Adapt2Learn: A Toolkit for Configuring the Learning Algorithm for Adaptive Physical Tools for Motor-Skill Learning
Year: 2021
Type: conference-paper
Abstract: A recent study on motor-skill training showed that adaptive training tools that use shape-change to adapt the training difficulty based on learners’ performance can lead to higher learning gains. However, to date, no support tools exist to help designers create adaptive learning tools. Our formative study shows that developing the adaptive learning algorithm poses a particular challenge. To address this, we built 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. Once uploaded, 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 then lets designers visualize their tool’s adaptation and evaluate the learning algorithm. To validate that Adapt2Learn can generate adaptation algorithms for different tools, we built several application examples that demonstrate successful deployment.
Authors: Dishita G Turakhia, Andrew Wong, Yini Qi, Lotta-Gili Blumberg, Yoonji Kim, Stefanie Mueller
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
Funder: National Science Foundation
OpenAlex ID: W3175361714
