8 papers
Data and Learning Where it Matters for Contact-Rich Manipulation
Oliver Hausdörfer, Linus Schwarz, Gabor Marko +7
Learned policies trained end-to-end on large datasets often remain brittle in high-precision tasks and struggle with generalization. We find that these limitations largely stem fro…
CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
Ralf Römer, Yi Zhang, Yuming Li +1
To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe upd…
From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies
Ralf Römer, Julian Balletshofer, Jakob Thumm +3
Diffusion policies (DPs) achieve state-of-the-art performance on complex manipulation tasks by learning from large-scale demonstration datasets, often spanning multiple embodiments…
CRISP -- Compliant ROS2 Controllers for Learning-Based Manipulation Policies and Teleoperation
Daniel San José Pro, Oliver Hausdörfer, Ralf Römer +3
Learning-based controllers, such as diffusion policies and vision-language action models, often generate low-frequency or discontinuous robot state changes. Achieving smooth refere…
Failure Prediction at Runtime for Generative Robot Policies
Ralf Römer, Adrian Kobras, Luca Worbis +1
Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. However, distribution shifts from un…
ARMimic: Learning Robotic Manipulation from Passive Human Demonstrations in Augmented Reality
Rohan Walia, Yusheng Wang, Ralf Römer +3
Imitation learning is a powerful paradigm for robot skill acquisition, yet conventional demonstration methods--such as kinesthetic teaching and teleoperation--are cumbersome, hardw…