Search our Publications
Latest Publications
William Huang, Yi Mei, Guenther Raidl, Fangfang Zhang, Laurenz Tomandl, Steffen Limmer, Mengjie Zhang, Tobias Rodemann , "Genetic Programming Hyper-Heuristic for Dynamic Electric Dial-a-Ride Problem", 2025 IEEE Congress on Evolutionary Computation (CEC), 2025.
AbstractThis paper studies the Dynamic Electric Dial-A-Ride Problem (DEDARP), which is a recent challenging combinatorial optimisation that has many applications in the real-world ridesharing services with electric vehicles. In addition to the challenges from the NP-hardness of dial-a-ride, we fact extra challenges for making real-time dispatching decisions in dynamic environments with unpredicted new requests and selecting proper time for the vehicles t...
Download Bibtex file
Mathias Franzius , "Physical Markers for Learning without Labeling", Honda Technical Forum 2025, 2025.
AbstractPhysical Markers (PMs) are simple, camera-detectable tags that enable direct interaction with physical parts for rapid data collection and labeling in dynamic factory environments. They allow operators or inspectors to attach small, machine-readable markers near specific local features such as defects, surface variations, or assembly errors. When viewed by a camera, the PM provides a unique ID and spatial reference, allowing the surrounding regio...
Download Bibtex file Per Mail Request
Svenja Kenneweg, Julian Eggert, Jörg Deigmöller, Philipp Cimiano , "A compositional approach to modeling the semantics of vague temporal adverbials", CogSci 2025, 2025.
AbstractVague temporal adverbials, such as "recently," "just," "some time ago," and "long time ago," describe the temporal distance between a past event and the utterance time but leave the exact duration under-specified. These adverbials' interpretation is influenced by the event's properties, like its duration and frequency. The paper introduces a compositional, cognitive model to represent these adverbials' semantics as probabilistic distributions, co...
Download Bibtex file
Raphael Wenzel , "Cooperative Behavior Planning for Automated Vehicles in Ordering Situations", TU Darmstadt, 2025.
AbstractAutomated Driving has the potential to profoundly reduce traffic fatalities. However, challenges remain when extending the Operational Design Domain of automated vehicles to urban scenarios, especially in mixed traffic where automated systems interact with human drivers. This thesis investigates behavior planning strategies in the scenario class of \emph{Cooperative Ordering Problems} where two vehicles have to cooperatively determine their o...
Download Bibtex file Per Mail Request
Laurenz Tomandl, Maria Bresich, Guenther Raidl, William Huang, Yi Mei, Steffen Limmer, Tobias Rodemann , "A Reinforcement Learning Guided Large Neighborhood Search for the Dynamic Electric Autonomous Dial-a-Ride Problem ", The 11th International Conference on Machine Learning, Optimization, and Data Science, 2025.
AbstractWe consider a version of the Dynamic Electric Autonomous Dial-a-Ride Problem (DynEADARP) recently proposed and approached by means of a Genetic Programming (GP) hyperheuristic. This problem integrates the challenges of the static dial-a-ride problem with those of considering the charging of the fleet of electric vehicles and the dynamic nature of customer requests, i.e., the online aspect. The objective is to minimize the total travel time for se...
Download Bibtex file Per Mail Request
Felix Ocker , "When robots take initiative: Agentic AI for human-robot cooperation", summit munich_i, 2025.
AbstractAs robots move beyond rigid, rule-based behavior, a new class of intelligent agents is emerging—robots that take initiative, act with purpose, and collaborate with humans. This talk explores the shift toward agentic AI, highlighting key design patterns and recent breakthroughs that have the potential to make autonomy not just possible, but useful. From language model-based robots that offer support only when truly needed, to systems that plan for...
Download Bibtex file Per Mail Request
Andrea Castellani , "Real-World Energy Management Data from a Smart Building for Optimization and Machine Learning", Deep Learning Techniques for Observable Smart Grid and Sustainable Energy Systems (Workshop at IJCNN 2025), 2025.
AbstractThis tutorial presents a real-world energy management dataset collected from a smart company building over six years’ time. The dataset includes energy consumption from various sites, renewable energy production from photovoltaic and combined heat-and-power systems, and detailed heating and cooling system operations. It also contains high-resolution weather station measurements, making it a valuable resource for energy analysis and optimization. ...
Download Bibtex file Per Mail Request
Qingshan Xu, Jiao Liu, Melvin Wong, Caishun Chen, Yew Soon Ong , "Looks Great, Functions Better: Physics Conform Text-to-3D Shape Generation", International Joint Conference on Neural Networks, 2025.
AbstractText-to-3D shape generation has shown great promise in generating novel 3D content based on given text prompts. However, existing generative methods mainly consider geometric or visual plausibility while ignoring functionality for the generated 3D shapes. This greatly hinders the practicality of generated 3D shapes in real-world applications. Towards physical AI, we propose Fun3D, a physics conform functional text-to-3D shape generation method. B...
Download Bibtex file Per Mail Request
Ahmed Sadik and Siddhata Govind , "Benchmarking LLM for Code Smells Detection: OpenAI GPT-4.0 vs DeepSeek-V3", arXiv, 2025.
AbstractDetermining which Large Language Model (LLM) is superior for code smell detection is a complex challenge. This study aims to establish a systematic methodology and evaluation matrix to address this question. We introduce a curated dataset containing smelly code implementations of identical scenarios across four major programming languages: Java, Python, JavaScript, and C++. Each dataset entry is annotated with known code smells, serving as ground...
Download Bibtex file Per Mail Request
Ahmed Sadik, Muhammad Ashfaq, Niko Mäkitalo, Tommi Mikkonen , "Urban Air Mobility as a System of Systems: An LLM-Enhanced Holonic Approach", arXiv, 2025.
AbstractUrban Air Mobility (UAM) is an emerging System of Systems (SoS) that presents significant challenges in system architecture, planning, task management, and execution. Traditional approaches often struggle with scalability, adaptability, and seamless resource integration within dynamic and complex environments. To overcome these limitations, this paper introduces an intelligent holonic architecture enhanced by Large Language Models (LLMs). By inco...
Download Bibtex file Per Mail Request
1 ... 16 17 18 19 20 21 ... 183
Follow us
