Search our Publications
Latest Publications
Nikolay Matyunin and Ali Raza , "AI-Driven Holistic Approaches for Cybersecurity and Privacy at HRI-EU", University of Kent, Institute of Cyber Security for Society (iCSS), 2024.
AbstractWe are planning to give am exchange/overview talk during our trip to Kent for the project wrap-up In this talk, we will introduce the Honda Research Institute, its core research directions, and highlight a few recent applications of generative artificial Intelligence (AI) across diverse domains. Then, we will showcase how advancements of AI and Large Language Models (LLMs) can be applied in the fields of security and privacy, with examples of ...
Download Bibtex file Per Mail Request
Hao Tong , "Advancing Optimization and Evaluation for Dynamic Capacitated Arc Routing Problems", University of Birmingham, 2024.
AbstractThe Capacitated arc routing problem (CARP) is a challenging combinatorial optimization problem abstracted from real-world applications, such as waste collection and road gritting. It aims at scheduling a fleet of vehicles, each with a limited capacity, to serve a series of tasks in a graph spending the lowest possible total cost. In real applications, unexpected dynamic changes usually occur when vehicles are in their service, which potentially c...
Download Bibtex file Per Mail Request
Qingshan Xu, Jiao Liu, Melvin Wong, Ge Jin, Ryan Lau, Yew Soon Ong, Stefan Menzel, Thiago de Jesus de Araujo Rios, Joo-Hwee Lim, Chin Chun Ooi , "Towards End-to-End Prompt-Vision-Physics Neural Network for Fast Design Discovery", IEEE Conference on Artificial Intelligence, 2024.
AbstractIn this paper, we present the study of an end-to-end prompt-vision-physics neural network (PVPNN) to speed up the design discovery process in science and engineering. PVPNN has the potential to transform design discovery by enabling researchers and engineers to specify design requirements seamlessly via prompts, analyze available large-scale relevant historical data sets to generate novel physics-conform designs and predict the efficacy of potent...
Download Bibtex file
Christiane Attig, Christiane Wiebel, Patricia Wollstadt, Thomas Franke , "The cooperative card game “Hanabi” as a research environment for human-human and human-AI collaboration ", 53rd DGPs Congress, 2024.
AbstractWith disruptive innovations in the field of social AI (e.g., Large Language Models having voice abilities, AI agents being able to display false belief understanding), engineering psychology research needs to incorporate theories and paradigms of social psychology more strongly than ever. Indeed, empirical studies and theoretical frameworks from engineering psychology that focus on the interaction between humans and AI agents with cooperative and...
Download Bibtex file Per Mail Request
Melvin Wong, Thiago de Jesus de Araujo Rios, Stefan Menzel, Yew Soon Ong , "Prompt Evolutionary Design Optimization with Generative Shape and Vision-Language models", IEEE Congress on Evolutionary Computation, 2024.
AbstractRapid advancements in text-to-3D shape synthesis using generative AI models have achieved remarkable generalization performance, generating novel designs based on combinations of different concepts. However, designs synthesized through automated optimization often result in ill-defined shapes, which render such designs impractical for engineering design applications. We present the first end-to-end prompt evolution design optimization (PREDO) fra...
Download Bibtex file Per Mail Request
Jens Engel, Thomas Schmitt, Tobias Rodemann, Jürgen Adamy , "Hierarchical MPC for building energy management: Incorporating data-driven error compensation and mitigating information asymmetry", Applied Energy, 2024.
AbstractThe increasing adoption of renewable energy sources (RESs) in public power grids has led to a demand for more intelligent energy management systems (EMSs) in large-scale buildings. A common approach for controlling EMSs for buildings is Model Predictive Control (MPC). For large-scale buildings, hierarchical MPC schemes have been proposed, offering the advantage of scalability through problem decomposition into multiple layers. However, hierarc...
Download Bibtex file
Pavel Smirnov and Michael Gienger , "Knowledge-based actions preconditions augmentation", HRI-EU, 2024.
AbstractThe problem of planning long-horizon goals is relevant when robot is targeted to accompany humans in daily tasks (e.g. cooking a dinner, cleaning up a room, loading/unloading vehicles and so on). This report describes experimental results, which demonstrate the value of memorizing goal-directed planning interactions (interactions between intelligent agent and LLM) in terms of actions and their preconditions. Results demonstrate that action precon...
Download Bibtex file Per Mail Request
Yanrong Wang , Mohan Sridharan, Dirk Ruiken , "Hybrid planning and control for changing contact manipulation", The 5th UK Robot Manipulation Workshop, 2024.
AbstractMany existing architectures for robots that move and interact with their domain include an approach for Task and Motion planning (TAMP). This approach combines high-level, abstract task planning, often with a discrete, symbolic representation, and low-level motion planning and control based on a continuous representation. Despite considerable research, there are some key open problems in TAMP. First, the differences in representation and processi...
Download Bibtex file Per Mail Request
Matti Krüger, Yutaka Ooshima, Yu Fang , "Virtual reflections on a dynamic 2D eye model improve spatial reference identification", arXiv, Cornell University, 2024.
AbstractThe visible orientation of human eyes creates some transparency about people's spatial attention and other mental states. This leads to a dual role for the eyes as a means of sensing and communication. Accordingly, artificial eye models are being explored as communication media in human-machine interaction scenarios. One challenge in the use of eye models for communication consists of resolving spatial reference ambiguities, especially for screen...
Download Bibtex file Per Mail Request
Felix Ocker and Maximilian Holland , "Generative KI: Anwendungen für Engineering, Robotik und Produktion", KI in der Produktion: Fraunhofer IGCV-Summit 2024, 2024.
AbstractGenerative Künstliche Intelligenz kann Texte, Bilder und andere Daten basierend auf Prompts generieren. Dieser Vortrag stellt einige Anwendungen der Technologie im Ingenieurskontext vor. Diese umfassen Knowledge Graph RAG, Tool Use für Robotik und Agenten für Planungsprozesse....
Download Bibtex file Per Mail Request
1 ... 27 28 29 30 31 32 ... 183
Follow us
