More Like this

1. Design Conjectures for Place-Based Science Learning About Water: Implementing Mobile Augmented Reality with Families

   Zimmerman, H. T. ; Land, S. M. ; Grills, K. E. ; Chiu, Y.-C. ; Jung, Y. J. ; Williams, J. ( January 2020 , Proceedings of the 14th International Conference for the Learning Sciences)

   From a design-based research study with 31 families, we share the design conjectures that guided the first two iterations of research. The team developed a mobile augmented reality app focused on water-rock interactions to make earth sciences appealing to rural families. We iterated on one design element, the augmented reality visualizations, to understand how these AR elements influence families’ learning behavior in a children’s garden cave as well as their resulting geosciences knowledge. This analysis is an example of how design conjecture maps can be used to support research and development of mobile computer-supported collaborative learning opportunities for families inmore »outdoor, informal learning settings.« less
2. Online Continual Learning for Embedded Devices

   Hayes, T ; Kanan, C. ( August 2022 , Conference on Lifelong Learning Agents)

   Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets. However, this setting poses unique challenges: embedded devices have limited memory and compute capacity and conventional machine learning models suffer from catastrophic forgetting when updated on non-stationary data streams. While several online continual learning models have been developed, their effectiveness for embedded applications has not been rigorously studied. In this paper, we first identify criteria that online continual learners must meet to effectively perform real-time, on-device learning. We then study the efficacy of several online continual learning methods whenmore »used with mobile neural networks. We measure their performance, memory usage, compute requirements, and ability to generalize to out-of-domain inputs.« less
3. Using Digital Sketching and Augmented Reality Mobile Apps to Improve Spatial Visualization in a Freshmen Engineering Course

   https://doi.org/10.18260/1-2--33501  

   Bairaktarova, Diana ; Van Den Einde, Lelli ; Bell, John ( June 2019 , 2019 ASEE Annual Conference & Exposition)

   Spatial reasoning skills contribute to performance in many STEM fields. For example, drawing sectional views of three-dimensional objects is an essential skill for engineering students. There is considerable variation in the spatial reasoning skills of prospective engineering students, putting some at risk for compromised performance in their classes. This study takes place in a first-year engineering Spatial Visualization course to integrate recent practices in engineering design education with cognitive psychology research on the nature of spatial learning. We employed three main pedagogical strategies in the course - 1) in class instruction on sketching; 2) spatial visualization training; and 3) manipulationmore »of physical objects (CAD/3D print creations). This course endeavors to use current technology, online accessibility, and implementation of the three pedagogical strategies to bring about student growth in spatial reasoning. This study is designed to determine the effect of adding two different spatial reasoning training apps to this environment. Over 230 students (three sections) participated in our study. In two of the three sections, students received interactive spatial visualization training using either a spatial visualization mobile touchscreen app in one section or an Augmented Reality (AR) app in the other section. Research suggests that there are benefits to using the Spatial Vis Classroom mobile app for college students.The app has been shown to increase student persistence resulting in large learning gains as measured by the Purdue assessment of spatial visualization (PSVT-R), especially for students starting with poor spatial visualization skills. The Spatial Vis Classroom app can be used in the classroom or assigned as homework. The AR app is designed to help users develop their mental rotation abilities. It is designed to support a holistic understanding of 3-dimensional objects, and research has shown that, in combination with a traditional curriculum, it increases students’ abilities also measured by the PSVT-R. Of particular interest, the data suggest that the app overcomes the advantage found by males over females in a traditional class alone focused on spatial reasoning. Both of the course sections were required to use the apps for approximately the same time in class and outside of class. Students in the control section were required to do hand sketching activities in class and outside of class, with roughly the same completion time as for the sections with the apps. Students grades were not affected by using the three different approaches as grading was based on completion only. Based on current literature, we hypothesize that overall benefits (PSVT-R gains) will be comparable across the 3 treatments but there will be different effects on attitude and engagement (confidence,enjoyment, and self-efficacy). Lastly, we hypothesize that the treatments will have different effects on male/female and ethnic categories of the study participants. The final paper will include an analysis of results and a report of the findings.« less
4. Edge-assisted Collaborative Image Recognition for Mobile Augmented Reality

   https://doi.org/10.1145/3469033  

   Lan, G ; Liu, Z ; Zhang, Y ; Scargill, T ; Stojkovic, J. ; Joe-Wong, C. ; Gorlatova, M. ( February 2022 , ACM transactions on sensor networks)

   Mobile Augmented Reality (AR), which overlays digital content on the real-world scenes surrounding a user, is bringing immersive interactive experiences where the real and virtual worlds are tightly coupled. To enable seamless and precise AR experiences, an image recognition system that can accurately recognize the object in the camera view with low system latency is required. However, due to the pervasiveness and severity of image distortions, an effective and robust image recognition solution for “in the wild” mobile AR is still elusive. In this article, we present CollabAR, an edge-assisted system that provides distortion-tolerant image recognition for mobile AR withmore »imperceptible system latency. CollabAR incorporates both distortion-tolerant and collaborative image recognition modules in its design. The former enables distortion-adaptive image recognition to improve the robustness against image distortions, while the latter exploits the spatial-temporal correlation among mobile AR users to improve recognition accuracy. Moreover, as it is difficult to collect a large-scale image distortion dataset, we propose a Cycle-Consistent Generative Adversarial Network-based data augmentation method to synthesize realistic image distortion. Our evaluation demonstrates that CollabAR achieves over 85% recognition accuracy for “in the wild” images with severe distortions, while reducing the end-to-end system latency to as low as 18.2 ms.« less
5. Tar AR: Bringing the past to life in place-based augmented reality science learning.

   Davis, M. ( April 2021 , MuseWeb 2021 Annual Meeting Professional Forum)

   Informal science learning spaces such as museums have been exploring the potential of Augmented Reality (AR) as a means to connect visitors to places, times, or types of content that are otherwise inaccessible. This proposal reports on a design-based research project conducted at La Brea Tar Pits, an active paleontological dig site located within a city park in the heart of Los Angeles. The Natural History Museums of Los Angeles County and the University of Southern California engaged in a research practice partnership to enhance place-based science learning through the design and iterative testing of potential AR exhibits. Results frommore »one implementation show that AR technology increased visitor interest in the park and positive emotions around science content. Significant learning gains and decreases in science misconceptions also occurred for participants. We also give guidance on developing scientifically accurate assets for AR experiences and leading users through a virtual narrative. This presentation offers insights into museum and university partnerships for promoting public understanding of science in informal spaces by leveraging place-based learning through technology-enhanced engagement. https://mw21.museweb.net/proposal/tar-ar-bringing-the-past-to-life-in-place-based-augmented-reality-science-learning/« less