Research

Scholar

I study how robots can learn complex behaviors in unstructured environments, combining robotics and machine learning.

Space robotics: manipulation and mobility for in-orbit servicing and planetary exploration, such as contact-rich assembly, regolith excavation and driving on granular terrain.
Reinforcement learning: model-based, model-free and continual methods for adaptive control, with a focus on sample efficiency and reward-free adaptation to changing conditions.
Modeling and simulation: procedural scene generation, domain randomization and high-fidelity physics for sim-to-real transfer.

Publications

2026 5 publications

arXiv preprint

PINGU: Extending Air-Bearing Spacecraft Emulators with Open-Source Actuators and Learned Control for Contact-Rich Proximity Operations

Ricard Marsal i Castan, Akiyoshi Uchida, Aman Arora, Pedro Lima, Matteo El Hariry, Andrej Orsula, Francesco Grella, Antoine Richard, Cédric Pradalier, Miguel Olivares-Mendez

PDF HTML Website Code

@article{marsalicastan2026pingu,
  title         = {{PINGU: Extending Air-Bearing Spacecraft Emulators with Open-Source Actuators and Learned Control for Contact-Rich Proximity Operations}},
  author        = {Marsal i Castan, Ricard and Uchida, Akiyoshi and Arora, Aman and Lima, Pedro and El Hariry, Matteo and Orsula, Andrej and Grella, Francesco and Richard, Antoine and Pradalier, C\'{e}dric and Olivares-Mendez, Miguel},
  journal       = {arXiv:2609.23554},
  year          = {2026},
  doi           = {10.48550/arXiv.2609.23554},
  eprint        = {2609.23554},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

i-SAIRAS & iSpaRo 2026

Fleet-to-Lab: A Transfer Learning Framework for Lunar Rover Slippage Estimation via Model Fusion

Riccardo Viviano, Saki Omi, Andrej Orsula, Miguel Olivares-Mendez

PDF HTML Code

@article{viviano2026fleettolab,
  title         = {{Fleet-To-Lab: A Transfer Learning Framework For Lunar Rover Slippage Estimation Via Model Fusion}},
  author        = {Viviano, Riccardo and Omi, Saki and Orsula, Andrej and Olivares-Mendez, Miguel},
  journal       = {arXiv:2609.17187},
  year          = {2026},
  doi           = {10.48550/arXiv.2609.17187},
  eprint        = {2609.17187},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

arXiv preprint

FALCON-S: Fixed-Wing Ground-Effect Aerodynamics Simulator and Flight Control Learning Suite

Matteo El Hariry, Pedro Lima, Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez

PDF HTML Code

@article{elhariry2026falcons,
  title         = {{FALCON-S: Fixed-wing ground-effect Aerodynamics Simulator and Flight Control Learning Suite}},
  author        = {El Hariry, Matteo and Lima, Pedro and Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel},
  journal       = {arXiv:2609.06046},
  year          = {2026},
  doi           = {10.48550/arXiv.2609.06046},
  eprint        = {2609.06046},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

SPAICE 2026

Reward-Free Continual Adaptation for Resilient Space Robots

Andrej Orsula, Miguel Olivares-Mendez, Carol Martinez

PDF HTML Code

@article{orsula2026rewardfree,
  title         = {{Reward-Free Continual Adaptation for Resilient Space Robots}},
  author        = {Orsula, Andrej and Olivares-Mendez, Miguel and Martinez, Carol},
  journal       = {arXiv:2608.23452},
  year          = {2026},
  doi           = {10.48550/arXiv.2608.23452},
  eprint        = {2608.23452},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

arXiv preprint

Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks

Ricard Marsal i Castan, Aman Arora, Antoine Richard, Andrej Orsula, Cédric Pradalier, Miguel Olivares-Mendez

PDF HTML Code

@article{marsalicastan2026learning,
  title         = {{Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks}},
  author        = {Marsal i Castan, Ricard and Arora, Aman and Richard, Antoine and Orsula, Andrej and Pradalier, C\'{e}dric and Olivares-Mendez, Miguel},
  journal       = {arXiv:2607.24292},
  year          = {2026},
  doi           = {10.48550/arXiv.2607.24292},
  eprint        = {2607.24292},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

2025 7 publications

PhD Thesis University of Luxembourg

Robot Learning Beyond Earth: Enabling Adaptive Autonomy in Space

Andrej Orsula

PDF Website Code

@phdthesis{orsula2025robot,
  title  = {{Robot Learning Beyond Earth: Enabling Adaptive Autonomy in Space}},
  author = {Orsula, Andrej},
  school = {University of Luxembourg},
  year   = {2025},
  url    = {https://hdl.handle.net/10993/67015},
}

IAC 2025

RL-AVIST: Reinforcement Learning for Autonomous Visual Inspection of Space Targets

Matteo El Hariry, Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez

PDF HTML Code

@inproceedings{elhariry2025rlavist,
  title     = {{RL-AVIST: Reinforcement Learning for Autonomous Visual Inspection of Space Targets}},
  author    = {El Hariry, Matteo and Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel},
  booktitle = {76th International Astronautical Congress (IAC)},
  year      = {2025},
  publisher = {International Astronautical Federation (IAF)},
  pages     = {602--610},
  doi       = {10.52202/083093-0058},
}

arXiv preprint

Space Robotics Bench: Robot Learning Beyond Earth

Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

PDF HTML Video Website Code

@article{orsula2025space,
  title         = {{Space Robotics Bench: Robot Learning Beyond Earth}},
  author        = {Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel and Martinez, Carol},
  journal       = {arXiv:2509.23328},
  year          = {2025},
  doi           = {10.48550/arXiv.2509.23328},
  eprint        = {2509.23328},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

ASTRA 2025

Learning Tool-Aware Adaptive Compliant Control for Autonomous Regolith Excavation

Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

PDF HTML Code

@inproceedings{orsula2025learning,
  title         = {{Learning Tool-Aware Adaptive Compliant Control for Autonomous Regolith Excavation}},
  author        = {Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel and Martinez, Carol},
  booktitle     = {18th Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA)},
  year          = {2025},
  doi           = {10.48550/arXiv.2509.05475},
  eprint        = {2509.05475},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

iSpaRo 2025

Sim2Dust: Mastering Dynamic Waypoint Tracking on Granular Media

Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

PDF HTML Code

@inproceedings{orsula2025simdust,
  title     = {{Sim2Dust: Mastering Dynamic Waypoint Tracking on Granular Media}},
  author    = {Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel and Martinez, Carol},
  booktitle = {2025 International Conference on Space Robotics (iSpaRo)},
  year      = {2025},
  pages     = {336--342},
  doi       = {10.1109/iSpaRo66239.2025.11436990},
}

ICRA 2025 Workshop on Enhancing Dexterity in Space Environments

Learning Compliant Manipulation in Space

Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

PDF

@inproceedings{orsula2025learningb,
  title     = {{Learning Compliant Manipulation in Space}},
  author    = {Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel and Martinez, Carol},
  booktitle = {IEEE International Conference on Robotics and Automation (ICRA) Workshop on Enhancing Dexterity in Space Environments: The Potential of Soft Robotic Systems},
  year      = {2025},
  url       = {https://hdl.handle.net/10993/67133},
}

IAC 2025

Advancing Adaptive Autonomy Through Procedural Space Environments

Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

@inproceedings{orsula2025advancing,
  title     = {{Advancing Adaptive Autonomy Through Procedural Space Environments}},
  author    = {Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel and Martinez, Carol},
  booktitle = {76th International Astronautical Congress (IAC)},
  year      = {2025},
  publisher = {International Astronautical Federation (IAF)},
  pages     = {96--105},
  doi       = {10.52202/083093-0011},
}

2024 5 publications

CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data

Towards Benchmarking Robotic Manipulation in Space

Andrej Orsula, Antoine Richard, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

PDF Code

@inproceedings{orsula2024towards,
  title     = {{Towards Benchmarking Robotic Manipulation in Space}},
  author    = {Orsula, Andrej and Richard, Antoine and Geist, Matthieu and Olivares-Mendez, Miguel and Martinez, Carol},
  booktitle = {CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data},
  year      = {2024},
  url       = {https://openreview.net/forum?id=nIAlBA0oKA},
}

IEEE Access

GraspLDM: Generative 6-DoF Grasp Synthesis Using Latent Diffusion Models

Kuldeep R. Barad, Andrej Orsula, Antoine Richard, Jan Dentler, Miguel Olivares-Mendez, Carol Martinez

PDF HTML Video Code

@article{barad2024graspldm,
  title     = {{GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Models}},
  author    = {Barad, Kuldeep R. and Orsula, Andrej and Richard, Antoine and Dentler, Jan and Olivares-Mendez, Miguel and Martinez, Carol},
  journal   = {IEEE Access},
  year      = {2024},
  volume    = {12},
  pages     = {164621--164633},
  doi       = {10.1109/ACCESS.2024.3492118},
  publisher = {IEEE},
}

iSpaRo 2024

Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space

Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

PDF HTML Code

@inproceedings{orsula2024leveraging,
  title        = {{Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space}},
  author       = {Orsula, Andrej and Geist, Matthieu and Olivares-Mendez, Miguel and Martinez, Carol},
  booktitle    = {2024 International Conference on Space Robotics (iSpaRo)},
  year         = {2024},
  pages        = {357--364},
  doi          = {10.1109/iSpaRo60631.2024.10688111},
  organization = {IEEE},
}

NeurIPS 2024 Datasets and Benchmarks Track

A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-World Robotics

Puze Liu, Jonas Günster, Niklas Funk, Simon Gröger, Dong Chen, Haitham Bou-Ammar, Julius Jankowski, Ante Marić, Sylvain Calinon, Andrej Orsula, et al.

PDF HTML Talk

@inproceedings{liu2024retrospective,
  title     = {{A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics}},
  author    = {Liu, Puze and G\"{u}nster, Jonas and Funk, Niklas and Gr\"{o}ger, Simon and Chen, Dong and Bou-Ammar, Haitham and Jankowski, Julius and Mari\'{c}, Ante and Calinon, Sylvain and Orsula, Andrej and Olivares-Mendez, Miguel and Zhou, Hongyi and Lioutikov, Rudolf and Neumann, Gerhard and Likmeta, Amarildo and Zhalehmehrabi, Amirhossein and Bonenfant, Thomas and Restelli, Marcello and Tateo, Davide and Liu, Ziyuan and Peters, Jan},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2024},
  pages     = {9690--9726},
  volume    = {37},
  doi       = {10.52202/079017-0309},
}

VR 2024 Abstracts and Workshops

Immersive Rover Control and Obstacle Detection Based on Extended Reality and Artificial Intelligence

Sofía Coloma, Alexandre Frantz, Dave van der Meer, Ernest Skrzypczyk, Andrej Orsula, Miguel Olivares-Mendez

PDF HTML

@inproceedings{coloma2024immersive,
  title        = {{Immersive Rover Control and Obstacle Detection based on Extended Reality and Artificial Intelligence}},
  author       = {Coloma, Sof\'{i}a and Frantz, Alexandre and van der Meer, Dave and Skrzypczyk, Ernest and Orsula, Andrej and Olivares-Mendez, Miguel},
  booktitle    = {2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)},
  year         = {2024},
  pages        = {743--744},
  doi          = {10.1109/VRW62533.2024.00168},
  organization = {IEEE},
}

2023 1 publication

NeurIPS 2023 Robot Air Hockey Challenge

Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning

Andrej Orsula

PDF HTML Video Talk Code

@article{orsula2023learning,
  title         = {{Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning}},
  author        = {Orsula, Andrej},
  journal       = {arXiv:2406.00518},
  year          = {2024},
  doi           = {10.48550/arXiv.2406.00518},
  eprint        = {2406.00518},
  archiveprefix = {arXiv},
  primaryclass  = {cs.RO},
}

2022 1 publication

IROS 2022

Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning

Andrej Orsula, Simon Bøgh, Miguel Olivares-Mendez, Carol Martinez

PDF HTML Video Talk Code

@inproceedings{orsula2022learning,
  title        = {{Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning}},
  author       = {Orsula, Andrej and B{\o}gh, Simon and Olivares-Mendez, Miguel and Martinez, Carol},
  booktitle    = {2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year         = {2022},
  pages        = {4112--4119},
  doi          = {10.1109/IROS47612.2022.9981661},
  organization = {IEEE},
}

2021 1 publication

Master’s Thesis Aalborg University

Deep Reinforcement Learning for Robotic Grasping from Octrees: Learning Manipulation from Compact 3D Observations

Andrej Orsula

PDF Video Website Code

@mastersthesis{orsula2021deep,
  title  = {{Deep Reinforcement Learning for Robotic Grasping from Octrees: Learning Manipulation from Compact 3D Observations}},
  author = {Orsula, Andrej},
  type   = {Master's Thesis},
  school = {Aalborg University},
  year   = {2021},
}