13 papers
Safe Reinforcement Learning with Receding-Horizon Safety Critic and Differentiable Action Shields
Siwei Ju, Jan Peters, Oleg Arenz
Despite the Markov assumption, safety failures in robot reinforcement learning rarely occur instantaneously; they typically emerge over several steps as the policy enters unfamilia…
A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning
Anish Diwan, Jan Peters, Oleg Arenz
Inverse Reinforcement Learning (IRL) is classically solved using Lagrangian optimisation, by jointly optimising a primal-dual problem with gradient descent to obtain the optimal re…
Continue, Abort, or Fall: Viability-Aware Policy Selection (VAPS) for Safe Humanoid Acrobatics
Siwei Ju, Lu Liu, Jan Peters +1
Dynamic humanoid motions such as flips risk hardware damage due to suboptimal policies, disturbances or sim-to-real gaps. A motion tracking policy offers no way out once the maneuv…
ExoLaN: Physics-Consistent Context-Aware Dynamics Learning for Exoskeletons
Lucas Schulze, Maximilian Schwarz, Jona Hoppe +2
Task-agnostic assistive exoskeleton control based on human intention offers greater flexibility than conventional approaches that rely on predefined tasks or motion patterns. Human…
Embedding Physics Priors in Robot Learning: A Survey
Mattia Piccinini, Lucas Schulze, Alice Plebe +10
The rapid progress of artificial intelligence is reshaping robotics and accelerating the adoption of learning-based approaches. While purely data-driven methods have achieved remar…
Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control
Siwei Ju, Jan Tauberschmidt, Oleg Arenz +2
Learning high-performance control policies that remain consistent with expert behavior is a fundamental challenge in robotics. Reinforcement learning can discover high-performing s…
GaussTwin: Unified Simulation and Correction with Gaussian Splatting for Robotic Digital Twins
Yichen Cai, Paul Jansonnie, Cristiana de Farias +2
Digital twins promise to enhance robotic manipulation by maintaining a consistent link between real-world perception and simulation. However, most existing systems struggle with th…
Mathematical Foundations of Modeling ETL Process Chains
Levin Maier, Lucas Schulze, Robert Lilow +10
Extract-Transform-Load (ETL) processes are core components of modern data processing infrastructures. The throughput of processed data records can be adjusted by changing the amoun…
Floating-Base Deep Lagrangian Networks
Lucas Schulze, Juliano Decico Negri, Victor Barasuol +4
Grey-box methods for system identification combine deep learning with physics-informed constraints, capturing complex dependencies while improving out-of-distribution generalizatio…
Context-Aware Deep Lagrangian Networks for Model Predictive Control
Lucas Schulze, Jan Peters, Oleg Arenz
Controlling a robot based on physics-consistent dynamic models, such as Deep Lagrangian Networks (DeLaN), can improve the generalizability and interpretability of the resulting beh…
Maximum Total Correlation Reinforcement Learning
Bang You, Puze Liu, Huaping Liu +2
Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward fu…
Learning Hierarchical Domain Models Through Environment-Grounded Interaction
Claudius Kienle, Benjamin Alt, Oleg Arenz +1
Domain models enable autonomous agents to solve long-horizon tasks by producing interpretable plans. However, in open-world environments, a single general domain model cannot captu…
QueryCAD: Grounded Question Answering for CAD Models
Claudius Kienle, Benjamin Alt, Darko Katic +2
CAD models are widely used in industry and are essential for robotic automation processes. However, these models are rarely considered in novel AI-based approaches, such as the aut…