Panagiotis Petropoulakis

Munich, Germany

Originally from 🇬🇷

I am Panagiotis Petropoulakis, a Ph.D. researcher at the Chair of Computing in Civil and Building Engineering (CCBE) and the Georg Nemetschek Institute (GNI) at the Technical University of Munich (TUM). I am also a doctoral candidate at the TUM School of Computation, Information and Technology (CIT), affiliated with the Chair of Robotics, Artificial Intelligence and Real-Time Systems under Prof. Alois Knoll.

My research focuses on construction robotics, mobile manipulation, state representation learning, traversability, Sim2Real transfer, and long-horizon reasoning for autonomous robots operating in complex and unstructured environments.

I investigate how learning-based perception, geometric and semantic representations, and structured reasoning can be combined with planning and control to enable robots to understand construction tasks, execute them safely in the physical world, verify task completion, and recover from failures.

My work spans reliable mobile-robot navigation, terrain-aware motion planning, mobile manipulation, task-aware decision-making, and the integration of digital construction information with physical robotic execution.

Our time is limited, so we should use it wisely. I choose to spend mine on four things I love: my passion for research, staying active and healthy through sports and nutritious food, connecting with family and friends, and volunteering. I am passionate about being involved in initiatives related to children interested in technology and women in tech.

My goal through my research and projects is to connect with people, both to offer and to learn from them, and ideally, to leave a positive impact.

For additional information, please visit my blog, browse my student projects, and have a look at my CV.

news

Aug 15, 2024	Our article State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping has been accepted at the IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2024

selected publications

arXiv
Scalix: Uncertainty-Aware Scale-Consistent Monocular SLAM

Sebastian Barbas Laina, Tianyi Zhang, Panagiotis Petropoulakis, and 5 more authors

arXiv preprint arXiv:2608.17553, Aug 2026

Abs arXiv Bib HTML PDF

Cameras are ubiquitous sensors in robotics due to their compact form factor and the perceptual richness captured through visual information. Monocular SLAM enables robots to understand the environment with a minimum setup, however, it inherently suffers from scale ambiguity. A common solution is to provide multi-modal sensor configurations, such as visual-inertial systems, where scale is observable unless the robot navigates under a constant-velocity motion, a common scenario in mobile robotics. With the advent of deep-learning, geometric foundation models have been used to address this problem, but the depth maps are often noisy and scale-inconsistent across frames. In this paper, we propose Scalix, a real-time monocular SLAM framework that achieves metric-scale state estimation by integrating learned depth cues into a probabilistic factor-graph formulation. By augmenting existing monocular depth models with both per-pixel depth uncertainty and per-frame scale uncertainty, Scalix treats scale predictions as independent measurements within its optimization, leading to improved scale consistency through multi-view data associations. Experiments in large-scale outdoor and indoor environments demonstrate state-of-the-art performance on both metric and up-to-scale benchmarks while maintaining real-time operation and generalization.
@article{Laina:2026:Scalix, title = {Scalix: Uncertainty-Aware Scale-Consistent Monocular SLAM}, author = {Laina, Sebastian Barbas and Zhang, Tianyi and Petropoulakis, Panagiotis and Schaefer, Simon and Boche, Simon and Jung, Jaehyung and Gentil, Cedric Le and Leutenegger, Stefan}, year = {2026}, month = aug, journal = {arXiv preprint arXiv:2608.17553}, doi = {10.48550/arXiv.2608.17553}, }
SMC
State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

Panagiotis Petropoulakis^*, Ludwig Gräf^*, Mohammadhossein Malmir^†, and 2 more authors

In 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Kuching, Malaysia, Oct 2024

Abs arXiv Bib HTML PDF Video Code

Choosing an appropriate representation of the environment for the underlying decision-making process of the reinforcement learning agent is not always straightforward. The state representation should be inclusive enough to allow the agent to informatively decide on its actions and disentangled enough to simplify policy training and the corresponding sim2real transfer. Given this outlook, this work examines the effect of various representations in incentivizing the agent to solve a specific robotic task: antipodal and planar object grasping. A continuum of state representations is defined, starting from hand-crafted numerical states to encoded image-based representations, with decreasing levels of induced task-specific knowledge. The effects of each representation on the ability of the agent to solve the task in simulation and the transferability of the learned policy to the real robot are examined and compared against a model-based approach with complete system knowledge. The results show that reinforcement learning agents using numerical states can perform on par with non-learning baselines. Furthermore, we find that agents using image-based representations from pre-trained environment embedding vectors perform better than end-to-end trained agents, and hypothesize that separation of representation learning from reinforcement learning can benefit sim2real transfer. Finally, we conclude that incentivizing the state representation with task-specific knowledge facilitates faster convergence for agent training and increases success rates in sim2real robot control.
@inproceedings{Petropoulakis:2024:StateRep, title = {State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping}, author = {Petropoulakis, Panagiotis and Gräf, Ludwig and Malmir, Mohammadhossein and Josifovski, Josip and Knoll, Alois}, year = {2024}, month = oct, booktitle = {2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, location = {Kuching, Malaysia}, doi = {10.1109/SMC54092.2024.10832053}, }