Видео

"CenterGrasp: Object-Aware Implicit Representation Learning for Simultaneous Shape Reconstruction and 6-DoF Grasp Estimation" Eugenio Chisari, Nick Heppert, Tim Welschehold, Wolfram Burgard, Abhinav Valada RA-L 2024 Website: centergrasp.cs.uni-freiburg.de/ Arxiv: arxiv.org/abs/2312.08240 Code: github.com/robot-learning-freiburg/CenterGrasp

Daniel Honerkamp*, Harsh Mahesheka*, Jan Ole von Hartz, Tim Welschehold and Abhinav Valada Zero-Cost Whole-Body Teleoperation for Mobile Manipulation ArXiv Preprint Paper: arxiv.org/pdf/2409.15095.pdf Code & Project: moma-teleop.cs.uni-freiburg.de/

Ahmed Rida Sekkat*, Rohit Mohan*, Oliver Sawade, Elmar Matthes, Abhinav Valada AmodalSynthDrive: A Synthetic Amodal Perception Dataset For Autonomous Driving Project Webpage: amodalsynthdrive.cs.uni-freiburg.de/ Paper: arxiv.org/abs/2309.06547 Music: pixabay.com/music/beats-relaxed-vlog-night-street-131746

Humans seemingly incorporate potential touch signals in their perception. Our goal is to equip robots with a similar capability, which we term PseudoTouch. PseudoTouch aims to predict the expected touch signal based on a visual patch representing the touched area. We frame this problem as the task of learning a low-dimensional visual-tactile embedding, wherein we encode a depth patch from which...

Teaching robots new skills quickly and conveniently is crucial for the broader adoption of robotic systems. In this work, we address the problem of one-shot imitation from a single human demonstration, given by an RGB-D video recording. We propose a two-stage process. In the first stage we extract the demonstration trajectory offline. This entails segmenting manipulated objects and determining ...

Nikhil Gosala, Kürsat Petek, B Ravi Kiran, Senthil Yogamani, Paulo L. J. Drews-Jr, Wolfram Burgard, Abhinav Valada, LetsMap: Unsupervised Representation Learning for Semantic BEV Mapping European Conference on Computer Vision (ECCV), 2024. Paper: arxiv.org/abs/2405.18852 Code & Project: letsmap.cs.uni-freiburg.de

Abdelrhman Werby*, Chenguang Huang*, Martin Buechner*, Abhinav Valada, Wolfram Burgard Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation Robotics: Science and Systems, 2024, Delft, Netherlands Paper: arxiv.org/pdf/2403.17846 Code & Project: hovsg.github.io/ Chapters 0:00 Intro 0:08 Motivation for HOV-SG 0:46 HOV-SG Pipeline 3:27 Language-Grounded Navigation wit...

Daniel Honerkamp*, Martin Buechner*, Fabien Despinoy, Tim Welschehold, Abhinav Valada Language-Grounded Dynamic Scene Graphs for Interactive Object Search w Mobile Manipulation IEEE Robotics and Automation Letters (RA-L), 2024. Paper: arxiv.org/abs/2403.08605 Code & Project: moma-llm.cs.uni-freiburg.de/ Chapters 0:00 Intro 0:10 Interactive Object Search Task 0:58 MoMa-LLM Method 1:41 Reasoning ...

INoD: Injected Noise Discriminator for Self-Supervised Learning in Agricultural Fields by Julia Hindel, Nikhil Gosala, Kevin Bregler, and Abhinav Valada. Paper: ieeexplore.ieee.org/document/10202201 Code and Dataset: inod.cs.uni-freiburg.de Music by Bensound.com, License code: WTHYEH7WJFBCAQRH.

Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perception by Julia Hindel, Daniele Cattaneo and Abhinav Valada. Paper: arxiv.org/abs/2407.18145 Code & Manual: topics.cs.uni-freiburg.de Visualisation: vecteezy.com Music by Bensound.com, License code: OAFQ8PL0FMINUBNA.

Website: mobile-manipulation.net/events/moma2024/ ► Full Workshop Timeline ◄ Due to technical issues, unfortunately there is no recording available for the opening remarks and Yoshihiro Okumatsu's talk. We are very sorry. ▸ Paper Spotlights ◂ ruclips.net/video/bEVx_E3iUyk/видео.html - Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models - MobileAfford: Mobile Robotic Mani...

Jan Ole von Hartz, Tim Welschehold, Abhinav Valada, and Joschka Boedecker The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations Paper: arxiv.org/pdf/2407.13432 Code & Project: tapas-gmm.cs.uni-freiburg.de/ Chapters 0:00 Intro and Method 1:13 Live Demo 1:35 Tasks 1:55 Demo Collection 2:07 Zero-Shot Generalization 2:52 Zero-Shot Skill Reuse 3:24 Baseline Compariso...

Website: robonerf.github.io/2024/ ► Full Workshop Timeline ◄ ▸ Introduction by Zubair and Nick ◂ ruclips.net/video/jyEZtbXs3fg/видео.html ▸ Jeannette Bohg ◂ ruclips.net/video/jyEZtbXs3fg/видео.html Assistant Professor Stanford ▸ Yen-Chen Lin ◂ ruclips.net/video/jyEZtbXs3fg/видео.html Research Sceintist Nvidia ▸ Xiaolong Wang ◂ ruclips.net/video/jyEZtbXs3fg/видео.html Assistant Professor Univers...

Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation Daniel Honerkamp*1, Martin Büchner*1, Fabian Despinoy^2, Tim Welschehold^1 , and Abhinav Valada^1 Paper: arxiv.org/abs/2403.08605 Project website: moma-llm.cs.uni-freiburg.de/ 1: Department of Computer Science, University of Freiburg, Germany. 2: Toyota Motor Europe (TME).

PASTEL: A Good Foundation is Worth Many Labels Label-Efficient Panoptic Segmentation

MDPCalib: Automatic Target-Less Camera-LiDAR Calibration From Motion and Deep Point Correspondences

BOpt-GMM - Bayesian Optimization for Sample-Efficient Policy Improvement in Robotic Manipulation

BEVCar: Camera-Radar Fusion for BEV Map and Object Segmentation

Amodal Optical Flow

Merry Christmas from the Robot Learning Lab - 2023

CenterGrasp Teaser

Panoptic Out-of-Distribution Segmentation

FreiDOG ft. Akaishi Daiko Freiburg @ 10th anniversary of kite-mentoring

CURB-SG: Collaborative Dynamic 3D Scene Graphs for Automated Driving

SPINO: Few-Shot Panoptic Segmentation With Foundation Models

The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation

Efficient Learning of Urban Driving Policies Using Bird's-Eye-View State Representations (ITSC 2023)

RaLF: Flow-based Global and Metric Radar Localization in LiDAR Maps

Syn-Mediverse: A Multimodal Synthetic Dataset for Scene Understanding of Healthcare Facilities