Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SmallSatSim: A High-Fidelity Simulation and Training Toolkit for Microgravity Robotic Close Proximity Operations

David Schwartz, Alexander Hansson, Sabrina Bodmer, David Sternberg, Oliver Jia-Richards, Keenan Albee

Abstract

Microgravity rendezvous and close proximity operations (RPO) is a growing area of interest for applications spanning in-space assembly and manufacturing (ISAM), orbital debris remediation, and small body exploration. Microgravity environments present unique challenges for robotic control and planning algorithms for new agile RPO mission scenarios like free-floating manipulation, planning under failure, and estimating high-fidelity dynamics of tumbling bodies. To facilitate the development and testing of novel RPO algorithms, we introduce SmallSatSim, a high-fidelity simulation toolkit that leverages the MuJoCo physics engine to accurately model small satellite RPO dynamics in local microgravity robotic free-flight settings, including under model disturbances and perturbations. The framework includes cutting edge out-of-the-box free-flyer control techniques. A GPU-accelerated pipeline using MuJoCo MJX and JAX is implemented for sampling- and learning-based simulation uses cases. SmallSatSim also supports configurable failure models, enabling the evaluation of safe control strategies under adversarial conditions. Visualization, logging, and GPU-enabled parallelization further enhance SmallSatSim's capability for RPO testing. We outline SmallSatSim's features and intended use cases, and demonstrate its use for robotic RPO planning and control. The open-sourced toolkit aims to accelerate research in autonomous, agile robotic small satellite operations.

SmallSatSim: A High-Fidelity Simulation and Training Toolkit for Microgravity Robotic Close Proximity Operations

Abstract

Microgravity rendezvous and close proximity operations (RPO) is a growing area of interest for applications spanning in-space assembly and manufacturing (ISAM), orbital debris remediation, and small body exploration. Microgravity environments present unique challenges for robotic control and planning algorithms for new agile RPO mission scenarios like free-floating manipulation, planning under failure, and estimating high-fidelity dynamics of tumbling bodies. To facilitate the development and testing of novel RPO algorithms, we introduce SmallSatSim, a high-fidelity simulation toolkit that leverages the MuJoCo physics engine to accurately model small satellite RPO dynamics in local microgravity robotic free-flight settings, including under model disturbances and perturbations. The framework includes cutting edge out-of-the-box free-flyer control techniques. A GPU-accelerated pipeline using MuJoCo MJX and JAX is implemented for sampling- and learning-based simulation uses cases. SmallSatSim also supports configurable failure models, enabling the evaluation of safe control strategies under adversarial conditions. Visualization, logging, and GPU-enabled parallelization further enhance SmallSatSim's capability for RPO testing. We outline SmallSatSim's features and intended use cases, and demonstrate its use for robotic RPO planning and control. The open-sourced toolkit aims to accelerate research in autonomous, agile robotic small satellite operations.
Paper Structure (16 sections, 6 equations, 6 figures, 3 tables)

This paper contains 16 sections, 6 equations, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. A Simulation Environment for Microgravity Close Prox Ops
  4. Physics Backends
  5. Key Customizable Features
  6. Simulation Structure
  7. Environments, Models, and More
  8. 6DoF Model
  9. Perturbation and Disturbance Modeling
  10. Contact and Collision Modeling
  11. Reinforcement Learning Support
  12. Demonstration Use Cases
  13. Lunar Gateway Inspection under Thruster Failures
  14. Rendezvous and Docking with Soft Contacts
  15. Massively Parallel Simulation and Training
  16. ...and 1 more sections

Figures (6)

  • Figure 1: A visualization of some of SmallSatSim's simulation environments, showcasing a space station, trajectory visualization, and a microgravity free-flyer.
  • Figure 2: Overview of the SmallSatSim simulation architecture and its interaction with MuJoCo. BaseController and BasePlanner provide templates for interaction with customizable environments. Utilities to enable reinforcement learning-based control are detailed in Figure \ref{['fig:rl']}.
  • Figure 3: The data flow for SmallSatSim's reinforcement learning pipeline.
  • Figure 4: SmallSatSim using the Gateway environment and the NominalMPCController with the MissionPlanner Inspection Planner. Early uses of SmallSatSim have included safe free-flyer inspection of cislunar stations under thruster failures albeeArchitectingAutonomySafe2025.
  • Figure 5: Rendezvous and docking with soft contacts, controlled by NominalMPCController. The simulation continues through contact. Plots show contact force magnitude and dock position error over time.
  • ...and 1 more figures