Context in Intelligent Environments

According to current trends, the home of the future will be smart and sensor technology will be ubiquitous. The flood of incoming data is used to increase our quality of life, e.g. through smart assistants or home automation. Eventually, this technology will set the scene for socially competent assistive agents to support us in our everyday lives. Such ambient intelligent systems do not only require an extensive amount of data but also a consistent and comprehensive representation of contextual knowledge.

In our research we aim to define these requirements and explore different possibilities to infer and process knowledge in dynamic environments. One of the major principles is that context needs to be adapted to the present situation. We approach this by providing multiple representations of the environment as well as anticipating reasoning methods.

The 'Reflected Reality' system is our in-house prototype and the heart of our smart lab. It is capable of inferring contextual knowledge in a human-agent shared environment, and to provide it to virtual or physical agents when required. It incorporates a semantics-based reasoning engine as well as a state-of-the-art game engine which allow the generation and representation of context on multiple levels of abstraction. The focus is on creating a research environment for agent development and experiments in context-dependent situations.

Videos

Smart Substitutional Reality

Involved researchers

Prof. Dr. Birgit Lugrin

Elisabeth Ganal (M.Sc.)

Related publications

2022[ to top ]

Don’t Touch This! - Investigating the Potential of Visualizing Touched Surfaces on the Consideration of Behavior Change Ganal, E.; Heimbrock, M.; Schaper, P.; Lugrin, B. in Persuasive Technology 2022, N. Baghaei, J. Vassileva, R. Ali, K. Oyibo (eds.) (2022).
- [ BibTeX ]
- [ EndNote ]
@inproceedings{ganal2022touch, author = {Ganal, E. and Heimbrock, M. and Schaper, P. and Lugrin, B.}, booktitle = {Persuasive Technology 2022}, editor = {Baghaei, N. and Vassileva, J. and Ali, R. and Oyibo, K.}, keywords = {schaper}, publisher = {Springer International Publishing}, title = {Don’t Touch This! - Investigating the Potential of Visualizing Touched Surfaces on the Consideration of Behavior Change}, year = 2022 }

%0 Conference Paper %1 ganal2022touch %A Ganal, E. %A Heimbrock, M. %A Schaper, P. %A Lugrin, B. %B Persuasive Technology 2022 %D 2022 %E Baghaei, N. %E Vassileva, J. %E Ali, R. %E Oyibo, K. %I Springer International Publishing %T Don’t Touch This! - Investigating the Potential of Visualizing Touched Surfaces on the Consideration of Behavior Change

2020[ to top ]

(Expressive) Social Robot or Tablet? – On the Benefits of Embodiment and Non-verbal Expressivity of the Interface for a Smart Environment Deublein, Andrea; Lugrin, Birgit in International Conference on Persuasive Technology (PERSUASIVE 2020), Lecture Notes in Computer Science, G.-H. S., J. T., M. C. (eds.) (2020). (Vol. 12064)
- [ BibTeX ]
- [ EndNote ]
@inproceedings{deublein2021expressive, author = {Deublein, Andrea and Lugrin, Birgit}, booktitle = {International Conference on Persuasive Technology (PERSUASIVE 2020)}, editor = {S., Gram-Hansen and T., Jonasen and C., Midden}, keywords = {reflectedreality}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {(Expressive) Social Robot or Tablet? – On the Benefits of Embodiment and Non-verbal Expressivity of the Interface for a Smart Environment}, volume = 12064, year = 2020 }

%0 Conference Paper %1 deublein2021expressive %A Deublein, Andrea %A Lugrin, Birgit %B International Conference on Persuasive Technology (PERSUASIVE 2020) %D 2020 %E S., Gram-Hansen %E T., Jonasen %E C., Midden %I Springer %R 10.1007/978-3-030-45712-9_7 %T (Expressive) Social Robot or Tablet? – On the Benefits of Embodiment and Non-verbal Expressivity of the Interface for a Smart Environment %V 12064
Horror Laboratory and Forest Cabin - A Horror Game Series for Desktop Computer, Virtual Reality, and Smart Substitutional Reality Steinhaeusser, Sophia C.; Lugrin, Birgit in Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play (2020).
- [ BibTeX ]
- [ EndNote ]
@inproceedings{Steinhaeusser_2020, author = {Steinhaeusser, Sophia C. and Lugrin, Birgit}, booktitle = {Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play}, keywords = {steinhaeusser}, publisher = {ACM}, title = {Horror Laboratory and Forest Cabin - A Horror Game Series for Desktop Computer, Virtual Reality, and Smart Substitutional Reality}, year = 2020 }

%0 Conference Paper %1 Steinhaeusser_2020 %A Steinhaeusser, Sophia C. %A Lugrin, Birgit %B Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play %D 2020 %I ACM %R 10.1145/3383668.3419924 %T Horror Laboratory and Forest Cabin - A Horror Game Series for Desktop Computer, Virtual Reality, and Smart Substitutional Reality
What if it speaks like it was from the village? Effects of a Robot speaking in Regional Language Variations on Users’ Evaluations Lugrin, B.; Ströle, E.; Obremski, D.; Schwab, F.; Lange, B. in 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2020) (2020). 1315–1320.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The present contribution investigates the effects of spoken language varieties, in particular non-standard / regional language compared to standard language (in our study: High German), in social robotics. Based on (media) psychological and sociolinguistic research, we assumed that a robot speaking in regional language (i.e., dialect and regional accent) would be considered less competent compared to the same robot speaking in standard language (H1). Contrarily, we assumed that regional language might enhance perceived social skills and likability of a robot, at least so when taking into account whether and how much the human observers making the evaluations talk in regional language themselves. More precisely, it was assumed that the more the study participants spoke in regional language, the better their ratings of the dialect-speaking robot on social skills and likeability would be (H2). We also investigated whether the robot’s gender (male vs. female voice) would have an effect on the ratings (RQ). H1 received full, H2 limited empirical support by the data, while the robot’s gender (RQ) turned out to be a mostly negligible factor. Based on our results, practical implications for robots speaking in regional language varieties are suggested.

@inproceedings{9223432, abstract = {The present contribution investigates the effects of spoken language varieties, in particular non-standard / regional language compared to standard language (in our study: High German), in social robotics. Based on (media) psychological and sociolinguistic research, we assumed that a robot speaking in regional language (i.e., dialect and regional accent) would be considered less competent compared to the same robot speaking in standard language (H1). Contrarily, we assumed that regional language might enhance perceived social skills and likability of a robot, at least so when taking into account whether and how much the human observers making the evaluations talk in regional language themselves. More precisely, it was assumed that the more the study participants spoke in regional language, the better their ratings of the dialect-speaking robot on social skills and likeability would be (H2). We also investigated whether the robot’s gender (male vs. female voice) would have an effect on the ratings (RQ). H1 received full, H2 limited empirical support by the data, while the robot’s gender (RQ) turned out to be a mostly negligible factor. Based on our results, practical implications for robots speaking in regional language varieties are suggested.}, author = {Lugrin, B. and Ströle, E. and Obremski, D. and Schwab, F. and Lange, B.}, booktitle = {29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2020)}, keywords = {reflectedreality}, pages = {1315-1320}, title = {What if it speaks like it was from the village? Effects of a Robot speaking in Regional Language Variations on Users’ Evaluations}, year = 2020 }

%0 Conference Paper %1 9223432 %A Lugrin, B. %A Ströle, E. %A Obremski, D. %A Schwab, F. %A Lange, B. %B 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2020) %D 2020 %P 1315-1320 %R 10.1109/RO-MAN47096.2020.9223432 %T What if it speaks like it was from the village? Effects of a Robot speaking in Regional Language Variations on Users’ Evaluations %U https://ieeexplore.ieee.org/document/9223432/ %X The present contribution investigates the effects of spoken language varieties, in particular non-standard / regional language compared to standard language (in our study: High German), in social robotics. Based on (media) psychological and sociolinguistic research, we assumed that a robot speaking in regional language (i.e., dialect and regional accent) would be considered less competent compared to the same robot speaking in standard language (H1). Contrarily, we assumed that regional language might enhance perceived social skills and likability of a robot, at least so when taking into account whether and how much the human observers making the evaluations talk in regional language themselves. More precisely, it was assumed that the more the study participants spoke in regional language, the better their ratings of the dialect-speaking robot on social skills and likeability would be (H2). We also investigated whether the robot’s gender (male vs. female voice) would have an effect on the ratings (RQ). H1 received full, H2 limited empirical support by the data, while the robot’s gender (RQ) turned out to be a mostly negligible factor. Based on our results, practical implications for robots speaking in regional language varieties are suggested.
Context Matters! Identifying Social Context Factors and Assessing Their Relevance for a Socially Assistive Robot von der Pütten, Astrid Marieke Rosenthal; Lugrin, Birgit; Steinhaeusser, Sophia C.; Klass, Lina in Companion of the 2020 International Conference on Human-Robot Interaction (2020). 409–411.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{Rosenthal_von_der_P_tten_2020, author = {von der Pütten, Astrid Marieke Rosenthal and Lugrin, Birgit and Steinhaeusser, Sophia C. and Klass, Lina}, booktitle = {Companion of the 2020 International Conference on Human-Robot Interaction}, keywords = {steinhaeusser}, pages = {409-411}, publisher = {ACM}, title = {Context Matters! Identifying Social Context Factors and Assessing Their Relevance for a Socially Assistive Robot}, year = 2020 }

%0 Conference Paper %1 Rosenthal_von_der_P_tten_2020 %A von der Pütten, Astrid Marieke Rosenthal %A Lugrin, Birgit %A Steinhaeusser, Sophia C. %A Klass, Lina %B Companion of the 2020 International Conference on Human-Robot Interaction %D 2020 %I ACM %P 409-411 %R 10.1145/3371382.3378370 %T Context Matters! Identifying Social Context Factors and Assessing Their Relevance for a Socially Assistive Robot %U https://doi.org/10.1145%2F3371382.3378370

2019[ to top ]

Identifying Social Context Factors Relevant for a Robotic Elderly Assistant. Lugrin, Birgit; Rosenthal von der Pütten, Astrid M.; Hahn, Svenja in International Conference on Social Robotics (ICSR), Lecture Notes in Computer Science, M. A. Salichs, S. S. Ge, E. I. Barakova, J.-J. Cabibihan, A. R. Wagner, Álvaro C. González, H. He (eds.) (2019). (Vol. 11876) 558–567.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{conf/socrob/LugrinPH19, author = {Lugrin, Birgit and Rosenthal von der Pütten, Astrid M. and Hahn, Svenja}, booktitle = {International Conference on Social Robotics (ICSR)}, crossref = {conf/socrob/2019}, editor = {Salichs, Miguel A. and Ge, Shuzhi Sam and Barakova, Emilia Ivanova and Cabibihan, John-John and Wagner, Alan R. and González, Álvaro Castro and He, Hongsheng}, keywords = {reflectedreality}, pages = {558-567}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Identifying Social Context Factors Relevant for a Robotic Elderly Assistant.}, volume = 11876, year = 2019 }

%0 Conference Paper %1 conf/socrob/LugrinPH19 %A Lugrin, Birgit %A Rosenthal von der Pütten, Astrid M. %A Hahn, Svenja %B International Conference on Social Robotics (ICSR) %D 2019 %E Salichs, Miguel A. %E Ge, Shuzhi Sam %E Barakova, Emilia Ivanova %E Cabibihan, John-John %E Wagner, Alan R. %E González, Álvaro Castro %E He, Hongsheng %I Springer %P 558-567 %T Identifying Social Context Factors Relevant for a Robotic Elderly Assistant. %U http://dblp.uni-trier.de/db/conf/socrob/icsr2019.html#LugrinPH19 %V 11876
Reflected Reality: A Mixed Reality Knowledge Representation for Context-aware Systems. Eckstein, Benjamin; Niebling, Florian; Lugrin, Birgit in 11th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games) (2019). 1–4.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{conf/vsgames/EcksteinNL19, author = {Eckstein, Benjamin and Niebling, Florian and Lugrin, Birgit}, booktitle = {11th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games)}, crossref = {conf/vsgames/2019}, keywords = {reflectedreality}, pages = {1-4}, publisher = {IEEE}, title = {Reflected Reality: A Mixed Reality Knowledge Representation for Context-aware Systems.}, year = 2019 }

%0 Conference Paper %1 conf/vsgames/EcksteinNL19 %A Eckstein, Benjamin %A Niebling, Florian %A Lugrin, Birgit %B 11th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games) %D 2019 %I IEEE %P 1-4 %T Reflected Reality: A Mixed Reality Knowledge Representation for Context-aware Systems. %U http://dblp.uni-trier.de/db/conf/vsgames/vsgames2019.html#EcksteinNL19 %@ 978-1-7281-4540-2
Smart substitutional reality: Integrating the smart home into virtual reality Eckstein, Benjamin; Krapp, Eva; Elsässer, Anne; Lugrin, Birgit in Entertainment Computing (2019). 31 100306.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Recent advances in VR technology allow users to consume immersive content within their own living room. Substitutional Reality (SR) promises to enhance this experience by integrating the physical environment into the simulation. We propose a novel approach, called Smart Substitutional Reality (SSR), that extends the passive haptics of SR with the interactive functionality of a smart home environment. SSR is meant to serve as a foundation for serious games. In this paper, we describe the concept of SSR alongside the implementation of a prototype in our smart lab. We designed multiple virtual environments with a varying degree of mismatch compared to the real world, and added selected objects to induce additional haptic and thermal stimuli to increase immersion. In two user studies we investigate their impact on spatial presence and intrinsic motivation which are especially important for serious games. Results suggest that spatial presence is maintained with higher mismatch, and increased by inducing additional stimuli. Intrinsic motivation is increased in both cases.

@article{ECKSTEIN2019100306, abstract = {Recent advances in VR technology allow users to consume immersive content within their own living room. Substitutional Reality (SR) promises to enhance this experience by integrating the physical environment into the simulation. We propose a novel approach, called Smart Substitutional Reality (SSR), that extends the passive haptics of SR with the interactive functionality of a smart home environment. SSR is meant to serve as a foundation for serious games. In this paper, we describe the concept of SSR alongside the implementation of a prototype in our smart lab. We designed multiple virtual environments with a varying degree of mismatch compared to the real world, and added selected objects to induce additional haptic and thermal stimuli to increase immersion. In two user studies we investigate their impact on spatial presence and intrinsic motivation which are especially important for serious games. Results suggest that spatial presence is maintained with higher mismatch, and increased by inducing additional stimuli. Intrinsic motivation is increased in both cases.}, author = {Eckstein, Benjamin and Krapp, Eva and Elsässer, Anne and Lugrin, Birgit}, journal = {Entertainment Computing}, keywords = {reflectedreality}, pages = 100306, title = {Smart substitutional reality: Integrating the smart home into virtual reality}, volume = 31, year = 2019 }

%0 Journal Article %1 ECKSTEIN2019100306 %A Eckstein, Benjamin %A Krapp, Eva %A Elsässer, Anne %A Lugrin, Birgit %D 2019 %J Entertainment Computing %P 100306 %R https://doi.org/10.1016/j.entcom.2019.100306 %T Smart substitutional reality: Integrating the smart home into virtual reality %U http://www.sciencedirect.com/science/article/pii/S1875952119300151 %V 31 %X Recent advances in VR technology allow users to consume immersive content within their own living room. Substitutional Reality (SR) promises to enhance this experience by integrating the physical environment into the simulation. We propose a novel approach, called Smart Substitutional Reality (SSR), that extends the passive haptics of SR with the interactive functionality of a smart home environment. SSR is meant to serve as a foundation for serious games. In this paper, we describe the concept of SSR alongside the implementation of a prototype in our smart lab. We designed multiple virtual environments with a varying degree of mismatch compared to the real world, and added selected objects to induce additional haptic and thermal stimuli to increase immersion. In two user studies we investigate their impact on spatial presence and intrinsic motivation which are especially important for serious games. Results suggest that spatial presence is maintained with higher mismatch, and increased by inducing additional stimuli. Intrinsic motivation is increased in both cases.

2018[ to top ]

Towards Serious Games and Applications in Smart Substitutional Reality Eckstein, Benjamin; Krapp, Eva; Lugrin, Birgit in 10th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games 2018) (2018). 25–32.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Substitutional Reality (SR), the integration of the physical environment into Virtual Reality (VR), is a novel approach to facilitate and intensify the use of home-based VR systems. We propose to extend the passive haptics of SR with the interactive functionality of a smart home environment. This concept of smart SR is meant as a foundation for serious games and applications. In this paper, we describe the concept behind smart SR as well as the prototype in our lab environment. We created multiple virtual environments with a varying degree of mismatch regarding the real world. We present a user study where we examined the influence of these environments on the perceived sense of presence and motivation of users. Our findings showed that presence was high in all conditions while motivation increased with the level of mismatch. This provides us with a promising basis for further research.

@inproceedings{eckstein2018towards, abstract = {Substitutional Reality (SR), the integration of the physical environment into Virtual Reality (VR), is a novel approach to facilitate and intensify the use of home-based VR systems. We propose to extend the passive haptics of SR with the interactive functionality of a smart home environment. This concept of smart SR is meant as a foundation for serious games and applications. In this paper, we describe the concept behind smart SR as well as the prototype in our lab environment. We created multiple virtual environments with a varying degree of mismatch regarding the real world. We present a user study where we examined the influence of these environments on the perceived sense of presence and motivation of users. Our findings showed that presence was high in all conditions while motivation increased with the level of mismatch. This provides us with a promising basis for further research.}, author = {Eckstein, Benjamin and Krapp, Eva and Lugrin, Birgit}, booktitle = {10th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games 2018)}, keywords = {reflectedreality}, pages = {25-32}, publisher = {IEEE}, title = {Towards Serious Games and Applications in Smart Substitutional Reality}, year = 2018 }

%0 Conference Paper %1 eckstein2018towards %A Eckstein, Benjamin %A Krapp, Eva %A Lugrin, Birgit %B 10th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games 2018) %D 2018 %I IEEE %P 25-32 %T Towards Serious Games and Applications in Smart Substitutional Reality %U https://www.researchgate.net/publication/327720238_Towards_Serious_Games_and_Applications_in_Smart_Substitutional_Reality %X Substitutional Reality (SR), the integration of the physical environment into Virtual Reality (VR), is a novel approach to facilitate and intensify the use of home-based VR systems. We propose to extend the passive haptics of SR with the interactive functionality of a smart home environment. This concept of smart SR is meant as a foundation for serious games and applications. In this paper, we describe the concept behind smart SR as well as the prototype in our lab environment. We created multiple virtual environments with a varying degree of mismatch regarding the real world. We present a user study where we examined the influence of these environments on the perceived sense of presence and motivation of users. Our findings showed that presence was high in all conditions while motivation increased with the level of mismatch. This provides us with a promising basis for further research.

2016[ to top ]

Augmented Reasoning in the Mirror World Eckstein, Benjamin; Lugrin, Birgit in 22nd ACM Conference on Virtual Reality Software and Technology (VRST 2016) (2016). 313–314.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In order to enable a social agent to behave in a believable and realistic way, it needs a wide range of information in the form of both low-level value-based data as well as high-level semantic knowledge. In this work we propose a system that puts a virtual reality layer between the real world and an agent\u0027s knowledge representation. This mirror world allows the agent to use its abstract representation of the environment and inferred events as an additional source of knowledge when reasoning about the real world. Additionally, users and developers can use the mirror world, with its visualized data and highlighting of the agent\u0027s reasoning, for further understanding of the agent\u0027s behavior, debugging and testing, or the simulation of additional sensor input.

@inproceedings{Eckstein:2016:ARM:2993369.2996316, abstract = {In order to enable a social agent to behave in a believable and realistic way, it needs a wide range of information in the form of both low-level value-based data as well as high-level semantic knowledge. In this work we propose a system that puts a virtual reality layer between the real world and an agent\u0027s knowledge representation. This mirror world allows the agent to use its abstract representation of the environment and inferred events as an additional source of knowledge when reasoning about the real world. Additionally, users and developers can use the mirror world, with its visualized data and highlighting of the agent\u0027s reasoning, for further understanding of the agent\u0027s behavior, debugging and testing, or the simulation of additional sensor input.}, author = {Eckstein, Benjamin and Lugrin, Birgit}, booktitle = {22nd ACM Conference on Virtual Reality Software and Technology (VRST 2016)}, keywords = {reflectedreality}, pages = {313-314}, publisher = {ACM}, title = {Augmented Reasoning in the Mirror World}, year = 2016 }

%0 Conference Paper %1 Eckstein:2016:ARM:2993369.2996316 %A Eckstein, Benjamin %A Lugrin, Birgit %B 22nd ACM Conference on Virtual Reality Software and Technology (VRST 2016) %D 2016 %I ACM %P 313-314 %R 10.1145/2993369.2996316 %T Augmented Reasoning in the Mirror World %U http://doi.acm.org/10.1145/2993369.2996316 %X In order to enable a social agent to behave in a believable and realistic way, it needs a wide range of information in the form of both low-level value-based data as well as high-level semantic knowledge. In this work we propose a system that puts a virtual reality layer between the real world and an agent\u0027s knowledge representation. This mirror world allows the agent to use its abstract representation of the environment and inferred events as an additional source of knowledge when reasoning about the real world. Additionally, users and developers can use the mirror world, with its visualized data and highlighting of the agent\u0027s reasoning, for further understanding of the agent\u0027s behavior, debugging and testing, or the simulation of additional sensor input. %@ 978-1-4503-4491-3
Dynamic Context Integration through Modularized Ontologies and Semantic Blueprints Eckstein, Benjamin; Lugrin, Birgit in 5th International Workshop on Human-Agent Interaction Design and Models (HAIDM 2016), in conjunction with IJCAI 2016 (2016).
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Some recent approaches in context-aware systems deploy on-tologies to benefit from their expressive power and extensive availability within the World Wide Web. However, wide-ranging ontologies tend to grow into large and complicated constructs, thereby making them difficult to maintain or reason on. In this work, we present a lightweight system design that combines the advantages of minimal, distributed or modularized ontologies with the computational power of a state-of-the-art real-time interactive system. Therefore, we introduce a simple data-structure called blueprints, that describes various reasoning operations to allow the dynamic integration of domain-specific knowledge for time-critical tasks, e.g. in multi-agent systems. Following this concept, we formulate four major use cases which are described through exemplary problems and proposed solutions. The presented design aims at porta-bility and adaptability, while maintaining real-time capability.

@inproceedings{eckstein2016dynamic, abstract = {Some recent approaches in context-aware systems deploy on-tologies to benefit from their expressive power and extensive availability within the World Wide Web. However, wide-ranging ontologies tend to grow into large and complicated constructs, thereby making them difficult to maintain or reason on. In this work, we present a lightweight system design that combines the advantages of minimal, distributed or modularized ontologies with the computational power of a state-of-the-art real-time interactive system. Therefore, we introduce a simple data-structure called blueprints, that describes various reasoning operations to allow the dynamic integration of domain-specific knowledge for time-critical tasks, e.g. in multi-agent systems. Following this concept, we formulate four major use cases which are described through exemplary problems and proposed solutions. The presented design aims at porta-bility and adaptability, while maintaining real-time capability.}, author = {Eckstein, Benjamin and Lugrin, Birgit}, booktitle = {5th International Workshop on Human-Agent Interaction Design and Models (HAIDM 2016), in conjunction with IJCAI 2016}, keywords = {reflectedreality}, title = {Dynamic Context Integration through Modularized Ontologies and Semantic Blueprints}, year = 2016 }

%0 Conference Paper %1 eckstein2016dynamic %A Eckstein, Benjamin %A Lugrin, Birgit %B 5th International Workshop on Human-Agent Interaction Design and Models (HAIDM 2016), in conjunction with IJCAI 2016 %D 2016 %T Dynamic Context Integration through Modularized Ontologies and Semantic Blueprints %X Some recent approaches in context-aware systems deploy on-tologies to benefit from their expressive power and extensive availability within the World Wide Web. However, wide-ranging ontologies tend to grow into large and complicated constructs, thereby making them difficult to maintain or reason on. In this work, we present a lightweight system design that combines the advantages of minimal, distributed or modularized ontologies with the computational power of a state-of-the-art real-time interactive system. Therefore, we introduce a simple data-structure called blueprints, that describes various reasoning operations to allow the dynamic integration of domain-specific knowledge for time-critical tasks, e.g. in multi-agent systems. Following this concept, we formulate four major use cases which are described through exemplary problems and proposed solutions. The presented design aims at porta-bility and adaptability, while maintaining real-time capability.
PEARS - Physics Extension And Representation through Semantics Eckstein, B.; Lugrin, Jean-Luc; Wiebusch, D.; Latoschik, M.E. in IEEE Transactions on Computational Intelligence and AI in Games (2016). 8(2) 178–189.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Today\u0027s physics engines mainly simulate classical mechanics and rigid body dynamics, with some late advances also capable of simulating massive particle systems and some approximations of fluid dynamics. An accurate numerical simulation of complex non-mechanical processes in real-time is beyond the state-of-the-art in the respective fields. This article illustrates an alternative approach to a purely numerical solution. It uses a semantic representation of physical properties and processes as well as a reasoning engine to model cause and effect between objects, based on their material properties. Classical collision detection is combined with semantic rules to model various physical processes, e.g., in the areas of thermodynamics, electrodynamics, and fluid dynamics as well as chemical processes. Each process is broken down into fine-grained sub-processes capable of approximating continuous transitions with discretized state changes. Our system applies these high-level state descriptions to low-level value changes, which are directly mapped to a graphical representation of the scene. We demonstrate our framework\u0027s ability to support multiple complex, causally connected physical and chemical processes by simulating a Goldberg machine. Our performance benchmarks validate its scalability and potential application for entertainment or edutainment purposes.

@article{7347376, abstract = {Today\u0027s physics engines mainly simulate classical mechanics and rigid body dynamics, with some late advances also capable of simulating massive particle systems and some approximations of fluid dynamics. An accurate numerical simulation of complex non-mechanical processes in real-time is beyond the state-of-the-art in the respective fields. This article illustrates an alternative approach to a purely numerical solution. It uses a semantic representation of physical properties and processes as well as a reasoning engine to model cause and effect between objects, based on their material properties. Classical collision detection is combined with semantic rules to model various physical processes, e.g., in the areas of thermodynamics, electrodynamics, and fluid dynamics as well as chemical processes. Each process is broken down into fine-grained sub-processes capable of approximating continuous transitions with discretized state changes. Our system applies these high-level state descriptions to low-level value changes, which are directly mapped to a graphical representation of the scene. We demonstrate our framework\u0027s ability to support multiple complex, causally connected physical and chemical processes by simulating a Goldberg machine. Our performance benchmarks validate its scalability and potential application for entertainment or edutainment purposes.}, author = {Eckstein, B. and Lugrin, Jean-Luc and Wiebusch, D. and Latoschik, M.E.}, journal = {IEEE Transactions on Computational Intelligence and AI in Games}, keywords = {reflectedreality}, month = {June}, number = 2, pages = {178-189}, title = {PEARS - Physics Extension And Representation through Semantics}, volume = 8, year = 2016 }

%0 Journal Article %1 7347376 %A Eckstein, B. %A Lugrin, Jean-Luc %A Wiebusch, D. %A Latoschik, M.E. %D 2016 %J IEEE Transactions on Computational Intelligence and AI in Games %N 2 %P 178-189 %R 10.1109/TCIAIG.2015.2505404 %T PEARS - Physics Extension And Representation through Semantics %U http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7347376 %V 8 %X Today\u0027s physics engines mainly simulate classical mechanics and rigid body dynamics, with some late advances also capable of simulating massive particle systems and some approximations of fluid dynamics. An accurate numerical simulation of complex non-mechanical processes in real-time is beyond the state-of-the-art in the respective fields. This article illustrates an alternative approach to a purely numerical solution. It uses a semantic representation of physical properties and processes as well as a reasoning engine to model cause and effect between objects, based on their material properties. Classical collision detection is combined with semantic rules to model various physical processes, e.g., in the areas of thermodynamics, electrodynamics, and fluid dynamics as well as chemical processes. Each process is broken down into fine-grained sub-processes capable of approximating continuous transitions with discretized state changes. Our system applies these high-level state descriptions to low-level value changes, which are directly mapped to a graphical representation of the scene. We demonstrate our framework\u0027s ability to support multiple complex, causally connected physical and chemical processes by simulating a Goldberg machine. Our performance benchmarks validate its scalability and potential application for entertainment or edutainment purposes.