7 papers
A Robust Placeability Metric for Model-Free Unified Pick-and-Place Reasoning
Benno Wingender, Nils Dengler, Rohit Menon +2
Reliable manipulation of previously unseen objects remains a fundamental challenge for autonomous robotic systems operating in unstructured environments. In particular, robust pick…
SG-DOR: Learning Scene Graphs with Direction-Conditioned Occlusion Reasoning for Pepper Plants
Rohit Menon, Niklas Mueller-Goldingen, Sicong Pan +2
Robotic harvesting in dense crop canopies requires effective interventions that depend not only on geometry, but also on explicit, direction-conditioned relations identifying which…
EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images
Rohit Menon, Nils Dengler, Sicong Pan +2
For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous system…
Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection
Nils Dengler, Jesper Mücke, Rohit Menon +1
Service robots operating in cluttered human environments such as homes, offices, and schools cannot rely on predefined object arrangements and must continuously update their semant…
GO-VMP: Global Optimization for View Motion Planning in Fruit Mapping
Allen Isaac Jose, Sicong Pan, Tobias Zaenker +3
Automating labor-intensive tasks such as crop monitoring with robots is essential for enhancing production and conserving resources. However, autonomously monitoring horticulture c…
Compact Multi-Object Placement Using Adjacency-Aware Reinforcement Learning
Benedikt Kreis, Nils Dengler, Jorge de Heuvel +3
Close and precise placement of irregularly shaped objects requires a skilled robotic system. The manipulation of objects that have sensitive top surfaces and a fixed set of neighbo…