Modelling prospective memory and resilient situated communications via Wizard of Oz
Yanzhe Li, Frank Broz, Mark Neerincx
TL;DR
Problem: designing robust, context-aware communication for SARs in elder care requires modeling prospective memory under speech and perception failures. Approach: a scenario-based, Wizard of Oz study to collect multimodal data in a home-like setting and to prototype a shared prospective memory between a user and a robot. Contributions: a data-collection methodology for naturalistic HRI conversations and a proposed framework for a shared PM that informs reminder timing and dialogue initiation. Significance: offers a pathway to more reliable, personalized assistance for older adults that could enhance independence and interaction quality in daily activities.
Abstract
This abstract presents a scenario for human-robot action in a home setting involving an older adult and a robot. The scenario is designed to explore the envisioned modelling of memory for communication with a socially assistive robots (SAR). The scenario will enable the gathering of data on failures of speech technology and human-robot communication involving shared memory that may occur during daily activities such as a music-listening activity.