Alle Publikationen
- <<
- <
- 1
2017
-
(2017): An Evolutionary Transfer Reinforcement Learning Framework for Multiagent Systems. In: IEEE Transactions on Evolutionary Computation 21 (4), S. 601-615. DOI: 10.1109/TEVC.2017.2664665
Abstract: In this paper, we present an evolutionary transfer reinforcement learning framework (eTL) for developing intelligent agents capable of adapting to the dynamic environment of multiagent systems (MASs). Specifically, we take inspiration from Darwin's theory of natural selection and Universal Darwinism as the principal driving forces that govern the evolutionary knowledge transfer process. The essential backbone of our proposed eTL comprises several meme-inspired evolutionary mechanisms, namely meme representation, meme expression, meme assimilation, meme internal evolution, and meme external evolution. Our proposed approach constructs social selection mechanisms that are modeled after the principles of human learning to identify appropriate interacting partners. eTL also models the intrinsic parallelism of natural evolution and errors that are introduced due to the physiological limits of the agents' ability to perceive differences, so as to generate "growth" and "variation" of knowledge that agents have of the world, thus exhibiting higher adaptivity capabilities on solving complex problems. To verify the efficacy of the proposed paradigm, comprehensive investigations of the proposed eTL against existing state-of-the-art TL methods in MAS, are conducted on the "minefield navigation tasks" platform and the "Unreal Tournament 2004" first person shooter computer game, in which homogeneous and heterogeneous learning machines are considered.
-
(2017): Culture-specific models of negotiation for virtual characters. Multi-attribute decision-making based on culture-specific values. In: AI & Society 32 (1), S. 51-63. DOI: 10.1007/s00146-014-0570-7
Abstract: We posit that observed differences in negotiation performance across cultures can be explained by participants trying to optimize across multiple values, where the relative importance of values differs across cultures. We look at two ways for specifying weights on values for different cultures: one in which the weights of the model are hand-crafted, based on intuition interpreting Hofstede dimensions for the cultures, and one in which the weights of the model are learned from data using inverse reinforcement learning (IRL). We apply this model to the Ultimatum Game and integrate it into a virtual human dialog system. We show that weights learned from IRL surpass both a weak baseline with random weights and a strong baseline considering only one factor for maximizing gain in own wealth in accounting for the behavior of human players from four different cultures. We also show that the weights learned with our model for one culture outperform weights learned for other cultures when playing against opponents of the first culture.
Keywords: Cultural decision-making, culture specific, Disziplin, entscheiden, Inverse reinforcement learning: Hofstede, Kulturtheorie, Mensch-Technik-Relationen (MTR), NEGOTIATION, Realtechnik, Science and Technology Studies (STS), social importance dynamics, Sozial Intelligente Agenten, Soziale Robotik, Spieltheorie, Technik, Ultimatum Game, virtual agents 2014
-
(2014): Generating Task-Oriented Interactions of Service Robots. In: IEEE Transactions on Systems, Man, and Cybernetics: Systems 44 (8), S. 981-994. DOI: 10.1109/TSMC.2014.2298214
Abstract: Human-robot interaction (HRI) may play a key role in enhancing a robot's capability in practical service tasks, allowing productive human-robot collaboration. To obtain appropriate human aid for conducting tasks, a robot should be capable of generating meaningful questions regarding the task procedures in real time and applying the results to modify its task plans or behaviors. However, few studies on integrating robot task management and HRI in such high-level task planning exist. In this paper, we propose a new scheme of script-based task planning and HRI that supports the planning and is generated by it. The planning operates on a set of plain and easily writable task procedures, or scripts. The approach produces robust, practical, and easy-to-manipulate robot behavior. Based on the scripts, the system identifies plan ambiguities that require interaction with humans, and resolves them using the human response. The interaction thus generated is highly relevant and task-oriented. The robot learns from the interaction history to improve its subsequent planning in general, or personalize it. Two simulation cases, of a home service and a museum-guide robot, are presented to show how the robots lead appropriate interaction and smoothly adjust their task plans to user commands or responses. Such close integration of HRI and robot task planning is expected to advance the practicality of service robots.
Keywords: ALIGNMENT, Communication, CONTROL ARCHITECTURE, Design, human-robot interaction, INTEGRATION, KNOWLEDGE, Mensch-Technik-Relationen (MTR), MIND, PROGRAMS, Realtechnik, Science and Technology Studies (STS), script, script-based task planning, service robot, Serviceroboter, Soziale Robotik, task-oriented interaction, Technik 2013
-
(2013): A cross-cultural, multimodal, affective corpus for gesture expressivity analysis. In: Journal on Multimodal User Interfaces 7 (1-2), S. 121-134. DOI: 10.1007/s12193-012-0112-x
Abstract: A multimodal, cross-cultural corpus of affective behavior is presented in this research work. The corpus construction process, including issues related to the design and implementation of an experiment, is discussed along with resulting acoustic prosody, facial expressions and gesture expressivity features. However, research work presented here focuses more on the cross-cultural aspect of gestural behavior defining a common corpus construction protocol aiming to identify cultural patterns within non-verbal behavior across cultures i.e. German, Greek and Italian. Culture specific findings regarding gesture expressivity are derived from the affective analysis performed. Additionally, the multimodal aspect, including prosody and facial expressions, is researched in terms of fusion techniques. Finally, a release plan of the corpus to the public domain is discussed aiming to establish the current corpus as a benchmark multimodal, cross-cultural standard and reference point.
2012
-
(2012): Mind Scripting. In: Science, Technology, & Human Values 37 (6), S. 684-707. DOI: 10.1177/0162243911401633
Abstract: The interventionist turn in science and technology studies (STS) increasingly involves researchers with practices of technology development and thus entails the need for appropriate methodologies. Based in software engineering, this article introduces the deconstructive technique of "mind scripting" as a method for analyzing processes of the co-materialization of gender and technology and as a tool to support cooperative, reflective work practices. Anchored in critical design approaches, "mind scripting" is a means for development teams to disclose discourses implicitly guiding work practices in order to make negotiable the underlying value systems. After discussing its foundation in deconstructivist feminist theory, the author illustrates how the method is applied by drawing on selected empirical results. Generating insights into the reproduction of hegemonic social discourses in development processes, "mind scripting" enables the rethinking of established ways of doing.
- <<
- <
- 1