most citedSafety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents

14 citations · 14 across the 6 of their papers we have counts for

collaborators

11 papers

cs.LG2025

scipy.spatial.transform: Differentiable Framework-Agnostic 3D Transformations in Python

Martin Schuck, Alexander von Rohr, Angela P. Schoellig

Three-dimensional rigid-body transforms, i.e. rotations and translations, are central to modern differentiable machine learning pipelines in robotics, vision, and simulation. Howev…

cs.RO2025

Improving Drone Racing Performance Through Iterative Learning MPC

Haocheng Zhao, Niklas Schlüter, Lukas Brunke +1

Autonomous drone racing presents a challenging control problem, requiring real-time decision-making and robust handling of nonlinear system dynamics. While iterative learning model…

cs.RO2025

Where Did I Leave My Glasses? Open-Vocabulary Semantic Exploration in Real-World Semi-Static Environments

Benjamin Bogenberger, Oliver Harrison, Orrin Dahanaggamaarachchi +4

Robots deployed in real-world environments, such as homes, must not only navigate safely but also understand their surroundings and adapt to changes in the environment. To perform…

cs.RO2025

Deploying SICNav in the Field: Safe and Interactive Crowd Navigation using MPC and Bilevel Optimization

Sepehr Samavi, Garvish Bhutani, Florian Shkurti +1

Safe and efficient navigation in crowded environments remains a critical challenge for robots that provide a variety of service tasks such as food delivery or autonomous wheelchair…

eess.SY2025

Addressing Relative Degree Issues in Control Barrier Function Synthesis with Physics-Informed Neural Networks

Lukas Brunke, Siqi Zhou, Francesco D'Orazio +1

In robotics, control barrier function (CBF)-based safety filters are commonly used to enforce state constraints. A critical challenge arises when the relative degree of the CBF var…

cs.RO2025

SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions

Sepehr Samavi, Anthony Lem, Fumiaki Sato +5

To navigate crowds without collisions, robots must interact with humans by forecasting their future motion and reacting accordingly. While learning-based prediction models have sho…