6 papers
Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control
Johannes Hechtl, Yannik Blei, Simon Ball +5
While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target pos…
TACTIC: Understanding Tactile Encoders and Conditioning for Contact-rich Robot Manipulation Policies
Seongjin Bien, Débora Oliveira Makowski, Carlo Kneissl +6
Tactile information is essential for contact-rich manipulation tasks in robotics. Vision-based tactile sensors make it particularly easy to design end-to-end manipulation policies…
Norm2Tex: Augmenting Visuo-Tactile Simulations with Texture
Seongjin Bien, Débora Oliveira Makowski, Roberto Calandra +2
Large-scale datasets are essential for training generalist robot control policies. Collecting real-world tactile data is costly and time-consuming, motivating the use of tactile si…
FlowTouch: View-Invariant Visuo-Tactile Prediction
Seongjin Bien, Carlo Kneissl, Tobias Jülg +6
Tactile sensation is essential for contact-rich manipulation tasks. It provides direct feedback on object geometry, surface properties, and interaction forces, enhancing perception…
VLAgents: A Policy Server for Efficient VLA Inference
Tobias Jülg, Khaled Gamal, Nisarga Nilavadi +5
The rapid emergence of Vision-Language-Action models (VLAs) has a significant impact on robotics. However, their deployment remains complex due to the fragmented interfaces and the…
Robot Control Stack: A Lean Ecosystem for Robot Learning at Scale
Tobias Jülg, Pierre Krack, Seongjin Bien +7
Vision-Language-Action models (VLAs) mark a major shift in robot learning. They replace specialized architectures and task-tailored components of expert policies with large-scale d…