Adapt2Learn: A Toolkit for Configuring the Learning Algorithm for Adaptive Physical Too... [Preview]
Dishita G Turakhia, Andrew Wong, Yini Qi, Lotta-Gili Blumberg, Yoonji Kim, Stefanie Mueller
DIS '21: ACM Designing Interactive Systems Conference
Session: The Physical World
Abstract
A recent study on motor-skill training suggests that adaptive training tools that use shape-change to adapt the training difficulty based on learners' performance can lead to higher learning gains. However, no support tools exist to help designers create adaptive learning tools. Our formative study shows that developing the adaptive learning algorithm is particularly challenging. We address this by building Adapt2Learn, a toolkit that auto-generates the learning algorithm for adaptive tools. Designers choose their tool's sensors and actuators, Adapt2Learn then configures the learning algorithm and generates a microcontroller script that designers can deploy on the tool. The script assesses the learner's performance via the sensors, computes the training difficulty, and actuates the tool to adapt the difficulty. Adapt2Learn's visualization tool lets designers visualize their tool's adaptation and evaluate the learning algorithm. To validate that Adapt2Learn can generate adaptation algorithms for different tools, we build several application examples that demonstrate successful deployment.
DOI:: [ Ссылка ]
WEB:: [ Ссылка ]
Video Previews for ACM DIS 2021 Papers & Pictorials
