Search our Publications
Latest Publications
Thomas H Weisswange , "Cooperative Intelligence - Research at the Honda Research Institute Europe", Hochschule Reutlingen, Germany, 2024.
AbstractInvited talk at the University of Applied Science Reutlingen, presenting an overview of HRI-EU's projects and its general approach to science and technology....
Download Bibtex file Per Mail Request
Jens Engel, Thomas Schmitt, Tobias Rodemann, Jürgen Adamy , "Evaluating the Impact of Data Availability on Machine Learning-augmented MPC for a Building Energy Management System", IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe) 2024, 2024.
AbstractA major challenge in the development of Model Predictive Control (MPC)-based energy management systems (EMSs) for buildings is the availability of an accurate model. One approach to address this is to augment an existing gray-box model with data-driven residual estimators. The efficacy of such estimators, and hence the performance of the EMS, relies on the availability of sufficient and suitable training data. In this work, we evaluate how...
Download Bibtex file
Daniel Tanneberg, Felix Ocker, Stephan Hasler, Jörg Deigmöller, Anna Belardinelli, Chao Wang, Heiko Wersing, Bernhard Sendhoff, Michael Gienger , "To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2024.
AbstractHow can a robot provide unobtrusive physical support within a group of humans? We present Attentive Support, a novel interaction concept for robots to support a group of humans. It combines scene perception, dialogue acquisition, situation understanding, and behavior generation with the common-sense reasoning capabilities of Large Language Models (LLMs). In addition to following user instructions, Attentive Support is capable of deciding whe...
Download Bibtex file Per Mail Request
Steffen Limmer , "Automated Machine Learning", GECCO 2024, Evolutionary Computation in Practice, 2024.
AbstractThe manual development of well performing machine learning pipelines is a time-consuming task, which requires a substantial amount of human expertise. The automation of this task, also known as automated machine learning (AutoML), is gaining increasing attention in academia as well as industry. This talk gives a practical introduction to AutoML and to TPOT, one of the most popular AutoML tools. Furthermore, an overview to AutoML related activitie...
Download Bibtex file Per Mail Request
Maria Bresich, Guenther Raidl, Steffen Limmer , "Letting a Large Neighborhood Search for an Electric Dial-A-Ride Problem Fly: On-The-Fly Charging Station Insertion", GECCO '24: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 142–150, 2024.
AbstractWe consider the electric autonomous dial-a-ride problem (E-ADARP), a challenging extension of the dial-a-ride problem with the goal of finding minimum cost routes serving given transportation requests with a fleet of electric and autonomous vehicles (EAVs). Special emphasis lies on the minimization of user excess ride time under consideration of the charging requirements of the EAVs while constraints regarding, for example, user ride times and t...
Download Bibtex file
Angus Kenny, Tapabrata Ray, Steffen Limmer, Hemant Kumar Singh, Tobias Rodemann, Markus Olhofer , "Using Bayesian Optimization to Improve Hyperparameter Search in AutoML", GECCO '24: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 340–348, 2024.
AbstractAutomated machine learning (AutoML) has emerged as a pivotal tool for applying machine learning (ML) models to real-world problems. Among the various AutoML tools, the tree-based pipeline optimization tool (TPOT) is known for effectively solving complex tasks. TPOT’s search involves two fundamental objectives: finding optimal pipeline structures (i.e., combinations of ML operators) and identifying suitable hyperparameters for these structures. Wh...
Download Bibtex file
Anna Belardinelli , "Gaze-based intention estimation: principles, methodologies, and applications in HRI", ACM Transactions on Human-Robot Interaction, 2024.
AbstractIntention prediction has become a relevant field of research in Human-Machine and Human-Robot Interaction. Indeed, any artificial system (co)-operating with and along humans, designed to assist and coordinate its actions with a human partner, needs first to infer the human’s current intention. To spare the user the cognitive burden of explicitly uttering their goals, this inference relies mostly on behavioral cues deemed indicative of the curr...
Download Bibtex file
Christiane Wiebel , "Investigating Eye Movement Measures in the context of Human Machine Cooperation", Graduate Centre GGN Colloquium Giessen, 2024.
AbstractToday many intelligent systems do not act autonomously but operate in interaction with a human user. Recent HMI research has hypothesized that such an interaction between human and machine is best reached by designing the system to behave cooperatively. In this context, modelling the user is one important subtask and eye tracking measures are a popular tool. In this talk I will summarize some of our recent work on investigating eye movement measu...
Download Bibtex file Per Mail Request
Joao Soares, Fernando Lezama, Ricardo Faia, Steffen Limmer, Manuel Dietrich, Tobias Rodemann, Sergio Ramos, Zita Vale , "Review on fairness in local energy systems", Applied Energy, 2024.
AbstractThe discussion of fairness is gaining considerable attention in the context of Local Energy Systems (LES). This is partially motivated by the energy transition, which has put more attention on technologies and production closer to the end-user. In other words, we are evolving towards a more user-centric approach, which requires dealing with fairness and justice due to the users’ participation in the loop. Their willingness to participate depends ...
Download Bibtex file
Fan Zhang and Michael Gienger , "Robot Manipulation with Flow Matching", Conference on Robot Learning (CoRL), workshop Mastering Robot Manipulation in a World of Abundant Data, 2024.
AbstractThis paper presents a new imitation learning paradigm for robot manipulation with flow matching policy. Flow matching represents a robot visuomotor policy as a conditional process of flowing random waypoints to desired robot action trajectories, by regressing vector fields of fixed conditional probability paths. We evaluate the proposed method across two simulation benchmarks and a real-world dataset with 10 tasks across Activities of Daily Livin...
Download Bibtex file Per Mail Request
1 ... 28 29 30 31 32 33 ... 183
Follow us
