6 papers
DISC: Dense Integrated Semantic Context for Large-Scale Open-Set Semantic Mapping
Felix Igelbrink, Lennart Niecksch, Martin Atzmueller +1
Open-set semantic mapping enables language-driven robotic perception, but current instance-centric approaches are bottlenecked by context-depriving and computationally expensive cr…
Agentic AI for Robot Control: Flexible but still Fragile
Oscar Lima, Marc Vinci, Martin Günther +10
Recent work leverages the capabilities and commonsense priors of generative models for robot control. In this paper, we present an agentic control system in which a reasoning-capab…
A Scene Graph Backed Approach to Open Set Semantic Mapping
Martin Günther, Felix Igelbrink, Oscar Lima +3
While Open Set Semantic Mapping and 3D Semantic Scene Graphs (3DSSGs) are established paradigms in robotic perception, deploying them effectively to support high-level reasoning in…
LIEREx: Language-Image Embeddings for Robotic Exploration
Felix Igelbrink, Lennart Niecksch, Marian Renz +2
Semantic maps allow a robot to reason about its surroundings to fulfill tasks such as navigating known environments, finding specific objects, and exploring unmapped areas. Traditi…
ExPrIS: Knowledge-Level Expectations as Priors for Object Interpretation from Sensor Data
Marian Renz, Martin Günther, Felix Igelbrink +2
While deep learning has significantly advanced robotic object recognition, purely data-driven approaches often lack semantic consistency and fail to leverage valuable, pre-existing…
Saliency Map-Guided Knowledge Discovery for Subclass Identification with LLM-Based Symbolic Approximations
Tim Bohne, Anne-Kathrin Patricia Windler, Martin Atzmueller
This paper proposes a novel neuro-symbolic approach for sensor signal-based knowledge discovery, focusing on identifying latent subclasses in time series classification tasks. The…