黑料福利网

Topic 

Simulated Users as Interactive Crash Test Dummies: How Computationally Rational Models can Improve User Interface Design

Abstract

Smartphones, tablets, and in-vehicle interfaces are incredibly complex, and users interact with them in a variety of situations and dynamic environments. Our goal is to improve interaction with these devices - to help users find the information they need and complete tasks as efficiently as possible. Understanding how users visually scan and physically interact with an interface is key to achieving this goal. Unfortunately, traditional user studies can be resource-intensive and time-consuming, making them impractical for evaluating the wide range of features and contexts found in modern devices.

In this talk, Patrick Ebel discusses how computational models that simulate human behavior can provide a compelling alternative. He'll explore how reinforcement learning, computational rationality, and biomechanical simulation offer a new way to simulate human behavior without the need to collect vast amounts of data.

About the speaker

Patrick Ebel leads the Junior Research Group CIAO () at ScaDS.AI, Leipzig University. Before joining ScaDS.AI, he received his Ph.D. in Computer Science from the University of Cologne in 2023, where he defended his dissertation Data-Driven Evaluation of In-Vehicle Information Systems with summa cum laude. His research is positioned at the intersection of machine learning, human-computer interaction, and mobility, and focuses on the development of computational cognitive models that simulate human-like interaction behavior. 

 

Your host

Pavlo Bazilinskyy Assistant Professor Industrial Design, will host Patrick Ebel.

Registration is required but free of charge.