@article{RienerSchlacklMalsametal.2021, author = {Riener, Andreas and Schlackl, Dominik and Malsam, Julia and Huber, Josef and Homm, Benjamin and Kaczmar, Marion and Kleitsch, Iris and Megos, Alina and Park, Eunji and Sanverdi, G{\"u}ls{\"u}m and Schmidt, Sabrina and Bracaci, Daniel and Anees, Esha}, title = {Improving the UX for Users of Automated Shuttle Buses in Public Transport: Investigating Aspects of Exterior Communication and Interior Design}, volume = {5}, pages = {61}, journal = {Multimodal Technologies and Interaction}, number = {10}, publisher = {MDPI}, address = {Basel}, issn = {2414-4088}, doi = {https://doi.org/10.3390/mti5100061}, year = {2021}, abstract = {As a precursor to future public transportation, automated shuttle buses can already be experienced in some test regions, but the general public still has reservations and may not yet be ready for this change. For example, the fact that such vehicles might operate independently (without a human driver) creates a barrier of uncertainty and mistrust among people. In this work, we aim to identify and classify the prevailing reservations and propose solutions. We followed the User Centered Design (UCD) process to design concepts that are specifically tailored to the needs of future public transport users. After related work analysis, on-site research, and pre-studies, two main studies were conducted specifically to address communication in the exterior (n = 24) and interior/service design (n = 21). For both studies, we applied a mixed-methods approach combining quantitative and qualitative measures. Our results indicate that, in general, existing ways of communication in the exterior are insufficient to meet future needs. The two visualization concepts for external communication developed in this work were rated (significantly) better in most dimensions of the User Experience Questionnaire (UEQ), when compared to the baseline condition with no additional visualization. Furthermore, preferences among the study participants towards simple, highly visible, and well-known lighting concepts could be observed. As for the interior, the results show that participants rated attractiveness highly for the two design concepts (closer, further in the future) as compared to current, state-of-the-art solutions (automated buses currently in operation). For the "near future" concept, the pragmatic quality dominated, while in the other (the "far future") concept the hedonic quality was in the foreground. From the results, design recommendations in different categories were derived, which reflect the general openness of the public towards new technologies and interior approaches, but also point out the importance for privacy and designated personal spaces inside an (automated) shuttle bus. Some of the results do not strictly apply to automated shuttle buses, and can serve as valuable suggestions for improving conventional shuttle buses.}, language = {en} } @inproceedings{SchlacklWeiglRiener2020, author = {Schlackl, Dominik and Weigl, Klemens and Riener, Andreas}, title = {eHMI visualization on the entire car body: results of a comparative evaluation of concepts for the communication between AVs and manual drivers}, booktitle = {Tagungsband: Mensch \& Computer 2020}, editor = {Alt, Florian and Schneegass, Stefan and Hornecker, Eva}, publisher = {ACM}, address = {New York}, isbn = {978-1-4503-7540-5}, doi = {https://doi.org/10.1145/3404983.3410011}, pages = {79 -- 83}, year = {2020}, language = {en} } @thesis{Schlackl2021, author = {Schlackl, Dominik}, title = {UX improvements in intelligent user interfaces through AI deployment}, subtitle = {design and evaluation of human-centered explainable AI concepts}, publisher = {Technische Hochschule Ingolstadt}, address = {Ingolstadt}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:573-33341}, pages = {65, XLIX}, school = {Technische Hochschule Ingolstadt}, year = {2021}, abstract = {Artificial intelligence (AI) is a highly relevant subfield of computer science and a basic prerequisite for the implementation of intelligent user interfaces. However, AI-supported systems often entail a lack of transparency (i.e., explainability and interpretability) for the inexperienced end user, resulting in poor user interaction and ultimately the loss of trust and acceptance. This has resulted in calls for human-centered explainable AI. In this work, we applied the user centered design process in order to design an explainable and understandable AI assistant in the business-to- business invoicing context. It supports users in filling out web forms by intelligently prefilling input fields, and thus increases performance and enhances user experience. We combined several quantitative and qualitative measures in a mixed methods approach. Based on a review of prior work as well as investigative preliminary interviews and a focus group discussion, an empirical main study (n = 30) was conducted. In it, five prototyped concepts varying in degrees of transparency (different visual and textual indicators) were evaluated and compared. Our findings indicate that an increase in the level of detail provided by the system results in decreasing efficiency, measured in longer task completion times. Displaying AI confidence level via percentage values and color codes tends to increase accuracy, measured in an 8 \% lower error rate and almost twice as many error-free tasks, compared to AI proposals without contextual information. We found interrelations between the respondents' age and achieved efficiency as well as accuracy across concepts. User satisfaction seems to increase with an increasing level of detail, whereas hedonic quality (be-goals) achieved high ratings, especially for the display of the confidence level, and for textual explanations of the AI proposals. Almost no differences were found for the pragmatic quality (do-goals). Trust was high for the baseline (no AI support) and when the AI proposals are supplemented by confidence levels. We found low trust for AI proposals without contextual information. In summary, we recommend a clear and quick-to-grasp indicator. Displays of the confidence level with percentage values and color codes were evaluated well in almost all dimensions and achieved the highest overall attractiveness.}, language = {en} }