1

High-Resolution Pixelwise Contact Area and Normal Force Estimation for the GelSight Mini Visuotactile Sensor Using Neural Networks
This work presents a training procedure and a pretrained model that can estimate the normal force distribution and the contact area acting upon the GelSight Mini visuotactile sensor. The representation maps from the raw output images of the sensor to the normal force distribution acting across the entire sensor surface. This is appealing as it allows to directly do classical force control based on the output of visuotactile sensors. Moreover, it yields a physically grounded, interpretable representation of the tactile signals.
Niklas Funk, Paul-Otto Mueller, Boris Belousov, Anton Savchenko, Rolf Findeisen, Jan Peters
PDF Cite Project
High-Resolution Pixelwise Contact Area and Normal Force Estimation for the GelSight Mini Visuotactile Sensor Using Neural Networks
Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery
Robot assembly discovery is a challenging problem that lives at the intersection of resource allocation and motion planning. The goal …
Niklas Funk, Svenja Menzenbach, Georgia Chalvatzaki, Jan Peters
PDF Cite Project
SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion
We propose learning task-space, data-driven cost functions as diffusion models. Diffusion models represent expressive multimodal distributions and exhibit proper gradients over the entire space. We exploit these properties for motion optimization by integrating the learned cost functions with other costs in a single objective function, and optimize all of them jointly by gradient descent.
Niklas Funk, Julen Urain, Georgia Chalvatzaki, Jan Peters
PDF Cite Project
SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion
Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery
Spotlight Presentation and Poster Presentation! - Robot assembly discovery is a challenging problem that lives at the intersection of …
Niklas Funk, Svenja Menzenbach, Georgia Chalvatzaki, Jan Peters
Cite
Reinforcement Learning for Assembly with Structured Graph Representations and Search
Assembly problems are demanding as they require abstract high-level reasoning over action sequences together with a smooth execution of …
Niklas Funk, Georgia Chalvatzaki, Boris Belousov, Jan Peters
Cite
Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery
We propose a novel hybrid method for Robot Assembly discovery that is based on a combination of Mixed Integer Programming and a graph-based reinforcement learning agent.
Niklas Funk, Svenja Menzenbach, Georgia Chalvatzaki, Jan Peters
PDF Cite Project
Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery
Real Robot Challenge: A Robotics Competition in the Cloud
Dexterous manipulation remains an open problem in robotics. To coordinate efforts of the research community towards tackling this …
Stefan Bauer, Manuel Wüthrich, Felix Widmaier, Annika Buchholz, Sebastian Stark, Anirudh Goyal, Thomas Steinbrenner, Joel Akpo, Shruti Joshi, Vincent Berenz, Vaibhav Agrawal, Niklas Funk, Julen Urain, Jan Peters, Joe Watson, Claire Chen, Krishnan Srinivasan, Junwu Zhang, Jeffrey Zhang, Matthew Walter, Rishabh Madan, Takuma Yoneda, Denis Yarats, Arthur Allshire, Ethan Gordon, Tapomayukh Bhattacharjee, Siddhartha Srinivasa, Animesh Garg, Takahiro Maeda, Harshit Sikchi, Jilong Wang, Qingfeng Yao, Shuyu Yang, Robert McCarthy, Francisco Sanchez, Qiang Wang, David Bulens, Kevin McGuinness, Noel O’Connor, Redmond Stephen, Bernhard Schölkopf
PDF Cite
Learn2Assemble with structured representations and search for robotic architectural construction
We propose a novel method for learning to assemble arbitrary structures from scratch. The transformer-like graph-based neural network jointly decides which blocks to use and how to assemble the structure with the robot-in-the-loop.
Niklas Funk, Georgia Chalvatzaki, Boris Belousov, Jan Peters
PDF Cite Project
Learn2Assemble with structured representations and search for robotic architectural construction
Reinforcement Learning for Sequential Assembly of SL-Blocks-Self-interlocking combinatorial design based on Machine Learning
Adaptive reconfigurable structures are seen as the next big step in the evolution of architecture. However, to achieve this vision, new …
Bastian Wibranek, Yuxi Liu, Niklas Funk, Boris Belousov, Jan Peters, Oliver Tessmann
PDF Cite
Reinforcement Learning for Sequential Assembly of SL-Blocks-Self-interlocking combinatorial design based on Machine Learning
Autonomous Electric Race Car Design
Autonomous driving and electric vehicles are nowadays very active research and development areas. In this paper we present the …
Niklas Funk, Nikhilesh Alatur, Robin Deuber, Frederick Gonon, Nico Messikommer, Julian Nubert, Moritz Patriarca, Simon Schaefer, Dominic Scotoni, Nicholas Bunger, Renaud Dube, Raghav Khanna, Mark Pfeiffer, Erik Wilhelm, Roland Siegwart
PDF Cite Video
Autonomous Electric Race Car Design