The acquisition of commonsense knowledge remains a core challenge in both robotics and artificial intelligence. While Large Language Models (LLMs) encode rich latent knowledge, their unstructured and probabilistic nature limits their direct use in safety-critical domains like robotics. In this paper, we present a pipeline for extracting structured commonsense knowledge from LLMs and integrating it into a symbolic knowledge graph based on the Ontology for Robotic Knowledge Acquisition (ORKA). Grounded in the theory of conceptual spaces, our method targets physical object properties—both categorical (e.g., shape, material, location) and quantifiable (e.g., size, weight, temperature)—relevant to embodied reasoning. We evaluate the pipeline across a diverse set of LLMs, model sizes, and quantization levels, using human-annotated ground truth to assess accuracy. Results show that even compact and quantized models can produce reliable, interpretable knowledge. We also analyze the influence of measurement units and contextual relevance, highlighting trade-offs between model types and use cases. These results indicate that even smaller LLMs can serve as a useful intermediate source for deriving structured commonsense representations in robotics contexts.

Personal service robots are increasingly deployed to support daily living in domestic environments, particularly for elderly and individuals requiring assistance. These robots must perceive complex and dynamic surroundings, understand tasks, and execute context-appropriate actions. However, current systems typically rely on proprietary, hard-coded solutions tied to specific hardware and software, resulting in siloed implementations that are difficult to adapt and scale across platforms. Ontologies and Knowledge Graphs (KGs) offer a solution to enable interoperability across systems, through structured and standardized representations of knowledge and reasoning. However, symbolic systems such as KGs and ontologies struggle with raw and noisy sensory input. In contrast, multimodal language models are well suited for interpreting input such as images and natural language, but often lack transparency, consistency, and knowledge grounding. In this work, we propose a neurosymbolic framework that combines the perceptual strengths of multimodal language models with the structured representations provided by KGs and ontologies, with the aim of supporting interoperability in robotic applications. Our approach generates ontology-compliant KGs that can inform robot behavior in a platform-independent manner. We evaluated this framework by integrating robot perception data, ontologies, and five multimodal models (three LLaMA-based and two GPT-based models), each using different modes of neural-symbolic interaction. We assess the consistency and effectiveness of the generated KGs across multiple runs and configurations, and perform statistical analyzes to evaluate performance. Results show that GPT-o1 and LLaMA 4 Maverick consistently outperform other models. However, our findings also indicate that newer models do not guarantee better results, highlighting the critical role of the integration strategy in generating ontology-compliant KGs.

In order to test how explanations affect a user working together with a collaborative robot, we created a test scenario where a user sorts trash together with a collaborative robot. Sometimes the robot is not able to fulfill its part of the task. Different modalities (textual, graphical, both) for explaining this error to the user are tested in a between subjects design and the effects on task performance, cognitive load and trust are analyzed.

With the increased use of social robots in critical applications, like elder care and rehabilitation, it becomes necessary to investigate the user's trust in robots to prevent over- and under-utilization of the robotic systems. While several studies have shown how trust increases through personalised behaviour, there is a lack of research concerned with the influence of personalised physical appearance. This study explores the effect of personalised physical appearance on trust in human-robot-interaction (HRI). In an online game, 60 participants interacted with a robot, where half of the participants were asked to personalise the robot prior to the game. Trust was measured through a trust-related questionnaire as well as by evaluating user behaviour during the game. Results indicate that personalised physical appearance does not directly correlate to higher trust perceptions, however, there was significant evidence that players exhibit more trusting behaviours in a game against a personalised robot.