Time | Topic | Presenter |
09:00 – 10:00 | Welcoming + Invited Talk “Making Robots Explainable and Trustworthy” by Lars Kunze | Philipp Cimiano |
10:00 – 10:25 | Towards Improving Large Language Models’ Planning Capabilities on WoT Thing Descriptions by Generating Python Objects as Intermediary Representations | Lukas Kinder & Tobias Käfer |
10:25 – 10:55 | Coffee break | – |
10:55 – 11:20 | Mixing Mastery: Bridging Human Knowledge to Domestic Robotics | Vanessa Hassouna, Alina Hawkin & Michael Beetz |
11:20 – 11:45 | The SPA Ontology: Towards a Web of Things Ready for Robotic Agents | Michael Freund, Daniel Schraudner, Sebastian Schmid, Christoph Stade, Thomas Wehr & Andreas Harth |
11:45 – 12:10 | Towards a Knowledge Engineering Methodology for Flexible Robot Manipulation in Everyday Tasks | Michaela Kümpel, Jan-Philipp Töberg, Vanessa Hassouna, Philipp Cimiano & Michael Beetz |
12:10 – 12:20 | Towards Seamless Human-Robot Dialogue through a Robot Action Ontology | Diego Reforgiato Recupero & Lorenzo Boi |
12:20 – 12:30 | KB4RL: Towards a Knowledge Base for automatic creation of State and Action Spaces for Reinforcement Learning | Lobna Joualy, Eric Demeester & Nikolaos Tsiogkas |
Invited Talk: Making Robots Explainable and Trustworthy
Autonomous robot systems operating in real-world environments are required to understand their surroundings, assess their capabilities, and explain what they have seen, what they have done, what they planning to do, and why. These explanations need to be tailored to different stakeholders including end-users, developers, and regulators. In this talk, I will discuss how we design, develop, and evaluate fundamental AI technologies in simulation and real-world applications to make robots explainable and trustworthy and how this helps to overcome critical barriers which impede the current deployment of autonomous systems in economically and socially important areas.