Our Research

We investigate robots that can understand their environment semantically and geometrically, in order to perform manipulation and other safety critical tasks in proximity to humans. This encompasses semantic understanding under open-set conditions, map representations of the environment, active perception and planning, as well as adaptation and continual self-supervised learning.
Method for setting more precisely a position and/or orientation of a device head

US Patent 12,226,867, 2025

ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding

CVPR 2025

arxivPDFlabelmaker.orgcode
DepthSplat: Connecting Gaussian Splatting and Depth

CVPR 2025

arxivPDFwebsitecode
FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction

2025

arxivPDF
Loop Closure from Two Views: Revisiting PGO for Scalable Trajectory Estimation through Monocular Priors

2025

arxivPDF
Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs

Robotics and Automation Letters (RA-L) 2025

arxivPDFwebsitedoi
FrontierNet: Learning Visual Cues to Explore

2025

arxivPDF
NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models

IROS 2024

Method for localizing a mobile construction robot on a construction site using semantic segmentation, construction robot system and computer program product

US Patent App. 18/284,646, 2024

OptXR: Optimization of Maintenance Processes with Extended Reality and Digital Twins

Center for Sustainable Future Mobility Symposium 2024 (CSFM 2024), 2024

Lost & Found: Updating Dynamic 3D Scene Graphs from Egocentric Observations

2024

arxivPDF
HoloSpot: Intuitive Object Manipulation via Mixed Reality Drag-and-Drop

2024

arxivPDFwebsite
Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization Using Geometrical Information

ECCV 2024

doiarxivPDFcode
“Where am I?” Scene Retrieval with Language

ECCV 2024

doiarxivPDFwebsitewebsite
SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection

2024

arxivPDFwebsite
OpenDAS: Open-Vocabulary Domain Adaptation for Segmentation

2024

arxivPDFwebsite
SNI-SLAM: Semantic Neural Implicit SLAM

CVPR 2024

arxivPDFcodecodeopenaccess.thecvf.com
A 3D Mixed Reality Interface for Human-Robot Teaming

ICRA 2024

arxivPDFcode
Active Visual Localization for Multi-Agent Collaboration: A Data-Driven Approach

ICRA 2024

arxivPDF
OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation

2024

arxivPDF
Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds

ICRA 2024

arxivPDFwebsitecode
LabelMaker: Automatic Semantic Label Generation from RGB-D Trajectories

3DV 2024

arxivPDFlabelmaker.orgcode
Unsupervised Continual Semantic Adaptation through Neural Rendering

CVPR 2023

doicodewebsite