Bernhard Sendhoff and Martin Kreutz , "Variable encoding of modular neural networks for time series prediction", Congress on Evolutionary Computation CEC, pp. 259-266, 1999.
Yaochu Jin, Werner von Seelen, Bernhard Sendhoff , "On Generating FC^3 Fuzzy Rule Systems From Data Using Evolution Strategies", IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 29, no. 4, pp. 829-845, 1999.
AbstractSophisticated fuzzy rule systems are supposed to be flexible, complete, consistent and compact (FC^3). Flexibility, completeness and consistency are essential for fuzzy systems to exhibit an excellent performance and to have a clear physical meaning, while compactness is crucial when the number of the input variables increases. However, the completeness and consistency conditions are often violated if a fuzzy system is generated from data collect...
Edgar Körner and Gen Matsumoto , "Cortical architecture and self-referential control for brain-like processing in artificial neural systems", Artificial life and robotics, vol. 2, no. 3, pp. 170–178, 1998.
Edgar Körner , "Synchronization of Decision Processes - But Not of Spikes: Gamma Paced Temporal Encoding in Model Cortical Columns", Bochum-Tamagawa Brain Forum, 1997.
Edgar Körner and Ursula Körner , "Concurrent Parallel-Sequential Processing in Gamma Controlled Cortical-Type Networks of Spiking Neurones", Proc. International Conference on Artificial Neural Networks, pp. 91–96, 1997.
Edgar Körner, Hiroshi Tsujino, Tomohiko Masutani , "A Cortical-type Modular Neural Network for Hypothetical Reasoning", Neural Networks, vol. 10, no. 5, pp. 791–814, 1997.
Mariam Arustashvili , "Knowledge Graph Completion on a Situational Knowledge Graph Describing Household Actions", Mannheim Univeristy, 1970.
AbstractThe primary objective of this thesis is to explore the potential of various KGC methods to improve the accuracy and adaptability of situational knowledge graphs in a robotics context. Specifically, my goal is to assess how well traditional graph-based machine learning and language models can predict parent actions — high-level tasks — and anticipate next sub-actions — granular steps — based on knowledge of the environment and user behavior. This ...
Jörg Deigmöller, Pavel Smirnov, Julian Eggert, Chao Wang, Johane Takeuchi , "Situational Question Answering over Commonsense Knowledge using Memory Nets", Communications in Computer and Information Science, 1970.
AbstractEmbodied Question Answering (EQA) is a rather novel research direction, which bridges the gap between environmental reasoning and actionable capabilities of mobile robotic platforms. Such mobile robotic platforms are usually located in random simulated environments. The task is to answer user requests about the environment by dynamic exploration. User requests are mostly related to object properties or positional relations to other objects in a s...
Jörg Deigmöller, Stephan Hasler, Nakul Agarwal, Chao Wang, Daniel Tanneberg, Reza Ghoddoosian, Fan Zhang, Felix Ocker, Anna Belardinelli, Behzad Dariush, Michael Gienger , "Context-Aware Human-Robot Collaboration Through Integrated Vision-Language Models and Action Understanding", arXiv, 1970.
AbstractThis work presents a human-robot interaction framework that enables robots to naturally and adaptively support people in collaborative tasks by deeply understanding situational context. The system integrates Vision-Language Models (VLMs) with object and action detection to extract detailed information about who is involved (person), what they are doing (action), and what they are interacting with (object), besides the general environment context...
Anna Belardinelli, Chao Wang, Daniel Tanneberg, Matti Krüger, Stephan Hasler, Michael Gienger , "Explaining to and being explained by a service robot: Four HRI studies revisited under a framework for explainability", 3rd TRR 318 Conference, 1970.
AbstractRobotic butlers relieving users from domestic chores are currently dominating the media narration on AI and letting the public phantasize of a near future where these systems will smoothly navigate our private spaces and interact with us in a natural and transparent way. This vision will hardly be realized as long as potential users are not able to interpret and trust such autonomous systems. This can only happen by negotiating with them a c...