Explainable AI Improves Human Decision Making – A Mushroom Picking Experiment at an Art Festival
The "AI Forest" is an artificial indoor forest and interactive game environment that was first presented at the Ars Electronica Festival 2021 in Linz, Austria. The task of visitors was to find ten haptic mushroom models in the bushes and scan them using a tablet. The virtual basket had to be filled with as many different edible species as possible. An artificially intelligent mushroom identification app, which had been trained with a large number of photos of forest mushrooms, assisted the players with advice. The purpose of the app was to identify mushroom species and classify them as edible or poisonous.
In addition to its playful character, the AI Forest represented an innovative research environment in which questions about decision-making in teamwork with AI and about explainable artificial intelligence methods were investigated.
This video gives an overview of the installation, our scientific user study on human decision-making with AI assistance, and it gives impressions of the festival.
The idea for the AI Forest originated in the research project "HOXAI - Hands-on Explainable AI", a collaboration between the LIT Robopsychology Lab and the Visual Data Science Lab at JKU Linz.
For more details on our study, read our preprint: https://osf.io/68emr
Citation: Leichtmann, B., Hinterreiter, A., Humer, C., Streit, M., & Mara, M. (2022, September 21). Explainable Artificial Intelligence improves human decision-making: Results from a mushroom picking experiment at a public art festival. Retrieved from osf.io/68emr
If you talk about our research in your work, please make sure to give appropriate credit and cite our related research paper. Thank you very much!
Social media:
Follow us on Twitter: https://twitter.com/RobopsychLinz
Use #AIForest to talk about our installation.
For more information on our research on explainable AI, visit our HOXAI project website:
https://www.jku.at/en/lit-robopsychology-lab/research/projects/hoxai/
For more information about the Ars Electronica Festival 2021, visit the festival page:
https://ars.electronica.art/newdigitaldeal/en/ai-forest/
© LIT Robopsychology Lab, Johannes Kepler University Linz, Linz, Austria.
Responsible Research Team: Benedikt Leichtmann (1), Andreas Hinterreiter (2), Christina Humer (2), Marc Streit (2), & Martina Mara (1)
Affiliations: (1) LIT Robopsychology Lab, Johannes Kepler University Linz, Linz Austria; (2) Visual Data Science Lab, Institute of Computer Graphics, Johannes Kepler University Linz, Linz Austria.
Date of study: September 2021
Funding information:
This work was funded by Johannes Kepler University Linz, Linz Institute of Technology (LIT), the State of Upper Austria, and the Federal Ministry of Education, Science and Research under grant number LIT-2019-7-SEE-117, awarded to Martina Mara and Marc Streit, the Austrian Science Fund under grant number FWF DFH 23--N, the Human-Interpretable Machine Learning project (funded by the State of Upper Austria). The AI Forest installation and tablet game could be realized by funding through the LIT Special Call for the Ars Electronica Festival 2021 awarded to Martina Mara. The publication is also supported by the Johannes Kepler Open Access Publishing Fund.
Acknowledgments:
We thank Birke van Maartens for the artistic concept of the artificial forest and the scenery design, Nives Meloni for coordinating the exhibition area, Leonie Haasler and Gabriel Vitel for the construction of the artificial forest (stage building), Moritz Heckmann for helping to implement the game, Kenji Tanaka for the sound design, and Stefan Eibelwimmer for the graphic design of the tablet game and Christopher Lindinger who helped in the conceptualization of the game. Additionally, we thank the Johannes Kepler University press team and Roman Peherstorfer and his team for the video documentation of the installation. Furthermore, we also thank all the student assistants and colleagues from the Robopsychology Lab at Johannes Kepler University Linz who actively supported the installation and data collection and who also spontaneously stepped in to help when the number of visitors was high.
Finally, we thank Dr. Otto Stoik and the members of the Mycological Working Group (MYAG) at the Biology Center Linz, Austria, who supported us in the development of items for the mushroom knowledge test and provided mushroom images for this study. We also thank the members of the German Mycological Society (DGfM) for providing additional images.
Mushroom Images taken from the Danish Mushroom Database (Danish Mycological Society. (2022). Danish fungal records database [Accessed March 29, 2022]. www.svampeatlas.dk). Copyright of images shown between 1:23 and 1:43 by (top to bottom):
- © Jørgen Christiansen
- © Michael Sonniks
- © Kasper Malmberg
- © Flemming Ryden
The “AI Forest” is an artificial indoor forest and interactive game environment that was first presented at the Ars Electronica Festival 2021 in Linz, Austria. The task of visitors was to find ten haptic mushroom models in the bushes and scan them using a tablet. The virtual basket had to be filled with as many different edible species as possible. An artificially intelligent mushroom identification app, which had been trained with a large number of photos of forest mushrooms, assisted the players with advice. The purpose of the app was to identify mushroom species and classify them as edible or poisonous.
In addition to its playful character, the AI Forest represented an innovative research environment in which questions about decision-making in teamwork with AI and about explainable artificial intelligence methods were investigated.
This video gives an overview of the installation, our scientific user study on human decision-making with AI assistance, and it gives impressions of the festival.
The idea for the AI Forest originated in the research project “HOXAI – Hands-on Explainable AI”, a collaboration between the LIT Robopsychology Lab and the Visual Data Science Lab at JKU Linz.
For more details on our study, read our preprint: https://osf.io/68emr
Citation: Leichtmann, B., Hinterreiter, A., Humer, C., Streit, M., & Mara, M. (2022, September 21). Explainable Artificial Intelligence improves human decision-making: Results from a mushroom picking experiment at a public art festival. Retrieved from osf.io/68emr
If you talk about our research in your work, please make sure to give appropriate credit and cite our related research paper. Thank you very much!
Social media:
Follow us on Twitter: https://twitter.com/RobopsychLinz
Use #AIForest to talk about our installation.
For more information on our research on explainable AI, visit our HOXAI project website:
https://www.jku.at/en/lit-robopsychology-lab/research/projects/hoxai/
For more information about the Ars Electronica Festival 2021, visit the festival page:
https://ars.electronica.art/newdigitaldeal/en/ai-forest/
© LIT Robopsychology Lab, Johannes Kepler University Linz, Linz, Austria.
Responsible Research Team: Benedikt Leichtmann (1), Andreas Hinterreiter (2), Christina Humer (2), Marc Streit (2), & Martina Mara (1)
Affiliations: (1) LIT Robopsychology Lab, Johannes Kepler University Linz, Linz Austria; (2) Visual Data Science Lab, Institute of Computer Graphics, Johannes Kepler University Linz, Linz Austria.
Date of study: September 2021
Funding information:
This work was funded by Johannes Kepler University Linz, Linz Institute of Technology (LIT), the State of Upper Austria, and the Federal Ministry of Education, Science and Research under grant number LIT-2019-7-SEE-117, awarded to Martina Mara and Marc Streit, the Austrian Science Fund under grant number FWF DFH 23–N, the Human-Interpretable Machine Learning project (funded by the State of Upper Austria). The AI Forest installation and tablet game could be realized by funding through the LIT Special Call for the Ars Electronica Festival 2021 awarded to Martina Mara. The publication is also supported by the Johannes Kepler Open Access Publishing Fund.
Acknowledgments:
We thank Birke van Maartens for the artistic concept of the artificial forest and the scenery design, Nives Meloni for coordinating the exhibition area, Leonie Haasler and Gabriel Vitel for the construction of the artificial forest (stage building), Moritz Heckmann for helping to implement the game, Kenji Tanaka for the sound design, and Stefan Eibelwimmer for the graphic design of the tablet game and Christopher Lindinger who helped in the conceptualization of the game. Additionally, we thank the Johannes Kepler University press team and Roman Peherstorfer and his team for the video documentation of the installation. Furthermore, we also thank all the student assistants and colleagues from the Robopsychology Lab at Johannes Kepler University Linz who actively supported the installation and data collection and who also spontaneously stepped in to help when the number of visitors was high.
Finally, we thank Dr. Otto Stoik and the members of the Mycological Working Group (MYAG) at the Biology Center Linz, Austria, who supported us in the development of items for the mushroom knowledge test and provided mushroom images for this study. We also thank the members of the German Mycological Society (DGfM) for providing additional images.
Mushroom Images taken from the Danish Mushroom Database (Danish Mycological Society. (2022). Danish fungal records database [Accessed March 29, 2022]. www.svampeatlas.dk). Copyright of images shown between 1:23 and 1:43 by (top to bottom):
– © Jørgen Christiansen
– © Michael Sonniks
– © Kasper Malmberg
– © Flemming Ryden
