THESIS PROJECT
AI for Electric Orbit Raising

Project Description

About

At Vinterstellar, we design tools and strategies for the future of satellite operations. We’re now offering a Master Thesis project that explores how Artificial Intelligence (AI) and Machine Learning (ML) can revolutionize Electrical Orbit Raising (EOR) trajectory optimization — making the process faster, smarter, and more robust.

Thesis Objective

The goal is to develop AI-based methods that can solve or approximate the EOR optimization problem directly. Moving beyond traditional iterative solvers, you will investigate how deep learning and reinforcement learning can learn the underlying structure of the EOR problem and predict optimal thrust strategies — reducing computation time and improving solution robustness.

What You’ll Gain

 

    • Hands-on experience in applied AI/ML for space systems
    • Insights into orbital mechanics, trajectory design, and optimization
    • Skills in combining numerical optimization with data-driven methods
    • A chance to contribute to the development of Vinterstellar’s in-house orbit analysis tools
    • Direct collaboration with engineers and researchers in the Swedish space ecosystem

What you will work on

    • Dataset Generation: Automate the creation of training datasets from existing EOR optimization runs and simulations
    • Model Development: Explore supervised learning, reinforcement learning, and physics-informed models for trajectory generation
    • Pipeline Development: Build a modular end-to-end system integrating data generation, model training, evaluation, and inference
    • Benchmarking: Compare AI-driven solutions with classical optimization in terms of speed, convergence reliability, and trajectory quality (ΔV, time of flight, eccentricity control)

Location & Collaboration

  • Work closely with the Vinterstellar team
  • Duration: ~5 months (thesis project)
  • Flexible setup (remote or hybrid with touchpoints in Sweden)

How to Apply

Send your CV, transcript, and a short motivation letter to: career@vinterstellar.se

Applications reviewed continuously.

Who Should Apply?

We’re looking for motivated master’s students in:

  • Aerospace Engineering (with focus on astrodynamics or mission analysis)
  • Computer Science / Data Science (with interest in space applications)
  • Engineering Physics, Applied Mathematics, or similar fields

An ideal candidate has strong programming skills in Python, experience with ML frameworks (TensorFlow, PyTorch, Scikit-learn), and a genuine curiosity about applying AI to real-world space engineering problems.