J
Jacek Malec
Researcher at Lund University
Publications - 76
Citations - 943
Jacek Malec is an academic researcher from Lund University. The author has contributed to research in topics: Robot & Knowledge representation and reasoning. The author has an hindex of 15, co-authored 73 publications receiving 857 citations. Previous affiliations of Jacek Malec include Mälardalen University College & Wrocław University of Technology.
Papers
More filters
Journal ArticleDOI
A new Q-learning algorithm based on the metropolis criterion
Maozu Guo,Yang Liu,Jacek Malec +2 more
TL;DR: The Metropolis criterion of simulated annealing algorithm is introduced in order to balance exploration and exploitation of Q- learning, and the modified Q-learning algorithm based on this criterion, SA-Q-learning, is presented.
Journal ArticleDOI
Knowledge-based instruction of manipulation tasks for industrial robotics
Maj Stenmark,Jacek Malec +1 more
TL;DR: This paper focuses on the knowledge put into ontologies created for robotic devices and manufacturing tasks, and presents examples of AI-related services that use the semantic descriptions of skills to help users instruct the robot adequately.
Proceedings ArticleDOI
On the integration of skilled robot motions for productivity in manufacturing
Anders Björkelund,Lisett Edstrom,Mathias Haage,Jacek Malec,Klas Nilsson,Pierre Nugues,Sven Gestegard Robertz,Denis Storkle,Anders Blomdell,Rolf Johansson,Magnus Linderoth,Anders Nilsson,Anders Robertsson,Andreas Stolt,Herman Bruyninckx +14 more
TL;DR: This work proposes techniques that build on existing knowledge by converting structured data into an RDF-based knowledge base that can be gradually extended as part of the interaction during the definition of the robot task.
Proceedings ArticleDOI
Knowledge-Based Reconfiguration of Automation Systems
TL;DR: This article describes the work in progress on knowledge-based reconfiguration of a class of automation systems, exploiting ontology-based rewriting, simplifying creation of the final configuration files.
Proceedings Article
Knowledge for Intelligent Industrial Robots
TL;DR: An architecture to integrate disparate knowledge representations used in different places in robotics and automation is developed, which abstracts the components used in design or production as data sources, and provides a uniform access to them via standard interfaces.