A5041742195- AI-based Problem Solving and Planning
- Semantic Web and Ontologies
- Robotic Path Planning Algorithms
- Logic, Reasoning, and Knowledge
- Natural Language Processing Techniques
- Topic Modeling
- Robot Manipulation and Learning
- Reinforcement Learning in Robotics
- Modular Robots and Swarm Intelligence
- Robotics and Sensor-Based Localization
- Multi-Agent Systems and Negotiation
- Service-Oriented Architecture and Web Services
- Robotics and Automated Systems
- Multimodal Machine Learning Applications
- Biomedical Text Mining and Ontologies
- Explainable Artificial Intelligence (XAI)
- Manufacturing Process and Optimization
- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- Intelligent Tutoring Systems and Adaptive Learning
- Action Observation and Synchronization
- Artificial Intelligence in Games
- Speech and dialogue systems
- Social Robot Interaction and HRI
- EEG and Brain-Computer Interfaces
University of Bremen
2016-2025
Staats- und Universitätsbibliothek Bremen
2019
German Research Centre for Artificial Intelligence
2018
Polytechnic University of Timişoara
2013-2014
In this paper we present KnowRob2, a second generation knowledge representation and reasoning framework for robotic agents. KnowRob2 is an extension partial redesign of KnowRob, currently one the most advanced processing systems robots that has enabled them to successfully perform complex manipulation tasks such as making pizza, conducting chemical experiments, setting tables. The base appears be conventional first-order time interval logic base, but it exists large part only virtually: many...
The present study forms part of a research project that aims to develop cognition-enabled robotic agents with environmental interaction capabilities close human proficiency. This approach is based on human-derived neuronal data in combination shared ontology enable robots learn from experiences. To gain further insight into the relation between activity patterns and ontological classes, we introduced General Linear Model (GLM) analyses fMRI participants who were presented complex...
With the advancements in robotic technology and progress human-robot interaction research, interest deploying mixed teams rescue missions is increasing. Due to their complementary capabilities terms of locomotion, visibility reachability areas, are considerably deployed real-world settings, albeit agents such scenarios normally fully teleoperated. A major barrier successful efficient mission execution those lack cognitive skills systems. In this paper, we present a cognition-enabled...
This paper develops an efficient approach to generate a collision-free and dynamically feasible trajectory that enables robotic vehicle inspect the entire workspace or subset consisting of one several regions. The makes it possible specify constraints on order in which regions should be inspected by using colors ensure with same color are as group. A key aspect is transformation multiregion inspection into clustered traveling salesman problem (CTSP). achieved generating points medial axis...
This paper introduces a method to efficiently compute global motion plans for robotic manipulators in dynamically changing environments. An offline computation step is used construct sparse roadmap approximate the configuration space of manipulator an empty environment. When robot running, representation environment keep track robot's free workspace maintained as sensor updates are received. The conjunction with data computed quickly good quality plans.
A fundamental issue concerning the treatment of meaning in context is how to deal with extremely flexible relationship that appears hold between descriptions, which are taken as exchangeable bearers meaning, and actual contexts those descriptions pick out. Such appear always only be suggested, or constrained, by so relating levels description, such linguistic utterances, use, a situated, fully embodied environment language users find themselves, remains an unsolved challenge. The present...
Effective teaching of surgical decision making requires providing students with a deep understanding the domain so that they have ability to make decisions in novel situations. This means them thorough causal relations between actions and their possible effects context various states patient as well previous actions. Intelligent tutoring systems teach thus require such knowledge, but there are currently no medical ontologies encompass it. While it is engineer needed by hand, this large...
We propose a solution for handling abort commands given to robots. The is exemplified with running scenario household kitchen robot uses planning find sequences of actions that must be performed in order gracefully cancel previously received command. Planning Domain Definition Language (PDDL) used write domain model activities and behaviours, this enriched knowledge from online ontologies graphs, like DBPedia. discuss the results obtained different scenarios.