Search our Publications
Latest Publications
Nima Nabizadeh, Martin Ernst Heckmann, Dorothea Kolossa , "MyFixit: An Annotated Corpus and Annotation Tool for Extracting Information from Instructional Text", LREC 2020: 12th Conference on Language Resources and Evaluation, 2020.
AbstractText instructions are the most common way of learning and teaching various tasks for humans. For having a system capable of supporting humans in such tasks, a vital step is to extract a machine-understandable knowledge from the instructions. In this paper, we focus on the complex task of repairing devices. For this purpose, we interduce a semi-structured corpus of repair manuals, annotated with the information that a repair assistant can use to h...
Download Bibtex file
Saif Sidhik, Mohan Sridharan, Dirk Ruiken , "Learning Hybrid Models for Variable Impedance Control of Changing-Contact Manipulation Tasks", Conference on Advances in Cognitive Systems 2020, 2020.
AbstractMany robot manipulation tasks comprise discrete action sequences characterized by continuous dynamics, while the transitions between these discrete dynamic modes are characterized by discontinuous dynamics. The individual modes can represent different types of contacts, surfaces, or other factors, and different control strategies may be needed for each mode and the transitions between the modes. This paper describes a piece-wise continuous, hybr...
Download Bibtex file
Viktor Losing, Martina Hasenjäger, Taizo Yoshikawa , "Personalized Online Learning with Pseudo-Ground Truth", IROS 2020, 2020.
AbstractPersonalized online machine learning allows a very accurate modelling of individual behavior and demands. In particular, a system that dynamically adapts during runtime can initiate a continuous collaboration with its user where both alternatively adjust to each other to maximize the system's utility. However, in application scenarios based on supervised learning it is often unclear how to obtain the required ground truth for such dynamic systems...
Download Bibtex file Per Mail Request
Nils Einecke and Sven Rebhan , "Spacecraft Collision Avoidance Challenge: design and results of a machine learning competition", Arxiv, 2020.
AbstractSpacecraft collision avoidance procedures have become an essential part of satellite operations. Complex and constantly updated estimates of the collision risk between orbiting objects inform the various operators who can then plan risk mitigation measures. Such measures could be aided by the development of suitable machine learning models predicting, for example, the evolution of the collision risk in time. In an attempt to study this opportunit...
Download Bibtex file
Newton Masinde, Liat Khitman, Iakov Dlikman, Kalman György Graffi , "Systematic Evaluation of LibreSocial - a Peer-to-Peer Framework for Online Social Networks", MDPI Future Internet - Special Issue "Security and Privacy in Social Networks and Solutions", vol. 12, no. 140, pp. 1-26, 2020.
AbstractPeer-to-peer (P2P) networks have been under investigation for several years now, with many novel mechanisms proposed as is evidenced by articles available. Much of the research has focused on showing how the proposed mechanism affects the system performance. In addition, several applications have been proposed to harness the benefits of the P2P networks. Of these applications, online social networks (OSNs) have raised much interest particularly b...
Download Bibtex file
Theodoros Stouraitis, Lei Yan, Joao Moura, Michael Gienger, Sethu Vijayakumar , "Impact-Aware Planning through Stiffness and Motion Optimization", IROS 2020, 2020.
AbstractMotion plans for manipulation task include making and break of contact, as well as adjustments of the stiffness characteristics. These behaviours can be organized into different modes that represent different phases of the motion. The former are related with the discrete and distinct contact events, while the latter are relevant to the custom restrictions of each scenario. This paper presents the following contributions: a general and accurate co...
Download Bibtex file Per Mail Request
Ahmad Reza Cheraghi, Jochen Peters, Kalman György Graffi , "Prevention of Ant Mills in Pheromone based Swarm Algorithms", International Conference on Intelligent Robotics and Control Engineering (IRCE), 2020.
AbstractComputer scientists use animal-based phenomenon as source of inspiration to develop swarm algorithm and simulate their behaviors. One example is ants foraging. For finding food the ants are moving randomly in any direction. After they found food, they spread pheromones to make it easy for other ants to find it. The more ants, the better the pheromone trail. This pheromone-based search algorithm should increase the efficiency of food delivery. How...
Download Bibtex file
Ahmad Reza Cheraghi, Karol Actun, Sahdia Shahzad, Kalman György Graffi , "Swarm-Sim: A 2D & 3D Simulation Core for Swarm Agents", 3rd International Conference on Intelligent Robotics and Control Engineering (IRCE 2020), 2020.
Abstract(Robot) swarm networks are consisting of magnitudes of individual agents that are capable to move in a world and interact with each other or with passive items. Through local, individual algorithms applied in the agents desired properties of the swarm can emerge. In this paper, we present Swarm-Sim, a round-based simulator that supports the evaluation of such large scaled swarms in a 2D and 3D world. Agents can move in the simulated world, percei...
Download Bibtex file
Qiqi Liu, Yaochu Jin, Martin Heiderich, Tobias Rodemann, Guo Yu , "An Adaptive Reference Vector Guided Evolutionary Algorithm Using Growing Neural Gas for Many-objective Optimization of Irregular Problems", IEEE Transactions on Cybernetics, vol. 52, no. 5, pp. 2698 - 2711, 2020.
AbstractMost reference vector-based decomposition algorithms for solving multiobjective optimization problems may not be well suited for solving problems with irregular Pareto fronts (PFs) because the distribution of predefined reference vectors may not match well with the distribution of the Pareto-optimal solutions. Thus, the adaptation of the reference vectors is an intuitive way for decomposition-based algorithms to deal with irregular PFs. However, ...
Download Bibtex file
Andrea Castellani, Sebastian Schmitt, Stefano Squartini , "Real-World Anomaly Detection with Siamese Neural Networks and Digital Twin Systems", IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020.
AbstractNowadays, with the continuously growing /mount of monitored data present in Smart Company environment, the need for Anomaly Detection technique has become more relevant in order to identify some anomalous behavior from time-series data generated by sensors. With the Digital Twin, a detailed simulation of a complex physical system, it is possible to provide more data to feed in a Machine Learning algorithm and thus help in the anomaly detec...
Download Bibtex file
1 ... 66 67 68 69 70 71 ... 183
Follow us
