_action	object	The desired control action sent by the controller to the left and right thrusters at the current time step.
effective_action	object	The control action received by the robot dynamics model after accounting for thruster faults and execution delays.
transition_metrics	object	State transition quality and fault impact metrics calculated from the state, action, and fault condition.

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?: Each record includes the current robot state, commanded action, thruster fault condition, execution delay, effective action, next state, state difference, and transition metrics. These fields support analysis of how anomalies affect control execution and state evolution.

Which fault conditions are represented?: The data covers anomalies in thrusters and actuation, including thrust deviations, failures, saturation, and control delays. It is simulation data for studying fault-conditioned dynamics and state prediction, not a record of actual on-orbit operations.

Which tasks can this dataset support?: It can support state transition modeling, next-state prediction for robots, dynamics model training for simulation-based reinforcement learning, thruster fault impact analysis, and evaluation of fault-resilient control.

How can I access the data, and what are the licensing terms?: Follow the download or access instructions on the product page. Review the applicable license for permitted uses and redistribution restrictions; if these terms are not stated, contact the data provider for clarification.

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={Thruster Fault and Actuation Delay State Transition Dataset},
  author={MOBIUSI INC},
  year={2026},
  url={https://www.mobiusi.com/datasets/5cc5ef79e4a131547fcff9a1042f4e93?dataset_task_cate_id=11},
  urldate={2026-10-28},
  keywords={thruster fault dataset,state transition data,on-orbit servicing robots,actuation delay simulation,robot state prediction,reinforcement learning dynamics,fault-aware control,thruster saturation data},
  version={1.0}
}

Using this in research? Please cite us.

placeholder

Scene

Domain

Modality

Task